H10.7 top features

Top feature 0 in H10.7: (feature 15488)

TOP ACTIVATIONS
MAX = 5.230

have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
charges
Token charges
Feature activation+0.000
against
Token against
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+5.230
Anderson
Token Anderson
Feature activation+0.000
dismissed
Token dismissed
Feature activation+0.000
,
Token,
Feature activation+0.000
acknowledging
Token acknowledging
Feature activation+0.000
that
Token that
Feature activation+0.000
A
TokenA
Feature activation+0.000
:
Token:
Feature activation+4.527
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+1.202
E
TokenE
Feature activation+0.000
:
Token:
Feature activation+5.219
P
TokenP
Feature activation+0.000
/
Token/
Feature activation+0.563
RL
TokenRL
Feature activation+0.000
:
Token:
Feature activation+0.282
O
TokenO
Feature activation+0.000
h
Token h
Feature activation+0.000
dc
Tokendc
Feature activation+0.000
in
Token in
Feature activation+0.000
same
Token same
Feature activation+0.000
st
Token st
Feature activation+0.000
,
Token,
Feature activation+4.985
h
Token h
Feature activation+0.000
dc
Tokendc
Feature activation+0.000
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Sl
Token Sl
Feature activation+0.000
that
Token that
Feature activation+0.718
P
Token P
Feature activation+0.000
(
Token(
Feature activation+2.669
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
|
Token|
Feature activation+4.948
H
TokenH
Feature activation+0.000
)
Token)
Feature activation+0.000
<
Token <
Feature activation+0.000
P
TokenP
Feature activation+0.000
(
Token(
Feature activation+0.000
I
TokenI
Feature activation+0.000
:
Token:
Feature activation+1.878
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+1.135
A
TokenA
Feature activation+0.000
:
Token:
Feature activation+4.527
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+1.202
E
TokenE
Feature activation+0.000
:
Token:
Feature activation+5.219
P
TokenP
Feature activation+0.000
know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.042
P
Token P
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
|
Token|
Feature activation+4.308
E
TokenE
Feature activation+0.000
)
Token)
Feature activation+0.000
>
Token >
Feature activation+0.000
P
Token P
Feature activation+0.000
(
Token(
Feature activation+0.827
poor
Token poor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+4.223
the
Token the
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
complaints
Token complaints
Feature activation+0.000
,
Token,
Feature activation+0.000
over
Token over
Feature activation+0.000
election
Token election
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
spokesperson
Token spokesperson
Feature activation+0.000
for
Token for
Feature activation+3.975
H
Token H
Feature activation+0.713
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
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
grateful
Token grateful
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Grad
Token Grad
Feature activation+3.924
H
TokenH
Feature activation+0.000
acker
Tokenacker
Feature activation+0.000
village
Token village
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
a
Token a
Feature activation+0.000
ball
Token ball
Feature activation+0.000
tap
Token tap
Feature activation+0.000
,"
Token,"
Feature activation+3.825
Hear
Token Hear
Feature activation+0.000
n
Tokenn
Feature activation+0.000
testified
Token testified
Feature activation+0.000
.
Token.
Feature activation+0.392
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
of
Token of
Feature activation+0.000
snow
Token snow
Feature activation+0.606
sh
Tokensh
Feature activation+0.000
oe
Tokenoe
Feature activation+3.802
ha
Token ha
Feature activation+0.167
res
Tokenres
Feature activation+0.000
across
Token across
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Pennsylvania
Token Pennsylvania
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
part
Token part
Feature activation+0.000
in
Token in
Feature activation+0.000
restraining
Token restraining
Feature activation+0.000
the
Token the
Feature activation+3.747
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
j
Tokenj
Feature activation+0.000
acker
Tokenacker
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Under
TokenUnder
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.678
H
TokenH
Feature activation+1.278
ann
Tokenann
Feature activation+0.000
ibal
Tokenibal
Feature activation+0.000
Directive
Token Directive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.176
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Davis
TokenDavis
Feature activation+0.000
and
Token and
Feature activation+3.658
Holl
Token Holl
Feature activation+0.000
iday
Tokeniday
Feature activation+0.000
then
Token then
Feature activation+0.000
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
Sch
TokenSch
Feature activation+0.000
ultz
Tokenultz
Feature activation+0.000
also
Token also
Feature activation+0.000
ordered
Token ordered
Feature activation+0.072
Davis
Token Davis
Feature activation+0.000
and
Token and
Feature activation+3.494
Holl
Token Holl
Feature activation+0.000
iday
Tokeniday
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
in
Token in
Feature activation+0.000
't
Token't
Feature activation+0.000
your
Token your
Feature activation+0.000
favourites
Token favourites
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.464
BS
TokenBS
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
many
Token many
Feature activation+0.000
people
Token people
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+0.000
Matt
TokenMatt
Feature activation+3.397
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
and
Token and
Feature activation+0.000
murdered
Token murdered
Feature activation+0.000
him
Token him
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+3.362
Den
Token Den
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
's
Token's
Feature activation+0.000
silly
Token silly
Feature activation+0.000
?"
Token?"
Feature activation+1.762
an
Token an
Feature activation+0.000
incred
Token incred
Feature activation+0.000
ulous
Tokenulous
Feature activation+3.317
Walsh
Token Walsh
Feature activation+0.000
reacted
Token reacted
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
><
Token><
Feature activation+0.256
!--
Token!--
Feature activation+0.000
Product
Token Product
Feature activation+0.000
name
Token name
Feature activation+0.000
--
Token --
Feature activation+0.000
>
Token>
Feature activation+3.254
h
Tokenh
Feature activation+0.000
1
Token1
Feature activation+0.322
>
Token>
Feature activation+0.000
<
Token <
Feature activation+2.279
p
Tokenp
Feature activation+0.000

Top DFA by src position
MAX = 6.043

motion
Token motion
Feature activation+0.001
Top resid features:
demanding
Token demanding
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
Mr
Token Mr
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
H
Token H
Feature activation+6.043
Top resid features:
ynes
Tokenynes
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation-0.009
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
office
Token office
Feature activation-0.006
Top resid features:
:
Token:
Feature activation-0.007
Top resid features:
H
TokenH
Feature activation+1.747
Top resid features:
/
Token/
Feature activation+0.019
Top resid features:
I
TokenI
Feature activation+0.034
Top resid features:
:
Token:
Feature activation+0.019
Top resid features:
H
TokenH
Feature activation+2.164
Top resid features:
/
Token/
Feature activation+0.016
Top resid features:
A
TokenA
Feature activation+0.001
Top resid features:
:
Token:
Feature activation+0.005
Top resid features:
H
TokenH
Feature activation+1.567
Top resid features:
/
Token/
Feature activation-0.001
Top resid features:
1
Token 1
Feature activation+0.002
Top resid features:
:
Token:
Feature activation-0.006
Top resid features:
ch
Token ch
Feature activation-0.019
Top resid features:
1
Token 1
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
h
Token h
Feature activation+3.592
Top resid features:
dc
Tokendc
Feature activation-0.006
Top resid features:
in
Token in
Feature activation-0.043
Top resid features:
same
Token same
Feature activation-0.038
Top resid features:
st
Token st
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
E
TokenE
Feature activation-0.058
Top resid features:
)
Token)
Feature activation-0.002
Top resid features:
>
Token >
Feature activation-0.003
Top resid features:
P
Token P
Feature activation+0.004
Top resid features:
(
Token(
Feature activation-0.005
Top resid features:
H
TokenH
Feature activation+1.765
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.020
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
E
TokenE
Feature activation-0.006
Top resid features:
:
Token:
Feature activation-0.008
Top resid features:
H
TokenH
Feature activation+2.263
Top resid features:
/
Token/
Feature activation+0.011
Top resid features:
I
TokenI
Feature activation+0.136
Top resid features:
:
Token:
Feature activation+0.013
Top resid features:
H
TokenH
Feature activation+2.399
Top resid features:
/
Token/
Feature activation+0.009
Top resid features:
A
TokenA
Feature activation+0.018
Top resid features:
:
Token:
Feature activation-0.004
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.005
Top resid features:
know
Token know
Feature activation-0.013
Top resid features:
that
Token that
Feature activation-0.005
Top resid features:
P
Token P
Feature activation-0.001
Top resid features:
(
Token(
Feature activation-0.006
Top resid features:
H
TokenH
Feature activation+2.436
Top resid features:
|
Token|
Feature activation+0.019
Top resid features:
E
TokenE
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
>
Token >
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
According
TokenAccording
Feature activation-0.018
Top resid features:
to
Token to
Feature activation-0.021
Top resid features:
H
Token H
Feature activation+4.909
Top resid features:
enn
Tokenenn
Feature activation-0.021
Top resid features:
ep
Tokenep
Feature activation-0.001
Top resid features:
in
Tokenin
Feature activation+0.012
Top resid features:
County
Token County
Feature activation+0.040
Top resid features:
Attorney
Token Attorney
Feature activation-0.031
Top resid features:
The
Token The
Feature activation-0.017
Top resid features:
firm
Token firm
Feature activation-0.012
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
hired
Token hired
Feature activation-0.003
Top resid features:
by
Token by
Feature activation-0.004
Top resid features:
H
Token H
Feature activation+4.742
Top resid features:
icken
Tokenicken
Feature activation-0.113
Top resid features:
lo
Tokenlo
Feature activation+0.000
Top resid features:
oper
Tokenoper
Feature activation+0.005
Top resid features:
's
Token's
Feature activation-0.055
Top resid features:
government
Token government
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
We
TokenWe
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.006
Top resid features:
Grad
Token Grad
Feature activation-0.015
Top resid features:
H
TokenH
Feature activation+4.626
Top resid features:
acker
Tokenacker
Feature activation-0.036
Top resid features:
hope
Token hope
Feature activation+0.001
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
enjoy
Token enjoy
Feature activation+0.001
Top resid features:
reading
Token reading
Feature activation-0.000
Top resid features:
's
Token's
Feature activation-0.005
Top resid features:
parents
Token parents
Feature activation+0.042
Top resid features:
'
Token'
Feature activation-0.001
Top resid features:
basement
Token basement
Feature activation-0.008
Top resid features:
when
Token when
Feature activation-0.001
Top resid features:
Hear
Token Hear
Feature activation+4.036
Top resid features:
n
Tokenn
Feature activation+0.015
Top resid features:
decided
Token decided
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
give
Token give
Feature activation-0.001
Top resid features:
Russell
Token Russell
Feature activation-0.025
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sustain
Token sustain
Feature activation-0.005
Top resid features:
snow
Token snow
Feature activation+0.000
Top resid features:
sh
Tokensh
Feature activation-0.003
Top resid features:
oe
Tokenoe
Feature activation+0.038
Top resid features:
ha
Token ha
Feature activation+3.893
Top resid features:
re
Tokenre
Feature activation+0.023
Top resid features:
populations
Token populations
Feature activation+0.049
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
face
Token face
Feature activation+0.001
Top resid features:
due
Tokendue
Feature activation+0.044
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
completely
Token completely
Feature activation+0.013
Top resid features:
disarm
Token disarm
Feature activation+0.025
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
hij
Token hij
Feature activation+3.991
Top resid features:
acker
Tokenacker
Feature activation+0.188
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
who
Token who
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
restrained
Token restrained
Feature activation-0.001
Top resid features:
controversial
Token controversial
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
secretive
Token secretive
Feature activation-0.058
Top resid features:
âĢ
Token âĢ
Feature activation+0.089
Top resid features:
ľ
Tokenľ
Feature activation+0.044
Top resid features:
H
TokenH
Feature activation+4.158
Top resid features:
ann
Tokenann
Feature activation+0.060
Top resid features:
ibal
Tokenibal
Feature activation+0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.036
Top resid features:
Ŀ
TokenĿ
Feature activation+0.058
Top resid features:
procedure
Token procedure
Feature activation+0.032
Top resid features:
police
Token police
Feature activation+0.050
Top resid features:
chief
Token chief
Feature activation+0.071
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Davis
Token Davis
Feature activation-0.013
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
Holl
Token Holl
Feature activation+3.961
Top resid features:
iday
Tokeniday
Feature activation+0.004
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Davis
TokenDavis
Feature activation-0.013
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
Holl
Token Holl
Feature activation+2.744
Top resid features:
iday
Tokeniday
Feature activation-0.004
Top resid features:
then
Token then
Feature activation-0.007
Top resid features:
met
Token met
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
Rob
Token Rob
Feature activation+0.018
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
thing
Token thing
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.019
Top resid features:
MH
TokenMH
Feature activation+3.848
Top resid features:
I
Token I
Feature activation+0.009
Top resid features:
get
Token get
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
impression
Token impression
Feature activation-0.000
Top resid features:
that
Token that
Feature activation-0.003
Top resid features:
Ju
TokenJu
Feature activation+0.001
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+0.011
Top resid features:
Matt
Token Matt
Feature activation-0.070
Top resid features:
H
Token H
Feature activation+4.242
Top resid features:
inton
Tokeninton
Feature activation-0.117
Top resid features:
(@
Token (@
Feature activation-0.038
Top resid features:
Matt
TokenMatt
Feature activation-0.041
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-0.010
Top resid features:
False
TokenFalse
Feature activation-0.018
Top resid features:
accusation
Token accusation
Feature activation+0.007
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
Luke
Token Luke
Feature activation-0.029
Top resid features:
Har
Token Har
Feature activation+2.485
Top resid features:
wood
Tokenwood
Feature activation+0.006
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
18
Token 18
Feature activation-0.000
Top resid features:
when
Token when
Feature activation-0.003
Top resid features:
because
Token because
Feature activation-0.000
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
silly
Token silly
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.001
Top resid features:
Hew
Token Hew
Feature activation+1.874
Top resid features:
itt
Tokenitt
Feature activation+0.009
Top resid features:
responded
Token responded
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation-0.000
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
int
Tokenint
Feature activation+0.004
Top resid features:
ro
Tokenro
Feature activation+0.005
Top resid features:
">
Token">
Feature activation+0.001
Top resid features:
<
Token <
Feature activation+0.008
Top resid features:
h
Tokenh
Feature activation+3.473
Top resid features:
1
Token1
Feature activation+0.059
Top resid features:
><
Token><
Feature activation+0.141
Top resid features:
!--
Token!--
Feature activation+0.038
Top resid features:
Product
Token Product
Feature activation+0.037
Top resid features:
name
Token name
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.03

Head 3: 0.03

Head 4: 0.04

Head 5: 0.02

Head 6: 0.03

Head 7: 0.51

Head 8: 0.03

Head 9: 0.03

Head 10: 0.11

Head 11: 0.05

Positive logits

cast2.77

vantage2.49

ynski2.42

odon2.40

oc2.40

}}}2.39

cius2.34

berto2.30

vale2.29

2.28

ometric2.24

______2.22

ovic2.20

2.19

ovi2.19

etting2.14

intosh2.14

bane2.13

onyms2.10

Ples2.09

Negative logits

Hu-3.48

Halo-3.32

Harding-3.28

Huang-3.10

Hu-3.09

Hait-3.04

Hag-3.04

Helm-2.87

Hannah-2.82

Hal-2.82

Hollande-2.76

HL-2.76

Hanson-2.71

Hatch-2.70

Hamm-2.69

HL-2.66

Alph-2.66

FH-2.62

HAM-2.62

Higgins-2.61

INTERVAL 4.707 - 5.230
CONTAINS 0.000%

that
Token that
Feature activation+0.718
P
Token P
Feature activation+0.000
(
Token(
Feature activation+2.669
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
|
Token|
Feature activation+4.948
H
TokenH
Feature activation+0.000
)
Token)
Feature activation+0.000
<
Token <
Feature activation+0.000
P
TokenP
Feature activation+0.000
(
Token(
Feature activation+0.000
A
TokenA
Feature activation+0.000
:
Token:
Feature activation+4.527
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+1.202
E
TokenE
Feature activation+0.000
:
Token:
Feature activation+5.219
P
TokenP
Feature activation+0.000
/
Token/
Feature activation+0.563
RL
TokenRL
Feature activation+0.000
:
Token:
Feature activation+0.282
O
TokenO
Feature activation+0.000
h
Token h
Feature activation+0.000
dc
Tokendc
Feature activation+0.000
in
Token in
Feature activation+0.000
same
Token same
Feature activation+0.000
st
Token st
Feature activation+0.000
,
Token,
Feature activation+4.985
h
Token h
Feature activation+0.000
dc
Tokendc
Feature activation+0.000
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Sl
Token Sl
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
charges
Token charges
Feature activation+0.000
against
Token against
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+5.230
Anderson
Token Anderson
Feature activation+0.000
dismissed
Token dismissed
Feature activation+0.000
,
Token,
Feature activation+0.000
acknowledging
Token acknowledging
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 4.184 - 4.707
CONTAINS 0.000%

know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.042
P
Token P
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
|
Token|
Feature activation+4.308
E
TokenE
Feature activation+0.000
)
Token)
Feature activation+0.000
>
Token >
Feature activation+0.000
P
Token P
Feature activation+0.000
(
Token(
Feature activation+0.827
I
TokenI
Feature activation+0.000
:
Token:
Feature activation+1.878
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+1.135
A
TokenA
Feature activation+0.000
:
Token:
Feature activation+4.527
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+1.202
E
TokenE
Feature activation+0.000
:
Token:
Feature activation+5.219
P
TokenP
Feature activation+0.000
poor
Token poor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+4.223
the
Token the
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
complaints
Token complaints
Feature activation+0.000
,
Token,
Feature activation+0.000
over
Token over
Feature activation+0.000

INTERVAL 3.661 - 4.184
CONTAINS 0.001%

election
Token election
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
spokesperson
Token spokesperson
Feature activation+0.000
for
Token for
Feature activation+3.975
H
Token H
Feature activation+0.713
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
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
a
Token a
Feature activation+0.000
ball
Token ball
Feature activation+0.000
tap
Token tap
Feature activation+0.000
,"
Token,"
Feature activation+3.825
Hear
Token Hear
Feature activation+0.000
n
Tokenn
Feature activation+0.000
testified
Token testified
Feature activation+0.000
.
Token.
Feature activation+0.392
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
of
Token of
Feature activation+0.000
snow
Token snow
Feature activation+0.606
sh
Tokensh
Feature activation+0.000
oe
Tokenoe
Feature activation+3.802
ha
Token ha
Feature activation+0.167
res
Tokenres
Feature activation+0.000
across
Token across
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Pennsylvania
Token Pennsylvania
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
grateful
Token grateful
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Grad
Token Grad
Feature activation+3.924
H
TokenH
Feature activation+0.000
acker
Tokenacker
Feature activation+0.000
village
Token village
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Under
TokenUnder
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.678
H
TokenH
Feature activation+1.278
ann
Tokenann
Feature activation+0.000
ibal
Tokenibal
Feature activation+0.000
Directive
Token Directive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 3.138 - 3.661
CONTAINS 0.001%

't
Token't
Feature activation+0.000
your
Token your
Feature activation+0.000
favourites
Token favourites
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.464
BS
TokenBS
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
many
Token many
Feature activation+0.000
people
Token people
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+3.252
H
Token H
Feature activation+0.377
ogg
Tokenogg
Feature activation+0.000
.
Token.
Feature activation+0.236
Activ
Token Activ
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
's
Token's
Feature activation+0.000
silly
Token silly
Feature activation+0.000
?"
Token?"
Feature activation+1.762
an
Token an
Feature activation+0.000
incred
Token incred
Feature activation+0.000
ulous
Tokenulous
Feature activation+3.317
Walsh
Token Walsh
Feature activation+0.000
reacted
Token reacted
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
murdered
Token murdered
Feature activation+0.000
him
Token him
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+3.362
Den
Token Den
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
><
Token><
Feature activation+0.256
!--
Token!--
Feature activation+0.000
Product
Token Product
Feature activation+0.000
name
Token name
Feature activation+0.000
--
Token --
Feature activation+0.000
>
Token>
Feature activation+3.254
h
Tokenh
Feature activation+0.000
1
Token1
Feature activation+0.322
>
Token>
Feature activation+0.000
<
Token <
Feature activation+2.279
p
Tokenp
Feature activation+0.000

INTERVAL 2.615 - 3.138
CONTAINS 0.002%

there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
some
Token some
Feature activation+0.000
hypothesis
Token hypothesis
Feature activation+0.000
H
Token H
Feature activation+0.000
and
Token and
Feature activation+2.791
some
Token some
Feature activation+0.000
event
Token event
Feature activation+0.000
E
Token E
Feature activation+0.000
such
Token such
Feature activation+0.000
that
Token that
Feature activation+1.919
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
[
Token[
Feature activation+0.000
D
TokenD
Feature activation+0.000
ov
Tokenov
Feature activation+2.780
Hik
Token Hik
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
NEW
TokenNEW
Feature activation+0.000
DEL
Token DEL
Feature activation+0.000
HI
TokenHI
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
ideal
Token ideal
Feature activation+0.579
geometric
Token geometric
Feature activation+0.000
phase
Token phase
Feature activation+2.901
holog
Token holog
Feature activation+0.000
ram
Tokenram
Feature activation+0.000
mod
Token mod
Feature activation+0.000
ifies
Tokenifies
Feature activation+0.000
the
Token the
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
Resident
Token Resident
Feature activation+0.000
tuition
Token tuition
Feature activation+0.000
at
Token at
Feature activation+0.000
U
Token U
Feature activation+2.696
H
TokenH
Feature activation+0.000
Man
Token Man
Feature activation+0.000
oa
Tokenoa
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
wholesale
Token wholesale
Feature activation+0.000
price
Token price
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.984
M
TokenM
Feature activation+0.000
aine
Tokenaine
Feature activation+0.000
:
Token:
Feature activation+0.000
Cig
Token Cig
Feature activation+0.000
arette
Tokenarette
Feature activation+0.000

INTERVAL 2.092 - 2.615
CONTAINS 0.004%

He
Token He
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
trial
Token trial
Feature activation+0.000
with
Token with
Feature activation+2.451
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
pro
Token pro
Feature activation+0.000
teams
Token teams
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
to
Token to
Feature activation+0.909
the
Token the
Feature activation+0.000
Technical
Token Technical
Feature activation+0.000
Office
Token Office
Feature activation+0.000
of
Token of
Feature activation+2.595
the
Token the
Feature activation+0.313
R
Token R
Feature activation+0.000
LM
TokenLM
Feature activation+0.000
on
Token on
Feature activation+0.000
5
Token 5
Feature activation+0.000
helping
Token helping
Feature activation+0.000
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.000
#
Token #
Feature activation+3.186
Hur
TokenHur
Feature activation+0.000
ricane
Tokenricane
Feature activation+2.307
Har
TokenHar
Feature activation+0.862
vey
Tokenvey
Feature activation+0.000
relief
Token relief
Feature activation+0.000
in
Token in
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
wasted
Token wasted
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
ideal
Token ideal
Feature activation+0.000
geometric
Token geometric
Feature activation+0.000
phase
Token phase
Feature activation+2.158
holog
Token holog
Feature activation+0.000
rams
Tokenrams
Feature activation+0.000
can
Token can
Feature activation+0.000
also
Token also
Feature activation+0.000
produce
Token produce
Feature activation+0.000
found
Token found
Feature activation+0.000
out
Token out
Feature activation+0.093
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
condition
Token condition
Feature activation+0.000
.
Token.
Feature activation+2.222
Lou
Token Lou
Feature activation+0.000
Geh
Token Geh
Feature activation+0.000
rig
Tokenrig
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.569 - 2.092
CONTAINS 0.008%

Cyrus
Token Cyrus
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
left
Token left
Feature activation+1.985
a
Token a
Feature activation+0.000
hole
Token hole
Feature activation+0.000
at
Token at
Feature activation+0.000
corner
Token corner
Feature activation+0.000
for
Token for
Feature activation+2.151
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
Mr
Token Mr
Feature activation+1.713
Assad
Token Assad
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
doing
Token doing
Feature activation+0.000
better
Token better
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+2.014
arrison
Tokenarrison
Feature activation+0.000
said
Token said
Feature activation+0.000
Cunningham
Token Cunningham
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
late
Token late
Feature activation+0.000
2000
Token 2000
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+1.587
After
Token After
Feature activation+0.000
getting
Token getting
Feature activation+0.000
past
Token past
Feature activation+0.000
is
Token is
Feature activation+0.000
imposing
Token imposing
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
hijab
Token hijab
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.727
head
Token head
Feature activation+0.043
scar
Tokenscar
Feature activation+0.000
f
Tokenf
Feature activation+0.000
.
Token.
Feature activation+0.200
She
Token She
Feature activation+0.000

INTERVAL 1.046 - 1.569
CONTAINS 0.019%

.
Token.
Feature activation+1.443
The
Token The
Feature activation+0.000
revelations
Token revelations
Feature activation+0.000
date
Token date
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+1.177
Mad
Token Mad
Feature activation+0.000
sen
Tokensen
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+0.000
Ċ
TokenĊ
Feature activation+0.000
Mont
TokenMont
Feature activation+0.000
gomery
Tokengomery
Feature activation+0.000
also
Token also
Feature activation+0.000
told
Token told
Feature activation+1.297
Gordon
Token Gordon
Feature activation+0.000
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
were
Token were
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
7
Token 7
Feature activation+0.000
64
Token64
Feature activation+0.000
calories
Token calories
Feature activation+0.000
/
Token/
Feature activation+1.124
hr
Tokenhr
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.698
Th
TokenTh
Feature activation+0.000
rill
Tokenrill
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.000
points
Tokenpoints
Feature activation+0.000
,
Token,
Feature activation+1.227
she
Token she
Feature activation+0.000
reaches
Token reaches
Feature activation+0.000
Kur
Token Kur
Feature activation+0.000
uth
Tokenuth
Feature activation+0.000
when
Token when
Feature activation+0.000
and
Token and
Feature activation+0.000
Frances
Token Frances
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+1.483
ans
Tokenans
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.000
mark
Token mark
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.523 - 1.046
CONTAINS 0.050%

don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
see
Token see
Feature activation+0.000
player
Token player
Feature activation+1.026
housing
Token housing
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Central
Token Central
Feature activation+0.000
movement
Token movement
Feature activation+0.000
in
Token in
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
Kong
Token Kong
Feature activation+0.000
and
Token and
Feature activation+0.773
an
Token an
Feature activation+0.000
Occupy
Token Occupy
Feature activation+0.000
Parliament
Token Parliament
Feature activation+0.000
movement
Token movement
Feature activation+0.000
in
Token in
Feature activation+2.580
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
uses
Token uses
Feature activation+0.000
only
Token only
Feature activation+0.000
HTML
Token HTML
Feature activation+0.000
and
Token and
Feature activation+0.705
JavaScript
Token JavaScript
Feature activation+0.000
,
Token,
Feature activation+0.000
displays
Token displays
Feature activation+0.000
type
Token type
Feature activation+0.000
in
Token in
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
Halifax
Token Halifax
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
behind
Token behind
Feature activation+0.529
the
Token the
Feature activation+0.000
plans
Token plans
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
wishing
Token wishing
Feature activation+0.000
for
Token for
Feature activation+0.000
Ky
Token Ky
Feature activation+0.000
ron
Tokenron
Feature activation+0.928
's
Token's
Feature activation+0.000
safe
Token safe
Feature activation+0.000
return
Token return
Feature activation+0.000
as
Token as
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000

INTERVAL 0.000 - 0.523
CONTAINS 99.915%

âĢĵ
Token âĢĵ
Feature activation+0.000
here
Token here
Feature activation+0.000
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
good
Token good
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
NOT
Token NOT
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
maritime
Token maritime
Feature activation+0.000
transport
Token transport
Feature activation+0.000
subsequently
Token subsequently
Feature activation+0.000
enable
Token enable
Feature activation+0.000
bananas
Token bananas
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
traded
Token traded
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
...
Token...
Feature activation+0.000
have
Tokenhave
Feature activation+0.000
now
Token now
Feature activation+0.000
learnt
Token learnt
Feature activation+0.000
to
Token to
Feature activation+0.000
produce
Token produce
Feature activation+0.000
the
Token the
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
National
Token National
Feature activation+0.000
Aud
Token Aud
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
on
Tokenon
Feature activation+0.000
Society
Token Society
Feature activation+0.000
Guide
Token Guide
Feature activation+0.000
to
Token to
Feature activation+0.000
Nature
Token Nature
Feature activation+0.000
Photography
Token Photography
Feature activation+0.000
has
Token has
Feature activation+0.000
quietly
Token quietly
Feature activation+0.000
turned
Token turned
Feature activation+0.000
him
Token him
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
lockdown
Token lockdown
Feature activation+0.000
corner
Token corner
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
he
Token he
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 H10.7: (feature 24265)

TOP ACTIVATIONS
MAX = 2.439

damage
Token damage
Feature activation+0.000
.
Token.
Feature activation+0.000
Whereas
Token Whereas
Feature activation+0.000
the
Token the
Feature activation+0.000
mechanisms
Token mechanisms
Feature activation+0.000
and
Token and
Feature activation+2.439
kin
Token kin
Feature activation+0.000
etics
Tokenetics
Feature activation+0.066
of
Token of
Feature activation+0.000
liver
Token liver
Feature activation+0.000
regeneration
Token regeneration
Feature activation+0.000
's
Token's
Feature activation+0.000
Overse
Token Overse
Feature activation+0.000
as
Tokenas
Feature activation+0.000
Territories
Token Territories
Feature activation+0.000
'
Token'
Feature activation+0.000
hidden
Token hidden
Feature activation+2.339
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.206
developing
Token developing
Feature activation+0.281
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
he
Token he
Feature activation+0.995
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.310
employed
Token employed
Feature activation+0.139
for
Token for
Feature activation+0.000
A
Token A
Feature activation+0.000
Color
Token Color
Feature activation+0.000
Map
Token Map
Feature activation+0.000
adopted
Token adopted
Feature activation+0.000
the
Token the
Feature activation+0.000
doub
Token doub
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
ive
Tokenive
Feature activation+2.266
framework
Token framework
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
traumat
Token traumat
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+2.218
may
Token may
Feature activation+1.946
have
Token have
Feature activation+1.901
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
scope
Token scope
Feature activation+0.000
and
Token and
Feature activation+2.172
would
Token would
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
grease
Token grease
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+2.135
results
Token results
Feature activation+0.000
of
Token of
Feature activation+0.000
giving
Token giving
Feature activation+0.000
&
Token &
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
support
Token support
Feature activation+0.000
reform
Token reform
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.124
experience
Token experience
Feature activation+0.000
and
Token and
Feature activation+2.102
background
Token background
Feature activation+0.292
can
Token can
Feature activation+0.000
car
Token car
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Transfer
TokenTransfer
Feature activation+0.000
ring
Tokenring
Feature activation+0.000
security
Token security
Feature activation+2.022
responsibilities
Token responsibilities
Feature activation+0.000
"
Token"
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.820
o
Token o
Feature activation+0.000
mits
Tokenmits
Feature activation+1.055
well
Token well
Feature activation+0.000
-
Token-
Feature activation+0.000
known
Tokenknown
Feature activation+2.016
explanations
Token explanations
Feature activation+0.000
for
Token for
Feature activation+0.495
important
Token important
Feature activation+1.261
features
Token features
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
operating
Token operating
Feature activation+0.005
models
Token models
Feature activation+0.000
,
Token,
Feature activation+0.000
processes
Token processes
Feature activation+0.000
and
Token and
Feature activation+1.977
governance
Token governance
Feature activation+0.754
.
Token.
Feature activation+0.000
Ent
Token Ent
Feature activation+0.000
rust
Tokenrust
Feature activation+0.000
ing
Tokening
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
was
Token was
Feature activation+0.369
very
Token very
Feature activation+0.418
well
Token well
Feature activation+1.976
fed
Token fed
Feature activation+0.000
...
Token ...
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
like
Token like
Feature activation+0.000
hed
Tokenhed
Feature activation+0.000
.
Token .
Feature activation+0.000
But
Token But
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
that
Token that
Feature activation+1.968
period
Token period
Feature activation+0.000
he
Token he
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
increases
Token increases
Feature activation+0.000
his
Token his
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+2.218
may
Token may
Feature activation+1.946
have
Token have
Feature activation+1.901
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
and
Token and
Feature activation+1.924
motivation
Token motivation
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
essay
Token essay
Feature activation+0.000
,
Token,
Feature activation+0.000
reluctance
Token reluctance
Feature activation+0.000
to
Token to
Feature activation+0.000
interfere
Token interfere
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
judicial
Token judicial
Feature activation+1.919
process
Token process
Feature activation+0.000
,
Token,
Feature activation+0.000
statements
Token statements
Feature activation+0.000
he
Token he
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+2.218
may
Token may
Feature activation+1.946
have
Token have
Feature activation+1.901
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
traditions
Token traditions
Feature activation+0.000
,
Token,
Feature activation+1.143
practices
Token practices
Feature activation+0.057
,
Token,
Feature activation+1.899
social
Token social
Feature activation+0.890
structure
Token structure
Feature activation+0.000
,
Token,
Feature activation+1.071
economic
Token economic
Feature activation+0.885
systems
Token systems
Feature activation+0.011
.
Token.
Feature activation+0.100
Any
Token Any
Feature activation+1.020
individual
Token individual
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.883
expression
Token expression
Feature activation+0.000
of
Token of
Feature activation+0.163
any
Token any
Feature activation+0.026
view
Token view
Feature activation+0.000
is
Token is
Feature activation+0.000
g
Tokeng
Feature activation+0.000
usting
Tokenusting
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
such
Token such
Feature activation+1.858
acts
Token acts
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.129
outlawed
Token outlawed
Feature activation+0.000

Top DFA by src position
MAX = 3.103

liver
Token liver
Feature activation-0.003
Top resid features:
damage
Token damage
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Whereas
Token Whereas
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
mechanisms
Token mechanisms
Feature activation+3.103
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
kin
Token kin
Feature activation+0.000
Top resid features:
etics
Tokenetics
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
liver
Token liver
Feature activation+0.000
Top resid features:
Overse
Token Overse
Feature activation-0.003
Top resid features:
as
Tokenas
Feature activation-0.005
Top resid features:
Territories
Token Territories
Feature activation-0.007
Top resid features:
'
Token'
Feature activation+0.001
Top resid features:
hidden
Token hidden
Feature activation-0.003
Top resid features:
role
Token role
Feature activation+2.995
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
developing
Token developing
Feature activation-0.011
Top resid features:
countries
Token countries
Feature activation-0.061
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
exceedingly
Token exceedingly
Feature activation-0.001
Top resid features:
proud
Token proud
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
process
Token process
Feature activation+2.976
Top resid features:
he
Token he
Feature activation+0.022
Top resid features:
âĢ
TokenâĢ
Feature activation-0.014
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
s
Tokens
Feature activation-0.008
Top resid features:
employed
Token employed
Feature activation+0.000
Top resid features:
ignorant
Token ignorant
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
your
Token your
Feature activation+0.001
Top resid features:
interpret
Token interpret
Feature activation-0.014
Top resid features:
ive
Tokenive
Feature activation-0.003
Top resid features:
framework
Token framework
Feature activation+2.849
Top resid features:
).
Token).
Feature activation-0.003
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.000
Top resid features:
faithful
Token faithful
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
traumat
Token traumat
Feature activation-0.001
Top resid features:
ized
Tokenized
Feature activation+0.002
Top resid features:
from
Token from
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
experiences
Token experiences
Feature activation+2.998
Top resid features:
they
Token they
Feature activation-0.027
Top resid features:
may
Token may
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
limited
Tokenlimited
Feature activation-0.016
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.057
Top resid features:
its
Token its
Feature activation+0.034
Top resid features:
scope
Token scope
Feature activation+2.783
Top resid features:
and
Token and
Feature activation+0.046
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation+0.000
Top resid features:
grease
Token grease
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
know
Token know
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
results
Token results
Feature activation+2.987
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
giving
Token giving
Feature activation-0.001
Top resid features:
&
Token &
Feature activation+0.022
Top resid features:
sharing
Token sharing
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
support
Token support
Feature activation+0.005
Top resid features:
reform
Token reform
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Their
Token Their
Feature activation+0.089
Top resid features:
experience
Token experience
Feature activation+2.428
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
background
Token background
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
r
Tokenr
Feature activation+0.000
Top resid features:
slated
Token slated
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
begin
Token begin
Feature activation-0.001
Top resid features:
transferring
Token transferring
Feature activation-0.012
Top resid features:
security
Token security
Feature activation-0.010
Top resid features:
responsibilities
Token responsibilities
Feature activation+2.574
Top resid features:
to
Token to
Feature activation-0.013
Top resid features:
Afghan
Token Afghan
Feature activation+0.000
Top resid features:
security
Token security
Feature activation+0.001
Top resid features:
forces
Token forces
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
reports
Token reports
Feature activation+0.007
Top resid features:
non
Token non
Feature activation-0.006
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
existent
Tokenexistent
Feature activation+0.004
Top resid features:
events
Token events
Feature activation+1.286
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
o
Token o
Feature activation+0.008
Top resid features:
mits
Tokenmits
Feature activation-0.045
Top resid features:
well
Token well
Feature activation+0.009
Top resid features:
approach
Token approach
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
operating
Token operating
Feature activation+0.019
Top resid features:
models
Token models
Feature activation+0.275
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
processes
Token processes
Feature activation+1.870
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
governance
Token governance
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ent
Token Ent
Feature activation+0.000
Top resid features:
rust
Tokenrust
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
saying
Token saying
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
treated
Token treated
Feature activation+2.432
Top resid features:
well
Token well
Feature activation+0.091
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
"
Token"
Feature activation+0.025
Top resid features:
.
Token .
Feature activation+0.001
Top resid features:
But
Token But
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
after
Token after
Feature activation+0.003
Top resid features:
that
Token that
Feature activation-0.011
Top resid features:
period
Token period
Feature activation+2.695
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
incredibly
Token incredibly
Feature activation+0.007
Top resid features:
increases
Token increases
Feature activation-0.004
Top resid features:
his
Token his
Feature activation-0.001
Top resid features:
attack
Token attack
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
traumat
Token traumat
Feature activation+0.001
Top resid features:
ized
Tokenized
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
experiences
Token experiences
Feature activation+2.598
Top resid features:
they
Token they
Feature activation-0.014
Top resid features:
may
Token may
Feature activation+0.011
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.002
Top resid features:
ence
Tokenence
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.150
Top resid features:
purpose
Token purpose
Feature activation+2.309
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
motivation
Token motivation
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
essay
Token essay
Feature activation+0.000
Top resid features:
not
Token not
Feature activation-0.000
Top resid features:
interfere
Token interfere
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
judicial
Token judicial
Feature activation-0.016
Top resid features:
process
Token process
Feature activation+1.519
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
Egyptian
Token Egyptian
Feature activation+0.002
Top resid features:
government
Token government
Feature activation-0.000
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
traumat
Token traumat
Feature activation+0.008
Top resid features:
ized
Tokenized
Feature activation-0.002
Top resid features:
from
Token from
Feature activation-0.019
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
experiences
Token experiences
Feature activation+2.430
Top resid features:
they
Token they
Feature activation-0.000
Top resid features:
may
Token may
Feature activation-0.005
Top resid features:
have
Token have
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
notes
Token notes
Feature activation+0.001
Top resid features:
about
Token about
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.097
Top resid features:
traditions
Token traditions
Feature activation+0.618
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
practices
Token practices
Feature activation+1.723
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
social
Token social
Feature activation+0.000
Top resid features:
structure
Token structure
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
economic
Token economic
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
individual
Token individual
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
experience
Token experience
Feature activation+2.226
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
perception
Token perception
Feature activation+0.254
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
society
Token society
Feature activation-0.005
Top resid features:
views
Token views
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
practices
Token practices
Feature activation+2.641
Top resid features:
as
Token as
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
dis
Tokendis
Feature activation-0.004
Top resid features:
g
Tokeng
Feature activation+0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.02

Head 3: 0.03

Head 4: 0.08

Head 5: 0.03

Head 6: 0.04

Head 7: 0.51

Head 8: 0.02

Head 9: 0.06

Head 10: 0.03

Head 11: 0.11

Positive logits

ulton2.53

204392.50

hess2.27

Bahá2.24

alde2.18

umbledore2.14

eus2.07

Jews2.07

kefeller2.05

lehem2.03

Jewish1.99

Jew1.98

yss1.97

Buckingham1.97

anyahu1.94

ones1.93

Wink1.93

1.92

rices1.92

Pirate1.91

Negative logits

Technique-1.92

Instit-1.92

stim-1.89

Tactics-1.85

method-1.82

Opportun-1.81

enforcing-1.81

Injury-1.81

malfunction-1.79

Reduced-1.79

Condition-1.78

activity-1.76

Purpose-1.73

Performance-1.73

Module-1.73

acronym-1.72

category-1.71

section-1.71

vable-1.70

Opportunity-1.70

INTERVAL 2.195 - 2.439
CONTAINS 0.001%

the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
he
Token he
Feature activation+0.995
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.310
employed
Token employed
Feature activation+0.139
for
Token for
Feature activation+0.000
A
Token A
Feature activation+0.000
Color
Token Color
Feature activation+0.000
Map
Token Map
Feature activation+0.000
traumat
Token traumat
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+2.218
may
Token may
Feature activation+1.946
have
Token have
Feature activation+1.901
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
adopted
Token adopted
Feature activation+0.000
the
Token the
Feature activation+0.000
doub
Token doub
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
ive
Tokenive
Feature activation+2.266
framework
Token framework
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
damage
Token damage
Feature activation+0.000
.
Token.
Feature activation+0.000
Whereas
Token Whereas
Feature activation+0.000
the
Token the
Feature activation+0.000
mechanisms
Token mechanisms
Feature activation+0.000
and
Token and
Feature activation+2.439
kin
Token kin
Feature activation+0.000
etics
Tokenetics
Feature activation+0.066
of
Token of
Feature activation+0.000
liver
Token liver
Feature activation+0.000
regeneration
Token regeneration
Feature activation+0.000
's
Token's
Feature activation+0.000
Overse
Token Overse
Feature activation+0.000
as
Tokenas
Feature activation+0.000
Territories
Token Territories
Feature activation+0.000
'
Token'
Feature activation+0.000
hidden
Token hidden
Feature activation+2.339
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.206
developing
Token developing
Feature activation+0.281
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.951 - 2.195
CONTAINS 0.001%

support
Token support
Feature activation+0.000
reform
Token reform
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.124
experience
Token experience
Feature activation+0.000
and
Token and
Feature activation+2.102
background
Token background
Feature activation+0.292
can
Token can
Feature activation+0.000
car
Token car
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
hed
Tokenhed
Feature activation+0.000
.
Token .
Feature activation+0.000
But
Token But
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
that
Token that
Feature activation+1.968
period
Token period
Feature activation+0.000
he
Token he
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
increases
Token increases
Feature activation+0.000
his
Token his
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
was
Token was
Feature activation+0.369
very
Token very
Feature activation+0.418
well
Token well
Feature activation+1.976
fed
Token fed
Feature activation+0.000
...
Token ...
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
like
Token like
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+2.135
results
Token results
Feature activation+0.000
of
Token of
Feature activation+0.000
giving
Token giving
Feature activation+0.000
&
Token &
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
to
Token to
Feature activation+0.000
operating
Token operating
Feature activation+0.005
models
Token models
Feature activation+0.000
,
Token,
Feature activation+0.000
processes
Token processes
Feature activation+0.000
and
Token and
Feature activation+1.977
governance
Token governance
Feature activation+0.754
.
Token.
Feature activation+0.000
Ent
Token Ent
Feature activation+0.000
rust
Tokenrust
Feature activation+0.000
ing
Tokening
Feature activation+0.000

INTERVAL 1.707 - 1.951
CONTAINS 0.002%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+2.218
may
Token may
Feature activation+1.946
have
Token have
Feature activation+1.901
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
against
Token against
Feature activation+0.187
overcrowd
Token overcrowd
Feature activation+0.000
ing
Tokening
Feature activation+0.000
are
Token are
Feature activation+0.780
a
Token a
Feature activation+1.202
regular
Token regular
Feature activation+1.762
occurrence
Token occurrence
Feature activation+0.000
inside
Token inside
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
reluctance
Token reluctance
Feature activation+0.000
to
Token to
Feature activation+0.000
interfere
Token interfere
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
judicial
Token judicial
Feature activation+1.919
process
Token process
Feature activation+0.000
,
Token,
Feature activation+0.000
statements
Token statements
Feature activation+0.000
he
Token he
Feature activation+0.000
made
Token made
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000
then
Token then
Feature activation+0.000
the
Token the
Feature activation+0.000
fiscal
Token fiscal
Feature activation+1.712
impact
Token impact
Feature activation+0.000
is
Token is
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
ary
Tokenary
Feature activation+0.000
(
Token (
Feature activation+0.000
aud
Token aud
Feature activation+0.000
itors
Tokenitors
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
experience
Token experience
Feature activation+0.000
or
Token or
Feature activation+1.821
professional
Token professional
Feature activation+1.070
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 1.463 - 1.707
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token .
Feature activation+0.000
No
Token No
Feature activation+0.000
?
Token ?
Feature activation+0.000
No
Token No
Feature activation+1.574
problem
Token problem
Feature activation+0.000
!
Token!
Feature activation+0.000
Special
Token Special
Feature activation+0.000
Summon
Token Summon
Feature activation+0.000
Gladiator
Token Gladiator
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
other
Token other
Feature activation+0.072
technology
Token technology
Feature activation+0.000
or
Token or
Feature activation+1.545
knowledge
Token knowledge
Feature activation+0.000
was
Token was
Feature activation+0.000
ever
Token ever
Feature activation+0.000
shared
Token shared
Feature activation+0.000
as
Token as
Feature activation+0.000
believe
Token believe
Feature activation+0.000
their
Token their
Feature activation+0.000
voices
Token voices
Feature activation+0.000
,
Token,
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
and
Token and
Feature activation+1.699
identities
Token identities
Feature activation+0.000
deserve
Token deserve
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
heard
Token heard
Feature activation+0.000
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
controversy
Token controversy
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
alleged
Token alleged
Feature activation+1.650
involvement
Token involvement
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
murder
Token murder
Feature activation+0.000
of
Token of
Feature activation+0.000
emotions
Token emotions
Feature activation+0.000
,
Token,
Feature activation+0.300
behaviours
Token behaviours
Feature activation+0.000
,
Token,
Feature activation+1.819
and
Token and
Feature activation+1.793
even
Token even
Feature activation+1.496
morals
Token morals
Feature activation+0.000
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
]
Token]
Feature activation+0.000
Early
Token Early
Feature activation+0.000

INTERVAL 1.219 - 1.463
CONTAINS 0.005%

,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.173
effect
Token effect
Feature activation+0.000
this
Token this
Feature activation+0.457
might
Token might
Feature activation+1.231
have
Token have
Feature activation+0.503
on
Token on
Feature activation+0.000
polar
Token polar
Feature activation+0.000
izing
Tokenizing
Feature activation+0.006
opinion
Token opinion
Feature activation+0.000
a
Token a
Feature activation+0.000
strong
Token strong
Feature activation+0.000
chance
Token chance
Feature activation+0.000
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
new
Token new
Feature activation+1.300
social
Token social
Feature activation+0.198
development
Token development
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
influence
Token influence
Feature activation+0.000
Union
Token Union
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.854
secretive
Token secretive
Feature activation+1.411
years
Token years
Feature activation+0.000
long
Token long
Feature activation+0.000
operation
Token operation
Feature activation+0.000
resulted
Token resulted
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
net
Token net
Feature activation+1.388
result
Token result
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
market
Token market
Feature activation+0.000
be
Token be
Feature activation+0.000
league
Tokenleague
Feature activation+0.000
red
Tokenred
Feature activation+0.000
by
Token by
Feature activation+0.000
difficulties
Token difficulties
Feature activation+0.000
and
Token and
Feature activation+1.445
lawsuits
Token lawsuits
Feature activation+0.000
.
Token.
Feature activation+0.000
Queens
Token Queens
Feature activation+0.000
now
Token now
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.976 - 1.219
CONTAINS 0.012%

The
TokenThe
Feature activation+0.000
No
Token No
Feature activation+0.000
Jab
Token Jab
Feature activation+0.000
,
Token,
Feature activation+0.000
No
Token No
Feature activation+0.088
Play
Token Play
Feature activation+1.200
policy
Token policy
Feature activation+0.000
was
Token was
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
to
Token to
Feature activation+0.000
counter
Token counter
Feature activation+0.000
plans
Token plans
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.350
developed
Token developed
Feature activation+0.000
and
Token and
Feature activation+1.094
then
Token then
Feature activation+0.655
edited
Token edited
Feature activation+0.000
,
Token,
Feature activation+0.623
rem
Token rem
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
in
Token in
Feature activation+0.000
landscape
Token landscape
Feature activation+0.138
,
Token,
Feature activation+0.501
the
Token the
Feature activation+0.143
ecosystem
Token ecosystem
Feature activation+0.374
and
Token and
Feature activation+1.128
the
Token the
Feature activation+0.819
disruption
Token disruption
Feature activation+0.000
this
Token this
Feature activation+0.116
caused
Token caused
Feature activation+0.040
to
Token to
Feature activation+0.209
Levin
Token Levin
Feature activation+0.000
told
Token told
Feature activation+0.000
his
Token his
Feature activation+0.000
troops
Token troops
Feature activation+0.000
before
Token before
Feature activation+0.105
the
Token the
Feature activation+0.978
operation
Token operation
Feature activation+0.000
began
Token began
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
adjust
Token adjust
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
funding
Token funding
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ization
Tokenization
Feature activation+1.086
goals
Token goals
Feature activation+0.311
set
Token set
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
project
Token project
Feature activation+0.000

INTERVAL 0.732 - 0.976
CONTAINS 0.031%

armed
Token armed
Feature activation+0.000
forces
Token forces
Feature activation+0.000
besides
Token besides
Feature activation+0.000
the
Token the
Feature activation+0.000
challenges
Token challenges
Feature activation+0.000
and
Token and
Feature activation+0.860
the
Token the
Feature activation+0.502
inf
Token inf
Feature activation+0.000
rast
Tokenrast
Feature activation+0.000
ruct
Tokenruct
Feature activation+0.000
ural
Tokenural
Feature activation+0.847
that
Token that
Feature activation+0.000
come
Token come
Feature activation+0.000
with
Token with
Feature activation+0.057
specific
Token specific
Feature activation+0.070
challenges
Token challenges
Feature activation+0.000
and
Token and
Feature activation+0.927
needs
Token needs
Feature activation+0.000
.
Token.
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
this
Token this
Feature activation+0.489
subject
Token subject
Feature activation+0.000
and
Token and
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.778
subject
Token subject
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
for
Token for
Feature activation+0.000
them
Token them
Feature activation+0.000
Gal
TokenGal
Feature activation+0.000
axy
Tokenaxy
Feature activation+0.000
Quest
Token Quest
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.005
Journey
Token Journey
Feature activation+0.798
Contin
Token Contin
Feature activation+0.000
ues
Tokenues
Feature activation+0.000
Edit
Token Edit
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.000
authors
Tokenauthors
Feature activation+0.000
/
Token/
Feature activation+0.000
tone
Tokentone
Feature activation+0.000
_
Token_
Feature activation+0.790
v
Tokenv
Feature activation+0.000
ays
Tokenays
Feature activation+0.000
).
Token).
Feature activation+0.000
Tone
Token Tone
Feature activation+0.000
maintains
Token maintains
Feature activation+0.000

INTERVAL 0.488 - 0.732
CONTAINS 0.074%

ipl
Tokenipl
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
Spec
Token Spec
Feature activation+0.000
ifies
Tokenifies
Feature activation+0.000
the
Token the
Feature activation+0.000
scaling
Token scaling
Feature activation+0.513
factor
Token factor
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
damage
Token damage
Feature activation+0.000
players
Token players
Feature activation+0.000
constantly
Token constantly
Feature activation+0.000
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.581
space
Token space
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ift
Tokenift
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.162
core
Token core
Feature activation+0.556
functionality
Token functionality
Feature activation+0.000
that
Token that
Feature activation+0.000
users
Token users
Feature activation+0.000
enjoyed
Token enjoyed
Feature activation+0.000
was
Token was
Feature activation+0.000
living
Token living
Feature activation+0.000
sources
Token sources
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
organic
Token organic
Feature activation+0.604
compounds
Token compounds
Feature activation+0.000
contain
Token contain
Feature activation+0.000
elements
Token elements
Feature activation+0.000
,
Token,
Feature activation+0.280
including
Token including
Feature activation+0.000
ridiculous
Token ridiculous
Feature activation+0.000
at
Token at
Feature activation+0.000
best
Token best
Feature activation+0.000
,
Token,
Feature activation+0.000
reckless
Token reckless
Feature activation+0.000
at
Token at
Feature activation+0.670
worst
Token worst
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 0.244 - 0.488
CONTAINS 0.188%

pretty
Token pretty
Feature activation+0.000
famous
Token famous
Feature activation+0.000
local
Token local
Feature activation+0.251
chefs
Token chefs
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.394
meat
Token meat
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.867
recipes
Token recipes
Feature activation+0.000
at
Token at
Feature activation+0.000
data
Token data
Feature activation+0.000
less
Token less
Feature activation+0.000
accessible
Token accessible
Feature activation+0.000
and
Token and
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
more
Token more
Feature activation+0.486
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
fascinated
Token fascinated
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
intensity
Token intensity
Feature activation+0.000
,
Token,
Feature activation+0.312
the
Token the
Feature activation+0.496
brutality
Token brutality
Feature activation+0.000
,
Token,
Feature activation+0.056
and
Token and
Feature activation+0.077
the
Token the
Feature activation+0.393
household
Token household
Feature activation+0.000
or
Token or
Feature activation+0.136
even
Token even
Feature activation+0.000
an
Token an
Feature activation+0.189
estate
Token estate
Feature activation+0.000
,
Token,
Feature activation+0.272
hierarchy
Token hierarchy
Feature activation+0.000
and
Token and
Feature activation+0.216
kins
Token kins
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
,
Token,
Feature activation+0.507
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
cause
Tokencause
Feature activation+0.000
real
Token real
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
-
Token-
Feature activation+0.325
type
Tokentype
Feature activation+0.000
broth
Token broth
Feature activation+0.000
as
Tokenas
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000

INTERVAL 0.000 - 0.244
CONTAINS 99.684%

.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
my
Token my
Feature activation+0.000
career
Token career
Feature activation+0.000
we
Token we
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
action
Token action
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Eng
TokenEng
Feature activation+0.000
age
Tokenage
Feature activation+0.000
directly
Token directly
Feature activation+0.000
with
Token with
Feature activation+0.000
potential
Token potential
Feature activation+0.000
recruits
Token recruits
Feature activation+0.000
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
has
Tokenhas
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.000
reality
Token reality
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
development
Token development
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
6
Token6
Feature activation+0.000
)
Token)
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
defense
Token defense
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
than
Token than
Feature activation+0.000
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
TokenâĢĵ
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 H10.7: (feature 22254)

TOP ACTIVATIONS
MAX = 6.520

his
Token his
Feature activation+0.000
when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+5.238
or
Token or
Feature activation+6.520
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
chest
Token chest
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
Photos
Token Photos
Feature activation+0.000
B
Token B
Feature activation+0.000
and
Token and
Feature activation+6.227
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
the
Token the
Feature activation+0.000
template
Token template
Feature activation+0.000
August
Token August
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.453
(
Token(
Feature activation+6.193
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Se
Token Se
Feature activation+0.000
clusion
Tokenclusion
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
2
Token2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+5.825
C
Token C
Feature activation+0.000
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000
TOR
TokenTOR
Feature activation+0.000
BA
TokenBA
Feature activation+0.000
(
Token (
Feature activation+0.000
Toronto
TokenToronto
Feature activation+0.392
Off
Token Off
Feature activation+0.000
road
Tokenroad
Feature activation+5.704
B
Token B
Feature activation+0.000
icy
Tokenicy
Feature activation+0.000
cling
Tokencling
Feature activation+0.526
Association
Token Association
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
conversation
Token conversation
Feature activation+0.000
;
Token;
Feature activation+0.000
(
Token (
Feature activation+5.687
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
recently
Token recently
Feature activation+0.000
awoken
Token awoken
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
coma
Token coma
Feature activation+0.000
and
Token and
Feature activation+5.669
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
unsure
Token unsure
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
's
Token's
Feature activation+0.000
Office
Token Office
Feature activation+0.000
Photo
Token Photo
Feature activation+0.000
:
Token:
Feature activation+5.340
B
Token B
Feature activation+0.601
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
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+5.238
or
Token or
Feature activation+6.520
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
land
Token land
Feature activation+0.000
base
Token base
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
/
Token/
Feature activation+5.049
B
TokenB
Feature activation+0.000
has
Token has
Feature activation+0.000
less
Token less
Feature activation+0.000
resources
Token resources
Feature activation+0.000
for
Token for
Feature activation+0.000
lower
Token lower
Feature activation+0.000
the
Token the
Feature activation+0.000
incidence
Token incidence
Feature activation+0.000
of
Token of
Feature activation+0.000
diseases
Token diseases
Feature activation+0.000
;
Token;
Feature activation+4.983
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
provide
Token provide
Feature activation+0.000
cur
Token cur
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+4.634
C
Token C
Feature activation+0.000
:
Token:
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.000
and
Token and
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+3.288
not
Token not
Feature activation+4.548
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
problems
Token problems
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
updated
Token updated
Feature activation+0.000
Open
Token Open
Feature activation+4.446
B
TokenB
Feature activation+0.000
azaar
Tokenazaar
Feature activation+0.000
logo
Token logo
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
785
Token785
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
C
Token C
Feature activation+4.341
bo
Tokenbo
Feature activation+0.000
e
Tokene
Feature activation+0.000
bitcoin
Token bitcoin
Feature activation+0.000
futures
Token futures
Feature activation+0.000
settled
Token settled
Feature activation+0.000
"
Token "
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.000
Mr
Token Mr
Feature activation+0.972
.
Token.
Feature activation+4.341
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
say
Token say
Feature activation+0.000
once
Token once
Feature activation+0.000
again
Token again
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
Volks
Token Volks
Feature activation+4.180
b
Tokenb
Feature activation+0.143
ü
Tokenü
Feature activation+0.009
h
Tokenh
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
Fight
Token Fight
Feature activation+0.000
w
Token w
Feature activation+0.000
weights
Token weights
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
144
Token 144
Feature activation+4.131
b
Token b
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
8
Token 8
Feature activation+0.000
51
Token51
Feature activation+0.000
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.724
Image
TokenImage
Feature activation+0.000
:
Token:
Feature activation+4.002
b
Token b
Feature activation+1.483
umble
Tokenumble
Feature activation+0.533
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.637
Much
TokenMuch
Feature activation+0.000
,
Token,
Feature activation+0.000
300
Token300
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
C
Token C
Feature activation+3.973
ME
TokenME
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.000
was
Token was
Feature activation+0.000
near
Token near
Feature activation+0.000
2
Token 2
Feature activation+0.000

Top DFA by src position
MAX = 7.122

a
Token a
Feature activation-0.004
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
very
Token very
Feature activation+0.001
Top resid features:
confused
Token confused
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
b
Token b
Feature activation+7.122
Top resid features:
)
Token)
Feature activation-0.053
Top resid features:
had
Token had
Feature activation+0.006
Top resid features:
only
Token only
Feature activation+0.002
Top resid features:
recently
Token recently
Feature activation-0.001
Top resid features:
awoken
Token awoken
Feature activation-0.002
Top resid features:
your
Token your
Feature activation+0.008
Top resid features:
chest
Token chest
Feature activation+0.002
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.040
Top resid features:
see
Token see
Feature activation+0.039
Top resid features:
Photos
Token Photos
Feature activation+0.071
Top resid features:
B
Token B
Feature activation+6.442
Top resid features:
and
Token and
Feature activation+0.052
Top resid features:
C
Token C
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Turn
Token Turn
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.175
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
(
Token(
Feature activation+0.005
Top resid features:
b
Tokenb
Feature activation+6.620
Top resid features:
)
Token)
Feature activation+0.014
Top resid features:
Pr
Token Pr
Feature activation-0.002
Top resid features:
one
Tokenone
Feature activation+0.001
Top resid features:
restraint
Token restraint
Feature activation+0.001
Top resid features:
allowed
Token allowed
Feature activation-0.001
Top resid features:
2
Token2
Feature activation+0.002
Top resid features:
nd
Tokennd
Feature activation+0.015
Top resid features:
Place
Token Place
Feature activation-0.033
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
Player
Token Player
Feature activation+0.050
Top resid features:
B
Token B
Feature activation+6.332
Top resid features:
:
Token:
Feature activation+0.055
Top resid features:
True
Token True
Feature activation+0.001
Top resid features:
Draco
Token Draco
Feature activation+0.000
Top resid features:
Dinosaur
Token Dinosaur
Feature activation+0.020
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation-0.002
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Toronto
Token Toronto
Feature activation-0.001
Top resid features:
Off
Token Off
Feature activation+0.005
Top resid features:
road
Tokenroad
Feature activation+0.002
Top resid features:
B
Token B
Feature activation+5.925
Top resid features:
iking
Tokeniking
Feature activation-0.106
Top resid features:
Association
Token Association
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Check
Token Check
Feature activation-0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
your
Token your
Feature activation+0.001
Top resid features:
opinion
Token opinion
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
(
Token (
Feature activation-0.001
Top resid features:
b
Tokenb
Feature activation+6.172
Top resid features:
)
Token)
Feature activation-0.008
Top resid features:
it
Token it
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
)
Token)
Feature activation+0.021
Top resid features:
very
Token very
Feature activation+0.004
Top resid features:
confused
Token confused
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
b
Token b
Feature activation+6.263
Top resid features:
)
Token)
Feature activation-0.034
Top resid features:
had
Token had
Feature activation+0.013
Top resid features:
only
Token only
Feature activation+0.012
Top resid features:
recently
Token recently
Feature activation-0.011
Top resid features:
awoken
Token awoken
Feature activation+0.009
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-0.023
Top resid features:
:
Token:
Feature activation-0.007
Top resid features:
B
Token B
Feature activation+5.826
Top resid features:
ex
Tokenex
Feature activation+0.025
Top resid features:
ar
Tokenar
Feature activation-0.061
Top resid features:
County
Token County
Feature activation+0.023
Top resid features:
Sheriff
Token Sheriff
Feature activation+0.020
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
)
Token)
Feature activation+0.009
Top resid features:
very
Token very
Feature activation+0.002
Top resid features:
confused
Token confused
Feature activation-0.019
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
b
Token b
Feature activation+5.835
Top resid features:
)
Token)
Feature activation-0.047
Top resid features:
had
Token had
Feature activation-0.000
Top resid features:
only
Token only
Feature activation-0.000
Top resid features:
recently
Token recently
Feature activation-0.002
Top resid features:
awoken
Token awoken
Feature activation-0.004
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
opposed
Token opposed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Mono
Token Mono
Feature activation-0.033
Top resid features:
B
TokenB
Feature activation+4.327
Top resid features:
variant
Token variant
Feature activation-0.003
Top resid features:
which
Token which
Feature activation+0.004
Top resid features:
runs
Token runs
Feature activation-0.002
Top resid features:
at
Token at
Feature activation-0.002
Top resid features:
20
Token 20
Feature activation-0.013
Top resid features:
)
Token)
Feature activation+0.033
Top resid features:
adopt
Token adopt
Feature activation+0.001
Top resid features:
preventive
Token preventive
Feature activation+0.003
Top resid features:
measures
Token measures
Feature activation-0.011
Top resid features:
;
Token;
Feature activation-0.007
Top resid features:
b
Token b
Feature activation+5.542
Top resid features:
)
Token)
Feature activation-0.025
Top resid features:
educate
Token educate
Feature activation+0.003
Top resid features:
communities
Token communities
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.016
Top resid features:
lower
Token lower
Feature activation+0.006
Top resid features:
4
Token4
Feature activation+0.002
Top resid features:
th
Tokenth
Feature activation-0.003
Top resid features:
Place
Token Place
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
Player
Token Player
Feature activation+0.002
Top resid features:
B
Token B
Feature activation+5.107
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
True
Token True
Feature activation+0.001
Top resid features:
Draco
Token Draco
Feature activation+0.001
Top resid features:
Dinosaur
Token Dinosaur
Feature activation+0.000
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
they
Token they
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.030
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
re
Tokenre
Feature activation+0.004
Top resid features:
b
Token b
Feature activation+3.864
Top resid features:
uss
Tokenuss
Feature activation+0.008
Top resid features:
ing
Tokening
Feature activation+0.009
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
!
Token!
Feature activation-0.017
Top resid features:
Identity
Token Identity
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
Open
Token Open
Feature activation-0.011
Top resid features:
B
TokenB
Feature activation+4.785
Top resid features:
azaar
Tokenazaar
Feature activation+0.090
Top resid features:
logo
Token logo
Feature activation-0.003
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
recently
Token recently
Feature activation-0.000
Top resid features:
gone
Token gone
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
its
Token its
Feature activation-0.001
Top resid features:
competitor
Token competitor
Feature activation+0.002
Top resid features:
C
Token C
Feature activation-0.000
Top resid features:
bo
Tokenbo
Feature activation+4.853
Top resid features:
e
Tokene
Feature activation+0.023
Top resid features:
both
Token both
Feature activation+0.001
Top resid features:
launched
Token launched
Feature activation+0.000
Top resid features:
bitcoin
Token bitcoin
Feature activation-0.032
Top resid features:
futures
Token futures
Feature activation-0.001
Top resid features:
chief
Token chief
Feature activation+0.021
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
staff
Token staff
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Tony
Token Tony
Feature activation-0.004
Top resid features:
B
Token B
Feature activation+4.877
Top resid features:
lando
Tokenlando
Feature activation+0.108
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
she
Token she
Feature activation-0.002
Top resid features:
already
Token already
Feature activation-0.000
Top resid features:
had
Token had
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
work
Token work
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Volks
Token Volks
Feature activation-0.005
Top resid features:
b
Tokenb
Feature activation+3.296
Top resid features:
ü
Tokenü
Feature activation+0.072
Top resid features:
hn
Tokenhn
Feature activation-0.067
Top resid features:
en
Tokenen
Feature activation-0.012
Top resid features:
artists
Token artists
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
w
Token w
Feature activation+0.001
Top resid features:
weights
Token weights
Feature activation-0.004
Top resid features:
118
Token 118
Feature activation-0.054
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
2
Token2
Feature activation-0.013
Top resid features:
b
Token b
Feature activation+2.183
Top resid features:
pm
Tokenpm
Feature activation-0.013
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.002
Top resid features:
610
Token 610
Feature activation-0.006
Top resid features:
calories
Token calories
Feature activation-0.019
Top resid features:
/
Token/
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Image
TokenImage
Feature activation-0.003
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
b
Token b
Feature activation+2.018
Top resid features:
umble
Tokenumble
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
But
TokenBut
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
785
Token785
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:
the
Token the
Feature activation-0.001
Top resid features:
C
Token C
Feature activation-0.001
Top resid features:
bo
Tokenbo
Feature activation+2.412
Top resid features:
e
Tokene
Feature activation-0.016
Top resid features:
bitcoin
Token bitcoin
Feature activation-0.009
Top resid features:
futures
Token futures
Feature activation+0.007
Top resid features:
settled
Token settled
Feature activation+0.000
Top resid features:
up
Token up
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.04

Head 3: 0.03

Head 4: 0.04

Head 5: 0.02

Head 6: 0.05

Head 7: 0.51

Head 8: 0.02

Head 9: 0.04

Head 10: 0.09

Head 11: 0.05

Positive logits

Reincarnated2.52

WATCHED2.25

serv2.21

sel2.17

tel2.16

Sel2.09

lez2.07

ress2.07

Si2.06

UTERS2.06

]]2.06

Satellite2.06

());2.04

)2.02

iliary2.01

ilion2.00

>>1.98

essa1.98

"],1.97

tnc1.94

Negative logits

Byrne-3.12

BAR-3.11

bery-3.10

Byr-3.00

BA-2.94

Babe-2.90

Berk-2.87

Bj-2.76

Briggs-2.73

BB-2.72

BUR-2.69

Boyle-2.69

Biden-2.69

Brock-2.68

-2.64

Baldwin-2.63

BO-2.63

Kobe-2.62

BM-2.62

Brennan-2.59

INTERVAL 5.868 - 6.520
CONTAINS 0.000%

his
Token his
Feature activation+0.000
when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+5.238
or
Token or
Feature activation+6.520
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
August
Token August
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.453
(
Token(
Feature activation+6.193
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Se
Token Se
Feature activation+0.000
clusion
Tokenclusion
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
chest
Token chest
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
Photos
Token Photos
Feature activation+0.000
B
Token B
Feature activation+0.000
and
Token and
Feature activation+6.227
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
the
Token the
Feature activation+0.000
template
Token template
Feature activation+0.000

INTERVAL 5.216 - 5.868
CONTAINS 0.001%

County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
's
Token's
Feature activation+0.000
Office
Token Office
Feature activation+0.000
Photo
Token Photo
Feature activation+0.000
:
Token:
Feature activation+5.340
B
Token B
Feature activation+0.601
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
recently
Token recently
Feature activation+0.000
awoken
Token awoken
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
coma
Token coma
Feature activation+0.000
and
Token and
Feature activation+5.669
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
unsure
Token unsure
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+5.238
or
Token or
Feature activation+6.520
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
2
Token2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+5.825
C
Token C
Feature activation+0.000
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
conversation
Token conversation
Feature activation+0.000
;
Token;
Feature activation+0.000
(
Token (
Feature activation+5.687
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 4.564 - 5.216
CONTAINS 0.000%

land
Token land
Feature activation+0.000
base
Token base
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
/
Token/
Feature activation+5.049
B
TokenB
Feature activation+0.000
has
Token has
Feature activation+0.000
less
Token less
Feature activation+0.000
resources
Token resources
Feature activation+0.000
for
Token for
Feature activation+0.000
lower
Token lower
Feature activation+0.000
the
Token the
Feature activation+0.000
incidence
Token incidence
Feature activation+0.000
of
Token of
Feature activation+0.000
diseases
Token diseases
Feature activation+0.000
;
Token;
Feature activation+4.983
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
provide
Token provide
Feature activation+0.000
cur
Token cur
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+4.634
C
Token C
Feature activation+0.000
:
Token:
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.000

INTERVAL 3.912 - 4.564
CONTAINS 0.001%

,
Token,
Feature activation+0.000
300
Token300
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
C
Token C
Feature activation+3.973
ME
TokenME
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.000
was
Token was
Feature activation+0.000
near
Token near
Feature activation+0.000
2
Token 2
Feature activation+0.000
and
Token and
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+3.288
not
Token not
Feature activation+4.548
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.724
Image
TokenImage
Feature activation+0.000
:
Token:
Feature activation+4.002
b
Token b
Feature activation+1.483
umble
Tokenumble
Feature activation+0.533
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.637
Much
TokenMuch
Feature activation+0.000
"
Token "
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.000
Mr
Token Mr
Feature activation+0.972
.
Token.
Feature activation+4.341
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
the
Token the
Feature activation+0.000
Fight
Token Fight
Feature activation+0.000
w
Token w
Feature activation+0.000
weights
Token weights
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
144
Token 144
Feature activation+4.131
b
Token b
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
8
Token 8
Feature activation+0.000
51
Token51
Feature activation+0.000

INTERVAL 3.260 - 3.912
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.637
Much
TokenMuch
Feature activation+0.000
like
Token like
Feature activation+0.271
B
Token B
Feature activation+1.015
umble
Tokenumble
Feature activation+3.310
's
Token's
Feature activation+0.000
B
Token B
Feature activation+0.386
FF
TokenFF
Feature activation+1.003
feature
Token feature
Feature activation+0.000
,
Token,
Feature activation+4.197
w
Token w
Feature activation+0.000
/
Token/
Feature activation+0.000
o
Tokeno
Feature activation+0.000
weights
Token weights
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
168
Token 168
Feature activation+3.794
b
Token b
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
7
Token 7
Feature activation+0.000
64
Token64
Feature activation+0.000
.
Token.
Feature activation+0.430
As
TokenAs
Feature activation+0.396
far
Token far
Feature activation+0.000
as
Token as
Feature activation+0.000
control
Token control
Feature activation+0.000
,
Token,
Feature activation+3.626
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
b
Token b
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ubi
Tokenubi
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.253
,
Token,
Feature activation+3.335
Bur
Token Bur
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ese
Tokenese
Feature activation+0.000
:
Token:
Feature activation+0.000
l
Token l
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
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+3.288
not
Token not
Feature activation+4.548
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
now
Token now
Feature activation+0.000

INTERVAL 2.608 - 3.260
CONTAINS 0.002%

ü
Tokenü
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
n
Tokenn
Feature activation+0.000
von
Token von
Feature activation+0.000
18
Token 18
Feature activation+0.000
28
Token28
Feature activation+2.656
bis
Token bis
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
er
Token er
Feature activation+0.000
w
Tokenw
Feature activation+0.000
ä
Tokenä
Feature activation+0.000
its
Token its
Feature activation+0.000
dating
Token dating
Feature activation+0.000
and
Token and
Feature activation+0.000
friendship
Token friendship
Feature activation+0.000
platforms
Token platforms
Feature activation+0.000
,"
Token,"
Feature activation+3.042
reads
Token reads
Feature activation+3.126
an
Token an
Feature activation+0.000
official
Token official
Feature activation+0.000
B
Token B
Feature activation+1.027
umble
Tokenumble
Feature activation+2.159
dating
Token dating
Feature activation+0.000
and
Token and
Feature activation+0.000
friendship
Token friendship
Feature activation+0.000
platforms
Token platforms
Feature activation+0.000
,"
Token,"
Feature activation+3.042
reads
Token reads
Feature activation+3.126
an
Token an
Feature activation+0.000
official
Token official
Feature activation+0.000
B
Token B
Feature activation+1.027
umble
Tokenumble
Feature activation+2.159
statement
Token statement
Feature activation+0.000
"
Token "
Feature activation+0.000
complex
Tokencomplex
Feature activation+0.000
legal
Token legal
Feature activation+0.000
matters
Token matters
Feature activation+0.000
"
Token"
Feature activation+0.000
surrounding
Token surrounding
Feature activation+3.001
what
Token what
Feature activation+0.000
's
Token's
Feature activation+0.000
going
Token going
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.023
the
Token the
Feature activation+0.000
Bureau
Token Bureau
Feature activation+0.000
of
Token of
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
Statistics
Token Statistics
Feature activation+0.000
(
Token (
Feature activation+3.049
B
TokenB
Feature activation+0.000
JS
TokenJS
Feature activation+0.000
)
Token)
Feature activation+0.000
shows
Token shows
Feature activation+0.000
there
Token there
Feature activation+0.000

INTERVAL 1.956 - 2.608
CONTAINS 0.007%

an
Token an
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
competitive
Tokencompetitive
Feature activation+0.000
manner
Token manner
Feature activation+0.000
.
Token.
Feature activation+2.201
"
Token "
Feature activation+1.677
Open
TokenOpen
Feature activation+0.000
reach
Tokenreach
Feature activation+0.000
is
Token is
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
body
Token body
Feature activation+0.000
concealed
Token concealed
Feature activation+0.000
,
Token,
Feature activation+1.259
the
Token the
Feature activation+2.167
Otto
Token Otto
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
worm
Token worm
Feature activation+0.000
would
Token would
Feature activation+0.000
lur
Token lur
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+2.448
According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.864
admissions
Token admissions
Feature activation+0.000
made
Token made
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
doctors
Token doctors
Feature activation+0.000
who
Token who
Feature activation+0.000
examined
Token examined
Feature activation+2.245
him
Token him
Feature activation+0.000
(
Token (
Feature activation+0.000
n
Tokenn
Feature activation+0.000
aked
Tokenaked
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
blah
Token blah
Feature activation+0.000
-
Token-
Feature activation+1.098
bl
Tokenbl
Feature activation+0.031
ah
Tokenah
Feature activation+1.073
,
Token,
Feature activation+2.507
da
Token da
Feature activation+0.000
-
Token-
Feature activation+0.000
da
Tokenda
Feature activation+0.000
-
Token-
Feature activation+0.000
da
Tokenda
Feature activation+0.000

INTERVAL 1.304 - 1.956
CONTAINS 0.015%

emailed
Token emailed
Feature activation+0.000
to
Token to
Feature activation+0.000
local
Token local
Feature activation+0.000
party
Token party
Feature activation+0.000
members
Token members
Feature activation+0.000
,
Token,
Feature activation+1.589
Stevens
Token Stevens
Feature activation+0.000
said
Token said
Feature activation+0.000
Theresa
Token Theresa
Feature activation+0.000
May
Token May
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
George
Token George
Feature activation+0.000
Le
Token Le
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
,
Token,
Feature activation+0.000
Mark
Token Mark
Feature activation+1.476
Bram
Token Bram
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
,
Token,
Feature activation+0.000
Marc
Token Marc
Feature activation+0.000
Urban
Token Urban
Feature activation+0.000
it
Tokenit
Feature activation+0.357
Pan
Token Pan
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
S
Token S
Feature activation+0.000
DP
TokenDP
Feature activation+1.311
Feng
Token Feng
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
an
Tokenan
Feature activation+0.144
Workers
Token Workers
Feature activation+0.000
'
Token'
Feature activation+0.000
a
Token a
Feature activation+0.000
joint
Token joint
Feature activation+0.000
statement
Token statement
Feature activation+0.000
,
Token,
Feature activation+0.000
Bahrain
Token Bahrain
Feature activation+0.000
,
Token,
Feature activation+1.510
Egypt
Token Egypt
Feature activation+0.000
,
Token,
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
Arabia
Token Arabia
Feature activation+0.000
and
Token and
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
(
Token (
Feature activation+1.865
Beta
TokenBeta
Feature activation+0.000
9
Token 9
Feature activation+0.000
)
Token)
Feature activation+0.000
released
Token released
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.652 - 1.304
CONTAINS 0.050%

.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.000
Mr
Token Mr
Feature activation+0.972
.
Token.
Feature activation+4.341
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
considers
Token considers
Feature activation+0.000
surplus
Token surplus
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.700
Senate
Token Senate
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
yet
Token yet
Feature activation+0.000
taken
Token taken
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
billion
Token billion
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.679
MG
TokenMG
Feature activation+0.000
F
TokenF
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
time
Token time
Feature activation+0.000
will
Token will
Feature activation+0.000
work
Token work
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
for
Token for
Feature activation+0.958
harvesting
Token harvesting
Feature activation+0.421
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
m
Tokenm
Feature activation+0.000
leaning
Token leaning
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
more
Token more
Feature activation+0.000
with
Token with
Feature activation+0.766
Thur
Token Thur
Feature activation+0.000
man
Tokenman
Feature activation+0.000
than
Token than
Feature activation+0.455
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000

INTERVAL 0.000 - 0.652
CONTAINS 99.924%

Ċ
TokenĊ
Feature activation+0.000
Please
TokenPlease
Feature activation+0.000
visit
Token visit
Feature activation+0.000
the
Token the
Feature activation+0.000
Friends
Token Friends
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Tool
Token Tool
Feature activation+0.000
L
Token L
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
Library
Token Library
Feature activation+0.000
for
Token for
Feature activation+0.000
Cyber
Token Cyber
Feature activation+0.000
Intelligence
Token Intelligence
Feature activation+0.000
in
Token in
Feature activation+0.000
Lang
Token Lang
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
,
Token,
Feature activation+0.000
Vir
Token Vir
Feature activation+0.000
g
Tokeng
Feature activation+0.000
ina
Tokenina
Feature activation+0.000
[
Token [
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
13
Token 13
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
figured
Token figured
Feature activation+0.000
out
Token out
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
punch
Token punch
Feature activation+0.000
bus
Token bus
Feature activation+0.000
000
Token000
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
names
Token names
Feature activation+0.000
,
Token,
Feature activation+0.000
phone
Token phone
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
,
Token,
Feature activation+0.000
email
Token email
Feature activation+0.000
addresses
Token addresses
Feature activation+0.000
and
Token and
Feature activation+0.000
sending
Token sending
Feature activation+0.000
data
Token data
Feature activation+0.000
and
Token and
Feature activation+0.000
imagery
Token imagery
Feature activation+0.000
when
Token when
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
alert
Token alert
Feature activation+0.000
the
Token the
Feature activation+0.000
owner
Token owner
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 H10.7: (feature 14813)

TOP ACTIVATIONS
MAX = 6.093

condition
Token condition
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.032
What
TokenWhat
Feature activation+0.000
is
Token is
Feature activation+6.093
S
Token S
Feature activation+1.626
j
Tokenj
Feature activation+0.000
ö
Tokenö
Feature activation+0.000
gren
Tokengren
Feature activation+0.000
's
Token's
Feature activation+0.000
role
Tokenrole
Feature activation+0.000
==
Token ==
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.056
to
Tokento
Feature activation+0.000
_
Token_
Feature activation+5.626
s
Tokens
Feature activation+0.000
end
Token end
Feature activation+0.000
end
Token end
Feature activation+0.000
class
Token class
Feature activation+0.000
Person
Token Person
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
95
Token 95
Feature activation+0.000
MB
Token MB
Feature activation+0.000
/
Token /
Feature activation+5.363
s
Token s
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
a
Token a
Feature activation+0.002
line
Token line
Feature activation+0.000
of
Token of
Feature activation+0.000
S
Token S
Feature activation+0.000
+,
Token+,
Feature activation+4.954
M
Token M
Feature activation+0.000
+,
Token+,
Feature activation+1.122
L
Token L
Feature activation+0.000
+
Token+
Feature activation+0.197
:
Token:
Feature activation+0.048
S
TokenS
Feature activation+0.800
2
Token 2
Feature activation+0.000
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+4.940
graphene
Token graphene
Feature activation+0.000
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
imply
Token imply
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
talk
Token talk
Feature activation+0.000
given
Token given
Feature activation+0.000
by
Token by
Feature activation+0.000
Prof
Token Prof
Feature activation+0.175
.
Token.
Feature activation+4.531
Sark
Token Sark
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
rep
Token rep
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
pose
Tokenpose
Feature activation+4.364
the
Token the
Feature activation+0.000
features
Token features
Feature activation+0.000
for
Token for
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
because
Token because
Feature activation+3.311
38
Token38
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
ħ
Tokenħ
Feature activation+0.000
2
Token2
Feature activation+0.000
;
Token;
Feature activation+3.330
and
Token and
Feature activation+4.245
graphene
Token graphene
Feature activation+0.000
,
Token,
Feature activation+0.799
A
Token A
Feature activation+0.186
=
Token=
Feature activation+0.000
59
Token59
Feature activation+0.000
most
Token most
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Mr
Token Mr
Feature activation+0.193
.
Token.
Feature activation+4.084
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
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.580
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.747
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.869
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
any
Token any
Feature activation+0.000
big
Token big
Feature activation+0.000
fuss
Token fuss
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
,"
Token,"
Feature activation+3.792
he
Token he
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+0.922
s
Tokens
Feature activation+0.000
)
Token)
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
w
Token w
Feature activation+0.000
1982
Token 1982
Feature activation+0.000
(
Token (
Feature activation+3.765
s
Tokens
Feature activation+0.000
)
Token)
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.156
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.580
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.747
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.869
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
s
Token s
Feature activation+0.038
Os
TokenOs
Feature activation+0.120
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.156
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.580
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.747
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.869
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
,
Token,
Feature activation+0.000
S
Token S
Feature activation+0.000
only
Token only
Feature activation+0.000
and
Token and
Feature activation+3.458
the
Token the
Feature activation+0.000
graphene
Token graphene
Feature activation+0.000
p
Token p
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token ,
Feature activation+0.000
name
Token name
Feature activation+0.000
,
Token ,
Feature activation+0.000
passage
Token passage
Feature activation+0.000
,
Token ,
Feature activation+0.000
t
Token t
Feature activation+3.425
sv
Tokensv
Feature activation+0.000
FROM
Token FROM
Feature activation+0.000
tw
Token tw
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
,
Token ,
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
after
Token after
Feature activation+0.000
Mr
Token Mr
Feature activation+1.247
.
Token.
Feature activation+3.403
Sam
Token Sam
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ago
Tokenago
Feature activation+0.000
chi
Tokenchi
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
gers
Tokengers
Feature activation+0.000
moved
Token moved
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
February
Token February
Feature activation+0.000
and
Token and
Feature activation+3.385
has
Token has
Feature activation+0.000
since
Token since
Feature activation+0.000
spent
Token spent
Feature activation+0.000
time
Token time
Feature activation+0.000
with
Token with
Feature activation+0.000
for
Token for
Feature activation+0.000
espionage
Token espionage
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+3.344
ale
Tokenale
Feature activation+0.000
h
Tokenh
Feature activation+0.000
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.000
38
Token38
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
ħ
Tokenħ
Feature activation+0.000
2
Token2
Feature activation+0.000
;
Token;
Feature activation+3.330
and
Token and
Feature activation+4.245
graphene
Token graphene
Feature activation+0.000
,
Token,
Feature activation+0.799
A
Token A
Feature activation+0.186
=
Token=
Feature activation+0.000

Top DFA by src position
MAX = 6.627

withdrawal
Token withdrawal
Feature activation+0.001
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
diagnosis
Token diagnosis
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
S
Token S
Feature activation+6.627
Top resid features:
j
Tokenj
Feature activation-0.142
Top resid features:
ö
Tokenö
Feature activation-0.022
Top resid features:
gren
Tokengren
Feature activation+0.002
Top resid features:
's
Token's
Feature activation-0.009
Top resid features:
syndrome
Token syndrome
Feature activation+0.242
Top resid features:
=
Token =
Feature activation+0.002
Top resid features:
role
Token role
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
to
Tokento
Feature activation-0.007
Top resid features:
_
Token_
Feature activation-0.012
Top resid features:
s
Tokens
Feature activation+6.280
Top resid features:
end
Token end
Feature activation+0.001
Top resid features:
def
Token def
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
_
Token_
Feature activation-0.005
Top resid features:
role
Tokenrole
Feature activation-0.070
Top resid features:
up
Token up
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
110
Token 110
Feature activation-0.002
Top resid features:
MB
Token MB
Feature activation-0.005
Top resid features:
/
Token /
Feature activation-0.003
Top resid features:
s
Token s
Feature activation+6.021
Top resid features:
in
Token in
Feature activation+0.013
Top resid features:
write
Token write
Feature activation-0.048
Top resid features:
mode
Token mode
Feature activation-0.002
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.001
Top resid features:
up
Token up
Feature activation-0.005
Top resid features:
'm
Token'm
Feature activation-0.019
Top resid features:
thinking
Token thinking
Feature activation-0.039
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
line
Token line
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
S
Token S
Feature activation+3.654
Top resid features:
+,
Token+,
Feature activation-0.158
Top resid features:
M
Token M
Feature activation+0.000
Top resid features:
+,
Token+,
Feature activation+0.000
Top resid features:
L
Token L
Feature activation+0.000
Top resid features:
+
Token+
Feature activation+0.000
Top resid features:
intermediary
Token intermediary
Feature activation+0.000
Top resid features:
between
Token between
Feature activation-0.002
Top resid features:
Mo
Token Mo
Feature activation+0.103
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
S
Token S
Feature activation+3.358
Top resid features:
only
Token only
Feature activation+0.003
Top resid features:
nanop
Token nanop
Feature activation+0.016
Top resid features:
ores
Tokenores
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
talk
Token talk
Feature activation-0.001
Top resid features:
delivered
Token delivered
Feature activation+0.002
Top resid features:
by
Token by
Feature activation-0.011
Top resid features:
Prof
Token Prof
Feature activation-0.032
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Sark
Token Sark
Feature activation+5.232
Top resid features:
ar
Tokenar
Feature activation-0.003
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
August
Token August
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
we
Token we
Feature activation-0.003
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
actually
Token actually
Feature activation-0.003
Top resid features:
functions
Token functions
Feature activation-0.016
Top resid features:
built
Token built
Feature activation-0.012
Top resid features:
into
Token into
Feature activation-0.004
Top resid features:
SS
Token SS
Feature activation+4.669
Top resid features:
7
Token7
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
other
Token other
Feature activation-0.010
Top resid features:
purposes
Token purposes
Feature activation-0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.010
Top resid features:
42
Token42
Feature activation-0.003
Top resid features:
Ã
Token Ã
Feature activation+0.001
Top resid features:
ħ
Tokenħ
Feature activation-0.000
Top resid features:
2
Token2
Feature activation+0.001
Top resid features:
;
Token;
Feature activation+0.009
Top resid features:
S
Token S
Feature activation+4.606
Top resid features:
only
Token only
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
A
Token A
Feature activation+0.043
Top resid features:
=
Token=
Feature activation+0.001
Top resid features:
57
Token57
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-0.004
Top resid features:
Greg
Token Greg
Feature activation-0.016
Top resid features:
S
Token S
Feature activation+4.789
Top resid features:
ato
Tokenato
Feature activation+0.043
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
store
Token store
Feature activation+0.002
Top resid features:
manager
Token manager
Feature activation+0.002
Top resid features:
for
Token for
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
games
Token games
Feature activation-0.023
Top resid features:
s
Token s
Feature activation+0.327
Top resid features:
Os
TokenOs
Feature activation-0.011
Top resid features:
s
Token s
Feature activation+1.333
Top resid features:
Os
TokenOs
Feature activation-0.012
Top resid features:
s
Token s
Feature activation+1.214
Top resid features:
Os
TokenOs
Feature activation-0.015
Top resid features:
s
Token s
Feature activation+0.792
Top resid features:
Os
TokenOs
Feature activation-0.017
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
interview
Token interview
Feature activation-0.001
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
reporters
Token reporters
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
S
Token S
Feature activation+4.608
Top resid features:
otto
Tokenotto
Feature activation+0.049
Top resid features:
wondered
Token wondered
Feature activation-0.007
Top resid features:
why
Token why
Feature activation-0.008
Top resid features:
his
Token his
Feature activation-0.001
Top resid features:
comments
Token comments
Feature activation-0.003
Top resid features:
plot
Token plot
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
w
Token w
Feature activation-0.010
Top resid features:
2012
Token 2012
Feature activation-0.036
Top resid features:
(
Token (
Feature activation-0.010
Top resid features:
s
Tokens
Feature activation+4.534
Top resid features:
)
Token)
Feature activation+0.021
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.003
Top resid features:
w
Token w
Feature activation-0.026
Top resid features:
1982
Token 1982
Feature activation-0.041
Top resid features:
(
Token (
Feature activation-0.026
Top resid features:
for
Token for
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
games
Token games
Feature activation-0.025
Top resid features:
s
Token s
Feature activation+0.306
Top resid features:
Os
TokenOs
Feature activation-0.013
Top resid features:
s
Token s
Feature activation+1.407
Top resid features:
Os
TokenOs
Feature activation-0.014
Top resid features:
s
Token s
Feature activation+1.245
Top resid features:
Os
TokenOs
Feature activation-0.019
Top resid features:
s
Token s
Feature activation+0.799
Top resid features:
Os
TokenOs
Feature activation-0.021
Top resid features:
for
Token for
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
games
Token games
Feature activation-0.026
Top resid features:
s
Token s
Feature activation+0.296
Top resid features:
Os
TokenOs
Feature activation-0.014
Top resid features:
s
Token s
Feature activation+1.535
Top resid features:
Os
TokenOs
Feature activation-0.017
Top resid features:
s
Token s
Feature activation+1.337
Top resid features:
Os
TokenOs
Feature activation-0.022
Top resid features:
s
Token s
Feature activation+0.844
Top resid features:
Os
TokenOs
Feature activation-0.025
Top resid features:
followed
Token followed
Feature activation+0.002
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
mixed
Token mixed
Feature activation-0.170
Top resid features:
,
Token,
Feature activation-0.033
Top resid features:
S
Token S
Feature activation+4.124
Top resid features:
only
Token only
Feature activation+0.008
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
graphene
Token graphene
Feature activation+0.000
Top resid features:
p
Token p
Feature activation+0.000
Top resid features:
name
Token name
Feature activation-0.008
Top resid features:
,
Token ,
Feature activation-0.001
Top resid features:
passage
Token passage
Feature activation+0.006
Top resid features:
,
Token ,
Feature activation-0.000
Top resid features:
t
Token t
Feature activation-0.001
Top resid features:
sv
Tokensv
Feature activation+3.727
Top resid features:
FROM
Token FROM
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+0.013
Top resid features:
SELECT
Token SELECT
Feature activation+0.000
Top resid features:
cart
Token cart
Feature activation+0.001
Top resid features:
od
Tokenod
Feature activation+0.004
Top resid features:
musical
Token musical
Feature activation+0.005
Top resid features:
figures
Token figures
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Mam
Token Mam
Feature activation+0.022
Top resid features:
oru
Tokenoru
Feature activation+0.031
Top resid features:
Sam
Token Sam
Feature activation+3.853
Top resid features:
ur
Tokenur
Feature activation+0.001
Top resid features:
ago
Tokenago
Feature activation+0.082
Top resid features:
chi
Tokenchi
Feature activation+0.082
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
50
Token 50
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
believed
Token believed
Feature activation-0.018
Top resid features:
both
Token both
Feature activation-0.003
Top resid features:
Rodgers
Token Rodgers
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
Sak
Token Sak
Feature activation+3.934
Top resid features:
ho
Tokenho
Feature activation-0.016
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
rental
Token rental
Feature activation-0.014
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
espionage
Token espionage
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
S
TokenS
Feature activation+3.735
Top resid features:
ale
Tokenale
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
42
Token42
Feature activation-0.002
Top resid features:
Ã
Token Ã
Feature activation+0.011
Top resid features:
ħ
Tokenħ
Feature activation+0.000
Top resid features:
2
Token2
Feature activation+0.002
Top resid features:
;
Token;
Feature activation-0.002
Top resid features:
S
Token S
Feature activation+3.644
Top resid features:
only
Token only
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
A
Token A
Feature activation+0.044
Top resid features:
=
Token=
Feature activation+0.000
Top resid features:
57
Token57
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.03

Head 3: 0.03

Head 4: 0.04

Head 5: 0.02

Head 6: 0.05

Head 7: 0.51

Head 8: 0.03

Head 9: 0.03

Head 10: 0.12

Head 11: 0.05

Positive logits

abo2.56

ree2.53

ober2.44

obyl2.42

vironment2.30

annabin2.21

letal2.21

abortion2.21

jandro2.19

ronic2.19

ibal2.18

imon2.18

orescence2.14

obe2.13

abal2.10

itect2.09

gerald2.07

��2.06

bulldo2.05

ominium2.04

Negative logits

Sasha-3.04

Saunders-2.97

Samp-2.92

SS-2.92

Sag-2.87

SG-2.83

ISA-2.82

SAS-2.82

Santorum-2.74

ACS-2.71

Sav-2.70

Stevenson-2.65

SR-2.63

SS-2.61

Sina-2.60

Sans-2.59

Sass-2.58

Sa-2.56

Sok-2.51

NS-2.51

INTERVAL 5.484 - 6.093
CONTAINS 0.000%

condition
Token condition
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.032
What
TokenWhat
Feature activation+0.000
is
Token is
Feature activation+6.093
S
Token S
Feature activation+1.626
j
Tokenj
Feature activation+0.000
ö
Tokenö
Feature activation+0.000
gren
Tokengren
Feature activation+0.000
's
Token's
Feature activation+0.000
role
Tokenrole
Feature activation+0.000
==
Token ==
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.056
to
Tokento
Feature activation+0.000
_
Token_
Feature activation+5.626
s
Tokens
Feature activation+0.000
end
Token end
Feature activation+0.000
end
Token end
Feature activation+0.000
class
Token class
Feature activation+0.000
Person
Token Person
Feature activation+0.000

INTERVAL 4.875 - 5.484
CONTAINS 0.000%

âĢĵ
Token âĢĵ
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
95
Token 95
Feature activation+0.000
MB
Token MB
Feature activation+0.000
/
Token /
Feature activation+5.363
s
Token s
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
a
Token a
Feature activation+0.002
line
Token line
Feature activation+0.000
of
Token of
Feature activation+0.000
S
Token S
Feature activation+0.000
+,
Token+,
Feature activation+4.954
M
Token M
Feature activation+0.000
+,
Token+,
Feature activation+1.122
L
Token L
Feature activation+0.000
+
Token+
Feature activation+0.197
:
Token:
Feature activation+0.048
S
TokenS
Feature activation+0.800
2
Token 2
Feature activation+0.000
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+4.940
graphene
Token graphene
Feature activation+0.000
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
imply
Token imply
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 4.265 - 4.875
CONTAINS 0.000%

a
Token a
Feature activation+0.000
talk
Token talk
Feature activation+0.000
given
Token given
Feature activation+0.000
by
Token by
Feature activation+0.000
Prof
Token Prof
Feature activation+0.175
.
Token.
Feature activation+4.531
Sark
Token Sark
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
rep
Token rep
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
pose
Tokenpose
Feature activation+4.364
the
Token the
Feature activation+0.000
features
Token features
Feature activation+0.000
for
Token for
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
because
Token because
Feature activation+3.311

INTERVAL 3.656 - 4.265
CONTAINS 0.001%

most
Token most
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Mr
Token Mr
Feature activation+0.193
.
Token.
Feature activation+4.084
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
s
Tokens
Feature activation+0.000
)
Token)
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
w
Token w
Feature activation+0.000
1982
Token 1982
Feature activation+0.000
(
Token (
Feature activation+3.765
s
Tokens
Feature activation+0.000
)
Token)
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000
38
Token38
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
ħ
Tokenħ
Feature activation+0.000
2
Token2
Feature activation+0.000
;
Token;
Feature activation+3.330
and
Token and
Feature activation+4.245
graphene
Token graphene
Feature activation+0.000
,
Token,
Feature activation+0.799
A
Token A
Feature activation+0.186
=
Token=
Feature activation+0.000
59
Token59
Feature activation+0.000
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.580
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.747
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.869
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
any
Token any
Feature activation+0.000
big
Token big
Feature activation+0.000
fuss
Token fuss
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
,"
Token,"
Feature activation+3.792
he
Token he
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+0.922

INTERVAL 3.047 - 3.656
CONTAINS 0.001%

s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+0.000
s
Token s
Feature activation+0.038
Os
TokenOs
Feature activation+0.120
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.156
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.580
s
Token s
Feature activation+0.000
Os
TokenOs
Feature activation+3.747
s
Token s
Feature activation+0.000
for
Token for
Feature activation+0.000
espionage
Token espionage
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+3.344
ale
Tokenale
Feature activation+0.000
h
Tokenh
Feature activation+0.000
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
did
Token did
Feature activation+0.000
gers
Tokengers
Feature activation+0.000
moved
Token moved
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
February
Token February
Feature activation+0.000
and
Token and
Feature activation+3.385
has
Token has
Feature activation+0.000
since
Token since
Feature activation+0.000
spent
Token spent
Feature activation+0.000
time
Token time
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
finished
Token finished
Feature activation+0.000
product
Token product
Feature activation+0.000
yet
Token yet
Feature activation+0.000
,"
Token,"
Feature activation+3.155
said
Token said
Feature activation+3.131
Samp
Token Samp
Feature activation+0.000
son
Tokenson
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
and
Token and
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.222
Soc
TokenSoc
Feature activation+0.000
iety
Tokeniety
Feature activation+0.000
's
Token's
Feature activation+0.000
norms
Token norms
Feature activation+0.000
mirror
Token mirror
Feature activation+0.000

INTERVAL 2.437 - 3.047
CONTAINS 0.002%

The
TokenThe
Feature activation+0.000
word
Token word
Feature activation+0.000
sig
Token sig
Feature activation+0.000
uan
Tokenuan
Feature activation+0.000
aba
Tokenaba
Feature activation+0.000
or
Token or
Feature activation+2.566
s
Token s
Feature activation+0.559
ih
Tokenih
Feature activation+0.000
uan
Tokenuan
Feature activation+0.000
aba
Tokenaba
Feature activation+0.000
has
Token has
Feature activation+0.000
)
Token )
Feature activation+0.000
AS
Token AS
Feature activation+0.000
q
Token q
Feature activation+0.000
WHERE
Token WHERE
Feature activation+0.000
(
Token (
Feature activation+0.000
t
Token t
Feature activation+2.890
sv
Tokensv
Feature activation+0.170
@@
Token @@
Feature activation+0.000
q
Token q
Feature activation+0.000
)
Token )
Feature activation+0.000
)
Token )
Feature activation+0.000
Mus
TokenMus
Feature activation+0.000
st
Tokenst
Feature activation+0.000
s
Token s
Feature activation+0.000
say
Tokensay
Feature activation+0.000
s
Token s
Feature activation+0.566
something
Tokensomething
Feature activation+2.618
cru
Token cru
Feature activation+0.000
cc
Tokencc
Feature activation+0.000
ial
Tokenial
Feature activation+0.487
,"
Token,"
Feature activation+0.000
his
Token his
Feature activation+0.000
to
Token to
Feature activation+0.000
cell
Token cell
Feature activation+0.000
tower
Token tower
Feature activation+0.000
.
Token.
Feature activation+2.675
However
Token However
Feature activation+0.298
,
Token,
Feature activation+2.516
hackers
Token hackers
Feature activation+0.000
worked
Token worked
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
been
Token been
Feature activation+0.000
growing
Token growing
Feature activation+0.000
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+2.581
but
Token but
Feature activation+0.000
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

INTERVAL 1.828 - 2.437
CONTAINS 0.005%

him
Token him
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
.
Token.
Feature activation+0.169
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.531
S
TokenS
Feature activation+2.147
olis
Tokenolis
Feature activation+0.000
was
Token was
Feature activation+0.000
notified
Token notified
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
Trinity
Token Trinity
Feature activation+0.000
University
Token University
Feature activation+0.000
in
Token in
Feature activation+0.000
San
Token San
Feature activation+0.000
Antonio
Token Antonio
Feature activation+0.000
#
Token #
Feature activation+2.373
US
TokenUS
Feature activation+0.000
Av
TokenAv
Feature activation+0.000
M
TokenM
Feature activation+0.000
EX
TokenEX
Feature activation+0.000
pic
Token pic
Feature activation+0.000
know
Token know
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
pregnant
Token pregnant
Feature activation+0.000
.
Token.
Feature activation+2.206
Baylor
Token Baylor
Feature activation+0.000
informed
Token informed
Feature activation+1.578
Sil
Token Sil
Feature activation+0.000
er
Tokener
Feature activation+0.000
this
Token this
Feature activation+0.000
a
Token a
Feature activation+0.000
permit
Token permit
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
demonstration
Token demonstration
Feature activation+0.000
.
Token.
Feature activation+1.960
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.482
A
TokenA
Feature activation+0.000
sign
Token sign
Feature activation+0.000
on
Token on
Feature activation+0.000
7
Token 7
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
CV
TokenCV
Feature activation+1.964
SS
TokenSS
Feature activation+0.000
Vector
Token Vector
Feature activation+0.000
:
Token:
Feature activation+0.000
CV
Token CV
Feature activation+0.500
SS
TokenSS
Feature activation+0.000

INTERVAL 1.219 - 1.828
CONTAINS 0.013%

Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
define
Token define
Feature activation+0.000
(
Token (
Feature activation+0.000
has
Token has
Feature activation+0.027
-
Token-
Feature activation+1.456
sym
Tokensym
Feature activation+0.000
?
Token?
Feature activation+0.000
l
Token l
Feature activation+0.000
st
Tokenst
Feature activation+0.000
s
Token s
Feature activation+0.000
st
Tokenst
Feature activation+0.000
roy
Tokenroy
Feature activation+0.000
world
Token world
Feature activation+0.067
,
Token,
Feature activation+0.613
y
Token y
Feature activation+0.673
ess
Tokeness
Feature activation+1.307
,
Token,
Feature activation+0.418
but
Token but
Feature activation+0.776
world
Token world
Feature activation+0.778
iss
Token iss
Feature activation+0.290
inevitably
Token inevitably
Feature activation+0.000
.
Token.
Feature activation+0.000
Patient
Token Patient
Feature activation+0.000
EE
Token EE
Feature activation+0.000
555
Token555
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.312
s
Tokens
Feature activation+0.000
primary
Token primary
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000
is
Token is
Feature activation+0.000
sim
Token sim
Feature activation+0.000
which
Token which
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
racist
Token racist
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+1.248
sarc
Token sarc
Feature activation+0.000
asm
Tokenasm
Feature activation+0.000
,
Token,
Feature activation+0.000
Limbaugh
Token Limbaugh
Feature activation+0.000
was
Token was
Feature activation+0.000
just
Token just
Feature activation+0.000
off
Token off
Feature activation+0.000
side
Tokenside
Feature activation+0.000
.
Token.
Feature activation+0.785
Moments
Token Moments
Feature activation+0.000
later
Token later
Feature activation+1.449
the
Token the
Feature activation+0.000
striker
Token striker
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.609 - 1.219
CONTAINS 0.034%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.082
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.963
sustainable
Token sustainable
Feature activation+0.000
growth
Token growth
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
?
Token?
Feature activation+0.011
idden
Tokenidden
Feature activation+0.000
and
Token and
Feature activation+0.000
unc
Token unc
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
vocals
Token vocals
Feature activation+0.000
from
Token from
Feature activation+0.836
Jennifer
Token Jennifer
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
o
Tokeno
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.517
So
Token So
Feature activation+0.000
when
Token when
Feature activation+0.653
Horton
Token Horton
Feature activation+0.000
and
Token and
Feature activation+0.000
Daly
Token Daly
Feature activation+0.000
dug
Token dug
Feature activation+0.000
into
Token into
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
133
Token133
Feature activation+0.000
(
Token (
Feature activation+0.000
as
Tokenas
Feature activation+0.000
per
Token per
Feature activation+0.912
the
Token the
Feature activation+0.000
draft
Token draft
Feature activation+0.000
notification
Token notification
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
SN
Token SN
Feature activation+0.000
Ref
Token Ref
Feature activation+0.000
sd
Tokensd
Feature activation+0.000
al
Tokenal
Feature activation+0.000
,
Token,
Feature activation+0.903
the
Token the
Feature activation+0.000
object
Token object
Feature activation+0.000
was
Token was
Feature activation+0.000
discovered
Token discovered
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 0.609
CONTAINS 99.944%

from
Token from
Feature activation+0.000
dance
Token dance
Feature activation+0.000
hall
Tokenhall
Feature activation+0.000
star
Token star
Feature activation+0.000
Pop
Token Pop
Feature activation+0.000
ca
Tokenca
Feature activation+0.000
an
Tokenan
Feature activation+0.000
to
Token to
Feature activation+0.000
pop
Token pop
Feature activation+0.000
-
Token-
Feature activation+0.000
house
Tokenhouse
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
was
Token was
Feature activation+0.000
planning
Token planning
Feature activation+0.000
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
the
Token the
Feature activation+0.000
Greens
Token Greens
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
motion
Token motion
Feature activation+0.000
on
Token on
Feature activation+0.000
fi
Tokenfi
Feature activation+0.000
adventure
Token adventure
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
Me
Token Me
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
publishers
Token publishers
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
quantity
Token quantity
Feature activation+0.000
"
Token"
Feature activation+0.000
of
Token of
Feature activation+0.000
heroin
Token heroin
Feature activation+0.000
...
Token ...
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
and
Token and
Feature activation+0.000
drug
Token drug
Feature activation+0.000
not
Token not
Feature activation+0.000
operating
Token operating
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
areth
Tokenareth
Feature activation+0.000
Brick
Token Brick
Feature activation+0.000
man
Tokenman
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
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 H10.7: (feature 6139)

TOP ACTIVATIONS
MAX = 3.775

.[
Token.[
Feature activation+0.000
3
Token3
Feature activation+0.000
]
Token]
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+3.775
aur
Token aur
Feature activation+0.000
icular
Tokenicular
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
,
Token,
Feature activation+0.000
Lab
Token Lab
Feature activation+0.000
Association
Token Association
Feature activation+0.000
of
Token of
Feature activation+0.000
University
Token University
Feature activation+0.000
Prof
Token Prof
Feature activation+0.000
essors
Tokenessors
Feature activation+0.000
(
Token (
Feature activation+3.511
AA
TokenAA
Feature activation+0.000
UP
TokenUP
Feature activation+0.000
),
Token),
Feature activation+0.000
76
Token 76
Feature activation+0.000
percent
Token percent
Feature activation+0.000
offshore
Token offshore
Feature activation+0.000
.
Token.
Feature activation+0.000
Strong
Token Strong
Feature activation+0.000
-
Token-
Feature activation+0.000
sw
Tokensw
Feature activation+0.000
imming
Tokenimming
Feature activation+3.346
mur
Token mur
Feature activation+0.000
res
Tokenres
Feature activation+0.000
hunt
Token hunt
Feature activation+0.000
faster
Token faster
Feature activation+0.000
schooling
Token schooling
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
sol
Tokensol
Feature activation+0.000
ids
Tokenids
Feature activation+0.000
an
Token an
Feature activation+3.234
aer
Tokenaer
Feature activation+0.000
obic
Tokenobic
Feature activation+0.000
dig
Token dig
Feature activation+0.000
ester
Tokenester
Feature activation+0.000
that
Token that
Feature activation+0.000
C
TokenC
Feature activation+0.000
herry
Tokenherry
Feature activation+0.000
flu
Token flu
Feature activation+0.000
orescence
Tokenorescence
Feature activation+0.000
of
Token of
Feature activation+0.000
stri
Token stri
Feature activation+3.181
at
Tokenat
Feature activation+0.000
op
Tokenop
Feature activation+0.000
all
Tokenall
Feature activation+0.000
idal
Tokenidal
Feature activation+0.000
projection
Token projection
Feature activation+0.000
L
TokenL
Feature activation+0.000
/
Token/
Feature activation+0.498
AC
TokenAC
Feature activation+0.000
:
Token:
Feature activation+2.177
L
TokenL
Feature activation+0.006
/
Token/
Feature activation+3.121
PR
TokenPR
Feature activation+0.000
:
Token:
Feature activation+0.000
L
TokenL
Feature activation+0.000
/
Token/
Feature activation+0.000
UI
TokenUI
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.425
company
Token company
Feature activation+0.000
's
Token's
Feature activation+0.000
merger
Token merger
Feature activation+0.000
with
Token with
Feature activation+2.929
Blizzard
Token Blizzard
Feature activation+0.000
in
Token in
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
developed
Token developed
Feature activation+0.000
a
Token a
Feature activation+0.000
policy
Token policy
Feature activation+0.000
of
Token of
Feature activation+0.580
"
Token "
Feature activation+0.307
aggressive
Tokenaggressive
Feature activation+2.885
ass
Token ass
Feature activation+0.000
imilation
Tokenimilation
Feature activation+0.000
"
Token"
Feature activation+0.000
calling
Token calling
Feature activation+0.000
for
Token for
Feature activation+0.000
uster
Tokenuster
Feature activation+0.000
,
Token,
Feature activation+0.000
pay
Token pay
Feature activation+0.000
tribute
Token tribute
Feature activation+0.000
to
Token to
Feature activation+0.000
Sam
Token Sam
Feature activation+2.852
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.000
throw
Token throw
Feature activation+0.000
back
Tokenback
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Alternative
Token Alternative
Feature activation+0.000
for
Token for
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
(
Token (
Feature activation+2.820
Af
TokenAf
Feature activation+0.000
D
TokenD
Feature activation+0.000
)
Token)
Feature activation+0.000
party
Token party
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ru
Tokenru
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+2.796
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
,
Token,
Feature activation+0.000
Heath
Token Heath
Feature activation+0.000
had
Token had
Feature activation+0.000
aust
Token aust
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
,
Token,
Feature activation+2.531
wa
Token wa
Feature activation+0.000
,
Token,
Feature activation+2.719
vic
Token vic
Feature activation+0.000
,
Token,
Feature activation+1.992
t
Token t
Feature activation+0.000
as
Tokenas
Feature activation+0.000
,
Token,
Feature activation+1.830
In
Token In
Feature activation+0.000
an
Token an
Feature activation+0.000
included
Token included
Feature activation+0.000
comic
Token comic
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+2.706
Vampire
Token Vampire
Feature activation+0.000
lla
Tokenlla
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Guard
TokenGuard
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
whose
Token whose
Feature activation+0.000
name
Token name
Feature activation+0.000
contained
Token contained
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+0.000
As
Token As
Feature activation+2.705
at
Tokenat
Feature activation+0.000
ru
Tokenru
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
advised
Token advised
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.839
the
Token the
Feature activation+0.889
left
Token left
Feature activation+0.000
is
Token is
Feature activation+1.255
for
Token for
Feature activation+2.705
low
Token low
Feature activation+0.022
voltage
Token voltage
Feature activation+0.253
connections
Token connections
Feature activation+0.000
(
Token (
Feature activation+0.000
network
Tokennetwork
Feature activation+0.000
St
Token St
Feature activation+0.000
aves
Tokenaves
Feature activation+0.000
,
Token,
Feature activation+0.000
Axe
Token Axe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.701
H
TokenH
Feature activation+0.000
RC
TokenRC
Feature activation+0.000
:
Token:
Feature activation+0.000
Chest
Token Chest
Feature activation+0.000
,
Token,
Feature activation+0.000
determined
Token determined
Feature activation+0.000
by
Token by
Feature activation+0.515
the
Token the
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+2.665
a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
Canadian
TokenCanadian
Feature activation+0.000
news
Token news
Feature activation+0.000
passage
Token passage
Feature activation+0.000
,
Token ,
Feature activation+0.000
''
Token ''
Feature activation+0.000
)
Token )
Feature activation+0.000
),
Token),
Feature activation+0.000
'
Token '
Feature activation+2.601
D
TokenD
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
p
Tokenp
Feature activation+0.000
-
Token-
Feature activation+0.000
news
Tokennews
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
[
Token [
Feature activation+2.579
arch
Tokenarch
Feature activation+0.000
ived
Tokenived
Feature activation+0.000
].
Token].
Feature activation+0.000
The
Token The
Feature activation+0.000
articles
Token articles
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.000
things
Token things
Feature activation+0.000
that
Token that
Feature activation+0.000
make
Token make
Feature activation+2.573
Robinson
Token Robinson
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
books
Token books
Feature activation+0.000

Top DFA by src position
MAX = 4.113

chest
Token chest
Feature activation+0.014
Top resid features:
nut
Tokennut
Feature activation+0.001
Top resid features:
brown
Token brown
Feature activation+0.003
Top resid features:
F
Token F
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
aur
Token aur
Feature activation+4.113
Top resid features:
icular
Tokenicular
Feature activation+0.032
Top resid features:
ia
Tokenia
Feature activation+0.007
Top resid features:
.[
Token.[
Feature activation+0.001
Top resid features:
4
Token4
Feature activation-0.001
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
According
TokenAccording
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
American
Token American
Feature activation+0.192
Top resid features:
Association
Token Association
Feature activation+3.775
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
University
Token University
Feature activation-0.008
Top resid features:
Prof
Token Prof
Feature activation+0.024
Top resid features:
essors
Tokenessors
Feature activation-0.019
Top resid features:
(
Token (
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
same
Token same
Feature activation-0.000
Top resid features:
prey
Token prey
Feature activation-0.009
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
au
Token au
Feature activation+3.810
Top resid features:
ks
Tokenks
Feature activation+0.014
Top resid features:
tend
Token tend
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
feed
Token feed
Feature activation-0.003
Top resid features:
further
Token further
Feature activation-0.001
Top resid features:
Group
Token Group
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
integrate
Token integrate
Feature activation-0.002
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
aer
Tokenaer
Feature activation+3.445
Top resid features:
obic
Tokenobic
Feature activation+0.290
Top resid features:
digestion
Token digestion
Feature activation+0.007
Top resid features:
into
Token into
Feature activation+0.004
Top resid features:
its
Token its
Feature activation+0.001
Top resid features:
compost
Token compost
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
SP
Token SP
Feature activation+0.002
Top resid features:
-
Token-
Feature activation-0.031
Top resid features:
positive
Tokenpositive
Feature activation-0.002
Top resid features:
stri
Token stri
Feature activation+0.001
Top resid features:
aton
Tokenaton
Feature activation+3.509
Top resid features:
ig
Tokenig
Feature activation-0.003
Top resid features:
ral
Tokenral
Feature activation-0.002
Top resid features:
neurons
Token neurons
Feature activation+0.002
Top resid features:
(
Token (
Feature activation-0.000
Top resid features:
yellow
Tokenyellow
Feature activation-0.000
Top resid features:
/
Token/
Feature activation-0.001
Top resid features:
AV
TokenAV
Feature activation+0.264
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
L
TokenL
Feature activation-0.020
Top resid features:
/
Token/
Feature activation-0.003
Top resid features:
AC
TokenAC
Feature activation+3.321
Top resid features:
:
Token:
Feature activation+0.014
Top resid features:
L
TokenL
Feature activation-0.058
Top resid features:
/
Token/
Feature activation-0.004
Top resid features:
PR
TokenPR
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
ick
Tokenick
Feature activation+0.004
Top resid features:
started
Token started
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.001
Top resid features:
CEO
Token CEO
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
Activision
Token Activision
Feature activation+3.261
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
1991
Token 1991
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
he
Token he
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Policy
TokenPolicy
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
'
Token '
Feature activation-0.018
Top resid features:
aggressive
Tokenaggressive
Feature activation-0.000
Top resid features:
ass
Token ass
Feature activation+3.436
Top resid features:
imilation
Tokenimilation
Feature activation+0.045
Top resid features:
'
Token'
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
In
TokenIn
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
Sam
TokenSam
Feature activation-0.017
Top resid features:
Ard
Token Ard
Feature activation+3.299
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
terrific
Token terrific
Feature activation+0.008
Top resid features:
ambassador
Token ambassador
Feature activation-0.007
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
immigrant
Tokenimmigrant
Feature activation-0.005
Top resid features:
message
Token message
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Alternative
Token Alternative
Feature activation+3.174
Top resid features:
for
Token for
Feature activation+0.098
Top resid features:
Germany
Token Germany
Feature activation+0.010
Top resid features:
(
Token (
Feature activation+0.022
Top resid features:
Af
TokenAf
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.000
Top resid features:
than
Token than
Feature activation-0.001
Top resid features:
Heat
Token Heat
Feature activation+0.061
Top resid features:
hen
Tokenhen
Feature activation-0.015
Top resid features:
or
Token or
Feature activation+0.004
Top resid features:
As
Token As
Feature activation+0.005
Top resid features:
at
Tokenat
Feature activation+3.281
Top resid features:
ru
Tokenru
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
As
TokenAs
Feature activation-0.004
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
and
Tokenand
Feature activation+0.002
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
politics
Tokenpolitics
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
aust
Token aust
Feature activation+2.840
Top resid features:
ral
Tokenral
Feature activation+0.105
Top resid features:
ia
Tokenia
Feature activation+0.066
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
wa
Token wa
Feature activation+0.158
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
their
Token their
Feature activation-0.001
Top resid features:
daring
Token daring
Feature activation-0.009
Top resid features:
new
Token new
Feature activation+0.003
Top resid features:
line
Token line
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
Aurora
Token Aurora
Feature activation+3.242
Top resid features:
âĢ
TokenâĢ
Feature activation+0.057
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
marketing
Token marketing
Feature activation+0.009
Top resid features:
made
Token made
Feature activation-0.002
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
Heat
Token Heat
Feature activation+0.013
Top resid features:
hen
Tokenhen
Feature activation-0.034
Top resid features:
or
Token or
Feature activation+0.003
Top resid features:
As
Token As
Feature activation+0.012
Top resid features:
at
Tokenat
Feature activation+3.145
Top resid features:
ru
Tokenru
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
As
TokenAs
Feature activation-0.000
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
larger
Token larger
Feature activation-0.001
Top resid features:
one
Token one
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
AC
Token AC
Feature activation+3.145
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
smaller
Token smaller
Feature activation-0.002
Top resid features:
one
Token one
Feature activation-0.002
Top resid features:
on
Token on
Feature activation-0.005
Top resid features:
different
Token different
Feature activation+0.005
Top resid features:
parts
Token parts
Feature activation+0.003
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
AA
TokenAA
Feature activation+3.255
Top resid features:
:
Token:
Feature activation+0.002
Top resid features:
Helmet
Token Helmet
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
Should
Token Should
Feature activation+0.022
Top resid features:
er
Tokener
Feature activation+0.002
Top resid features:
parties
Token parties
Feature activation+0.049
Top resid features:
wishing
Token wishing
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
submit
Token submit
Feature activation+0.005
Top resid features:
that
Token that
Feature activation-0.003
Top resid features:
AJ
Token AJ
Feature activation+3.098
Top resid features:
E
TokenE
Feature activation+0.028
Top resid features:
should
Token should
Feature activation+0.006
Top resid features:
not
Token not
Feature activation+0.006
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
authorized
Token authorized
Feature activation+0.009
Top resid features:
,
Token ,
Feature activation+0.000
Top resid features:
''
Token ''
Feature activation+0.009
Top resid features:
)
Token )
Feature activation+0.008
Top resid features:
),
Token),
Feature activation-0.000
Top resid features:
'
Token '
Feature activation+0.014
Top resid features:
A
TokenA
Feature activation+3.027
Top resid features:
'
Token'
Feature activation+0.033
Top resid features:
)
Token )
Feature activation+0.010
Top resid features:
||
Token ||
Feature activation-0.003
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
weight
Tokenweight
Feature activation-0.001
Top resid features:
y
Tokeny
Feature activation+0.003
Top resid features:
ria
Tokenria
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
net
Tokennet
Feature activation-0.001
Top resid features:
[
Token [
Feature activation-0.000
Top resid features:
arch
Tokenarch
Feature activation+1.366
Top resid features:
ived
Tokenived
Feature activation+0.014
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
d
Token d
Feature activation-0.006
Top resid features:
p
Tokenp
Feature activation+0.001
Top resid features:
science
Token science
Feature activation-0.006
Top resid features:
fiction
Token fiction
Feature activation-0.002
Top resid features:
war
Token war
Feature activation-0.023
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Aurora
Token Aurora
Feature activation+3.358
Top resid features:
seems
Token seems
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.07

Head 2: 0.03

Head 3: 0.04

Head 4: 0.04

Head 5: 0.02

Head 6: 0.05

Head 7: 0.50

Head 8: 0.03

Head 9: 0.02

Head 10: 0.07

Head 11: 0.06

Positive logits

Ply2.81

symp2.48

kered2.20

merce2.19

kefeller2.16

ksh2.04

Wid2.00

)))1.96

nings1.96

dw1.95

lycer1.95

ply1.93

lesi1.91

Wrest1.90

pow1.89

EStreamFrame1.84

Winc1.83

sett1.83

println1.83

Puzzles1.82

Negative logits

Aura-3.15

Ara-3.05

Avatar-2.98

ABE-2.90

Alexander-2.78

Amazon-2.73

Archdemon-2.72

Alic-2.71

Amazon-2.70

Assassin-2.64

atar-2.61

ARC-2.61

Ak-2.56

Aqua-2.56

Adams-2.56

Atlas-2.52

AF-2.52

â-2.51

aura-2.50

Ali-2.50

INTERVAL 3.397 - 3.775
CONTAINS 0.000%

Association
Token Association
Feature activation+0.000
of
Token of
Feature activation+0.000
University
Token University
Feature activation+0.000
Prof
Token Prof
Feature activation+0.000
essors
Tokenessors
Feature activation+0.000
(
Token (
Feature activation+3.511
AA
TokenAA
Feature activation+0.000
UP
TokenUP
Feature activation+0.000
),
Token),
Feature activation+0.000
76
Token 76
Feature activation+0.000
percent
Token percent
Feature activation+0.000
.[
Token.[
Feature activation+0.000
3
Token3
Feature activation+0.000
]
Token]
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+3.775
aur
Token aur
Feature activation+0.000
icular
Tokenicular
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
,
Token,
Feature activation+0.000
Lab
Token Lab
Feature activation+0.000

INTERVAL 3.020 - 3.397
CONTAINS 0.001%

offshore
Token offshore
Feature activation+0.000
.
Token.
Feature activation+0.000
Strong
Token Strong
Feature activation+0.000
-
Token-
Feature activation+0.000
sw
Tokensw
Feature activation+0.000
imming
Tokenimming
Feature activation+3.346
mur
Token mur
Feature activation+0.000
res
Tokenres
Feature activation+0.000
hunt
Token hunt
Feature activation+0.000
faster
Token faster
Feature activation+0.000
schooling
Token schooling
Feature activation+0.000
L
TokenL
Feature activation+0.000
/
Token/
Feature activation+0.498
AC
TokenAC
Feature activation+0.000
:
Token:
Feature activation+2.177
L
TokenL
Feature activation+0.006
/
Token/
Feature activation+3.121
PR
TokenPR
Feature activation+0.000
:
Token:
Feature activation+0.000
L
TokenL
Feature activation+0.000
/
Token/
Feature activation+0.000
UI
TokenUI
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
sol
Tokensol
Feature activation+0.000
ids
Tokenids
Feature activation+0.000
an
Token an
Feature activation+3.234
aer
Tokenaer
Feature activation+0.000
obic
Tokenobic
Feature activation+0.000
dig
Token dig
Feature activation+0.000
ester
Tokenester
Feature activation+0.000
that
Token that
Feature activation+0.000
C
TokenC
Feature activation+0.000
herry
Tokenherry
Feature activation+0.000
flu
Token flu
Feature activation+0.000
orescence
Tokenorescence
Feature activation+0.000
of
Token of
Feature activation+0.000
stri
Token stri
Feature activation+3.181
at
Tokenat
Feature activation+0.000
op
Tokenop
Feature activation+0.000
all
Tokenall
Feature activation+0.000
idal
Tokenidal
Feature activation+0.000
projection
Token projection
Feature activation+0.000

INTERVAL 2.642 - 3.020
CONTAINS 0.001%

aust
Token aust
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
,
Token,
Feature activation+2.531
wa
Token wa
Feature activation+0.000
,
Token,
Feature activation+2.719
vic
Token vic
Feature activation+0.000
,
Token,
Feature activation+1.992
t
Token t
Feature activation+0.000
as
Tokenas
Feature activation+0.000
,
Token,
Feature activation+1.830
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.425
company
Token company
Feature activation+0.000
's
Token's
Feature activation+0.000
merger
Token merger
Feature activation+0.000
with
Token with
Feature activation+2.929
Blizzard
Token Blizzard
Feature activation+0.000
in
Token in
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
developed
Token developed
Feature activation+0.000
a
Token a
Feature activation+0.000
policy
Token policy
Feature activation+0.000
of
Token of
Feature activation+0.580
"
Token "
Feature activation+0.307
aggressive
Tokenaggressive
Feature activation+2.885
ass
Token ass
Feature activation+0.000
imilation
Tokenimilation
Feature activation+0.000
"
Token"
Feature activation+0.000
calling
Token calling
Feature activation+0.000
for
Token for
Feature activation+0.000
determined
Token determined
Feature activation+0.000
by
Token by
Feature activation+0.515
the
Token the
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+2.665
a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
Canadian
TokenCanadian
Feature activation+0.000
news
Token news
Feature activation+0.000
St
Token St
Feature activation+0.000
aves
Tokenaves
Feature activation+0.000
,
Token,
Feature activation+0.000
Axe
Token Axe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.701
H
TokenH
Feature activation+0.000
RC
TokenRC
Feature activation+0.000
:
Token:
Feature activation+0.000
Chest
Token Chest
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.265 - 2.642
CONTAINS 0.002%

passage
Token passage
Feature activation+0.000
,
Token ,
Feature activation+0.000
''
Token ''
Feature activation+0.000
)
Token )
Feature activation+0.000
),
Token),
Feature activation+0.000
'
Token '
Feature activation+2.601
D
TokenD
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
the
Token the
Feature activation+0.000
Caucasus
Token Caucasus
Feature activation+0.000
between
Token between
Feature activation+0.472
Armen
Token Armen
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
and
Token and
Feature activation+2.420
Azerbaijan
Token Azerbaijan
Feature activation+0.000
is
Tokenis
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
p
Tokenp
Feature activation+0.000
-
Token-
Feature activation+0.000
news
Tokennews
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
[
Token [
Feature activation+2.579
arch
Tokenarch
Feature activation+0.000
ived
Tokenived
Feature activation+0.000
].
Token].
Feature activation+0.000
The
Token The
Feature activation+0.000
articles
Token articles
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.795
a
Token a
Feature activation+0.111
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.422
B
TokenB
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
provided
Tokenprovided
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
accounting
Token accounting
Feature activation+0.000
and
Token and
Feature activation+2.298
marketing
Token marketing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mult
TokenMult
Feature activation+0.000

INTERVAL 1.887 - 2.265
CONTAINS 0.003%

belt
Token belt
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
National
Token National
Feature activation+1.011
Anthem
Token Anthem
Feature activation+0.000
at
Token at
Feature activation+1.892
Arlington
Token Arlington
Feature activation+0.000
like
Token like
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
G
Token G
Feature activation+0.021
SR
TokenSR
Feature activation+0.000
H
TokenH
Feature activation+0.000
and
Token and
Feature activation+0.000
physician
Token physician
Feature activation+0.000
-
Token-
Feature activation+1.910
ass
Tokenass
Feature activation+0.000
essed
Tokenessed
Feature activation+0.000
health
Token health
Feature activation+0.000
str
Token str
Feature activation+0.000
ata
Tokenata
Feature activation+0.000
published
Token published
Feature activation+0.000
complaints
Token complaints
Feature activation+0.000
about
Token about
Feature activation+0.000
many
Token many
Feature activation+0.000
anime
Token anime
Feature activation+0.150
,
Token,
Feature activation+1.974
and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
regular
Token regular
Feature activation+0.000
report
Token report
Feature activation+0.000
also
Token also
Feature activation+0.000
to
Token to
Feature activation+0.000
break
Token break
Feature activation+0.000
Mus
Token Mus
Feature activation+0.000
skin
Token skin
Feature activation+0.000
relative
Token relative
Feature activation+0.000
to
Token to
Feature activation+2.201
A
Token A
Feature activation+0.313
com
Tokencom
Feature activation+0.000
ys
Tokenys
Feature activation+0.000
skin
Token skin
Feature activation+0.000
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.000
news
Token news
Feature activation+0.000
of
Token of
Feature activation+1.749
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
of
Token of
Feature activation+1.926
Elena
Token Elena
Feature activation+0.000
Balt
Token Balt
Feature activation+0.000
acha
Tokenacha
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000

INTERVAL 1.510 - 1.887
CONTAINS 0.007%

ĥ
Tokenĥ
Feature activation+0.000
Ĺ
TokenĹ
Feature activation+0.000
á
Tokená
Feature activation+1.053
ĥ
Tokenĥ
Feature activation+0.000
£
Token£
Feature activation+0.000
á
Tokená
Feature activation+1.528
ĥ
Tokenĥ
Feature activation+0.000
ļ
Tokenļ
Feature activation+0.000
á
Tokená
Feature activation+1.616
ĥ
Tokenĥ
Feature activation+0.000
ĺ
Tokenĺ
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
=
Token=
Feature activation+0.000
\
Token\
Feature activation+1.609
alpha
Tokenalpha
Feature activation+0.000
^{
Token^{
Feature activation+0.000
2
Token2
Feature activation+0.000
^{
Token^{
Feature activation+0.000
k
Tokenk
Feature activation+0.000
Se
Token Se
Feature activation+0.000
gar
Tokengar
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
set
Token set
Feature activation+0.000
around
Token around
Feature activation+1.587
the
Token the
Feature activation+0.000
fictional
Token fictional
Feature activation+0.000
village
Token village
Feature activation+0.000
of
Token of
Feature activation+0.000
Swe
Token Swe
Feature activation+0.000
ĥ
Tokenĥ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
á
Token á
Feature activation+0.787
ĥ
Tokenĥ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
á
Tokená
Feature activation+1.626
ĥ
Tokenĥ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
á
Tokená
Feature activation+1.620
ĥ
Tokenĥ
Feature activation+0.000
IJ
TokenIJ
Feature activation+0.000
evaluation
Token evaluation
Feature activation+0.000
panel
Token panel
Feature activation+0.000
composed
Token composed
Feature activation+0.000
of
Token of
Feature activation+0.000
ESA
Token ESA
Feature activation+0.000
,
Token,
Feature activation+1.618
the
Token the
Feature activation+1.310
Raspberry
Token Raspberry
Feature activation+0.000
Pi
Token Pi
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.132 - 1.510
CONTAINS 0.017%

combine
Token combine
Feature activation+0.000
all
Token all
Feature activation+0.000
plans
Token plans
Feature activation+0.000
-
Token -
Feature activation+0.000
architectural
Token architectural
Feature activation+0.005
,
Token,
Feature activation+1.470
engineering
Token engineering
Feature activation+0.000
,
Token,
Feature activation+0.368
and
Token and
Feature activation+0.317
mechanical
Token mechanical
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.149
depression
Token depression
Feature activation+0.000
was
Token was
Feature activation+0.000
weaker
Token weaker
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+1.148
anxiety
Token anxiety
Feature activation+0.000
.
Token.
Feature activation+0.000
Given
Token Given
Feature activation+0.000
the
Token the
Feature activation+0.000
higher
Token higher
Feature activation+0.000
documenting
Token documenting
Feature activation+0.000
the
Token the
Feature activation+0.000
basis
Token basis
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
variable
Token variable
Feature activation+1.161
ann
Token ann
Feature activation+0.000
uity
Tokenuity
Feature activation+0.000
recommendations
Token recommendations
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
padded
Token padded
Feature activation+1.457
envelop
Token envelop
Feature activation+0.000
-
Token -
Feature activation+0.000
inside
Token inside
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.619
trolls
Token trolls
Feature activation+0.000
they
Token they
Feature activation+0.000
left
Token left
Feature activation+0.000
behind
Token behind
Feature activation+0.000
on
Token on
Feature activation+1.221
4
Token 4
Feature activation+0.000
chan
Tokenchan
Feature activation+0.000
have
Token have
Feature activation+0.000
seen
Token seen
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 0.755 - 1.132
CONTAINS 0.037%

beaten
Token beaten
Feature activation+0.000
down
Token down
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
.
Token.
Feature activation+0.795
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
amines
Tokenamines
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.343
being
Token being
Feature activation+0.847
capt
Token capt
Feature activation+0.000
agon
Tokenagon
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
official
Token official
Feature activation+0.000
website
Token website
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
registered
Token registered
Feature activation+0.000
in
Token in
Feature activation+0.874
the
Token the
Feature activation+0.139
Armenian
Token Armenian
Feature activation+0.000
script
Token script
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
).
Token).
Feature activation+0.000
After
Token After
Feature activation+0.000
the
Token the
Feature activation+0.336
visitation
Token visitation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.768
wise
Token wise
Feature activation+0.000
men
Token men
Feature activation+0.000
(
Token (
Feature activation+0.000
who
Tokenwho
Feature activation+0.000
surprisingly
Token surprisingly
Feature activation+0.000
keep
Token keep
Feature activation+0.000
patients
Token patients
Feature activation+0.000
safe
Token safe
Feature activation+0.000
from
Token from
Feature activation+0.000
aerial
Token aerial
Feature activation+0.000
and
Token and
Feature activation+1.052
artillery
Token artillery
Feature activation+0.000
bombardment
Token bombardment
Feature activation+0.000
by
Token by
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.377 - 0.755
CONTAINS 0.099%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
committee
Token committee
Feature activation+0.000
from
Token from
Feature activation+0.000
Alabama
Token Alabama
Feature activation+0.000
,
Token,
Feature activation+0.633
Jackie
Token Jackie
Feature activation+0.000
Curt
Token Curt
Feature activation+0.000
iss
Tokeniss
Feature activation+0.000
,
Token,
Feature activation+0.000
sought
Token sought
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
involving
Token involving
Feature activation+0.000
aval
Token aval
Feature activation+0.000
anches
Tokenanches
Feature activation+0.000
,
Token,
Feature activation+0.710
falls
Token falls
Feature activation+0.000
on
Token on
Feature activation+0.000
slippery
Token slippery
Feature activation+0.000
slopes
Token slopes
Feature activation+0.000
,
Token,
Feature activation+0.007
very
Token very
Feature activation+0.000
attractive
Token attractive
Feature activation+0.000
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
home
Token home
Feature activation+0.644
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MO
TokenMO
Feature activation+0.000
ON
TokenON
Feature activation+0.000
increase
Token increase
Feature activation+0.000
oil
Token oil
Feature activation+0.000
production
Token production
Feature activation+0.000
in
Token in
Feature activation+0.000
Alaska
Token Alaska
Feature activation+0.000
and
Token and
Feature activation+0.638
in
Token in
Feature activation+1.661
Western
Token Western
Feature activation+0.880
public
Token public
Feature activation+0.000
lands
Token lands
Feature activation+0.000
in
Token in
Feature activation+0.000
at
Token at
Feature activation+0.000
these
Token these
Feature activation+0.000
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.382
the
Token the
Feature activation+0.000
overall
Token overall
Feature activation+0.000
gest
Token gest
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.377
CONTAINS 99.834%

allow
Token allow
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.000
voters
Token voters
Feature activation+0.000
to
Token to
Feature activation+0.000
approve
Token approve
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
the
Token the
Feature activation+0.000
$
Token $
Feature activation+0.000
we
Token we
Feature activation+0.000
decided
Token decided
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
home
Token home
Feature activation+0.000
this
Token this
Feature activation+0.000
badly
Token badly
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
the
Token the
Feature activation+0.000
brand
Token brand
Feature activation+0.000
is
Token is
Feature activation+0.000
known
Token known
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
related
Tokenrelated
Feature activation+0.000
content
Token content
Feature activation+0.000
that
Token that
Feature activation+0.000
violated
Token violated
Feature activation+0.000
existing
Token existing
Feature activation+0.000
or
Token or
Feature activation+0.000
recently
Token recently
Feature activation+0.000
implemented
Token implemented
Feature activation+0.000
ads
Token ads
Feature activation+0.000
policies
Token policies
Feature activation+0.000
.
Token.
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
urate
Tokenurate
Feature activation+0.000
administration
Token administration
Feature activation+0.000
to
Token to
Feature activation+0.000
mothers
Token mothers
Feature activation+0.000
during
Token during
Feature activation+0.000
labor
Token labor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ir
Token Ir
Feature activation+0.000
respective
Tokenrespective
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H10.7: (feature 12536)

TOP ACTIVATIONS
MAX = 7.853

in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
collection
Token collection
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.853
f
Tokenf
Feature activation+0.751
ung
Tokenung
Feature activation+0.000
ible
Tokenible
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Falk
Token Falk
Feature activation+0.000
(@
Token (@
Feature activation+0.000
thereal
Tokenthereal
Feature activation+0.000
m
Tokenm
Feature activation+0.000
j
Tokenj
Feature activation+0.000
f
Tokenf
Feature activation+6.227
1
Token1
Feature activation+0.000
)
Token)
Feature activation+0.000
January
Token January
Feature activation+0.000
7
Token 7
Feature activation+0.000
,
Token,
Feature activation+0.000
really
Token really
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
praised
Token praised
Feature activation+0.000
about
Token about
Feature activation+5.774
fo
Token fo
Feature activation+0.000
obar
Tokenobar
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
000
Token000
Feature activation+0.000
VW
Token VW
Feature activation+0.000
engines
Token engines
Feature activation+0.000
fitted
Token fitted
Feature activation+0.000
with
Token with
Feature activation+0.000
"
Token "
Feature activation+5.083
def
Tokendef
Feature activation+0.000
eat
Tokeneat
Feature activation+0.000
devices
Token devices
Feature activation+0.000
"
Token"
Feature activation+0.000
were
Token were
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+1.253
,
Token,
Feature activation+4.805
its
Token its
Feature activation+0.000
functionality
Token functionality
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
further
Token further
Feature activation+0.000
to
Token to
Feature activation+0.000
email
Token email
Feature activation+0.000
us
Token us
Feature activation+0.000
at
Token at
Feature activation+0.000
mail
Token mail
Feature activation+0.000
@
Token@
Feature activation+4.138
f
Tokenf
Feature activation+1.415
ant
Tokenant
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
ories
Tokenories
Feature activation+0.000
podcast
Tokenpodcast
Feature activation+0.000
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Chain
TokenChain
Feature activation+0.000
of
Token of
Feature activation+4.096
F
Token F
Feature activation+0.270
ools
Tokenools
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000
F
TokenF
Feature activation+0.000
(
Token (
Feature activation+0.000
30
Token30
Feature activation+0.000
°
Token °
Feature activation+0.355
C
TokenC
Feature activation+0.000
),
Token),
Feature activation+4.038
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
hires
Token hires
Feature activation+0.124
Frenchman
Token Frenchman
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
84
Token 84
Feature activation+0.000
°
Token °
Feature activation+0.000
F
TokenF
Feature activation+0.000
(
Token (
Feature activation+0.529
29
Token29
Feature activation+1.855
°
Token °
Feature activation+3.426
C
TokenC
Feature activation+0.551
)
Token)
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
86
Token 86
Feature activation+0.000
1
Token 1
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
it
Token it
Feature activation+3.378
feels
Token feels
Feature activation+0.000
good
Token good
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
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+0.000
F
Token F
Feature activation+3.271
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
.
Token.
Feature activation+0.000
Nor
Token Nor
Feature activation+0.000
are
Token are
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Source
TokenSource
Feature activation+0.000
:
Token:
Feature activation+3.218
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
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.181
f
Token f
Feature activation+0.249
akes
Tokenakes
Feature activation+0.000
and
Token and
Feature activation+3.207
there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
e
Tokene
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
twitter
Token twitter
Feature activation+0.000
Image
Token Image
Feature activation+0.000
caption
Token caption
Feature activation+0.000
Mrs
Token Mrs
Feature activation+2.996
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Neill
TokenNeill
Feature activation+0.000
's
Token's
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
open
Token open
Feature activation+0.000
source
Token source
Feature activation+0.000
with
Token with
Feature activation+0.000
free
Token free
Feature activation+0.000
.
Token.
Feature activation+0.000
F
Token F
Feature activation+2.970
SF
TokenSF
Feature activation+0.000
's
Token's
Feature activation+0.000
definition
Token definition
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
in
Token in
Feature activation+0.000
1997
Token 1997
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
twenty
Token twenty
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+2.939
the
Token the
Feature activation+0.000
initial
Token initial
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
centre
Token centre
Feature activation+0.000
in
Token in
Feature activation+0.000
North
Token North
Feature activation+2.913
Fr
Token Fr
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
for
Token for
Feature activation+0.000
which
Token which
Feature activation+0.000
de
Token de
Feature activation+0.000
ac
Token ac
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
s
Token s
Feature activation+0.000
Ä
TokenÄ
Feature activation+0.000
ĥ
Tokenĥ
Feature activation+2.893
exist
Token exist
Feature activation+0.000
e
Tokene
Feature activation+0.000
o
Token o
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ŀ
Tokenŀ
Feature activation+0.000
Over
TokenOver
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
28
Token 28
Feature activation+0.000
years
Token years
Feature activation+1.465
,
Token,
Feature activation+2.886
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
go
Token go
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
out
Token out
Feature activation+0.000
soon
Token soon
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+2.832
aber
Tokenaber
Feature activation+0.000
told
Token told
Feature activation+0.000
us
Token us
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000

Top DFA by src position
MAX = 9.261

Ċ
TokenĊ
Feature activation-0.004
Top resid features:
What
TokenWhat
Feature activation-0.011
Top resid features:
does
Token does
Feature activation-0.009
Top resid features:
âĢ
Token âĢ
Feature activation-0.028
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
f
Tokenf
Feature activation+9.261
Top resid features:
ung
Tokenung
Feature activation+0.059
Top resid features:
ible
Tokenible
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.014
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
mean
Token mean
Feature activation+0.000
Top resid features:
Falk
Token Falk
Feature activation+0.082
Top resid features:
(@
Token (@
Feature activation+0.006
Top resid features:
thereal
Tokenthereal
Feature activation-0.004
Top resid features:
m
Tokenm
Feature activation+0.010
Top resid features:
j
Tokenj
Feature activation+0.013
Top resid features:
f
Tokenf
Feature activation+6.897
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.002
Top resid features:
64
Token 64
Feature activation-0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
bit
Tokenbit
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Fo
Token Fo
Feature activation+6.436
Top resid features:
obar
Tokenobar
Feature activation+0.013
Top resid features:
2000
Token2000
Feature activation+0.075
Top resid features:
supports
Token supports
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
majority
Token majority
Feature activation-0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
fitted
Token fitted
Feature activation+0.003
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
"
Token "
Feature activation-0.003
Top resid features:
def
Tokendef
Feature activation+5.490
Top resid features:
eat
Tokeneat
Feature activation+0.375
Top resid features:
devices
Token devices
Feature activation-0.013
Top resid features:
"
Token"
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
or
Token or
Feature activation+0.001
Top resid features:
64
Token 64
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
bit
Tokenbit
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Fo
Token Fo
Feature activation+5.476
Top resid features:
obar
Tokenobar
Feature activation+0.037
Top resid features:
2000
Token2000
Feature activation+0.073
Top resid features:
supports
Token supports
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
majority
Token majority
Feature activation-0.002
Top resid features:
website
Token website
Feature activation-0.001
Top resid features:
https
Token https
Feature activation-0.001
Top resid features:
://
Token://
Feature activation+0.001
Top resid features:
www
Tokenwww
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
f
Tokenf
Feature activation+2.853
Top resid features:
ant
Tokenant
Feature activation+0.038
Top resid features:
he
Tokenhe
Feature activation-0.011
Top resid features:
ories
Tokenories
Feature activation+0.012
Top resid features:
podcast
Tokenpodcast
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
Chain
TokenChain
Feature activation+0.006
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
F
Token F
Feature activation+4.359
Top resid features:
ools
Tokenools
Feature activation+0.468
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
built
Token built
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ph
TokenPh
Feature activation-0.029
Top resid features:
ile
Tokenile
Feature activation+0.003
Top resid features:
as
Tokenas
Feature activation-0.025
Top resid features:
F
Token F
Feature activation+2.739
Top resid features:
ogg
Tokenogg
Feature activation-0.025
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
a
Token a
Feature activation-0.015
Top resid features:
rich
Token rich
Feature activation-0.007
Top resid features:
British
Token British
Feature activation+0.004
Top resid features:
shaving
Token shaving
Feature activation+0.001
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.028
Top resid features:
84
Token 84
Feature activation+0.009
Top resid features:
°
Token °
Feature activation+0.013
Top resid features:
F
TokenF
Feature activation+4.050
Top resid features:
(
Token (
Feature activation+0.031
Top resid features:
29
Token29
Feature activation+0.024
Top resid features:
°
Token °
Feature activation+0.007
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.001
Top resid features:
D
TokenD
Feature activation-0.004
Top resid features:
ang
Tokenang
Feature activation-0.013
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
it
Token it
Feature activation-0.007
Top resid features:
Fe
Token Fe
Feature activation+3.803
Top resid features:
els
Tokenels
Feature activation+0.334
Top resid features:
Good
Token Good
Feature activation-0.070
Top resid features:
to
Token to
Feature activation+0.056
Top resid features:
Be
Token Be
Feature activation+0.004
Top resid features:
a
Token a
Feature activation-0.003
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-0.000
Top resid features:
about
Token about
Feature activation-0.002
Top resid features:
F
Token F
Feature activation+0.512
Top resid features:
of
Tokenof
Feature activation+3.522
Top resid features:
ana
Tokenana
Feature activation-0.100
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.030
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
case
Token case
Feature activation-0.000
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-0.000
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
F
Token F
Feature activation+2.845
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
lux
Tokenlux
Feature activation+0.043
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.007
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
lot
Token lot
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.016
Top resid features:
f
Token f
Feature activation+2.205
Top resid features:
akes
Tokenakes
Feature activation+0.288
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.002
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
critic
Token critic
Feature activation+0.007
Top resid features:
ising
Tokenising
Feature activation+0.005
Top resid features:
Mrs
Token Mrs
Feature activation+0.013
Top resid features:
Foster
Token Foster
Feature activation+3.679
Top resid features:
over
Token over
Feature activation-0.001
Top resid features:
social
Token social
Feature activation-0.001
Top resid features:
media
Token media
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Free
Token Free
Feature activation+0.072
Top resid features:
Software
Token Software
Feature activation-0.052
Top resid features:
Foundation
Token Foundation
Feature activation+0.049
Top resid features:
(
Token (
Feature activation+0.006
Top resid features:
FS
TokenFS
Feature activation+0.533
Top resid features:
F
TokenF
Feature activation+2.131
Top resid features:
)'
Token)'
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
official
Token official
Feature activation-0.006
Top resid features:
four
Token four
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.093
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
In
TokenIn
Feature activation+0.007
Top resid features:
late
Token late
Feature activation+0.003
Top resid features:
1989
Token 1989
Feature activation+0.002
Top resid features:
Fin
Token Fin
Feature activation+3.430
Top resid features:
ial
Tokenial
Feature activation+0.044
Top resid features:
's
Token's
Feature activation+0.010
Top resid features:
investors
Token investors
Feature activation-0.000
Top resid features:
finally
Token finally
Feature activation-0.000
Top resid features:
cut
Token cut
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.026
Top resid features:
rest
Token rest
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
mainland
Token mainland
Feature activation-0.075
Top resid features:
North
Token North
Feature activation-0.105
Top resid features:
Fr
Token Fr
Feature activation+3.881
Top resid features:
is
Tokenis
Feature activation-0.030
Top resid features:
ia
Tokenia
Feature activation-0.048
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
Low
Token Low
Feature activation-0.029
Top resid features:
c
Token c
Feature activation+0.007
Top resid features:
ine
Tokenine
Feature activation-0.003
Top resid features:
s
Token s
Feature activation-0.007
Top resid features:
Ä
TokenÄ
Feature activation+0.002
Top resid features:
ĥ
Tokenĥ
Feature activation-0.003
Top resid features:
f
Token f
Feature activation+2.803
Top resid features:
ie
Tokenie
Feature activation+0.012
Top resid features:
cel
Token cel
Feature activation-0.023
Top resid features:
m
Token m
Feature activation+0.005
Top resid features:
ai
Tokenai
Feature activation-0.001
Top resid features:
t
Token t
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
possible
Token possible
Feature activation-0.001
Top resid features:
spot
Token spot
Feature activation-0.001
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
F
Token F
Feature activation+2.006
Top resid features:
enn
Tokenenn
Feature activation+0.013
Top resid features:
ig
Tokenig
Feature activation+0.019
Top resid features:
if
Token if
Feature activation-0.000
Top resid features:
he
Token he
Feature activation-0.003
Top resid features:
decides
Token decides
Feature activation-0.000
Top resid features:
out
Token out
Feature activation-0.004
Top resid features:
soon
Token soon
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
F
TokenF
Feature activation+1.576
Top resid features:
aber
Tokenaber
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
following
Token following
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.07

Head 2: 0.04

Head 3: 0.03

Head 4: 0.03

Head 5: 0.02

Head 6: 0.05

Head 7: 0.50

Head 8: 0.03

Head 9: 0.03

Head 10: 0.10

Head 11: 0.04

Positive logits

odus2.49

Song2.49

oenix2.48

osite2.44

rame2.38

aux2.32

ioxide2.32

Raven2.31

Siege2.19

Queue2.17

Tracks2.17

ram2.17

Maps2.16

Seahawks2.15

oda2.15

rix2.14

Kore2.13

Raven2.11

ivan2.10

oxide2.10

Negative logits

TF-3.01

EF-2.84

Friedman-2.77

FM-2.66

fu-2.65

Fi-2.63

INF-2.62

LF-2.59

FA-2.56

FP-2.55

Farrell-2.55

FUN-2.54

NF-2.50

FI-2.49

Finn-2.48

Pf-2.47

NF-2.42

fisher-2.41

fi-2.41

FT-2.41

INTERVAL 7.068 - 7.853
CONTAINS 0.000%

in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
collection
Token collection
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.853
f
Tokenf
Feature activation+0.751
ung
Tokenung
Feature activation+0.000
ible
Tokenible
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 6.283 - 7.068
CONTAINS 0.000%

INTERVAL 5.497 - 6.283
CONTAINS 0.000%

really
Token really
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
praised
Token praised
Feature activation+0.000
about
Token about
Feature activation+5.774
fo
Token fo
Feature activation+0.000
obar
Tokenobar
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
Falk
Token Falk
Feature activation+0.000
(@
Token (@
Feature activation+0.000
thereal
Tokenthereal
Feature activation+0.000
m
Tokenm
Feature activation+0.000
j
Tokenj
Feature activation+0.000
f
Tokenf
Feature activation+6.227
1
Token1
Feature activation+0.000
)
Token)
Feature activation+0.000
January
Token January
Feature activation+0.000
7
Token 7
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 4.712 - 5.497
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+1.253
,
Token,
Feature activation+4.805
its
Token its
Feature activation+0.000
functionality
Token functionality
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
further
Token further
Feature activation+0.000
000
Token000
Feature activation+0.000
VW
Token VW
Feature activation+0.000
engines
Token engines
Feature activation+0.000
fitted
Token fitted
Feature activation+0.000
with
Token with
Feature activation+0.000
"
Token "
Feature activation+5.083
def
Tokendef
Feature activation+0.000
eat
Tokeneat
Feature activation+0.000
devices
Token devices
Feature activation+0.000
"
Token"
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 3.927 - 4.712
CONTAINS 0.000%

F
TokenF
Feature activation+0.000
(
Token (
Feature activation+0.000
30
Token30
Feature activation+0.000
°
Token °
Feature activation+0.355
C
TokenC
Feature activation+0.000
),
Token),
Feature activation+4.038
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
hires
Token hires
Feature activation+0.124
Frenchman
Token Frenchman
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
to
Token to
Feature activation+0.000
email
Token email
Feature activation+0.000
us
Token us
Feature activation+0.000
at
Token at
Feature activation+0.000
mail
Token mail
Feature activation+0.000
@
Token@
Feature activation+4.138
f
Tokenf
Feature activation+1.415
ant
Tokenant
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
ories
Tokenories
Feature activation+0.000
podcast
Tokenpodcast
Feature activation+0.000
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Chain
TokenChain
Feature activation+0.000
of
Token of
Feature activation+4.096
F
Token F
Feature activation+0.270
ools
Tokenools
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 3.141 - 3.927
CONTAINS 0.001%

1
Token 1
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
it
Token it
Feature activation+3.378
feels
Token feels
Feature activation+0.000
good
Token good
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.181
f
Token f
Feature activation+0.249
akes
Tokenakes
Feature activation+0.000
and
Token and
Feature activation+3.207
there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
84
Token 84
Feature activation+0.000
°
Token °
Feature activation+0.000
F
TokenF
Feature activation+0.000
(
Token (
Feature activation+0.529
29
Token29
Feature activation+1.855
°
Token °
Feature activation+3.426
C
TokenC
Feature activation+0.551
)
Token)
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
86
Token 86
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Source
TokenSource
Feature activation+0.000
:
Token:
Feature activation+3.218
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
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+0.000
F
Token F
Feature activation+3.271
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
.
Token.
Feature activation+0.000
Nor
Token Nor
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 2.356 - 3.141
CONTAINS 0.003%

-
Token-
Feature activation+0.000
thread
Tokenthread
Feature activation+0.000
design
Token design
Feature activation+0.000
.
Token.
Feature activation+0.000
W
Token W
Feature activation+0.366
CC
TokenCC
Feature activation+2.727
F
TokenF
Feature activation+0.000
tech
Tokentech
Feature activation+0.000
also
Token also
Feature activation+0.000
believes
Token believes
Feature activation+0.000
there
Token there
Feature activation+0.000
135
Token 135
Feature activation+0.000
degrees
Token degrees
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
16
Token 16
Feature activation+0.000
MP
Token MP
Feature activation+2.727
f
Token f
Feature activation+0.000
/
Token/
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+1.025
its
Token its
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
budget
Tokenbudget
Feature activation+0.000
submission
Token submission
Feature activation+0.000
Sinn
Token Sinn
Feature activation+2.710
F
Token F
Feature activation+0.000
é
Tokené
Feature activation+0.000
in
Tokenin
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
open
Token open
Feature activation+0.000
source
Token source
Feature activation+0.000
with
Token with
Feature activation+0.000
free
Token free
Feature activation+0.000
.
Token.
Feature activation+0.000
F
Token F
Feature activation+2.970
SF
TokenSF
Feature activation+0.000
's
Token's
Feature activation+0.000
definition
Token definition
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
de
Token de
Feature activation+0.000
ac
Token ac
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
s
Token s
Feature activation+0.000
Ä
TokenÄ
Feature activation+0.000
ĥ
Tokenĥ
Feature activation+2.893
exist
Token exist
Feature activation+0.000
e
Tokene
Feature activation+0.000
o
Token o
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ŀ
Tokenŀ
Feature activation+0.000

INTERVAL 1.571 - 2.356
CONTAINS 0.006%

William
Token William
Feature activation+0.000
Elf
Token Elf
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
Le
Token Le
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
established
Token established
Feature activation+1.919
the
Token the
Feature activation+0.500
genus
Token genus
Feature activation+0.000
Lab
Token Lab
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
in
Token in
Feature activation+0.000
new
Token new
Feature activation+0.000
Cu
Token Cu
Feature activation+0.000
pert
Tokenpert
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
.
Token.
Feature activation+2.106
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
her
Token her
Feature activation+0.000
mini
Token mini
Feature activation+0.000
-
Token-
Feature activation+0.000
me
Tokenme
Feature activation+0.000
Fiorina
Token Fiorina
Feature activation+0.000
and
Token and
Feature activation+1.673
huge
Token huge
Feature activation+0.000
amounts
Token amounts
Feature activation+0.000
of
Token of
Feature activation+0.000
secret
Token secret
Feature activation+0.000
cash
Token cash
Feature activation+0.000
ests
Tokenests
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
huge
Token huge
Feature activation+0.000
beer
Token beer
Feature activation+2.036
events
Token events
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
that
Token that
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
FDA
Token FDA
Feature activation+0.000
and
Token and
Feature activation+1.301
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+1.905
HC
Token HC
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
house
Token house
Feature activation+0.000

INTERVAL 0.785 - 1.571
CONTAINS 0.021%

(
Token (
Feature activation+0.000
approved
Tokenapproved
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
FDA
Token FDA
Feature activation+0.000
and
Token and
Feature activation+1.301
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+1.905
HC
Token HC
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
entire
Token entire
Feature activation+0.109
endeavor
Token endeavor
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.796
the
Token the
Feature activation+0.000
F
Token F
Feature activation+1.043
TR
TokenTR
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
between
Token between
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
and
Token and
Feature activation+0.000
days
Token days
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
diet
Token diet
Feature activation+0.000
low
Token low
Feature activation+0.000
in
Token in
Feature activation+1.424
F
Token F
Feature activation+0.600
OD
TokenOD
Feature activation+0.000
MAP
TokenMAP
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
around
Token around
Feature activation+0.000
with
Token with
Feature activation+0.000
jumping
Token jumping
Feature activation+0.000
between
Token between
Feature activation+0.000
ones
Token ones
Feature activation+0.000
,
Token,
Feature activation+0.856
tw
Token tw
Feature activation+0.000
os
Tokenos
Feature activation+0.000
,
Token,
Feature activation+0.620
th
Token th
Feature activation+0.000
rees
Tokenrees
Feature activation+0.000
suit
Token suit
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+0.000
,
Token,
Feature activation+0.000
buy
Token buy
Feature activation+0.000
some
Token some
Feature activation+0.997
foam
Token foam
Feature activation+0.000
bats
Token bats
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
your
Token your
Feature activation+0.000

INTERVAL 0.000 - 0.785
CONTAINS 99.968%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
weight
Token weight
Feature activation+0.000
off
Token off
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
Y
Token Y
Feature activation+0.000
ush
Tokenush
Feature activation+0.000
chenko
Tokenchenko
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
like
Token like
Feature activation+0.000
Yanukovych
Token Yanukovych
Feature activation+0.000
(
Token (
Feature activation+0.000
except
Tokenexcept
Feature activation+0.000
custom
Token custom
Feature activation+0.000
wra
Token wra
Feature activation+0.000
ppers
Tokenppers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Latest
TokenLatest
Feature activation+0.000
version
Token version
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Version
TokenVersion
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
merchandise
Token merchandise
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
shirts
Token shirts
Feature activation+0.000
,
Token,
Feature activation+0.000
created
Token created
Feature activation+0.000
by
Token by
Feature activation+0.000
K
Token K
Feature activation+0.000
A
TokenA
Feature activation+0.000
have
Token have
Feature activation+0.000
grown
Token grown
Feature activation+0.000
up
Token up
Feature activation+0.000
since
Token since
Feature activation+0.000
a
Token a
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.-
Token.-
Feature activation+0.000
led
Tokenled
Feature activation+0.000
campaign
Token campaign
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 H10.7: (feature 12792)

TOP ACTIVATIONS
MAX = 6.360

Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ospital
Tokenospital
Feature activation+0.088
X
Token X
Feature activation+0.000
-
Token -
Feature activation+0.000
(
Token (
Feature activation+6.360
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+0.000
Places
Token Places
Feature activation+0.000
-
Token -
Feature activation+0.000
super
Tokensuper
Feature activation+0.000
vised
Tokenvised
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.249
(
Token(
Feature activation+6.059
d
Tokend
Feature activation+0.000
)
Token)
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+0.000
's
Token's
Feature activation+0.000
statue
Token statue
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.131
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+5.786
A
Token A
Feature activation+0.000
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Wind
Token Wind
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
.
Token.
Feature activation+0.000
art
Token art
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token 5
Feature activation+5.706
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
p
Tokenp
Feature activation+0.000
.;
Token.;
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ospital
Tokenospital
Feature activation+0.000
X
Token X
Feature activation+0.000
-
Token -
Feature activation+0.000
(
Token (
Feature activation+5.123
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+0.000
Places
Token Places
Feature activation+0.000
-
Token -
Feature activation+0.000
make
Token make
Feature activation+0.000
Cobra
Token Cobra
Feature activation+0.000
Re
Token Re
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
(
Token (
Feature activation+0.000
8
Token8
Feature activation+4.957
c
Tokenc
Feature activation+0.000
+
Token+
Feature activation+0.000
/
Token/
Feature activation+0.503
9
Token9
Feature activation+0.826
a
Tokena
Feature activation+0.000
ed
Tokened
Feature activation+0.000
proteins
Token proteins
Feature activation+0.000
,
Token,
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+4.645
Î
Token Î
Feature activation+0.000
´
Token´
Feature activation+0.000
character
Token character
Feature activation+0.000
izes
Tokenizes
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
Sanford
Token Sanford
Feature activation+0.000
Police
Token Police
Feature activation+0.000
Chief
Token Chief
Feature activation+4.532
Cecil
Token Cecil
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
Gustav
Token Gustav
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Bast
Token Bast
Feature activation+0.000
os
Tokenos
Feature activation+0.000
30
Token 30
Feature activation+0.000
D
Token D
Feature activation+4.466
C
Token C
Feature activation+0.457
,
Token,
Feature activation+0.000
DM
Token DM
Feature activation+0.000
BRA
Token BRA
Feature activation+0.000
0
Token 0
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
trillion
Token trillion
Feature activation+0.000
in
Token in
Feature activation+0.000
2006
Token 2006
Feature activation+0.000
to
Token to
Feature activation+4.442
C
Token C
Feature activation+0.641
$
Token$
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
still
Token still
Feature activation+0.000
fall
Token fall
Feature activation+0.000
ill
Token ill
Feature activation+0.000
;
Token;
Feature activation+4.330
d
Token d
Feature activation+0.000
)
Token)
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
and
Token and
Feature activation+0.000
detect
Token detect
Feature activation+0.000
et
Tokenet
Feature activation+0.000
ace
Tokenace
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Conservation
Token Conservation
Feature activation+0.000
(
Token (
Feature activation+0.679
O
TokenO
Feature activation+4.321
CC
TokenCC
Feature activation+0.654
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ospital
Tokenospital
Feature activation+0.000
X
Token X
Feature activation+0.000
-
Token -
Feature activation+0.000
(
Token (
Feature activation+4.313
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+0.000
Places
Token Places
Feature activation+0.000
-
Token -
Feature activation+0.000
Sports
Token Sports
Feature activation+0.000
Talk
Token Talk
Feature activation+0.000
ðŁ
Token ðŁ
Feature activation+0.000
ı
Tokenı
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
(@
Token (@
Feature activation+4.275
C
TokenC
Feature activation+2.642
av
Tokenav
Feature activation+0.125
s
Tokens
Feature activation+0.000
Sports
TokenSports
Feature activation+0.000
Talk
TokenTalk
Feature activation+0.000
,
Token,
Feature activation+0.000
Malk
Token Malk
Feature activation+0.000
h
Tokenh
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
30
Token 30
Feature activation+0.053
D
Token D
Feature activation+4.211
C
Token C
Feature activation+0.000
G
Token G
Feature activation+0.000
EO
TokenEO
Feature activation+0.000
42
Token 42
Feature activation+0.000
Fu
Token Fu
Feature activation+0.000
S
TokenS
Feature activation+0.000
:
Token:
Feature activation+0.000
C
TokenC
Feature activation+0.486
/
Token/
Feature activation+0.473
C
TokenC
Feature activation+0.498
:
Token:
Feature activation+4.171
H
TokenH
Feature activation+0.000
/
Token/
Feature activation+0.243
I
TokenI
Feature activation+0.000
:
Token:
Feature activation+0.000
H
TokenH
Feature activation+0.000
in
Token in
Feature activation+0.000
April
Token April
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+4.160
CC
TokenCC
Feature activation+0.000
AIN
TokenAIN
Feature activation+0.000
:
Token:
Feature activation+0.000
It
Token It
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
law
Token law
Feature activation+0.000
against
Token against
Feature activation+0.000
F
Token F
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
/
Token/
Feature activation+4.082
C
TokenC
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Track
TokenTrack
Feature activation+0.000
4
Token 4
Feature activation+0.000
features
Token features
Feature activation+4.060
unc
Token unc
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
production
Token production
Feature activation+0.000
from
Token from
Feature activation+0.388
Sv
Token Sv
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Track
TokenTrack
Feature activation+0.000
3
Token 3
Feature activation+0.000
features
Token features
Feature activation+3.890
unc
Token unc
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
production
Token production
Feature activation+0.000
from
Token from
Feature activation+0.347
Sv
Token Sv
Feature activation+0.000

Top DFA by src position
MAX = 6.787

H
TokenH
Feature activation+0.004
Top resid features:
ospital
Tokenospital
Feature activation-0.004
Top resid features:
X
Token X
Feature activation+0.012
Top resid features:
-
Token -
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+0.023
Top resid features:
c
Tokenc
Feature activation+6.787
Top resid features:
)
Token)
Feature activation+0.022
Top resid features:
Forbidden
Token Forbidden
Feature activation-0.007
Top resid features:
Places
Token Places
Feature activation-0.004
Top resid features:
-
Token -
Feature activation-0.003
Top resid features:
Sylv
Token Sylv
Feature activation+0.005
Top resid features:
2015
Token 2015
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
(
Token(
Feature activation-0.006
Top resid features:
c
Tokenc
Feature activation+6.485
Top resid features:
)
Token)
Feature activation-0.003
Top resid features:
Se
Token Se
Feature activation+0.002
Top resid features:
clusion
Tokenclusion
Feature activation+0.000
Top resid features:
allowed
Token allowed
Feature activation+0.000
Top resid features:
if
Token if
Feature activation-0.000
Top resid features:
2
Token2
Feature activation-0.002
Top resid features:
nd
Tokennd
Feature activation-0.002
Top resid features:
Place
Token Place
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
Player
Token Player
Feature activation-0.006
Top resid features:
C
Token C
Feature activation+6.241
Top resid features:
:
Token:
Feature activation-0.004
Top resid features:
True
Token True
Feature activation-0.000
Top resid features:
Draco
Token Draco
Feature activation-0.000
Top resid features:
Dinosaur
Token Dinosaur
Feature activation+0.000
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
Top resid features:
ic
Tokenic
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
art
Token art
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
5
Token 5
Feature activation-0.004
Top resid features:
C
Token C
Feature activation+5.479
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
p
Tokenp
Feature activation+0.011
Top resid features:
.;
Token.;
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
H
TokenH
Feature activation+0.004
Top resid features:
ospital
Tokenospital
Feature activation-0.004
Top resid features:
X
Token X
Feature activation+0.007
Top resid features:
-
Token -
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+0.020
Top resid features:
c
Tokenc
Feature activation+3.534
Top resid features:
)
Token)
Feature activation+0.011
Top resid features:
Forbidden
Token Forbidden
Feature activation-0.012
Top resid features:
Places
Token Places
Feature activation-0.002
Top resid features:
-
Token -
Feature activation-0.004
Top resid features:
Sylv
Token Sylv
Feature activation+0.003
Top resid features:
An
Token An
Feature activation+0.007
Top resid features:
ac
Tokenac
Feature activation+0.003
Top resid features:
onda
Tokenonda
Feature activation+0.018
Top resid features:
(
Token (
Feature activation-0.021
Top resid features:
8
Token8
Feature activation-0.004
Top resid features:
c
Tokenc
Feature activation+3.832
Top resid features:
),
Token),
Feature activation+0.010
Top resid features:
with
Token with
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
cru
Token cru
Feature activation-0.004
Top resid features:
x
Tokenx
Feature activation+0.001
Top resid features:
genetic
Token genetic
Feature activation-0.000
Top resid features:
network
Token network
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
The
Token The
Feature activation+0.004
Top resid features:
constant
Token constant
Feature activation+0.062
Top resid features:
c
Token c
Feature activation+5.193
Top resid features:
reflects
Token reflects
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
combined
Token combined
Feature activation+0.001
Top resid features:
efficiency
Token efficiency
Feature activation-0.010
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Personal
TokenPersonal
Feature activation-0.000
Top resid features:
approach
Token approach
Feature activation+0.001
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
Police
Token Police
Feature activation+0.003
Top resid features:
chief
Token chief
Feature activation-0.003
Top resid features:
Cecil
Token Cecil
Feature activation+5.152
Top resid features:
Smith
Token Smith
Feature activation-0.106
Top resid features:
,
Token,
Feature activation-0.033
Top resid features:
who
Token who
Feature activation-0.013
Top resid features:
took
Token took
Feature activation-0.003
Top resid features:
over
Token over
Feature activation-0.002
Top resid features:
ah
Tokenah
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
John
Token John
Feature activation+0.001
Top resid features:
29
Token 29
Feature activation-0.001
Top resid features:
D
Token D
Feature activation+0.053
Top resid features:
C
Token C
Feature activation+2.881
Top resid features:
G
Token G
Feature activation-0.018
Top resid features:
HA
TokenHA
Feature activation+0.036
Top resid features:
82
Token 82
Feature activation-0.001
Top resid features:
Gustav
Token Gustav
Feature activation+0.006
Top resid features:
o
Tokeno
Feature activation+0.002
Top resid features:
more
Token more
Feature activation-0.042
Top resid features:
than
Token than
Feature activation-0.014
Top resid features:
doubled
Token doubled
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
from
Token from
Feature activation-0.026
Top resid features:
C
Token C
Feature activation+5.364
Top resid features:
$
Token$
Feature activation+0.074
Top resid features:
2
Token2
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
2
Token2
Feature activation+0.001
Top resid features:
trillion
Token trillion
Feature activation-0.030
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
incidence
Token incidence
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
diseases
Token diseases
Feature activation+0.000
Top resid features:
;
Token;
Feature activation-0.016
Top resid features:
c
Token c
Feature activation+4.903
Top resid features:
)
Token)
Feature activation-0.027
Top resid features:
provide
Token provide
Feature activation+0.000
Top resid features:
cur
Token cur
Feature activation+0.022
Top resid features:
ative
Tokenative
Feature activation+0.004
Top resid features:
treatment
Token treatment
Feature activation-0.008
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
follow
Token follow
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Organization
Token Organization
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.041
Top resid features:
C
Token C
Feature activation+4.507
Top resid features:
et
Tokenet
Feature activation+0.160
Top resid features:
ace
Tokenace
Feature activation+0.033
Top resid features:
an
Tokenan
Feature activation+0.092
Top resid features:
Conservation
Token Conservation
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+0.014
Top resid features:
H
TokenH
Feature activation+0.003
Top resid features:
ospital
Tokenospital
Feature activation-0.003
Top resid features:
X
Token X
Feature activation+0.005
Top resid features:
-
Token -
Feature activation-0.004
Top resid features:
(
Token (
Feature activation+0.015
Top resid features:
c
Tokenc
Feature activation+2.779
Top resid features:
)
Token)
Feature activation+0.005
Top resid features:
Forbidden
Token Forbidden
Feature activation-0.008
Top resid features:
Places
Token Places
Feature activation-0.001
Top resid features:
-
Token -
Feature activation-0.003
Top resid features:
Sylv
Token Sylv
Feature activation+0.002
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
Akron
Token Akron
Feature activation-0.103
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.025
Top resid features:
C
TokenC
Feature activation+4.486
Top resid features:
av
Tokenav
Feature activation+0.196
Top resid features:
s
Tokens
Feature activation+0.113
Top resid features:
Sports
Token Sports
Feature activation+0.029
Top resid features:
Talk
Token Talk
Feature activation-0.005
Top resid features:
ðŁ
Token ðŁ
Feature activation+0.023
Top resid features:
ah
Tokenah
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
John
Token John
Feature activation+0.001
Top resid features:
29
Token 29
Feature activation-0.001
Top resid features:
D
Token D
Feature activation+0.037
Top resid features:
C
Token C
Feature activation+2.567
Top resid features:
G
Token G
Feature activation-0.025
Top resid features:
HA
TokenHA
Feature activation+0.042
Top resid features:
82
Token 82
Feature activation-0.005
Top resid features:
Gustav
Token Gustav
Feature activation+0.005
Top resid features:
o
Tokeno
Feature activation+0.001
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
N
TokenN
Feature activation+0.029
Top resid features:
/
Token/
Feature activation-0.004
Top resid features:
S
TokenS
Feature activation+0.027
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
C
TokenC
Feature activation+3.023
Top resid features:
/
Token/
Feature activation-0.002
Top resid features:
C
TokenC
Feature activation+1.407
Top resid features:
:
Token:
Feature activation+0.025
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
KEN
TokenKEN
Feature activation-0.006
Top resid features:
NY
TokenNY
Feature activation+0.004
Top resid features:
M
Token M
Feature activation-0.013
Top resid features:
CC
TokenCC
Feature activation+4.626
Top resid features:
AIN
TokenAIN
Feature activation+0.042
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
happened
Token happened
Feature activation+0.000
Top resid features:
within
Token within
Feature activation+0.000
Top resid features:
doctor
Token doctor
Feature activation-0.004
Top resid features:
claimed
Token claimed
Feature activation-0.001
Top resid features:
F
Token F
Feature activation+0.007
Top resid features:
GM
TokenGM
Feature activation-0.019
Top resid features:
/
Token/
Feature activation+0.002
Top resid features:
C
TokenC
Feature activation+4.817
Top resid features:
was
Token was
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
religious
Token religious
Feature activation-0.005
Top resid features:
requirement
Token requirement
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
production
Token production
Feature activation-0.008
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
Sv
Token Sv
Feature activation+0.046
Top resid features:
idden
Tokenidden
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
unc
Token unc
Feature activation+1.986
Top resid features:
redited
Tokenredited
Feature activation-0.010
Top resid features:
vocals
Token vocals
Feature activation-0.005
Top resid features:
from
Token from
Feature activation-0.007
Top resid features:
Jennifer
Token Jennifer
Feature activation-0.005
Top resid features:
Dec
Token Dec
Feature activation-0.004
Top resid features:
production
Token production
Feature activation-0.014
Top resid features:
from
Token from
Feature activation-0.004
Top resid features:
Sv
Token Sv
Feature activation+0.064
Top resid features:
idden
Tokenidden
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
unc
Token unc
Feature activation+1.991
Top resid features:
redited
Tokenredited
Feature activation-0.014
Top resid features:
vocals
Token vocals
Feature activation-0.017
Top resid features:
from
Token from
Feature activation-0.013
Top resid features:
Jennifer
Token Jennifer
Feature activation-0.013
Top resid features:
Dec
Token Dec
Feature activation-0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.04

Head 3: 0.03

Head 4: 0.04

Head 5: 0.02

Head 6: 0.07

Head 7: 0.50

Head 8: 0.03

Head 9: 0.03

Head 10: 0.09

Head 11: 0.05

Positive logits

channelAvailability2.91

Fighters2.85

=-=-2.59

offer2.59

utz2.42

ohm2.34

2.30

oof2.27

oys2.17

Offline2.16

Hero2.12

unk2.09

_>2.07

oor2.07

2.05

quickShipAvailable2.05

Hammer2.05

rieg2.04

agnetic2.04

Ludwig2.04

Negative logits

CSI-3.08

CS-3.02

Cul-2.99

CC-2.90

CI-2.89

CS-2.85

CCC-2.83

Chennai-2.82

CP-2.82

Cambodia-2.76

cs-2.73

CET-2.70

Coulter-2.68

Cunningham-2.65

Carpenter-2.63

CC-2.63

CP-2.62

Cameron-2.61

CU-2.61

Chapel-2.60

INTERVAL 5.724 - 6.360
CONTAINS 0.000%

super
Tokensuper
Feature activation+0.000
vised
Tokenvised
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.249
(
Token(
Feature activation+6.059
d
Tokend
Feature activation+0.000
)
Token)
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+0.000
's
Token's
Feature activation+0.000
statue
Token statue
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ospital
Tokenospital
Feature activation+0.088
X
Token X
Feature activation+0.000
-
Token -
Feature activation+0.000
(
Token (
Feature activation+6.360
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+0.000
Places
Token Places
Feature activation+0.000
-
Token -
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.131
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+5.786
A
Token A
Feature activation+0.000
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Wind
Token Wind
Feature activation+0.000

INTERVAL 5.088 - 5.724
CONTAINS 0.000%

pl
Tokenpl
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
.
Token.
Feature activation+0.000
art
Token art
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token 5
Feature activation+5.706
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
p
Tokenp
Feature activation+0.000
.;
Token.;
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ospital
Tokenospital
Feature activation+0.000
X
Token X
Feature activation+0.000
-
Token -
Feature activation+0.000
(
Token (
Feature activation+5.123
c
Tokenc
Feature activation+0.000
)
Token)
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+0.000
Places
Token Places
Feature activation+0.000
-
Token -
Feature activation+0.000

INTERVAL 4.452 - 5.088
CONTAINS 0.000%

make
Token make
Feature activation+0.000
Cobra
Token Cobra
Feature activation+0.000
Re
Token Re
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
(
Token (
Feature activation+0.000
8
Token8
Feature activation+4.957
c
Tokenc
Feature activation+0.000
+
Token+
Feature activation+0.000
/
Token/
Feature activation+0.503
9
Token9
Feature activation+0.826
a
Tokena
Feature activation+0.000
ed
Tokened
Feature activation+0.000
proteins
Token proteins
Feature activation+0.000
,
Token,
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+4.645
Î
Token Î
Feature activation+0.000
´
Token´
Feature activation+0.000
character
Token character
Feature activation+0.000
izes
Tokenizes
Feature activation+0.000
the
Token the
Feature activation+0.000
Gustav
Token Gustav
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Bast
Token Bast
Feature activation+0.000
os
Tokenos
Feature activation+0.000
30
Token 30
Feature activation+0.000
D
Token D
Feature activation+4.466
C
Token C
Feature activation+0.457
,
Token,
Feature activation+0.000
DM
Token DM
Feature activation+0.000
BRA
Token BRA
Feature activation+0.000
0
Token 0
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
Sanford
Token Sanford
Feature activation+0.000
Police
Token Police
Feature activation+0.000
Chief
Token Chief
Feature activation+4.532
Cecil
Token Cecil
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 3.816 - 4.452
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Track
TokenTrack
Feature activation+0.000
4
Token 4
Feature activation+0.000
features
Token features
Feature activation+4.060
unc
Token unc
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
production
Token production
Feature activation+0.000
from
Token from
Feature activation+0.388
Sv
Token Sv
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Track
TokenTrack
Feature activation+0.000
3
Token 3
Feature activation+0.000
features
Token features
Feature activation+3.890
unc
Token unc
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
production
Token production
Feature activation+0.000
from
Token from
Feature activation+0.347
Sv
Token Sv
Feature activation+0.000
,
Token,
Feature activation+0.000
Malk
Token Malk
Feature activation+0.000
h
Tokenh
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
30
Token 30
Feature activation+0.053
D
Token D
Feature activation+4.211
C
Token C
Feature activation+0.000
G
Token G
Feature activation+0.000
EO
TokenEO
Feature activation+0.000
42
Token 42
Feature activation+0.000
Fu
Token Fu
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
still
Token still
Feature activation+0.000
fall
Token fall
Feature activation+0.000
ill
Token ill
Feature activation+0.000
;
Token;
Feature activation+4.330
d
Token d
Feature activation+0.000
)
Token)
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
and
Token and
Feature activation+0.000
detect
Token detect
Feature activation+0.000
et
Tokenet
Feature activation+0.000
ace
Tokenace
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Conservation
Token Conservation
Feature activation+0.000
(
Token (
Feature activation+0.679
O
TokenO
Feature activation+4.321
CC
TokenCC
Feature activation+0.654
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 3.180 - 3.816
CONTAINS 0.002%

return
Token return
Feature activation+0.000
:
Token:
Feature activation+0.000
1
Token1
Feature activation+0.000
depth
Token depth
Feature activation+0.000
=
Token=
Feature activation+0.000
1
Token1
Feature activation+3.722
C
Token C
Feature activation+0.000
=
Token =
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
O
Token O
Feature activation+0.000
him
Token him
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
@
Token @
Feature activation+1.502
create
Tokencreate
Feature activation+0.000
c
Tokenc
Feature activation+3.212
ra
Tokenra
Feature activation+0.848
ig
Tokenig
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
No
Token No
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
(
Token (
Feature activation+0.000
8
Token8
Feature activation+3.532
c
Tokenc
Feature activation+0.000
+
Token+
Feature activation+0.000
),
Token),
Feature activation+0.499
and
Token and
Feature activation+0.000
last
Token last
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+3.239
B
Token B
Feature activation+0.000
:
Token:
Feature activation+0.000
Inv
Token Inv
Feature activation+0.000
oked
Tokenoked
Feature activation+0.000
True
Token True
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+3.458
A
Token A
Feature activation+0.000
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Wind
Token Wind
Feature activation+0.000

INTERVAL 2.544 - 3.180
CONTAINS 0.004%

liquids
Token liquids
Feature activation+0.000
are
Token are
Feature activation+0.000
composed
Token composed
Feature activation+0.000
primarily
Token primarily
Feature activation+0.000
of
Token of
Feature activation+0.032
these
Token these
Feature activation+2.681
particles
Token particles
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
purified
Token purified
Feature activation+0.000
water
Token water
Feature activation+0.000
.
Token.
Feature activation+1.150
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mit
TokenMit
Feature activation+0.000
chell
Tokenchell
Feature activation+0.000
and
Token and
Feature activation+2.756
Cer
Token Cer
Feature activation+0.000
im
Tokenim
Feature activation+0.000
agic
Tokenagic
Feature activation+0.000
are
Token are
Feature activation+0.000
due
Token due
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
:
Token:
Feature activation+2.722
Cav
Token Cav
Feature activation+0.000
endish
Tokenendish
Feature activation+0.000
Press
Token Press
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
prev
Token prev
Feature activation+0.000
.
Token.
Feature activation+0.000
de
Token de
Feature activation+0.000
art
Token art
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token 4
Feature activation+3.088
39
Token39
Feature activation+1.849
al
Token al
Feature activation+0.000
in
Tokenin
Feature activation+0.000
.
Token.
Feature activation+0.297
1
Token 1
Feature activation+0.506
âĢĶ
Token âĢĶ
Feature activation+0.000
John
Token John
Feature activation+0.000
Cena
Token Cena
Feature activation+0.000
(@
Token (@
Feature activation+0.000
John
TokenJohn
Feature activation+0.000
C
TokenC
Feature activation+2.573
ena
Tokenena
Feature activation+0.000
)
Token)
Feature activation+0.000
November
Token November
Feature activation+0.000
8
Token 8
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.908 - 2.544
CONTAINS 0.005%

more
Token more
Feature activation+0.000
information
Token information
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SOURCE
TokenSOURCE
Feature activation+2.346
Cedar
Token Cedar
Feature activation+0.000
Grove
Token Grove
Feature activation+0.000
Comp
Token Comp
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
ing
Tokening
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
default
Token default
Feature activation+0.000
V
Token V
Feature activation+0.000
9
Token9
Feature activation+2.045
enc
Token enc
Feature activation+0.166
oder
Tokenoder
Feature activation+0.000
in
Token in
Feature activation+0.000
GNOME
Token GNOME
Feature activation+0.000
Shell
Token Shell
Feature activation+0.000
Commonwealth
Token Commonwealth
Feature activation+0.000
by
Token by
Feature activation+0.000
banning
Token banning
Feature activation+0.000
F
Token F
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
/
Token/
Feature activation+1.916
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
support
Token support
Feature activation+0.000
already
Token already
Feature activation+0.000
read
Token read
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
book
Token book
Feature activation+0.000
.
Token.
Feature activation+1.963
Trent
Token Trent
Feature activation+0.000
races
Token races
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
hall
Token hall
Feature activation+0.000
:
Token:
Feature activation+0.000
Mail
Token Mail
Feature activation+0.000
C
TokenC
Feature activation+0.000
WP
TokenWP
Feature activation+0.000
,
Token,
Feature activation+0.000
Mail
Token Mail
Feature activation+2.116
Client
Token Client
Feature activation+0.000
for
Token for
Feature activation+0.000
WordPress
Token WordPress
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000

INTERVAL 1.272 - 1.908
CONTAINS 0.015%

congressman
Token congressman
Feature activation+0.000
from
Token from
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
.
Token.
Feature activation+0.782
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.284
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
executive
Token executive
Feature activation+0.000
order
Token order
Feature activation+0.000
is
Token is
Feature activation+0.000
II
Token II
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Communications
Token Communications
Feature activation+0.000
Act
Token Act
Feature activation+0.000
of
Token of
Feature activation+1.350
1934
Token 1934
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
(@
Token (@
Feature activation+0.000
S
TokenS
Feature activation+0.000
BN
TokenBN
Feature activation+0.000
ation
Tokenation
Feature activation+0.400
C
TokenC
Feature activation+1.510
BB
TokenBB
Feature activation+1.309
)
Token)
Feature activation+0.000
November
Token November
Feature activation+0.000
9
Token 9
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
from
Token from
Feature activation+0.000
al
Token al
Feature activation+0.000
f
Tokenf
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
a
Tokena
Feature activation+0.000
and
Token and
Feature activation+1.396
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+1.730
cotton
Token cotton
Feature activation+0.000
seed
Tokenseed
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
racing
Token racing
Feature activation+0.000
driver
Token driver
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.000
Francis
Token Francis
Feature activation+1.736
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
5
Token 5
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Earl
Token Earl
Feature activation+0.000

INTERVAL 0.636 - 1.272
CONTAINS 0.052%

always
Token always
Feature activation+0.000
circumcised
Token circumcised
Feature activation+0.000
,
Token,
Feature activation+0.760
as
Token as
Feature activation+0.000
are
Token are
Feature activation+0.777
many
Token many
Feature activation+0.676
Africans
Token Africans
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.717
the
Token the
Feature activation+0.216
procedure
Token procedure
Feature activation+0.000
ended
Token ended
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
sequence
Token sequence
Feature activation+0.000
C
Token C
Feature activation+0.000
CC
TokenCC
Feature activation+0.698
GG
TokenGG
Feature activation+0.000
G
TokenG
Feature activation+0.000
(
Token (
Feature activation+0.000
under
Tokenunder
Feature activation+0.000
lined
Tokenlined
Feature activation+0.000
the
Token the
Feature activation+0.000
suspect
Token suspect
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
.
Token.
Feature activation+1.150
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.855
The
TokenThe
Feature activation+0.000
Trooper
Token Trooper
Feature activation+0.000
diseng
Token diseng
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
contact
Token contact
Feature activation+0.000
correctional
Token correctional
Feature activation+0.000
facility
Token facility
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Crown
Token Crown
Feature activation+0.000
and
Token and
Feature activation+1.075
defence
Token defence
Feature activation+0.000
lawyers
Token lawyers
Feature activation+0.000
argued
Token argued
Feature activation+0.000
over
Token over
Feature activation+0.000
whether
Token whether
Feature activation+0.000
to
Token to
Feature activation+0.000
CPS
Token CPS
Feature activation+0.000
,
Token,
Feature activation+0.497
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
or
Token or
Feature activation+1.210
Child
Token Child
Feature activation+0.000
Protective
Token Protective
Feature activation+0.000
Services
Token Services
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 0.000 - 0.636
CONTAINS 99.921%

has
Token has
Feature activation+0.000
shown
Token shown
Feature activation+0.000
me
Token me
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
very
Token very
Feature activation+0.000
much
Token much
Feature activation+0.000
embedded
Token embedded
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
sc
Tokensc
Feature activation+0.000
rup
Tokenrup
Feature activation+0.000
ulously
Tokenulously
Feature activation+0.000
honest
Token honest
Feature activation+0.000
magazine
Token magazine
Feature activation+0.000
that
Token that
Feature activation+0.000
cast
Token cast
Feature activation+0.000
an
Token an
Feature activation+0.000
appra
Token appra
Feature activation+0.000
testimony
Token testimony
Feature activation+0.000
,
Token,
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
alleging
Token alleging
Feature activation+0.000
she
Token she
Feature activation+0.000
influenced
Token influenced
Feature activation+0.000
the
Token the
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
alien
Token alien
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
whose
Tokenwhose
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Future
Token Future
Feature activation+0.000
working
Token working
Feature activation+0.000
group
Token group
Feature activation+0.000
has
Token has
Feature activation+0.000
operated
Token operated
Feature activation+0.000
since
Token since
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
hack
Token hack
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
secret
Token secret
Feature activation+0.000
computer
Token computer
Feature activation+0.000
system
Token system
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
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 H10.7: (feature 20321)

TOP ACTIVATIONS
MAX = 2.909

your
Token your
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+2.909
believe
Token believe
Feature activation+0.000
God
Token God
Feature activation+0.000
approves
Token approves
Feature activation+0.000
of
Token of
Feature activation+0.000
slavery
Token slavery
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
amp
Token amp
Feature activation+0.000
up
Token up
Feature activation+2.809
speculation
Token speculation
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
run
Token run
Feature activation+0.000
for
Token for
Feature activation+0.000
are
Token are
Feature activation+0.140
now
Token now
Feature activation+0.172
putting
Token putting
Feature activation+0.000
forward
Token forward
Feature activation+1.025
theories
Token theories
Feature activation+0.007
and
Token and
Feature activation+2.523
predictions
Token predictions
Feature activation+0.357
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.988
Bitcoin
Token Bitcoin
Feature activation+0.000
Price
Token Price
Feature activation+0.000
only
Token only
Feature activation+0.000
three
Token three
Feature activation+0.000
percent
Token percent
Feature activation+2.011
of
Token of
Feature activation+0.000
Hornets
Token Hornets
Feature activation+0.000
fans
Token fans
Feature activation+2.455
would
Token would
Feature activation+0.291
have
Token have
Feature activation+0.434
picked
Token picked
Feature activation+0.020
another
Token another
Feature activation+0.000
player
Token player
Feature activation+0.000
unless
Token unless
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
stated
Token stated
Feature activation+0.000
.
Token.
Feature activation+0.000
Thoughts
Token Thoughts
Feature activation+0.000
and
Token and
Feature activation+2.426
opinions
Token opinions
Feature activation+0.104
are
Token are
Feature activation+0.840
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+1.060
my
Token my
Feature activation+0.379
the
Token the
Feature activation+0.000
poor
Token poor
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+2.419
framing
Token framing
Feature activation+0.000
of
Token of
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
and
Token and
Feature activation+0.000
whites
Token whites
Feature activation+0.000
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+0.000
the
Token the
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.514
or
Token or
Feature activation+2.409
ideals
Token ideals
Feature activation+0.757
that
Token that
Feature activation+0.210
characterize
Token characterize
Feature activation+0.212
a
Token a
Feature activation+0.000
community
Token community
Feature activation+0.000
is
Token is
Feature activation+0.000
worried
Token worried
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
but
Tokenbut
Feature activation+0.567
not
Token not
Feature activation+1.335
too
Token too
Feature activation+2.322
worried
Token worried
Feature activation+0.000
(
Token (
Feature activation+0.000
pdf
Tokenpdf
Feature activation+0.000
)âĢĶ
Token)âĢĶ
Feature activation+0.000
about
Tokenabout
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
of
Token of
Feature activation+0.244
rumor
Token rumor
Feature activation+0.000
and
Token and
Feature activation+2.263
conjecture
Token conjecture
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
Afghans
Token Afghans
Feature activation+0.000
know
Token know
Feature activation+0.000
white
Token white
Feature activation+0.000
nationalists
Token nationalists
Feature activation+0.000
have
Token have
Feature activation+0.000
different
Token different
Feature activation+0.000
views
Token views
Feature activation+0.000
and
Token and
Feature activation+2.254
motivations
Token motivations
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
broad
Token broad
Feature activation+0.421
and
Token and
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
The
Token The
Feature activation+0.000
official
Token official
Feature activation+2.210
theory
Token theory
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
destruction
Token destruction
Feature activation+0.000
of
Token of
Feature activation+0.000
more
Token more
Feature activation+0.000
comprehens
Token comprehens
Feature activation+0.000
ively
Tokenively
Feature activation+0.000
the
Token the
Feature activation+0.000
attitudes
Token attitudes
Feature activation+0.000
and
Token and
Feature activation+2.177
outlook
Token outlook
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
should
Token should
Feature activation+0.000
these
Token these
Feature activation+2.130
predictions
Token predictions
Feature activation+0.000
come
Token come
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
my
Token my
Feature activation+0.000
head
Token head
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
or
Token or
Feature activation+2.105
pre
Token pre
Feature activation+0.000
occup
Tokenoccup
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
workshops
Token workshops
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
interests
Token interests
Feature activation+0.000
and
Token and
Feature activation+2.094
needs
Token needs
Feature activation+0.188
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
patrons
Token patrons
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
was
Token was
Feature activation+0.000
willing
Token willing
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.839
and
Token and
Feature activation+2.087
even
Token even
Feature activation+1.917
eager
Token eager
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
three
Token three
Feature activation+0.000
percent
Token percent
Feature activation+2.011
of
Token of
Feature activation+0.000
Hornets
Token Hornets
Feature activation+0.000
fans
Token fans
Feature activation+2.455
would
Token would
Feature activation+0.291
have
Token have
Feature activation+0.434
of
Token of
Feature activation+0.000
Hug
Token Hug
Feature activation+0.000
eness
Tokeneness
Feature activation+0.000
;
Token;
Feature activation+0.000
Crusader
Token Crusader
Feature activation+0.000
's
Token's
Feature activation+1.959
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
Blessed
Token Blessed
Feature activation+0.000
Hammer
Token Hammer
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ow
Tokenow
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
and
Token and
Feature activation+1.945
disinformation
Token disinformation
Feature activation+0.031
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
was
Token was
Feature activation+0.000
willing
Token willing
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.839
and
Token and
Feature activation+2.087
even
Token even
Feature activation+1.917
eager
Token eager
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
with
Token with
Feature activation+0.000

Top DFA by src position
MAX = 3.438

kill
Token kill
Feature activation-0.020
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
doctor
Token doctor
Feature activation-0.001
Top resid features:
if
Token if
Feature activation+0.005
Top resid features:
you
Token you
Feature activation-0.002
Top resid features:
believe
Token believe
Feature activation+3.438
Top resid features:
God
Token God
Feature activation-0.013
Top resid features:
wants
Token wants
Feature activation-0.005
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
?
Token?
Feature activation+0.002
Top resid features:
Thursday
Token Thursday
Feature activation+0.006
Top resid features:
tried
Token tried
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
amp
Token amp
Feature activation-0.001
Top resid features:
up
Token up
Feature activation+0.002
Top resid features:
speculation
Token speculation
Feature activation+2.990
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
could
Token could
Feature activation-0.001
Top resid features:
run
Token run
Feature activation-0.000
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
teams
Token teams
Feature activation+0.016
Top resid features:
are
Token are
Feature activation+0.011
Top resid features:
now
Token now
Feature activation+0.017
Top resid features:
putting
Token putting
Feature activation+0.007
Top resid features:
forward
Token forward
Feature activation+0.218
Top resid features:
theories
Token theories
Feature activation+2.305
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
predictions
Token predictions
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.006
Top resid features:
27
Token 27
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
fans
Token fans
Feature activation+0.005
Top resid features:
agreed
Token agreed
Feature activation+2.116
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Hornets
Token Hornets
Feature activation+0.000
Top resid features:
should
Token should
Feature activation-0.017
Top resid features:
trade
Token trade
Feature activation-0.009
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
money
Token money
Feature activation-0.015
Top resid features:
unless
Token unless
Feature activation+0.020
Top resid features:
otherwise
Token otherwise
Feature activation+0.008
Top resid features:
stated
Token stated
Feature activation+0.049
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Thoughts
Token Thoughts
Feature activation+2.769
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
opinions
Token opinions
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
men
Token men
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
There
Token There
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
fixation
Token fixation
Feature activation+2.817
Top resid features:
on
Token on
Feature activation+0.005
Top resid features:
drug
Token drug
Feature activation-0.002
Top resid features:
use
Token use
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.001
Top resid features:
if
Token if
Feature activation+0.001
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
describe
Token describe
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
guiding
Token guiding
Feature activation+0.019
Top resid features:
beliefs
Token beliefs
Feature activation+2.746
Top resid features:
or
Token or
Feature activation+0.036
Top resid features:
ideals
Token ideals
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
characterize
Token characterize
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
central
Token central
Feature activation+0.002
Top resid features:
bank
Token bank
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.029
Top resid features:
worried
Token worried
Feature activation+2.464
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.068
Top resid features:
but
Tokenbut
Feature activation+0.039
Top resid features:
not
Token not
Feature activation+0.044
Top resid features:
too
Token too
Feature activation-0.019
Top resid features:
worried
Token worried
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
stuff
Token stuff
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
rumor
Token rumor
Feature activation+2.447
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
conjecture
Token conjecture
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
Afghans
Token Afghans
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
white
Token white
Feature activation+0.003
Top resid features:
nationalists
Token nationalists
Feature activation-0.008
Top resid features:
have
Token have
Feature activation+0.007
Top resid features:
different
Token different
Feature activation+0.079
Top resid features:
views
Token views
Feature activation+2.535
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
motivations
Token motivations
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
7
Token7
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
official
Token official
Feature activation-0.020
Top resid features:
theory
Token theory
Feature activation+2.508
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
destruction
Token destruction
Feature activation+0.012
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
WTC
Token WTC
Feature activation+0.046
Top resid features:
represents
Token represents
Feature activation-0.001
Top resid features:
more
Token more
Feature activation+0.019
Top resid features:
comprehens
Token comprehens
Feature activation-0.004
Top resid features:
ively
Tokenively
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
attitudes
Token attitudes
Feature activation+2.423
Top resid features:
and
Token and
Feature activation+0.056
Top resid features:
outlook
Token outlook
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
nation
Token nation
Feature activation+0.000
Top resid features:
teams
Token teams
Feature activation-0.014
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
now
Token now
Feature activation+0.003
Top resid features:
putting
Token putting
Feature activation+0.002
Top resid features:
forward
Token forward
Feature activation+0.017
Top resid features:
theories
Token theories
Feature activation+1.410
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
predictions
Token predictions
Feature activation+0.726
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
my
Token my
Feature activation-0.004
Top resid features:
head
Token head
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
have
Token have
Feature activation+0.054
Top resid features:
concerns
Token concerns
Feature activation+2.315
Top resid features:
or
Token or
Feature activation+0.094
Top resid features:
pre
Token pre
Feature activation+0.000
Top resid features:
occup
Tokenoccup
Feature activation+0.000
Top resid features:
ations
Tokenations
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
offers
Token offers
Feature activation-0.003
Top resid features:
workshops
Token workshops
Feature activation+0.007
Top resid features:
based
Token based
Feature activation+0.007
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.053
Top resid features:
interests
Token interests
Feature activation+2.428
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
needs
Token needs
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
patrons
Token patrons
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+0.038
Top resid features:
was
Token was
Feature activation+0.034
Top resid features:
willing
Token willing
Feature activation+2.367
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
eager
Token eager
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.008
Top resid features:
27
Token 27
Feature activation+0.001
Top resid features:
percent
Token percent
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.008
Top resid features:
fans
Token fans
Feature activation+0.008
Top resid features:
agreed
Token agreed
Feature activation+1.569
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Hornets
Token Hornets
Feature activation+0.002
Top resid features:
should
Token should
Feature activation-0.013
Top resid features:
trade
Token trade
Feature activation-0.014
Top resid features:
up
Token up
Feature activation+0.002
Top resid features:
New
Token New
Feature activation-0.007
Top resid features:
Sets
Token Sets
Feature activation+0.011
Top resid features:
:
Token :
Feature activation-0.001
Top resid features:
Monk
Token Monk
Feature activation+0.016
Top resid features:
's
Token's
Feature activation-0.004
Top resid features:
based
Token based
Feature activation+1.177
Top resid features:
on
Token on
Feature activation-0.024
Top resid features:
Expl
Token Expl
Feature activation+0.005
Top resid features:
oding
Tokenoding
Feature activation+0.002
Top resid features:
Palm
Token Palm
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
âĢ
Token âĢ
Feature activation+0.009
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
ow
Tokenow
Feature activation+0.124
Top resid features:
doubt
Token doubt
Feature activation+2.102
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
disinformation
Token disinformation
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Trump
Token Trump
Feature activation-0.000
Top resid features:
campaign
Token campaign
Feature activation+0.012
Top resid features:
was
Token was
Feature activation+0.023
Top resid features:
willing
Token willing
Feature activation+2.275
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.007
Top resid features:
and
Token and
Feature activation-0.018
Top resid features:
even
Token even
Feature activation+0.008
Top resid features:
eager
Token eager
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.03

Head 4: 0.10

Head 5: 0.02

Head 6: 0.04

Head 7: 0.50

Head 8: 0.02

Head 9: 0.07

Head 10: 0.03

Head 11: 0.09

Positive logits

AFL2.50

204392.24

Steam2.11

Steam2.08

wcsstore2.06

catentry2.06

Pack2.03

ð2.02

Baltimore2.01

Sail1.98

ć1.97

Ravens1.97

��1.94

Robo1.93

SourceFile1.93

NRL1.89

cock1.88

Baltimore1.87

inyl1.86

Pg1.84

Negative logits

Frontier-2.22

deception-2.02

ortunately-2.00

negotiator-1.88

replace-1.87

reorgan-1.86

options-1.85

isSpecial-1.80

printf-1.77

adjust-1.75

cumbers-1.75

pseudonym-1.74

efficient-1.73

ias-1.72

Strategy-1.72

accompan-1.72

bluff-1.71

adapter-1.69

ossier-1.69

parasitic-1.67

INTERVAL 2.618 - 2.909
CONTAINS 0.000%

on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
amp
Token amp
Feature activation+0.000
up
Token up
Feature activation+2.809
speculation
Token speculation
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
run
Token run
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+2.909
believe
Token believe
Feature activation+0.000
God
Token God
Feature activation+0.000
approves
Token approves
Feature activation+0.000
of
Token of
Feature activation+0.000
slavery
Token slavery
Feature activation+0.000

INTERVAL 2.327 - 2.618
CONTAINS 0.001%

the
Token the
Feature activation+0.000
poor
Token poor
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+2.419
framing
Token framing
Feature activation+0.000
of
Token of
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
and
Token and
Feature activation+0.000
whites
Token whites
Feature activation+0.000
unless
Token unless
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
stated
Token stated
Feature activation+0.000
.
Token.
Feature activation+0.000
Thoughts
Token Thoughts
Feature activation+0.000
and
Token and
Feature activation+2.426
opinions
Token opinions
Feature activation+0.104
are
Token are
Feature activation+0.840
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+1.060
my
Token my
Feature activation+0.379
only
Token only
Feature activation+0.000
three
Token three
Feature activation+0.000
percent
Token percent
Feature activation+2.011
of
Token of
Feature activation+0.000
Hornets
Token Hornets
Feature activation+0.000
fans
Token fans
Feature activation+2.455
would
Token would
Feature activation+0.291
have
Token have
Feature activation+0.434
picked
Token picked
Feature activation+0.020
another
Token another
Feature activation+0.000
player
Token player
Feature activation+0.000
are
Token are
Feature activation+0.140
now
Token now
Feature activation+0.172
putting
Token putting
Feature activation+0.000
forward
Token forward
Feature activation+1.025
theories
Token theories
Feature activation+0.007
and
Token and
Feature activation+2.523
predictions
Token predictions
Feature activation+0.357
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.988
Bitcoin
Token Bitcoin
Feature activation+0.000
Price
Token Price
Feature activation+0.000
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+0.000
the
Token the
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.514
or
Token or
Feature activation+2.409
ideals
Token ideals
Feature activation+0.757
that
Token that
Feature activation+0.210
characterize
Token characterize
Feature activation+0.212
a
Token a
Feature activation+0.000
community
Token community
Feature activation+0.000

INTERVAL 2.036 - 2.327
CONTAINS 0.001%

workshops
Token workshops
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
interests
Token interests
Feature activation+0.000
and
Token and
Feature activation+2.094
needs
Token needs
Feature activation+0.188
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
patrons
Token patrons
Feature activation+0.000
.
Token.
Feature activation+0.000
white
Token white
Feature activation+0.000
nationalists
Token nationalists
Feature activation+0.000
have
Token have
Feature activation+0.000
different
Token different
Feature activation+0.000
views
Token views
Feature activation+0.000
and
Token and
Feature activation+2.254
motivations
Token motivations
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
broad
Token broad
Feature activation+0.421
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
should
Token should
Feature activation+0.000
these
Token these
Feature activation+2.130
predictions
Token predictions
Feature activation+0.000
come
Token come
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
was
Token was
Feature activation+0.000
willing
Token willing
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.839
and
Token and
Feature activation+2.087
even
Token even
Feature activation+1.917
eager
Token eager
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
of
Token of
Feature activation+0.244
rumor
Token rumor
Feature activation+0.000
and
Token and
Feature activation+2.263
conjecture
Token conjecture
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
Afghans
Token Afghans
Feature activation+0.000
know
Token know
Feature activation+0.000

INTERVAL 1.745 - 2.036
CONTAINS 0.002%

y
Tokeny
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
A
Token A
Feature activation+0.000
third
Token third
Feature activation+1.899
added
Token added
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
.
Token.
Feature activation+0.000
19
Token19
Feature activation+0.000
%),
Token%),
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+1.830
likely
Token likely
Feature activation+0.000
team
Token team
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
East
Token East
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
storm
Token storm
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
were
Token were
Feature activation+1.847
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
phase
Token phase
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ow
Tokenow
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
and
Token and
Feature activation+1.945
disinformation
Token disinformation
Feature activation+0.031
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
forms
Token forms
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+1.789
also
Token also
Feature activation+1.728
pred
Token pred
Feature activation+0.000
isp
Tokenisp
Feature activation+0.000
osed
Tokenosed
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.454 - 1.745
CONTAINS 0.004%

this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
marvelous
Token marvelous
Feature activation+0.000
example
Token example
Feature activation+0.000
of
Token of
Feature activation+1.513
the
Token the
Feature activation+0.030
modern
Token modern
Feature activation+0.000
and
Token and
Feature activation+0.000
meaningless
Token meaningless
Feature activation+0.408
use
Token use
Feature activation+0.000
it
Token it
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.119
have
Token have
Feature activation+0.821
a
Token a
Feature activation+0.638
profound
Token profound
Feature activation+1.687
influence
Token influence
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
St
TokenSt
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
fiscal
Token fiscal
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
budget
Token budget
Feature activation+1.465
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
hopeful
Token hopeful
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+1.555
opinions
Token opinions
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000
,
Token,
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
claims
Token claims
Feature activation+0.000
,
Token,
Feature activation+1.909
the
Token the
Feature activation+1.497
delusions
Token delusions
Feature activation+0.000
,
Token,
Feature activation+1.786
and
Token and
Feature activation+1.672
the
Token the
Feature activation+1.353
errors
Token errors
Feature activation+0.000

INTERVAL 1.163 - 1.454
CONTAINS 0.008%

be
Token be
Feature activation+1.172
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+1.202
representatives
Token representatives
Feature activation+0.267
are
Token are
Feature activation+0.000
stating
Token stating
Feature activation+0.000
that
Token that
Feature activation+0.000
most
Token most
Feature activation+0.000
te
Tokente
Feature activation+0.000
ski
Token ski
Feature activation+0.000
area
Token area
Feature activation+0.000
with
Token with
Feature activation+0.000
warnings
Token warnings
Feature activation+0.000
and
Token and
Feature activation+1.168
observations
Token observations
Feature activation+0.366
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jim
TokenJim
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
than
Token than
Feature activation+0.000
anything
Token anything
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+1.257
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.135
realize
Token realize
Feature activation+0.000
how
Token how
Feature activation+0.000
morally
Token morally
Feature activation+0.000
culation
Tokenculation
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
tunnels
Token tunnels
Feature activation+0.000
ranges
Token ranges
Feature activation+0.000
from
Token from
Feature activation+1.327
them
Token them
Feature activation+0.000
being
Token being
Feature activation+0.000
for
Token for
Feature activation+0.000
drainage
Token drainage
Feature activation+0.000
,
Token,
Feature activation+0.000
edge
Token edge
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+1.393
worried
Token worried
Feature activation+0.000
about
Token about
Feature activation+0.000
drought
Token drought
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.873 - 1.163
CONTAINS 0.022%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
simply
Token simply
Feature activation+0.000
defy
Token defy
Feature activation+0.000
logic
Token logic
Feature activation+0.000
and
Token and
Feature activation+0.886
any
Token any
Feature activation+0.086
known
Token known
Feature activation+0.000
economic
Token economic
Feature activation+0.000
theories
Token theories
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.916
guide
Token guide
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.000
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
image
Token image
Feature activation+0.000
illustrates
Token illustrates
Feature activation+0.000
the
Token the
Feature activation+0.866
relative
Token relative
Feature activation+1.070
orient
Token orient
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
of
Token of
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
,
Token,
Feature activation+0.000
any
Token any
Feature activation+0.000
suggestions
Token suggestions
Feature activation+0.000
/
Token/
Feature activation+1.454
ide
Tokenide
Feature activation+0.000
as
Tokenas
Feature activation+0.044
/
Token/
Feature activation+1.050
feed
Tokenfeed
Feature activation+0.000
back
Tokenback
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
forget
Token forget
Feature activation+0.000
restart
Token restart
Feature activation+0.000
his
Token his
Feature activation+0.000
cricket
Token cricket
Feature activation+0.000
but
Token but
Feature activation+0.000
doctors
Token doctors
Feature activation+1.020
are
Token are
Feature activation+0.906
cautious
Token cautious
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
injury
Token injury
Feature activation+0.000
which
Token which
Feature activation+0.000

INTERVAL 0.582 - 0.873
CONTAINS 0.054%

are
Token are
Feature activation+0.000
below
Token below
Feature activation+0.000
the
Token the
Feature activation+0.000
free
Token free
Feature activation+0.000
throw
Token throw
Feature activation+0.000
line
Token line
Feature activation+0.723
extended
Token extended
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+0.000
sc
Tokensc
Feature activation+0.000
asters
Tokenasters
Feature activation+0.000
,
Token,
Feature activation+0.000
reputable
Token reputable
Feature activation+0.000
and
Token and
Feature activation+0.807
popular
Token popular
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
everything
Token everything
Feature activation+0.000
to
Token to
Feature activation+0.000
ics
Tokenics
Feature activation+0.000
in
Token in
Feature activation+0.000
conspir
Token conspir
Feature activation+0.000
atorial
Tokenatorial
Feature activation+0.205
lies
Token lies
Feature activation+0.000
including
Token including
Feature activation+0.795
a
Token a
Feature activation+0.430
theory
Token theory
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Sandy
Token Sandy
Feature activation+0.000
can
Token can
Feature activation+0.000
,
Token,
Feature activation+0.000
face
Token face
Feature activation+0.000
your
Token your
Feature activation+0.000
fears
Token fears
Feature activation+0.000
and
Token and
Feature activation+0.762
also
Token also
Feature activation+0.067
challenge
Token challenge
Feature activation+0.000
others
Token others
Feature activation+0.000
around
Token around
Feature activation+0.000
you
Token you
Feature activation+0.000
by
Token by
Feature activation+0.000
buying
Token buying
Feature activation+0.000
meat
Token meat
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.706
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
-
Token-
Feature activation+0.000
20
Token20
Feature activation+0.000

INTERVAL 0.291 - 0.582
CONTAINS 0.159%

to
Token to
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.517
just
Token just
Feature activation+0.000
plain
Token plain
Feature activation+0.570
wrong
Token wrong
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
learning
Token learning
Feature activation+0.000
about
Token about
Feature activation+0.000
their
Token their
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
and
Token and
Feature activation+0.296
seeing
Token seeing
Feature activation+0.113
the
Token the
Feature activation+0.000
images
Token images
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
has
Token has
Feature activation+0.000
issued
Token issued
Feature activation+0.000
an
Token an
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
false
Token false
Feature activation+0.000
,
Token,
Feature activation+0.530
misleading
Token misleading
Feature activation+0.000
and
Token and
Feature activation+0.733
amateur
Token amateur
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
is
Token is
Feature activation+0.000
inc
Token inc
Feature activation+0.000
ont
Tokenont
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
vert
Tokenvert
Feature activation+0.000
ible
Tokenible
Feature activation+0.312
.
Token.
Feature activation+0.000
Battles
Token Battles
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
teaching
Token teaching
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
values
Token values
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.138
far
Token far
Feature activation+0.000
below
Token below
Feature activation+0.350
the
Token the
Feature activation+0.105
levels
Token levels
Feature activation+0.000
measured
Token measured
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.291
CONTAINS 99.750%

period
Token period
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
complex
Token complex
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
log
Token log
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
UPDATE
TokenUPDATE
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
games
Token games
Feature activation+0.000
since
Token since
Feature activation+0.000
Love
Token Love
Feature activation+0.000
,
Token,
Feature activation+0.000
P
Token P
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
ovic
Tokenovic
Feature activation+0.000
and
Token and
Feature activation+0.000
B
Token B
Feature activation+0.000
funding
Token funding
Feature activation+0.000
that
Token that
Feature activation+0.000
judges
Token judges
Feature activation+0.000
say
Token say
Feature activation+0.000
is
Token is
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
overhaul
Token overhaul
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
still
Token still
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
ests
Tokenests
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
mort
Token mort
Feature activation+0.000
uary
Tokenuary
Feature activation+0.000
of
Token of
Feature activation+0.000
U
Token U
Feature activation+0.000
mber
Tokenmber
Feature activation+0.000
to
Tokento
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
where
Token where
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+0.266
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+0.266
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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 H10.7: (feature 13998)

TOP ACTIVATIONS
MAX = 7.664

-
Token-
Feature activation+0.000
500
Token500
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.[
Token.[
Feature activation+7.664
2
Token2
Feature activation+0.000
][
Token][
Feature activation+5.863
5
Token5
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
kid
Tokenkid
Feature activation+0.000
and
Token and
Feature activation+0.000
Kyl
Token Kyl
Feature activation+0.000
a
Tokena
Feature activation+0.000
One
Token One
Feature activation+0.000
Dance
Token Dance
Feature activation+6.691
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Elsewhere
TokenElsewhere
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
feet
Token feet
Feature activation+0.000
were
Token were
Feature activation+0.000
involved
Token involved
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.510
"
Token"
Feature activation+0.000
Sc
TokenSc
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ubs
Tokenubs
Feature activation+0.000
Factor
Token Factor
Feature activation+0.000
flood
Token flood
Feature activation+0.000
fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+6.041
almost
Token almost
Feature activation+5.394
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.[
Token.[
Feature activation+7.664
2
Token2
Feature activation+0.000
][
Token][
Feature activation+5.863
5
Token5
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Inter
TokenInter
Feature activation+0.000
Rating
Token Rating
Feature activation+0.000
:
Token:
Feature activation+0.049
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.129
1
Token1
Feature activation+0.000
/
Token/
Feature activation+5.597
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
12
Token 12
Feature activation+0.000
99
Token99
Feature activation+0.000
4
Token4
Feature activation+0.000
,
Token,
Feature activation+0.000
S
Token S
Feature activation+1.703
5
Token5
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+5.584
6
Token6
Feature activation+0.000
.[
Token.[
Feature activation+0.000
12
Token12
Feature activation+0.000
]
Token]
Feature activation+0.000
Sw
Token Sw
Feature activation+0.000
an
Token an
Feature activation+0.000
increased
Token increased
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
of
Token of
Feature activation+0.000
presence
Token presence
Feature activation+0.000
.[
Token.[
Feature activation+5.563
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.000
7
Token7
Feature activation+0.000
]
Token]
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
.
Token.
Feature activation+0.000
57
Token57
Feature activation+0.000
Alabama
Token Alabama
Feature activation+0.000
7
Token 7
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+5.521
6
Token 6
Feature activation+1.326
3
Token 3
Feature activation+0.486
3
Token 3
Feature activation+0.266
9
Token 9
Feature activation+0.032
.
Token.
Feature activation+0.000
South
Token South
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Yugoslavia
Token Yugoslavia
Feature activation+0.000
.[
Token.[
Feature activation+5.460
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+6.041
almost
Token almost
Feature activation+5.394
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000
reliability
Token reliability
Feature activation+0.000
local
Token local
Feature activation+0.000
television
Token television
Feature activation+0.000
stations
Token stations
Feature activation+0.000
.[
Token.[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+5.306
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
By
Token By
Feature activation+0.000
1988
Token 1988
Feature activation+0.000
,
Token,
Feature activation+0.000
year
Token year
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
Polar
Token Polar
Feature activation+0.000
climate
Token climate
Feature activation+0.000
.[
Token.[
Feature activation+5.275
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Land
Token Land
Feature activation+0.000
locked
Tokenlocked
Feature activation+0.000
areas
Token areas
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+0.000
Kil
Token Kil
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
jar
Token jar
Feature activation+0.000
[
Token[
Feature activation+5.215
d
Tokend
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
ious
Tokenious
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
discuss
Token discuss
Feature activation+0.000
-
Token-
Feature activation+0.000
inning
Tokeninning
Feature activation+0.000
situations
Token situations
Feature activation+0.000
)[
Token)[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+5.204
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.415
7
Token7
Feature activation+0.000
]
Token]
Feature activation+0.000
to
Token to
Feature activation+0.000
service
Token service
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
day
Token day
Feature activation+0.000
.[
Token.[
Feature activation+5.171
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
mid
Token mid
Feature activation+0.000
85
Token 85
Feature activation+0.000
career
Token career
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000
.[
Token.[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+5.123
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
languages
Token languages
Feature activation+0.000
would
Token would
Feature activation+0.000
survive
Token survive
Feature activation+0.000
.[
Token.[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+5.115
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Nevertheless
TokenNevertheless
Feature activation+0.000
investigations
Token investigations
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Royal
Token Royal
Feature activation+0.000
Institution
Token Institution
Feature activation+0.000
.[
Token.[
Feature activation+4.969
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
About
Token About
Feature activation+0.000
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+0.000
the
Token the
Feature activation+0.000
Norman
Token Norman
Feature activation+0.000
conquest
Token conquest
Feature activation+0.000
of
Token of
Feature activation+0.000
England
Token England
Feature activation+0.000
.[
Token.[
Feature activation+4.851
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000

Top DFA by src position
MAX = 8.767

0
Token0
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
885
Token885
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
).[
Token).[
Feature activation-0.018
Top resid features:
5
Token5
Feature activation+8.767
Top resid features:
]
Token]
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Due
TokenDue
Feature activation-0.006
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
Don
Token Don
Feature activation+0.006
Top resid features:
't
Token't
Feature activation-0.001
Top resid features:
Let
Token Let
Feature activation-0.004
Top resid features:
Me
Token Me
Feature activation-0.003
Top resid features:
Down
Token Down
Feature activation-0.002
Top resid features:
5
Token 5
Feature activation+6.848
Top resid features:
)
Token)
Feature activation-0.009
Top resid features:
Drake
Token Drake
Feature activation+0.143
Top resid features:
feat
Token feat
Feature activation-0.031
Top resid features:
Wiz
Token Wiz
Feature activation+0.001
Top resid features:
kid
Tokenkid
Feature activation+0.078
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
flesh
Token flesh
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
5
Token5
Feature activation+7.477
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
The
Token The
Feature activation-0.020
Top resid features:
cast
Token cast
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
crew
Token crew
Feature activation-0.002
Top resid features:
in
Token in
Feature activation-0.025
Top resid features:
flood
Token flood
Feature activation+0.004
Top resid features:
fill
Tokenfill
Feature activation-0.025
Top resid features:
routers
Token routers
Feature activation-0.047
Top resid features:
from
Token from
Feature activation+0.135
Top resid features:
5
Token 5
Feature activation+6.849
Top resid features:
to
Token to
Feature activation+0.301
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
0
Token0
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
885
Token885
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
).[
Token).[
Feature activation-0.010
Top resid features:
5
Token5
Feature activation+7.050
Top resid features:
]
Token]
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Due
TokenDue
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
2
Token 2
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
5
Token5
Feature activation+0.792
Top resid features:
/
Token/
Feature activation-0.002
Top resid features:
5
Token5
Feature activation+3.855
Top resid features:
.
Token.
Feature activation+0.110
Top resid features:
From
Token From
Feature activation-0.002
Top resid features:
12
Token 12
Feature activation+0.002
Top resid features:
46
Token46
Feature activation-0.001
Top resid features:
votes
Token votes
Feature activation-0.000
Top resid features:
including
Token including
Feature activation+0.002
Top resid features:
S
Token S
Feature activation+0.004
Top resid features:
4
Token4
Feature activation+0.124
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
S
Token S
Feature activation-0.003
Top resid features:
5
Token5
Feature activation+5.315
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
S
Token S
Feature activation+0.016
Top resid features:
6
Token6
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation+0.000
Top resid features:
12
Token12
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation-0.000
Top resid features:
r
Tokenr
Feature activation+0.000
Top resid features:
illing
Tokenilling
Feature activation-0.000
Top resid features:
realism
Token realism
Feature activation-0.001
Top resid features:
"[
Token"[
Feature activation-0.003
Top resid features:
5
Token5
Feature activation+7.050
Top resid features:
]
Token]
Feature activation+0.003
Top resid features:
HD
Token HD
Feature activation-0.005
Top resid features:
TV
TokenTV
Feature activation+0.000
Top resid features:
attempts
Token attempts
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
21
Token21
Feature activation-0.004
Top resid features:
Oregon
Token Oregon
Feature activation+0.005
Top resid features:
7
Token 7
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
1
Token1
Feature activation-0.022
Top resid features:
5
Token 5
Feature activation+4.305
Top resid features:
5
Token 5
Feature activation+1.251
Top resid features:
5
Token 5
Feature activation+0.812
Top resid features:
10
Token 10
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
57
Token57
Feature activation-0.012
Top resid features:
its
Token its
Feature activation-0.010
Top resid features:
nuclear
Token nuclear
Feature activation+0.001
Top resid features:
weapons
Token weapons
Feature activation-0.002
Top resid features:
program
Token program
Feature activation-0.001
Top resid features:
.[
Token.[
Feature activation-0.032
Top resid features:
5
Token5
Feature activation+6.640
Top resid features:
]
Token]
Feature activation+0.020
Top resid features:
A
Token A
Feature activation-0.015
Top resid features:
study
Token study
Feature activation+0.002
Top resid features:
by
Token by
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.021
Top resid features:
flood
Token flood
Feature activation-0.006
Top resid features:
fill
Tokenfill
Feature activation-0.014
Top resid features:
routers
Token routers
Feature activation-0.009
Top resid features:
from
Token from
Feature activation+0.202
Top resid features:
5
Token 5
Feature activation+6.103
Top resid features:
to
Token to
Feature activation+0.289
Top resid features:
almost
Token almost
Feature activation-0.026
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
purchasing
Token purchasing
Feature activation-0.002
Top resid features:
local
Token local
Feature activation-0.002
Top resid features:
television
Token television
Feature activation+0.000
Top resid features:
stations
Token stations
Feature activation-0.000
Top resid features:
.[
Token.[
Feature activation-0.025
Top resid features:
5
Token5
Feature activation+6.469
Top resid features:
][
Token][
Feature activation+0.006
Top resid features:
6
Token6
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
By
Token By
Feature activation+0.000
Top resid features:
1988
Token 1988
Feature activation+0.000
Top resid features:
climate
Token climate
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
north
Token north
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation-0.019
Top resid features:
5
Token5
Feature activation+6.491
Top resid features:
]
Token]
Feature activation+0.009
Top resid features:
Extreme
Token Extreme
Feature activation-0.005
Top resid features:
northern
Token northern
Feature activation-0.000
Top resid features:
Canada
Token Canada
Feature activation+0.001
Top resid features:
can
Token can
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
In
TokenIn
Feature activation-0.008
Top resid features:
2003
Token 2003
Feature activation+0.004
Top resid features:
,[
Token,[
Feature activation-0.044
Top resid features:
5
Token5
Feature activation+6.392
Top resid features:
]
Token]
Feature activation+0.001
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
Ray
Token Ray
Feature activation-0.007
Top resid features:
ware
Tokenware
Feature activation+0.001
Top resid features:
Group
Token Group
Feature activation-0.004
Top resid features:
ninth
Token ninth
Feature activation+0.016
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
inning
Tokeninning
Feature activation-0.002
Top resid features:
situations
Token situations
Feature activation-0.005
Top resid features:
)[
Token)[
Feature activation+0.012
Top resid features:
5
Token5
Feature activation+6.113
Top resid features:
][
Token][
Feature activation+0.007
Top resid features:
6
Token6
Feature activation+0.000
Top resid features:
][
Token][
Feature activation+0.000
Top resid features:
7
Token7
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
ome
Tokenome
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
other
Token other
Feature activation-0.001
Top resid features:
destinations
Token destinations
Feature activation-0.001
Top resid features:
.[
Token.[
Feature activation-0.008
Top resid features:
5
Token5
Feature activation+6.331
Top resid features:
]
Token]
Feature activation+0.003
Top resid features:
By
Token By
Feature activation-0.002
Top resid features:
1967
Token 1967
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
however
Token however
Feature activation-0.020
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
85
Token 85
Feature activation+0.006
Top resid features:
career
Token career
Feature activation+0.011
Top resid features:
blocks
Token blocks
Feature activation+0.001
Top resid features:
.[
Token.[
Feature activation-0.034
Top resid features:
5
Token5
Feature activation+6.183
Top resid features:
][
Token][
Feature activation-0.012
Top resid features:
6
Token6
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
endangered
Token endangered
Feature activation-0.003
Top resid features:
languages
Token languages
Feature activation-0.004
Top resid features:
would
Token would
Feature activation-0.002
Top resid features:
survive
Token survive
Feature activation-0.003
Top resid features:
.[
Token.[
Feature activation-0.008
Top resid features:
5
Token5
Feature activation+6.241
Top resid features:
][
Token][
Feature activation+0.005
Top resid features:
6
Token6
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
scientists
Token scientists
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
day
Token day
Feature activation-0.006
Top resid features:
.[
Token.[
Feature activation-0.030
Top resid features:
5
Token5
Feature activation+6.151
Top resid features:
]
Token]
Feature activation+0.014
Top resid features:
He
Token He
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
elected
Token elected
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
heavily
Token heavily
Feature activation-0.000
Top resid features:
forest
Token forest
Feature activation-0.000
Top resid features:
ed
Tokened
Feature activation-0.000
Top resid features:
.[
Token.[
Feature activation-0.023
Top resid features:
5
Token5
Feature activation+5.944
Top resid features:
]
Token]
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
This
TokenThis
Feature activation-0.007
Top resid features:
imposition
Token imposition
Feature activation-0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.16

Head 3: 0.04

Head 4: 0.04

Head 5: 0.03

Head 6: 0.02

Head 7: 0.50

Head 8: 0.04

Head 9: 0.04

Head 10: 0.04

Head 11: 0.03

Positive logits

Rodrig2.92

Seb2.75

ERT2.54

Raven2.40

Debug2.32

aleb2.28

atu2.28

Alberto2.25

ern2.23

ida2.23

alde2.15

msec2.15

assetsadobe2.14

Sakuya2.12

Nord2.12

Ravens2.12

odan2.11

roma2.10

uez2.09

Jacob2.09

Negative logits

Kitty-3.39

ppa-2.87

Clicker-2.82

-2.78

Chou-2.71

FUN-2.68

popcorn-2.62

Meow-2.58

Xperia-2.58

Pony-2.57

Garfield-2.47

FUN-2.45

Pledge-2.41

Buckley-2.40

Kit-2.38

lp-2.38

Lilly-2.35

Ples-2.35

Chloe-2.33

Crunch-2.32

INTERVAL 6.897 - 7.664
CONTAINS 0.000%

-
Token-
Feature activation+0.000
500
Token500
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.[
Token.[
Feature activation+7.664
2
Token2
Feature activation+0.000
][
Token][
Feature activation+5.863
5
Token5
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 6.131 - 6.897
CONTAINS 0.000%

kid
Tokenkid
Feature activation+0.000
and
Token and
Feature activation+0.000
Kyl
Token Kyl
Feature activation+0.000
a
Tokena
Feature activation+0.000
One
Token One
Feature activation+0.000
Dance
Token Dance
Feature activation+6.691
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Elsewhere
TokenElsewhere
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
feet
Token feet
Feature activation+0.000
were
Token were
Feature activation+0.000
involved
Token involved
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.510
"
Token"
Feature activation+0.000
Sc
TokenSc
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ubs
Tokenubs
Feature activation+0.000
Factor
Token Factor
Feature activation+0.000

INTERVAL 5.365 - 6.131
CONTAINS 0.001%

4
Token4
Feature activation+0.000
,
Token,
Feature activation+0.000
S
Token S
Feature activation+1.703
5
Token5
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+5.584
6
Token6
Feature activation+0.000
.[
Token.[
Feature activation+0.000
12
Token12
Feature activation+0.000
]
Token]
Feature activation+0.000
Sw
Token Sw
Feature activation+0.000
an
Token an
Feature activation+0.000
increased
Token increased
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
of
Token of
Feature activation+0.000
presence
Token presence
Feature activation+0.000
.[
Token.[
Feature activation+5.563
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.000
7
Token7
Feature activation+0.000
]
Token]
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
South
Token South
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Yugoslavia
Token Yugoslavia
Feature activation+0.000
.[
Token.[
Feature activation+5.460
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
Rating
Token Rating
Feature activation+0.000
:
Token:
Feature activation+0.049
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.129
1
Token1
Feature activation+0.000
/
Token/
Feature activation+5.597
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
12
Token 12
Feature activation+0.000
99
Token99
Feature activation+0.000
flood
Token flood
Feature activation+0.000
fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+6.041
almost
Token almost
Feature activation+5.394
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000

INTERVAL 4.598 - 5.365
CONTAINS 0.001%

the
Token the
Feature activation+0.000
Norman
Token Norman
Feature activation+0.000
conquest
Token conquest
Feature activation+0.000
of
Token of
Feature activation+0.000
England
Token England
Feature activation+0.000
.[
Token.[
Feature activation+4.851
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
85
Token 85
Feature activation+0.000
career
Token career
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000
.[
Token.[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+5.123
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
for
Token for
Feature activation+0.000
flight
Token flight
Feature activation+0.000
.[
Token.[
Feature activation+4.796
3
Token3
Feature activation+0.000
]
Token]
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
-
Token-
Feature activation+0.000
inning
Tokeninning
Feature activation+0.000
situations
Token situations
Feature activation+0.000
)[
Token)[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+5.204
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.415
7
Token7
Feature activation+0.000
]
Token]
Feature activation+0.000
to
Token to
Feature activation+0.000
investigations
Token investigations
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Royal
Token Royal
Feature activation+0.000
Institution
Token Institution
Feature activation+0.000
.[
Token.[
Feature activation+4.969
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
About
Token About
Feature activation+0.000
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+0.000

INTERVAL 3.832 - 4.598
CONTAINS 0.002%

abc
Tokenabc
Feature activation+0.000
123
Token123
Feature activation+0.000
::
Token::
Feature activation+0.000
",
Token",
Feature activation+0.000
from
Token from
Feature activation+0.000
=>
Token =>
Feature activation+4.086
5
Token 5
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
for
Token for
Feature activation+0.000
Secondary
Token Secondary
Feature activation+0.000
4
Token 4
Feature activation+0.000
,
Token,
Feature activation+0.000
5
Token 5
Feature activation+0.000
and
Token and
Feature activation+4.101
6
Token 6
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
join
Token join
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
.[
Token.[
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+4.230
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.015
7
Token7
Feature activation+0.000
][
Token][
Feature activation+0.000
8
Token8
Feature activation+0.000
security
Token security
Feature activation+0.000
on
Token on
Feature activation+0.000
blockchain
Token blockchain
Feature activation+0.000
in
Token in
Feature activation+0.000
five
Token five
Feature activation+0.000
or
Token or
Feature activation+4.287
ten
Token ten
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
probably
Token probably
Feature activation+0.258
ten
Token ten
Feature activation+0.000
in
Token in
Feature activation+0.000
between
Token between
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
5
Token 5
Feature activation+0.000
or
Token or
Feature activation+4.459
10
Token 10
Feature activation+0.000
videos
Token videos
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
type
Token type
Feature activation+0.000

INTERVAL 3.066 - 3.832
CONTAINS 0.001%

men
Token men
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+1.281
5
Token5
Feature activation+0.000
and
Token and
Feature activation+0.000
A
Token A
Feature activation+3.572
6
Token6
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+0.000
x
Token x
Feature activation+0.000
were
Token were
Feature activation+0.000
moved
Token moved
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
experimental
Token experimental
Feature activation+0.000
in
Token in
Feature activation+3.501
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
along
Token along
Feature activation+0.000
IS
TokenIS
Feature activation+0.000
OD
TokenOD
Feature activation+0.000
amp
Token amp
Feature activation+0.000
ute
Tokenute
Feature activation+0.000
e
Tokene
Feature activation+0.000
A
Token A
Feature activation+3.144
5
Token5
Feature activation+0.000
sw
Token sw
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
to
Token to
Feature activation+0.000
execute
Token execute
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
always
Token always
Feature activation+0.000
took
Token took
Feature activation+3.774
5
Token 5
Feature activation+0.000
cycles
Token cycles
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Rating
Token Rating
Feature activation+0.000
:
Token:
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
/
Token/
Feature activation+3.099
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
12
Token 12
Feature activation+0.000
46
Token46
Feature activation+0.000

INTERVAL 2.299 - 3.066
CONTAINS 0.002%

star
Tokenstar
Feature activation+0.000
(
Token (
Feature activation+0.000
9
Token9
Feature activation+0.000
a
Tokena
Feature activation+0.000
+
Token+
Feature activation+0.000
/
Token/
Feature activation+2.756
b
Tokenb
Feature activation+0.000
,
Token,
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
)
Token)
Feature activation+0.000
in
Token in
Feature activation+0.000
mantle
Token mantle
Feature activation+0.000
(
Token (
Feature activation+0.000
Figure
TokenFigure
Feature activation+0.000
5
Token 5
Feature activation+0.000
5
Token 5
Feature activation+0.000
5
Token 5
Feature activation+2.993
5
Token 5
Feature activation+4.696
2
Token 2
Feature activation+1.585
3
Token 3
Feature activation+0.265
4
Token 4
Feature activation+0.000
5
Token 5
Feature activation+0.270
donors
Token donors
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
another
Token another
Feature activation+0.000
five
Token five
Feature activation+0.000
to
Token to
Feature activation+2.543
transplant
Token transplant
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Though
TokenThough
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FOR
TokenFOR
Feature activation+0.000
WAR
TokenWAR
Feature activation+0.000
DS
TokenDS
Feature activation+0.000
(
Token (
Feature activation+2.306
6
Token6
Feature activation+0.000
):
Token):
Feature activation+0.000
Pierre
Token Pierre
Feature activation+0.000
Da
Token Da
Feature activation+0.000
Silva
Token Silva
Feature activation+0.000
as
Token as
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
5
Token5
Feature activation+0.000
âĪĴ
Token âĪĴ
Feature activation+2.317
6
Token 6
Feature activation+0.000
)
Token)
Feature activation+0.000
ÃĹ
Token ÃĹ
Feature activation+0.128
7
Token 7
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.533 - 2.299
CONTAINS 0.004%

har
Tokenhar
Feature activation+0.000
med
Tokenmed
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+2.012
83
Token 83
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000
killed
Token killed
Feature activation+0.000
.
Token.
Feature activation+0.000
BS
TokenBS
Feature activation+0.000
Y
TokenY
Feature activation+0.000
B
TokenB
Feature activation+0.000
JP
TokenJP
Feature activation+0.000
)
Token)
Feature activation+0.000
September
Token September
Feature activation+1.619
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
Rhode
Token Rhode
Feature activation+0.000
Island
Token Island
Feature activation+0.000
:
Token:
Feature activation+0.388
7
Token 7
Feature activation+1.588
.
Token.
Feature activation+0.000
5
Token5
Feature activation+4.334
6
Token 6
Feature activation+0.000
.
Token.
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
Joan
Token Joan
Feature activation+0.000
Cham
Token Cham
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
Group
Token Group
Feature activation+0.000
(
Token (
Feature activation+1.673
6
Token6
Feature activation+0.000
th
Tokenth
Feature activation+0.000
of
Token of
Feature activation+0.000
August
Token August
Feature activation+0.000
).
Token).
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
later
Token later
Feature activation+0.000
revised
Token revised
Feature activation+0.000
upward
Token upward
Feature activation+0.000
to
Token to
Feature activation+1.813
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
gallons
Token gallons
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.766 - 1.533
CONTAINS 0.008%

release
Token release
Feature activation+0.000
date
Token date
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.105
$
Token$
Feature activation+1.232
30
Token30
Feature activation+0.000
EAR
Token EAR
Feature activation+0.000
LY
TokenLY
Feature activation+0.000
ESC
Token ESC
Feature activation+0.000
APE
TokenAPE
Feature activation+0.000
conced
Token conced
Feature activation+0.000
ing
Tokening
Feature activation+0.000
four
Token four
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.896
five
Token five
Feature activation+0.000
penalties
Token penalties
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
57
Token57
Feature activation+0.000
Alabama
Token Alabama
Feature activation+0.000
7
Token 7
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+5.521
6
Token 6
Feature activation+1.326
3
Token 3
Feature activation+0.486
3
Token 3
Feature activation+0.266
9
Token 9
Feature activation+0.032
.
Token.
Feature activation+0.000
92
Token92
Feature activation+0.000
In
Token In
Feature activation+0.000
aug
Tokenaug
Feature activation+0.000
uration
Tokenuration
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.939
209
Token 209
Feature activation+0.000
defendants
Token defendants
Feature activation+0.000
were
Token were
Feature activation+0.000
indicted
Token indicted
Feature activation+0.000
on
Token on
Feature activation+0.000
k
Token k
Feature activation+0.852
''
Token''
Feature activation+0.000
(
Token (
Feature activation+0.000
P
TokenP
Feature activation+0.000
a
Token a
Feature activation+0.324
a
Token a
Feature activation+0.872
')
Token')
Feature activation+0.000
=
Token =
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.000
a
Token a
Feature activation+0.169

INTERVAL 0.000 - 0.766
CONTAINS 99.981%

on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000
matter
Token matter
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
says
Token says
Feature activation+0.000
photographer
Token photographer
Feature activation+0.000
Dwight
Token Dwight
Feature activation+0.000
Es
Token Es
Feature activation+0.000
7
Token7
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
poop
Token poop
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
factory
Token factory
Feature activation+0.000
waste
Token waste
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
the
Token the
Feature activation+0.000
senators
Token senators
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
views
Token views
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
fate
Token fate
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
dinosaurs
Token dinosaurs
Feature activation+0.000
the
Token the
Feature activation+0.000
Breaking
Token Breaking
Feature activation+0.000
News
Token News
Feature activation+0.000
newsletter
Token newsletter
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
inbox
Token inbox
Feature activation+0.000
We
Token We
Feature activation+0.000
're
Token're
Feature activation+0.000
sorry
Token sorry
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.000
,
Token,
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
-
Token-
Feature activation+0.000
Friday
TokenFriday
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
strive
Token strive
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
our
Token our
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 H10.7: (feature 23266)

TOP ACTIVATIONS
MAX = 5.919

King
Token King
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
's
Token's
Feature activation+5.919
Philip
Token Philip
Feature activation+0.000
R
Token R
Feature activation+0.000
ucker
Tokenucker
Feature activation+0.000
,
Token,
Feature activation+0.000
less
Token less
Feature activation+0.000
and
Token and
Feature activation+0.000
CE
Token CE
Feature activation+0.000
-
Token -
Feature activation+0.000
Before
Token Before
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+5.291
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
Sammy
Token Sammy
Feature activation+0.000
has
Token has
Feature activation+0.000
announced
Token announced
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+1.887
new
Token new
Feature activation+5.287
machine
Token machine
Feature activation+0.000
is
Token is
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
occur
Token occur
Feature activation+0.000
in
Token in
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+4.336
p
Tokenp
Feature activation+0.000
olar
Tokenolar
Feature activation+0.000
sol
Token sol
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ents
Tokenents
Feature activation+0.000
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+4.303
p
Tokenp
Feature activation+0.003
aul
Tokenaul
Feature activation+0.000
Era
Token Era
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
V
TokenV
Feature activation+0.000
Do
Token Do
Feature activation+0.000
ña
Tokenña
Feature activation+4.212
P
Token P
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Philippine
Token Philippine
Feature activation+0.000
make
Token make
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+4.003
P
Token P
Feature activation+0.199
ree
Tokenree
Feature activation+0.000
ce
Tokence
Feature activation+0.000
spent
Token spent
Feature activation+0.000
his
Token his
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
is
Token is
Feature activation+0.000
intermediary
Token intermediary
Feature activation+0.000
between
Token between
Feature activation+0.177
Mo
Token Mo
Feature activation+0.000
only
Token only
Feature activation+3.747
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
only
Token only
Feature activation+0.134
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
H
TokenH
Feature activation+0.000
|
Token|
Feature activation+0.000
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
)
Token)
Feature activation+0.000
<
Token <
Feature activation+3.745
P
TokenP
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.000
or
Token or
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+3.668
RO
TokenRO
Feature activation+0.000
OT
TokenOT
Feature activation+1.119
pu
Tokenpu
Feature activation+0.000
C
TokenC
Feature activation+0.000
K
TokenK
Feature activation+0.000
Before
Token Before
Feature activation+0.000
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+3.648
our
Token our
Feature activation+0.000
starting
Token starting
Feature activation+0.000
point
Token point
Feature activation+0.000
of
Token of
Feature activation+1.825
Pak
Token Pak
Feature activation+0.000
rical
Tokenrical
Feature activation+0.000
foundations
Token foundations
Feature activation+0.000
of
Token of
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+0.000
2
Token 2
Feature activation+3.605
p
Token p
Feature activation+0.000
ore
Tokenore
Feature activation+0.884
that
Token that
Feature activation+0.000
give
Token give
Feature activation+0.000
rise
Token rise
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.651
Vict
TokenVict
Feature activation+0.000
orian
Tokenorian
Feature activation+0.000
company
Token company
Feature activation+3.436
Patt
Token Patt
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
Foods
Token Foods
Feature activation+0.000
announced
Token announced
Feature activation+0.000
on
Token on
Feature activation+0.000
is
Token is
Feature activation+0.000
needed
Token needed
Feature activation+0.000
with
Token with
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+0.000
2
Token 2
Feature activation+3.399
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
.
Token.
Feature activation+0.000
Later
Token Later
Feature activation+0.000
,
Token,
Feature activation+0.000
2
Token 2
Feature activation+0.163
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+0.000
graphene
Token graphene
Feature activation+3.389
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
imply
Token imply
Feature activation+0.000
that
Token that
Feature activation+0.000
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
250
Token 250
Feature activation+1.860
actual
Token actual
Feature activation+3.385
sports
Token sports
Feature activation+0.000
fans
Token fans
Feature activation+0.000
participated
Token participated
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
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+0.445
for
Token for
Feature activation+3.320
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+0.000
shown
Token shown
Feature activation+0.000
.
Token.
Feature activation+0.000
Cle
Token Cle
Feature activation+0.000
avage
Tokenavage
Feature activation+0.000
sites
Token sites
Feature activation+0.000
for
Token for
Feature activation+3.203
the
Token the
Feature activation+0.254
restriction
Token restriction
Feature activation+0.000
enzyme
Token enzyme
Feature activation+0.600
N
Token N
Feature activation+0.000
si
Tokensi
Feature activation+0.000
alo
Tokenalo
Feature activation+0.000
Alto
Token Alto
Feature activation+0.000
Online
Token Online
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
@
Token @
Feature activation+3.203
P
TokenP
Feature activation+1.543
alo
Tokenalo
Feature activation+0.000
Al
TokenAl
Feature activation+0.000
to
Tokento
Feature activation+0.000
Week
TokenWeek
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
beauty
Token beauty
Feature activation+0.000
of
Token of
Feature activation+3.179
P
Token P
Feature activation+0.923
ono
Tokenono
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.118

Top DFA by src position
MAX = 6.523

Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
Post
Token Post
Feature activation-0.013
Top resid features:
's
Token's
Feature activation+0.024
Top resid features:
Philip
Token Philip
Feature activation+6.523
Top resid features:
R
Token R
Feature activation-0.004
Top resid features:
ucker
Tokenucker
Feature activation+0.037
Top resid features:
interviews
Token interviews
Feature activation+0.001
Top resid features:
Rep
Token Rep
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
though
Token though
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Ch
Token Ch
Feature activation+0.006
Top resid features:
ander
Tokenander
Feature activation+0.013
Top resid features:
p
Tokenp
Feature activation+5.868
Top resid features:
aul
Tokenaul
Feature activation-0.021
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
not
Token not
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
my
Token my
Feature activation-0.000
Top resid features:
like
Token like
Feature activation-0.000
Top resid features:
other
Token other
Feature activation-0.002
Top resid features:
gaming
Token gaming
Feature activation+0.037
Top resid features:
options
Token options
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
p
Token p
Feature activation+2.636
Top resid features:
ach
Tokenach
Feature activation+0.012
Top resid features:
isl
Tokenisl
Feature activation+0.004
Top resid features:
ot
Tokenot
Feature activation+0.000
Top resid features:
systems
Token systems
Feature activation+0.033
Top resid features:
are
Token are
Feature activation-0.006
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
usually
Token usually
Feature activation+0.004
Top resid features:
tolerate
Token tolerate
Feature activation+0.003
Top resid features:
non
Token non
Feature activation-0.057
Top resid features:
-
Token-
Feature activation-0.051
Top resid features:
p
Tokenp
Feature activation+4.728
Top resid features:
olar
Tokenolar
Feature activation+0.011
Top resid features:
sol
Token sol
Feature activation-0.011
Top resid features:
v
Tokenv
Feature activation-0.006
Top resid features:
ents
Tokenents
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
though
Token though
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Ch
Token Ch
Feature activation+0.002
Top resid features:
ander
Tokenander
Feature activation+0.001
Top resid features:
p
Tokenp
Feature activation+3.064
Top resid features:
aul
Tokenaul
Feature activation-0.008
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
not
Token not
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
my
Token my
Feature activation-0.000
Top resid features:
Ren
Token Ren
Feature activation+0.003
Top resid features:
amed
Tokenamed
Feature activation+0.004
Top resid features:
:
Token:
Feature activation-0.008
Top resid features:
Do
Token Do
Feature activation-0.001
Top resid features:
ña
Tokenña
Feature activation+0.010
Top resid features:
P
Token P
Feature activation+4.791
Top resid features:
az
Tokenaz
Feature activation+0.024
Top resid features:
in
Token in
Feature activation-0.030
Top resid features:
1981
Token 1981
Feature activation-0.005
Top resid features:
Ref
Token Ref
Feature activation-0.000
Top resid features:
it
Tokenit
Feature activation+0.007
Top resid features:
weekend
Token weekend
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
British
Token British
Feature activation+0.002
Top resid features:
engineer
Token engineer
Feature activation+0.001
Top resid features:
Chris
Token Chris
Feature activation+0.007
Top resid features:
P
Token P
Feature activation+4.279
Top resid features:
ree
Tokenree
Feature activation+0.210
Top resid features:
ce
Tokence
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
54
Token 54
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
S
Token S
Feature activation-0.003
Top resid features:
only
Token only
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
graphene
Token graphene
Feature activation+0.062
Top resid features:
p
Token p
Feature activation+2.026
Top resid features:
ore
Tokenore
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.101
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
applied
Token applied
Feature activation+0.027
Top resid features:
E
TokenE
Feature activation-0.004
Top resid features:
|
Token|
Feature activation+0.005
Top resid features:
H
TokenH
Feature activation+0.001
Top resid features:
)
Token)
Feature activation-0.002
Top resid features:
<
Token <
Feature activation-0.000
Top resid features:
P
TokenP
Feature activation+1.217
Top resid features:
(
Token(
Feature activation+0.008
Top resid features:
~
Token~
Feature activation-0.003
Top resid features:
E
TokenE
Feature activation-0.002
Top resid features:
),
Token),
Feature activation-0.003
Top resid features:
so
Token so
Feature activation-0.010
Top resid features:
rent
Tokenrent
Feature activation-0.005
Top resid features:
star
Tokenstar
Feature activation+0.024
Top resid features:
craft
Tokencraft
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
pu
Tokenpu
Feature activation+4.414
Top resid features:
C
TokenC
Feature activation-0.001
Top resid features:
K
TokenK
Feature activation+0.006
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.002
Top resid features:
https
Token https
Feature activation-0.003
Top resid features:
://
Token://
Feature activation-0.001
Top resid features:
night
Token night
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
From
TokenFrom
Feature activation-0.003
Top resid features:
P
Token P
Feature activation+1.754
Top resid features:
aks
Tokenaks
Feature activation+0.010
Top resid features:
ong
Tokenong
Feature activation+0.015
Top resid features:
back
Token back
Feature activation+0.007
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
Pak
Token Pak
Feature activation+1.137
Top resid features:
Mo
Token Mo
Feature activation-0.002
Top resid features:
only
Token only
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
S
Token S
Feature activation-0.000
Top resid features:
only
Token only
Feature activation+0.007
Top resid features:
nanop
Token nanop
Feature activation+2.275
Top resid features:
ores
Tokenores
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
higher
Token higher
Feature activation-0.001
Top resid features:
water
Token water
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.045
Top resid features:
company
Token company
Feature activation+0.091
Top resid features:
Patt
Token Patt
Feature activation+3.566
Top resid features:
ies
Tokenies
Feature activation+0.077
Top resid features:
Foods
Token Foods
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
expand
Token expand
Feature activation+0.001
Top resid features:
its
Token its
Feature activation-0.000
Top resid features:
Mo
Token Mo
Feature activation-0.006
Top resid features:
only
Token only
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
S
Token S
Feature activation-0.000
Top resid features:
only
Token only
Feature activation+0.013
Top resid features:
nanop
Token nanop
Feature activation+2.231
Top resid features:
ores
Tokenores
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
higher
Token higher
Feature activation-0.002
Top resid features:
water
Token water
Feature activation-0.000
Top resid features:
S
Token S
Feature activation-0.011
Top resid features:
only
Token only
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
graphene
Token graphene
Feature activation+0.033
Top resid features:
p
Token p
Feature activation+1.365
Top resid features:
ore
Tokenore
Feature activation+0.011
Top resid features:
for
Token for
Feature activation+0.031
Top resid features:
all
Token all
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
applied
Token applied
Feature activation+0.029
Top resid features:
down
Token down
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation-0.027
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
60
Token60
Feature activation-0.004
Top resid features:
P
Token P
Feature activation+4.453
Top resid features:
PM
TokenPM
Feature activation+0.105
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
devoted
Token devoted
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
sports
Token sports
Feature activation+0.013
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
bad
Token bad
Feature activation-0.017
Top resid features:
luck
Token luck
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
P
Token P
Feature activation+2.084
Top resid features:
omin
Tokenomin
Feature activation+0.045
Top resid features:
ville
Tokenville
Feature activation+0.002
Top resid features:
registered
Token registered
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
career
Token career
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.022
Top resid features:
Integ
TokenInteg
Feature activation-0.022
Top resid features:
ration
Tokenration
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
p
Token p
Feature activation+2.671
Top resid features:
IC
TokenIC
Feature activation+0.007
Top resid features:
3
Token3
Feature activation-0.005
Top resid features:
into
Token into
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
HE
Token HE
Feature activation+0.016
Top resid features:
the
Token the
Feature activation-0.030
Top resid features:
Palo
Token Palo
Feature activation+0.502
Top resid features:
Alto
Token Alto
Feature activation+0.041
Top resid features:
Weekly
Token Weekly
Feature activation+0.117
Top resid features:
/
Token/
Feature activation+0.015
Top resid features:
P
TokenP
Feature activation+3.120
Top resid features:
alo
Tokenalo
Feature activation+0.028
Top resid features:
Alto
Token Alto
Feature activation-0.006
Top resid features:
Online
Token Online
Feature activation-0.004
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
Twitter
Token Twitter
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
now
Token now
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
with
Token with
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
P
Token P
Feature activation+3.565
Top resid features:
ono
Tokenono
Feature activation+0.367
Top resid features:
Player
TokenPlayer
Feature activation+0.081
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
you
Token you
Feature activation-0.007
Top resid features:
can
Token can
Feature activation-0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.06

Head 2: 0.03

Head 3: 0.02

Head 4: 0.03

Head 5: 0.02

Head 6: 0.05

Head 7: 0.50

Head 8: 0.03

Head 9: 0.04

Head 10: 0.10

Head 11: 0.06

Positive logits

hurst2.70

Elf2.43

ahl2.22

19322.22

emonium2.21

////////////////////////////////2.20

unal2.19

Harding2.16

maid2.15

aid2.15

Elijah2.13

adian2.12

alf2.11

ald2.09

eer2.09

alty2.09

alties2.08

Alley2.08

elf2.07

ersion2.06

Negative logits

perl-2.85

Peters-2.64

Pony-2.59

PIN-2.57

Mp-2.52

pony-2.45

PI-2.44

PAC-2.44

mp-2.42

Pak-2.41

Pact-2.40

Proposition-2.40

Pillar-2.39

Papa-2.38

Pon-2.37

WP-2.33

plugs-2.32

psi-2.32

pi-2.31

KP-2.30

INTERVAL 5.327 - 5.919
CONTAINS 0.000%

King
Token King
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
's
Token's
Feature activation+5.919
Philip
Token Philip
Feature activation+0.000
R
Token R
Feature activation+0.000
ucker
Tokenucker
Feature activation+0.000
,
Token,
Feature activation+0.000
less
Token less
Feature activation+0.000

INTERVAL 4.735 - 5.327
CONTAINS 0.000%

Sammy
Token Sammy
Feature activation+0.000
has
Token has
Feature activation+0.000
announced
Token announced
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+1.887
new
Token new
Feature activation+5.287
machine
Token machine
Feature activation+0.000
is
Token is
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+0.000
and
Token and
Feature activation+0.000
CE
Token CE
Feature activation+0.000
-
Token -
Feature activation+0.000
Before
Token Before
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+5.291
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000

INTERVAL 4.143 - 4.735
CONTAINS 0.000%

of
Token of
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
occur
Token occur
Feature activation+0.000
in
Token in
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+4.336
p
Tokenp
Feature activation+0.000
olar
Tokenolar
Feature activation+0.000
sol
Token sol
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ents
Tokenents
Feature activation+0.000
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+4.303
p
Tokenp
Feature activation+0.003
aul
Tokenaul
Feature activation+0.000
Era
Token Era
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
V
TokenV
Feature activation+0.000
Do
Token Do
Feature activation+0.000
ña
Tokenña
Feature activation+4.212
P
Token P
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Philippine
Token Philippine
Feature activation+0.000

INTERVAL 3.551 - 4.143
CONTAINS 0.001%

https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+3.668
RO
TokenRO
Feature activation+0.000
OT
TokenOT
Feature activation+1.119
pu
Tokenpu
Feature activation+0.000
C
TokenC
Feature activation+0.000
K
TokenK
Feature activation+0.000
make
Token make
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+4.003
P
Token P
Feature activation+0.199
ree
Tokenree
Feature activation+0.000
ce
Tokence
Feature activation+0.000
spent
Token spent
Feature activation+0.000
his
Token his
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
is
Token is
Feature activation+0.000
intermediary
Token intermediary
Feature activation+0.000
between
Token between
Feature activation+0.177
Mo
Token Mo
Feature activation+0.000
only
Token only
Feature activation+3.747
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
only
Token only
Feature activation+0.134
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
rical
Tokenrical
Feature activation+0.000
foundations
Token foundations
Feature activation+0.000
of
Token of
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+0.000
2
Token 2
Feature activation+3.605
p
Token p
Feature activation+0.000
ore
Tokenore
Feature activation+0.884
that
Token that
Feature activation+0.000
give
Token give
Feature activation+0.000
rise
Token rise
Feature activation+0.000
H
TokenH
Feature activation+0.000
|
Token|
Feature activation+0.000
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
)
Token)
Feature activation+0.000
<
Token <
Feature activation+3.745
P
TokenP
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 2.959 - 3.551
CONTAINS 0.001%

ore
Tokenore
Feature activation+0.000
area
Token area
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.014
type
Token type
Feature activation+0.000
of
Token of
Feature activation+3.143
the
Token the
Feature activation+3.106
p
Token p
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
plays
Token plays
Feature activation+0.000
a
Token a
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+0.445
for
Token for
Feature activation+3.320
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+0.000
is
Token is
Feature activation+0.000
needed
Token needed
Feature activation+0.000
with
Token with
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+0.000
2
Token 2
Feature activation+3.399
nanop
Token nanop
Feature activation+0.000
ores
Tokenores
Feature activation+0.000
.
Token.
Feature activation+0.000
Later
Token Later
Feature activation+0.000
,
Token,
Feature activation+0.000
area
Token area
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.014
type
Token type
Feature activation+0.000
of
Token of
Feature activation+3.143
the
Token the
Feature activation+3.106
p
Token p
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
plays
Token plays
Feature activation+0.000
a
Token a
Feature activation+0.000
less
Token less
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
beauty
Token beauty
Feature activation+0.000
of
Token of
Feature activation+3.179
P
Token P
Feature activation+0.923
ono
Tokenono
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.118

INTERVAL 2.367 - 2.959
CONTAINS 0.002%

,
Token,
Feature activation+0.000
Shiv
Token Shiv
Feature activation+0.000
nar
Tokennar
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+2.858
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
became
Token became
Feature activation+0.000
a
Token a
Feature activation+0.000
link
Token link
Feature activation+0.000
women
Token women
Feature activation+0.000
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
ash
Token ash
Feature activation+0.000
ram
Tokenram
Feature activation+0.000
in
Token in
Feature activation+2.717
2002
Token 2002
Feature activation+0.000
,
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
below
Token below
Feature activation+0.000
advertisement
Token advertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.660
.
Token.
Feature activation+2.737
Stone
Token Stone
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
unveiling
Token unveiling
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
the
Token the
Feature activation+0.000
line
Token line
Feature activation+0.000
.
Token.
Feature activation+1.015
A
Token A
Feature activation+0.000
loss
Token loss
Feature activation+0.000
for
Token for
Feature activation+2.739
Ch
Token Ch
Feature activation+0.000
ivas
Tokenivas
Feature activation+0.000
would
Token would
Feature activation+0.000
likely
Token likely
Feature activation+0.000
mean
Token mean
Feature activation+0.000
which
Token which
Feature activation+0.000
was
Token was
Feature activation+0.000
24
Token 24
Feature activation+0.000
th
Tokenth
Feature activation+0.000
on
Token on
Feature activation+1.199
the
Token the
Feature activation+2.689
P
Token P
Feature activation+0.000
GA
TokenGA
Feature activation+0.000
Tour
Token Tour
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.776 - 2.367
CONTAINS 0.006%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
250
Token 250
Feature activation+1.860
actual
Token actual
Feature activation+3.385
sports
Token sports
Feature activation+0.000
fans
Token fans
Feature activation+0.000
participated
Token participated
Feature activation+0.000
in
Token in
Feature activation+0.000
listening
Token listening
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
p
Token p
Feature activation+0.000
itter
Tokenitter
Feature activation+0.000
p
Token p
Feature activation+2.149
atter
Tokenatter
Feature activation+0.000
of
Token of
Feature activation+0.000
children
Token children
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
"
Token"
Feature activation+0.000
That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000
very
Token very
Feature activation+0.000
thoughtful
Token thoughtful
Feature activation+0.000
."
Token."
Feature activation+2.034
Pyrrha
Token Pyrrha
Feature activation+0.000
smiled
Token smiled
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Thank
TokenThank
Feature activation+0.000
complete
Token complete
Feature activation+0.000
index
Token index
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
information
Token information
Feature activation+0.000
about
Token about
Feature activation+2.046
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
our
Token our
Feature activation+0.000
University
Token University
Feature activation+0.000
of
Token of
Feature activation+0.000
Pug
Token Pug
Feature activation+0.000
et
Tokenet
Feature activation+0.000
Sound
Token Sound
Feature activation+0.000
in
Token in
Feature activation+1.907
Washington
Token Washington
Feature activation+0.000
also
Token also
Feature activation+0.000
told
Token told
Feature activation+0.000
students
Token students
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 1.184 - 1.776
CONTAINS 0.013%

mill
Tokenmill
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+1.342
el
Tokenel
Feature activation+0.000
osi
Tokenosi
Feature activation+0.000
made
Token made
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
on
Token on
Feature activation+0.000
ogo
Tokenogo
Feature activation+0.000
.
Token.
Feature activation+0.279
In
Token In
Feature activation+0.000
seven
Token seven
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
,
Token,
Feature activation+1.476
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
raised
Token raised
Feature activation+0.000
a
Token a
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
op
Token op
Feature activation+0.000
")
Token")
Feature activation+0.000
(
Token (
Feature activation+0.000
error
Tokenerror
Feature activation+0.000
"
Token "
Feature activation+0.000
no
Tokenno
Feature activation+1.561
e
Token e
Feature activation+0.000
")
Token")
Feature activation+0.000
(
Token (
Feature activation+0.000
const
Tokenconst
Feature activation+0.000
a
Token a
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
programs
Token programs
Feature activation+0.000
.
Token.
Feature activation+0.648
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.603
Through
TokenThrough
Feature activation+1.238
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+0.000
be
Token be
Feature activation+0.000
mod
Token mod
Feature activation+0.000
elled
Tokenelled
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
M
Token M
Feature activation+1.229
DP
TokenDP
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
because
Token because
Feature activation+0.000
one
Token one
Feature activation+0.000

INTERVAL 0.592 - 1.184
CONTAINS 0.041%

half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
participants
Token participants
Feature activation+0.000
preferred
Token preferred
Feature activation+0.000
Single
Token Single
Feature activation+0.890
P
Token P
Feature activation+0.000
ayer
Tokenayer
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Token a
Feature activation+0.000
system
Token system
Feature activation+0.000
B
TokenB
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
it
Tokenit
Feature activation+0.000
Tim
Token Tim
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
S
Token S
Feature activation+0.665
DP
TokenDP
Feature activation+0.000
J
Token J
Feature activation+0.000
alan
Tokenalan
Feature activation+0.000
B
Token B
Feature activation+0.000
esar
Tokenesar
Feature activation+0.000
John
Token John
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
son
Tokenson
Feature activation+0.000
.
Token.
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
John
Token John
Feature activation+0.843
Paul
Token Paul
Feature activation+0.000
son
Tokenson
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Goldman
Token Goldman
Feature activation+0.000
News
Token News
Feature activation+0.000
and
Token and
Feature activation+0.000
CJ
Token CJ
Feature activation+0.000
OB
TokenOB
Feature activation+0.000
680
Token 680
Feature activation+0.000
shows
Token shows
Feature activation+0.840
the
Token the
Feature activation+0.899
800
Token 800
Feature activation+0.000
Manit
Token Manit
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
Terry
Token Terry
Feature activation+0.000
Gill
Token Gill
Feature activation+0.000
iam
Tokeniam
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.823
The
TokenThe
Feature activation+0.000
General
Token General
Feature activation+0.000
-
Token-
Feature activation+0.000
Direct
TokenDirect
Feature activation+0.000
orate
Tokenorate
Feature activation+0.000

INTERVAL 0.000 - 0.592
CONTAINS 99.935%

're
Token're
Feature activation+0.000
really
Token really
Feature activation+0.000
pleased
Token pleased
Feature activation+0.000
Al
Token Al
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
air
Tokenair
Feature activation+0.000
is
Token is
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
and
Token and
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
Across
TokenAcross
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
,
Token,
Feature activation+0.000
vegan
Token vegan
Feature activation+0.000
restaurants
Token restaurants
Feature activation+0.000
and
Token and
Feature activation+0.000
shops
Token shops
Feature activation+0.000
are
Token are
Feature activation+0.000
spr
Token spr
Feature activation+0.000
outing
Tokenouting
Feature activation+0.000
up
Token up
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
sofa
Token sofa
Feature activation+0.000
across
Token across
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
he
Token he
Feature activation+0.000
believed
Token believed
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
over
Tokenover
Feature activation+0.000
and
Token and
Feature activation+0.000
over
Token over
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
constantly
Token constantly
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
political
Token political
Feature activation+0.000
unification
Token unification
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
working
Token working
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