H10.3 top features

Top feature 0 in H10.3: (feature 22088)

TOP ACTIVATIONS
MAX = 6.263

we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.599
$
Token $
Feature activation+0.695
75
Token75
Feature activation+6.263
m
Tokenm
Feature activation+3.837
in
Token in
Feature activation+0.190
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+1.130
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
about
Token about
Feature activation+0.390
six
Token six
Feature activation+4.508
miles
Token miles
Feature activation+5.672
(
Token (
Feature activation+0.343
10
Token10
Feature activation+3.459
km
Tokenkm
Feature activation+2.072
)
Token)
Feature activation+3.105
east
Token east
Feature activation+4.704
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
,
Token,
Feature activation+0.039
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
leaders
Token leaders
Feature activation+0.285
on
Token on
Feature activation+5.519
Sunday
Token Sunday
Feature activation+1.661
afternoon
Token afternoon
Feature activation+0.166
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
journey
Token journey
Feature activation+0.000
the
Token the
Feature activation+0.877
Greens
Token Greens
Feature activation+1.378
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
motion
Token motion
Feature activation+0.000
on
Token on
Feature activation+4.946
Wednesday
Token Wednesday
Feature activation+0.519
afternoon
Token afternoon
Feature activation+0.340
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.542
Hanson
Token Hanson
Feature activation+0.529
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
,
Token,
Feature activation+0.039
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
Survey
Token Survey
Feature activation+2.405
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+1.516
.
Token.
Feature activation+0.000
1
Token1
Feature activation+4.520
magnitude
Token magnitude
Feature activation+0.758
quake
Token quake
Feature activation+1.236
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
,
Token,
Feature activation+0.039
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
about
Token about
Feature activation+0.390
six
Token six
Feature activation+4.508
miles
Token miles
Feature activation+5.672
(
Token (
Feature activation+0.343
10
Token10
Feature activation+3.459
km
Tokenkm
Feature activation+2.072
)
Token)
Feature activation+3.105
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
the
Token the
Feature activation+4.502
Senate
Token Senate
Feature activation+3.685
he
Token he
Feature activation+0.065
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.100
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
data
Token data
Feature activation+0.198
was
Token was
Feature activation+0.000
posted
Token posted
Feature activation+1.666
on
Token on
Feature activation+3.891
a
Token a
Feature activation+0.000
profile
Token profile
Feature activation+0.000
called
Token called
Feature activation+0.000
EM
Token EM
Feature activation+0.000
LE
TokenLE
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.599
$
Token $
Feature activation+0.695
75
Token75
Feature activation+6.263
m
Tokenm
Feature activation+3.837
in
Token in
Feature activation+0.190
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+1.130
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
or
Token or
Feature activation+0.000
injuries
Token injuries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
U
TokenU
Feature activation+3.708
ps
Tokenps
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ge
Tokenge
Feature activation+0.011
in
Token in
Feature activation+0.000
big
Token big
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
the
Token the
Feature activation+4.502
Senate
Token Senate
Feature activation+3.685
he
Token he
Feature activation+0.065
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.100
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.968
would
Token would
Feature activation+0.388
now
Token now
Feature activation+0.232
settle
Token settle
Feature activation+0.897
the
Token the
Feature activation+0.764
matter
Token matter
Feature activation+1.218
promptly
Token promptly
Feature activation+3.669
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
magnitude
Token magnitude
Feature activation+0.758
quake
Token quake
Feature activation+1.236
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
,
Token,
Feature activation+0.039
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.462
US
Token US
Feature activation+3.449
Geological
Token Geological
Feature activation+2.597
Survey
Token Survey
Feature activation+2.405
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+1.516
promptly
Token promptly
Feature activation+3.669
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
the
Token the
Feature activation+4.502
Senate
Token Senate
Feature activation+3.685
he
Token he
Feature activation+0.065
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.100
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000
is
Token is
Feature activation+0.000
worth
Token worth
Feature activation+0.058
âĤ¬
Token âĤ¬
Feature activation+0.000
65
Token65
Feature activation+3.204
m
Tokenm
Feature activation+0.847
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
ulas
Tokenulas
Feature activation+0.556
has
Token has
Feature activation+0.000
1
Token1
Feature activation+4.520
magnitude
Token magnitude
Feature activation+0.758
quake
Token quake
Feature activation+1.236
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
does
Token does
Feature activation+0.000
seem
Token seem
Feature activation+0.000
a
Token a
Feature activation+0.000
fairly
Token fairly
Feature activation+0.000
distant
Token distant
Feature activation+0.000
prospect
Token prospect
Feature activation+2.639
right
Token right
Feature activation+0.625
now
Token now
Feature activation+0.702
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.415
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 6.572

Jonathan
Token Jonathan
Feature activation-0.000
Top resid features:
Franklin
Token Franklin
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Guardian
Token Guardian
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+6.572
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Since
TokenSince
Feature activation+0.001
Top resid features:
2009
Token 2009
Feature activation-0.001
Top resid features:
Earth
Token Earth
Feature activation-0.001
Top resid features:
rotation
Token rotation
Feature activation+0.001
Top resid features:
slows
Token slows
Feature activation+0.003
Top resid features:
Read
Token Read
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+3.574
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
The
TokenThe
Feature activation+0.002
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
Geological
Token Geological
Feature activation-0.000
Top resid features:
Survey
Token Survey
Feature activation+0.000
Top resid features:
Earth
Token Earth
Feature activation-0.001
Top resid features:
rotation
Token rotation
Feature activation+0.002
Top resid features:
slows
Token slows
Feature activation-0.000
Top resid features:
Read
Token Read
Feature activation+0.014
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+3.378
Top resid features:
Ċ
TokenĊ
Feature activation+0.204
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
US
Token US
Feature activation+0.002
Top resid features:
Geological
Token Geological
Feature activation-0.000
Top resid features:
Survey
Token Survey
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
January
Token January
Feature activation-0.035
Top resid features:
window
Token window
Feature activation+0.012
Top resid features:
Read
Token Read
Feature activation+0.014
Top resid features:
more
Token more
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+5.864
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
But
TokenBut
Feature activation+0.001
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
does
Token does
Feature activation+0.001
Top resid features:
seem
Token seem
Feature activation-0.000
Top resid features:
as
Token as
Feature activation-0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
happened
Token happened
Feature activation-0.000
Top resid features:
Read
Token Read
Feature activation+0.021
Top resid features:
more
Token more
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+5.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.100
Top resid features:
Di
TokenDi
Feature activation+0.004
Top resid features:
Nat
Token Nat
Feature activation-0.001
Top resid features:
ale
Tokenale
Feature activation+0.003
Top resid features:
was
Token was
Feature activation+0.018
Top resid features:
Earth
Token Earth
Feature activation-0.003
Top resid features:
rotation
Token rotation
Feature activation+0.001
Top resid features:
slows
Token slows
Feature activation+0.001
Top resid features:
Read
Token Read
Feature activation+0.013
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+2.457
Top resid features:
Ċ
TokenĊ
Feature activation+0.266
Top resid features:
The
TokenThe
Feature activation+0.008
Top resid features:
US
Token US
Feature activation+0.003
Top resid features:
Geological
Token Geological
Feature activation+0.000
Top resid features:
Survey
Token Survey
Feature activation-0.001
Top resid features:
Earth
Token Earth
Feature activation-0.001
Top resid features:
rotation
Token rotation
Feature activation+0.004
Top resid features:
slows
Token slows
Feature activation+0.000
Top resid features:
Read
Token Read
Feature activation+0.006
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+2.823
Top resid features:
Ċ
TokenĊ
Feature activation+0.156
Top resid features:
The
TokenThe
Feature activation+0.021
Top resid features:
US
Token US
Feature activation+0.019
Top resid features:
Geological
Token Geological
Feature activation+0.002
Top resid features:
Survey
Token Survey
Feature activation+0.001
Top resid features:
Earth
Token Earth
Feature activation-0.004
Top resid features:
rotation
Token rotation
Feature activation+0.007
Top resid features:
slows
Token slows
Feature activation+0.001
Top resid features:
Read
Token Read
Feature activation+0.017
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+2.930
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
The
TokenThe
Feature activation+0.002
Top resid features:
US
Token US
Feature activation+0.001
Top resid features:
Geological
Token Geological
Feature activation-0.000
Top resid features:
Survey
Token Survey
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.000
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
happened
Token happened
Feature activation-0.000
Top resid features:
Read
Token Read
Feature activation+0.005
Top resid features:
more
Token more
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+3.085
Top resid features:
Ċ
TokenĊ
Feature activation+0.067
Top resid features:
Di
TokenDi
Feature activation+0.001
Top resid features:
Nat
Token Nat
Feature activation-0.001
Top resid features:
ale
Tokenale
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
hard
Token hard
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
govern
Token govern
Feature activation-0.003
Top resid features:
Read
Token Read
Feature activation+0.010
Top resid features:
more
Token more
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+3.960
Top resid features:
Ċ
TokenĊ
Feature activation+0.190
Top resid features:
The
TokenThe
Feature activation+0.013
Top resid features:
data
Token data
Feature activation+0.006
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
posted
Token posted
Feature activation-0.004
Top resid features:
Jonathan
Token Jonathan
Feature activation-0.000
Top resid features:
Franklin
Token Franklin
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Guardian
Token Guardian
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+4.149
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
Since
TokenSince
Feature activation+0.012
Top resid features:
2009
Token 2009
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
damage
Token damage
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
injuries
Token injuries
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+2.932
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
U
TokenU
Feature activation-0.001
Top resid features:
ps
Tokenps
Feature activation+0.000
Top resid features:
ur
Tokenur
Feature activation+0.000
Top resid features:
ge
Tokenge
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.000
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
happened
Token happened
Feature activation-0.001
Top resid features:
Read
Token Read
Feature activation+0.018
Top resid features:
more
Token more
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+2.603
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
Di
TokenDi
Feature activation+0.000
Top resid features:
Nat
Token Nat
Feature activation-0.001
Top resid features:
ale
Tokenale
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.025
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
happened
Token happened
Feature activation-0.001
Top resid features:
Read
Token Read
Feature activation+0.153
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+2.940
Top resid features:
Ċ
TokenĊ
Feature activation+0.084
Top resid features:
Di
TokenDi
Feature activation-0.000
Top resid features:
Nat
Token Nat
Feature activation-0.000
Top resid features:
ale
Tokenale
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
Earth
Token Earth
Feature activation-0.001
Top resid features:
rotation
Token rotation
Feature activation+0.001
Top resid features:
slows
Token slows
Feature activation+0.001
Top resid features:
Read
Token Read
Feature activation+0.019
Top resid features:
more
Token more
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+1.743
Top resid features:
Ċ
TokenĊ
Feature activation+0.190
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
US
Token US
Feature activation+0.002
Top resid features:
Geological
Token Geological
Feature activation+0.000
Top resid features:
Survey
Token Survey
Feature activation+0.000
Top resid features:
Earth
Token Earth
Feature activation-0.006
Top resid features:
rotation
Token rotation
Feature activation+0.000
Top resid features:
slows
Token slows
Feature activation+0.000
Top resid features:
Read
Token Read
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+2.694
Top resid features:
Ċ
TokenĊ
Feature activation+0.135
Top resid features:
The
TokenThe
Feature activation+0.040
Top resid features:
US
Token US
Feature activation+0.057
Top resid features:
Geological
Token Geological
Feature activation+0.000
Top resid features:
Survey
Token Survey
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.000
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
happened
Token happened
Feature activation-0.000
Top resid features:
Read
Token Read
Feature activation+0.011
Top resid features:
more
Token more
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation+2.480
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
Di
TokenDi
Feature activation+0.012
Top resid features:
Nat
Token Nat
Feature activation-0.002
Top resid features:
ale
Tokenale
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
matched
Token matched
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
actions
Token actions
Feature activation+0.000
Top resid features:
Read
Token Read
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+3.476
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
But
TokenBut
Feature activation+0.002
Top resid features:
Arsenal
Token Arsenal
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
making
Token making
Feature activation+0.001
Top resid features:
Earth
Token Earth
Feature activation-0.003
Top resid features:
rotation
Token rotation
Feature activation-0.001
Top resid features:
slows
Token slows
Feature activation+0.001
Top resid features:
Read
Token Read
Feature activation+0.019
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+1.619
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
US
Token US
Feature activation+0.002
Top resid features:
Geological
Token Geological
Feature activation-0.000
Top resid features:
Survey
Token Survey
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
January
Token January
Feature activation-0.012
Top resid features:
window
Token window
Feature activation+0.003
Top resid features:
Read
Token Read
Feature activation+0.040
Top resid features:
more
Token more
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+2.981
Top resid features:
Ċ
TokenĊ
Feature activation+0.190
Top resid features:
But
TokenBut
Feature activation+0.003
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
does
Token does
Feature activation+0.001
Top resid features:
seem
Token seem
Feature activation-0.017
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.06

Head 3: 0.53

Head 4: 0.06

Head 5: 0.06

Head 6: 0.04

Head 7: 0.04

Head 8: 0.03

Head 9: 0.05

Head 10: 0.03

Head 11: 0.03

Positive logits

Nato6.65

­6.52

Facebook6.42

Nasa6.23

5.86

5.66

programme5.34

Isis5.24

organising5.24

programmes5.20

organis5.16

criticised5.08

Photograph5.05

organisation4.97

organisations4.93

authorised4.90

organise4.88

organisers4.78

emphas4.78

]:4.72

Negative logits

----5.99

----5.28

,)-5.10

)---4.91

---4.78

.---4.75

....-4.34

,...-4.24

-4.21

...-4.15

"...-3.76

''-3.69

...)-3.66

-3.66

``-3.45

U-3.38

---3.36

...?-3.34

-3.33

)...-3.27

INTERVAL 5.637 - 6.263
CONTAINS 0.000%

we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.599
$
Token $
Feature activation+0.695
75
Token75
Feature activation+6.263
m
Tokenm
Feature activation+3.837
in
Token in
Feature activation+0.190
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+1.130
,
Token,
Feature activation+0.000
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
,
Token,
Feature activation+0.039
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
about
Token about
Feature activation+0.390
six
Token six
Feature activation+4.508
miles
Token miles
Feature activation+5.672
(
Token (
Feature activation+0.343
10
Token10
Feature activation+3.459
km
Tokenkm
Feature activation+2.072
)
Token)
Feature activation+3.105
east
Token east
Feature activation+4.704

INTERVAL 5.011 - 5.637
CONTAINS 0.000%

to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
leaders
Token leaders
Feature activation+0.285
on
Token on
Feature activation+5.519
Sunday
Token Sunday
Feature activation+1.661
afternoon
Token afternoon
Feature activation+0.166
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
journey
Token journey
Feature activation+0.000

INTERVAL 4.384 - 5.011
CONTAINS 0.001%

Survey
Token Survey
Feature activation+2.405
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+1.516
.
Token.
Feature activation+0.000
1
Token1
Feature activation+4.520
magnitude
Token magnitude
Feature activation+0.758
quake
Token quake
Feature activation+1.236
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
,
Token,
Feature activation+0.039
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
,
Token,
Feature activation+0.039
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
about
Token about
Feature activation+0.390
six
Token six
Feature activation+4.508
miles
Token miles
Feature activation+5.672
(
Token (
Feature activation+0.343
10
Token10
Feature activation+3.459
km
Tokenkm
Feature activation+2.072
)
Token)
Feature activation+3.105
the
Token the
Feature activation+0.877
Greens
Token Greens
Feature activation+1.378
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
motion
Token motion
Feature activation+0.000
on
Token on
Feature activation+4.946
Wednesday
Token Wednesday
Feature activation+0.519
afternoon
Token afternoon
Feature activation+0.340
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.542
Hanson
Token Hanson
Feature activation+0.529
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
the
Token the
Feature activation+4.502
Senate
Token Senate
Feature activation+3.685
he
Token he
Feature activation+0.065
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.100
for
Token for
Feature activation+0.000

INTERVAL 3.758 - 4.384
CONTAINS 0.000%

have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.599
$
Token $
Feature activation+0.695
75
Token75
Feature activation+6.263
m
Tokenm
Feature activation+3.837
in
Token in
Feature activation+0.190
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+1.130
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
data
Token data
Feature activation+0.198
was
Token was
Feature activation+0.000
posted
Token posted
Feature activation+1.666
on
Token on
Feature activation+3.891
a
Token a
Feature activation+0.000
profile
Token profile
Feature activation+0.000
called
Token called
Feature activation+0.000
EM
Token EM
Feature activation+0.000
LE
TokenLE
Feature activation+0.000

INTERVAL 3.132 - 3.758
CONTAINS 0.001%

Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.462
US
Token US
Feature activation+3.449
Geological
Token Geological
Feature activation+2.597
Survey
Token Survey
Feature activation+2.405
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+1.516
or
Token or
Feature activation+0.000
injuries
Token injuries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
U
TokenU
Feature activation+3.708
ps
Tokenps
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ge
Tokenge
Feature activation+0.011
in
Token in
Feature activation+0.000
big
Token big
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000
is
Token is
Feature activation+0.000
worth
Token worth
Feature activation+0.058
âĤ¬
Token âĤ¬
Feature activation+0.000
65
Token65
Feature activation+3.204
m
Tokenm
Feature activation+0.847
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
ulas
Tokenulas
Feature activation+0.556
has
Token has
Feature activation+0.000
would
Token would
Feature activation+0.388
now
Token now
Feature activation+0.232
settle
Token settle
Feature activation+0.897
the
Token the
Feature activation+0.764
matter
Token matter
Feature activation+1.218
promptly
Token promptly
Feature activation+3.669
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
promptly
Token promptly
Feature activation+3.669
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.375
Roberts
TokenRoberts
Feature activation+1.040
told
Token told
Feature activation+3.305
the
Token the
Feature activation+4.502
Senate
Token Senate
Feature activation+3.685
he
Token he
Feature activation+0.065
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.100

INTERVAL 2.505 - 3.132
CONTAINS 0.001%

more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.462
US
Token US
Feature activation+3.449
Geological
Token Geological
Feature activation+2.597
Survey
Token Survey
Feature activation+2.405
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+1.516
.
Token.
Feature activation+0.000
1
Token1
Feature activation+4.520
magnitude
Token magnitude
Feature activation+0.758
quake
Token quake
Feature activation+1.236
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
.
Token.
Feature activation+0.000
45
Token45
Feature activation+5.637
pm
Tokenpm
Feature activation+4.676
Thursday
Token Thursday
Feature activation+1.788
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.611
in
Token in
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
arranged
Token arranged
Feature activation+0.000
sequences
Token sequences
Feature activation+2.554
of
Token of
Feature activation+0.003
Chinese
Token Chinese
Feature activation+0.853
characters
Token characters
Feature activation+4.252
,
Token,
Feature activation+0.000
spelled
Token spelled
Feature activation+0.000
does
Token does
Feature activation+0.000
seem
Token seem
Feature activation+0.000
a
Token a
Feature activation+0.000
fairly
Token fairly
Feature activation+0.000
distant
Token distant
Feature activation+0.000
prospect
Token prospect
Feature activation+2.639
right
Token right
Feature activation+0.625
now
Token now
Feature activation+0.702
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.415
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.397
to
Token to
Feature activation+0.813
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
step
Token step
Feature activation+0.000
back
Token back
Feature activation+2.571
and
Token and
Feature activation+0.258
marvel
Token marvel
Feature activation+0.196
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000

INTERVAL 1.879 - 2.505
CONTAINS 0.002%

res
Tokenres
Feature activation+2.059
,
Token,
Feature activation+0.000
disease
Token disease
Feature activation+0.494
transfer
Token transfer
Feature activation+1.097
from
Token from
Feature activation+0.000
humans
Token humans
Feature activation+1.912
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
habitat
Token habitat
Feature activation+0.000
loss
Token loss
Feature activation+1.461
for
Token for
Feature activation+0.000
Int
TokenInt
Feature activation+0.000
elligence
Tokenelligence
Feature activation+0.730
agencies
Token agencies
Feature activation+0.553
in
Token in
Feature activation+0.000
the
Token the
Feature activation+2.484
US
Token US
Feature activation+2.295
said
Token said
Feature activation+0.331
in
Token in
Feature activation+0.252
January
Token January
Feature activation+0.019
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.123
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.980
Congress
TokenCongress
Feature activation+0.000
has
Token has
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
changed
Token changed
Feature activation+0.000
the
Token the
Feature activation+0.000
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.100
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.968
high
Token high
Feature activation+0.923
court
Token court
Feature activation+2.283
to
Token to
Feature activation+0.000
clarify
Token clarify
Feature activation+0.488
his
Token his
Feature activation+0.000
eligibility
Token eligibility
Feature activation+0.730
,
Token,
Feature activation+0.000
evident
Token evident
Feature activation+1.094
three
Token three
Feature activation+0.285
hours
Token hours
Feature activation+1.109
before
Token before
Feature activation+1.507
his
Token his
Feature activation+0.327
arrival
Token arrival
Feature activation+1.886
,
Token,
Feature activation+0.079
with
Token with
Feature activation+0.524
large
Token large
Feature activation+0.000
crowds
Token crowds
Feature activation+0.253
of
Token of
Feature activation+0.038

INTERVAL 1.253 - 1.879
CONTAINS 0.004%

z
Tokenz
Feature activation+0.089
seemed
Token seemed
Feature activation+0.011
so
Token so
Feature activation+0.000
determined
Token determined
Feature activation+1.648
to
Token to
Feature activation+0.000
make
Token make
Feature activation+1.338
permanently
Token permanently
Feature activation+0.034
in
Token in
Feature activation+0.000
the
Token the
Feature activation+1.108
summer
Token summer
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.702
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.415
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+1.837
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
án
Tokenán
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+1.766
gay
Token gay
Feature activation+0.000
or
Token or
Feature activation+0.000
straight
Token straight
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.514
K
TokenK
Feature activation+0.000
oz
Tokenoz
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
also
Token also
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
was
Token was
Feature activation+0.000
planning
Token planning
Feature activation+0.445
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.131
the
Token the
Feature activation+0.877
Greens
Token Greens
Feature activation+1.378
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
motion
Token motion
Feature activation+0.000
on
Token on
Feature activation+4.946
Wednesday
Token Wednesday
Feature activation+0.519
Senate
Token Senate
Feature activation+1.250
president
Token president
Feature activation+0.980
,
Token,
Feature activation+0.288
Stephen
Token Stephen
Feature activation+0.000
Par
Token Par
Feature activation+0.000
ry
Tokenry
Feature activation+1.486
,
Token,
Feature activation+0.283
said
Token said
Feature activation+0.987
he
Token he
Feature activation+0.410
hoped
Token hoped
Feature activation+0.336
the
Token the
Feature activation+1.231

INTERVAL 0.626 - 1.253
CONTAINS 0.016%

says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+1.516
.
Token.
Feature activation+0.000
1
Token1
Feature activation+4.520
magnitude
Token magnitude
Feature activation+0.758
quake
Token quake
Feature activation+1.236
struck
Token struck
Feature activation+0.216
just
Token just
Feature activation+0.923
after
Token after
Feature activation+2.984
4
Token 4
Feature activation+3.545
ings
Tokenings
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.916
These
TokenThese
Feature activation+0.000
banners
Token banners
Feature activation+0.938
,
Token,
Feature activation+0.000
welcoming
Token welcoming
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.611
in
Token in
Feature activation+0.000
yet
Token yet
Feature activation+0.000
pushed
Token pushed
Feature activation+0.000
upon
Token upon
Feature activation+0.237
the
Token the
Feature activation+0.045
working
Token working
Feature activation+0.000
classes
Token classes
Feature activation+0.821
who
Token who
Feature activation+0.000
simply
Token simply
Feature activation+0.000
couldn
Token couldn
Feature activation+0.133
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
parents
Token parents
Feature activation+0.459
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.392
adults
Token adults
Feature activation+0.013
in
Token in
Feature activation+0.000
charge
Token charge
Feature activation+0.769
were
Token were
Feature activation+0.000
neglect
Token neglect
Feature activation+0.000
ful
Tokenful
Feature activation+1.363
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Mic
TokenMic
Feature activation+0.000
hel
Tokenhel
Feature activation+0.000
A
Token A
Feature activation+0.000
ulas
Tokenulas
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.850
Lyon
Token Lyon
Feature activation+0.150
president
Token president
Feature activation+0.175
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 0.000 - 0.626
CONTAINS 99.975%

Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
other
Token other
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
profound
Token profound
Feature activation+0.000
Comput
Token Comput
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
and
Token and
Feature activation+0.000
Humans
Token Humans
Feature activation+0.000
Apart
Token Apart
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Typically
TokenTypically
Feature activation+0.000
they
Token they
Feature activation+0.000
feature
Token feature
Feature activation+0.000
of
Token of
Feature activation+0.000
spar
Token spar
Feature activation+0.000
ring
Tokenring
Feature activation+0.000
.
Token.
Feature activation+0.000
Mem
Token Mem
Feature activation+0.000
orable
Tokenorable
Feature activation+0.000
quotes
Token quotes
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
should
Tokenshould
Feature activation+0.000
/
Token/
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
If
Token If
Feature activation+0.000
so
Token so
Feature activation+0.000
fun
Token fun
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
help
Token help
Feature activation+0.000
but
Token but
Feature activation+0.000
want
Token want
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 H10.3: (feature 18793)

TOP ACTIVATIONS
MAX = 4.948

one
Token one
Feature activation+0.898
in
Token in
Feature activation+0.081
J
Token J
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ark
Tokenark
Feature activation+0.000
hand
Tokenhand
Feature activation+4.948
--
Token --
Feature activation+0.216
who
Token who
Feature activation+1.884
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
daughter
Token daughter
Feature activation+1.594
vast
Token vast
Feature activation+0.000
famous
Token famous
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
railway
Token railway
Feature activation+1.506
station
Token station
Feature activation+4.852
--
Token --
Feature activation+0.000
somehow
Token somehow
Feature activation+0.880
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.701
becomes
Token becomes
Feature activation+0.011
deep
Token deep
Feature activation+0.000
sound
Token sound
Feature activation+0.946
beds
Token beds
Feature activation+4.534
and
Token and
Feature activation+0.000
drifting
Token drifting
Feature activation+0.000
melodies
Token melodies
Feature activation+4.821
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
this
Token this
Feature activation+0.000
track
Token track
Feature activation+1.745
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
oldest
Token oldest
Feature activation+4.328
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
4
Token 4
Feature activation+0.734
children
Token children
Feature activation+4.646
with
Token with
Feature activation+0.000
wife
Token wife
Feature activation+0.000
Dor
Token Dor
Feature activation+0.000
othe
Tokenothe
Feature activation+0.273
a
Tokena
Feature activation+3.898
of
Token of
Feature activation+0.000
lost
Token lost
Feature activation+0.000
,
Token,
Feature activation+0.000
unre
Token unre
Feature activation+0.000
leased
Tokenleased
Feature activation+0.572
devices
Token devices
Feature activation+4.583
and
Token and
Feature activation+0.000
allegations
Token allegations
Feature activation+1.571
that
Token that
Feature activation+0.000
security
Token security
Feature activation+0.000
employees
Token employees
Feature activation+0.410
inking
Tokeninking
Feature activation+0.239
the
Token the
Feature activation+0.000
area
Token area
Feature activation+3.799
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
wetlands
Token wetlands
Feature activation+4.552
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
adjacent
Token adjacent
Feature activation+0.000
areas
Token areas
Feature activation+1.647
more
Token more
Feature activation+0.000
long
Token long
Feature activation+0.000
tracks
Token tracks
Feature activation+2.315
with
Token with
Feature activation+0.000
deep
Token deep
Feature activation+0.000
sound
Token sound
Feature activation+0.946
beds
Token beds
Feature activation+4.534
and
Token and
Feature activation+0.000
drifting
Token drifting
Feature activation+0.000
melodies
Token melodies
Feature activation+4.821
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
slut
Token slut
Feature activation+1.294
or
Token or
Feature activation+0.943
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.005
other
Token other
Feature activation+0.618
examples
Token examples
Feature activation+4.519
over
Token over
Feature activation+0.416
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
four
Token four
Feature activation+0.138
years
Token years
Feature activation+4.390
do
Token do
Feature activation+0.117
so
Token so
Feature activation+0.284
at
Token at
Feature activation+0.000
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.000
peril
Token peril
Feature activation+4.431
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
operating
Token operating
Feature activation+0.000
system
Token system
Feature activation+1.491
is
Token is
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
got
Token got
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.243
amount
Token amount
Feature activation+4.428
of
Token of
Feature activation+0.000
time
Token time
Feature activation+4.178
as
Token as
Feature activation+0.000
Chris
Token Chris
Feature activation+0.000
Christie
Token Christie
Feature activation+3.254
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.001
expect
Token expect
Feature activation+0.375
creature
Token creature
Feature activation+0.000
com
Token com
Feature activation+0.000
forts
Tokenforts
Feature activation+4.422
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
72
Token 72
Feature activation+0.000
examples
Token examples
Feature activation+4.519
over
Token over
Feature activation+0.416
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
four
Token four
Feature activation+0.138
years
Token years
Feature activation+4.390
."
Token."
Feature activation+0.245
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.988
Cont
TokenCont
Feature activation+0.000
roversial
Tokenroversial
Feature activation+0.104
only
Token only
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
--
Token --
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
oldest
Token oldest
Feature activation+4.328
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
4
Token 4
Feature activation+0.734
children
Token children
Feature activation+4.646
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
concentration
Token concentration
Feature activation+0.928
of
Token of
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
Americans
Token Americans
Feature activation+4.312
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.970
's
Token's
Feature activation+0.000
spy
Token spy
Feature activation+0.000
Patriot
Token Patriot
Feature activation+0.000
Place
Token Place
Feature activation+0.846
retail
Token retail
Feature activation+0.000
and
Token and
Feature activation+0.000
dining
Token dining
Feature activation+0.000
area
Token area
Feature activation+4.304
at
Token at
Feature activation+0.000
Gil
Token Gil
Feature activation+0.000
lette
Tokenlette
Feature activation+0.000
Stadium
Token Stadium
Feature activation+2.932
.
Token.
Feature activation+0.310
of
Token of
Feature activation+0.000
graduating
Token graduating
Feature activation+1.664
high
Token high
Feature activation+1.766
school
Token school
Feature activation+2.614
no
Token no
Feature activation+0.000
less
Token less
Feature activation+4.297
--
Token --
Feature activation+0.110
be
Token be
Feature activation+0.000
unable
Token unable
Feature activation+0.934
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.964
indicating
Token indicating
Feature activation+0.000
their
Token their
Feature activation+0.000
cross
Token cross
Feature activation+0.000
-
Token-
Feature activation+0.000
device
Tokendevice
Feature activation+0.000
support
Token support
Feature activation+4.292
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
run
Token run
Feature activation+0.000
fact
Token fact
Feature activation+2.737
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
worms
Token worms
Feature activation+2.645
do
Token do
Feature activation+0.000
exist
Token exist
Feature activation+4.279
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
deep
Token deep
Feature activation+0.000
sea
Token sea
Feature activation+2.960
.
Token.
Feature activation+0.000
political
Token political
Feature activation+0.000
fortunes
Token fortunes
Feature activation+2.742
potentially
Token potentially
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
rise
Token rise
Feature activation+4.231
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
continued
Token continued
Feature activation+0.000
controversy
Token controversy
Feature activation+1.501
over
Token over
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.217
that
Token that
Feature activation+0.000
change
Token change
Feature activation+3.212
,
Token,
Feature activation+0.235
too
Token too
Feature activation+4.226
.
Token.
Feature activation+0.325
We
Token We
Feature activation+0.000
need
Token need
Feature activation+0.000
more
Token more
Feature activation+0.000
fathers
Token fathers
Feature activation+3.620

Top DFA by src position
MAX = 5.393

prevent
Token prevent
Feature activation+0.000
Top resid features:
girls
Token girls
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
born
Token born
Feature activation+0.001
Top resid features:
--
Token --
Feature activation+4.789
Top resid features:
leaving
Token leaving
Feature activation-0.004
Top resid features:
some
Token some
Feature activation+0.002
Top resid features:
communities
Token communities
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
India
Token India
Feature activation+0.005
Top resid features:
appears
Token appears
Feature activation+0.014
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
shopping
Token shopping
Feature activation+0.000
Top resid features:
mall
Token mall
Feature activation-0.002
Top resid features:
--
Token --
Feature activation+5.393
Top resid features:
or
Token or
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
say
Token say
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.076
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
*
Token*
Feature activation+0.252
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
his
Token his
Feature activation+0.010
Top resid features:
ambient
Token ambient
Feature activation-0.005
Top resid features:
music
Token music
Feature activation-0.006
Top resid features:
--
Token --
Feature activation+5.061
Top resid features:
long
Token long
Feature activation+0.008
Top resid features:
tracks
Token tracks
Feature activation+0.119
Top resid features:
with
Token with
Feature activation+0.011
Top resid features:
deep
Token deep
Feature activation-0.003
Top resid features:
sound
Token sound
Feature activation-0.009
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
Jon
Token Jon
Feature activation+0.003
Top resid features:
's
Token's
Feature activation+0.013
Top resid features:
only
Token only
Feature activation+0.005
Top resid features:
daughter
Token daughter
Feature activation-0.001
Top resid features:
--
Token --
Feature activation+5.097
Top resid features:
and
Token and
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
oldest
Token oldest
Feature activation+0.021
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
his
Token his
Feature activation-0.008
Top resid features:
Sand
Token Sand
Feature activation-0.005
Top resid features:
oval
Tokenoval
Feature activation-0.002
Top resid features:
/
Token/
Feature activation-0.003
Top resid features:
C
TokenC
Feature activation-0.003
Top resid features:
NET
TokenNET
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+5.307
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Against
TokenAgainst
Feature activation-0.010
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
backdrop
Token backdrop
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
hurt
Token hurt
Feature activation-0.000
Top resid features:
recovery
Token recovery
Feature activation+0.000
Top resid features:
02
Token 02
Feature activation-0.001
Top resid features:
:
Token:
Feature activation-0.000
Top resid features:
02
Token02
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+2.347
Top resid features:
Ċ
TokenĊ
Feature activation+0.050
Top resid features:
JUST
TokenJUST
Feature activation+0.001
Top resid features:
WATCHED
Token WATCHED
Feature activation+0.186
Top resid features:
Search
Token Search
Feature activation+0.001
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
*
Token*
Feature activation+0.253
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
his
Token his
Feature activation+0.011
Top resid features:
ambient
Token ambient
Feature activation-0.017
Top resid features:
music
Token music
Feature activation-0.007
Top resid features:
--
Token --
Feature activation+4.788
Top resid features:
long
Token long
Feature activation+0.013
Top resid features:
tracks
Token tracks
Feature activation+0.125
Top resid features:
with
Token with
Feature activation+0.020
Top resid features:
deep
Token deep
Feature activation-0.004
Top resid features:
sound
Token sound
Feature activation-0.021
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
know
Token know
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
stand
Token stand
Feature activation+0.002
Top resid features:
--
Token --
Feature activation+4.955
Top resid features:
if
Token if
Feature activation+0.003
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
stand
Token stand
Feature activation+0.002
Top resid features:
up
Token up
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
death
Token death
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Windows
Token Windows
Feature activation-0.014
Top resid features:
XP
Token XP
Feature activation-0.006
Top resid features:
--
Token --
Feature activation+4.930
Top resid features:
sure
Token sure
Feature activation+0.004
Top resid features:
you
Token you
Feature activation+0.012
Top resid features:
can
Token can
Feature activation+0.012
Top resid features:
still
Token still
Feature activation+0.001
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
eight
Token eight
Feature activation-0.001
Top resid features:
minutes
Token minutes
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
coverage
Token coverage
Feature activation-0.037
Top resid features:
--
Token --
Feature activation+4.754
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
fifth
Tokenfifth
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
Bush
Token Bush
Feature activation-0.001
Top resid features:
parties
Token parties
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
parking
Token parking
Feature activation+0.002
Top resid features:
lots
Token lots
Feature activation-0.003
Top resid features:
--
Token --
Feature activation+4.778
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
his
Token his
Feature activation+0.003
Top resid features:
baby
Token baby
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
It
Token It
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
know
Token know
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
stand
Token stand
Feature activation+0.002
Top resid features:
--
Token --
Feature activation+4.777
Top resid features:
if
Token if
Feature activation+0.002
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
stand
Token stand
Feature activation+0.003
Top resid features:
up
Token up
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
Jon
Token Jon
Feature activation+0.034
Top resid features:
's
Token's
Feature activation+0.032
Top resid features:
only
Token only
Feature activation+0.006
Top resid features:
daughter
Token daughter
Feature activation+0.012
Top resid features:
--
Token --
Feature activation+4.721
Top resid features:
and
Token and
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
oldest
Token oldest
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
U
Token U
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
S
TokenS
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
city
Token city
Feature activation-0.001
Top resid features:
--
Token --
Feature activation+4.282
Top resid features:
for
Token for
Feature activation+0.014
Top resid features:
instance
Token instance
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
Detroit
Token Detroit
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
parties
Token parties
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
parking
Token parking
Feature activation-0.016
Top resid features:
lots
Token lots
Feature activation-0.004
Top resid features:
--
Token --
Feature activation+4.740
Top resid features:
are
Token are
Feature activation+0.007
Top resid features:
his
Token his
Feature activation+0.002
Top resid features:
baby
Token baby
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
It
Token It
Feature activation+0.003
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
public
Token public
Feature activation-0.000
Top resid features:
education
Token education
Feature activation-0.000
Top resid features:
system
Token system
Feature activation-0.001
Top resid features:
--
Token --
Feature activation+4.883
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
verge
Token verge
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
graduating
Token graduating
Feature activation+0.049
Top resid features:
ľ
Tokenľ
Feature activation-0.017
Top resid features:
universal
Tokenuniversal
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ŀ
TokenĿ
Feature activation+0.025
Top resid features:
apps
Token apps
Feature activation-0.003
Top resid features:
--
Token --
Feature activation+4.845
Top resid features:
ones
Token ones
Feature activation+0.022
Top resid features:
with
Token with
Feature activation+0.018
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
small
Token small
Feature activation+0.020
Top resid features:
icon
Token icon
Feature activation+0.048
Top resid features:
like
Token like
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
classic
Token classic
Feature activation-0.002
Top resid features:
horror
Token horror
Feature activation-0.006
Top resid features:
story
Token story
Feature activation-0.007
Top resid features:
--
Token --
Feature activation+4.706
Top resid features:
ey
Token ey
Feature activation-0.004
Top resid features:
eless
Tokeneless
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
mouth
Token mouth
Feature activation-0.000
Top resid features:
less
Tokenless
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
no
Token no
Feature activation-0.000
Top resid features:
mood
Token mood
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
cooperate
Token cooperate
Feature activation+0.009
Top resid features:
--
Token --
Feature activation+4.761
Top resid features:
sensing
Token sensing
Feature activation+0.020
Top resid features:
their
Token their
Feature activation+0.003
Top resid features:
own
Token own
Feature activation+0.011
Top resid features:
political
Token political
Feature activation+0.003
Top resid features:
fortunes
Token fortunes
Feature activation+0.033
Top resid features:
prevent
Token prevent
Feature activation-0.000
Top resid features:
girls
Token girls
Feature activation-0.001
Top resid features:
from
Token from
Feature activation-0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
born
Token born
Feature activation+0.000
Top resid features:
--
Token --
Feature activation+3.250
Top resid features:
leaving
Token leaving
Feature activation-0.000
Top resid features:
some
Token some
Feature activation+0.001
Top resid features:
communities
Token communities
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
India
Token India
Feature activation-0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.10

Head 3: 0.53

Head 4: 0.08

Head 5: 0.08

Head 6: 0.02

Head 7: 0.06

Head 8: 0.02

Head 9: 0.04

Head 10: 0.01

Head 11: 0.02

Positive logits

--10.91

JUST7.55

7.43

``6.76

--6.35

`6.33

...6.33

..."6.05

---5.84

----5.80

.--5.67

5.50

!--5.49

Replay5.39

....5.15

-->5.09

``5.04

......5.02

`,5.01

|--4.92

Negative logits

-9.06

­-8.22

————————-7.43

————————————————-6.54

)—-6.22

-6.00

"—-5.98

[…]-5.91

————-5.58

-5.47

.—-5.24

-5.21

"…-5.03

-4.98

-4.92

Advertisements-4.88

…."-4.83

…]-4.81

­-4.76

-4.74

INTERVAL 4.454 - 4.948
CONTAINS 0.001%

deep
Token deep
Feature activation+0.000
sound
Token sound
Feature activation+0.946
beds
Token beds
Feature activation+4.534
and
Token and
Feature activation+0.000
drifting
Token drifting
Feature activation+0.000
melodies
Token melodies
Feature activation+4.821
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
this
Token this
Feature activation+0.000
track
Token track
Feature activation+1.745
had
Token had
Feature activation+0.000
one
Token one
Feature activation+0.898
in
Token in
Feature activation+0.081
J
Token J
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ark
Tokenark
Feature activation+0.000
hand
Tokenhand
Feature activation+4.948
--
Token --
Feature activation+0.216
who
Token who
Feature activation+1.884
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
daughter
Token daughter
Feature activation+1.594
long
Token long
Feature activation+0.000
tracks
Token tracks
Feature activation+2.315
with
Token with
Feature activation+0.000
deep
Token deep
Feature activation+0.000
sound
Token sound
Feature activation+0.946
beds
Token beds
Feature activation+4.534
and
Token and
Feature activation+0.000
drifting
Token drifting
Feature activation+0.000
melodies
Token melodies
Feature activation+4.821
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
slut
Token slut
Feature activation+1.294
or
Token or
Feature activation+0.943
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.005
other
Token other
Feature activation+0.618
examples
Token examples
Feature activation+4.519
over
Token over
Feature activation+0.416
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
four
Token four
Feature activation+0.138
years
Token years
Feature activation+4.390
the
Token the
Feature activation+0.000
oldest
Token oldest
Feature activation+4.328
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
4
Token 4
Feature activation+0.734
children
Token children
Feature activation+4.646
with
Token with
Feature activation+0.000
wife
Token wife
Feature activation+0.000
Dor
Token Dor
Feature activation+0.000
othe
Tokenothe
Feature activation+0.273
a
Tokena
Feature activation+3.898

INTERVAL 3.959 - 4.454
CONTAINS 0.004%

a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
concentration
Token concentration
Feature activation+0.928
of
Token of
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
Americans
Token Americans
Feature activation+4.312
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.970
's
Token's
Feature activation+0.000
spy
Token spy
Feature activation+0.000
Patriot
Token Patriot
Feature activation+0.000
Place
Token Place
Feature activation+0.846
retail
Token retail
Feature activation+0.000
and
Token and
Feature activation+0.000
dining
Token dining
Feature activation+0.000
area
Token area
Feature activation+4.304
at
Token at
Feature activation+0.000
Gil
Token Gil
Feature activation+0.000
lette
Tokenlette
Feature activation+0.000
Stadium
Token Stadium
Feature activation+2.932
.
Token.
Feature activation+0.310
uring
Tokenuring
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.125
younger
Token younger
Feature activation+0.000
than
Token than
Feature activation+0.000
18
Token 18
Feature activation+4.155
for
Token for
Feature activation+0.000
prostitution
Token prostitution
Feature activation+3.606
.
Token.
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.020
,
Token,
Feature activation+0.000
t
Tokent
Feature activation+0.000
enth
Tokenenth
Feature activation+2.434
of
Token of
Feature activation+0.168
Clinton
Token Clinton
Feature activation+0.830
's
Token's
Feature activation+3.194
time
Token time
Feature activation+4.128
(
Token (
Feature activation+0.000
one
Tokenone
Feature activation+0.000
-
Token-
Feature activation+0.000
tw
Tokentw
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
cause
Token cause
Feature activation+1.289
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
power
Token power
Feature activation+0.710
or
Token or
Feature activation+0.000
not
Token not
Feature activation+4.200
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
spider
Token spider
Feature activation+0.142
was
Token was
Feature activation+0.000
irrad
Token irrad
Feature activation+0.000

INTERVAL 3.464 - 3.959
CONTAINS 0.007%

political
Token political
Feature activation+0.000
leaders
Token leaders
Feature activation+3.473
believe
Token believe
Feature activation+0.000
they
Token they
Feature activation+0.101
are
Token are
Feature activation+0.320
false
Token false
Feature activation+3.662
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.357
"
Token"
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
that
Token that
Feature activation+0.000
fall
Token fall
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
visible
Token visible
Feature activation+0.000
spectrum
Token spectrum
Feature activation+3.659
--
Token --
Feature activation+0.000
light
Token light
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
visible
Token visible
Feature activation+0.387
get
Token get
Feature activation+0.000
ahead
Token ahead
Feature activation+3.986
.
Token.
Feature activation+0.832
And
Token And
Feature activation+1.707
stay
Token stay
Feature activation+1.097
ahead
Token ahead
Feature activation+3.918
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.109
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
remember
Token remember
Feature activation+1.876
"
Token "
Feature activation+0.000
Ocean
TokenOcean
Feature activation+0.000
's
Token's
Feature activation+0.000
Eleven
Token Eleven
Feature activation+0.113
"
Token"
Feature activation+3.578
--
Token --
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.087
got
Token got
Feature activation+2.136
taking
Token taking
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.067
Some
TokenSome
Feature activation+0.274
how
Tokenhow
Feature activation+3.390
or
Token or
Feature activation+0.000
other
Token other
Feature activation+3.877
,
Token,
Feature activation+0.090
they
Token they
Feature activation+0.740
've
Token've
Feature activation+0.240
managed
Token managed
Feature activation+2.221
to
Token to
Feature activation+0.060

INTERVAL 2.969 - 3.464
CONTAINS 0.013%

woke
Token woke
Feature activation+0.000
up
Token up
Feature activation+0.409
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
surprise
Token surprise
Feature activation+3.162
Wednesday
Token Wednesday
Feature activation+2.331
when
Token when
Feature activation+0.635
the
Token the
Feature activation+0.061
nation
Token nation
Feature activation+0.404
âĢ
TokenâĢ
Feature activation+0.000
pond
Token pond
Feature activation+1.730
throughout
Token throughout
Feature activation+0.000
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
history
Token history
Feature activation+3.277
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
G
Token G
Feature activation+0.000
RC
TokenRC
Feature activation+0.000
got
Token got
Feature activation+0.000
to
Token to
Feature activation+0.000
Iraqi
Token Iraqi
Feature activation+0.000
--
Token --
Feature activation+0.000
although
Token although
Feature activation+0.000
not
Token not
Feature activation+0.000
American
Token American
Feature activation+3.085
--
Token --
Feature activation+0.000
prosecution
Token prosecution
Feature activation+1.781
should
Token should
Feature activation+0.000
they
Token they
Feature activation+0.000
commit
Token commit
Feature activation+0.562
facts
Token facts
Feature activation+2.338
and
Token and
Feature activation+0.000
numbers
Token numbers
Feature activation+2.835
and
Token and
Feature activation+0.000
game
Token game
Feature activation+0.000
scores
Token scores
Feature activation+3.110
and
Token and
Feature activation+0.000
commence
Token commence
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.195
a
Token a
Feature activation+0.000
back
Token back
Feature activation+1.639
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.000
marriage
Token marriage
Feature activation+1.297
at
Token at
Feature activation+0.000
13
Token 13
Feature activation+3.419
when
Token when
Feature activation+0.116
he
Token he
Feature activation+0.000
found
Token found
Feature activation+0.075
out
Token out
Feature activation+1.101
she
Token she
Feature activation+0.000

INTERVAL 2.474 - 2.969
CONTAINS 0.020%

or
Token or
Feature activation+0.000
player
Token player
Feature activation+2.727
--
Token --
Feature activation+0.791
until
Token until
Feature activation+0.000
it
Token it
Feature activation+0.000
expired
Token expired
Feature activation+2.574
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.031
make
Token make
Feature activation+0.000
-
Token-
Feature activation+0.000
fifth
Tokenfifth
Feature activation+3.376
of
Token of
Feature activation+0.000
Bush
Token Bush
Feature activation+0.161
's
Token's
Feature activation+1.996
time
Token time
Feature activation+2.561
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
Of
TokenOf
Feature activation+0.000
the
Token the
Feature activation+0.000
16
Token 16
Feature activation+0.000
loans
Token loans
Feature activation+0.737
he
Token he
Feature activation+0.000
reported
Token reported
Feature activation+2.717
,
Token,
Feature activation+0.000
five
Token five
Feature activation+0.994
were
Token were
Feature activation+0.000
worth
Token worth
Feature activation+0.000
more
Token more
Feature activation+2.063
Party
Token Party
Feature activation+2.853
,
Token,
Feature activation+0.060
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.043
mean
Token mean
Feature activation+1.112
is
Token is
Feature activation+2.647
,
Token,
Feature activation+0.278
it
Token it
Feature activation+0.058
's
Token's
Feature activation+0.226
time
Token time
Feature activation+1.792
for
Token for
Feature activation+0.000
hilar
Token hilar
Feature activation+0.000
iously
Tokeniously
Feature activation+0.000
broke
Token broke
Feature activation+0.000
the
Token the
Feature activation+0.000
intense
Token intense
Feature activation+0.000
silence
Token silence
Feature activation+2.610
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.000
going
Token going
Feature activation+0.000

INTERVAL 1.979 - 2.474
CONTAINS 0.023%

put
Token put
Feature activation+0.000
him
Token him
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
choke
Token choke
Feature activation+0.000
hold
Tokenhold
Feature activation+2.233
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
paying
Token paying
Feature activation+0.000
for
Token for
Feature activation+0.000
no
Token no
Feature activation+0.000
place
Token place
Feature activation+0.000
among
Token among
Feature activation+0.000
us
Token us
Feature activation+1.465
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.416
--
Token --
Feature activation+0.000
were
Token were
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.000
military
Token military
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
'd
Token'd
Feature activation+0.000
rise
Token rise
Feature activation+0.000
from
Token from
Feature activation+0.000
obscurity
Token obscurity
Feature activation+2.126
to
Token to
Feature activation+0.000
explain
Token explain
Feature activation+0.777
that
Token that
Feature activation+0.384
if
Token if
Feature activation+0.000
women
Token women
Feature activation+0.267
offers
Token offers
Feature activation+0.000
employment
Token employment
Feature activation+0.000
subsidies
Token subsidies
Feature activation+1.939
and
Token and
Feature activation+0.000
tax
Token tax
Feature activation+0.000
exemptions
Token exemptions
Feature activation+2.401
to
Token to
Feature activation+0.000
attract
Token attract
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
investors
Token investors
Feature activation+2.178
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
very
Token very
Feature activation+0.000
much
Token much
Feature activation+0.000
in
Token in
Feature activation+0.000
demand
Token demand
Feature activation+2.131
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
net
Token net
Feature activation+0.000
reduction
Token reduction
Feature activation+1.697
in
Token in
Feature activation+0.000

INTERVAL 1.485 - 1.979
CONTAINS 0.033%

you
Token you
Feature activation+0.601
can
Token can
Feature activation+0.074
get
Token get
Feature activation+0.000
ahead
Token ahead
Feature activation+3.986
.
Token.
Feature activation+0.832
And
Token And
Feature activation+1.707
stay
Token stay
Feature activation+1.097
ahead
Token ahead
Feature activation+3.918
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.109
closely
Token closely
Feature activation+0.000
tracking
Token tracking
Feature activation+0.000
the
Token the
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+0.000
recount
Token recount
Feature activation+0.802
drama
Token drama
Feature activation+1.657
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
race
Token race
Feature activation+0.000
this
Token this
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
Mitt
Token Mitt
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
won
Token won
Feature activation+0.000
213
Token 213
Feature activation+1.548
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Any
TokenAny
Feature activation+0.000
body
Tokenbody
Feature activation+0.000
means
Token means
Feature activation+0.000
--
Token --
Feature activation+0.000
Digital
Token Digital
Feature activation+0.000
Restrict
Token Restrict
Feature activation+0.000
ions
Tokenions
Feature activation+2.320
Management
Token Management
Feature activation+1.723
(
Token (
Feature activation+0.000
DR
TokenDR
Feature activation+0.000
M
TokenM
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Time
TokenTime
Feature activation+0.000
keeper
Tokenkeeper
Feature activation+0.224
Catherine
Token Catherine
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
illo
Tokenillo
Feature activation+1.638
and
Token and
Feature activation+0.000
backup
Token backup
Feature activation+0.000
time
Token time
Feature activation+0.000
keeper
Tokenkeeper
Feature activation+0.000
Clarence
Token Clarence
Feature activation+0.000

INTERVAL 0.990 - 1.485
CONTAINS 0.039%

-->
Token -->
Feature activation+0.000
other
Token other
Feature activation+0.208
points
Token points
Feature activation+1.076
of
Token of
Feature activation+0.000
interest
Token interest
Feature activation+1.240
here
Token here
Feature activation+0.675
-->
Token -->
Feature activation+0.000
Token
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
>
Token>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.000
than
Token than
Feature activation+0.000
100
Token 100
Feature activation+0.000
world
Token world
Feature activation+0.000
leaders
Token leaders
Feature activation+1.275
promised
Token promised
Feature activation+0.087
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
historic
Token historic
Feature activation+0.000
U
Token U
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
NEW
TokenNEW
Feature activation+0.000
YORK
Token YORK
Feature activation+0.000
(
Token (
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
Money
TokenMoney
Feature activation+1.222
.
Token.
Feature activation+0.077
com
Tokencom
Feature activation+0.006
)
Token)
Feature activation+1.733
--
Token --
Feature activation+0.000
The
Token The
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
10
Token 10
Feature activation+0.000
km
Token km
Feature activation+0.000
(
Token (
Feature activation+0.000
6
Token6
Feature activation+1.024
miles
Token miles
Feature activation+0.000
)
Token)
Feature activation+0.000
of
Token of
Feature activation+0.000
visibility
Token visibility
Feature activation+0.000
,
Token,
Feature activation+0.000
light
Token light
Feature activation+3.270
pass
Token pass
Feature activation+0.257
right
Token right
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
silicon
Token silicon
Feature activation+1.379
and
Token and
Feature activation+0.000
never
Token never
Feature activation+0.000
get
Token get
Feature activation+0.000
converted
Token converted
Feature activation+0.839
to
Token to
Feature activation+0.000

INTERVAL 0.495 - 0.990
CONTAINS 0.076%

dedicated
Token dedicated
Feature activation+0.361
to
Token to
Feature activation+0.000
making
Token making
Feature activation+0.000
Lor
Token Lor
Feature activation+0.000
ica
Tokenica
Feature activation+0.011
accessible
Token accessible
Feature activation+0.667
to
Token to
Feature activation+0.000
all
Token all
Feature activation+1.644
bodies
Token bodies
Feature activation+1.596
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
--
Token --
Feature activation+0.050
you
Token you
Feature activation+0.601
can
Token can
Feature activation+0.074
get
Token get
Feature activation+0.000
ahead
Token ahead
Feature activation+3.986
.
Token.
Feature activation+0.832
And
Token And
Feature activation+1.707
stay
Token stay
Feature activation+1.097
ahead
Token ahead
Feature activation+3.918
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
fund
Token fund
Feature activation+1.314
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.000
million
Token million
Feature activation+0.000
grants
Token grants
Feature activation+0.572
in
Token in
Feature activation+0.000
1988
Token 1988
Feature activation+0.120
and
Token and
Feature activation+0.000
2008
Token 2008
Feature activation+0.752
from
Token from
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
coach
Token coach
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Wood
Token Wood
Feature activation+0.000
son
Tokenson
Feature activation+0.247
said
Token said
Feature activation+0.660
.
Token.
Feature activation+0.023
"
Token "
Feature activation+0.000
He
TokenHe
Feature activation+0.000
's
Token's
Feature activation+0.000
had
Token had
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
means
Token means
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
design
Token design
Feature activation+0.928
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
beginning
Token beginning
Feature activation+3.003
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000

INTERVAL 0.000 - 0.495
CONTAINS 99.784%

operations
Token operations
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
transforming
Token transforming
Feature activation+0.000
it
Token it
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
driven
Token driven
Feature activation+0.000
by
Token by
Feature activation+0.000
religious
Token religious
Feature activation+0.000
gave
Token gave
Feature activation+0.000
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
run
Tokenrun
Feature activation+0.000
,
Token,
Feature activation+0.000
Series
Token Series
Feature activation+0.000
-
Token-
Feature activation+0.000
cl
Tokencl
Feature activation+0.000
inch
Tokeninch
Feature activation+0.000
Kardashian
Token Kardashian
Feature activation+0.000
's
Token's
Feature activation+0.000
Paris
Token Paris
Feature activation+0.000
robbery
Token robbery
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
anniversary
Token anniversary
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
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
both
Token both
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
.
Token.
Feature activation+0.000
Carroll
Token Carroll
Feature activation+0.000
also
Token also
Feature activation+0.000
denied
Token denied
Feature activation+0.000
that
Token that
Feature activation+0.000
backing
Token backing
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
's
Token's
Feature activation+0.000
exit
Token exit
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature 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
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
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+0.060
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+0.060
by
Token by
Feature activation+0.000
headed
Token headed
Feature activation+0.060
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.060
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
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+0.060
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.060
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.060
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.060
by
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+0.060
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+0.060
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 2 in H10.3: (feature 21771)

TOP ACTIVATIONS
MAX = 4.973

fitted
Token fitted
Feature activation+0.570
with
Token with
Feature activation+0.409
"
Token "
Feature activation+0.177
def
Tokendef
Feature activation+0.000
eat
Tokeneat
Feature activation+0.686
devices
Token devices
Feature activation+4.973
"
Token"
Feature activation+1.802
were
Token were
Feature activation+0.000
registered
Token registered
Feature activation+0.716
in
Token in
Feature activation+0.275
London
Token London
Feature activation+0.561
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.419
$
Token $
Feature activation+0.415
75
Token75
Feature activation+3.862
m
Tokenm
Feature activation+2.551
in
Token in
Feature activation+0.000
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+0.833
,
Token,
Feature activation+0.000
political
Token political
Feature activation+0.000
activist
Token activist
Feature activation+2.011
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.143
own
Token own
Feature activation+0.094
right
Token right
Feature activation+3.750
"
Token"
Feature activation+0.000
who
Token who
Feature activation+0.000
felt
Token felt
Feature activation+0.000
"
Token "
Feature activation+0.000
very
Tokenvery
Feature activation+0.000
can
Token can
Feature activation+0.000
take
Token take
Feature activation+0.888
more
Token more
Feature activation+0.134
than
Token than
Feature activation+0.294
two
Token two
Feature activation+0.737
hours
Token hours
Feature activation+3.733
of
Token of
Feature activation+0.643
her
Token her
Feature activation+0.000
day
Token day
Feature activation+1.743
-
Token -
Feature activation+0.000
each
Token each
Feature activation+0.007
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.522
Constitution
Token Constitution
Feature activation+1.046
".
Token".
Feature activation+0.407
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.608
Congress
TokenCongress
Feature activation+0.452
has
Token has
Feature activation+0.048
repeatedly
Token repeatedly
Feature activation+0.333
changed
Token changed
Feature activation+0.313
the
Token the
Feature activation+0.499
Czech
Token Czech
Feature activation+0.467
s
Tokens
Feature activation+1.288
cited
Token cited
Feature activation+0.000
"
Token "
Feature activation+0.000
constitutional
Tokenconstitutional
Feature activation+0.134
reasons
Token reasons
Feature activation+3.593
"
Token"
Feature activation+1.250
for
Token for
Feature activation+0.077
their
Token their
Feature activation+0.023
refusal
Token refusal
Feature activation+1.827
,
Token,
Feature activation+0.000
document
Token document
Feature activation+0.506
surfaced
Token surfaced
Feature activation+0.299
as
Token as
Feature activation+0.000
U
Token U
Feature activation+1.677
.
Token.
Feature activation+0.630
S
TokenS
Feature activation+3.377
.
Token.
Feature activation+0.707
Secretary
Token Secretary
Feature activation+0.706
of
Token of
Feature activation+2.234
State
Token State
Feature activation+0.328
Rex
Token Rex
Feature activation+0.000
and
Token and
Feature activation+0.049
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
about
Token about
Feature activation+0.124
six
Token six
Feature activation+2.667
miles
Token miles
Feature activation+3.370
(
Token (
Feature activation+0.340
10
Token10
Feature activation+1.599
km
Tokenkm
Feature activation+1.113
)
Token)
Feature activation+1.942
east
Token east
Feature activation+2.540
He
TokenHe
Feature activation+0.441
still
Token still
Feature activation+0.000
has
Token has
Feature activation+0.000
"
Token "
Feature activation+0.000
legal
Tokenlegal
Feature activation+0.170
concerns
Token concerns
Feature activation+3.224
"
Token"
Feature activation+0.347
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
use
Token use
Feature activation+0.956
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000
multi
Tokenmulti
Feature activation+0.627
-
Token-
Feature activation+0.142
p
Tokenp
Feature activation+0.000
olar
Tokenolar
Feature activation+0.593
world
Token world
Feature activation+3.191
"
Token"
Feature activation+0.082
in
Token in
Feature activation+0.000
which
Token which
Feature activation+1.022
Latin
Token Latin
Feature activation+0.425
American
Token American
Feature activation+0.461
.
Token.
Feature activation+0.009
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.686
Advertisement
TokenAdvertisement
Feature activation+0.162
Ċ
TokenĊ
Feature activation+0.513
Ċ
TokenĊ
Feature activation+3.092
The
TokenThe
Feature activation+1.453
package
Token package
Feature activation+0.902
fell
Token fell
Feature activation+0.000
apart
Token apart
Feature activation+0.095
after
Token after
Feature activation+0.090
M
Token M
Feature activation+0.705
ice
Tokenice
Feature activation+0.088
lli
Tokenlli
Feature activation+1.059
,
Token,
Feature activation+0.000
senior
Token senior
Feature activation+0.518
vice
Token vice
Feature activation+3.075
president
Token president
Feature activation+0.885
at
Token at
Feature activation+0.584
the
Token the
Feature activation+2.138
show
Token show
Feature activation+1.101
's
Token's
Feature activation+1.821
"
Token "
Feature activation+0.000
every
Tokenevery
Feature activation+0.000
day
Tokenday
Feature activation+0.377
anti
Token anti
Feature activation+1.334
-
Token-
Feature activation+0.420
Semitism
TokenSemitism
Feature activation+3.071
"
Token"
Feature activation+1.072
in
Token in
Feature activation+0.128
Ukraine
Token Ukraine
Feature activation+0.942
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
been
Token been
Feature activation+0.185
dated
Token dated
Feature activation+1.488
to
Token to
Feature activation+1.378
about
Token about
Feature activation+0.502
1300
Token 1300
Feature activation+2.605
AD
TokenAD
Feature activation+3.016
and
Token and
Feature activation+0.289
is
Token is
Feature activation+0.145
made
Token made
Feature activation+0.156
of
Token of
Feature activation+0.545
calf
Token calf
Feature activation+0.030
The
TokenThe
Feature activation+1.453
package
Token package
Feature activation+0.902
fell
Token fell
Feature activation+0.000
apart
Token apart
Feature activation+0.095
after
Token after
Feature activation+0.090
Democratic
Token Democratic
Feature activation+3.016
House
Token House
Feature activation+2.679
minority
Token minority
Feature activation+2.904
leader
Token leader
Feature activation+1.149
Nancy
Token Nancy
Feature activation+0.394
Pelosi
Token Pelosi
Feature activation+0.987
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.569
The
TokenThe
Feature activation+0.794
House
Token House
Feature activation+1.520
on
Token on
Feature activation+2.960
Friday
Token Friday
Feature activation+0.579
tried
Token tried
Feature activation+0.025
to
Token to
Feature activation+0.173
pass
Token pass
Feature activation+0.000
two
Token two
Feature activation+0.026
was
Token was
Feature activation+0.398
"
Token "
Feature activation+0.000
an
Tokenan
Feature activation+0.099
absolutely
Token absolutely
Feature activation+0.000
natural
Token natural
Feature activation+0.126
reaction
Token reaction
Feature activation+2.910
to
Token to
Feature activation+1.095
the
Token the
Feature activation+0.889
band
Token band
Feature activation+0.000
it
Tokenit
Feature activation+0.453
coup
Token coup
Feature activation+2.256
fell
Token fell
Feature activation+0.000
apart
Token apart
Feature activation+0.095
after
Token after
Feature activation+0.090
Democratic
Token Democratic
Feature activation+3.016
House
Token House
Feature activation+2.679
minority
Token minority
Feature activation+2.904
leader
Token leader
Feature activation+1.149
Nancy
Token Nancy
Feature activation+0.394
Pelosi
Token Pelosi
Feature activation+0.987
and
Token and
Feature activation+1.059
her
Token her
Feature activation+1.619
Wales
Token Wales
Feature activation+0.160
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
struct
Tokenstruct
Feature activation+0.000
ured
Tokenured
Feature activation+1.058
mayhem
Token mayhem
Feature activation+2.892
"
Token"
Feature activation+0.118
with
Token with
Feature activation+0.000
many
Token many
Feature activation+0.057
delays
Token delays
Feature activation+0.103
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.295
produced
Token produced
Feature activation+0.218
"
Token "
Feature activation+0.000
conf
Tokenconf
Feature activation+0.000
lict
Tokenlict
Feature activation+0.213
minerals
Token minerals
Feature activation+2.886
"
Token"
Feature activation+1.307
four
Token four
Feature activation+0.882
years
Token years
Feature activation+0.042
ago
Token ago
Feature activation+0.798
are
Token are
Feature activation+0.033

Top DFA by src position
MAX = 4.000

"
Token "
Feature activation-0.037
Top resid features:
def
Tokendef
Feature activation-0.000
Top resid features:
eat
Tokeneat
Feature activation+0.003
Top resid features:
devices
Token devices
Feature activation-0.003
Top resid features:
"
Token"
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+2.653
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
Car
TokenCar
Feature activation-0.000
Top resid features:
firm
Token firm
Feature activation-0.000
Top resid features:
Volkswagen
Token Volkswagen
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Jonathan
Token Jonathan
Feature activation+0.000
Top resid features:
Franklin
Token Franklin
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Guardian
Token Guardian
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+4.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.000
Top resid features:
Since
TokenSince
Feature activation+0.002
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
dis
Tokendis
Feature activation-0.001
Top resid features:
gr
Tokengr
Feature activation-0.000
Top resid features:
ace
Tokenace
Feature activation+0.001
Top resid features:
ful
Tokenful
Feature activation+0.001
Top resid features:
'
Token'
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+3.225
Top resid features:
Ċ
TokenĊ
Feature activation+0.190
Top resid features:
Mrs
TokenMrs
Feature activation-0.000
Top resid features:
O
Token O
Feature activation-0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Neill
TokenNeill
Feature activation+0.000
Top resid features:
taste
Token taste
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.001
Top resid features:
daily
Token daily
Feature activation-0.000
Top resid features:
commute
Token commute
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+3.591
Top resid features:
Ċ
TokenĊ
Feature activation-0.048
Top resid features:
For
TokenFor
Feature activation+0.011
Top resid features:
C
Token C
Feature activation-0.000
Top resid features:
resp
Tokenresp
Feature activation+0.000
Top resid features:
o
Tokeno
Feature activation-0.001
Top resid features:
president
Token president
Feature activation-0.001
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Constitution
Token Constitution
Feature activation-0.001
Top resid features:
".
Token".
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+2.876
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Congress
TokenCongress
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.000
Top resid features:
changed
Token changed
Feature activation+0.000
Top resid features:
treaty
Token treaty
Feature activation+0.000
Top resid features:
threatened
Token threatened
Feature activation+0.000
Top resid features:
UK
Token UK
Feature activation-0.001
Top resid features:
interests
Token interests
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.069
Top resid features:
Ċ
TokenĊ
Feature activation+1.536
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
He
TokenHe
Feature activation+0.001
Top resid features:
still
Token still
Feature activation+0.001
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.109
Top resid features:
interference
Token interference
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
affairs
Token affairs
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.120
Top resid features:
Ċ
TokenĊ
Feature activation+1.392
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
four
Token four
Feature activation-0.001
Top resid features:
say
Token say
Feature activation+0.001
Top resid features:
Qatar
Token Qatar
Feature activation-0.003
Top resid features:
Earth
Token Earth
Feature activation+0.001
Top resid features:
rotation
Token rotation
Feature activation+0.001
Top resid features:
slows
Token slows
Feature activation+0.003
Top resid features:
Read
Token Read
Feature activation-0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+1.633
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
Geological
Token Geological
Feature activation+0.000
Top resid features:
Survey
Token Survey
Feature activation+0.000
Top resid features:
treaty
Token treaty
Feature activation+0.001
Top resid features:
threatened
Token threatened
Feature activation+0.001
Top resid features:
UK
Token UK
Feature activation-0.001
Top resid features:
interests
Token interests
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.134
Top resid features:
Ċ
TokenĊ
Feature activation+1.542
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
He
TokenHe
Feature activation+0.002
Top resid features:
still
Token still
Feature activation+0.001
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
"
Token "
Feature activation-0.259
Top resid features:
in
Tokenin
Feature activation-0.000
Top resid features:
oco
Tokenoco
Feature activation-0.000
Top resid features:
River
Token River
Feature activation-0.001
Top resid features:
belt
Token belt
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.272
Top resid features:
Ċ
TokenĊ
Feature activation+1.939
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
For
TokenFor
Feature activation+0.001
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
Chavez
Token Chavez
Feature activation-0.000
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
bill
Token bill
Feature activation+0.006
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
month
Token month
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.132
Top resid features:
Ċ
TokenĊ
Feature activation+1.278
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+0.004
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+0.000
Top resid features:
having
Token having
Feature activation+0.000
Top resid features:
treatment
Token treatment
Feature activation+0.000
Top resid features:
following
Token following
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
allegations
Token allegations
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.967
Top resid features:
Ċ
TokenĊ
Feature activation+0.132
Top resid features:
House
TokenHouse
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Cards
Token Cards
Feature activation+0.001
Top resid features:
could
Token could
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
anti
Token anti
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Semitism
TokenSemitism
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.575
Top resid features:
Ċ
TokenĊ
Feature activation+1.517
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
But
TokenBut
Feature activation+0.001
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
uneasy
Token uneasy
Feature activation-0.000
Top resid features:
conference
Token conference
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
space
Token space
Feature activation-0.000
Top resid features:
station
Token station
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+2.178
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
"
Token"
Feature activation-0.001
Top resid features:
It
TokenIt
Feature activation+0.001
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
not
Token not
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
bill
Token bill
Feature activation+0.008
Top resid features:
this
Token this
Feature activation+0.002
Top resid features:
month
Token month
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.109
Top resid features:
Ċ
TokenĊ
Feature activation+1.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
negotiating
Token negotiating
Feature activation+0.001
Top resid features:
countries
Token countries
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+1.638
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
T
TokenT
Feature activation-0.000
Top resid features:
PA
TokenPA
Feature activation+0.000
Top resid features:
allows
Token allows
Feature activation-0.000
Top resid features:
Mr
Token Mr
Feature activation+0.006
Top resid features:
blocking
Token blocking
Feature activation+0.001
Top resid features:
Sev
Token Sev
Feature activation-0.001
Top resid features:
ast
Tokenast
Feature activation+0.000
Top resid features:
opol
Tokenopol
Feature activation-0.000
Top resid features:
airport
Token airport
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+1.490
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
And
TokenAnd
Feature activation+0.003
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
negotiating
Token negotiating
Feature activation+0.000
Top resid features:
countries
Token countries
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+1.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
T
TokenT
Feature activation-0.000
Top resid features:
PA
TokenPA
Feature activation+0.000
Top resid features:
allows
Token allows
Feature activation+0.000
Top resid features:
Mr
Token Mr
Feature activation+0.003
Top resid features:
Justice
Token Justice
Feature activation-0.000
Top resid features:
Alliance
Token Alliance
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.210
Top resid features:
Ċ
TokenĊ
Feature activation+1.456
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
Crown
Token Crown
Feature activation-0.001
Top resid features:
Court
Token Court
Feature activation-0.001
Top resid features:
system
Token system
Feature activation+0.004
Top resid features:
lict
Tokenlict
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
free
Tokenfree
Feature activation-0.002
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
mines
Token mines
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+2.699
Top resid features:
Ċ
TokenĊ
Feature activation+0.313
Top resid features:
More
TokenMore
Feature activation-0.001
Top resid features:
than
Token than
Feature activation-0.001
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.04

Head 3: 0.52

Head 4: 0.07

Head 5: 0.07

Head 6: 0.04

Head 7: 0.04

Head 8: 0.06

Head 9: 0.06

Head 10: 0.03

Head 11: 0.03

Positive logits

Nato8.35

Nasa7.70

7.63

organisers7.30

recognise7.22

organisations7.17

organisation7.11

recognised7.06

programme6.97

realised6.91

realise6.88

organise6.83

authorised6.79

civilisation6.78

programmes6.76

organising6.66

criticised6.59

organised6.57

analyse6.42

maths6.37

Negative logits

—--5.27

-4.65

––-4.34

··-4.29

advertisement-4.27

————-4.10

—"-4.08

.—-4.08

-4.00

­-3.81

——-3.76

ADVERTISEMENT-3.73

-3.65

colored-3.56

-3.55

.–-3.54

)—-3.47

defense-3.44

urized-3.28

apologize-3.26

INTERVAL 4.476 - 4.973
CONTAINS 0.000%

fitted
Token fitted
Feature activation+0.570
with
Token with
Feature activation+0.409
"
Token "
Feature activation+0.177
def
Tokendef
Feature activation+0.000
eat
Tokeneat
Feature activation+0.686
devices
Token devices
Feature activation+4.973
"
Token"
Feature activation+1.802
were
Token were
Feature activation+0.000
registered
Token registered
Feature activation+0.716
in
Token in
Feature activation+0.275
London
Token London
Feature activation+0.561

INTERVAL 3.978 - 4.476
CONTAINS 0.000%

INTERVAL 3.481 - 3.978
CONTAINS 0.001%

can
Token can
Feature activation+0.000
take
Token take
Feature activation+0.888
more
Token more
Feature activation+0.134
than
Token than
Feature activation+0.294
two
Token two
Feature activation+0.737
hours
Token hours
Feature activation+3.733
of
Token of
Feature activation+0.643
her
Token her
Feature activation+0.000
day
Token day
Feature activation+1.743
-
Token -
Feature activation+0.000
each
Token each
Feature activation+0.007
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.419
$
Token $
Feature activation+0.415
75
Token75
Feature activation+3.862
m
Tokenm
Feature activation+2.551
in
Token in
Feature activation+0.000
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+0.833
,
Token,
Feature activation+0.000
Czech
Token Czech
Feature activation+0.467
s
Tokens
Feature activation+1.288
cited
Token cited
Feature activation+0.000
"
Token "
Feature activation+0.000
constitutional
Tokenconstitutional
Feature activation+0.134
reasons
Token reasons
Feature activation+3.593
"
Token"
Feature activation+1.250
for
Token for
Feature activation+0.077
their
Token their
Feature activation+0.023
refusal
Token refusal
Feature activation+1.827
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.522
Constitution
Token Constitution
Feature activation+1.046
".
Token".
Feature activation+0.407
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.608
Congress
TokenCongress
Feature activation+0.452
has
Token has
Feature activation+0.048
repeatedly
Token repeatedly
Feature activation+0.333
changed
Token changed
Feature activation+0.313
the
Token the
Feature activation+0.499
political
Token political
Feature activation+0.000
activist
Token activist
Feature activation+2.011
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.143
own
Token own
Feature activation+0.094
right
Token right
Feature activation+3.750
"
Token"
Feature activation+0.000
who
Token who
Feature activation+0.000
felt
Token felt
Feature activation+0.000
"
Token "
Feature activation+0.000
very
Tokenvery
Feature activation+0.000

INTERVAL 2.984 - 3.481
CONTAINS 0.001%

The
TokenThe
Feature activation+1.453
package
Token package
Feature activation+0.902
fell
Token fell
Feature activation+0.000
apart
Token apart
Feature activation+0.095
after
Token after
Feature activation+0.090
Democratic
Token Democratic
Feature activation+3.016
House
Token House
Feature activation+2.679
minority
Token minority
Feature activation+2.904
leader
Token leader
Feature activation+1.149
Nancy
Token Nancy
Feature activation+0.394
Pelosi
Token Pelosi
Feature activation+0.987
and
Token and
Feature activation+0.049
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
about
Token about
Feature activation+0.124
six
Token six
Feature activation+2.667
miles
Token miles
Feature activation+3.370
(
Token (
Feature activation+0.340
10
Token10
Feature activation+1.599
km
Tokenkm
Feature activation+1.113
)
Token)
Feature activation+1.942
east
Token east
Feature activation+2.540
.
Token.
Feature activation+0.009
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.686
Advertisement
TokenAdvertisement
Feature activation+0.162
Ċ
TokenĊ
Feature activation+0.513
Ċ
TokenĊ
Feature activation+3.092
The
TokenThe
Feature activation+1.453
package
Token package
Feature activation+0.902
fell
Token fell
Feature activation+0.000
apart
Token apart
Feature activation+0.095
after
Token after
Feature activation+0.090
been
Token been
Feature activation+0.185
dated
Token dated
Feature activation+1.488
to
Token to
Feature activation+1.378
about
Token about
Feature activation+0.502
1300
Token 1300
Feature activation+2.605
AD
TokenAD
Feature activation+3.016
and
Token and
Feature activation+0.289
is
Token is
Feature activation+0.145
made
Token made
Feature activation+0.156
of
Token of
Feature activation+0.545
calf
Token calf
Feature activation+0.030
"
Token "
Feature activation+0.000
multi
Tokenmulti
Feature activation+0.627
-
Token-
Feature activation+0.142
p
Tokenp
Feature activation+0.000
olar
Tokenolar
Feature activation+0.593
world
Token world
Feature activation+3.191
"
Token"
Feature activation+0.082
in
Token in
Feature activation+0.000
which
Token which
Feature activation+1.022
Latin
Token Latin
Feature activation+0.425
American
Token American
Feature activation+0.461

INTERVAL 2.486 - 2.984
CONTAINS 0.003%

just
Token just
Feature activation+0.411
after
Token after
Feature activation+1.685
4
Token 4
Feature activation+1.837
.
Token.
Feature activation+0.000
45
Token45
Feature activation+2.863
pm
Tokenpm
Feature activation+2.581
Thursday
Token Thursday
Feature activation+1.250
,
Token,
Feature activation+0.057
and
Token and
Feature activation+0.049
was
Token was
Feature activation+0.000
centered
Token centered
Feature activation+0.000
which
Token which
Feature activation+0.295
produced
Token produced
Feature activation+0.218
"
Token "
Feature activation+0.000
conf
Tokenconf
Feature activation+0.000
lict
Tokenlict
Feature activation+0.213
minerals
Token minerals
Feature activation+2.886
"
Token"
Feature activation+1.307
four
Token four
Feature activation+0.882
years
Token years
Feature activation+0.042
ago
Token ago
Feature activation+0.798
are
Token are
Feature activation+0.033
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.569
The
TokenThe
Feature activation+0.794
House
Token House
Feature activation+1.520
on
Token on
Feature activation+2.960
Friday
Token Friday
Feature activation+0.579
tried
Token tried
Feature activation+0.025
to
Token to
Feature activation+0.173
pass
Token pass
Feature activation+0.000
two
Token two
Feature activation+0.026
the
Token the
Feature activation+0.197
Church
Token Church
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ivity
Tokenivity
Feature activation+2.677
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.602
but
Tokenbut
Feature activation+0.348
declined
Token declined
Feature activation+0.851
to
Token to
Feature activation+0.038
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.419
$
Token $
Feature activation+0.415
75
Token75
Feature activation+3.862
m
Tokenm
Feature activation+2.551
in
Token in
Feature activation+0.000
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+0.833
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.989 - 2.486
CONTAINS 0.005%

,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.336
said
Token said
Feature activation+0.151
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.187
Mr
TokenMr
Feature activation+0.362
Pod
Token Pod
Feature activation+0.000
kan
Tokenkan
Feature activation+0.000
owicz
Tokenowicz
Feature activation+0.837
said
Token said
Feature activation+0.000
-
Token-
Feature activation+0.308
operation
Tokenoperation
Feature activation+0.758
since
Token since
Feature activation+0.335
air
Token air
Feature activation+0.237
strikes
Token strikes
Feature activation+0.977
began
Token began
Feature activation+2.027
in
Token in
Feature activation+0.028
Syria
Token Syria
Feature activation+1.638
in
Token in
Feature activation+0.067
September
Token September
Feature activation+0.000
.
Token.
Feature activation+0.000
gay
Token gay
Feature activation+0.245
or
Token or
Feature activation+0.000
straight
Token straight
Feature activation+0.239
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.017
Ċ
TokenĊ
Feature activation+2.395
K
TokenK
Feature activation+0.000
oz
Tokenoz
Feature activation+0.000
ak
Tokenak
Feature activation+0.658
also
Token also
Feature activation+0.225
appeared
Token appeared
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
40
Token 40
Feature activation+0.777
billion
Token billion
Feature activation+0.716
euros
Token euros
Feature activation+2.013
to
Token to
Feature activation+0.345
leverage
Token leverage
Feature activation+0.208
private
Token private
Feature activation+0.080
investment
Token investment
Feature activation+0.168
in
Token in
Feature activation+0.410
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
the
Token the
Feature activation+0.405
impression
Token impression
Feature activation+0.020
that
Token that
Feature activation+0.000
Mr
Token Mr
Feature activation+2.001
Palin
Token Palin
Feature activation+0.093
and
Token and
Feature activation+0.125
Ms
Token Ms
Feature activation+0.770
Bruce
Token Bruce
Feature activation+0.270
aren
Token aren
Feature activation+0.135

INTERVAL 1.492 - 1.989
CONTAINS 0.017%

and
Token and
Feature activation+0.301
officials
Token officials
Feature activation+0.054
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
portraying
Token portraying
Feature activation+0.357
Ukraine
Token Ukraine
Feature activation+1.843
as
Token as
Feature activation+0.007
a
Token a
Feature activation+0.060
hot
Token hot
Feature activation+0.000
bed
Tokenbed
Feature activation+1.495
of
Token of
Feature activation+0.000
if
Token if
Feature activation+0.174
they
Token they
Feature activation+0.158
succeeded
Token succeeded
Feature activation+1.218
."
Token."
Feature activation+0.051
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.873
G
TokenG
Feature activation+0.000
bag
Tokenbag
Feature activation+0.000
bo
Tokenbo
Feature activation+0.489
refused
Token refused
Feature activation+0.768
to
Token to
Feature activation+0.367
said
Token said
Feature activation+0.000
80
Token 80
Feature activation+0.133
,
Token,
Feature activation+0.008
000
Token000
Feature activation+0.262
VW
Token VW
Feature activation+0.591
engines
Token engines
Feature activation+1.912
fitted
Token fitted
Feature activation+0.570
with
Token with
Feature activation+0.409
"
Token "
Feature activation+0.177
def
Tokendef
Feature activation+0.000
eat
Tokeneat
Feature activation+0.686
coded
Tokencoded
Feature activation+0.000
warning
Token warning
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.573
The
TokenThe
Feature activation+0.108
sm
Token sm
Feature activation+0.000
og
Tokenog
Feature activation+0.265
is
Token is
Feature activation+0.000
expected
Token expected
Feature activation+0.138
TPP
Token TPP
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.569
The
TokenThe
Feature activation+0.794
House
Token House
Feature activation+1.520
on
Token on
Feature activation+2.960
Friday
Token Friday
Feature activation+0.579
tried
Token tried
Feature activation+0.025
to
Token to
Feature activation+0.173
pass
Token pass
Feature activation+0.000

INTERVAL 0.995 - 1.492
CONTAINS 0.052%

Ċ
TokenĊ
Feature activation+0.279
The
TokenThe
Feature activation+0.000
band
Token band
Feature activation+0.054
's
Token's
Feature activation+0.000
debut
Token debut
Feature activation+0.109
album
Token album
Feature activation+1.006
Cost
Token Cost
Feature activation+0.000
ello
Tokenello
Feature activation+0.000
Music
Token Music
Feature activation+0.290
peaked
Token peaked
Feature activation+0.828
at
Token at
Feature activation+0.268
Ċ
TokenĊ
Feature activation+0.008
T
TokenT
Feature activation+0.000
in
Tokenin
Feature activation+0.000
,
Token,
Feature activation+0.035
tantal
Token tantal
Feature activation+2.437
um
Tokenum
Feature activation+1.231
and
Token and
Feature activation+0.000
t
Token t
Feature activation+0.000
ung
Tokenung
Feature activation+0.073
sten
Tokensten
Feature activation+0.410
,
Token,
Feature activation+0.000
make
Token make
Feature activation+0.000
headlines
Token headlines
Feature activation+0.158
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.350
Mr
TokenMr
Feature activation+1.221
P
Token P
Feature activation+0.000
ree
Tokenree
Feature activation+0.000
ce
Tokence
Feature activation+0.332
spent
Token spent
Feature activation+0.183
his
Token his
Feature activation+0.000
approached
Token approached
Feature activation+0.000
,
Token,
Feature activation+0.000
Scott
Token Scott
Feature activation+0.587
exited
Token exited
Feature activation+0.691
the
Token the
Feature activation+0.000
car
Token car
Feature activation+1.131
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
gun
Token gun
Feature activation+0.335
again
Token again
Feature activation+0.770
.
Token.
Feature activation+0.000
composer
Token composer
Feature activation+0.000
Ole
Token Ole
Feature activation+0.000
Bull
Token Bull
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.008
More
TokenMore
Feature activation+0.000
funer
Token funer
Feature activation+0.000
als
Tokenals
Feature activation+0.000
were
Token were
Feature activation+0.000
held
Token held
Feature activation+0.444

INTERVAL 0.497 - 0.995
CONTAINS 0.226%

finances
Token finances
Feature activation+0.502
and
Token and
Feature activation+0.000
Russia
Token Russia
Feature activation+0.485
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.618
A
TokenA
Feature activation+0.000
resolution
Token resolution
Feature activation+0.316
of
Token of
Feature activation+0.000
inquiry
Token inquiry
Feature activation+0.391
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.455
sale
Token sale
Feature activation+0.986
on
Token on
Feature activation+1.198
"
Token "
Feature activation+0.000
closed
Tokenclosed
Feature activation+0.114
"
Token"
Feature activation+0.600
or
Token or
Feature activation+0.266
"
Token "
Feature activation+0.000
secret
Tokensecret
Feature activation+0.625
"
Token"
Feature activation+0.516
Facebook
Token Facebook
Feature activation+0.676
would
Token would
Feature activation+0.035
convince
Token convince
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+1.543
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.249
ify
Tokenify
Feature activation+0.759
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.394
But
TokenBut
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Merkel
Token Merkel
Feature activation+0.000
told
Token told
Feature activation+0.453
the
Token the
Feature activation+0.311
U
Token U
Feature activation+0.834
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.725
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.552
Tuesday
Token Tuesday
Feature activation+0.125
to
Token to
Feature activation+0.000
expect
Token expect
Feature activation+0.183
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.809
The
TokenThe
Feature activation+0.464
officer
Token officer
Feature activation+0.507
in
Token in
Feature activation+0.984
charge
Token charge
Feature activation+0.976
of
Token of
Feature activation+0.208
the
Token the
Feature activation+0.000
inquiry
Token inquiry
Feature activation+0.457
,
Token,
Feature activation+0.090
Jose
Token Jose
Feature activation+0.000

INTERVAL 0.000 - 0.497
CONTAINS 99.696%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
possible
Token possible
Feature activation+0.000
reason
Token reason
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
oppose
Token oppose
Feature activation+0.000
taxpayer
Token taxpayer
Feature activation+0.000
funding
Token funding
Feature activation+0.000
explicit
Token explicit
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
all
Token all
Feature activation+0.000
felt
Token felt
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+0.000
She
Token She
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000
gone
Token gone
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
Taco
Token Taco
Feature activation+0.000
Bell
Token Bell
Feature activation+0.000
.
Token.
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
Ob
Token Ob
Feature activation+0.000
ney
Tokenney
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
photo
Token photo
Feature activation+0.000
collection
Token collection
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
him
Token him
Feature activation+0.000
continuing
Token continuing
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 H10.3: (feature 23924)

TOP ACTIVATIONS
MAX = 6.590

have
Token have
Feature activation+0.000
great
Token great
Feature activation+0.000
chemistry
Token chemistry
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
but
Tokenbut
Feature activation+6.590
]
Token ]
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
changing
Token changing
Feature activation+0.000
[
Token [
Feature activation+0.000
policy
Tokenpolicy
Feature activation+6.147
]
Token]
Feature activation+0.000
forever
Token forever
Feature activation+0.000
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
the
Token the
Feature activation+0.000
For
TokenFor
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
it
Tokenit
Feature activation+5.776
was
Token was
Feature activation+6.033
]
Token]
Feature activation+0.000
an
Token an
Feature activation+0.000
incredible
Token incredible
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
[
Token [
Feature activation+0.000
support
Tokensupport
Feature activation+4.032
ing
Tokening
Feature activation+5.967
]
Token]
Feature activation+0.000
council
Token council
Feature activation+0.000
's
Token's
Feature activation+0.000
goals
Token goals
Feature activation+0.000
and
Token and
Feature activation+0.535
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
businessman
Token businessman
Feature activation+0.000
[
Token [
Feature activation+0.000
like
Tokenlike
Feature activation+1.855
Trump
Token Trump
Feature activation+5.781
]
Token]
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
"
Token "
Feature activation+0.000
For
TokenFor
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
it
Tokenit
Feature activation+5.776
was
Token was
Feature activation+6.033
]
Token]
Feature activation+0.000
an
Token an
Feature activation+0.000
incredible
Token incredible
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
ten
Token ten
Feature activation+0.000
ement
Tokenement
Feature activation+0.000
-
Token-
Feature activation+0.000
houses
Tokenhouses
Feature activation+0.018
[
Token [
Feature activation+0.000
were
Tokenwere
Feature activation+5.731
]
Token]
Feature activation+0.000
owned
Token owned
Feature activation+0.000
jointly
Token jointly
Feature activation+0.000
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.000
American
Token American
Feature activation+0.000
[
Token [
Feature activation+0.000
public
Tokenpublic
Feature activation+5.252
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.373
s
Tokens
Feature activation+5.674
]
Token]
Feature activation+0.000
red
Token red
Feature activation+0.000
line
Token line
Feature activation+0.000
is
Token is
Feature activation+0.000
:
Token:
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
present
Token present
Feature activation+0.000
[
Token [
Feature activation+0.000
sur
Tokensur
Feature activation+0.000
rog
Tokenrog
Feature activation+0.000
acy
Tokenacy
Feature activation+5.642
]
Token]
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
win
Token win
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
control
Tokencontrol
Feature activation+0.000
[
Token [
Feature activation+0.000
its
Tokenits
Feature activation+5.622
]
Token]
Feature activation+0.000
borders
Token borders
Feature activation+0.000
against
Token against
Feature activation+0.000
both
Token both
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
The
TokenThe
Feature activation+1.923
S
Token S
Feature activation+0.000
RO
TokenRO
Feature activation+4.917
s
Tokens
Feature activation+5.611
]
Token]
Feature activation+0.000
treat
Token treat
Feature activation+0.000
kids
Token kids
Feature activation+0.000
as
Token as
Feature activation+0.000
little
Token little
Feature activation+0.000
Many
TokenMany
Feature activation+0.000
countries
Token countries
Feature activation+0.000
feel
Token feel
Feature activation+0.000
[
Token [
Feature activation+0.000
foreign
Tokenforeign
Feature activation+1.976
parents
Token parents
Feature activation+5.578
]
Token]
Feature activation+0.000
simply
Token simply
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
for
Token for
Feature activation+0.000
California
Token California
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
[
Token [
Feature activation+0.000
also
Tokenalso
Feature activation+5.349
]
Token]
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
crucial
Token crucial
Feature activation+0.000
difference
Token difference
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
[
Token [
Feature activation+0.000
existing
Tokenexisting
Feature activation+5.317
]
Token]
Feature activation+0.000
customs
Token customs
Feature activation+0.000
union
Token union
Feature activation+0.561
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
We
TokenWe
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
allow
Token allow
Feature activation+0.000
[
Token [
Feature activation+0.000
it
Tokenit
Feature activation+5.317
]
Token]
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
submerged
Token submerged
Feature activation+0.000
by
Token by
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
it
Tokenit
Feature activation+0.000
in
Token in
Feature activation+0.000
[
Token [
Feature activation+0.000
his
Tokenhis
Feature activation+5.307
]
Token]
Feature activation+0.000
footsteps
Token footsteps
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+1.263
provider
Token provider
Feature activation+5.274
]
Token]
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
degree
Token degree
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
[
Token [
Feature activation+0.000
public
Tokenpublic
Feature activation+5.252
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.373
s
Tokens
Feature activation+5.674
]
Token]
Feature activation+0.000
red
Token red
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
[
Token [
Feature activation+0.000
W
TokenW
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ford
Tokenford
Feature activation+5.251
]
Token]
Feature activation+0.000
was
Token was
Feature activation+0.000
really
Token really
Feature activation+0.000
bad
Token bad
Feature activation+0.000
off
Token off
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
j
Tokenj
Feature activation+0.771
ur
Tokenur
Feature activation+0.000
ors
Tokenors
Feature activation+5.173
]
Token]
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.079
been
Token been
Feature activation+0.000

Top DFA by src position
MAX = 6.507

to
Token to
Feature activation+0.006
Top resid features:
have
Token have
Feature activation+0.003
Top resid features:
great
Token great
Feature activation+0.001
Top resid features:
chemistry
Token chemistry
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
[
Token [
Feature activation+6.495
Top resid features:
but
Tokenbut
Feature activation+0.080
Top resid features:
]
Token ]
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
passing
Token passing
Feature activation-0.014
Top resid features:
them
Token them
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
changing
Token changing
Feature activation+0.086
Top resid features:
[
Token [
Feature activation+6.391
Top resid features:
policy
Tokenpolicy
Feature activation+0.270
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
forever
Token forever
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
allowing
Token allowing
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
"
Token "
Feature activation-0.054
Top resid features:
For
TokenFor
Feature activation-0.004
Top resid features:
me
Token me
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
[
Token [
Feature activation+6.507
Top resid features:
it
Tokenit
Feature activation+0.095
Top resid features:
was
Token was
Feature activation+0.018
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
incredible
Token incredible
Feature activation+0.000
Top resid features:
That
TokenThat
Feature activation+0.004
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
well
Token well
Feature activation-0.001
Top resid features:
as
Token as
Feature activation+0.014
Top resid features:
[
Token [
Feature activation+6.083
Top resid features:
support
Tokensupport
Feature activation+0.029
Top resid features:
ing
Tokening
Feature activation+0.071
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
council
Token council
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.008
Top resid features:
We
TokenWe
Feature activation+0.000
Top resid features:
need
Token need
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
businessman
Token businessman
Feature activation-0.063
Top resid features:
[
Token [
Feature activation+6.461
Top resid features:
like
Tokenlike
Feature activation+0.102
Top resid features:
Trump
Token Trump
Feature activation-0.050
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
"
Token "
Feature activation-0.039
Top resid features:
For
TokenFor
Feature activation-0.007
Top resid features:
me
Token me
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
[
Token [
Feature activation+6.324
Top resid features:
it
Tokenit
Feature activation+0.048
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
incredible
Token incredible
Feature activation+0.000
Top resid features:
while
Token while
Feature activation-0.011
Top resid features:
ten
Token ten
Feature activation-0.002
Top resid features:
ement
Tokenement
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.020
Top resid features:
houses
Tokenhouses
Feature activation+0.314
Top resid features:
[
Token [
Feature activation+3.944
Top resid features:
were
Tokenwere
Feature activation+0.023
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
owned
Token owned
Feature activation+0.000
Top resid features:
jointly
Token jointly
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
certain
Token certain
Feature activation+0.007
Top resid features:
degree
Token degree
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
American
Token American
Feature activation+0.018
Top resid features:
[
Token [
Feature activation+5.383
Top resid features:
public
Tokenpublic
Feature activation+0.121
Top resid features:
âĢ
TokenâĢ
Feature activation+0.104
Top resid features:
Ļ
TokenĻ
Feature activation+0.205
Top resid features:
s
Tokens
Feature activation+0.123
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
World
Token World
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
agencies
Token agencies
Feature activation+0.026
Top resid features:
present
Token present
Feature activation+0.129
Top resid features:
[
Token [
Feature activation+4.669
Top resid features:
sur
Tokensur
Feature activation-0.032
Top resid features:
rog
Tokenrog
Feature activation-0.018
Top resid features:
acy
Tokenacy
Feature activation-0.005
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
had
Token had
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.055
Top resid features:
ĺ
Tokenĺ
Feature activation-0.005
Top resid features:
control
Tokencontrol
Feature activation+0.129
Top resid features:
[
Token [
Feature activation+6.147
Top resid features:
its
Tokenits
Feature activation-0.002
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
borders
Token borders
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
out
Token out
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
school
Token school
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
[
Token [
Feature activation+6.013
Top resid features:
The
TokenThe
Feature activation+0.100
Top resid features:
S
Token S
Feature activation-0.002
Top resid features:
RO
TokenRO
Feature activation-0.009
Top resid features:
s
Tokens
Feature activation+0.045
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.069
Top resid features:
ľ
Tokenľ
Feature activation-0.005
Top resid features:
Many
TokenMany
Feature activation-0.005
Top resid features:
countries
Token countries
Feature activation-0.001
Top resid features:
feel
Token feel
Feature activation-0.007
Top resid features:
[
Token [
Feature activation+6.073
Top resid features:
foreign
Tokenforeign
Feature activation-0.102
Top resid features:
parents
Token parents
Feature activation+0.053
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
simply
Token simply
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.052
Top resid features:
California
Token California
Feature activation+0.149
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
but
Token but
Feature activation+0.130
Top resid features:
[
Token [
Feature activation+5.785
Top resid features:
also
Tokenalso
Feature activation-0.080
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
United
Token United
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
crucial
Token crucial
Feature activation+0.001
Top resid features:
difference
Token difference
Feature activation+0.004
Top resid features:
between
Token between
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
[
Token [
Feature activation+5.399
Top resid features:
existing
Tokenexisting
Feature activation+0.104
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
customs
Token customs
Feature activation+0.000
Top resid features:
union
Token union
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
"
Token"
Feature activation-0.055
Top resid features:
We
TokenWe
Feature activation+0.002
Top resid features:
will
Token will
Feature activation-0.002
Top resid features:
not
Token not
Feature activation-0.004
Top resid features:
allow
Token allow
Feature activation-0.006
Top resid features:
[
Token [
Feature activation+4.306
Top resid features:
it
Tokenit
Feature activation+0.027
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
submerged
Token submerged
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.010
Top resid features:
sp
Tokensp
Feature activation-0.003
Top resid features:
it
Tokenit
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.042
Top resid features:
[
Token [
Feature activation+5.764
Top resid features:
his
Tokenhis
Feature activation+0.028
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
footsteps
Token footsteps
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
recipient
Token recipient
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.056
Top resid features:
Ļ
TokenĻ
Feature activation-0.011
Top resid features:
s
Tokens
Feature activation-0.007
Top resid features:
[
Token [
Feature activation+5.354
Top resid features:
email
Tokenemail
Feature activation+0.029
Top resid features:
provider
Token provider
Feature activation+0.004
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
certain
Token certain
Feature activation+0.004
Top resid features:
degree
Token degree
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
American
Token American
Feature activation+0.033
Top resid features:
[
Token [
Feature activation+5.413
Top resid features:
public
Tokenpublic
Feature activation+0.079
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Telegraph
Token Telegraph
Feature activation-0.011
Top resid features:
:
Token:
Feature activation-0.009
Top resid features:
'
Token '
Feature activation-0.008
Top resid features:
I
TokenI
Feature activation+0.001
Top resid features:
know
Token know
Feature activation-0.019
Top resid features:
[
Token [
Feature activation+5.824
Top resid features:
W
TokenW
Feature activation+0.013
Top resid features:
ol
Tokenol
Feature activation+0.004
Top resid features:
ford
Tokenford
Feature activation+0.020
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
clear
Token clear
Feature activation-0.003
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
[
Token [
Feature activation+5.698
Top resid features:
j
Tokenj
Feature activation+0.008
Top resid features:
ur
Tokenur
Feature activation-0.004
Top resid features:
ors
Tokenors
Feature activation+0.138
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.03

Head 3: 0.50

Head 4: 0.11

Head 5: 0.10

Head 6: 0.02

Head 7: 0.04

Head 8: 0.04

Head 9: 0.04

Head 10: 0.02

Head 11: 0.04

Positive logits

]8.35

],8.21

],"8.20

].8.03

]."7.92

]7.66

?]7.47

].7.42

.]7.28

]:7.27

']7.27

],7.27

]"7.26

]}7.14

]'7.03

!]7.00

]-6.87

];6.83

:]6.82

"]6.56

Negative logits

"))-3.02

)).-2.32

))-2.24

76561-2.24

ÍÍ-2.15

prototype-2.14

))-2.13

));-2.09

icka-2.09

));-2.02

METHOD-1.99

merga-1.96

Blueprint-1.94

blance-1.94

morrow-1.91

lucky-1.91

umpy-1.86

uez-1.86

hov-1.82

unic-1.80

INTERVAL 5.931 - 6.590
CONTAINS 0.000%

as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
[
Token [
Feature activation+0.000
support
Tokensupport
Feature activation+4.032
ing
Tokening
Feature activation+5.967
]
Token]
Feature activation+0.000
council
Token council
Feature activation+0.000
's
Token's
Feature activation+0.000
goals
Token goals
Feature activation+0.000
and
Token and
Feature activation+0.535
For
TokenFor
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
it
Tokenit
Feature activation+5.776
was
Token was
Feature activation+6.033
]
Token]
Feature activation+0.000
an
Token an
Feature activation+0.000
incredible
Token incredible
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
great
Token great
Feature activation+0.000
chemistry
Token chemistry
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
but
Tokenbut
Feature activation+6.590
]
Token ]
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
changing
Token changing
Feature activation+0.000
[
Token [
Feature activation+0.000
policy
Tokenpolicy
Feature activation+6.147
]
Token]
Feature activation+0.000
forever
Token forever
Feature activation+0.000
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 5.272 - 5.931
CONTAINS 0.001%

"
Token "
Feature activation+0.000
For
TokenFor
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
[
Token [
Feature activation+0.000
it
Tokenit
Feature activation+5.776
was
Token was
Feature activation+6.033
]
Token]
Feature activation+0.000
an
Token an
Feature activation+0.000
incredible
Token incredible
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
ten
Token ten
Feature activation+0.000
ement
Tokenement
Feature activation+0.000
-
Token-
Feature activation+0.000
houses
Tokenhouses
Feature activation+0.018
[
Token [
Feature activation+0.000
were
Tokenwere
Feature activation+5.731
]
Token]
Feature activation+0.000
owned
Token owned
Feature activation+0.000
jointly
Token jointly
Feature activation+0.000
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.000
crucial
Token crucial
Feature activation+0.000
difference
Token difference
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
[
Token [
Feature activation+0.000
existing
Tokenexisting
Feature activation+5.317
]
Token]
Feature activation+0.000
customs
Token customs
Feature activation+0.000
union
Token union
Feature activation+0.561
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+1.263
provider
Token provider
Feature activation+5.274
]
Token]
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
present
Token present
Feature activation+0.000
[
Token [
Feature activation+0.000
sur
Tokensur
Feature activation+0.000
rog
Tokenrog
Feature activation+0.000
acy
Tokenacy
Feature activation+5.642
]
Token]
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
win
Token win
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 4.613 - 5.272
CONTAINS 0.002%

school
Token school
Feature activation+0.000
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
The
TokenThe
Feature activation+1.923
S
Token S
Feature activation+0.000
RO
TokenRO
Feature activation+4.917
s
Tokens
Feature activation+5.611
]
Token]
Feature activation+0.000
treat
Token treat
Feature activation+0.000
kids
Token kids
Feature activation+0.000
as
Token as
Feature activation+0.000
[
Token [
Feature activation+0.000
the
Tokenthe
Feature activation+3.858
J
Token J
Feature activation+0.000
T
TokenT
Feature activation+2.106
AC
TokenAC
Feature activation+4.478
's
Token's
Feature activation+4.680
]
Token]
Feature activation+0.176
assessment
Token assessment
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
degree
Token degree
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
[
Token [
Feature activation+0.000
public
Tokenpublic
Feature activation+5.252
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.373
s
Tokens
Feature activation+5.674
]
Token]
Feature activation+0.000
red
Token red
Feature activation+0.000
"
Token "
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
then
Token then
Feature activation+0.000
[
Token [
Feature activation+0.000
Thor
Token Thor
Feature activation+4.264
was
Token was
Feature activation+4.684
]
Token]
Feature activation+0.000
number
Token number
Feature activation+0.000
three
Token three
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
[
Token [
Feature activation+0.000
W
TokenW
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ford
Tokenford
Feature activation+5.251
]
Token]
Feature activation+0.000
was
Token was
Feature activation+0.000
really
Token really
Feature activation+0.000
bad
Token bad
Feature activation+0.000
off
Token off
Feature activation+0.000

INTERVAL 3.954 - 4.613
CONTAINS 0.004%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
operations
Token operations
Feature activation+0.000
of
Token of
Feature activation+0.000
[
Token [
Feature activation+0.000
her
Tokenher
Feature activation+4.032
]
Token]
Feature activation+0.000
own
Token own
Feature activation+0.000
faculties
Token faculties
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
We
TokenWe
Feature activation+0.000
practiced
Token practiced
Feature activation+0.000
in
Token in
Feature activation+0.000
them
Token them
Feature activation+0.000
[
Token [
Feature activation+0.000
Sunday
TokenSunday
Feature activation+4.573
]
Token]
Feature activation+0.000
--
Token --
Feature activation+0.000
now
Token now
Feature activation+0.000
we
Token we
Feature activation+0.000
'll
Token'll
Feature activation+0.000
have
Token have
Feature activation+3.871
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
leg
Token leg
Feature activation+4.224
at
Token at
Feature activation+0.683
home
Token home
Feature activation+4.429
].
Token].
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
friend
Token friend
Feature activation+0.000
[
Token [
Feature activation+0.000
He
TokenHe
Feature activation+0.006
ath
Tokenath
Feature activation+1.150
Led
Token Led
Feature activation+0.000
ger
Tokenger
Feature activation+4.084
]
Token]
Feature activation+0.000
died
Token died
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
his
Token his
Feature activation+0.000
pickup
Token pickup
Feature activation+0.000
of
Token of
Feature activation+0.000
[
Token [
Feature activation+0.000
Company
TokenCompany
Feature activation+0.052
of
Token of
Feature activation+0.000
Heroes
Token Heroes
Feature activation+4.398
developer
Token developer
Feature activation+3.330
]
Token]
Feature activation+0.000
Relic
Token Relic
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 3.295 - 3.954
CONTAINS 0.003%

of
Tokenof
Feature activation+3.060
the
Token the
Feature activation+2.355
country
Token country
Feature activation+2.502
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.063
s
Tokens
Feature activation+3.751
population
Token population
Feature activation+2.807
]
Token]
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
name
Token name
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
[
Token [
Feature activation+0.000
an
Tokenan
Feature activation+0.000
ancient
Token ancient
Feature activation+0.000
Sanskrit
Token Sanskrit
Feature activation+0.000
language
Token language
Feature activation+3.592
scholar
Token scholar
Feature activation+3.642
]
Token]
Feature activation+0.000
means
Token means
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
those
Token those
Feature activation+0.000
teams
Token teams
Feature activation+0.000
[
Token [
Feature activation+0.000
to
Tokento
Feature activation+3.268
have
Token have
Feature activation+3.871
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
leg
Token leg
Feature activation+4.224
at
Token at
Feature activation+0.683
home
Token home
Feature activation+4.429
completely
Token completely
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
[
Token [
Feature activation+0.000
the
Tokenthe
Feature activation+4.252
members
Token members
Feature activation+3.505
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
]
Token]
Feature activation+0.000
possession
Token possession
Feature activation+0.000
.
Token.
Feature activation+0.000
We
TokenWe
Feature activation+0.000
had
Token had
Feature activation+0.000
some
Token some
Feature activation+0.000
[
Token [
Feature activation+0.000
compan
Tokencompan
Feature activation+0.000
ies
Tokenies
Feature activation+3.849
]
Token]
Feature activation+0.000
that
Token that
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
'
Token '
Feature activation+0.000

INTERVAL 2.636 - 3.295
CONTAINS 0.003%

and
Token and
Feature activation+0.000
give
Token give
Feature activation+0.000
[
Token [
Feature activation+0.266
the
Tokenthe
Feature activation+0.821
first
Token first
Feature activation+1.499
team
Token team
Feature activation+3.003
]
Token]
Feature activation+0.768
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
break
Token break
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.112
say
Token say
Feature activation+1.451
,
Token,
Feature activation+0.000
portraying
Token portraying
Feature activation+0.059
their
Token their
Feature activation+0.000
violence
Token violence
Feature activation+2.662
as
Token as
Feature activation+0.147
a
Token a
Feature activation+0.000
product
Token product
Feature activation+1.367
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
g
Tokeng
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
ances
Tokenances
Feature activation+3.049
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.995
].
Token].
Feature activation+0.000
But
Token But
Feature activation+0.000
if
Token if
Feature activation+0.000
borrowed
Token borrowed
Feature activation+0.000
this
Token this
Feature activation+0.000
[
Token [
Feature activation+0.000
360
Token360
Feature activation+0.712
-
Token-
Feature activation+0.000
degree
Tokendegree
Feature activation+2.897
]
Token]
Feature activation+0.000
camera
Token camera
Feature activation+0.000
someone
Token someone
Feature activation+0.000
just
Token just
Feature activation+0.000
made
Token made
Feature activation+0.000
,
Token,
Feature activation+0.000
Ob
Token Ob
Feature activation+0.000
a
Tokena
Feature activation+0.000
[
Token [
Feature activation+0.000
Mart
TokenMart
Feature activation+0.000
ins
Tokenins
Feature activation+3.020
]
Token]
Feature activation+0.000
and
Token and
Feature activation+0.000
myself
Token myself
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000

INTERVAL 1.977 - 2.636
CONTAINS 0.003%

means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
[
Token [
Feature activation+0.000
the
Tokenthe
Feature activation+3.858
J
Token J
Feature activation+0.000
T
TokenT
Feature activation+2.106
AC
TokenAC
Feature activation+4.478
's
Token's
Feature activation+4.680
]
Token]
Feature activation+0.176
assessment
Token assessment
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
worked
Token worked
Feature activation+0.000
for
Token for
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+2.236
)
Token)
Feature activation+0.000
fought
Token fought
Feature activation+0.000
for
Token for
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Tokenin
Feature activation+0.961
which
Token which
Feature activation+2.951
case
Token case
Feature activation+3.985
,
Token,
Feature activation+2.195
bin
Token bin
Feature activation+0.000
Laden
Token Laden
Feature activation+2.024
later
Token later
Feature activation+1.105
clar
Token clar
Feature activation+0.000
ifies
Tokenifies
Feature activation+4.075
,
Token,
Feature activation+2.093
they
Token they
Feature activation+0.689
the
Token the
Feature activation+1.166
Dem
Token Dem
Feature activation+0.000
io
Tokenio
Feature activation+4.014
in
Token in
Feature activation+0.000
some
Token some
Feature activation+0.000
markets
Token markets
Feature activation+2.494
]
Token]
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
highly
Token highly
Feature activation+0.000
competitive
Token competitive
Feature activation+0.000
general
Token general
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
[
Token [
Feature activation+0.000
Prince
TokenPrince
Feature activation+0.000
Philip
Token Philip
Feature activation+2.354
and
Token and
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
Mont
Token Mont
Feature activation+0.000
b
Tokenb
Feature activation+0.000
atten
Tokenatten
Feature activation+4.395

INTERVAL 1.318 - 1.977
CONTAINS 0.004%

We
TokenWe
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
businessman
Token businessman
Feature activation+0.000
[
Token [
Feature activation+0.000
like
Tokenlike
Feature activation+1.855
Trump
Token Trump
Feature activation+5.781
]
Token]
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
year
Token year
Feature activation+0.000
or
Token or
Feature activation+0.000
two
Token two
Feature activation+0.000
[
Token [
Feature activation+0.000
before
Tokenbefore
Feature activation+1.740
it
Token it
Feature activation+1.594
comes
Token comes
Feature activation+0.604
out
Token out
Feature activation+3.342
],
Token],
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
here
Token here
Feature activation+0.000
to
Token to
Feature activation+0.000
focus
Token focus
Feature activation+0.000
on
Token on
Feature activation+0.000
[
Token [
Feature activation+0.000
Marvel
TokenMarvel
Feature activation+1.698
].
Token].
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
breast
Token breast
Feature activation+0.000
feed
Tokenfeed
Feature activation+1.480
unless
Token unless
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+0.000
SB
TokenSB
Feature activation+0.000
[
Token [
Feature activation+0.000
Russian
TokenRussian
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Security
Token Security
Feature activation+0.000
Service
Token Service
Feature activation+1.708
]
Token]
Feature activation+0.000
ready
Token ready
Feature activation+0.000
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+0.000

INTERVAL 0.659 - 1.318
CONTAINS 0.009%

because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
racial
Token racial
Feature activation+0.000
discord
Token discord
Feature activation+0.000
[
Token [
Feature activation+0.000
in
Tokenin
Feature activation+1.068
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
department
Token department
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Bin
Token Bin
Feature activation+0.000
Laden
Token Laden
Feature activation+1.525
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.390
s
Tokens
Feature activation+0.000
brother
Token brother
Feature activation+0.787
]
Token]
Feature activation+0.000
Bakr
Token Bakr
Feature activation+0.000
bin
Token bin
Feature activation+0.000
Laden
Token Laden
Feature activation+0.000
and
Token and
Feature activation+0.000
recipient
Token recipient
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+1.263
provider
Token provider
Feature activation+5.274
]
Token]
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.000
2021
Token 2021
Feature activation+0.000
,
Token,
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
[
Token [
Feature activation+0.000
car
Tokencar
Feature activation+0.894
rier
Tokenrier
Feature activation+3.840
rocket
Token rocket
Feature activation+3.303
]
Token]
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
combination
Token combination
Feature activation+1.108
of
Token of
Feature activation+0.812
B
Token B
Feature activation+0.000
isson
Tokenisson
Feature activation+0.000
nette
Tokennette
Feature activation+0.259
and
Token and
Feature activation+0.000
Scott
Token Scott
Feature activation+0.739

INTERVAL 0.000 - 0.659
CONTAINS 99.970%

've
Token've
Feature activation+0.000
been
Token been
Feature activation+0.000
slept
Token slept
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
wake
Token wake
Feature activation+0.000
,
Token,
Feature activation+0.000
defendant
Token defendant
Feature activation+0.000
or
Token or
Feature activation+0.000
plaintiff
Token plaintiff
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+0.000
normally
Token normally
Feature activation+0.000
goes
Token goes
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
weekly
Token weekly
Feature activation+0.000
trial
Token trial
Feature activation+0.000
quests
Token quests
Feature activation+0.000
in
Token in
Feature activation+0.000
Aether
Token Aether
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
Archive
Token Archive
Feature activation+0.000
,
Token,
Feature activation+0.000
Sanct
Token Sanct
Feature activation+0.000
um
Tokenum
Feature activation+0.000
O
Token O
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
5
Token 5
Feature activation+0.000
th
Tokenth
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
price
Token price
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
subscription
Token subscription
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token5
Feature activation+0.000
p
Token p
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
ET
Token ET
Feature activation+0.000
,
Token,
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
Bowl
Token Bowl
Feature activation+0.000
-
Token -
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H10.3: (feature 22105)

TOP ACTIVATIONS
MAX = 4.706

short
Token short
Feature activation+0.000
period
Token period
Feature activation+0.995
of
Token of
Feature activation+0.000
time
Token time
Feature activation+2.175
,
Token,
Feature activation+0.000
though
Token though
Feature activation+4.706
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.114
have
Token have
Feature activation+0.000
changed
Token changed
Feature activation+2.476
,
Token,
Feature activation+0.000
play
Token play
Feature activation+0.418
caught
Token caught
Feature activation+0.000
Fa
Token Fa
Feature activation+0.000
Ze
TokenZe
Feature activation+0.094
off
Token off
Feature activation+0.000
guard
Token guard
Feature activation+4.502
and
Token and
Feature activation+0.000
Reneg
Token Reneg
Feature activation+0.000
ades
Tokenades
Feature activation+0.270
followed
Token followed
Feature activation+1.671
it
Token it
Feature activation+1.684
what
Token what
Feature activation+0.000
G
Token G
Feature activation+0.000
j
Tokenj
Feature activation+0.000
oni
Tokenoni
Feature activation+0.263
had
Token had
Feature activation+0.942
done
Token done
Feature activation+4.421
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.008
her
Token her
Feature activation+0.000
allegation
Token allegation
Feature activation+1.972
that
Token that
Feature activation+0.000
that
Token that
Feature activation+0.000
could
Token could
Feature activation+0.000
stand
Token stand
Feature activation+0.132
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
way
Token way
Feature activation+4.406
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
would
Token would
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+0.809
it
Token it
Feature activation+0.000
ple
Token ple
Feature activation+0.000
ases
Tokenases
Feature activation+4.268
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
if
Token if
Feature activation+0.000
big
Token big
Feature activation+2.181
publishers
Token publishers
Feature activation+1.023
and
Tokenand
Feature activation+0.461
then
Token then
Feature activation+2.036
would
Token would
Feature activation+0.505
sc
Token sc
Feature activation+0.000
oot
Tokenoot
Feature activation+0.727
away
Token away
Feature activation+4.252
.
Token.
Feature activation+0.106
"
Token "
Feature activation+0.000
You
TokenYou
Feature activation+0.044
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.402
or
Tokenor
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
original
Token original
Feature activation+0.000
form
Token form
Feature activation+4.204
,
Token,
Feature activation+0.000
men
Token men
Feature activation+0.286
ager
Tokenager
Feature activation+0.000
ies
Tokenies
Feature activation+3.178
âĢĶ
TokenâĢĶ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.551
then
Token then
Feature activation+2.455
just
Token just
Feature activation+1.188
like
Token like
Feature activation+1.663
that
Token that
Feature activation+4.192
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.318
walks
Token walks
Feature activation+0.000
away
Token away
Feature activation+2.741
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
oldest
Token oldest
Feature activation+1.349
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
know
Token know
Feature activation+3.460
of
Token of
Feature activation+4.164
was
Token was
Feature activation+0.000
uncovered
Token uncovered
Feature activation+0.431
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+2.930
during
Token during
Feature activation+0.000
"
Token"
Feature activation+0.000
A
Token A
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
rup
Tokenrup
Feature activation+2.771
and
Token and
Feature activation+0.000
co
Token co
Feature activation+4.162
.
Token.
Feature activation+2.731
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
one
Token one
Feature activation+2.839
concept
Token concept
Feature activation+1.263
works
Token works
Feature activation+3.362
with
Token with
Feature activation+0.000
larger
Token larger
Feature activation+0.000
ov
Token ov
Feature activation+0.000
aries
Tokenaries
Feature activation+4.148
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
'll
Token'll
Feature activation+0.000
implant
Token implant
Feature activation+0.000
these
Token these
Feature activation+0.000
this
Token this
Feature activation+0.983
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
guard
Token guard
Feature activation+1.582
spl
Token spl
Feature activation+0.000
itter
Tokenitter
Feature activation+4.134
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
sport
Token sport
Feature activation+0.000
o
Tokeno
Feature activation+0.000
vel
Tokenvel
Feature activation+0.000
ed
Tokened
Feature activation+0.000
path
Token path
Feature activation+2.020
to
Token to
Feature activation+0.000
victory
Token victory
Feature activation+4.105
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.352
there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
spawned
Token spawned
Feature activation+0.533
of
Token of
Feature activation+0.000
unusually
Token unusually
Feature activation+0.000
warm
Token warm
Feature activation+0.000
ocean
Token ocean
Feature activation+0.733
waters
Token waters
Feature activation+4.095
?
Token?
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+1.512
,
Token,
Feature activation+0.000
free
Token free
Feature activation+1.566
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
distraction
Token distraction
Feature activation+2.304
of
Token of
Feature activation+0.000
capitalism
Token capitalism
Feature activation+4.094
.
Token.
Feature activation+0.000
Also
Token Also
Feature activation+3.110
,
Token,
Feature activation+0.129
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.097
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+2.602
,
Token,
Feature activation+0.000
however
Token however
Feature activation+4.066
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
measurement
Token measurement
Feature activation+0.375
of
Token of
Feature activation+0.000
polarization
Token polarization
Feature activation+0.763
oy
Tokenoy
Feature activation+3.182
is
Token is
Feature activation+0.000
joining
Token joining
Feature activation+0.000
in
Token in
Feature activation+2.097
,
Token,
Feature activation+0.000
too
Token too
Feature activation+4.061
,
Token,
Feature activation+0.000
telling
Token telling
Feature activation+0.000
NPR
Token NPR
Feature activation+1.397
's
Token's
Feature activation+0.000
"
Token "
Feature activation+0.000
Penguin
Token Penguin
Feature activation+0.000
Random
Token Random
Feature activation+0.000
House
Token House
Feature activation+1.002
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+3.965
,
Token,
Feature activation+0.372
is
Token is
Feature activation+0.241
big
Token big
Feature activation+1.277
enough
Token enough
Feature activation+3.013
to
Token to
Feature activation+0.000
reported
Token reported
Feature activation+0.000
stolen
Token stolen
Feature activation+2.106
in
Token in
Feature activation+0.000
England
Token England
Feature activation+2.988
and
Token and
Feature activation+0.000
Wales
Token Wales
Feature activation+3.960
:
Token:
Feature activation+0.000
in
Token in
Feature activation+0.000
2012
Token 2012
Feature activation+0.933
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
Sandy
Token Sandy
Feature activation+0.928
herself
Token herself
Feature activation+1.911
has
Token has
Feature activation+2.171
so
Token so
Feature activation+0.000
loudly
Token loudly
Feature activation+1.320
said
Token said
Feature activation+3.960
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
global
Tokenglobal
Feature activation+0.000
warming
Token warming
Feature activation+2.077
."
Token."
Feature activation+0.000

Top DFA by src position
MAX = 5.077

unique
Token unique
Feature activation-0.000
Top resid features:
flavors
Token flavors
Feature activation-0.000
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
difficult
Token difficult
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+3.076
Top resid features:
often
Tokenoften
Feature activation-0.001
Top resid features:
unpredictable
Token unpredictable
Feature activation+0.003
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.052
Top resid features:
process
Tokenprocess
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
Australian
Token Australian
Feature activation-0.001
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
lost
Token lost
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+0.001
Top resid features:
round
Token round
Feature activation-0.005
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.378
Top resid features:
only
Tokenonly
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
reset
Token reset
Feature activation-0.000
Top resid features:
Philip
Token Philip
Feature activation+0.001
Top resid features:
"
Token "
Feature activation+0.001
Top resid features:
She
Token She
Feature activation-0.002
Top resid features:
had
Token had
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+5.055
Top resid features:
numerous
Token numerous
Feature activation+0.003
Top resid features:
times
Token times
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
She
Token She
Feature activation+0.001
Top resid features:
told
Token told
Feature activation-0.009
Top resid features:
Des
Token Des
Feature activation-0.002
Top resid features:
pic
Tokenpic
Feature activation-0.000
Top resid features:
able
Tokenable
Feature activation-0.000
Top resid features:
Me
Token Me
Feature activation-0.000
Top resid features:
2
Token 2
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+5.077
Top resid features:
F
TokenF
Feature activation-0.001
Top resid features:
rozen
Tokenrozen
Feature activation-0.001
Top resid features:
seems
Token seems
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.060
Top resid features:
dis
Token dis
Feature activation-0.014
Top resid features:
interest
Tokeninterest
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
subscription
Token subscription
Feature activation-0.050
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.750
Top resid features:
and
Tokenand
Feature activation+0.001
Top resid features:
Penguin
Token Penguin
Feature activation-0.021
Top resid features:
Random
Token Random
Feature activation-0.017
Top resid features:
House
Token House
Feature activation-0.045
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.054
Top resid features:
inc
Token inc
Feature activation-0.020
Top resid features:
hed
Tokenhed
Feature activation+0.010
Top resid features:
closer
Token closer
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.814
Top resid features:
and
Tokenand
Feature activation-0.024
Top resid features:
then
Token then
Feature activation-0.012
Top resid features:
would
Token would
Feature activation+0.008
Top resid features:
sc
Token sc
Feature activation-0.003
Top resid features:
oot
Tokenoot
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Z
TokenZ
Feature activation+0.008
Top resid features:
oos
Tokenoos
Feature activation-0.017
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.603
Top resid features:
or
Tokenor
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.181
Top resid features:
in
Token in
Feature activation-0.016
Top resid features:
their
Token their
Feature activation-0.004
Top resid features:
original
Token original
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.097
Top resid features:
Ŀ
TokenĿ
Feature activation-0.034
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
man
Token man
Feature activation-0.019
Top resid features:
says
Token says
Feature activation-0.023
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.921
Top resid features:
and
Tokenand
Feature activation+0.038
Top resid features:
then
Token then
Feature activation+0.060
Top resid features:
just
Token just
Feature activation-0.014
Top resid features:
like
Token like
Feature activation+0.008
Top resid features:
that
Token that
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Z
TokenZ
Feature activation+0.001
Top resid features:
oos
Tokenoos
Feature activation-0.018
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+3.114
Top resid features:
or
Tokenor
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
their
Token their
Feature activation-0.000
Top resid features:
original
Token original
Feature activation-0.002
Top resid features:
Australian
Token Australian
Feature activation-0.002
Top resid features:
team
Token team
Feature activation+0.001
Top resid features:
lost
Token lost
Feature activation+0.009
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
round
Token round
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.691
Top resid features:
only
Tokenonly
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
reset
Token reset
Feature activation+0.009
Top resid features:
Philip
Token Philip
Feature activation+0.004
Top resid features:
"
Token "
Feature activation+0.009
Top resid features:
their
Token their
Feature activation-0.000
Top resid features:
hormones
Token hormones
Feature activation-0.001
Top resid features:
were
Token were
Feature activation+0.001
Top resid features:
just
Token just
Feature activation-0.001
Top resid features:
fine
Token fine
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.088
Top resid features:
a
Tokena
Feature activation+0.001
Top resid features:
good
Token good
Feature activation-0.000
Top resid features:
sign
Token sign
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
ov
Token ov
Feature activation-0.003
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
strike
Token strike
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.040
Top resid features:
itself
Token itself
Feature activation-0.005
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.493
Top resid features:
the
Tokenthe
Feature activation+0.008
Top resid features:
Thai
Token Thai
Feature activation-0.000
Top resid features:
box
Token box
Feature activation-0.002
Top resid features:
ers
Tokeners
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
Des
Token Des
Feature activation-0.001
Top resid features:
pic
Tokenpic
Feature activation-0.001
Top resid features:
able
Tokenable
Feature activation+0.000
Top resid features:
Me
Token Me
Feature activation-0.001
Top resid features:
2
Token 2
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.646
Top resid features:
F
TokenF
Feature activation-0.001
Top resid features:
rozen
Tokenrozen
Feature activation+0.002
Top resid features:
seems
Token seems
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
have
Token have
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Hur
TokenHur
Feature activation-0.002
Top resid features:
ricane
Tokenricane
Feature activation-0.006
Top resid features:
Sandy
Token Sandy
Feature activation-0.005
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+3.374
Top resid features:
and
Tokenand
Feature activation-0.000
Top resid features:
being
Token being
Feature activation+0.001
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
independent
Token independent
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.986
Top resid features:
Chinese
Token Chinese
Feature activation+0.002
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
style
Tokenstyle
Feature activation+0.003
Top resid features:
rail
Token rail
Feature activation+0.000
Top resid features:
systems
Token systems
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.489
Top resid features:
all
Tokenall
Feature activation-0.003
Top resid features:
free
Token free
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
distraction
Token distraction
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
best
Token best
Feature activation-0.001
Top resid features:
evidence
Token evidence
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
both
Token both
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.269
Top resid features:
evidence
Tokenevidence
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
could
Token could
Feature activation-0.000
Top resid features:
not
Token not
Feature activation-0.000
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.991
Top resid features:
and
Tokenand
Feature activation-0.001
Top resid features:
being
Token being
Feature activation+0.001
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
independent
Token independent
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+3.582
Top resid features:
has
Tokenhas
Feature activation+0.003
Top resid features:
given
Token given
Feature activation-0.001
Top resid features:
New
Token New
Feature activation-0.001
Top resid features:
York
Token York
Feature activation+0.002
Top resid features:
Mayor
Token Mayor
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.036
Top resid features:
dis
Token dis
Feature activation-0.011
Top resid features:
interest
Tokeninterest
Feature activation-0.006
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
subscription
Token subscription
Feature activation-0.028
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.546
Top resid features:
and
Tokenand
Feature activation+0.004
Top resid features:
Penguin
Token Penguin
Feature activation-0.012
Top resid features:
Random
Token Random
Feature activation-0.010
Top resid features:
House
Token House
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
property
Token property
Feature activation-0.006
Top resid features:
crime
Token crime
Feature activation-0.001
Top resid features:
rose
Token rose
Feature activation+0.000
Top resid features:
until
Token until
Feature activation-0.003
Top resid features:
2001
Token 2001
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+4.120
Top resid features:
but
Tokenbut
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
has
Token has
Feature activation-0.001
Top resid features:
fallen
Token fallen
Feature activation-0.000
Top resid features:
by
Token by
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.814
Top resid features:
and
Tokenand
Feature activation-0.002
Top resid features:
being
Token being
Feature activation+0.003
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
independent
Token independent
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+3.851
Top resid features:
has
Tokenhas
Feature activation-0.001
Top resid features:
given
Token given
Feature activation-0.002
Top resid features:
New
Token New
Feature activation-0.003
Top resid features:
York
Token York
Feature activation+0.005
Top resid features:
Mayor
Token Mayor
Feature activation+0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.08

Head 3: 0.50

Head 4: 0.10

Head 5: 0.10

Head 6: 0.02

Head 7: 0.05

Head 8: 0.03

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

10.26

"—9.63

—"9.36

)—8.77

.—7.61

—-7.58

,—6.18

——6.17

Advertisement5.85

————5.26

5.01

­4.98

––4.90

4.82

­4.61

AMY4.50

advertisement4.39

————————4.38

4.28

--4.27

Negative logits

`.-5.27

`,-4.91

..-4.85

..............-4.10

//-4.06

...-4.02

`-3.94

......-3.79

Nato-3.68

organise-3.65

Nasa-3.65

....-3.64

"]=>-3.63

--3.56

JUST-3.53

..."-3.52

!!-3.49

`-3.44

practise-3.44

flavours-3.42

INTERVAL 4.236 - 4.706
CONTAINS 0.001%

that
Token that
Feature activation+0.000
could
Token could
Feature activation+0.000
stand
Token stand
Feature activation+0.132
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
way
Token way
Feature activation+4.406
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
would
Token would
Feature activation+0.000
short
Token short
Feature activation+0.000
period
Token period
Feature activation+0.995
of
Token of
Feature activation+0.000
time
Token time
Feature activation+2.175
,
Token,
Feature activation+0.000
though
Token though
Feature activation+4.706
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.114
have
Token have
Feature activation+0.000
changed
Token changed
Feature activation+2.476
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+0.809
it
Token it
Feature activation+0.000
ple
Token ple
Feature activation+0.000
ases
Tokenases
Feature activation+4.268
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
if
Token if
Feature activation+0.000
big
Token big
Feature activation+2.181
publishers
Token publishers
Feature activation+1.023
play
Token play
Feature activation+0.418
caught
Token caught
Feature activation+0.000
Fa
Token Fa
Feature activation+0.000
Ze
TokenZe
Feature activation+0.094
off
Token off
Feature activation+0.000
guard
Token guard
Feature activation+4.502
and
Token and
Feature activation+0.000
Reneg
Token Reneg
Feature activation+0.000
ades
Tokenades
Feature activation+0.270
followed
Token followed
Feature activation+1.671
it
Token it
Feature activation+1.684
and
Tokenand
Feature activation+0.461
then
Token then
Feature activation+2.036
would
Token would
Feature activation+0.505
sc
Token sc
Feature activation+0.000
oot
Tokenoot
Feature activation+0.727
away
Token away
Feature activation+4.252
.
Token.
Feature activation+0.106
"
Token "
Feature activation+0.000
You
TokenYou
Feature activation+0.044
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.402

INTERVAL 3.765 - 4.236
CONTAINS 0.002%

spawned
Token spawned
Feature activation+0.533
of
Token of
Feature activation+0.000
unusually
Token unusually
Feature activation+0.000
warm
Token warm
Feature activation+0.000
ocean
Token ocean
Feature activation+0.733
waters
Token waters
Feature activation+4.095
?
Token?
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+1.512
,
Token,
Feature activation+0.000
Penguin
Token Penguin
Feature activation+0.000
Random
Token Random
Feature activation+0.000
House
Token House
Feature activation+1.002
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+3.965
,
Token,
Feature activation+0.372
is
Token is
Feature activation+0.241
big
Token big
Feature activation+1.277
enough
Token enough
Feature activation+3.013
to
Token to
Feature activation+0.000
or
Tokenor
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
original
Token original
Feature activation+0.000
form
Token form
Feature activation+4.204
,
Token,
Feature activation+0.000
men
Token men
Feature activation+0.286
ager
Tokenager
Feature activation+0.000
ies
Tokenies
Feature activation+3.178
âĢĶ
TokenâĢĶ
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
minor
Token minor
Feature activation+0.000
medical
Token medical
Feature activation+0.000
emergency
Token emergency
Feature activation+3.845
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+0.339
there
Token there
Feature activation+2.622
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.303
of
Token of
Feature activation+0.000
Broadway
Token Broadway
Feature activation+0.000
productions
Token productions
Feature activation+3.829
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 3.294 - 3.765
CONTAINS 0.010%

That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.000
typical
Token typical
Feature activation+0.469
me
Token me
Feature activation+2.239
though
Token though
Feature activation+3.459
."
Token."
Feature activation+0.658
Wayne
Token Wayne
Feature activation+0.435
is
Token is
Feature activation+0.000
planning
Token planning
Feature activation+0.128
a
Token a
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Its
Token Its
Feature activation+0.000
sh
Token sh
Feature activation+0.000
ambling
Tokenambling
Feature activation+0.000
quality
Token quality
Feature activation+3.350
is
Token is
Feature activation+0.000
true
Token true
Feature activation+1.380
to
Token to
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
said
Token said
Feature activation+0.650
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
laugh
Token laugh
Feature activation+3.488
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.209
When
TokenWhen
Feature activation+0.000
enough
Token enough
Feature activation+0.071
talent
Token talent
Feature activation+3.422
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
15
Token 15
Feature activation+0.608
years
Token years
Feature activation+3.586
and
Token and
Feature activation+0.279
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
youngster
Token youngster
Feature activation+1.108
who
Token who
Feature activation+0.279
this
Tokenthis
Feature activation+0.065
big
Token big
Feature activation+0.776
one
Token one
Feature activation+3.555
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.346
in
Token in
Feature activation+3.720
,
Token,
Feature activation+0.092
a
Token a
Feature activation+0.000
small
Token small
Feature activation+0.458
bedroom
Token bedroom
Feature activation+2.959
at
Token at
Feature activation+0.000

INTERVAL 2.824 - 3.294
CONTAINS 0.026%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
cause
Token cause
Feature activation+3.270
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Tim
TokenTim
Feature activation+0.000
ed
Tokened
Feature activation+0.000
use
Token use
Feature activation+0.000
chemical
Token chemical
Feature activation+0.124
weapons
Token weapons
Feature activation+3.007
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
battlefield
Token battlefield
Feature activation+3.043
.
Token.
Feature activation+0.000
Adolf
Token Adolf
Feature activation+0.000
Hitler
Token Hitler
Feature activation+0.779
ref
Token ref
Feature activation+0.000
rained
Tokenrained
Feature activation+0.962
the
Token the
Feature activation+0.000
increase
Token increase
Feature activation+0.745
translated
Token translated
Feature activation+0.000
into
Token into
Feature activation+0.000
wage
Token wage
Feature activation+0.000
growth
Token growth
Feature activation+2.953
at
Token at
Feature activation+0.000
middle
Token middle
Feature activation+0.000
and
Token and
Feature activation+0.000
lower
Token lower
Feature activation+0.000
incomes
Token incomes
Feature activation+3.104
engaging
Token engaging
Feature activation+0.000
in
Token in
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
exploration
Token exploration
Feature activation+1.384
,
Token,
Feature activation+0.000
however
Token however
Feature activation+3.118
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.759
the
Token the
Feature activation+0.000
vintage
Token vintage
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
street
Token street
Feature activation+0.000
-
Token-
Feature activation+0.000
legal
Tokenlegal
Feature activation+0.000
siblings
Token siblings
Feature activation+3.291
;
Token;
Feature activation+0.000
a
Token a
Feature activation+0.000
red
Token red
Feature activation+0.000
Mil
Token Mil
Feature activation+0.000
le
Tokenle
Feature activation+0.000

INTERVAL 2.353 - 2.824
CONTAINS 0.036%

Order
Token Order
Feature activation+1.476
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
hand
Token hand
Feature activation+2.764
,
Token,
Feature activation+0.366
is
Token is
Feature activation+0.646
far
Token far
Feature activation+0.463
bigger
Token bigger
Feature activation+2.342
than
Token than
Feature activation+0.000
The
TokenThe
Feature activation+0.000
second
Token second
Feature activation+0.465
star
Token star
Feature activation+2.668
:
Token:
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Commodore
Token Commodore
Feature activation+2.495
âĢĶ
TokenâĢĶ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
er
Tokener
Feature activation+2.162
when
Token when
Feature activation+0.000
engaging
Token engaging
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
online
Token online
Feature activation+0.000
behavior
Token behavior
Feature activation+2.415
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
understood
Token understood
Feature activation+0.730
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
recruited
Token recruited
Feature activation+0.328
by
Token by
Feature activation+0.000
several
Token several
Feature activation+0.000
universities
Token universities
Feature activation+2.822
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
chose
Token chose
Feature activation+0.000
Illinois
Token Illinois
Feature activation+1.632
State
Token State
Feature activation+1.728
of
Token of
Feature activation+0.000
many
Token many
Feature activation+0.000
cities
Token cities
Feature activation+2.044
in
Token in
Feature activation+0.000
Southern
Token Southern
Feature activation+0.000
England
Token England
Feature activation+2.593
âĢĶ
TokenâĢĶ
Feature activation+0.000
including
Tokenincluding
Feature activation+0.000
far
Token far
Feature activation+0.388
away
Token away
Feature activation+0.693
cities
Token cities
Feature activation+2.375

INTERVAL 1.883 - 2.353
CONTAINS 0.050%

Prot
TokenProt
Feature activation+0.000
ests
Tokenests
Feature activation+0.000
,
Token,
Feature activation+0.000
violence
Token violence
Feature activation+0.801
,
Token,
Feature activation+0.000
riots
Token riots
Feature activation+1.911
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
a
Token a
Feature activation+0.000
Nazi
Token Nazi
Feature activation+0.375
law
Tokenlaw
Feature activation+0.000
types
Token types
Feature activation+2.726
,
Token,
Feature activation+0.000
Nor
Token Nor
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ath
Tokenath
Feature activation+2.098
suggests
Token suggests
Feature activation+2.560
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
conditions
Token conditions
Feature activation+0.989
for
Token for
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
one
Token one
Feature activation+1.740
for
Token for
Feature activation+0.000
them
Token them
Feature activation+1.885
;
Token;
Feature activation+0.000
when
Token when
Feature activation+0.000
Type
Token Type
Feature activation+0.000
kit
Tokenkit
Feature activation+0.000
integrated
Token integrated
Feature activation+0.000
issues
Token issues
Feature activation+3.262
,
Token,
Feature activation+0.000
unlikely
Token unlikely
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
global
Token global
Feature activation+1.907
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
struggling
Token struggling
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
atmosphere
Token atmosphere
Feature activation+1.760
or
Token or
Feature activation+0.000
mood
Token mood
Feature activation+1.932
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+3.087
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
helps
Token helps
Feature activation+2.129

INTERVAL 1.412 - 1.883
CONTAINS 0.060%

years
Token years
Feature activation+0.179
before
Token before
Feature activation+0.000
Trump
Token Trump
Feature activation+0.494
first
Token first
Feature activation+0.000
declared
Token declared
Feature activation+0.000
bankruptcy
Token bankruptcy
Feature activation+1.512
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Att
TokenAtt
Feature activation+0.000
acking
Tokenacking
Feature activation+0.000
him
Token him
Feature activation+0.267
before
Token before
Feature activation+0.000
a
Token a
Feature activation+0.000
packed
Token packed
Feature activation+0.000
auditor
Token auditor
Feature activation+0.000
ium
Tokenium
Feature activation+1.659
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
bl
Token bl
Feature activation+0.000
azer
Tokenazer
Feature activation+0.000
collar
Token collar
Feature activation+0.000
written
Token written
Feature activation+0.000
in
Token in
Feature activation+0.000
computer
Token computer
Feature activation+0.202
code
Token code
Feature activation+2.469
from
Token from
Feature activation+0.000
1967
Token 1967
Feature activation+1.643
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
previously
Token previously
Feature activation+0.000
unknown
Token unknown
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
NPR
Token NPR
Feature activation+1.397
's
Token's
Feature activation+0.000
"
Token "
Feature activation+0.000
Science
TokenScience
Feature activation+0.000
Friday
Token Friday
Feature activation+0.475
"
Token"
Feature activation+1.447
host
Token host
Feature activation+0.000
I
Token I
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
Flat
Token Flat
Feature activation+0.000
ow
Tokenow
Feature activation+1.812
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
quarter
Token quarter
Feature activation+0.317
of
Token of
Feature activation+0.000
2010
Token 2010
Feature activation+1.472
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.941 - 1.412
CONTAINS 0.068%

,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+3.965
,
Token,
Feature activation+0.372
is
Token is
Feature activation+0.241
big
Token big
Feature activation+1.277
enough
Token enough
Feature activation+3.013
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+0.809
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
Liberal
Token Liberal
Feature activation+0.000
government
Token government
Feature activation+0.724
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
forward
Token forward
Feature activation+1.087
quickly
Token quickly
Feature activation+0.965
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
revamped
Token revamped
Feature activation+0.000
Trans
Token Trans
Feature activation+0.000
or
Token or
Feature activation+0.000
player
Token player
Feature activation+0.051
.
Token.
Feature activation+0.000
Crew
Token Crew
Feature activation+0.000
3
Token 3
Feature activation+0.000
(
Token (
Feature activation+1.366
Tap
TokenTap
Feature activation+1.758
any
Token any
Feature activation+0.201
number
Token number
Feature activation+1.878
of
Token of
Feature activation+0.659
creatures
Token creatures
Feature activation+1.919
t
Tokent
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
bother
Token bother
Feature activation+0.490
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.999
),
Token),
Feature activation+0.000
he
Token he
Feature activation+0.000
uses
Token uses
Feature activation+0.000
disturb
Token disturb
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
considered
Token considered
Feature activation+0.000
weak
Token weak
Feature activation+1.879
by
Token by
Feature activation+0.000
enthusiasts
Token enthusiasts
Feature activation+1.113
and
Token and
Feature activation+0.000
anat
Token anat
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
ma
Tokenma
Feature activation+0.279
by
Token by
Feature activation+0.000

INTERVAL 0.471 - 0.941
CONTAINS 0.099%

exposed
Token exposed
Feature activation+0.000
to
Token to
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
lead
Token lead
Feature activation+0.542
after
Token after
Feature activation+0.000
government
Token government
Feature activation+0.000
officials
Token officials
Feature activation+0.629
switched
Token switched
Feature activation+0.000
their
Token their
Feature activation+0.000
realistically
Token realistically
Feature activation+2.870
.
Token.
Feature activation+0.000
B
Token B
Feature activation+0.000
asing
Tokenasing
Feature activation+0.000
this
Token this
Feature activation+0.000
competition
Token competition
Feature activation+0.523
largely
Token largely
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.000
entirely
Token entirely
Feature activation+0.853
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
a
Token a
Feature activation+0.000
terrorist
Token terrorist
Feature activation+1.864
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.525
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.256
State
Token State
Feature activation+0.796
will
Token will
Feature activation+0.479
list
Token list
Feature activation+0.000
we
Token we
Feature activation+0.000
keep
Token keep
Feature activation+0.000
knocking
Token knocking
Feature activation+0.000
down
Token down
Feature activation+0.000
these
Token these
Feature activation+0.000
barriers
Token barriers
Feature activation+0.873
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
China
Token China
Feature activation+1.727
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.170
a
Token a
Feature activation+0.000
half
Token half
Feature activation+0.656
war
Token war
Feature activation+0.844
in
Token in
Feature activation+0.000
Korea
Token Korea
Feature activation+1.955
or
Token or
Feature activation+0.960
the
Token the
Feature activation+0.354
Middle
Token Middle
Feature activation+0.135

INTERVAL 0.000 - 0.471
CONTAINS 99.649%

might
Token might
Feature activation+0.000
inquire
Token inquire
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
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
proximity
Token proximity
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
secure
Token secure
Feature activation+0.000
channel
Token channel
Feature activation+0.000
for
Token for
Feature activation+0.000
users
Token users
Feature activation+0.000
to
Token to
Feature activation+0.000
communicate
Token communicate
Feature activation+0.000
even
Token even
Feature activation+0.000
without
Token without
Feature activation+0.000
installing
Token installing
Feature activation+0.000
Tor
Token Tor
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
.
Token.
Feature activation+0.000
official
Token official
Feature activation+0.000
with
Token with
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
work
Token work
Feature activation+0.000
itself
Token itself
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
largely
Token largely
Feature activation+0.000
undertaken
Token undertaken
Feature activation+0.000
by
Token by
Feature activation+0.000
angry
Token angry
Feature activation+0.000
and
Token and
Feature activation+0.000
confronted
Token confronted
Feature activation+0.000
her
Token her
Feature activation+0.000
for
Token for
Feature activation+0.000
communicating
Token communicating
Feature activation+0.000
with
Token with
Feature activation+0.000
friends
Token friends
Feature activation+0.000
on
Token on
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H10.3: (feature 1739)

TOP ACTIVATIONS
MAX = 8.683

few
Token few
Feature activation+0.000
blue
Token blue
Feature activation+0.000
ones
Token ones
Feature activation+0.000
every
Token every
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+8.683
then
Token then
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
around
Token around
Feature activation+0.000
conservatives
Token conservatives
Feature activation+0.000
say
Token say
Feature activation+0.000
their
Token their
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+4.481
replace
Token replace
Feature activation+0.000
later
Token later
Feature activation+0.000
plan
Token plan
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atter
Tokenatter
Feature activation+0.000
:
Token:
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+3.906
Later
Token Later
Feature activation+0.000
-
Token -
Feature activation+0.000
B
Token B
Feature activation+0.000
ibliography
Tokenibliography
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
sense
Token sense
Feature activation+0.000
of
Token of
Feature activation+0.000
self
Token self
Feature activation+0.000
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
and
Token and
Feature activation+2.828
now
Token now
Feature activation+0.000
?
Token?
Feature activation+0.000
(
Token (
Feature activation+0.000
Dam
TokenDam
Feature activation+0.000
asio
Tokenasio
Feature activation+0.000
organisation
Token organisation
Feature activation+0.000
's
Token's
Feature activation+0.000
before
Token before
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+1.153
-
Token-
Feature activation+1.867
after
Tokenafter
Feature activation+0.000
school
Token school
Feature activation+0.000
care
Token care
Feature activation+0.000
program
Token program
Feature activation+0.000
.
Token.
Feature activation+0.000
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
neither
Token neither
Feature activation+0.000
here
Token here
Feature activation+0.000
nor
Token nor
Feature activation+1.181
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
the
Token the
Feature activation+0.000
organisation
Token organisation
Feature activation+0.000
's
Token's
Feature activation+0.000
before
Token before
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+1.153
-
Token-
Feature activation+1.867
after
Tokenafter
Feature activation+0.000
school
Token school
Feature activation+0.000
care
Token care
Feature activation+0.000
program
Token program
Feature activation+0.000
structure
Token structure
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
this
Token this
Feature activation+0.000
day
Token day
Feature activation+0.000
and
Token and
Feature activation+1.037
age
Token age
Feature activation+0.000
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
,
Token,
Feature activation+0.000
young
Token young
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
In
TokenIn
Feature activation+0.000
this
Token this
Feature activation+0.000
day
Token day
Feature activation+0.000
and
Token and
Feature activation+0.631
age
Token age
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
by
Token by
Feature activation+0.000
its
Token its
Feature activation+0.000
current
Token current
Feature activation+0.000
and
Token and
Feature activation+0.410
past
Token past
Feature activation+0.000
owners
Token owners
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
experience
Token experience
Feature activation+0.000
once
Token once
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Tokena
Feature activation+0.354
lifetime
Token lifetime
Feature activation+0.000
things
Token things
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
fraction
Token fraction
Feature activation+0.000
will
Token will
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
again
Token again
Feature activation+0.000
and
Token and
Feature activation+0.336
again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
Trust
Token Trust
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
end
Token end
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.262
end
Tokenend
Feature activation+0.000
.
Token.
Feature activation+0.000
Last
Token Last
Feature activation+0.000
time
Token time
Feature activation+0.000
these
Token these
Feature activation+0.000
for
Token for
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+0.000
problems
Token problems
Feature activation+0.000
here
Token here
Feature activation+0.000
and
Token and
Feature activation+0.255
abroad
Token abroad
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jewish
TokenJewish
Feature activation+0.000
general
Token general
Feature activation+0.000
settled
Token settled
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
with
Token with
Feature activation+0.000
C
Token C
Feature activation+0.039
MD
TokenMD
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
,
Token,
Feature activation+0.000
paying
Token paying
Feature activation+0.000
who
Token who
Feature activation+0.000
oppose
Token oppose
Feature activation+0.000
their
Token their
Feature activation+0.000
rule
Token rule
Feature activation+0.000
here
Token here
Feature activation+0.000
and
Token and
Feature activation+0.011
abroad
Token abroad
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
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
<|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
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

Top DFA by src position
MAX = 12.348

few
Token few
Feature activation-0.013
Top resid features:
blue
Token blue
Feature activation-0.059
Top resid features:
ones
Token ones
Feature activation-0.015
Top resid features:
every
Token every
Feature activation+0.409
Top resid features:
now
Token now
Feature activation+0.067
Top resid features:
and
Token and
Feature activation+12.348
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
conservatives
Token conservatives
Feature activation-0.085
Top resid features:
say
Token say
Feature activation+0.089
Top resid features:
their
Token their
Feature activation-0.034
Top resid features:
repeal
Token repeal
Feature activation-0.200
Top resid features:
now
Token now
Feature activation+0.168
Top resid features:
and
Token and
Feature activation+8.658
Top resid features:
replace
Token replace
Feature activation+0.000
Top resid features:
later
Token later
Feature activation+0.000
Top resid features:
plan
Token plan
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ant
Token Ant
Feature activation-0.142
Top resid features:
im
Tokenim
Feature activation-0.009
Top resid features:
atter
Tokenatter
Feature activation+0.033
Top resid features:
:
Token:
Feature activation+0.147
Top resid features:
Now
Token Now
Feature activation+0.850
Top resid features:
and
Token and
Feature activation+7.442
Top resid features:
Later
Token Later
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
ibliography
Tokenibliography
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
sense
Token sense
Feature activation-0.105
Top resid features:
of
Token of
Feature activation-0.094
Top resid features:
self
Token self
Feature activation+0.119
Top resid features:
about
Token about
Feature activation-0.335
Top resid features:
here
Token here
Feature activation+2.476
Top resid features:
and
Token and
Feature activation+6.292
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Dam
TokenDam
Feature activation+0.000
Top resid features:
asio
Tokenasio
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.014
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
organisation
Token organisation
Feature activation+0.085
Top resid features:
's
Token's
Feature activation-0.032
Top resid features:
before
Token before
Feature activation+1.875
Top resid features:
-
Token-
Feature activation+1.952
Top resid features:
and
Tokenand
Feature activation+1.302
Top resid features:
-
Token-
Feature activation+0.280
Top resid features:
after
Tokenafter
Feature activation+0.000
Top resid features:
school
Token school
Feature activation+0.000
Top resid features:
care
Token care
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.594
Top resid features:
that
Token that
Feature activation+0.171
Top resid features:
's
Token's
Feature activation-0.120
Top resid features:
neither
Token neither
Feature activation-0.568
Top resid features:
here
Token here
Feature activation+1.660
Top resid features:
nor
Token nor
Feature activation+3.145
Top resid features:
there
Token there
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:
There
TokenThere
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
organisation
Token organisation
Feature activation+0.211
Top resid features:
's
Token's
Feature activation+0.010
Top resid features:
before
Token before
Feature activation+1.023
Top resid features:
-
Token-
Feature activation+3.815
Top resid features:
and
Tokenand
Feature activation+0.055
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
after
Tokenafter
Feature activation+0.000
Top resid features:
school
Token school
Feature activation+0.000
Top resid features:
care
Token care
Feature activation+0.000
Top resid features:
structure
Token structure
Feature activation-0.022
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
In
Token In
Feature activation-0.020
Top resid features:
this
Token this
Feature activation-0.076
Top resid features:
day
Token day
Feature activation-1.452
Top resid features:
and
Token and
Feature activation+6.009
Top resid features:
age
Token age
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Australia
Token Australia
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
young
Token young
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
"
Token"
Feature activation-0.000
Top resid features:
In
TokenIn
Feature activation-0.034
Top resid features:
this
Token this
Feature activation-0.030
Top resid features:
day
Token day
Feature activation-1.393
Top resid features:
and
Token and
Feature activation+5.666
Top resid features:
age
Token age
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:
's
Token's
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
company
Token company
Feature activation-0.046
Top resid features:
by
Token by
Feature activation+0.347
Top resid features:
its
Token its
Feature activation+0.495
Top resid features:
current
Token current
Feature activation-0.155
Top resid features:
and
Token and
Feature activation+3.488
Top resid features:
past
Token past
Feature activation+0.000
Top resid features:
owners
Token owners
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
reasons
Token reasons
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
experience
Token experience
Feature activation-0.031
Top resid features:
once
Token once
Feature activation+0.025
Top resid features:
-
Token-
Feature activation+0.891
Top resid features:
in
Tokenin
Feature activation+0.220
Top resid features:
-
Token-
Feature activation+3.024
Top resid features:
a
Tokena
Feature activation+0.165
Top resid features:
lifetime
Token lifetime
Feature activation+0.000
Top resid features:
things
Token things
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
will
Token will
Feature activation-0.060
Top resid features:
want
Token want
Feature activation-0.115
Top resid features:
to
Token to
Feature activation-0.098
Top resid features:
see
Token see
Feature activation-0.192
Top resid features:
again
Token again
Feature activation+1.259
Top resid features:
and
Token and
Feature activation+4.275
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Trust
Token Trust
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
back
Token back
Feature activation-0.094
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
should
Token should
Feature activation+0.003
Top resid features:
be
Token be
Feature activation-0.008
Top resid features:
end
Token end
Feature activation+2.826
Top resid features:
-
Token-
Feature activation+1.227
Top resid features:
to
Tokento
Feature activation+0.775
Top resid features:
-
Token-
Feature activation-0.075
Top resid features:
end
Tokenend
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
America
Token America
Feature activation-0.354
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
problems
Token problems
Feature activation-0.121
Top resid features:
here
Token here
Feature activation+2.116
Top resid features:
and
Token and
Feature activation+3.309
Top resid features:
abroad
Token abroad
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:
Jewish
TokenJewish
Feature activation+0.000
Top resid features:
sued
Token sued
Feature activation+0.007
Top resid features:
by
Token by
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
Center
Token Center
Feature activation-0.089
Top resid features:
for
Token for
Feature activation+0.041
Top resid features:
Media
Token Media
Feature activation+2.180
Top resid features:
and
Token and
Feature activation+0.067
Top resid features:
Democracy
Token Democracy
Feature activation+0.026
Top resid features:
for
Token for
Feature activation+0.027
Top resid features:
failure
Token failure
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.025
Top resid features:
who
Token who
Feature activation-0.132
Top resid features:
oppose
Token oppose
Feature activation-0.654
Top resid features:
their
Token their
Feature activation+0.003
Top resid features:
rule
Token rule
Feature activation+0.033
Top resid features:
here
Token here
Feature activation+1.205
Top resid features:
and
Token and
Feature activation+2.341
Top resid features:
abroad
Token abroad
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.027
Top resid features:
Saturday
Token Saturday
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.067
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
The
TokenThe
Feature activation+0.215
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation-0.996
Top resid features:
ar
Tokenar
Feature activation-0.094
Top resid features:
said
Token said
Feature activation+0.010
Top resid features:
Saturday
Token Saturday
Feature activation-0.072
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.116
Top resid features:
Ċ
TokenĊ
Feature activation+0.077
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation-0.309
Top resid features:
ar
Tokenar
Feature activation-0.058
Top resid features:
said
Token said
Feature activation-0.021
Top resid features:
Saturday
Token Saturday
Feature activation-0.292
Top resid features:
.
Token.
Feature activation-0.071
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
ar
Tokenar
Feature activation-0.007
Top resid features:
said
Token said
Feature activation-0.005
Top resid features:
Saturday
Token Saturday
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.04

Head 3: 0.50

Head 4: 0.05

Head 5: 0.04

Head 6: 0.03

Head 7: 0.05

Head 8: 0.03

Head 9: 0.05

Head 10: 0.04

Head 11: 0.10

Positive logits

subsequ2.54

BuyableInstoreAndOnline2.45

issance2.42

ailability2.42

fml2.32

lived2.24

]"2.21

akespe2.21

=]2.21

uctions2.20

Klux2.17

etheus2.14

ALTH2.11

imum2.11

MQ2.10

dated2.08

endra2.05

<-2.01

=~=~2.00

Jeanne2.00

Negative logits

-3.54

[…]-2.85

2018-2.79

2018-2.55

)—-2.46

-2.42

2017-2.42

2016-2.37

2017-2.27

borders-2.23

)),-2.21

2016-2.20

-2.19

.—-2.10

"},-2.08

''-2.08

foreigners-2.02

-1.99

,''-1.97

Tas-1.96

INTERVAL 7.815 - 8.683
CONTAINS 0.000%

few
Token few
Feature activation+0.000
blue
Token blue
Feature activation+0.000
ones
Token ones
Feature activation+0.000
every
Token every
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+8.683
then
Token then
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
around
Token around
Feature activation+0.000

INTERVAL 6.947 - 7.815
CONTAINS 0.000%

INTERVAL 6.078 - 6.947
CONTAINS 0.000%

INTERVAL 5.210 - 6.078
CONTAINS 0.000%

INTERVAL 4.342 - 5.210
CONTAINS 0.000%

conservatives
Token conservatives
Feature activation+0.000
say
Token say
Feature activation+0.000
their
Token their
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+4.481
replace
Token replace
Feature activation+0.000
later
Token later
Feature activation+0.000
plan
Token plan
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 3.473 - 4.342
CONTAINS 0.000%

Ant
Token Ant
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atter
Tokenatter
Feature activation+0.000
:
Token:
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+3.906
Later
Token Later
Feature activation+0.000
-
Token -
Feature activation+0.000
B
Token B
Feature activation+0.000
ibliography
Tokenibliography
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000

INTERVAL 2.605 - 3.473
CONTAINS 0.000%

sense
Token sense
Feature activation+0.000
of
Token of
Feature activation+0.000
self
Token self
Feature activation+0.000
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
and
Token and
Feature activation+2.828
now
Token now
Feature activation+0.000
?
Token?
Feature activation+0.000
(
Token (
Feature activation+0.000
Dam
TokenDam
Feature activation+0.000
asio
Tokenasio
Feature activation+0.000

INTERVAL 1.737 - 2.605
CONTAINS 0.000%

organisation
Token organisation
Feature activation+0.000
's
Token's
Feature activation+0.000
before
Token before
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+1.153
-
Token-
Feature activation+1.867
after
Tokenafter
Feature activation+0.000
school
Token school
Feature activation+0.000
care
Token care
Feature activation+0.000
program
Token program
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.868 - 1.737
CONTAINS 0.000%

structure
Token structure
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
this
Token this
Feature activation+0.000
day
Token day
Feature activation+0.000
and
Token and
Feature activation+1.037
age
Token age
Feature activation+0.000
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
,
Token,
Feature activation+0.000
young
Token young
Feature activation+0.000
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
neither
Token neither
Feature activation+0.000
here
Token here
Feature activation+0.000
nor
Token nor
Feature activation+1.181
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
the
Token the
Feature activation+0.000
organisation
Token organisation
Feature activation+0.000
's
Token's
Feature activation+0.000
before
Token before
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+1.153
-
Token-
Feature activation+1.867
after
Tokenafter
Feature activation+0.000
school
Token school
Feature activation+0.000
care
Token care
Feature activation+0.000
program
Token program
Feature activation+0.000

INTERVAL 0.000 - 0.868
CONTAINS 99.999%

future
Token future
Feature activation+0.000
when
Token when
Feature activation+0.000
Kinect
Token Kinect
Feature activation+0.000
cameras
Token cameras
Feature activation+0.000
are
Token are
Feature activation+0.000
built
Token built
Feature activation+0.000
directly
Token directly
Feature activation+0.000
into
Token into
Feature activation+0.000
laptops
Token laptops
Feature activation+0.000
and
Token and
Feature activation+0.000
tablets
Token tablets
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
NHS
Token NHS
Feature activation+0.000
!
Token!
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
why
Token why
Feature activation+0.000
also
Token also
Feature activation+0.000
left
Token left
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
mysterious
Token mysterious
Feature activation+0.000
element
Token element
Feature activation+0.000
of
Token of
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Looking
TokenLooking
Feature activation+0.000
for
Token for
Feature activation+0.000
C
Token C
Feature activation+0.000
++
Token++
Feature activation+0.000
17
Token17
Feature activation+0.000
-
Token -
Feature activation+0.000
Ur
Token Ur
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
Pro
Token Pro
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
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
clear
Token clear
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
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 H10.3: (feature 16060)

TOP ACTIVATIONS
MAX = 4.767

s
Tokens
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
establishment
Tokenestablishment
Feature activation+0.000
sounding
Token sounding
Feature activation+0.000
rhetoric
Token rhetoric
Feature activation+4.767
scares
Token scares
Feature activation+0.138
them
Token them
Feature activation+2.588
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.300
talk
Token talk
Feature activation+0.000
the
Token the
Feature activation+0.000
bidding
Token bidding
Feature activation+1.646
of
Token of
Feature activation+0.000
powerful
Token powerful
Feature activation+0.004
dark
Token dark
Feature activation+0.000
forces
Token forces
Feature activation+4.726
running
Token running
Feature activation+0.155
the
Token the
Feature activation+0.001
country
Token country
Feature activation+3.811
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+2.801
-
Token -
Feature activation+0.000
just
Token just
Feature activation+0.000
think
Token think
Feature activation+0.372
of
Token of
Feature activation+0.000
Almost
Token Almost
Feature activation+0.139
Human
Token Human
Feature activation+4.583
creator
Token creator
Feature activation+0.000
Joel
Token Joel
Feature activation+0.000
Wy
Token Wy
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.598
it
Token it
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
is
Token is
Feature activation+1.417
incorrect
Token incorrect
Feature activation+4.460
,"
Token,"
Feature activation+0.000
St
Token St
Feature activation+0.000
rief
Tokenrief
Feature activation+0.000
said
Token said
Feature activation+0.188
.
Token.
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
previous
Token previous
Feature activation+0.000
effort
Token effort
Feature activation+4.339
Fr
Token Fr
Feature activation+0.000
inge
Tokeninge
Feature activation+4.446
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.241
But
TokenBut
Feature activation+0.000
that
Token that
Feature activation+0.000
successful
Token successful
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
infamous
Token infamous
Feature activation+0.970
-
Token -
Feature activation+0.000
lobbyists
Token lobbyists
Feature activation+4.403
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
lobbyist
Token lobbyist
Feature activation+0.000
Rick
Token Rick
Feature activation+0.000
Davis
Token Davis
Feature activation+1.340
Joel
Token Joel
Feature activation+0.000
Wy
Token Wy
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
previous
Token previous
Feature activation+0.000
effort
Token effort
Feature activation+4.339
Fr
Token Fr
Feature activation+0.000
inge
Tokeninge
Feature activation+4.446
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.241
govern
Token govern
Feature activation+1.701
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+2.847
handed
Token handed
Feature activation+1.092
them
Token them
Feature activation+4.237
,
Token,
Feature activation+0.000
doing
Token doing
Feature activation+0.103
the
Token the
Feature activation+0.000
bidding
Token bidding
Feature activation+1.646
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.738
Lead
TokenLead
Feature activation+0.000
ers
Tokeners
Feature activation+3.063
like
Token like
Feature activation+0.000
Obama
Token Obama
Feature activation+4.231
govern
Token govern
Feature activation+1.701
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+2.847
handed
Token handed
Feature activation+1.092
no
Token no
Feature activation+0.000
matter
Token matter
Feature activation+0.239
what
Token what
Feature activation+2.765
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
situation
Token situation
Feature activation+4.231
is
Token is
Feature activation+0.010
saying
Token saying
Feature activation+0.818
that
Token that
Feature activation+1.532
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.003
Almost
Token Almost
Feature activation+0.139
Human
Token Human
Feature activation+4.583
creator
Token creator
Feature activation+0.000
Joel
Token Joel
Feature activation+0.000
Wy
Token Wy
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
previous
Token previous
Feature activation+0.000
effort
Token effort
Feature activation+4.339
Fr
Token Fr
Feature activation+0.000
inge
Tokeninge
Feature activation+4.446
Art
Token Art
Feature activation+0.000
es
Tokenes
Feature activation+0.000
ia
Tokenia
Feature activation+1.571
,
Token,
Feature activation+0.397
New
Token New
Feature activation+0.290
Mexico
Token Mexico
Feature activation+4.144
,
Token,
Feature activation+0.509
training
Token training
Feature activation+0.508
supervisor
Token supervisor
Feature activation+0.000
Brian
Token Brian
Feature activation+0.000
Y
Token Y
Feature activation+0.000
's
Token's
Feature activation+0.093
book
Token book
Feature activation+2.147
-
Token -
Feature activation+0.197
what
Token what
Feature activation+1.117
is
Token is
Feature activation+2.439
it
Token it
Feature activation+4.125
?
Token?
Feature activation+1.504
-
Token -
Feature activation+1.875
"
Token "
Feature activation+0.552
Cons
TokenCons
Feature activation+0.000
cience
Tokencience
Feature activation+0.690
'll
Token'll
Feature activation+0.000
deliver
Token deliver
Feature activation+2.494
that
Token that
Feature activation+1.126
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
some
Token some
Feature activation+4.069
;
Token;
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
beautifully
Token beautifully
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+3.914
that
Token that
Feature activation+0.000
few
Token few
Feature activation+0.214
believe
Token believe
Feature activation+0.306
Russia
Token Russia
Feature activation+2.608
would
Token would
Feature activation+0.132
country
Token country
Feature activation+0.000
back
Token back
Feature activation+2.740
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Atlantic
Token Atlantic
Feature activation+2.298
fold
Token fold
Feature activation+3.903
It
Token It
Feature activation+0.000
st
Token st
Feature activation+0.000
ings
Tokenings
Feature activation+2.083
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
It
TokenIt
Feature activation+0.000
makes
Token makes
Feature activation+0.000
it
Token it
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
difficult
Token difficult
Feature activation+3.869
when
Token when
Feature activation+0.000
other
Token other
Feature activation+0.000
women
Token women
Feature activation+1.602
join
Token join
Feature activation+0.129
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
getting
Token getting
Feature activation+0.000
along
Token along
Feature activation+0.791
with
Token with
Feature activation+0.000
Vladimir
Token Vladimir
Feature activation+0.069
Putin
Token Putin
Feature activation+3.831
-
Token -
Feature activation+0.000
anat
Token anat
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
ma
Tokenma
Feature activation+1.940
in
Token in
Feature activation+0.000
powerful
Token powerful
Feature activation+0.004
dark
Token dark
Feature activation+0.000
forces
Token forces
Feature activation+4.726
running
Token running
Feature activation+0.155
the
Token the
Feature activation+0.001
country
Token country
Feature activation+3.811
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+2.801
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
s
Tokens
Feature activation+0.000
misinterpret
Token misinterpret
Feature activation+1.857
an
Token an
Feature activation+0.000
airliner
Token airliner
Feature activation+1.318
at
Token at
Feature activation+0.000
such
Token such
Feature activation+0.000
height
Token height
Feature activation+3.726
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
threat
Token threat
Feature activation+1.597
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 5.446

s
Tokens
Feature activation-0.000
Top resid features:
deb
Token deb
Feature activation-0.000
Top resid features:
au
Tokenau
Feature activation+0.000
Top resid features:
ched
Tokenched
Feature activation-0.000
Top resid features:
system
Token system
Feature activation-0.002
Top resid features:
-
Token -
Feature activation+5.272
Top resid features:
fantasy
Token fantasy
Feature activation-0.008
Top resid features:
democracy
Token democracy
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
deb
Token deb
Feature activation-0.000
Top resid features:
au
Tokenau
Feature activation+0.000
Top resid features:
ched
Tokenched
Feature activation-0.000
Top resid features:
system
Token system
Feature activation-0.002
Top resid features:
-
Token -
Feature activation+5.249
Top resid features:
fantasy
Token fantasy
Feature activation-0.011
Top resid features:
democracy
Token democracy
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
sci
Token sci
Feature activation+0.009
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
fi
Tokenfi
Feature activation+0.001
Top resid features:
series
Token series
Feature activation-0.012
Top resid features:
before
Token before
Feature activation-0.022
Top resid features:
-
Token -
Feature activation+4.538
Top resid features:
just
Token just
Feature activation-0.001
Top resid features:
think
Token think
Feature activation+0.045
Top resid features:
of
Token of
Feature activation+0.167
Top resid features:
Almost
Token Almost
Feature activation+0.005
Top resid features:
Human
Token Human
Feature activation-0.008
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
place
Token place
Feature activation+0.001
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
assumption
Token assumption
Feature activation-0.008
Top resid features:
-
Token -
Feature activation+5.446
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
Roger
Token Roger
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
going
Token going
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
sci
Token sci
Feature activation+0.012
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
fi
Tokenfi
Feature activation+0.004
Top resid features:
series
Token series
Feature activation+0.003
Top resid features:
before
Token before
Feature activation-0.005
Top resid features:
-
Token -
Feature activation+4.382
Top resid features:
just
Token just
Feature activation+0.001
Top resid features:
think
Token think
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
Almost
Token Almost
Feature activation+0.001
Top resid features:
Human
Token Human
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Washington
Token Washington
Feature activation+0.006
Top resid features:
's
Token's
Feature activation+0.005
Top resid features:
most
Token most
Feature activation+0.013
Top resid features:
successful
Token successful
Feature activation+0.035
Top resid features:
-
Token -
Feature activation+4.956
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
infamous
Token infamous
Feature activation+0.009
Top resid features:
-
Token -
Feature activation+0.090
Top resid features:
lobbyists
Token lobbyists
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
sci
Token sci
Feature activation+0.009
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
fi
Tokenfi
Feature activation+0.000
Top resid features:
series
Token series
Feature activation+0.001
Top resid features:
before
Token before
Feature activation+0.001
Top resid features:
-
Token -
Feature activation+4.362
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
Almost
Token Almost
Feature activation-0.208
Top resid features:
Human
Token Human
Feature activation+0.068
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
deb
Token deb
Feature activation-0.001
Top resid features:
au
Tokenau
Feature activation+0.001
Top resid features:
ched
Tokenched
Feature activation+0.000
Top resid features:
system
Token system
Feature activation-0.006
Top resid features:
-
Token -
Feature activation+4.945
Top resid features:
fantasy
Token fantasy
Feature activation-0.027
Top resid features:
democracy
Token democracy
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
not
Token not
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
deb
Token deb
Feature activation-0.000
Top resid features:
au
Tokenau
Feature activation+0.000
Top resid features:
ched
Tokenched
Feature activation-0.001
Top resid features:
system
Token system
Feature activation-0.005
Top resid features:
-
Token -
Feature activation+4.218
Top resid features:
fantasy
Token fantasy
Feature activation-0.014
Top resid features:
democracy
Token democracy
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
assumption
Token assumption
Feature activation-0.001
Top resid features:
-
Token -
Feature activation+4.887
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
Roger
Token Roger
Feature activation+0.024
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
sci
Token sci
Feature activation+0.004
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
fi
Tokenfi
Feature activation+0.000
Top resid features:
series
Token series
Feature activation-0.003
Top resid features:
before
Token before
Feature activation-0.006
Top resid features:
-
Token -
Feature activation+4.528
Top resid features:
just
Token just
Feature activation+0.002
Top resid features:
think
Token think
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
Almost
Token Almost
Feature activation+0.004
Top resid features:
Human
Token Human
Feature activation-0.000
Top resid features:
deadly
Token deadly
Feature activation+0.001
Top resid features:
force
Token force
Feature activation+0.001
Top resid features:
only
Token only
Feature activation+0.002
Top resid features:
when
Token when
Feature activation-0.000
Top resid features:
necessary
Token necessary
Feature activation-0.000
Top resid features:
-
Token -
Feature activation+4.875
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
when
Token when
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Barry
Token Barry
Feature activation+0.013
Top resid features:
Gold
Token Gold
Feature activation-0.002
Top resid features:
water
Tokenwater
Feature activation+0.009
Top resid features:
's
Token's
Feature activation+0.019
Top resid features:
book
Token book
Feature activation+0.016
Top resid features:
-
Token -
Feature activation+4.500
Top resid features:
what
Token what
Feature activation+0.058
Top resid features:
is
Token is
Feature activation+0.130
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
inspired
Token inspired
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+0.035
Top resid features:
instead
Token instead
Feature activation-0.013
Top resid features:
-
Token -
Feature activation+2.287
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
end
Token end
Feature activation-0.002
Top resid features:
result
Token result
Feature activation+0.000
Top resid features:
fell
Token fell
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.093
Top resid features:
long
Token long
Feature activation+0.012
Top resid features:
worried
Token worried
Feature activation+0.006
Top resid features:
by
Token by
Feature activation+0.003
Top resid features:
Moscow
Token Moscow
Feature activation-0.002
Top resid features:
-
Token -
Feature activation+4.283
Top resid features:
had
Token had
Feature activation+0.002
Top resid features:
assumed
Token assumed
Feature activation+0.003
Top resid features:
Europe
Token Europe
Feature activation+0.022
Top resid features:
itself
Token itself
Feature activation+0.002
Top resid features:
faced
Token faced
Feature activation+0.003
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
came
Token came
Feature activation+0.000
Top resid features:
back
Token back
Feature activation-0.001
Top resid features:
."
Token."
Feature activation-0.006
Top resid features:
Again
Token Again
Feature activation-0.005
Top resid features:
-
Token -
Feature activation+4.601
Top resid features:
o
Token o
Feature activation+0.001
Top resid features:
uch
Tokenuch
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.063
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
ca
Token ca
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
m
Tokenm
Feature activation-0.003
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
their
Token their
Feature activation-0.000
Top resid features:
side
Token side
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+4.283
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
then
Token then
Feature activation-0.003
Top resid features:
they
Token they
Feature activation+0.004
Top resid features:
won
Token won
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
deb
Token deb
Feature activation-0.001
Top resid features:
au
Tokenau
Feature activation+0.000
Top resid features:
ched
Tokenched
Feature activation+0.000
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+3.843
Top resid features:
fantasy
Token fantasy
Feature activation-0.002
Top resid features:
democracy
Token democracy
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
deb
Token deb
Feature activation-0.001
Top resid features:
au
Tokenau
Feature activation+0.000
Top resid features:
ched
Tokenched
Feature activation+0.001
Top resid features:
system
Token system
Feature activation-0.002
Top resid features:
-
Token -
Feature activation+4.208
Top resid features:
fantasy
Token fantasy
Feature activation-0.008
Top resid features:
democracy
Token democracy
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
about
Token about
Feature activation-0.000
Top resid features:
33
Token 33
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
000
Token000
Feature activation-0.000
Top resid features:
feet
Token feet
Feature activation-0.003
Top resid features:
-
Token -
Feature activation+4.545
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
altitude
Token altitude
Feature activation-0.013
Top resid features:
considered
Token considered
Feature activation-0.004
Top resid features:
by
Token by
Feature activation+0.001
Top resid features:
those
Token those
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.08

Head 3: 0.50

Head 4: 0.08

Head 5: 0.08

Head 6: 0.01

Head 7: 0.06

Head 8: 0.06

Head 9: 0.05

Head 10: 0.01

Head 11: 0.02

Positive logits

-9.63

5.85

``5.16

...4.55

realise4.54

''4.52

:-4.45

,...4.38

realised4.32

recognised4.26

recognise4.24

"...4.23

..."4.14

isations4.11

''.4.08

.....4.00

....3.96

 3.96

----------------------------------------------------------------3.95

"-3.95

Negative logits

-7.34

­-7.10

-6.43

-6.19

-6.16

­-6.11

…"-5.92

.–-5.77

-5.63

……………………-5.62

-5.60

—--5.38

advertisement-5.16

––-5.16

————-5.12

…………-5.07

ADVERTISEMENT-5.00

"…-4.97

…."-4.82

————————-4.70

INTERVAL 4.290 - 4.767
CONTAINS 0.001%

-
Token -
Feature activation+0.000
just
Token just
Feature activation+0.000
think
Token think
Feature activation+0.372
of
Token of
Feature activation+0.000
Almost
Token Almost
Feature activation+0.139
Human
Token Human
Feature activation+4.583
creator
Token creator
Feature activation+0.000
Joel
Token Joel
Feature activation+0.000
Wy
Token Wy
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
bidding
Token bidding
Feature activation+1.646
of
Token of
Feature activation+0.000
powerful
Token powerful
Feature activation+0.004
dark
Token dark
Feature activation+0.000
forces
Token forces
Feature activation+4.726
running
Token running
Feature activation+0.155
the
Token the
Feature activation+0.001
country
Token country
Feature activation+3.811
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+2.801
Joel
Token Joel
Feature activation+0.000
Wy
Token Wy
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
previous
Token previous
Feature activation+0.000
effort
Token effort
Feature activation+4.339
Fr
Token Fr
Feature activation+0.000
inge
Tokeninge
Feature activation+4.446
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.241
successful
Token successful
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
infamous
Token infamous
Feature activation+0.970
-
Token -
Feature activation+0.000
lobbyists
Token lobbyists
Feature activation+4.403
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
lobbyist
Token lobbyist
Feature activation+0.000
Rick
Token Rick
Feature activation+0.000
Davis
Token Davis
Feature activation+1.340
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.598
it
Token it
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
is
Token is
Feature activation+1.417
incorrect
Token incorrect
Feature activation+4.460
,"
Token,"
Feature activation+0.000
St
Token St
Feature activation+0.000
rief
Tokenrief
Feature activation+0.000
said
Token said
Feature activation+0.188
.
Token.
Feature activation+0.000

INTERVAL 3.814 - 4.290
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+3.914
that
Token that
Feature activation+0.000
few
Token few
Feature activation+0.214
believe
Token believe
Feature activation+0.306
Russia
Token Russia
Feature activation+2.608
would
Token would
Feature activation+0.132
Almost
Token Almost
Feature activation+0.139
Human
Token Human
Feature activation+4.583
creator
Token creator
Feature activation+0.000
Joel
Token Joel
Feature activation+0.000
Wy
Token Wy
Feature activation+0.000
man
Tokenman
Feature activation+4.197
's
Token's
Feature activation+0.000
previous
Token previous
Feature activation+0.000
effort
Token effort
Feature activation+4.339
Fr
Token Fr
Feature activation+0.000
inge
Tokeninge
Feature activation+4.446
country
Token country
Feature activation+0.000
back
Token back
Feature activation+2.740
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Atlantic
Token Atlantic
Feature activation+2.298
fold
Token fold
Feature activation+3.903
It
Token It
Feature activation+0.000
st
Token st
Feature activation+0.000
ings
Tokenings
Feature activation+2.083
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
's
Token's
Feature activation+0.093
book
Token book
Feature activation+2.147
-
Token -
Feature activation+0.197
what
Token what
Feature activation+1.117
is
Token is
Feature activation+2.439
it
Token it
Feature activation+4.125
?
Token?
Feature activation+1.504
-
Token -
Feature activation+1.875
"
Token "
Feature activation+0.552
Cons
TokenCons
Feature activation+0.000
cience
Tokencience
Feature activation+0.690
of
Token of
Feature activation+0.000
getting
Token getting
Feature activation+0.000
along
Token along
Feature activation+0.791
with
Token with
Feature activation+0.000
Vladimir
Token Vladimir
Feature activation+0.069
Putin
Token Putin
Feature activation+3.831
-
Token -
Feature activation+0.000
anat
Token anat
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
ma
Tokenma
Feature activation+1.940
in
Token in
Feature activation+0.000

INTERVAL 3.337 - 3.814
CONTAINS 0.004%

would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
reach
Token reach
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
altitude
Token altitude
Feature activation+3.678
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
Monday
Token Monday
Feature activation+0.295
a
Token a
Feature activation+0.000
Ukrainian
Token Ukrainian
Feature activation+0.000
for
Token for
Feature activation+0.000
one
Token one
Feature activation+1.214
bit
Token bit
Feature activation+2.623
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+3.565
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
only
Token only
Feature activation+0.000
considered
Token considered
Feature activation+0.000
by
Token by
Feature activation+0.000
those
Token those
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+3.430
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
completely
Token completely
Feature activation+0.000
safe
Token safe
Feature activation+2.166
.
Token.
Feature activation+0.000
hardly
Token hardly
Feature activation+0.026
the
Token the
Feature activation+0.000
adult
Token adult
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
room
Token room
Feature activation+3.701
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.341
trying
Token trying
Feature activation+0.342
to
Token to
Feature activation+0.000
be
Token be
Feature activation+3.362
introduction
Token introduction
Feature activation+2.088
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
P
Token P
Feature activation+0.000
FF
TokenFF
Feature activation+0.000
methodology
Token methodology
Feature activation+3.491
.
Token.
Feature activation+0.358
Better
Token Better
Feature activation+0.319
yet
Token yet
Feature activation+3.262
,
Token,
Feature activation+0.000
read
Token read
Feature activation+0.000

INTERVAL 2.860 - 3.337
CONTAINS 0.008%

what
Token what
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+2.398
in
Token in
Feature activation+0.000
every
Token every
Feature activation+0.000
situation
Token situation
Feature activation+3.021
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.598
it
Token it
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
is
Token is
Feature activation+1.417
Alex
Token Alex
Feature activation+0.000
Jones
Token Jones
Feature activation+0.128
'
Token'
Feature activation+0.147
new
Token new
Feature activation+0.103
documentary
Token documentary
Feature activation+2.056
blockbuster
Token blockbuster
Feature activation+3.039
End
Token End
Feature activation+0.000
Game
Token Game
Feature activation+2.352
in
Token in
Feature activation+0.000
high
Token high
Feature activation+0.000
quality
Token quality
Feature activation+0.405
reason
Token reason
Feature activation+0.855
I
Token I
Feature activation+0.000
race
Token race
Feature activation+3.234
in
Token in
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+2.944
is
Token is
Feature activation+0.308
because
Token because
Feature activation+0.671
the
Token the
Feature activation+0.000
cars
Token cars
Feature activation+1.172
give
Token give
Feature activation+0.000
back
Token back
Feature activation+0.000
."
Token."
Feature activation+0.000
Again
Token Again
Feature activation+0.000
-
Token -
Feature activation+0.000
o
Token o
Feature activation+0.000
uch
Tokenuch
Feature activation+3.079
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
ca
Token ca
Feature activation+0.000
ust
Tokenust
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
contrast
Token contrast
Feature activation+1.441
to
Token to
Feature activation+0.000
bear
Token bear
Feature activation+0.000
wrestling
Token wrestling
Feature activation+3.176
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
form
Token form
Feature activation+0.000
of
Token of
Feature activation+0.000
serious
Token serious
Feature activation+0.000

INTERVAL 2.383 - 2.860
CONTAINS 0.017%

use
Token use
Feature activation+0.000
them
Token them
Feature activation+1.379
to
Token to
Feature activation+0.000
question
Token question
Feature activation+0.365
your
Token your
Feature activation+0.000
evaluation
Token evaluation
Feature activation+2.770
that
Token that
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
born
Token born
Feature activation+0.654
the
Token the
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+0.000
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
Era
Token Era
Feature activation+2.583
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
his
Token his
Feature activation+0.000
career
Token career
Feature activation+0.000
went
Token went
Feature activation+0.000
jokes
Token jokes
Feature activation+0.000
-
Token -
Feature activation+0.000
especially
Token especially
Feature activation+2.032
the
Token the
Feature activation+0.401
bad
Token bad
Feature activation+2.896
ones
Token ones
Feature activation+2.517
-
Token -
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
dime
Token dime
Feature activation+0.000
a
Token a
Feature activation+0.000
-
Token -
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
called
Token called
Feature activation+0.000
orbit
Token orbit
Feature activation+0.000
control
Token control
Feature activation+2.653
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
atell
Tokenatell
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+3.914
that
Token that
Feature activation+0.000
few
Token few
Feature activation+0.214
believe
Token believe
Feature activation+0.306
Russia
Token Russia
Feature activation+2.608
would
Token would
Feature activation+0.132
attack
Token attack
Feature activation+0.450
any
Token any
Feature activation+0.000
NATO
Token NATO
Feature activation+0.000
state
Token state
Feature activation+1.939

INTERVAL 1.907 - 2.383
CONTAINS 0.026%

cerned
Tokencerned
Feature activation+1.215
they
Token they
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+2.368
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
stopped
Token stopped
Feature activation+0.974
to
Token to
Feature activation+0.000
check
Token check
Feature activation+1.370
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.000
grants
Token grants
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
Kong
Token Kong
Feature activation+0.136
democracy
Token democracy
Feature activation+2.242
will
Token will
Feature activation+0.000
directly
Token directly
Feature activation+0.000
affect
Token affect
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
habit
Token habit
Feature activation+0.000
of
Token of
Feature activation+0.000
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+0.037
in
Token in
Feature activation+0.000
tears
Token tears
Feature activation+2.046
on
Token on
Feature activation+0.000
national
Token national
Feature activation+0.000
television
Token television
Feature activation+2.499
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
defensive
Token defensive
Feature activation+0.000
partner
Token partner
Feature activation+0.521
Francois
Token Francois
Feature activation+0.000
Beau
Token Beau
Feature activation+0.000
che
Tokenche
Feature activation+0.000
min
Tokenmin
Feature activation+2.206
more
Token more
Feature activation+0.000
at
Token at
Feature activation+0.000
ease
Token ease
Feature activation+0.763
.
Token.
Feature activation+0.000
Go
Token Go
Feature activation+0.000
received
Token received
Feature activation+0.000
a
Token a
Feature activation+0.000
boost
Token boost
Feature activation+0.000
-
Token -
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+1.987
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
top
Token top
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000
bo
Token bo
Feature activation+0.000

INTERVAL 1.430 - 1.907
CONTAINS 0.046%

't
Token't
Feature activation+0.000
get
Token get
Feature activation+0.000
any
Token any
Feature activation+0.000
more
Token more
Feature activation+0.000
tone
Token tone
Feature activation+0.000
deaf
Token deaf
Feature activation+1.670
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
backing
Token backing
Feature activation+0.000
Little
Token Little
Feature activation+0.000
League
Token League
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
make
Token make
Feature activation+0.000
capital
Token capital
Feature activation+0.000
punishment
Token punishment
Feature activation+0.126
obligatory
Token obligatory
Feature activation+1.476
for
Token for
Feature activation+0.000
drug
Token drug
Feature activation+0.000
crimes
Token crimes
Feature activation+1.758
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
chip
Token chip
Feature activation+0.484
that
Token that
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.061
includes
Token includes
Feature activation+1.762
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
filament
Token filament
Feature activation+0.010
today
Token today
Feature activation+1.331
.
Token.
Feature activation+0.000
African
Token African
Feature activation+0.000
countries
Token countries
Feature activation+1.070
from
Token from
Feature activation+0.000
Algeria
Token Algeria
Feature activation+0.107
to
Token to
Feature activation+0.000
Zimbabwe
Token Zimbabwe
Feature activation+1.736
had
Token had
Feature activation+0.000
some
Token some
Feature activation+0.000
form
Token form
Feature activation+0.000
of
Token of
Feature activation+0.000
legal
Token legal
Feature activation+0.000
Sylv
Token Sylv
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
Marg
Token Marg
Feature activation+0.000
aine
Tokenaine
Feature activation+1.462
-
Token -
Feature activation+0.383
11
Token 11
Feature activation+1.813
-
Token -
Feature activation+0.000
Sy
Token Sy
Feature activation+0.000
mm
Tokenmm
Feature activation+0.000
etry
Tokenetry
Feature activation+0.928
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.953 - 1.430
CONTAINS 0.065%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
frontier
Token frontier
Feature activation+0.788
tra
Token tra
Feature activation+0.000
pper
Tokenpper
Feature activation+1.025
who
Token who
Feature activation+0.000
inspired
Token inspired
Feature activation+0.000
Leonardo
Token Leonardo
Feature activation+0.000
Di
Token Di
Feature activation+0.000
Cap
TokenCap
Feature activation+0.000
a
Token a
Feature activation+0.000
title
Token title
Feature activation+0.008
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
fabric
Token fabric
Feature activation+0.000
ating
Tokenating
Feature activation+1.145
a
Token a
Feature activation+0.000
claim
Token claim
Feature activation+0.112
on
Token on
Feature activation+1.046
via
Token via
Feature activation+0.000
plot
Token plot
Feature activation+0.012
the
Token the
Feature activation+0.000
Church
Token Church
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ivity
Tokenivity
Feature activation+1.225
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
declined
Token declined
Feature activation+0.078
to
Token to
Feature activation+0.167
Israel
Token Israel
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
using
Token using
Feature activation+0.000
force
Token force
Feature activation+1.003
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
ships
Token ships
Feature activation+0.068
from
Token from
Feature activation+0.000
entering
Token entering
Feature activation+0.140
42
Token 42
Feature activation+0.000
%
Token%
Feature activation+0.000
32
Token 32
Feature activation+0.000
%
Token%
Feature activation+0.000
Other
Token Other
Feature activation+0.000
-
Token -
Feature activation+1.363
1
Token 1
Feature activation+0.517
%
Token%
Feature activation+1.653
Und
Token Und
Feature activation+0.000
ecided
Tokenecided
Feature activation+0.576
7
Token 7
Feature activation+0.000

INTERVAL 0.477 - 0.953
CONTAINS 0.132%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.027
The
TokenThe
Feature activation+0.000
officer
Token officer
Feature activation+0.000
in
Token in
Feature activation+0.000
charge
Token charge
Feature activation+0.637
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
inquiry
Token inquiry
Feature activation+0.000
,
Token,
Feature activation+0.000
Jose
Token Jose
Feature activation+0.000
up
Token up
Feature activation+0.037
to
Token to
Feature activation+0.000
seven
Token seven
Feature activation+0.000
days
Token days
Feature activation+0.000
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.632
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
focused
Token focused
Feature activation+0.000
on
Token on
Feature activation+0.000
helping
Token helping
Feature activation+0.000
Aut
TokenAut
Feature activation+0.000
umn
Tokenumn
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
-
Token -
Feature activation+0.304
Scotland
Token Scotland
Feature activation+0.055
votes
Token votes
Feature activation+0.616
Yes
Token Yes
Feature activation+0.804
to
Token to
Feature activation+0.000
independence
Token independence
Feature activation+0.452
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
what
Token what
Feature activation+0.000
awaits
Token awaits
Feature activation+0.016
you
Token you
Feature activation+2.234
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.184
speak
Token speak
Feature activation+0.700
up
Token up
Feature activation+2.217
-
Token -
Feature activation+0.000
it
Token it
Feature activation+0.504
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
a
Token a
Feature activation+0.000
win
Token win
Feature activation+0.000
over
Token over
Feature activation+0.000
Argentina
Token Argentina
Feature activation+0.794
had
Token had
Feature activation+0.000
them
Token them
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000

INTERVAL 0.000 - 0.477
CONTAINS 99.701%

OH
TokenOH
Feature activation+0.000
talents
Token talents
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
X
TokenX
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
omi
Tokenomi
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
s
Tokens
Feature activation+0.000
second
Token second
Feature activation+0.000
anniversary
Token anniversary
Feature activation+0.000
The
Token The
Feature activation+0.000
team
Token team
Feature activation+0.000
existed
Token existed
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
application
Token application
Feature activation+0.000
developers
Token developers
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
visit
Token visit
Feature activation+0.000
the
Token the
Feature activation+0.000
worlds
Token worlds
Feature activation+0.000
created
Token created
Feature activation+0.000
by
Token by
Feature activation+0.000
your
Token your
Feature activation+0.000
friends
Token friends
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
threat
Token threat
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
him
Token him
Feature activation+0.000
awake
Token awake
Feature activation+0.000
some
Token some
Feature activation+0.000
nights
Token nights
Feature activation+0.000
,
Token,
Feature activation+0.000
biomass
Token biomass
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
company
Token company
Feature activation+0.000
is
Token is
Feature activation+0.000
facing
Token facing
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
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 H10.3: (feature 11403)

TOP ACTIVATIONS
MAX = 5.813

processing
Token processing
Feature activation+0.000
everything
Token everything
Feature activation+0.000
(
Token (
Feature activation+0.000
was
Tokenwas
Feature activation+5.730
the
Token the
Feature activation+0.581
hardest
Token hardest
Feature activation+5.813
part
Token part
Feature activation+5.750
),"
Token),"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
everything
Token everything
Feature activation+0.000
(
Token (
Feature activation+0.000
was
Tokenwas
Feature activation+5.730
the
Token the
Feature activation+0.581
hardest
Token hardest
Feature activation+5.813
part
Token part
Feature activation+5.750
),"
Token),"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
"
Token"
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
processing
Token processing
Feature activation+0.000
everything
Token everything
Feature activation+0.000
(
Token (
Feature activation+0.000
was
Tokenwas
Feature activation+5.730
the
Token the
Feature activation+0.581
hardest
Token hardest
Feature activation+5.813
part
Token part
Feature activation+5.750
),"
Token),"
Feature activation+0.000
he
Token he
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.255
combination
Token combination
Feature activation+5.163
of
Token of
Feature activation+4.249
B
Token B
Feature activation+0.000
isson
Tokenisson
Feature activation+0.000
nette
Tokennette
Feature activation+2.389
and
Token and
Feature activation+0.151
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
hit
Token hit
Feature activation+0.000
and
Token and
Feature activation+0.000
(
Token (
Feature activation+0.000
White
TokenWhite
Feature activation+5.145
)
Token)
Feature activation+0.000
came
Token came
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
stable
Token stable
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
yet
Tokenyet
Feature activation+5.107
)
Token)
Feature activation+0.049
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
more
Token more
Feature activation+0.000
was
Token was
Feature activation+0.000
angry
Token angry
Feature activation+0.000
that
Token that
Feature activation+0.000
(
Token (
Feature activation+0.130
the
Tokenthe
Feature activation+1.855
boy
Token boy
Feature activation+4.969
)
Token)
Feature activation+0.006
glared
Token glared
Feature activation+0.000
at
Token at
Feature activation+0.000
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
he
Tokenhe
Feature activation+2.154
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.878
s
Tokens
Feature activation+4.635
there
Token there
Feature activation+4.901
)."
Token)."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sunday
TokenSunday
Feature activation+0.000
marked
Token marked
Feature activation+0.000
know
Token know
Feature activation+0.000
(
Token (
Feature activation+0.000
he
Tokenhe
Feature activation+2.154
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.878
s
Tokens
Feature activation+4.635
there
Token there
Feature activation+4.901
)."
Token)."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sunday
TokenSunday
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
worked
Token worked
Feature activation+0.000
for
Token for
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+4.627
)
Token)
Feature activation+0.000
fought
Token fought
Feature activation+0.000
for
Token for
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
menu
Token menu
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
Che
TokenChe
Feature activation+0.000
f
Tokenf
Feature activation+3.290
Jorge
Token Jorge
Feature activation+4.358
)
Token)
Feature activation+0.000
Val
Token Val
Feature activation+0.000
le
Tokenle
Feature activation+0.000
jo
Tokenjo
Feature activation+0.000
aims
Token aims
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.255
combination
Token combination
Feature activation+5.163
of
Token of
Feature activation+4.249
B
Token B
Feature activation+0.000
isson
Tokenisson
Feature activation+0.000
nette
Tokennette
Feature activation+2.389
and
Token and
Feature activation+0.151
Scott
Token Scott
Feature activation+3.664
otherwise
Token otherwise
Feature activation+0.000
(
Token (
Feature activation+0.216
which
Tokenwhich
Feature activation+2.775
includes
Token includes
Feature activation+2.053
Victoria
Token Victoria
Feature activation+1.720
Police
Token Police
Feature activation+4.241
),
Token),
Feature activation+0.000
is
Token is
Feature activation+0.000
restrained
Token restrained
Feature activation+0.000
from
Token from
Feature activation+0.000
interfering
Token interfering
Feature activation+0.000
150
Token150
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+0.000
(
Token (
Feature activation+0.000
f
Tokenf
Feature activation+0.000
iscal
Tokeniscal
Feature activation+4.196
year
Token year
Feature activation+2.682
)
Token)
Feature activation+0.000
20
Token 20
Feature activation+0.000
26
Token26
Feature activation+0.000
alone
Token alone
Feature activation+0.000
":
Token":
Feature activation+0.000
"
Token "
Feature activation+0.000
Will
TokenWill
Feature activation+0.000
(
Token (
Feature activation+0.000
Fer
TokenFer
Feature activation+0.000
rell
Tokenrell
Feature activation+4.146
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
written
Token written
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
O
TokenO
Feature activation+0.000
le
Tokenle
Feature activation+0.000
ks
Tokenks
Feature activation+0.000
ak
Tokenak
Feature activation+4.056
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.142
s
Tokens
Feature activation+2.363
)
Token)
Feature activation+0.000
finding
Token finding
Feature activation+0.000
of
Token of
Feature activation+0.000
interior
Token interior
Feature activation+0.000
(
Token (
Feature activation+0.338
Prince
TokenPrince
Feature activation+0.474
Nay
Token Nay
Feature activation+0.000
ef
Tokenef
Feature activation+4.025
bin
Token bin
Feature activation+0.000
Abdul
Token Abdul
Feature activation+0.054
Az
Token Az
Feature activation+0.000
iz
Tokeniz
Feature activation+3.857
)
Token)
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+0.000
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+2.279
the
Token the
Feature activation+0.285
bombing
Token bombing
Feature activation+3.902
)
Token)
Feature activation+0.000
were
Token were
Feature activation+0.000
killers
Token killers
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
This
TokenThis
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
(
Token (
Feature activation+0.000
of
Tokenof
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+3.879
)
Token)
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
accepted
Token accepted
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Nay
Token Nay
Feature activation+0.000
ef
Tokenef
Feature activation+4.025
bin
Token bin
Feature activation+0.000
Abdul
Token Abdul
Feature activation+0.054
Az
Token Az
Feature activation+0.000
iz
Tokeniz
Feature activation+3.857
)
Token)
Feature activation+0.000
is
Token is
Feature activation+0.000
reported
Token reported
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000

Top DFA by src position
MAX = 6.610

Ċ
TokenĊ
Feature activation+0.014
Top resid features:
"
Token"
Feature activation+0.373
Top resid features:
Just
TokenJust
Feature activation-0.007
Top resid features:
processing
Token processing
Feature activation-0.018
Top resid features:
everything
Token everything
Feature activation-0.004
Top resid features:
(
Token (
Feature activation+6.568
Top resid features:
was
Tokenwas
Feature activation+0.041
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
hardest
Token hardest
Feature activation-0.066
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
),"
Token),"
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
"
Token"
Feature activation+0.385
Top resid features:
Just
TokenJust
Feature activation-0.008
Top resid features:
processing
Token processing
Feature activation-0.001
Top resid features:
everything
Token everything
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+6.610
Top resid features:
was
Tokenwas
Feature activation-0.019
Top resid features:
the
Token the
Feature activation-0.090
Top resid features:
hardest
Token hardest
Feature activation-0.065
Top resid features:
part
Token part
Feature activation-0.066
Top resid features:
),"
Token),"
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
"
Token"
Feature activation+0.089
Top resid features:
Just
TokenJust
Feature activation+0.006
Top resid features:
processing
Token processing
Feature activation-0.021
Top resid features:
everything
Token everything
Feature activation-0.013
Top resid features:
(
Token (
Feature activation+6.551
Top resid features:
was
Tokenwas
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
hardest
Token hardest
Feature activation+0.000
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
),"
Token),"
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
I
TokenI
Feature activation-0.002
Top resid features:
think
Token think
Feature activation-0.012
Top resid features:
(
Token (
Feature activation+6.177
Top resid features:
the
Tokenthe
Feature activation+0.009
Top resid features:
combination
Token combination
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
isson
Tokenisson
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.002
Top resid features:
made
Token made
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
hit
Token hit
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+6.145
Top resid features:
White
TokenWhite
Feature activation-0.020
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
came
Token came
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.011
Top resid features:
now
Token now
Feature activation+0.009
Top resid features:
more
Token more
Feature activation-0.009
Top resid features:
stable
Token stable
Feature activation-0.065
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
(
Token (
Feature activation+6.099
Top resid features:
yet
Tokenyet
Feature activation-0.055
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.002
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.006
Top resid features:
angry
Token angry
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.030
Top resid features:
(
Token (
Feature activation+5.735
Top resid features:
the
Tokenthe
Feature activation+0.087
Top resid features:
boy
Token boy
Feature activation-0.010
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
glared
Token glared
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
let
Token let
Feature activation-0.002
Top resid features:
me
Token me
Feature activation+0.005
Top resid features:
know
Token know
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+5.745
Top resid features:
he
Tokenhe
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.042
Top resid features:
there
Token there
Feature activation-0.039
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
let
Token let
Feature activation+0.024
Top resid features:
me
Token me
Feature activation+0.007
Top resid features:
know
Token know
Feature activation-0.010
Top resid features:
(
Token (
Feature activation+5.423
Top resid features:
he
Tokenhe
Feature activation+0.051
Top resid features:
âĢ
TokenâĢ
Feature activation+0.038
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
s
Tokens
Feature activation-0.003
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
died
Token died
Feature activation-0.012
Top resid features:
for
Token for
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
worked
Token worked
Feature activation-0.109
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
(
Token (
Feature activation+5.865
Top resid features:
and
Tokenand
Feature activation-0.050
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
fought
Token fought
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
tasting
Token tasting
Feature activation+0.000
Top resid features:
menu
Token menu
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+5.201
Top resid features:
Che
TokenChe
Feature activation-0.010
Top resid features:
f
Tokenf
Feature activation+0.005
Top resid features:
Jorge
Token Jorge
Feature activation-0.004
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Val
Token Val
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.009
Top resid features:
I
TokenI
Feature activation-0.002
Top resid features:
think
Token think
Feature activation-0.006
Top resid features:
(
Token (
Feature activation+5.098
Top resid features:
the
Tokenthe
Feature activation+0.049
Top resid features:
combination
Token combination
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
isson
Tokenisson
Feature activation+0.000
Top resid features:
servants
Token servants
Feature activation+0.073
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
agents
Token agents
Feature activation-0.012
Top resid features:
or
Token or
Feature activation-0.004
Top resid features:
otherwise
Token otherwise
Feature activation-0.002
Top resid features:
(
Token (
Feature activation+5.228
Top resid features:
which
Tokenwhich
Feature activation-0.056
Top resid features:
includes
Token includes
Feature activation-0.083
Top resid features:
Victoria
Token Victoria
Feature activation-0.005
Top resid features:
Police
Token Police
Feature activation+0.026
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.012
Top resid features:
$
Token $
Feature activation-0.006
Top resid features:
150
Token150
Feature activation-0.002
Top resid features:
billion
Token billion
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.023
Top resid features:
(
Token (
Feature activation+5.272
Top resid features:
f
Tokenf
Feature activation-0.001
Top resid features:
iscal
Tokeniscal
Feature activation-0.049
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
Goods
Token Goods
Feature activation+0.001
Top resid features:
":
Token":
Feature activation-0.002
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
Will
TokenWill
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+5.087
Top resid features:
Fer
TokenFer
Feature activation+0.023
Top resid features:
rell
Tokenrell
Feature activation-0.041
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
players
Token players
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
every
Token every
Feature activation+0.001
Top resid features:
spot
Token spot
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+4.838
Top resid features:
O
TokenO
Feature activation-0.000
Top resid features:
le
Tokenle
Feature activation+0.002
Top resid features:
ks
Tokenks
Feature activation+0.001
Top resid features:
ak
Tokenak
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.022
Top resid features:
The
TokenThe
Feature activation+0.012
Top resid features:
minister
Token minister
Feature activation+0.025
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
interior
Token interior
Feature activation-0.036
Top resid features:
(
Token (
Feature activation+4.863
Top resid features:
Prince
TokenPrince
Feature activation+0.109
Top resid features:
Nay
Token Nay
Feature activation-0.016
Top resid features:
ef
Tokenef
Feature activation-0.012
Top resid features:
bin
Token bin
Feature activation+0.000
Top resid features:
Abdul
Token Abdul
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.012
Top resid features:
Those
TokenThose
Feature activation-0.012
Top resid features:
people
Token people
Feature activation-0.006
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
died
Token died
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+4.662
Top resid features:
in
Tokenin
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
bombing
Token bombing
Feature activation-0.009
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
"
Token"
Feature activation+0.007
Top resid features:
This
TokenThis
Feature activation+0.002
Top resid features:
scheme
Token scheme
Feature activation+0.109
Top resid features:
(
Token (
Feature activation+4.476
Top resid features:
of
Tokenof
Feature activation+0.157
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
government
Token government
Feature activation+0.060
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.016
Top resid features:
The
TokenThe
Feature activation+0.017
Top resid features:
minister
Token minister
Feature activation+0.037
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
interior
Token interior
Feature activation-0.022
Top resid features:
(
Token (
Feature activation+4.792
Top resid features:
Prince
TokenPrince
Feature activation+0.044
Top resid features:
Nay
Token Nay
Feature activation-0.017
Top resid features:
ef
Tokenef
Feature activation-0.017
Top resid features:
bin
Token bin
Feature activation-0.008
Top resid features:
Abdul
Token Abdul
Feature activation-0.013
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.50

Head 4: 0.11

Head 5: 0.12

Head 6: 0.02

Head 7: 0.03

Head 8: 0.04

Head 9: 0.05

Head 10: 0.02

Head 11: 0.04

Positive logits

),"7.61

)."6.58

)"6.57

)",6.47

)5.80

)'5.42

,)5.22

)--5.11

)4.86

)}4.82

)...4.80

)\4.75

)—4.68

)-4.68

)!4.59

?)4.46

.)4.45

)?4.42

)=4.41

)4.37

Negative logits

".[-3.14

[/-2.62

-2.57

};-2.39

.[-2.32

[...]-2.32

][-2.29

,[-2.29

];-2.13

[…]-2.04

amber-1.97

();-1.92

."[-1.92

amd-1.88

(~-1.87

(<-1.86

([-1.85

guiName-1.78

Previous-1.77

*:-1.77

INTERVAL 5.232 - 5.813
CONTAINS 0.000%

"
Token"
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
processing
Token processing
Feature activation+0.000
everything
Token everything
Feature activation+0.000
(
Token (
Feature activation+0.000
was
Tokenwas
Feature activation+5.730
the
Token the
Feature activation+0.581
hardest
Token hardest
Feature activation+5.813
part
Token part
Feature activation+5.750
),"
Token),"
Feature activation+0.000
he
Token he
Feature activation+0.000
processing
Token processing
Feature activation+0.000
everything
Token everything
Feature activation+0.000
(
Token (
Feature activation+0.000
was
Tokenwas
Feature activation+5.730
the
Token the
Feature activation+0.581
hardest
Token hardest
Feature activation+5.813
part
Token part
Feature activation+5.750
),"
Token),"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
everything
Token everything
Feature activation+0.000
(
Token (
Feature activation+0.000
was
Tokenwas
Feature activation+5.730
the
Token the
Feature activation+0.581
hardest
Token hardest
Feature activation+5.813
part
Token part
Feature activation+5.750
),"
Token),"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 4.651 - 5.232
CONTAINS 0.001%

ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.255
combination
Token combination
Feature activation+5.163
of
Token of
Feature activation+4.249
B
Token B
Feature activation+0.000
isson
Tokenisson
Feature activation+0.000
nette
Tokennette
Feature activation+2.389
and
Token and
Feature activation+0.151
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
stable
Token stable
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
yet
Tokenyet
Feature activation+5.107
)
Token)
Feature activation+0.049
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
more
Token more
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
hit
Token hit
Feature activation+0.000
and
Token and
Feature activation+0.000
(
Token (
Feature activation+0.000
White
TokenWhite
Feature activation+5.145
)
Token)
Feature activation+0.000
came
Token came
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
(
Token (
Feature activation+0.000
he
Tokenhe
Feature activation+2.154
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.878
s
Tokens
Feature activation+4.635
there
Token there
Feature activation+4.901
)."
Token)."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sunday
TokenSunday
Feature activation+0.000
marked
Token marked
Feature activation+0.000
was
Token was
Feature activation+0.000
angry
Token angry
Feature activation+0.000
that
Token that
Feature activation+0.000
(
Token (
Feature activation+0.130
the
Tokenthe
Feature activation+1.855
boy
Token boy
Feature activation+4.969
)
Token)
Feature activation+0.006
glared
Token glared
Feature activation+0.000
at
Token at
Feature activation+0.000
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 4.069 - 4.651
CONTAINS 0.001%

I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.255
combination
Token combination
Feature activation+5.163
of
Token of
Feature activation+4.249
B
Token B
Feature activation+0.000
isson
Tokenisson
Feature activation+0.000
nette
Tokennette
Feature activation+2.389
and
Token and
Feature activation+0.151
Scott
Token Scott
Feature activation+3.664
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
worked
Token worked
Feature activation+0.000
for
Token for
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+4.627
)
Token)
Feature activation+0.000
fought
Token fought
Feature activation+0.000
for
Token for
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
150
Token150
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+0.000
(
Token (
Feature activation+0.000
f
Tokenf
Feature activation+0.000
iscal
Tokeniscal
Feature activation+4.196
year
Token year
Feature activation+2.682
)
Token)
Feature activation+0.000
20
Token 20
Feature activation+0.000
26
Token26
Feature activation+0.000
alone
Token alone
Feature activation+0.000
menu
Token menu
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
Che
TokenChe
Feature activation+0.000
f
Tokenf
Feature activation+3.290
Jorge
Token Jorge
Feature activation+4.358
)
Token)
Feature activation+0.000
Val
Token Val
Feature activation+0.000
le
Tokenle
Feature activation+0.000
jo
Tokenjo
Feature activation+0.000
aims
Token aims
Feature activation+0.000
":
Token":
Feature activation+0.000
"
Token "
Feature activation+0.000
Will
TokenWill
Feature activation+0.000
(
Token (
Feature activation+0.000
Fer
TokenFer
Feature activation+0.000
rell
Tokenrell
Feature activation+4.146
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
written
Token written
Feature activation+0.000

INTERVAL 3.488 - 4.069
CONTAINS 0.001%

who
Token who
Feature activation+0.000
died
Token died
Feature activation+0.000
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+2.279
the
Token the
Feature activation+0.285
bombing
Token bombing
Feature activation+3.902
)
Token)
Feature activation+0.000
were
Token were
Feature activation+0.000
killers
Token killers
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+4.249
B
Token B
Feature activation+0.000
isson
Tokenisson
Feature activation+0.000
nette
Tokennette
Feature activation+2.389
and
Token and
Feature activation+0.151
Scott
Token Scott
Feature activation+3.664
Sab
Token Sab
Feature activation+0.000
our
Tokenour
Feature activation+0.000
in
Tokenin
Feature activation+5.272
,
Token,
Feature activation+0.162
another
Token another
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.253
deal
Token deal
Feature activation+3.733
)
Token)
Feature activation+0.000
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
Exxon
Token Exxon
Feature activation+0.000
views
Token views
Feature activation+0.000
of
Token of
Feature activation+0.000
interior
Token interior
Feature activation+0.000
(
Token (
Feature activation+0.338
Prince
TokenPrince
Feature activation+0.474
Nay
Token Nay
Feature activation+0.000
ef
Tokenef
Feature activation+4.025
bin
Token bin
Feature activation+0.000
Abdul
Token Abdul
Feature activation+0.054
Az
Token Az
Feature activation+0.000
iz
Tokeniz
Feature activation+3.857
)
Token)
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
where
Token where
Feature activation+0.000
(
Token (
Feature activation+0.000
sic
Tokensic
Feature activation+3.502
)
Token)
Feature activation+0.000
massively
Token massively
Feature activation+0.000
outnumbered
Token outnumbered
Feature activation+0.000
and
Token and
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 2.907 - 3.488
CONTAINS 0.001%

(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
impact
Token impact
Feature activation+1.954
of
Token of
Feature activation+0.000
WikiLeaks
Token WikiLeaks
Feature activation+1.951
revelations
Token revelations
Feature activation+3.082
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
my
Token my
Feature activation+0.000
he
Token he
Feature activation+0.000
val
Tokenval
Feature activation+0.000
(
Token (
Feature activation+0.000
friend
Tokenfriend
Feature activation+3.156
)
Token)
Feature activation+0.000
Ash
Token Ash
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
least
Token least
Feature activation+0.000
1993
Token 1993
Feature activation+0.000
(
Token (
Feature activation+0.000
via
Tokenvia
Feature activation+0.350
Zero
Token Zero
Feature activation+0.000
Hedge
Token Hedge
Feature activation+3.404
)."
Token)."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
leak
Token leak
Feature activation+0.000
use
Token use
Feature activation+0.000
(
Token (
Feature activation+0.000
see
Tokensee
Feature activation+0.000
ssh
Token ssh
Feature activation+0.000
(
Token(
Feature activation+0.000
1
Token1
Feature activation+3.239
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
l
Tokenl
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
menu
Token menu
Feature activation+3.034
,
Token,
Feature activation+0.950
you
Token you
Feature activation+0.000
'll
Token'll
Feature activation+0.000
see
Token see
Feature activation+1.041
below
Token below
Feature activation+3.303
it
Token it
Feature activation+3.161
an
Token an
Feature activation+0.000
Other
Token Other
Feature activation+0.465
folder
Token folder
Feature activation+3.360
that
Token that
Feature activation+0.000

INTERVAL 2.325 - 2.907
CONTAINS 0.002%

been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
wholesale
Token wholesale
Feature activation+0.000
M
Token M
Feature activation+0.000
(
Token(
Feature activation+0.000
S
TokenS
Feature activation+2.389
)
Token)
Feature activation+0.000
P
TokenP
Feature activation+0.000
expenses
Token expenses
Feature activation+0.000
scandal
Token scandal
Feature activation+0.000
?
Token?
Feature activation+0.000
V
TokenV
Feature activation+0.000
IES
TokenIES
Feature activation+0.000
:
Token:
Feature activation+0.000
(
Token (
Feature activation+0.000
L
TokenL
Feature activation+0.000
aughter
Tokenaughter
Feature activation+2.374
)
Token)
Feature activation+0.000
He
Token He
Feature activation+0.000
found
Token found
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
Form
TokenForm
Feature activation+0.000
ula
Tokenula
Feature activation+1.224
One
Token One
Feature activation+3.110
racing
Token racing
Feature activation+2.877
)
Token)
Feature activation+0.000
track
Token track
Feature activation+0.000
has
Token has
Feature activation+0.000
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
He
Token He
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
care
Tokencare
Feature activation+0.000
(
Token(
Feature activation+0.000
s
Tokens
Feature activation+2.439
)
Token)
Feature activation+0.000
about
Token about
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+2.243
counties
Token counties
Feature activation+2.362
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.140
)
Token)
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.744 - 2.325
CONTAINS 0.002%

had
Token had
Feature activation+0.000
wrapped
Token wrapped
Feature activation+0.000
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
7
Token7
Feature activation+0.000
th
Tokenth
Feature activation+1.917
)
Token)
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
lot
Token lot
Feature activation+0.000
that
Token that
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
know
Token know
Feature activation+0.000
(
Token (
Feature activation+0.000
he
Tokenhe
Feature activation+2.154
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.878
s
Tokens
Feature activation+4.635
there
Token there
Feature activation+4.901
)."
Token)."
Feature activation+0.000
told
Token told
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
impact
Token impact
Feature activation+1.954
of
Token of
Feature activation+0.000
WikiLeaks
Token WikiLeaks
Feature activation+1.951
revelations
Token revelations
Feature activation+3.082
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.000
but
Token but
Feature activation+0.000
Those
TokenThose
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+0.000
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+2.279
the
Token the
Feature activation+0.285
bombing
Token bombing
Feature activation+3.902
)
Token)
Feature activation+0.000
were
Token were
Feature activation+0.000
killers
Token killers
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
angry
Token angry
Feature activation+0.000
that
Token that
Feature activation+0.000
(
Token (
Feature activation+0.130
the
Tokenthe
Feature activation+1.855
boy
Token boy
Feature activation+4.969
)
Token)
Feature activation+0.006
glared
Token glared
Feature activation+0.000
at
Token at
Feature activation+0.000
me
Token me
Feature activation+0.000

INTERVAL 1.163 - 1.744
CONTAINS 0.004%

and
Tokenand
Feature activation+0.000
W
Token W
Feature activation+0.000
3
Token3
Feature activation+0.000
C
TokenC
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
engineer
Token engineer
Feature activation+1.243
)
Token)
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Watson
Token Watson
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
(
Token(
Feature activation+0.000
c
Tokenc
Feature activation+2.087
),
Token),
Feature activation+0.000
5
Token 5
Feature activation+0.307
(
Token(
Feature activation+0.000
c
Tokenc
Feature activation+1.502
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.000
5
Token 5
Feature activation+0.000
(
Token(
Feature activation+0.000
d
Tokend
Feature activation+1.037
charged
Token charged
Feature activation+0.000
with
Token with
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
pleaded
Token pleaded
Feature activation+0.000
guilty
Token guilty
Feature activation+1.492
to
Token to
Feature activation+2.348
)
Token)
Feature activation+0.000
possessing
Token possessing
Feature activation+0.000
a
Token a
Feature activation+0.000
bl
Token bl
Feature activation+0.000
situation
Token situation
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
pot
Tokenpot
Feature activation+0.000
ential
Tokenential
Feature activation+1.502
)
Token)
Feature activation+0.000
new
Token new
Feature activation+0.000
residential
Token residential
Feature activation+0.000
incentives
Token incentives
Feature activation+0.000
can
Token can
Feature activation+0.000
He
Token He
Feature activation+0.000
means
Token means
Feature activation+0.000
EX
Token EX
Feature activation+0.000
ACT
TokenACT
Feature activation+0.000
LY
TokenLY
Feature activation+1.326
that
Token that
Feature activation+1.169
)?
Token)?
Feature activation+0.000
(
Token (
Feature activation+0.000
e
Tokene
Feature activation+0.000
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000

INTERVAL 0.581 - 1.163
CONTAINS 0.013%

them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
defer
Token defer
Feature activation+0.000
(
Token (
Feature activation+0.000
not
Tokennot
Feature activation+0.000
avoid
Token avoid
Feature activation+0.986
)
Token)
Feature activation+0.000
capital
Token capital
Feature activation+0.000
-
Token-
Feature activation+0.000
g
Tokeng
Feature activation+0.000
ains
Tokenains
Feature activation+0.000
is
Token is
Feature activation+0.000
by
Token by
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
me
Tokenme
Feature activation+0.626
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
artist
Token artist
Feature activation+0.000
ide
Tokenide
Feature activation+0.217
his
Token his
Feature activation+0.000
feet
Token feet
Feature activation+1.092
,
Token,
Feature activation+0.000
challenge
Token challenge
Feature activation+0.000
shots
Token shots
Feature activation+0.917
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+1.419
.)
Token.)
Feature activation+0.000
okay
Token okay
Feature activation+0.000
,
Token,
Feature activation+0.000
du
Token du
Feature activation+0.000
pe
Token pe
Feature activation+0.000
uple
Tokenuple
Feature activation+0.000
"
Token"
Feature activation+0.000
(
Token (
Feature activation+0.000
writing
Tokenwriting
Feature activation+0.585
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
good
Token good
Feature activation+0.695
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
e
Tokene
Feature activation+0.000
.
Token.
Feature activation+0.000
not
Token not
Feature activation+0.083
h
Token h
Feature activation+0.000
arrass
Tokenarrass
Feature activation+0.838
)
Token)
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
insult
Token insult
Feature activation+0.000
us
Token us
Feature activation+0.000

INTERVAL 0.000 - 0.581
CONTAINS 99.976%

undermines
Token undermines
Feature activation+0.000
the
Token the
Feature activation+0.000
ability
Token ability
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
poorest
Token poorest
Feature activation+0.000
to
Token to
Feature activation+0.000
invest
Token invest
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
them
Token them
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
where
Token where
Feature activation+0.000
people
Token people
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Scar
Token Scar
Feature activation+0.000
://
Token://
Feature activation+0.000
inst
Tokeninst
Feature activation+0.000
agram
Tokenagram
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.000
p
Tokenp
Feature activation+0.000
/
Token/
Feature activation+0.000
B
TokenB
Feature activation+0.000
X
TokenX
Feature activation+0.000
SE
TokenSE
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
of
Token of
Feature activation+0.000
rape
Token rape
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
should
Token should
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
an
Tokenan
Feature activation+0.000
mi
Tokenmi
Feature activation+0.000
began
Token began
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
facility
Token facility
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+0.000
but
Token but
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H10.3: (feature 13630)

TOP ACTIVATIONS
MAX = 9.139

unauthorized
Token unauthorized
Feature activation+0.000
clone
Token clone
Feature activation+7.374
of
Token of
Feature activation+0.338
the
Token the
Feature activation+0.000
old
Token old
Feature activation+1.477
site
Token site
Feature activation+9.139
and
Token and
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
involve
Token involve
Feature activation+0.000
any
Token any
Feature activation+0.000
be
Token be
Feature activation+1.013
a
Token a
Feature activation+0.000
creative
Token creative
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
gimmick
Token gimmick
Feature activation+7.617
here
Token here
Feature activation+8.504
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
out
Token out
Feature activation+0.000
on
Token on
Feature activation+0.000
March
Token March
Feature activation+0.000
2
Token 2
Feature activation+3.958
and
Token and
Feature activation+0.000
March
Token March
Feature activation+0.000
9
Token 9
Feature activation+8.307
to
Token to
Feature activation+0.000
reflect
Token reflect
Feature activation+0.335
new
Token new
Feature activation+0.000
information
Token information
Feature activation+7.993
given
Token given
Feature activation+1.918
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.089
all
Token all
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
hoax
Token hoax
Feature activation+8.191
!
Token!
Feature activation+1.714
Read
Token Read
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
turned
Token turned
Feature activation+0.000
March
Token March
Feature activation+0.000
9
Token 9
Feature activation+8.307
to
Token to
Feature activation+0.000
reflect
Token reflect
Feature activation+0.335
new
Token new
Feature activation+0.000
information
Token information
Feature activation+7.993
given
Token given
Feature activation+1.918
.]
Token.]
Feature activation+0.000
A
TokenA
Feature activation+0.000
new
Token new
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+1.013
a
Token a
Feature activation+0.000
creative
Token creative
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
gimmick
Token gimmick
Feature activation+7.617
here
Token here
Feature activation+8.504
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
make
Token make
Feature activation+0.000
stand
Token stand
Feature activation+2.909
against
Token against
Feature activation+0.000
social
Token social
Feature activation+0.000
injust
Token injust
Feature activation+0.000
ices
Tokenices
Feature activation+7.540
before
Token before
Feature activation+0.000
first
Token first
Feature activation+0.000
home
Token home
Feature activation+0.000
preseason
Token preseason
Feature activation+3.351
game
Token game
Feature activation+7.430
ices
Tokenices
Feature activation+7.540
before
Token before
Feature activation+0.000
first
Token first
Feature activation+0.000
home
Token home
Feature activation+0.000
preseason
Token preseason
Feature activation+3.351
game
Token game
Feature activation+7.430
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
With
TokenWith
Feature activation+0.000
new
Token new
Feature activation+0.000
site
Token site
Feature activation+1.781
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.639
unauthorized
Token unauthorized
Feature activation+0.000
clone
Token clone
Feature activation+7.374
of
Token of
Feature activation+0.338
the
Token the
Feature activation+0.000
old
Token old
Feature activation+1.477
site
Token site
Feature activation+9.139
and
Token and
Feature activation+0.000
soccer
Token soccer
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
[
Token[
Feature activation+0.000
UPDATE
TokenUPDATE
Feature activation+0.881
below
Token below
Feature activation+7.335
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
ban
Token ban
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
free
Tokenfree
Feature activation+0.000
speech
Token speech
Feature activation+4.629
zones
Token zones
Feature activation+7.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.667
on
Token on
Feature activation+0.000
college
Token college
Feature activation+0.000
campuses
Token campuses
Feature activation+7.133
zones
Token zones
Feature activation+7.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.667
on
Token on
Feature activation+0.000
college
Token college
Feature activation+0.000
campuses
Token campuses
Feature activation+7.133
]
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
not
Token not
Feature activation+0.000
involve
Token involve
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
principals
Token principals
Feature activation+6.765
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+2.753
iso
Token iso
Feature activation+0.000
Hunt
TokenHunt
Feature activation+4.873
America
Token America
Feature activation+4.168
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.167
s
Tokens
Feature activation+0.000
heroin
Token heroin
Feature activation+3.688
habit
Token habit
Feature activation+6.727
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
fraught
Token fraught
Feature activation+0.000
no
Token no
Feature activation+0.000
Donald
Token Donald
Feature activation+0.804
Trump
Token Trump
Feature activation+6.578
2
Token 2
Feature activation+4.818
.
Token.
Feature activation+0.000
0
Token0
Feature activation+6.631
!]
Token!]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
this
Token this
Feature activation+0.000
:
Token:
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
Donald
Token Donald
Feature activation+0.804
Trump
Token Trump
Feature activation+6.578
2
Token 2
Feature activation+4.818
.
Token.
Feature activation+0.000
0
Token0
Feature activation+6.631
!]
Token!]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
cite
Token cite
Feature activation+2.694
here
Token here
Feature activation+4.548
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
rough
Token rough
Feature activation+3.958
estimates
Token estimates
Feature activation+6.538
,
Token,
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
more
Token more
Feature activation+0.000
when
Token when
Feature activation+0.000
Milo
Token Milo
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
CS
Token CS
Feature activation+0.000
UF
TokenUF
Feature activation+6.511
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ass
TokenAss
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.685
folly
Token folly
Feature activation+0.160
in
Token in
Feature activation+0.000
another
Token another
Feature activation+0.000
article
Token article
Feature activation+6.477
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.342
Project
TokenProject
Feature activation+0.000
ed
Tokened
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
This
TokenThis
Feature activation+0.000
paragraph
Token paragraph
Feature activation+1.154
is
Token is
Feature activation+0.000
obsolete
Token obsolete
Feature activation+6.432
:]
Token:]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
you
Token you
Feature activation+0.000

Top DFA by src position
MAX = 10.125

finish
Token finish
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.097
Top resid features:
[
Token[
Feature activation+10.125
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.009
Top resid features:
Wednesday
Token Wednesday
Feature activation-0.003
Top resid features:
11
Token 11
Feature activation-0.000
Top resid features:
:
Token:
Feature activation-0.000
Top resid features:
00
Token00
Feature activation+0.000
Top resid features:
R
Token R
Feature activation-0.002
Top resid features:
umblr
Tokenumblr
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
[
Token[
Feature activation+9.595
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.007
Top resid features:
:
Token:
Feature activation+0.384
Top resid features:
It
Token It
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
all
Token all
Feature activation-0.002
Top resid features:
(
Token (
Feature activation-0.001
Top resid features:
0
Token0
Feature activation-0.000
Top resid features:
AP
Token AP
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.081
Top resid features:
[
Token[
Feature activation+9.223
Top resid features:
Ed
TokenEd
Feature activation-0.003
Top resid features:
note
Token note
Feature activation+0.027
Top resid features:
:
Token:
Feature activation+0.565
Top resid features:
This
Token This
Feature activation+0.042
Top resid features:
article
Token article
Feature activation+0.010
Top resid features:
R
Token R
Feature activation+0.004
Top resid features:
umblr
Tokenumblr
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
[
Token[
Feature activation+9.115
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.023
Top resid features:
:
Token:
Feature activation+0.433
Top resid features:
It
Token It
Feature activation+0.059
Top resid features:
was
Token was
Feature activation+0.111
Top resid features:
all
Token all
Feature activation+0.035
Top resid features:
(
Token (
Feature activation-0.001
Top resid features:
0
Token0
Feature activation-0.000
Top resid features:
AP
Token AP
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.053
Top resid features:
[
Token[
Feature activation+8.935
Top resid features:
Ed
TokenEd
Feature activation-0.003
Top resid features:
note
Token note
Feature activation+0.004
Top resid features:
:
Token:
Feature activation+0.299
Top resid features:
This
Token This
Feature activation+0.052
Top resid features:
article
Token article
Feature activation+0.007
Top resid features:
R
Token R
Feature activation+0.011
Top resid features:
umblr
Tokenumblr
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
[
Token[
Feature activation+8.856
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.014
Top resid features:
:
Token:
Feature activation+0.264
Top resid features:
It
Token It
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.006
Top resid features:
all
Token all
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ŀ
TokenĿ
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation-0.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
[
Token[
Feature activation+8.046
Top resid features:
Heat
TokenHeat
Feature activation+0.019
Top resid features:
âĢ
Token âĢ
Feature activation+0.150
Top resid features:
ĺ
Tokenĺ
Feature activation+0.039
Top resid features:
possibly
Tokenpossibly
Feature activation+0.045
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.009
Top resid features:
Ŀ
TokenĿ
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation-0.053
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
[
Token[
Feature activation+8.146
Top resid features:
Heat
TokenHeat
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.123
Top resid features:
ĺ
Tokenĺ
Feature activation+0.060
Top resid features:
possibly
Tokenpossibly
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
finish
Token finish
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.078
Top resid features:
[
Token[
Feature activation+8.317
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.030
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.001
Top resid features:
11
Token 11
Feature activation-0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
00
Token00
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation-0.001
Top resid features:
soccer
Token soccer
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.014
Top resid features:
[
Token[
Feature activation+8.488
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.275
Top resid features:
below
Token below
Feature activation+0.015
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:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.179
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
[
Token[
Feature activation+7.939
Top resid features:
RELATED
TokenRELATED
Feature activation+0.005
Top resid features:
:
Token:
Feature activation+0.228
Top resid features:
Arizona
Token Arizona
Feature activation+0.017
Top resid features:
considering
Token considering
Feature activation+0.118
Top resid features:
bill
Token bill
Feature activation+0.023
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.117
Top resid features:
âĢ
TokenâĢ
Feature activation-0.068
Top resid features:
Ŀ
TokenĿ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
[
Token[
Feature activation+7.953
Top resid features:
RELATED
TokenRELATED
Feature activation+0.008
Top resid features:
:
Token:
Feature activation+0.306
Top resid features:
Arizona
Token Arizona
Feature activation+0.005
Top resid features:
considering
Token considering
Feature activation+0.112
Top resid features:
bill
Token bill
Feature activation-0.005
Top resid features:
finish
Token finish
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.053
Top resid features:
[
Token[
Feature activation+8.186
Top resid features:
UPDATE
TokenUPDATE
Feature activation+0.020
Top resid features:
Wednesday
Token Wednesday
Feature activation-0.000
Top resid features:
11
Token 11
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
00
Token00
Feature activation+0.000
Top resid features:
since
Token since
Feature activation-0.004
Top resid features:
2006
Token 2006
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.053
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
[
Token[
Feature activation+7.931
Top resid features:
Viol
TokenViol
Feature activation+0.006
Top resid features:
ence
Tokenence
Feature activation+0.045
Top resid features:
is
Token is
Feature activation+0.075
Top resid features:
soaring
Token soaring
Feature activation+0.229
Top resid features:
in
Token in
Feature activation+0.075
Top resid features:
this
Token this
Feature activation-0.018
Top resid features:
fall
Token fall
Feature activation-0.033
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
[
Token[
Feature activation+7.580
Top resid features:
Say
TokenSay
Feature activation+0.020
Top resid features:
it
Token it
Feature activation+0.077
Top resid features:
with
Token with
Feature activation+0.024
Top resid features:
me
Token me
Feature activation+0.010
Top resid features:
:
Token:
Feature activation+0.256
Top resid features:
this
Token this
Feature activation-0.104
Top resid features:
fall
Token fall
Feature activation-0.086
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.055
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
[
Token[
Feature activation+7.549
Top resid features:
Say
TokenSay
Feature activation+0.060
Top resid features:
it
Token it
Feature activation+0.048
Top resid features:
with
Token with
Feature activation+0.044
Top resid features:
me
Token me
Feature activation-0.000
Top resid features:
:
Token:
Feature activation+0.226
Top resid features:
18
Token 18
Feature activation-0.001
Top resid features:
37
Token37
Feature activation+0.000
Top resid features:
.)
Token.)
Feature activation-0.064
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
[
Token[
Feature activation+8.131
Top resid features:
Aside
TokenAside
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.125
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
commodity
Token commodity
Feature activation+0.000
Top resid features:
prices
Token prices
Feature activation-0.012
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
opinion
Token opinion
Feature activation-0.001
Top resid features:
."
Token."
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
[
Token[
Feature activation+8.373
Top resid features:
RELATED
TokenRELATED
Feature activation+0.014
Top resid features:
:
Token:
Feature activation-0.102
Top resid features:
Students
Token Students
Feature activation+0.029
Top resid features:
fear
Token fear
Feature activation+0.006
Top resid features:
âĢ
Token âĢ
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.040
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
[
Token[
Feature activation+7.583
Top resid features:
An
TokenAn
Feature activation+0.001
Top resid features:
aside
Token aside
Feature activation+0.005
Top resid features:
:
Token:
Feature activation+0.258
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
them
Token them
Feature activation-0.004
Top resid features:
here
Token here
Feature activation-0.005
Top resid features:
?
Token?
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
[
Token[
Feature activation+7.520
Top resid features:
This
TokenThis
Feature activation+0.132
Top resid features:
paragraph
Token paragraph
Feature activation+0.097
Top resid features:
is
Token is
Feature activation+0.189
Top resid features:
obsolete
Token obsolete
Feature activation+0.123
Top resid features:
:]
Token:]
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.04

Head 3: 0.49

Head 4: 0.12

Head 5: 0.09

Head 6: 0.02

Head 7: 0.05

Head 8: 0.02

Head 9: 0.05

Head 10: 0.02

Head 11: 0.04

Positive logits

!]7.92

?]7.85

.]7.78

]7.64

...]7.53

]7.37

…]7.26

:]7.13

"]6.92

]"6.55

']6.23

][6.18

]:5.59

]'5.58

%]5.53

](5.53

]}5.49

][5.38

].5.34

]-5.30

Negative logits

));-5.92

)).-5.79

));-5.71

)),-5.39

),"-4.84

),-4.44

'),-4.41

"),-4.33

))-4.20

))-4.19

)-4.15

).-4.13

"))-4.09

").-4.08

");-4.06

).-4.05

)?-4.00

');-3.95

),-3.92

);-3.87

INTERVAL 8.225 - 9.139
CONTAINS 0.000%

on
Token on
Feature activation+0.000
March
Token March
Feature activation+0.000
2
Token 2
Feature activation+3.958
and
Token and
Feature activation+0.000
March
Token March
Feature activation+0.000
9
Token 9
Feature activation+8.307
to
Token to
Feature activation+0.000
reflect
Token reflect
Feature activation+0.335
new
Token new
Feature activation+0.000
information
Token information
Feature activation+7.993
given
Token given
Feature activation+1.918
unauthorized
Token unauthorized
Feature activation+0.000
clone
Token clone
Feature activation+7.374
of
Token of
Feature activation+0.338
the
Token the
Feature activation+0.000
old
Token old
Feature activation+1.477
site
Token site
Feature activation+9.139
and
Token and
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
involve
Token involve
Feature activation+0.000
any
Token any
Feature activation+0.000
be
Token be
Feature activation+1.013
a
Token a
Feature activation+0.000
creative
Token creative
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
gimmick
Token gimmick
Feature activation+7.617
here
Token here
Feature activation+8.504
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 7.311 - 8.225
CONTAINS 0.001%

It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.089
all
Token all
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
hoax
Token hoax
Feature activation+8.191
!
Token!
Feature activation+1.714
Read
Token Read
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
turned
Token turned
Feature activation+0.000
soccer
Token soccer
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
[
Token[
Feature activation+0.000
UPDATE
TokenUPDATE
Feature activation+0.881
below
Token below
Feature activation+7.335
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+1.013
a
Token a
Feature activation+0.000
creative
Token creative
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
gimmick
Token gimmick
Feature activation+7.617
here
Token here
Feature activation+8.504
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
ices
Tokenices
Feature activation+7.540
before
Token before
Feature activation+0.000
first
Token first
Feature activation+0.000
home
Token home
Feature activation+0.000
preseason
Token preseason
Feature activation+3.351
game
Token game
Feature activation+7.430
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
With
TokenWith
Feature activation+0.000
make
Token make
Feature activation+0.000
stand
Token stand
Feature activation+2.909
against
Token against
Feature activation+0.000
social
Token social
Feature activation+0.000
injust
Token injust
Feature activation+0.000
ices
Tokenices
Feature activation+7.540
before
Token before
Feature activation+0.000
first
Token first
Feature activation+0.000
home
Token home
Feature activation+0.000
preseason
Token preseason
Feature activation+3.351
game
Token game
Feature activation+7.430

INTERVAL 6.397 - 7.311
CONTAINS 0.001%

:
Token:
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
Donald
Token Donald
Feature activation+0.804
Trump
Token Trump
Feature activation+6.578
2
Token 2
Feature activation+4.818
.
Token.
Feature activation+0.000
0
Token0
Feature activation+6.631
!]
Token!]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
America
Token America
Feature activation+4.168
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.167
s
Tokens
Feature activation+0.000
heroin
Token heroin
Feature activation+3.688
habit
Token habit
Feature activation+6.727
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
fraught
Token fraught
Feature activation+0.000
when
Token when
Feature activation+0.000
Milo
Token Milo
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
CS
Token CS
Feature activation+0.000
UF
TokenUF
Feature activation+6.511
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ass
TokenAss
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
cite
Token cite
Feature activation+2.694
here
Token here
Feature activation+4.548
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
rough
Token rough
Feature activation+3.958
estimates
Token estimates
Feature activation+6.538
,
Token,
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
more
Token more
Feature activation+0.000
zones
Token zones
Feature activation+7.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.667
on
Token on
Feature activation+0.000
college
Token college
Feature activation+0.000
campuses
Token campuses
Feature activation+7.133
]
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

INTERVAL 5.483 - 6.397
CONTAINS 0.002%

more
Token more
Feature activation+0.000
-
Token-
Feature activation+0.000
or
Tokenor
Feature activation+0.000
-
Token-
Feature activation+0.000
less
Tokenless
Feature activation+0.000
correct
Token correct
Feature activation+6.291
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
August
Token August
Feature activation+0.000
2008
Token 2008
Feature activation+6.257
.
Token.
Feature activation+4.634
ON
Token ON
Feature activation+0.730
EGA
TokenEGA
Feature activation+5.704
ISH
TokenISH
Feature activation+0.000
IM
TokenIM
Feature activation+0.000
AS
TokenAS
Feature activation+0.000
U
TokenU
Feature activation+6.109
]
Token]
Feature activation+0.000
[
Token [
Feature activation+0.459
ãĤ
TokenãĤ
Feature activation+0.000
Ī
TokenĪ
Feature activation+0.000
ãĤ
TokenãĤ
Feature activation+0.000
this
Token this
Feature activation+0.000
presentation
Token presentation
Feature activation+6.238
in
Token in
Feature activation+0.000
Metro
Token Metro
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
x
Tokenx
Feature activation+5.541
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.561
new
Token new
Feature activation+0.000
black
Token black
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+1.465
rituals
Token rituals
Feature activation+5.050
into
Token into
Feature activation+0.000
sections
Token sections
Feature activation+5.810
exactly
Token exactly
Feature activation+1.414
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+2.878
(
Token (
Feature activation+0.000
See
Token See
Feature activation+0.529
the
Token the
Feature activation+0.000
table
Token table
Feature activation+5.973
at
Token at
Feature activation+0.198
the
Token the
Feature activation+0.000
end
Token end
Feature activation+6.114
for
Token for
Feature activation+0.000
references
Token references
Feature activation+5.488
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.031

INTERVAL 4.570 - 5.483
CONTAINS 0.002%

correct
Token correct
Feature activation+6.291
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
August
Token August
Feature activation+0.000
2008
Token 2008
Feature activation+6.257
.
Token.
Feature activation+4.634
See
Token See
Feature activation+0.529
the
Token the
Feature activation+0.000
table
Token table
Feature activation+5.973
at
Token at
Feature activation+0.198
the
Token the
Feature activation+0.000
!
Token!
Feature activation+1.714
Read
Token Read
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
turned
Token turned
Feature activation+0.000
out
Token out
Feature activation+4.653
to
Token to
Feature activation+0.000
be
Token be
Feature activation+1.013
a
Token a
Feature activation+0.000
creative
Token creative
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
UPDATE
TokenUPDATE
Feature activation+0.712
Wednesday
Token Wednesday
Feature activation+2.694
11
Token 11
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+3.567
am
Token am
Feature activation+5.125
CT
Token CT
Feature activation+6.238
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
story
Token story
Feature activation+0.000
has
Token has
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
Donald
Token Donald
Feature activation+0.804
Trump
Token Trump
Feature activation+6.578
2
Token 2
Feature activation+4.818
.
Token.
Feature activation+0.000
0
Token0
Feature activation+6.631
!]
Token!]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
home
Token home
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.989
](
Token](
Feature activation+0.000
http
Tokenhttp
Feature activation+0.000
://
Token://
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 3.656 - 4.570
CONTAINS 0.003%

for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
remainder
Token remainder
Feature activation+2.232
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
deck
Token deck
Feature activation+3.846
.
Token.
Feature activation+3.559
More
Token More
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.685
folly
Token folly
Feature activation+0.160
[
Token [
Feature activation+0.000
who
Tokenwho
Feature activation+0.071
gave
Token gave
Feature activation+0.840
them
Token them
Feature activation+0.963
the
Token the
Feature activation+0.000
infection
Token infection
Feature activation+3.718
].
Token].
Feature activation+0.000
Of
Token Of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
write
Tokenwrite
Feature activation+1.994
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
own
Token own
Feature activation+3.782
Modern
Token Modern
Feature activation+0.000
Mag
Token Mag
Feature activation+0.000
ick
Tokenick
Feature activation+0.671
,
Token,
Feature activation+0.392
complete
Token complete
Feature activation+0.000
new
Token new
Feature activation+0.000
brand
Token brand
Feature activation+2.759
/
Token/
Feature activation+0.000
log
Tokenlog
Feature activation+0.000
o
Tokeno
Feature activation+5.289
.
Token.
Feature activation+4.112
W
Token W
Feature activation+0.000
iser
Tokeniser
Feature activation+2.199
heads
Token heads
Feature activation+1.760
appear
Token appear
Feature activation+1.416
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
mail
Token mail
Feature activation+0.000
-
Token-
Feature activation+0.000
order
Tokenorder
Feature activation+0.000
teachings
Token teachings
Feature activation+4.047
and
Token and
Feature activation+0.000
found
Token found
Feature activation+0.751
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
percentage
Token percentage
Feature activation+2.501

INTERVAL 2.742 - 3.656
CONTAINS 0.005%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ready
Token ready
Feature activation+4.148
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
stand
Token stand
Feature activation+2.909
against
Token against
Feature activation+0.000
social
Token social
Feature activation+0.000
injust
Token injust
Feature activation+0.000
ices
Tokenices
Feature activation+7.540
before
Token before
Feature activation+0.000
.
Token.
Feature activation+0.000
Sam
Token Sam
Feature activation+0.000
u
Tokenu
Feature activation+0.000
els
Tokenels
Feature activation+1.788
Port
Token Port
Feature activation+0.000
rait
Tokenrait
Feature activation+2.759
Collection
Token Collection
Feature activation+3.322
at
Token at
Feature activation+0.000
Duke
Token Duke
Feature activation+1.244
University
Token University
Feature activation+4.537
.
Token.
Feature activation+2.748
[
Token[
Feature activation+0.000
via
Tokenvia
Feature activation+0.000
Uber
Token Uber
Feature activation+1.036
G
TokenG
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
mo
Tokenmo
Feature activation+3.108
]
Token]
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
gun
Token gun
Feature activation+0.000
fight
Tokenfight
Feature activation+0.000
rpm
Tokenrpm
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
le
Tokenle
Feature activation+0.000
o
Tokeno
Feature activation+3.284
@
Token@
Feature activation+0.000
dj
Tokendj
Feature activation+0.000
ango
Tokenango
Feature activation+0.458
~
Token~
Feature activation+0.000
]
Token]
Feature activation+0.000
el
Tokenel
Feature activation+3.558
]
Token]
Feature activation+0.000
[
Token [
Feature activation+0.000
Damn
TokenDamn
Feature activation+0.000
able
Tokenable
Feature activation+1.619
Pact
Token Pact
Feature activation+3.024
][
Token][
Feature activation+0.000
Ill
TokenIll
Feature activation+0.000
-
Token-
Feature activation+0.000
G
TokenG
Feature activation+0.000
otten
Tokenotten
Feature activation+1.361

INTERVAL 1.828 - 2.742
CONTAINS 0.007%

The
Token The
Feature activation+0.000
commodity
Token commodity
Feature activation+0.000
prices
Token prices
Feature activation+0.073
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
cite
Token cite
Feature activation+2.694
here
Token here
Feature activation+4.548
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
rough
Token rough
Feature activation+3.958
estimates
Token estimates
Feature activation+6.538
elected
Token elected
Feature activation+0.000
governments
Token governments
Feature activation+0.693
of
Token of
Feature activation+0.000
EU
Token EU
Feature activation+0.000
member
Token member
Feature activation+0.000
states
Token states
Feature activation+1.980
are
Token are
Feature activation+0.000
making
Token making
Feature activation+0.000
it
Token it
Feature activation+0.000
harder
Token harder
Feature activation+0.084
to
Token to
Feature activation+0.000
of
Tokenof
Feature activation+0.000
whether
Token whether
Feature activation+0.000
to
Token to
Feature activation+0.000
divul
Token divul
Feature activation+0.000
ge
Tokenge
Feature activation+0.082
information
Token information
Feature activation+2.171
].
Token].
Feature activation+0.000
Can
Token Can
Feature activation+0.000
you
Token you
Feature activation+0.000
explain
Token explain
Feature activation+0.000
?
Token?
Feature activation+0.000
9
Token 9
Feature activation+8.307
to
Token to
Feature activation+0.000
reflect
Token reflect
Feature activation+0.335
new
Token new
Feature activation+0.000
information
Token information
Feature activation+7.993
given
Token given
Feature activation+1.918
.]
Token.]
Feature activation+0.000
A
TokenA
Feature activation+0.000
new
Token new
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
is
Token is
Feature activation+0.000
[
Token[
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
via
Token via
Feature activation+0.264
David
Token David
Feature activation+0.000
Shank
Token Shank
Feature activation+0.000
bone
Tokenbone
Feature activation+2.685
/
Token/
Feature activation+0.000
Flickr
TokenFlickr
Feature activation+0.000
]
Token]
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
NEW
TokenNEW
Feature activation+0.000

INTERVAL 0.914 - 1.828
CONTAINS 0.017%

history
Token history
Feature activation+0.000
."
Token."
Feature activation+0.000
[
Token [
Feature activation+0.000
Part
TokenPart
Feature activation+0.000
isan
Tokenisan
Feature activation+0.000
Review
Token Review
Feature activation+0.974
,
Token,
Feature activation+0.000
Winter
Token Winter
Feature activation+0.000
1967
Token 1967
Feature activation+1.754
,
Token,
Feature activation+0.000
p
Token p
Feature activation+0.000
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+1.216
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
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+1.465
rituals
Token rituals
Feature activation+5.050
into
Token into
Feature activation+0.000
sections
Token sections
Feature activation+5.810
exactly
Token exactly
Feature activation+1.414
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+2.878
(
Token (
Feature activation+0.000
although
Tokenalthough
Feature activation+0.000
:
Token:
Feature activation+0.000
*
Token *
Feature activation+0.000
gr
Tokengr
Feature activation+0.000
inning
Tokeninning
Feature activation+0.000
but
Token but
Feature activation+0.000
saying
Token saying
Feature activation+0.921
nothing
Token nothing
Feature activation+0.402
*
Token*
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Customer
TokenCustomer
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
It
TokenIt
Feature activation+0.235
's
Token's
Feature activation+1.247
a
Token a
Feature activation+0.000
book
Token book
Feature activation+1.590
about
Token about
Feature activation+0.077
]
Token]
Feature activation+0.000
my
Token my
Feature activation+0.000

INTERVAL 0.000 - 0.914
CONTAINS 99.961%

harm
Token harm
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
I
Token I
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Russell
Token Russell
Feature activation+0.000
might
Token might
Feature activation+0.000
He
TokenHe
Feature activation+0.000
is
Token is
Feature activation+0.000
set
Token set
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
five
Token five
Feature activation+0.000
million
Token million
Feature activation+0.000
existing
Token existing
Feature activation+0.000
pension
Token pension
Feature activation+0.000
up
Token up
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
round
Token round
Feature activation+0.000
of
Token of
Feature activation+0.000
redist
Token redist
Feature activation+0.000
ricting
Tokenricting
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
government
Token government
Feature activation+0.000
should
Token should
Feature activation+0.000
stop
Token stop
Feature activation+0.000
railing
Token railing
Feature activation+0.000
against
Token against
Feature activation+0.000
encryption
Token encryption
Feature activation+0.000
and
Token and
Feature activation+0.000
should
Token should
Feature activation+0.000
support
Token support
Feature activation+0.000
strong
Token strong
Feature activation+0.000
crypto
Token crypto
Feature activation+0.000
Find
Token Find
Feature activation+0.000
lay
Tokenlay
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
overall
Token overall
Feature activation+0.000
pick
Token pick
Feature activation+0.000
.[
Token.[
Feature activation+0.000
15
Token15
Feature activation+0.115
]
Token]
Feature activation+0.000
Jerome
Token Jerome
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 H10.3: (feature 15077)

TOP ACTIVATIONS
MAX = 5.050

after
Token after
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
official
Token official
Feature activation+0.000
leaves
Token leaves
Feature activation+4.470
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+5.050
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
U
TokenU
Feature activation+0.000
.
Token.
Feature activation+0.000
Worst
Token Worst
Feature activation+0.000
Fast
Token Fast
Feature activation+0.000
-
Token-
Feature activation+0.000
Food
TokenFood
Feature activation+0.000
Me
Token Me
Feature activation+0.000
als
Tokenals
Feature activation+5.001
)
Token)
Feature activation+0.254
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.160
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
same
Token same
Feature activation+0.000
point
Token point
Feature activation+3.889
about
Token about
Feature activation+0.556
flat
Token flat
Feature activation+0.000
-
Token-
Feature activation+0.000
sharing
Tokensharing
Feature activation+4.938
in
Token in
Feature activation+0.000
books
Token books
Feature activation+4.026
âĢĵ
Token âĢĵ
Feature activation+0.374
is
Token is
Feature activation+0.000
it
Token it
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+0.363
favour
Token favour
Feature activation+4.872
of
Token of
Feature activation+0.000
sidewalks
Token sidewalks
Feature activation+4.496
on
Token on
Feature activation+0.274
both
Token both
Feature activation+2.213
sides
Token sides
Feature activation+4.007
book
Token book
Feature activation+3.435
Germany
Token Germany
Feature activation+0.000
18
Token 18
Feature activation+0.000
66
Token66
Feature activation+2.762
-
Token-
Feature activation+0.000
1945
Token1945
Feature activation+4.772
,
Token,
Feature activation+0.000
chapter
Token chapter
Feature activation+0.000
13
Token 13
Feature activation+4.469
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
of
Token of
Feature activation+0.000
mult
Token mult
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
acial
Tokenacial
Feature activation+0.000
people
Token people
Feature activation+4.496
interviewed
Token interviewed
Feature activation+4.678
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
states
Token states
Feature activation+4.399
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ever
Token ever
Feature activation+0.000
see
Token see
Feature activation+4.562
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
world
Token world
Feature activation+4.653
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
what
Tokenwhat
Feature activation+0.000
you
Token you
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
recall
Token recall
Feature activation+3.360
from
Token from
Feature activation+0.229
this
Token this
Feature activation+0.439
review
Token review
Feature activation+4.624
,
Token,
Feature activation+1.123
our
Token our
Feature activation+0.000
Master
Token Master
Feature activation+0.000
System
Token System
Feature activation+0.453
actually
Token actually
Feature activation+0.514
with
Token with
Feature activation+0.000
increased
Token increased
Feature activation+0.000
funding
Token funding
Feature activation+3.550
for
Token for
Feature activation+0.000
abstinence
Token abstinence
Feature activation+0.701
education
Token education
Feature activation+4.595
,
Token,
Feature activation+0.411
which
Token which
Feature activation+0.000
teaches
Token teaches
Feature activation+0.000
abstinence
Token abstinence
Feature activation+0.000
until
Token until
Feature activation+0.000
read
Token read
Feature activation+0.277
a
Token a
Feature activation+0.000
book
Token book
Feature activation+1.866
by
Token by
Feature activation+0.000
this
Token this
Feature activation+0.154
author
Token author
Feature activation+4.592
because
Token because
Feature activation+0.000
Token
Feature activation+0.423
________
Token________
Feature activation+0.092
____
Token____
Feature activation+2.554
âĢ
TokenâĢ
Feature activation+0.000
that
Tokenthat
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
ever
Token ever
Feature activation+0.000
see
Token see
Feature activation+4.562
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
world
Token world
Feature activation+4.653
.)
Token.)
Feature activation+0.000
of
Token of
Feature activation+0.572
these
Token these
Feature activation+3.928
see
Token see
Feature activation+1.832
Trainer
Token Trainer
Feature activation+3.417
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+4.520
),
Token),
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
deal
Token deal
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.248
avoiding
Token avoiding
Feature activation+0.000
ice
Token ice
Feature activation+0.562
-
Token-
Feature activation+0.000
storms
Tokenstorms
Feature activation+4.514
and
Token and
Feature activation+0.000
lic
Token lic
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ice
Tokenice
Feature activation+3.576
during
Token during
Feature activation+0.000
.
Token.
Feature activation+2.911
A
Token A
Feature activation+0.102
part
Token part
Feature activation+0.058
2
Token 2
Feature activation+2.900
is
Token is
Feature activation+0.384
forthcoming
Token forthcoming
Feature activation+4.510
.)
Token.)
Feature activation+1.096
Using
Token Using
Feature activation+0.000
the
Token the
Feature activation+0.000
leverage
Token leverage
Feature activation+0.000
of
Token of
Feature activation+0.000
's
Token's
Feature activation+0.000
time
Token time
Feature activation+3.945
to
Token to
Feature activation+0.000
dump
Token dump
Feature activation+1.559
your
Token your
Feature activation+0.000
doctor
Token doctor
Feature activation+4.496
.)
Token .)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+0.363
favour
Token favour
Feature activation+4.872
of
Token of
Feature activation+0.000
sidewalks
Token sidewalks
Feature activation+4.496
on
Token on
Feature activation+0.274
both
Token both
Feature activation+2.213
sides
Token sides
Feature activation+4.007
,
Token,
Feature activation+0.174
but
Token but
Feature activation+0.023
number
Token number
Feature activation+2.764
of
Token of
Feature activation+0.000
mult
Token mult
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
acial
Tokenacial
Feature activation+0.000
people
Token people
Feature activation+4.496
interviewed
Token interviewed
Feature activation+4.678
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
states
Token states
Feature activation+4.399
.)
Token.)
Feature activation+0.000
Vermont
Token Vermont
Feature activation+0.339
and
Token and
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.656
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
analyzed
Token analyzed
Feature activation+4.486
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
small
Token small
Feature activation+0.000
number
Token number
Feature activation+2.764
happen
Token happen
Feature activation+3.395
until
Token until
Feature activation+0.000
after
Token after
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
official
Token official
Feature activation+0.000
leaves
Token leaves
Feature activation+4.470
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+5.050
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.082
from
Token from
Feature activation+0.000
2008
Token 2008
Feature activation+2.527
,
Token,
Feature activation+1.042
says
Token says
Feature activation+2.316
,
Token,
Feature activation+4.469
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.241
We
TokenWe
Feature activation+0.000
renew
Token renew
Feature activation+0.000
our
Token our
Feature activation+0.000

Top DFA by src position
MAX = 5.397

serve
Token serve
Feature activation-0.001
Top resid features:
both
Token both
Feature activation-0.003
Top resid features:
national
Token national
Feature activation-0.000
Top resid features:
interests
Token interests
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
(
Token (
Feature activation+5.397
Top resid features:
This
TokenThis
Feature activation+0.008
Top resid features:
can
Token can
Feature activation+0.003
Top resid features:
't
Token't
Feature activation+0.029
Top resid features:
happen
Token happen
Feature activation+0.025
Top resid features:
until
Token until
Feature activation+0.023
Top resid features:
advertising
Token advertising
Feature activation+0.003
Top resid features:
practices
Token practices
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
(
Token(
Feature activation+5.041
Top resid features:
More
TokenMore
Feature activation+0.021
Top resid features:
on
Token on
Feature activation+0.014
Top resid features:
TIME
Token TIME
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
com
Tokencom
Feature activation+0.086
Top resid features:
few
Token few
Feature activation+0.005
Top resid features:
good
Token good
Feature activation+0.003
Top resid features:
men
Token men
Feature activation+0.029
Top resid features:
below
Token below
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
(
Token (
Feature activation+4.692
Top resid features:
Strange
TokenStrange
Feature activation+0.021
Top resid features:
ly
Tokenly
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.059
Top resid features:
I
Token I
Feature activation+0.009
Top resid features:
made
Token made
Feature activation+0.067
Top resid features:
built
Token built
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
following
Token following
Feature activation-0.002
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+5.063
Top resid features:
I
TokenI
Feature activation+0.058
Top resid features:
âĢ
TokenâĢ
Feature activation+0.059
Top resid features:
Ļ
TokenĻ
Feature activation+0.026
Top resid features:
m
Tokenm
Feature activation+0.054
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
(
Token (
Feature activation+4.964
Top resid features:
You
TokenYou
Feature activation+0.005
Top resid features:
can
Token can
Feature activation+0.012
Top resid features:
read
Token read
Feature activation+0.049
Top resid features:
Craig
Token Craig
Feature activation+0.030
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
state
Token state
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
level
Tokenlevel
Feature activation-0.012
Top resid features:
analysis
Token analysis
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
(
Token (
Feature activation+4.772
Top resid features:
Del
TokenDel
Feature activation-0.002
Top resid features:
aware
Tokenaware
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Montana
Token Montana
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
underneath
Token underneath
Feature activation+0.001
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
(
Token(
Feature activation+4.615
Top resid features:
some
Tokensome
Feature activation-0.000
Top resid features:
cheat
Token cheat
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
sheets
Tokensheets
Feature activation+0.006
Top resid features:
actually
Token actually
Feature activation+0.000
Top resid features:
Sega
Token Sega
Feature activation-0.001
Top resid features:
Master
Token Master
Feature activation-0.002
Top resid features:
System
Token System
Feature activation+0.001
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+4.659
Top resid features:
If
TokenIf
Feature activation-0.017
Top resid features:
you
Token you
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.069
Top resid features:
Ļ
TokenĻ
Feature activation+0.133
Top resid features:
ll
Tokenll
Feature activation-0.010
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
past
Token past
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+4.761
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
current
Token current
Feature activation-0.001
Top resid features:
platform
Token platform
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
t
Tokent
Feature activation+0.005
Top resid features:
read
Token read
Feature activation+0.001
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+4.596
Top resid features:
No
TokenNo
Feature activation+0.005
Top resid features:
really
Token really
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
go
Token go
Feature activation+0.001
Top resid features:
look
Token look
Feature activation+0.001
Top resid features:
underneath
Token underneath
Feature activation+0.009
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
(
Token(
Feature activation+4.713
Top resid features:
some
Tokensome
Feature activation-0.000
Top resid features:
cheat
Token cheat
Feature activation+0.009
Top resid features:
-
Token-
Feature activation+0.013
Top resid features:
sheets
Tokensheets
Feature activation+0.018
Top resid features:
actually
Token actually
Feature activation+0.000
Top resid features:
proposals
Token proposals
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
published
Token published
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
(
Token (
Feature activation+4.837
Top resid features:
For
TokenFor
Feature activation+0.010
Top resid features:
critical
Token critical
Feature activation-0.002
Top resid features:
analyses
Token analyses
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.002
Top resid features:
term
Token term
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
(
Token (
Feature activation+4.507
Top resid features:
However
TokenHowever
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
data
Token data
Feature activation+0.021
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
after
Token after
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
insurance
Token insurance
Feature activation+0.004
Top resid features:
companies
Token companies
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
(
Token (
Feature activation+4.650
Top resid features:
I
TokenI
Feature activation+0.016
Top resid features:
discussed
Token discussed
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
administ
Token administ
Feature activation-0.000
Top resid features:
ation
Tokenation
Feature activation+0.001
Top resid features:
severity
Token severity
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:
pain
Token pain
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
(
Token (
Feature activation+4.399
Top resid features:
Does
TokenDoes
Feature activation+0.001
Top resid features:
n
Tokenn
Feature activation+0.002
Top resid features:
't
Token't
Feature activation-0.000
Top resid features:
sound
Token sound
Feature activation-0.008
Top resid features:
like
Token like
Feature activation+0.005
Top resid features:
built
Token built
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
following
Token following
Feature activation-0.002
Top resid features:
year
Token year
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+4.552
Top resid features:
I
TokenI
Feature activation+0.119
Top resid features:
âĢ
TokenâĢ
Feature activation+0.031
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
m
Tokenm
Feature activation+0.058
Top resid features:
in
Token in
Feature activation+0.029
Top resid features:
state
Token state
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
level
Tokenlevel
Feature activation-0.006
Top resid features:
analysis
Token analysis
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
(
Token (
Feature activation+4.395
Top resid features:
Del
TokenDel
Feature activation-0.008
Top resid features:
aware
Tokenaware
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Montana
Token Montana
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
state
Token state
Feature activation+0.009
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
level
Tokenlevel
Feature activation-0.014
Top resid features:
analysis
Token analysis
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
(
Token (
Feature activation+4.892
Top resid features:
Del
TokenDel
Feature activation-0.000
Top resid features:
aware
Tokenaware
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Montana
Token Montana
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
serve
Token serve
Feature activation-0.005
Top resid features:
both
Token both
Feature activation-0.007
Top resid features:
national
Token national
Feature activation-0.002
Top resid features:
interests
Token interests
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
(
Token (
Feature activation+5.029
Top resid features:
This
TokenThis
Feature activation+0.020
Top resid features:
can
Token can
Feature activation+0.006
Top resid features:
't
Token't
Feature activation+0.036
Top resid features:
happen
Token happen
Feature activation+0.029
Top resid features:
until
Token until
Feature activation+0.013
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
past
Token past
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
(
Token (
Feature activation+4.850
Top resid features:
The
TokenThe
Feature activation+0.015
Top resid features:
current
Token current
Feature activation+0.012
Top resid features:
platform
Token platform
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
from
Token from
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.49

Head 4: 0.14

Head 5: 0.13

Head 6: 0.02

Head 7: 0.02

Head 8: 0.02

Head 9: 0.07

Head 10: 0.02

Head 11: 0.02

Positive logits

.")7.83

.)7.66

.)7.27

...)5.91

…)5.68

!)5.67

?)5.12

,)4.25

)4.16

.):3.82

')3.74

")3.51

)"3.47

?)3.45

/)3.34

-)3.21

+)3.15

)3.13

*)3.07

)2.96

Negative logits

"],-4.68

],"-4.61

],-4.43

],-4.05

]);-3.98

]),-3.93

>,-3.75

":{"-3.73

]:-3.52

];-3.52

].-3.49

]).-3.38

\",-3.29

`.-3.26

\":-3.20

]}-3.17

"},-3.16

>.-3.14

`,-3.09

};-3.06

INTERVAL 4.545 - 5.050
CONTAINS 0.001%

book
Token book
Feature activation+3.435
Germany
Token Germany
Feature activation+0.000
18
Token 18
Feature activation+0.000
66
Token66
Feature activation+2.762
-
Token-
Feature activation+0.000
1945
Token1945
Feature activation+4.772
,
Token,
Feature activation+0.000
chapter
Token chapter
Feature activation+0.000
13
Token 13
Feature activation+4.469
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
same
Token same
Feature activation+0.000
point
Token point
Feature activation+3.889
about
Token about
Feature activation+0.556
flat
Token flat
Feature activation+0.000
-
Token-
Feature activation+0.000
sharing
Tokensharing
Feature activation+4.938
in
Token in
Feature activation+0.000
books
Token books
Feature activation+4.026
âĢĵ
Token âĢĵ
Feature activation+0.374
is
Token is
Feature activation+0.000
it
Token it
Feature activation+0.000
that
Tokenthat
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
ever
Token ever
Feature activation+0.000
see
Token see
Feature activation+4.562
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
world
Token world
Feature activation+4.653
.)
Token.)
Feature activation+0.000
with
Token with
Feature activation+0.000
increased
Token increased
Feature activation+0.000
funding
Token funding
Feature activation+3.550
for
Token for
Feature activation+0.000
abstinence
Token abstinence
Feature activation+0.701
education
Token education
Feature activation+4.595
,
Token,
Feature activation+0.411
which
Token which
Feature activation+0.000
teaches
Token teaches
Feature activation+0.000
abstinence
Token abstinence
Feature activation+0.000
until
Token until
Feature activation+0.000
after
Token after
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
official
Token official
Feature activation+0.000
leaves
Token leaves
Feature activation+4.470
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+5.050
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
U
TokenU
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 4.040 - 4.545
CONTAINS 0.004%

complete
Token complete
Feature activation+0.000
explanation
Token explanation
Feature activation+3.593
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.000
factors
Token factors
Feature activation+4.135
that
Token that
Feature activation+0.000
determine
Token determine
Feature activation+0.000
fair
Token fair
Feature activation+0.000
use
Token use
Feature activation+4.432
:
Token:
Feature activation+3.191
(
Token (
Feature activation+0.104
Hey
TokenHey
Feature activation+0.374
there
Token there
Feature activation+0.350
,
Token,
Feature activation+0.000
Rod
Token Rod
Feature activation+0.000
Stewart
Token Stewart
Feature activation+4.461
.)
Token.)
Feature activation+0.000
But
Token But
Feature activation+0.000
art
Token art
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.687
t
Tokent
Feature activation+0.009
scratch
Token scratch
Feature activation+4.359
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
try
Token try
Feature activation+3.004
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
.
Token.
Feature activation+2.911
A
Token A
Feature activation+0.102
part
Token part
Feature activation+0.058
2
Token 2
Feature activation+2.900
is
Token is
Feature activation+0.384
forthcoming
Token forthcoming
Feature activation+4.510
.)
Token.)
Feature activation+1.096
Using
Token Using
Feature activation+0.000
the
Token the
Feature activation+0.000
leverage
Token leverage
Feature activation+0.000
of
Token of
Feature activation+0.000
number
Token number
Feature activation+2.764
of
Token of
Feature activation+0.000
mult
Token mult
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
acial
Tokenacial
Feature activation+0.000
people
Token people
Feature activation+4.496
interviewed
Token interviewed
Feature activation+4.678
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
states
Token states
Feature activation+4.399
.)
Token.)
Feature activation+0.000

INTERVAL 3.535 - 4.040
CONTAINS 0.011%

than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
knockout
Token knockout
Feature activation+1.500
-
Token-
Feature activation+0.000
style
Tokenstyle
Feature activation+2.354
bracket
Token bracket
Feature activation+3.638
used
Token used
Feature activation+1.433
today
Token today
Feature activation+3.373
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
is
Token is
Feature activation+3.814
,
Token,
Feature activation+0.075
looking
Token looking
Feature activation+0.093
over
Token over
Feature activation+0.796
the
Token the
Feature activation+0.000
figures
Token figures
Feature activation+3.579
,
Token,
Feature activation+0.202
making
Token making
Feature activation+0.000
notes
Token notes
Feature activation+3.224
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+3.772
is
Token is
Feature activation+0.000
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
40
Token40
Feature activation+3.767
).
Token).
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
(
Token (
Feature activation+0.000
Image
TokenImage
Feature activation+0.111
credit
Token credit
Feature activation+0.905
:
Token:
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
Webb
Token Webb
Feature activation+3.660
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Deep
TokenDeep
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
standard
Token standard
Feature activation+2.959
of
Token of
Feature activation+0.000
behavior
Token behavior
Feature activation+4.171
.
Token.
Feature activation+2.975
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.621
)
Token)
Feature activation+0.269
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
UST
TokenUST
Feature activation+0.000
IN
TokenIN
Feature activation+0.000

INTERVAL 3.030 - 3.535
CONTAINS 0.013%

Matthew
TokenMatthew
Feature activation+0.000
18
Token 18
Feature activation+1.872
:
Token:
Feature activation+0.000
21
Token 21
Feature activation+3.004
-
Token-
Feature activation+0.000
22
Token22
Feature activation+3.252
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
App
TokenApp
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ause
Tokenause
Feature activation+3.321
)
Token)
Feature activation+0.000
(
Token (
Feature activation+0.000
C
TokenC
Feature activation+0.000
rowd
Tokenrowd
Feature activation+0.000
chanting
Token chanting
Feature activation+3.334
ant
Tokenant
Feature activation+0.000
farmer
Token farmer
Feature activation+0.000
".
Token".
Feature activation+0.000
(
Token (
Feature activation+0.000
What
TokenWhat
Feature activation+0.148
?
Token?
Feature activation+3.099
Maybe
Token Maybe
Feature activation+2.250
those
Token those
Feature activation+0.675
were
Token were
Feature activation+0.261
the
Token the
Feature activation+0.093
hack
Token hack
Feature activation+0.000
see
Token see
Feature activation+0.739
below
Token below
Feature activation+3.444
it
Token it
Feature activation+3.133
an
Token an
Feature activation+0.000
Other
Token Other
Feature activation+0.390
folder
Token folder
Feature activation+3.108
that
Token that
Feature activation+0.000
drops
Token drops
Feature activation+0.226
down
Token down
Feature activation+2.674
.)
Token.)
Feature activation+0.088
That
Token That
Feature activation+0.000
read
Token read
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
No
TokenNo
Feature activation+0.000
really
Token really
Feature activation+3.332
,
Token,
Feature activation+1.023
go
Token go
Feature activation+0.537
look
Token look
Feature activation+0.494
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.525 - 3.030
CONTAINS 0.013%

(
Token(
Feature activation+0.000
More
TokenMore
Feature activation+0.303
on
Token on
Feature activation+0.000
TIME
Token TIME
Feature activation+1.002
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.831
:
Token:
Feature activation+0.000
See
Token See
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
10
Token 10
Feature activation+0.000
technically
Token technically
Feature activation+0.080
came
Token came
Feature activation+0.000
in
Token in
Feature activation+0.275
the
Token the
Feature activation+0.000
stage
Token stage
Feature activation+2.718
directly
Token directly
Feature activation+2.739
preceding
Token preceding
Feature activation+0.802
the
Token the
Feature activation+0.000
final
Token final
Feature activation+3.509
,
Token,
Feature activation+1.025
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
given
Token given
Feature activation+0.000
a
Token a
Feature activation+0.000
contract
Token contract
Feature activation+1.504
extension
Token extension
Feature activation+2.707
Sunday
Token Sunday
Feature activation+2.632
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Consider
TokenConsider
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
issue
Token issue
Feature activation+2.043
of
Token of
Feature activation+0.000
Four
Token Four
Feature activation+0.000
Four
TokenFour
Feature activation+0.000
Two
TokenTwo
Feature activation+2.557
magazine
Token magazine
Feature activation+3.062
.
Token.
Feature activation+1.094
Subscribe
Token Subscribe
Feature activation+1.994
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
more
Token more
Feature activation+1.459
details
Token details
Feature activation+2.745
at
Token at
Feature activation+0.847
the
Token the
Feature activation+0.000
Icelandic
Token Icelandic
Feature activation+0.000
Wikipedia
Token Wikipedia
Feature activation+3.244
page
Token page
Feature activation+3.691

INTERVAL 2.020 - 2.525
CONTAINS 0.009%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
49
Token 49
Feature activation+0.000
ers
Tokeners
Feature activation+2.440
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
given
Token given
Feature activation+0.000
a
Token a
Feature activation+0.000
contract
Token contract
Feature activation+1.504
hours
Token hours
Feature activation+0.534
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.073
Bass
Token Bass
Feature activation+0.000
ano
Tokenano
Feature activation+2.494
recalls
Token recalls
Feature activation+2.818
.
Token.
Feature activation+1.421
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.621
I
TokenI
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
More
TokenMore
Feature activation+1.965
on
Token on
Feature activation+0.442
Whit
Token Whit
Feature activation+0.000
ewater
Tokenewater
Feature activation+2.226
,
Token,
Feature activation+0.783
WI
Token WI
Feature activation+3.248
PD
Token PD
Feature activation+2.252
here
Token here
Feature activation+3.904
.)
Token.)
Feature activation+0.129
travellers
Token travellers
Feature activation+0.000
'
Token'
Feature activation+0.000
edition
Token edition
Feature activation+3.061
single
Token single
Feature activation+0.688
malt
Token malt
Feature activation+0.828
whisky
Token whisky
Feature activation+2.043
?
Token?
Feature activation+1.044
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.497
Ċ
TokenĊ
Feature activation+0.573
Ċ
TokenĊ
Feature activation+0.471
-
Token-
Feature activation+0.000
powered
Tokenpowered
Feature activation+1.055
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.000
strong
Token strong
Feature activation+0.000
feet
Token feet
Feature activation+2.223
).
Token).
Feature activation+0.000
In
Token In
Feature activation+0.000
areas
Token areas
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.515 - 2.020
CONTAINS 0.012%

the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
4
Token4
Feature activation+1.881
-
Token-
Feature activation+0.000
5
Token5
Feature activation+3.192
).
Token).
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
ipped
Tokenipped
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
see
Token see
Feature activation+0.904
pictures
Token pictures
Feature activation+1.747
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
Nine
TokenNine
Feature activation+0.000
Fish
Token Fish
Feature activation+0.651
With
Token With
Feature activation+0.000
.
Token.
Feature activation+3.529
Pun
Token Pun
Feature activation+0.000
itive
Tokenitive
Feature activation+1.478
one
Token one
Feature activation+1.988
-
Token-
Feature activation+0.000
star
Tokenstar
Feature activation+1.675
reviews
Token reviews
Feature activation+3.782
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
reviewers
Token reviewers
Feature activation+0.028
down
Token down
Feature activation+0.000
history
Token history
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Read
TokenRead
Feature activation+0.034
-
Token-
Feature activation+0.000
More
TokenMore
Feature activation+1.666
)
Token)
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Scientists
TokenScientists
Feature activation+0.000
have
Token have
Feature activation+0.000
compiled
Token compiled
Feature activation+0.000
(
Token (
Feature activation+0.000
A
TokenA
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+0.000
leaning
Tokenleaning
Feature activation+0.000
critic
Token critic
Feature activation+1.726
of
Token of
Feature activation+0.000
Moore
Token Moore
Feature activation+1.348
summed
Token summed
Feature activation+0.000
up
Token up
Feature activation+0.240
the
Token the
Feature activation+0.000

INTERVAL 1.010 - 1.515
CONTAINS 0.015%

there
Token there
Feature activation+0.672
has
Token has
Feature activation+1.064
been
Token been
Feature activation+2.534
that
Token that
Feature activation+3.393
use
Token use
Feature activation+3.453
,
Token,
Feature activation+1.505
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.490
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.278
spokesman
Token spokesman
Feature activation+0.000
story
Token story
Feature activation+0.000
book
Tokenbook
Feature activation+0.000
sports
Token sports
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
shit
Token shit
Feature activation+0.000
right
Token right
Feature activation+1.037
there
Token there
Feature activation+0.000
folks
Token folks
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
ema
Tokenema
Feature activation+0.000
Me
Token Me
Feature activation+0.000
ht
Tokenht
Feature activation+0.000
a
Tokena
Feature activation+1.864
contributed
Token contributed
Feature activation+3.868
to
Token to
Feature activation+1.172
this
Token this
Feature activation+2.384
report
Token report
Feature activation+4.146
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.290
t
Tokent
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
in
Token in
Feature activation+0.000
time
Token time
Feature activation+1.404
for
Token for
Feature activation+0.000
today
Token today
Feature activation+1.924
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.926
s
Tokens
Feature activation+0.000
ency
Tokenency
Feature activation+2.248
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+2.267
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.298
The
TokenThe
Feature activation+0.000
Basics
Token Basics
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000

INTERVAL 0.505 - 1.010
CONTAINS 0.033%

(
Token (
Feature activation+0.000
In
TokenIn
Feature activation+0.000
fact
Token fact
Feature activation+1.117
,
Token,
Feature activation+0.000
penn
Token penn
Feature activation+0.000
ies
Tokenies
Feature activation+0.827
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.308
t
Tokent
Feature activation+0.000
been
Token been
Feature activation+0.000
language
Token language
Feature activation+1.679
?
Token?
Feature activation+1.298
Can
Token Can
Feature activation+0.000
I
Token I
Feature activation+0.000
borrow
Token borrow
Feature activation+0.000
structures
Token structures
Feature activation+0.962
without
Token without
Feature activation+0.000
fatal
Token fatal
Feature activation+0.000
interference
Token interference
Feature activation+3.002
like
Token like
Feature activation+0.000
Portuguese
Token Portuguese
Feature activation+1.872
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
sit
Token sit
Feature activation+0.000
without
Token without
Feature activation+0.000
support
Token support
Feature activation+0.758
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
equ
Token equ
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
to
Token to
Feature activation+0.000
analyses
Token analyses
Feature activation+2.769
of
Token of
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
dozen
Token dozen
Feature activation+1.760
of
Token of
Feature activation+0.572
these
Token these
Feature activation+3.928
see
Token see
Feature activation+1.832
Trainer
Token Trainer
Feature activation+3.417
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+4.520
structure
Token structure
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
this
Token this
Feature activation+0.000
day
Token day
Feature activation+0.000
and
Token and
Feature activation+0.640
age
Token age
Feature activation+0.000
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
,
Token,
Feature activation+0.000
young
Token young
Feature activation+0.000

INTERVAL 0.000 - 0.505
CONTAINS 99.890%

that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Congress
TokenCongress
Feature activation+0.000
has
Token has
Feature activation+0.000
always
Token always
Feature activation+0.000
--
Token --
Feature activation+0.000
let
Token let
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.000
put
Token put
Feature activation+0.000
'
Token'
Feature activation+0.000
options
Token options
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
allows
Token allows
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
easily
Token easily
Feature activation+0.000
search
Token search
Feature activation+0.000
for
Token for
Feature activation+0.000
information
Token information
Feature activation+0.000
Review
Token Review
Feature activation+0.000
-
Token-
Feature activation+0.000
Journal
TokenJournal
Feature activation+0.000
Follow
Token Follow
Feature activation+0.000
@
Token @
Feature activation+0.000
cs
Tokencs
Feature activation+0.000
ste
Tokenste
Feature activation+0.000
ven
Tokenven
Feature activation+0.000
s
Tokens
Feature activation+0.000
photo
Tokenphoto
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
house
Token house
Feature activation+0.000
of
Token of
Feature activation+0.000
worship
Token worship
Feature activation+0.000
?
Token?
Feature activation+0.000
Or
Token Or
Feature activation+0.000
toes
Token toes
Feature activation+0.000
?
Token?
Feature activation+0.000
Or
Token Or
Feature activation+0.000
some
Token some
Feature activation+0.000
glimpse
Token glimpse
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