H5.10 top features

Top feature 0 in H5.10: (feature 17535)

TOP ACTIVATIONS
MAX = 4.196

the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.869
and
Token and
Feature activation+0.000
heroes
Token heroes
Feature activation+0.417
of
Token of
Feature activation+0.000
9
Token 9
Feature activation+4.196
/
Token/
Feature activation+3.603
11
Token11
Feature activation+0.052
,
Token,
Feature activation+0.618
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
knowledge
Tokenknowledge
Feature activation+0.785
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.901
September
Token September
Feature activation+2.360
11
Token 11
Feature activation+2.175
attacks
Token attacks
Feature activation+4.193
in
Token in
Feature activation+2.532
the
Token the
Feature activation+1.786
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
in
Token in
Feature activation+1.587
anniversary
Token anniversary
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.227
terrorist
Token terrorist
Feature activation+4.050
attacks
Token attacks
Feature activation+3.683
.
Token.
Feature activation+0.000
Nearly
Token Nearly
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+1.757
in
Token in
Feature activation+1.125
the
Token the
Feature activation+2.142
terrorist
Token terrorist
Feature activation+3.901
attacks
Token attacks
Feature activation+3.926
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
,
Token,
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+1.757
in
Token in
Feature activation+1.125
the
Token the
Feature activation+2.142
terrorist
Token terrorist
Feature activation+3.901
attacks
Token attacks
Feature activation+3.926
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.176
,
Token,
Feature activation+1.974
2012
Token 2012
Feature activation+0.551
attack
Token attack
Feature activation+3.885
--
Token --
Feature activation+0.000
despite
Token despite
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
prior
Token prior
Feature activation+0.000
jihadist
Token jihadist
Feature activation+0.344
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.875
,
Token,
Feature activation+1.999
2001
Token 2001
Feature activation+3.310
attacks
Token attacks
Feature activation+3.761
were
Token were
Feature activation+2.296
divine
Token divine
Feature activation+0.000
punishment
Token punishment
Feature activation+0.242
for
Token for
Feature activation+0.000
legal
Token legal
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.227
terrorist
Token terrorist
Feature activation+4.050
attacks
Token attacks
Feature activation+3.683
.
Token.
Feature activation+0.000
Nearly
Token Nearly
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
victims
Token victims
Feature activation+0.869
and
Token and
Feature activation+0.000
heroes
Token heroes
Feature activation+0.417
of
Token of
Feature activation+0.000
9
Token 9
Feature activation+4.196
/
Token/
Feature activation+3.603
11
Token11
Feature activation+0.052
,
Token,
Feature activation+0.618
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.160
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.050
11
Token11
Feature activation+0.015
was
Token was
Feature activation+3.471
one
Token one
Feature activation+2.597
of
Token of
Feature activation+0.428
the
Token the
Feature activation+1.801
biggest
Token biggest
Feature activation+1.987
cataly
Token cataly
Feature activation+0.146
ere
Tokenere
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
On
TokenOn
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+3.412
,
Token,
Feature activation+1.937
2001
Token 2001
Feature activation+2.371
,
Token,
Feature activation+0.900
Lt
Token Lt
Feature activation+0.000
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.875
,
Token,
Feature activation+1.999
2001
Token 2001
Feature activation+3.310
attacks
Token attacks
Feature activation+3.761
were
Token were
Feature activation+2.296
divine
Token divine
Feature activation+0.000
punishment
Token punishment
Feature activation+0.242
for
Token for
Feature activation+0.000
had
Token had
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.181
planned
Token planned
Feature activation+2.737
attack
Token attack
Feature activation+3.116
methods
Token methods
Feature activation+1.941
,
Token,
Feature activation+0.012
the
Token the
Feature activation+0.000
precise
Token precise
Feature activation+0.123
volume
Token volume
Feature activation+0.343
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Letter
TokenLetter
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
11
Token 11
Feature activation+3.076
th
Tokenth
Feature activation+1.560
anniversary
Token anniversary
Feature activation+1.140
of
Token of
Feature activation+1.073
9
Token 9
Feature activation+2.020
/
Token/
Feature activation+1.983
of
Token of
Feature activation+0.000
Cont
Token Cont
Feature activation+0.000
rollers
Tokenrollers
Feature activation+0.000
on
Token on
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.986
,
Token,
Feature activation+0.889
18
Token 18
Feature activation+0.000
49
Token49
Feature activation+0.000
,
Token,
Feature activation+0.000
authorized
Token authorized
Feature activation+0.000
for
Token for
Feature activation+0.000
considering
Token considering
Feature activation+0.000
what
Token what
Feature activation+0.000
happened
Token happened
Feature activation+0.787
on
Token on
Feature activation+2.477
9
Token 9
Feature activation+2.889
/
Token/
Feature activation+1.769
11
Token11
Feature activation+0.116
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
conclusion
Token conclusion
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
11
Token 11
Feature activation+2.234
,
Token,
Feature activation+2.745
2013
Token 2013
Feature activation+0.000
,
Token,
Feature activation+0.000
motorcycle
Token motorcycle
Feature activation+0.000
convoy
Token convoy
Feature activation+0.472
into
Token into
Feature activation+0.000
Forces
Token Forces
Feature activation+0.000
had
Token had
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.181
planned
Token planned
Feature activation+2.737
attack
Token attack
Feature activation+3.116
methods
Token methods
Feature activation+1.941
,
Token,
Feature activation+0.012
the
Token the
Feature activation+0.000
precise
Token precise
Feature activation+0.123
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
World
Token World
Feature activation+0.000
Trade
Token Trade
Feature activation+0.000
Center
Token Center
Feature activation+2.726
in
Token in
Feature activation+1.220
Bahrain
Token Bahrain
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
instance
Token instance
Feature activation+0.000
federal
Token federal
Feature activation+0.000
officials
Token officials
Feature activation+0.000
insisted
Token insisted
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.104
terrorists
Token terrorists
Feature activation+2.641
'
Token'
Feature activation+0.599
method
Token method
Feature activation+0.104
of
Token of
Feature activation+0.000
operation
Token operation
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000

Top DFA by src position
MAX = 4.959

th
Tokenth
Feature activation+0.007
Top resid features:
anniversary
Token anniversary
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
September
Token September
Feature activation+0.024
Top resid features:
11
Token 11
Feature activation+4.553
Top resid features:
terrorist
Token terrorist
Feature activation+0.007
Top resid features:
attacks
Token attacks
Feature activation+0.106
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Nearly
Token Nearly
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
There
TokenThere
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.036
Top resid features:
The
TokenThe
Feature activation-0.008
Top resid features:
9
Token 9
Feature activation+0.016
Top resid features:
/
Token/
Feature activation+0.007
Top resid features:
11
Token11
Feature activation+2.917
Top resid features:
advance
Token advance
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
knowledge
Tokenknowledge
Feature activation+0.001
Top resid features:
conspiracy
Token conspiracy
Feature activation+0.003
Top resid features:
theories
Token theories
Feature activation+0.004
Top resid features:
th
Tokenth
Feature activation-0.003
Top resid features:
anniversary
Token anniversary
Feature activation+0.004
Top resid features:
of
Token of
Feature activation-0.021
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
September
Token September
Feature activation+0.041
Top resid features:
11
Token 11
Feature activation+4.959
Top resid features:
terrorist
Token terrorist
Feature activation-0.092
Top resid features:
attacks
Token attacks
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Nearly
Token Nearly
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation-0.000
Top resid features:
anniversary
Token anniversary
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
September
Token September
Feature activation+0.012
Top resid features:
11
Token 11
Feature activation+3.350
Top resid features:
terrorist
Token terrorist
Feature activation+0.015
Top resid features:
attacks
Token attacks
Feature activation+0.219
Top resid features:
.
Token.
Feature activation-0.061
Top resid features:
Nearly
Token Nearly
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation+0.000
Top resid features:
anniversary
Token anniversary
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
September
Token September
Feature activation+0.016
Top resid features:
11
Token 11
Feature activation+2.292
Top resid features:
terrorist
Token terrorist
Feature activation+0.028
Top resid features:
attacks
Token attacks
Feature activation+0.072
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
Nearly
Token Nearly
Feature activation-0.000
Top resid features:
3
Token 3
Feature activation-0.000
Top resid features:
more
Token more
Feature activation-0.003
Top resid features:
security
Token security
Feature activation-0.003
Top resid features:
before
Token before
Feature activation+0.043
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
September
Token September
Feature activation-0.008
Top resid features:
11
Token 11
Feature activation+4.572
Top resid features:
,
Token,
Feature activation-0.044
Top resid features:
2012
Token 2012
Feature activation+0.002
Top resid features:
attack
Token attack
Feature activation+0.021
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
despite
Token despite
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.008
Top resid features:
claimed
Token claimed
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.029
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
September
Token September
Feature activation-0.002
Top resid features:
11
Token 11
Feature activation+4.183
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
2001
Token 2001
Feature activation+0.211
Top resid features:
attacks
Token attacks
Feature activation+0.116
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
divine
Token divine
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation-0.005
Top resid features:
anniversary
Token anniversary
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.024
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
September
Token September
Feature activation+0.006
Top resid features:
11
Token 11
Feature activation+4.590
Top resid features:
terrorist
Token terrorist
Feature activation-0.147
Top resid features:
attacks
Token attacks
Feature activation+0.061
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Nearly
Token Nearly
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation+0.003
Top resid features:
anniversary
Token anniversary
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
September
Token September
Feature activation+0.044
Top resid features:
11
Token 11
Feature activation+3.484
Top resid features:
terrorist
Token terrorist
Feature activation+0.060
Top resid features:
attacks
Token attacks
Feature activation+0.159
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Nearly
Token Nearly
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation-0.000
Top resid features:
:
Token:
Feature activation-0.005
Top resid features:
I
Token I
Feature activation-0.013
Top resid features:
believe
Token believe
Feature activation-0.006
Top resid features:
9
Token 9
Feature activation+0.061
Top resid features:
/
Token/
Feature activation+0.024
Top resid features:
11
Token11
Feature activation+4.071
Top resid features:
was
Token was
Feature activation+0.142
Top resid features:
one
Token one
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:
biggest
Token biggest
Feature activation+0.000
Top resid features:
ere
Tokenere
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.045
Top resid features:
On
TokenOn
Feature activation-0.052
Top resid features:
September
Token September
Feature activation+0.110
Top resid features:
11
Token 11
Feature activation+4.106
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2001
Token 2001
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Lt
Token Lt
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.004
Top resid features:
claimed
Token claimed
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
September
Token September
Feature activation+0.009
Top resid features:
11
Token 11
Feature activation+3.934
Top resid features:
,
Token,
Feature activation-0.143
Top resid features:
2001
Token 2001
Feature activation+0.254
Top resid features:
attacks
Token attacks
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
divine
Token divine
Feature activation+0.000
Top resid features:
There
TokenThere
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.080
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
9
Token 9
Feature activation+0.020
Top resid features:
/
Token/
Feature activation+0.009
Top resid features:
11
Token11
Feature activation+1.686
Top resid features:
advance
Token advance
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
knowledge
Tokenknowledge
Feature activation+0.004
Top resid features:
conspiracy
Token conspiracy
Feature activation+0.006
Top resid features:
theories
Token theories
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
objectively
Token objectively
Feature activation+0.000
Top resid features:
examine
Token examine
Feature activation-0.000
Top resid features:
9
Token 9
Feature activation+0.019
Top resid features:
/
Token/
Feature activation+0.007
Top resid features:
11
Token11
Feature activation+1.656
Top resid features:
from
Token from
Feature activation+0.014
Top resid features:
different
Token different
Feature activation-0.002
Top resid features:
perspectives
Token perspectives
Feature activation+0.001
Top resid features:
while
Token while
Feature activation+0.003
Top resid features:
fostering
Token fostering
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
Cont
Token Cont
Feature activation+0.005
Top resid features:
rollers
Tokenrollers
Feature activation+0.011
Top resid features:
on
Token on
Feature activation+0.121
Top resid features:
September
Token September
Feature activation+0.147
Top resid features:
11
Token 11
Feature activation+3.428
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
18
Token 18
Feature activation+0.000
Top resid features:
49
Token49
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
authorized
Token authorized
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
happened
Token happened
Feature activation+0.005
Top resid features:
at
Token at
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
WTC
Token WTC
Feature activation+3.132
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
direct
Token direct
Feature activation+0.000
Top resid features:
contradiction
Token contradiction
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
organizer
Token organizer
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Sept
Token Sept
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
11
Token 11
Feature activation+3.470
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
2013
Token 2013
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
motorcycle
Token motorcycle
Feature activation+0.000
Top resid features:
convoy
Token convoy
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.045
Top resid features:
good
Token good
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
departed
Token departed
Feature activation+0.003
Top resid features:
Trayvon
Token Trayvon
Feature activation+0.010
Top resid features:
world
Token world
Feature activation-0.020
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
World
Token World
Feature activation-0.057
Top resid features:
Trade
Token Trade
Feature activation-0.246
Top resid features:
Center
Token Center
Feature activation+3.796
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Bahrain
Token Bahrain
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
instance
Token instance
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.177
Top resid features:
September
Token September
Feature activation+0.007
Top resid features:
11
Token 11
Feature activation+2.851
Top resid features:
attacks
Token attacks
Feature activation+0.323
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
all
Token all
Feature activation+0.002
Top resid features:
high
Token high
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.05

Head 4: 0.03

Head 5: 0.04

Head 6: 0.03

Head 7: 0.03

Head 8: 0.03

Head 9: 0.07

Head 10: 0.53

Head 11: 0.10

Positive logits

faked2.19

hoax2.15

bombing1.91

perpetrated1.82

bombings1.82

detonated1.80

debris1.78

wrecked1.75

anniversary1.74

Doomsday1.69

catastrophe1.68

disaster1.68

massacre1.68

disasters1.66

hijacked1.65

devastated1.65

airliner1.64

wreckage1.64

carnage1.63

fallout1.63

Negative logits

Ability-1.86

BuyableInstoreAndOnline-1.79

Skill-1.68

Fior-1.65

)=(-1.61

Ingredients-1.61

Magikarp-1.59

-1.57

Chan-1.57

-1.57

Wild-1.55

Agg-1.54

Parser-1.53

Allows-1.52

utic-1.52

ynt-1.49

Cooldown-1.49

colleg-1.47

Senegal-1.45

Skill-1.45

INTERVAL 3.776 - 4.196
CONTAINS 0.001%

knowledge
Tokenknowledge
Feature activation+0.785
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.901
September
Token September
Feature activation+2.360
11
Token 11
Feature activation+2.175
attacks
Token attacks
Feature activation+4.193
in
Token in
Feature activation+2.532
the
Token the
Feature activation+1.786
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
in
Token in
Feature activation+1.587
the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.869
and
Token and
Feature activation+0.000
heroes
Token heroes
Feature activation+0.417
of
Token of
Feature activation+0.000
9
Token 9
Feature activation+4.196
/
Token/
Feature activation+3.603
11
Token11
Feature activation+0.052
,
Token,
Feature activation+0.618
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.176
,
Token,
Feature activation+1.974
2012
Token 2012
Feature activation+0.551
attack
Token attack
Feature activation+3.885
--
Token --
Feature activation+0.000
despite
Token despite
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
prior
Token prior
Feature activation+0.000
jihadist
Token jihadist
Feature activation+0.344
anniversary
Token anniversary
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.227
terrorist
Token terrorist
Feature activation+4.050
attacks
Token attacks
Feature activation+3.683
.
Token.
Feature activation+0.000
Nearly
Token Nearly
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+1.757
in
Token in
Feature activation+1.125
the
Token the
Feature activation+2.142
terrorist
Token terrorist
Feature activation+3.901
attacks
Token attacks
Feature activation+3.926
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.356 - 3.776
CONTAINS 0.001%

ere
Tokenere
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
On
TokenOn
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+3.412
,
Token,
Feature activation+1.937
2001
Token 2001
Feature activation+2.371
,
Token,
Feature activation+0.900
Lt
Token Lt
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.227
terrorist
Token terrorist
Feature activation+4.050
attacks
Token attacks
Feature activation+3.683
.
Token.
Feature activation+0.000
Nearly
Token Nearly
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
victims
Token victims
Feature activation+0.869
and
Token and
Feature activation+0.000
heroes
Token heroes
Feature activation+0.417
of
Token of
Feature activation+0.000
9
Token 9
Feature activation+4.196
/
Token/
Feature activation+3.603
11
Token11
Feature activation+0.052
,
Token,
Feature activation+0.618
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.160
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.050
11
Token11
Feature activation+0.015
was
Token was
Feature activation+3.471
one
Token one
Feature activation+2.597
of
Token of
Feature activation+0.428
the
Token the
Feature activation+1.801
biggest
Token biggest
Feature activation+1.987
cataly
Token cataly
Feature activation+0.146
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.875
,
Token,
Feature activation+1.999
2001
Token 2001
Feature activation+3.310
attacks
Token attacks
Feature activation+3.761
were
Token were
Feature activation+2.296
divine
Token divine
Feature activation+0.000
punishment
Token punishment
Feature activation+0.242
for
Token for
Feature activation+0.000
legal
Token legal
Feature activation+0.000

INTERVAL 2.937 - 3.356
CONTAINS 0.001%

of
Token of
Feature activation+0.000
Cont
Token Cont
Feature activation+0.000
rollers
Tokenrollers
Feature activation+0.000
on
Token on
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.986
,
Token,
Feature activation+0.889
18
Token 18
Feature activation+0.000
49
Token49
Feature activation+0.000
,
Token,
Feature activation+0.000
authorized
Token authorized
Feature activation+0.000
had
Token had
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.181
planned
Token planned
Feature activation+2.737
attack
Token attack
Feature activation+3.116
methods
Token methods
Feature activation+1.941
,
Token,
Feature activation+0.012
the
Token the
Feature activation+0.000
precise
Token precise
Feature activation+0.123
volume
Token volume
Feature activation+0.343
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Letter
TokenLetter
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
11
Token 11
Feature activation+3.076
th
Tokenth
Feature activation+1.560
anniversary
Token anniversary
Feature activation+1.140
of
Token of
Feature activation+1.073
9
Token 9
Feature activation+2.020
/
Token/
Feature activation+1.983
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.875
,
Token,
Feature activation+1.999
2001
Token 2001
Feature activation+3.310
attacks
Token attacks
Feature activation+3.761
were
Token were
Feature activation+2.296
divine
Token divine
Feature activation+0.000
punishment
Token punishment
Feature activation+0.242
for
Token for
Feature activation+0.000

INTERVAL 2.517 - 2.937
CONTAINS 0.001%

world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
World
Token World
Feature activation+0.000
Trade
Token Trade
Feature activation+0.000
Center
Token Center
Feature activation+2.726
in
Token in
Feature activation+1.220
Bahrain
Token Bahrain
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
instance
Token instance
Feature activation+0.000
believe
Token believe
Feature activation+0.000
9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.050
11
Token11
Feature activation+0.015
was
Token was
Feature activation+3.471
one
Token one
Feature activation+2.597
of
Token of
Feature activation+0.428
the
Token the
Feature activation+1.801
biggest
Token biggest
Feature activation+1.987
cataly
Token cataly
Feature activation+0.146
sts
Tokensts
Feature activation+0.793
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.901
September
Token September
Feature activation+2.360
11
Token 11
Feature activation+2.175
attacks
Token attacks
Feature activation+4.193
in
Token in
Feature activation+2.532
the
Token the
Feature activation+1.786
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
in
Token in
Feature activation+1.587
2001
Token 2001
Feature activation+2.440
A
TokenA
Feature activation+0.000
decade
Token decade
Feature activation+0.000
after
Token after
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+2.638
,
Token,
Feature activation+2.586
Osama
Token Osama
Feature activation+0.000
Bin
Token Bin
Feature activation+0.000
Laden
Token Laden
Feature activation+0.002
was
Token was
Feature activation+0.449
not
Token not
Feature activation+0.000
Forces
Token Forces
Feature activation+0.000
had
Token had
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.181
planned
Token planned
Feature activation+2.737
attack
Token attack
Feature activation+3.116
methods
Token methods
Feature activation+1.941
,
Token,
Feature activation+0.012
the
Token the
Feature activation+0.000
precise
Token precise
Feature activation+0.123

INTERVAL 2.098 - 2.517
CONTAINS 0.002%

the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+1.757
in
Token in
Feature activation+1.125
the
Token the
Feature activation+2.142
terrorist
Token terrorist
Feature activation+3.901
attacks
Token attacks
Feature activation+3.926
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.875
,
Token,
Feature activation+1.999
2001
Token 2001
Feature activation+3.310
attacks
Token attacks
Feature activation+3.761
were
Token were
Feature activation+2.296
divine
Token divine
Feature activation+0.000
punishment
Token punishment
Feature activation+0.242
for
Token for
Feature activation+0.000
legal
Token legal
Feature activation+0.000
abortion
Token abortion
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
WTC
Token WTC
Feature activation+0.834
Building
Token Building
Feature activation+1.800
7
Token 7
Feature activation+2.419
was
Token was
Feature activation+2.002
not
Token not
Feature activation+1.145
hit
Token hit
Feature activation+1.428
by
Token by
Feature activation+1.024
an
Token an
Feature activation+0.508
attack
Token attack
Feature activation+0.000
on
Token on
Feature activation+0.339
the
Token the
Feature activation+0.000
World
Token World
Feature activation+0.000
Trade
Token Trade
Feature activation+0.000
Centre
Token Centre
Feature activation+2.299
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
for
Token for
Feature activation+0.000
considering
Token considering
Feature activation+0.000
what
Token what
Feature activation+0.000
happened
Token happened
Feature activation+0.787
on
Token on
Feature activation+2.477
9
Token 9
Feature activation+2.889
/
Token/
Feature activation+1.769
11
Token11
Feature activation+0.116
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000

INTERVAL 1.678 - 2.098
CONTAINS 0.003%

security
Token security
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
11
Token 11
Feature activation+1.176
,
Token,
Feature activation+1.974
2012
Token 2012
Feature activation+0.551
attack
Token attack
Feature activation+3.885
--
Token --
Feature activation+0.000
despite
Token despite
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
9
Token9
Feature activation+2.026
-
Token-
Feature activation+0.289
11
Token11
Feature activation+0.915
Pentagon
Token Pentagon
Feature activation+1.819
De
Token De
Feature activation+0.000
bris
Tokenbris
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
represent
Token represent
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
died
Token died
Feature activation+1.757
in
Token in
Feature activation+1.125
the
Token the
Feature activation+2.142
terrorist
Token terrorist
Feature activation+3.901
attacks
Token attacks
Feature activation+3.926
.
Token.
Feature activation+0.000
cell
Token cell
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Paris
Token Paris
Feature activation+0.000
attacks
Token attacks
Feature activation+1.736
may
Token may
Feature activation+0.000
still
Token still
Feature activation+0.000
be
Token be
Feature activation+0.000
at
Token at
Feature activation+0.000
large
Token large
Feature activation+0.000
photo
Token photo
Feature activation+0.000
plainly
Token plainly
Feature activation+0.000
labeled
Token labeled
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
9
Token9
Feature activation+2.026
-
Token-
Feature activation+0.289
11
Token11
Feature activation+0.915
Pentagon
Token Pentagon
Feature activation+1.819
De
Token De
Feature activation+0.000
bris
Tokenbris
Feature activation+0.000

INTERVAL 1.259 - 1.678
CONTAINS 0.004%

Ċ
TokenĊ
Feature activation+0.000
Letter
TokenLetter
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
11
Token 11
Feature activation+3.076
th
Tokenth
Feature activation+1.560
anniversary
Token anniversary
Feature activation+1.140
of
Token of
Feature activation+1.073
9
Token 9
Feature activation+2.020
/
Token/
Feature activation+1.983
11
Token11
Feature activation+0.000
a
Token a
Feature activation+0.000
full
Token full
Feature activation+0.152
explanation
Token explanation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.655
collapse
Token collapse
Feature activation+1.560
of
Token of
Feature activation+0.341
WTC
Token WTC
Feature activation+0.389
1
Token 1
Feature activation+1.635
and
Token and
Feature activation+0.469
2
Token 2
Feature activation+1.489
000
Token000
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
who
Token who
Feature activation+0.161
were
Token were
Feature activation+0.475
slaughtered
Token slaughtered
Feature activation+1.208
by
Token by
Feature activation+1.524
them
Token them
Feature activation+0.456
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
adopted
Token adopted
Feature activation+0.000
the
Token the
Feature activation+0.000
curriculum
Token curriculum
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
9
Token 9
Feature activation+1.359
/
Token/
Feature activation+1.132
11
Token11
Feature activation+0.000
seminar
Token seminar
Feature activation+0.000
is
Token is
Feature activation+0.000
taught
Token taught
Feature activation+0.000
recalled
Token recalled
Feature activation+0.000
last
Token last
Feature activation+0.000
fall
Token fall
Feature activation+0.000
's
Token's
Feature activation+0.000
terror
Token terror
Feature activation+0.203
attacks
Token attacks
Feature activation+1.284
in
Token in
Feature activation+0.671
which
Token which
Feature activation+0.616
two
Token two
Feature activation+0.036
lone
Token lone
Feature activation+0.241
-
Token-
Feature activation+0.000

INTERVAL 0.839 - 1.259
CONTAINS 0.011%

executive
Token executive
Feature activation+0.000
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Anne
Token Anne
Feature activation+0.000
Frank
Token Frank
Feature activation+1.110
Centre
Token Centre
Feature activation+0.000
for
Token for
Feature activation+0.000
Mutual
Token Mutual
Feature activation+0.000
Respect
Token Respect
Feature activation+0.000
.
Token.
Feature activation+0.000
shield
Token shield
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.053
Death
Token Death
Feature activation+0.000
Star
Token Star
Feature activation+0.947
and
Token and
Feature activation+0.920
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
turn
Token turn
Feature activation+0.000
,
Token,
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.053
Death
Token Death
Feature activation+0.000
Star
Token Star
Feature activation+0.947
and
Token and
Feature activation+0.920
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
turn
Token turn
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.082
1
Token 1
Feature activation+2.125
and
Token and
Feature activation+1.009
2
Token 2
Feature activation+1.786
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
aircraft
Token aircraft
Feature activation+1.065
impact
Token impact
Feature activation+0.147
damage
Token damage
Feature activation+0.000
combined
Token combined
Feature activation+0.000
with
Token with
Feature activation+0.000
intense
Token intense
Feature activation+0.000
investigating
Token investigating
Feature activation+0.000
the
Token the
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
Benghazi
Token Benghazi
Feature activation+0.064
terrorist
Token terrorist
Feature activation+0.813
attack
Token attack
Feature activation+1.052
given
Token given
Feature activation+0.000
House
Token House
Feature activation+0.000
Majority
Token Majority
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
Kevin
Token Kevin
Feature activation+0.000

INTERVAL 0.420 - 0.839
CONTAINS 0.030%

9
Token 9
Feature activation+0.000
/
Token/
Feature activation+0.050
11
Token11
Feature activation+0.015
was
Token was
Feature activation+3.471
one
Token one
Feature activation+2.597
of
Token of
Feature activation+0.428
the
Token the
Feature activation+1.801
biggest
Token biggest
Feature activation+1.987
cataly
Token cataly
Feature activation+0.146
sts
Tokensts
Feature activation+0.793
for
Token for
Feature activation+0.000
help
Token help
Feature activation+0.000
improve
Token improve
Feature activation+0.000
community
Token community
Feature activation+0.000
relations
Token relations
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.469
conflict
Token conflict
Feature activation+1.479
's
Token's
Feature activation+0.897
cent
Token cent
Feature activation+0.000
enary
Tokenenary
Feature activation+0.000
.
Token.
Feature activation+0.000
mission
Token mission
Feature activation+0.000
:
Token:
Feature activation+0.000
bring
Token bring
Feature activation+0.000
down
Token down
Feature activation+0.217
United
Token United
Feature activation+0.169
93
Token 93
Feature activation+0.510
.
Token.
Feature activation+0.587
She
Token She
Feature activation+0.000
took
Token took
Feature activation+0.000
off
Token off
Feature activation+0.000
from
Token from
Feature activation+0.000
released
Token released
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
shooter
Token shooter
Feature activation+0.156
Omar
Token Omar
Feature activation+0.708
Mate
Token Mate
Feature activation+0.000
en
Tokenen
Feature activation+0.652
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.508
Ċ
TokenĊ
Feature activation+0.000
Correction
TokenCorrection
Feature activation+0.000
:
Token:
Feature activation+0.000
Lan
Token Lan
Feature activation+0.800
za
Tokenza
Feature activation+0.878
killed
Token killed
Feature activation+0.646
20
Token 20
Feature activation+0.000
children
Token children
Feature activation+0.000
and
Token and
Feature activation+0.000
six
Token six
Feature activation+0.000
adults
Token adults
Feature activation+0.000

INTERVAL 0.000 - 0.420
CONTAINS 99.949%

E
TokenE
Feature activation+0.000
mpire
Tokenmpire
Feature activation+0.000
State
Token State
Feature activation+0.000
Building
Token Building
Feature activation+0.145
su
Token su
Feature activation+0.000
es
Tokenes
Feature activation+0.000
photographer
Token photographer
Feature activation+0.000
for
Token for
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
him
Token him
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
love
Token love
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
his
Token his
Feature activation+0.000
guy
Token guy
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
day
Tokenday
Feature activation+0.000
Saints
Token Saints
Feature activation+0.000
has
Token has
Feature activation+0.000
sat
Token sat
Feature activation+0.000
next
Token next
Feature activation+0.000
door
Token door
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
Center
Token Center
Feature activation+0.000
for
Token for
Feature activation+0.000
re
Tokenre
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
thing
Token thing
Feature activation+0.000
for
Token for
Feature activation+0.000
10
Token 10
Feature activation+0.000
years
Token years
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
are
Token are
Feature activation+0.000
truly
Token truly
Feature activation+0.000
great
Token great
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
bad
Token bad
Feature activation+0.000
:
Token:
Feature activation+0.000
Love
Token Love
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H5.10: (feature 10053)

TOP ACTIVATIONS
MAX = 3.278

19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
died
Token died
Feature activation+0.000
when
Token when
Feature activation+0.000
police
Token police
Feature activation+0.000
opened
Token opened
Feature activation+3.278
fire
Token fire
Feature activation+1.375
on
Token on
Feature activation+1.383
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
she
Token she
Feature activation+0.000
:
Token:
Feature activation+0.000
34
Token34
Feature activation+0.000
]
Token]
Feature activation+0.000
Gotham
Token Gotham
Feature activation+0.000
police
Token police
Feature activation+0.821
are
Token are
Feature activation+2.945
on
Token on
Feature activation+2.593
B
Token B
Feature activation+0.107
anes
Tokenanes
Feature activation+0.000
payroll
Token payroll
Feature activation+1.002
Ċ
TokenĊ
Feature activation+0.000
phone
Token phone
Feature activation+0.000
was
Token was
Feature activation+0.000
broken
Token broken
Feature activation+0.000
and
Token and
Feature activation+0.000
officers
Token officers
Feature activation+1.683
were
Token were
Feature activation+2.917
not
Token not
Feature activation+0.675
successful
Token successful
Feature activation+1.251
in
Token in
Feature activation+1.478
retrieving
Token retrieving
Feature activation+0.931
any
Token any
Feature activation+0.000
Chief
Token Chief
Feature activation+1.626
Larry
Token Larry
Feature activation+1.656
Smith
Token Smith
Feature activation+0.481
said
Token said
Feature activation+0.953
his
Token his
Feature activation+1.122
officers
Token officers
Feature activation+2.865
balanced
Token balanced
Feature activation+0.867
the
Token the
Feature activation+0.342
right
Token right
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+2.740
're
Token're
Feature activation+1.594
trying
Token trying
Feature activation+0.561
to
Token to
Feature activation+1.085
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Metropolitan
Token Metropolitan
Feature activation+0.179
police
Token police
Feature activation+0.000
's
Token's
Feature activation+2.724
road
Token road
Feature activation+0.021
death
Token death
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
unit
Token unit
Feature activation+1.353
is
Token is
Feature activation+1.285
burgl
Token burgl
Feature activation+0.000
aries
Tokenaries
Feature activation+0.504
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.043
officer
Token officer
Feature activation+1.594
did
Token did
Feature activation+2.677
not
Token not
Feature activation+1.912
initially
Token initially
Feature activation+0.114
chase
Token chase
Feature activation+1.091
him
Token him
Feature activation+0.992
,
Token,
Feature activation+0.308
showed
Token showed
Feature activation+0.000
Shelby
Token Shelby
Feature activation+0.647
and
Token and
Feature activation+0.647
several
Token several
Feature activation+0.161
other
Token other
Feature activation+0.664
officers
Token officers
Feature activation+2.657
surrounding
Token surrounding
Feature activation+0.970
Cr
Token Cr
Feature activation+0.210
ut
Tokenut
Feature activation+0.000
cher
Tokencher
Feature activation+0.184
as
Token as
Feature activation+0.200
is
Token is
Feature activation+0.000
suspected
Token suspected
Feature activation+0.000
of
Token of
Feature activation+0.000
killing
Token killing
Feature activation+0.000
C
Token C
Feature activation+0.000
pl
Tokenpl
Feature activation+2.635
.
Token.
Feature activation+1.483
Bry
Token Bry
Feature activation+0.000
on
Tokenon
Feature activation+0.000
D
Token D
Feature activation+0.168
ickson
Tokenickson
Feature activation+0.000
concluded
Token concluded
Feature activation+0.264
that
Token that
Feature activation+0.542
Tracy
Token Tracy
Feature activation+0.945
violated
Token violated
Feature activation+1.446
five
Token five
Feature activation+0.280
department
Token department
Feature activation+2.610
al
Tokenal
Feature activation+1.186
policies
Token policies
Feature activation+0.535
.
Token.
Feature activation+0.246
It
Token It
Feature activation+0.060
found
Token found
Feature activation+0.481
34
Token34
Feature activation+0.000
]
Token]
Feature activation+0.000
Gotham
Token Gotham
Feature activation+0.000
police
Token police
Feature activation+0.821
are
Token are
Feature activation+2.945
on
Token on
Feature activation+2.593
B
Token B
Feature activation+0.107
anes
Tokenanes
Feature activation+0.000
payroll
Token payroll
Feature activation+1.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
giving
Token giving
Feature activation+0.000
local
Token local
Feature activation+0.000
cops
Token cops
Feature activation+0.884
the
Token the
Feature activation+1.918
ability
Token ability
Feature activation+2.069
to
Token to
Feature activation+2.552
inquire
Token inquire
Feature activation+1.045
about
Token about
Feature activation+0.729
a
Token a
Feature activation+0.253
person
Token person
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
violence
Token violence
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+1.504
looking
Token looking
Feature activation+2.479
for
Token for
Feature activation+1.723
12
Token 12
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
be
Token be
Feature activation+0.000
successful
Token successful
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
officer
Token officer
Feature activation+2.453
used
Token used
Feature activation+2.466
the
Token the
Feature activation+0.796
new
Token new
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.207
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.143
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
successful
Token successful
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
officer
Token officer
Feature activation+2.453
used
Token used
Feature activation+2.466
the
Token the
Feature activation+0.796
new
Token new
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.207
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.481
The
Token The
Feature activation+0.252
âĢ
Token âĢ
Feature activation+0.073
ľ
Tokenľ
Feature activation+0.000
offic
Tokenoffic
Feature activation+1.429
ers
Tokeners
Feature activation+2.430
were
Token were
Feature activation+1.783
informed
Token informed
Feature activation+0.323
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.782
they
Token they
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+2.427
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
here
Token here
Feature activation+0.866
and
Token and
Feature activation+0.000
March
Token March
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
police
Token police
Feature activation+0.181
responded
Token responded
Feature activation+2.201
to
Token to
Feature activation+2.397
a
Token a
Feature activation+0.348
call
Token call
Feature activation+0.615
from
Token from
Feature activation+0.216
a
Token a
Feature activation+0.360
Brooklyn
Token Brooklyn
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Police
TokenPolice
Feature activation+0.042
added
Token added
Feature activation+2.381
that
Token that
Feature activation+0.659
2016
Token 2016
Feature activation+0.000
saw
Token saw
Feature activation+0.000
135
Token 135
Feature activation+0.000
days
Token days
Feature activation+0.000
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.737
Ċ
TokenĊ
Feature activation+0.013
Ċ
TokenĊ
Feature activation+0.108
"
Token"
Feature activation+1.407
We
TokenWe
Feature activation+2.358
investigated
Token investigated
Feature activation+1.156
and
Token and
Feature activation+0.204
determined
Token determined
Feature activation+0.340
who
Token who
Feature activation+0.000
the
Token the
Feature activation+0.205

Top DFA by src position
MAX = 3.725

,
Token,
Feature activation-0.005
Top resid features:
19
Token 19
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
died
Token died
Feature activation+0.001
Top resid features:
when
Token when
Feature activation+0.002
Top resid features:
police
Token police
Feature activation+3.725
Top resid features:
opened
Token opened
Feature activation-0.082
Top resid features:
fire
Token fire
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
4
Token4
Feature activation+0.006
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
34
Token34
Feature activation+0.003
Top resid features:
]
Token]
Feature activation+0.012
Top resid features:
Gotham
Token Gotham
Feature activation+0.023
Top resid features:
police
Token police
Feature activation+3.179
Top resid features:
are
Token are
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
anes
Tokenanes
Feature activation+0.000
Top resid features:
payroll
Token payroll
Feature activation+0.000
Top resid features:
Her
Token Her
Feature activation-0.007
Top resid features:
phone
Token phone
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.017
Top resid features:
broken
Token broken
Feature activation-0.023
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
officers
Token officers
Feature activation+3.508
Top resid features:
were
Token were
Feature activation-0.156
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
successful
Token successful
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
retrieving
Token retrieving
Feature activation+0.000
Top resid features:
Chief
Token Chief
Feature activation+0.008
Top resid features:
Larry
Token Larry
Feature activation-0.013
Top resid features:
Smith
Token Smith
Feature activation-0.004
Top resid features:
said
Token said
Feature activation+0.006
Top resid features:
his
Token his
Feature activation-0.004
Top resid features:
officers
Token officers
Feature activation+1.613
Top resid features:
balanced
Token balanced
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
right
Token right
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:
on
Token on
Feature activation-0.000
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation-0.000
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
Westminster
Token Westminster
Feature activation+0.003
Top resid features:
police
Token police
Feature activation+2.318
Top resid features:
Sgt
Token Sgt
Feature activation+0.775
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Dar
Token Dar
Feature activation+0.004
Top resid features:
in
Tokenin
Feature activation-0.000
Top resid features:
Up
Token Up
Feature activation+0.000
Top resid features:
."
Token."
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
The
TokenThe
Feature activation-0.013
Top resid features:
Metropolitan
Token Metropolitan
Feature activation+0.034
Top resid features:
police
Token police
Feature activation+2.680
Top resid features:
's
Token's
Feature activation-0.088
Top resid features:
road
Token road
Feature activation+0.000
Top resid features:
death
Token death
Feature activation+0.000
Top resid features:
investigation
Token investigation
Feature activation+0.000
Top resid features:
unit
Token unit
Feature activation+0.000
Top resid features:
residential
Token residential
Feature activation+0.002
Top resid features:
burgl
Token burgl
Feature activation+0.027
Top resid features:
aries
Tokenaries
Feature activation+0.036
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
The
TokenThe
Feature activation-0.034
Top resid features:
officer
Token officer
Feature activation+3.050
Top resid features:
did
Token did
Feature activation-0.013
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
initially
Token initially
Feature activation+0.000
Top resid features:
chase
Token chase
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
shot
Token shot
Feature activation+0.027
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
killed
Token killed
Feature activation-0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Officer
Token Officer
Feature activation+2.664
Top resid features:
Betty
Token Betty
Feature activation-0.021
Top resid features:
Shelby
Token Shelby
Feature activation+0.018
Top resid features:
as
Token as
Feature activation+0.011
Top resid features:
she
Token she
Feature activation+0.001
Top resid features:
responded
Token responded
Feature activation+0.120
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
initial
Token initial
Feature activation-0.000
Top resid features:
search
Token search
Feature activation+0.011
Top resid features:
area
Token area
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Police
Token Police
Feature activation+1.252
Top resid features:
reported
Token reported
Feature activation+0.002
Top resid features:
no
Token no
Feature activation-0.001
Top resid features:
confirmed
Token confirmed
Feature activation-0.001
Top resid features:
sightings
Token sightings
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
actions
Token actions
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Salt
Token Salt
Feature activation+0.004
Top resid features:
Lake
Token Lake
Feature activation+0.004
Top resid features:
City
Token City
Feature activation+0.005
Top resid features:
Police
Token Police
Feature activation+1.861
Top resid features:
officers
Token officers
Feature activation+0.588
Top resid features:
Detective
Token Detective
Feature activation+0.056
Top resid features:
Jeff
Token Jeff
Feature activation+0.000
Top resid features:
Payne
Token Payne
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
4
Token4
Feature activation+0.006
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
34
Token34
Feature activation+0.002
Top resid features:
]
Token]
Feature activation+0.016
Top resid features:
Gotham
Token Gotham
Feature activation+0.007
Top resid features:
police
Token police
Feature activation+2.836
Top resid features:
are
Token are
Feature activation+0.085
Top resid features:
on
Token on
Feature activation+0.016
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
anes
Tokenanes
Feature activation+0.000
Top resid features:
payroll
Token payroll
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
last
Token last
Feature activation-0.001
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
giving
Token giving
Feature activation-0.003
Top resid features:
local
Token local
Feature activation+0.007
Top resid features:
cops
Token cops
Feature activation+2.927
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
ability
Token ability
Feature activation-0.018
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
inquire
Token inquire
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
crying
Token crying
Feature activation-0.000
Top resid features:
."
Token."
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Police
TokenPolice
Feature activation+2.310
Top resid features:
have
Token have
Feature activation+0.022
Top resid features:
arrested
Token arrested
Feature activation+0.660
Top resid features:
six
Token six
Feature activation+0.005
Top resid features:
men
Token men
Feature activation-0.006
Top resid features:
suspected
Token suspected
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
successful
Token successful
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
one
Token one
Feature activation-0.030
Top resid features:
officer
Token officer
Feature activation+2.958
Top resid features:
used
Token used
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
knowledge
Token knowledge
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
successful
Token successful
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.005
Top resid features:
one
Token one
Feature activation-0.012
Top resid features:
officer
Token officer
Feature activation+2.118
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
knowledge
Token knowledge
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
which
Token which
Feature activation+0.002
Top resid features:
radio
Token radio
Feature activation+0.005
Top resid features:
ed
Tokened
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
officers
Token officers
Feature activation+1.710
Top resid features:
to
Token to
Feature activation-0.029
Top resid features:
look
Token look
Feature activation+0.026
Top resid features:
into
Token into
Feature activation+0.016
Top resid features:
Norton
Token Norton
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Dep
TokenDep
Feature activation+0.005
Top resid features:
uty
Tokenuty
Feature activation+0.113
Top resid features:
Durham
Token Durham
Feature activation+0.012
Top resid features:
Police
Token Police
Feature activation+2.092
Top resid features:
Chief
Token Chief
Feature activation+0.312
Top resid features:
Larry
Token Larry
Feature activation+0.002
Top resid features:
Smith
Token Smith
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+0.026
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.047
Top resid features:
In
TokenIn
Feature activation-0.004
Top resid features:
March
Token March
Feature activation+0.003
Top resid features:
2012
Token 2012
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
police
Token police
Feature activation+2.125
Top resid features:
responded
Token responded
Feature activation+0.684
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
call
Token call
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
last
Token last
Feature activation-0.010
Top resid features:
year
Token year
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Police
TokenPolice
Feature activation+2.648
Top resid features:
added
Token added
Feature activation+0.141
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
2016
Token 2016
Feature activation+0.000
Top resid features:
saw
Token saw
Feature activation+0.000
Top resid features:
135
Token 135
Feature activation+0.000
Top resid features:
traffic
Token traffic
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
said
Token said
Feature activation-0.008
Top resid features:
CH
Token CH
Feature activation+0.018
Top resid features:
P
TokenP
Feature activation+0.088
Top resid features:
Officer
Token Officer
Feature activation+2.075
Top resid features:
Tony
Token Tony
Feature activation+0.003
Top resid features:
Pol
Token Pol
Feature activation+0.002
Top resid features:
izz
Tokenizz
Feature activation-0.000
Top resid features:
i
Tokeni
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.02

Head 2: 0.04

Head 3: 0.04

Head 4: 0.03

Head 5: 0.04

Head 6: 0.02

Head 7: 0.03

Head 8: 0.03

Head 9: 0.07

Head 10: 0.52

Head 11: 0.15

Positive logits

patrols2.49

patrolling2.48

patrol2.29

Patrol2.27

Detect2.06

intendent2.04

Sergeant2.01

Officers2.01

Constable1.99

investigating1.99

Officer1.99

senal1.94

Detective1.94

Investigations1.94

officers1.93

stationed1.89

Uniform1.86

Inspector1.85

utenant1.83

Lieutenant1.82

Negative logits

thereum-1.76

rencies-1.67

lag-1.55

weet-1.47

────-1.43

currencies-1.35

egg-1.35

symmetry-1.34

iquid-1.33

Brazil-1.32

Torrent-1.32

planet-1.32

Virgin-1.30

Polit-1.30

TPP-1.27

imentary-1.27

coins-1.26

cerv-1.26

bub-1.25

fml-1.25

INTERVAL 2.950 - 3.278
CONTAINS 0.000%

19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
died
Token died
Feature activation+0.000
when
Token when
Feature activation+0.000
police
Token police
Feature activation+0.000
opened
Token opened
Feature activation+3.278
fire
Token fire
Feature activation+1.375
on
Token on
Feature activation+1.383
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
she
Token she
Feature activation+0.000

INTERVAL 2.622 - 2.950
CONTAINS 0.001%

is
Token is
Feature activation+0.000
suspected
Token suspected
Feature activation+0.000
of
Token of
Feature activation+0.000
killing
Token killing
Feature activation+0.000
C
Token C
Feature activation+0.000
pl
Tokenpl
Feature activation+2.635
.
Token.
Feature activation+1.483
Bry
Token Bry
Feature activation+0.000
on
Tokenon
Feature activation+0.000
D
Token D
Feature activation+0.168
ickson
Tokenickson
Feature activation+0.000
burgl
Token burgl
Feature activation+0.000
aries
Tokenaries
Feature activation+0.504
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.043
officer
Token officer
Feature activation+1.594
did
Token did
Feature activation+2.677
not
Token not
Feature activation+1.912
initially
Token initially
Feature activation+0.114
chase
Token chase
Feature activation+1.091
him
Token him
Feature activation+0.992
,
Token,
Feature activation+0.308
story
Token story
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+2.740
're
Token're
Feature activation+1.594
trying
Token trying
Feature activation+0.561
to
Token to
Feature activation+1.085
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Metropolitan
Token Metropolitan
Feature activation+0.179
police
Token police
Feature activation+0.000
's
Token's
Feature activation+2.724
road
Token road
Feature activation+0.021
death
Token death
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
unit
Token unit
Feature activation+1.353
is
Token is
Feature activation+1.285
Chief
Token Chief
Feature activation+1.626
Larry
Token Larry
Feature activation+1.656
Smith
Token Smith
Feature activation+0.481
said
Token said
Feature activation+0.953
his
Token his
Feature activation+1.122
officers
Token officers
Feature activation+2.865
balanced
Token balanced
Feature activation+0.867
the
Token the
Feature activation+0.342
right
Token right
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.295 - 2.622
CONTAINS 0.003%

34
Token34
Feature activation+0.000
]
Token]
Feature activation+0.000
Gotham
Token Gotham
Feature activation+0.000
police
Token police
Feature activation+0.821
are
Token are
Feature activation+2.945
on
Token on
Feature activation+2.593
B
Token B
Feature activation+0.107
anes
Tokenanes
Feature activation+0.000
payroll
Token payroll
Feature activation+1.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
March
Token March
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
police
Token police
Feature activation+0.181
responded
Token responded
Feature activation+2.201
to
Token to
Feature activation+2.397
a
Token a
Feature activation+0.348
call
Token call
Feature activation+0.615
from
Token from
Feature activation+0.216
a
Token a
Feature activation+0.360
Brooklyn
Token Brooklyn
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
store
Token store
Feature activation+0.000
,"
Token,"
Feature activation+0.000
police
Token police
Feature activation+0.876
said
Token said
Feature activation+2.332
.
Token.
Feature activation+0.860
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.346
The
TokenThe
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
successful
Token successful
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
officer
Token officer
Feature activation+2.453
used
Token used
Feature activation+2.466
the
Token the
Feature activation+0.796
new
Token new
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.207
to
Token to
Feature activation+0.000
giving
Token giving
Feature activation+0.000
local
Token local
Feature activation+0.000
cops
Token cops
Feature activation+0.884
the
Token the
Feature activation+1.918
ability
Token ability
Feature activation+2.069
to
Token to
Feature activation+2.552
inquire
Token inquire
Feature activation+1.045
about
Token about
Feature activation+0.729
a
Token a
Feature activation+0.253
person
Token person
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.967 - 2.295
CONTAINS 0.009%

a
Token a
Feature activation+0.000
confrontation
Token confrontation
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Captain
Token Captain
Feature activation+2.081
Chris
Token Chris
Feature activation+0.922
Fowler
Token Fowler
Feature activation+0.180
told
Token told
Feature activation+0.444
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
40
Token 40
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
for
Token for
Feature activation+0.000
police
Token police
Feature activation+0.049
to
Token to
Feature activation+2.262
arrive
Token arrive
Feature activation+2.138
and
Token and
Feature activation+0.626
that
Token that
Feature activation+0.034
police
Token police
Feature activation+0.000
only
Token only
Feature activation+1.806
came
Token came
Feature activation+1.740
gasoline
Token gasoline
Feature activation+0.000
was
Token was
Feature activation+0.000
dripping
Token dripping
Feature activation+0.000
.
Token.
Feature activation+0.000
Police
Token Police
Feature activation+0.000
asked
Token asked
Feature activation+2.141
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
step
Token step
Feature activation+0.000
away
Token away
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
tant
Token tant
Feature activation+0.000
rum
Tokenrum
Feature activation+0.000
.
Token.
Feature activation+0.000
Officers
Token Officers
Feature activation+2.210
held
Token held
Feature activation+1.974
down
Token down
Feature activation+0.821
the
Token the
Feature activation+0.336
kinderg
Token kinderg
Feature activation+0.000
art
Tokenart
Feature activation+0.000
ener
Tokenener
Feature activation+0.000
from
Token from
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
they
Token they
Feature activation+2.165
requested
Token requested
Feature activation+2.082
records
Token records
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.000
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.639 - 1.967
CONTAINS 0.019%

un
Token un
Feature activation+0.025
bec
Tokenbec
Feature activation+0.000
oming
Tokenoming
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.242
officer
Token officer
Feature activation+1.730
.
Token.
Feature activation+0.019
Other
Token Other
Feature activation+0.000
rules
Token rules
Feature activation+0.178
broken
Token broken
Feature activation+0.064
include
Token include
Feature activation+0.000
no
Token no
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+0.103
the
Token the
Feature activation+0.063
police
Token police
Feature activation+0.713
department
Token department
Feature activation+1.667
bothered
Token bothered
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.524
to
Token to
Feature activation+0.000
op
Tokenop
Feature activation+0.000
patrol
Token patrol
Feature activation+0.838
headquarters
Token headquarters
Feature activation+0.566
shack
Token shack
Feature activation+0.213
and
Token and
Feature activation+0.000
answers
Token answers
Feature activation+1.645
the
Token the
Feature activation+0.388
squ
Token squ
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
king
Tokenking
Feature activation+0.320
with
Token with
Feature activation+0.072
of
Token of
Feature activation+0.000
turning
Token turning
Feature activation+0.000
around
Token around
Feature activation+0.067
the
Token the
Feature activation+0.000
troubled
Token troubled
Feature activation+0.347
agency
Token agency
Feature activation+1.848
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Among
TokenAmong
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
but
Token but
Feature activation+0.000
deputies
Token deputies
Feature activation+0.452
do
Token do
Feature activation+0.880
not
Token not
Feature activation+1.055
have
Token have
Feature activation+1.876
a
Token a
Feature activation+0.651
motive
Token motive
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000

INTERVAL 1.311 - 1.639
CONTAINS 0.032%

their
Token their
Feature activation+1.089
shootings
Token shootings
Feature activation+0.712
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
police
Token police
Feature activation+1.005
officers
Token officers
Feature activation+1.395
,
Token,
Feature activation+0.618
security
Token security
Feature activation+0.719
guards
Token guards
Feature activation+0.479
,
Token,
Feature activation+0.753
or
Token or
Feature activation+0.326
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
cop
Token cop
Feature activation+1.025
who
Token who
Feature activation+1.431
arrested
Token arrested
Feature activation+1.335
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.637
the
Token the
Feature activation+0.435
one
Token one
Feature activation+0.450
who
Token who
Feature activation+1.280
an
Token an
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
off
Token off
Feature activation+0.000
-
Token-
Feature activation+0.000
duty
Tokenduty
Feature activation+0.801
policeman
Token policeman
Feature activation+1.320
and
Token and
Feature activation+0.322
his
Token his
Feature activation+0.723
wife
Token wife
Feature activation+0.000
ran
Token ran
Feature activation+0.144
back
Token back
Feature activation+0.010
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
cop
Token cop
Feature activation+1.025
who
Token who
Feature activation+1.431
arrested
Token arrested
Feature activation+1.335
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.637
the
Token the
Feature activation+0.435
one
Token one
Feature activation+0.450
police
Token police
Feature activation+0.000
's
Token's
Feature activation+2.724
road
Token road
Feature activation+0.021
death
Token death
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
unit
Token unit
Feature activation+1.353
is
Token is
Feature activation+1.285
looking
Token looking
Feature activation+1.126
into
Token into
Feature activation+0.607
the
Token the
Feature activation+0.000
collision
Token collision
Feature activation+0.000

INTERVAL 0.983 - 1.311
CONTAINS 0.058%

classified
Token classified
Feature activation+0.000
material
Token material
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
bureau
Token bureau
Feature activation+1.103
director
Token director
Feature activation+1.065
James
Token James
Feature activation+1.106
Comey
Token Comey
Feature activation+0.000
gave
Token gave
Feature activation+0.174
her
Token her
Feature activation+0.000
a
Token a
Feature activation+0.000
Ob
Token Ob
Feature activation+0.000
is
Tokenis
Feature activation+0.000
po
Tokenpo
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.284
's
Token's
Feature activation+1.014
Office
Token Office
Feature activation+0.972
.
Token.
Feature activation+1.079
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
R
TokenR
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
material
Token material
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
bureau
Token bureau
Feature activation+1.103
director
Token director
Feature activation+1.065
James
Token James
Feature activation+1.106
Comey
Token Comey
Feature activation+0.000
gave
Token gave
Feature activation+0.174
her
Token her
Feature activation+0.000
a
Token a
Feature activation+0.000
tongue
Token tongue
Feature activation+0.000
deliver
Token deliver
Feature activation+0.196
greater
Token greater
Feature activation+0.061
safety
Token safety
Feature activation+0.027
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
cops
Token cops
Feature activation+1.024
are
Token are
Feature activation+1.549
always
Token always
Feature activation+1.016
too
Token too
Feature activation+0.694
far
Token far
Feature activation+0.000
away
Token away
Feature activation+0.007
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.021
services
Token services
Feature activation+0.173
even
Token even
Feature activation+0.131
more
Token more
Feature activation+0.835
power
Token power
Feature activation+1.015
and
Token and
Feature activation+0.057
citizens
Token citizens
Feature activation+0.000
even
Token even
Feature activation+0.000
fewer
Token fewer
Feature activation+0.120
rights
Token rights
Feature activation+0.072

INTERVAL 0.656 - 0.983
CONTAINS 0.112%

Sheriff
Token Sheriff
Feature activation+0.048
John
Token John
Feature activation+1.669
Han
Token Han
Feature activation+0.000
lin
Tokenlin
Feature activation+0.333
,
Token,
Feature activation+0.347
who
Token who
Feature activation+0.923
said
Token said
Feature activation+0.365
he
Token he
Feature activation+0.410
would
Token would
Feature activation+0.244
not
Token not
Feature activation+0.358
use
Token use
Feature activation+0.404
him
Token him
Feature activation+0.541
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.818
is
Token is
Feature activation+0.038
charged
Token charged
Feature activation+0.022
with
Token with
Feature activation+0.809
counselling
Token counselling
Feature activation+0.000
to
Token to
Feature activation+0.000
Law
TokenLaw
Feature activation+0.674
enforcement
Token enforcement
Feature activation+1.270
appeared
Token appeared
Feature activation+0.997
to
Token to
Feature activation+0.008
deliberately
Token deliberately
Feature activation+0.219
target
Token target
Feature activation+0.976
black
Token black
Feature activation+0.019
residents
Token residents
Feature activation+0.000
:
Token:
Feature activation+0.000
Although
Token Although
Feature activation+0.000
black
Token black
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
village
Token village
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.625
withdrew
Token withdrew
Feature activation+0.877
later
Token later
Feature activation+0.000
and
Token and
Feature activation+0.000
no
Token no
Feature activation+0.000
arrests
Token arrests
Feature activation+0.115
were
Token were
Feature activation+0.259
recommended
Token recommended
Feature activation+0.000
that
Token that
Feature activation+0.170
two
Token two
Feature activation+0.385
of
Token of
Feature activation+0.840
the
Token the
Feature activation+1.174
four
Token four
Feature activation+0.722
officers
Token officers
Feature activation+1.996
keep
Token keep
Feature activation+1.087
their
Token their
Feature activation+0.983
jobs
Token jobs
Feature activation+1.295
,
Token,
Feature activation+0.012

INTERVAL 0.328 - 0.656
CONTAINS 0.277%

management
Token management
Feature activation+0.000
and
Token and
Feature activation+0.101
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.079
general
Token general
Feature activation+0.220
manager
Token manager
Feature activation+0.652
of
Token of
Feature activation+0.004
a
Token a
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
The
TokenThe
Feature activation+0.000
police
Token police
Feature activation+0.430
then
Token then
Feature activation+0.648
decided
Token decided
Feature activation+1.306
to
Token to
Feature activation+0.584
arrest
Token arrest
Feature activation+0.508
me
Token me
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
protecting
Token protecting
Feature activation+0.413
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
police
Token police
Feature activation+0.000
summoned
Token summoned
Feature activation+0.341
and
Token and
Feature activation+0.192
released
Token released
Feature activation+0.366
the
Token the
Feature activation+0.075
rapist
Token rapist
Feature activation+0.000
after
Token after
Feature activation+0.000
Amin
Token Amin
Feature activation+0.000
a
Tokena
Feature activation+0.000
Last
Token Last
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
started
Token started
Feature activation+0.000
with
Token with
Feature activation+0.000
former
Token former
Feature activation+0.000
Acting
Token Acting
Feature activation+0.346
Attorney
Token Attorney
Feature activation+0.000
General
Token General
Feature activation+0.000
Yates
Token Yates
Feature activation+0.000
stating
Token stating
Feature activation+0.000
that
Token that
Feature activation+0.017
Ċ
TokenĊ
Feature activation+0.000
Iran
TokenIran
Feature activation+0.000
's
Token's
Feature activation+0.000
justice
Token justice
Feature activation+0.000
system
Token system
Feature activation+0.147
is
Token is
Feature activation+0.333
based
Token based
Feature activation+0.501
on
Token on
Feature activation+0.163
Sharia
Token Sharia
Feature activation+0.000
law
Token law
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.328
CONTAINS 99.490%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
male
Token male
Feature activation+0.000
world
Token world
Feature activation+0.000
;
Token;
Feature activation+0.000
women
Token women
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
higher
Token higher
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
I
Token I
Feature activation+0.000
step
Token step
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+0.000
Maxwell
Token Maxwell
Feature activation+0.000
points
Token points
Feature activation+0.000
out
Token out
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
can
Token can
Feature activation+0.000
hardly
Token hardly
Feature activation+0.000
be
Token be
Feature activation+0.000
called
Token called
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
fine
Token fine
Feature activation+0.000
adjustments
Token adjustments
Feature activation+0.000
to
Token to
Feature activation+0.000
payload
Token payload
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
velocity
Token velocity
Feature activation+0.000
after
Token after
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
after
Token after
Feature activation+0.000
they
Token they
Feature activation+0.000
moved
Token moved
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H5.10: (feature 3722)

TOP ACTIVATIONS
MAX = 5.584

into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345
Jo
Token Jo
Feature activation+2.807
aquin
Tokenaquin
Feature activation+5.165
reached
Token reached
Feature activation+5.584
Category
Token Category
Feature activation+4.150
3
Token 3
Feature activation+2.370
status
Token status
Feature activation+2.157
late
Token late
Feature activation+0.574
Wednesday
Token Wednesday
Feature activation+0.491
Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345
Jo
Token Jo
Feature activation+2.807
aquin
Tokenaquin
Feature activation+5.165
reached
Token reached
Feature activation+5.584
Category
Token Category
Feature activation+4.150
3
Token 3
Feature activation+2.370
status
Token status
Feature activation+2.157
late
Token late
Feature activation+0.574
Ċ
TokenĊ
Feature activation+0.000
Hur
TokenHur
Feature activation+0.400
ricane
Tokenricane
Feature activation+0.529
Jo
Token Jo
Feature activation+2.877
aquin
Tokenaquin
Feature activation+4.260
strengthened
Token strengthened
Feature activation+4.264
rapidly
Token rapidly
Feature activation+1.422
Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hur
TokenHur
Feature activation+0.400
ricane
Tokenricane
Feature activation+0.529
Jo
Token Jo
Feature activation+2.877
aquin
Tokenaquin
Feature activation+4.260
strengthened
Token strengthened
Feature activation+4.264
rapidly
Token rapidly
Feature activation+1.422
Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
Harvey
Token Harvey
Feature activation+0.735
and
Token and
Feature activation+3.086
Irma
Token Irma
Feature activation+1.254
,
Token,
Feature activation+1.212
which
Token which
Feature activation+3.129
hit
Token hit
Feature activation+4.038
Texas
Token Texas
Feature activation+0.254
and
Token and
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
in
Token in
Feature activation+0.474
recent
Token recent
Feature activation+1.312
rates
Token rates
Feature activation+0.000
driven
Token driven
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
hurricane
Token hurricane
Feature activation+0.685
-
Token-
Feature activation+3.746
induced
Tokeninduced
Feature activation+2.866
shutdown
Token shutdown
Feature activation+0.000
of
Token of
Feature activation+0.000
refining
Token refining
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
A
Token A
Feature activation+0.000
snow
Token snow
Feature activation+0.000
storm
Tokenstorm
Feature activation+1.623
hit
Token hit
Feature activation+3.478
the
Token the
Feature activation+1.409
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
area
Token area
Feature activation+0.000
a
Token a
Feature activation+0.000
been
Token been
Feature activation+0.000
hit
Token hit
Feature activation+0.807
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.537
hurricanes
Token hurricanes
Feature activation+1.633
in
Token in
Feature activation+3.376
two
Token two
Feature activation+0.724
years
Token years
Feature activation+0.387
.
Token.
Feature activation+0.342
That
Token That
Feature activation+0.474
's
Token's
Feature activation+0.370
ricane
Tokenricane
Feature activation+0.529
Jo
Token Jo
Feature activation+2.877
aquin
Tokenaquin
Feature activation+4.260
strengthened
Token strengthened
Feature activation+4.264
rapidly
Token rapidly
Feature activation+1.422
Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345
Jo
Token Jo
Feature activation+2.807
aquin
Tokenaquin
Feature activation+5.165
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
a
Token a
Feature activation+0.000
storm
Token storm
Feature activation+0.401
is
Token is
Feature activation+0.781
coming
Token coming
Feature activation+3.315
,"
Token,"
Feature activation+0.000
one
Token one
Feature activation+0.000
administration
Token administration
Feature activation+0.000
source
Token source
Feature activation+0.000
said
Token said
Feature activation+0.000
heat
Token heat
Feature activation+0.000
wave
Token wave
Feature activation+0.960
continues
Token continues
Feature activation+2.210
to
Token to
Feature activation+1.060
sweep
Token sweep
Feature activation+2.555
across
Token across
Feature activation+3.215
America
Token America
Feature activation+0.000
.
Token.
Feature activation+0.623
Just
Token Just
Feature activation+0.073
like
Token like
Feature activation+0.368
during
Token during
Feature activation+0.931
by
Token by
Feature activation+1.472
a
Token a
Feature activation+1.102
fast
Token fast
Feature activation+1.260
moving
Token moving
Feature activation+2.535
cold
Token cold
Feature activation+0.579
front
Token front
Feature activation+3.168
,
Token,
Feature activation+0.845
continues
Token continues
Feature activation+2.319
into
Token into
Feature activation+1.225
Saturday
Token Saturday
Feature activation+1.775
evening
Token evening
Feature activation+1.505
saying
Token saying
Feature activation+0.000
his
Token his
Feature activation+0.000
response
Token response
Feature activation+0.000
to
Token to
Feature activation+0.000
Hurricane
Token Hurricane
Feature activation+0.168
Maria
Token Maria
Feature activation+3.157
lacks
Token lacks
Feature activation+0.000
the
Token the
Feature activation+0.000
urgency
Token urgency
Feature activation+0.000
that
Token that
Feature activation+0.000
followed
Token followed
Feature activation+0.000
Geological
Token Geological
Feature activation+0.000
Survey
Token Survey
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.315
4
Token 4
Feature activation+2.171
.
Token.
Feature activation+3.134
1
Token1
Feature activation+2.996
magnitude
Token magnitude
Feature activation+2.103
quake
Token quake
Feature activation+1.036
struck
Token struck
Feature activation+2.528
just
Token just
Feature activation+1.437
Hurricanes
Token Hurricanes
Feature activation+1.532
Harvey
Token Harvey
Feature activation+0.735
and
Token and
Feature activation+3.086
Irma
Token Irma
Feature activation+1.254
,
Token,
Feature activation+1.212
which
Token which
Feature activation+3.129
hit
Token hit
Feature activation+4.038
Texas
Token Texas
Feature activation+0.254
and
Token and
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
in
Token in
Feature activation+0.474
urgency
Token urgency
Feature activation+0.000
that
Token that
Feature activation+0.000
followed
Token followed
Feature activation+0.000
Hurricanes
Token Hurricanes
Feature activation+1.532
Harvey
Token Harvey
Feature activation+0.735
and
Token and
Feature activation+3.086
Irma
Token Irma
Feature activation+1.254
,
Token,
Feature activation+1.212
which
Token which
Feature activation+3.129
hit
Token hit
Feature activation+4.038
Texas
Token Texas
Feature activation+0.254
of
Token of
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
.
Token.
Feature activation+0.201
They
Token They
Feature activation+1.661
were
Token were
Feature activation+2.267
fierce
Token fierce
Feature activation+3.051
.
Token.
Feature activation+0.943
They
Token They
Feature activation+1.444
were
Token were
Feature activation+1.654
terrible
Token terrible
Feature activation+2.158
.
Token.
Feature activation+0.678
Survey
Token Survey
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.315
4
Token 4
Feature activation+2.171
.
Token.
Feature activation+3.134
1
Token1
Feature activation+2.996
magnitude
Token magnitude
Feature activation+2.103
quake
Token quake
Feature activation+1.036
struck
Token struck
Feature activation+2.528
just
Token just
Feature activation+1.437
after
Token after
Feature activation+1.294
my
Token my
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
the
Token the
Feature activation+0.000
dust
Token dust
Feature activation+0.000
storms
Token storms
Feature activation+1.601
that
Token that
Feature activation+2.949
visited
Token visited
Feature activation+2.808
this
Token this
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
since
Token since
Feature activation+0.102
at
Token at
Feature activation+0.012
least
Token least
Feature activation+0.041
Katrina
Token Katrina
Feature activation+2.923
,
Token,
Feature activation+2.170
scientists
Token scientists
Feature activation+0.000
have
Token have
Feature activation+0.000
warned
Token warned
Feature activation+0.000
that
Token that
Feature activation+0.000

Top DFA by src position
MAX = 5.729

landfall
Token landfall
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Hur
TokenHur
Feature activation+0.008
Top resid features:
ricane
Tokenricane
Feature activation+5.729
Top resid features:
Jo
Token Jo
Feature activation+0.007
Top resid features:
aquin
Tokenaquin
Feature activation+0.076
Top resid features:
strengthened
Token strengthened
Feature activation+0.026
Top resid features:
rapidly
Token rapidly
Feature activation-0.004
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.020
Top resid features:
landfall
Token landfall
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Hur
TokenHur
Feature activation+0.109
Top resid features:
ricane
Tokenricane
Feature activation+3.406
Top resid features:
Jo
Token Jo
Feature activation+0.084
Top resid features:
aquin
Tokenaquin
Feature activation+0.173
Top resid features:
strengthened
Token strengthened
Feature activation+0.363
Top resid features:
rapidly
Token rapidly
Feature activation+0.003
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.026
Top resid features:
landfall
Token landfall
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Hur
TokenHur
Feature activation+0.193
Top resid features:
ricane
Tokenricane
Feature activation+3.272
Top resid features:
Jo
Token Jo
Feature activation-0.042
Top resid features:
aquin
Tokenaquin
Feature activation+0.044
Top resid features:
strengthened
Token strengthened
Feature activation+0.023
Top resid features:
rapidly
Token rapidly
Feature activation+0.000
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
shifting
Token shifting
Feature activation+0.001
Top resid features:
track
Token track
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
hurricane
Token hurricane
Feature activation+3.819
Top resid features:
as
Token as
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
risk
Token risk
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
saying
Token saying
Feature activation+0.020
Top resid features:
his
Token his
Feature activation+0.006
Top resid features:
response
Token response
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
Hurricane
Token Hurricane
Feature activation+2.188
Top resid features:
Maria
Token Maria
Feature activation+0.342
Top resid features:
lacks
Token lacks
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
urgency
Token urgency
Feature activation+0.035
Top resid features:
that
Token that
Feature activation-0.015
Top resid features:
international
Token international
Feature activation+0.002
Top resid features:
rates
Token rates
Feature activation-0.026
Top resid features:
driven
Token driven
Feature activation-0.016
Top resid features:
by
Token by
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
hurricane
Token hurricane
Feature activation+4.480
Top resid features:
-
Token-
Feature activation-0.065
Top resid features:
induced
Tokeninduced
Feature activation+0.000
Top resid features:
shutdown
Token shutdown
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
refining
Token refining
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ŀ
TokenĿ
Feature activation+0.008
Top resid features:
A
Token A
Feature activation-0.008
Top resid features:
snow
Token snow
Feature activation+0.225
Top resid features:
storm
Tokenstorm
Feature activation+3.803
Top resid features:
hit
Token hit
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
York
Token York
Feature activation+0.000
Top resid features:
area
Token area
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.017
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
hit
Token hit
Feature activation+0.077
Top resid features:
with
Token with
Feature activation+0.010
Top resid features:
two
Token two
Feature activation+0.018
Top resid features:
hurricanes
Token hurricanes
Feature activation+2.384
Top resid features:
in
Token in
Feature activation-0.044
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
landfall
Token landfall
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
Hur
TokenHur
Feature activation+0.053
Top resid features:
ricane
Tokenricane
Feature activation+2.392
Top resid features:
Jo
Token Jo
Feature activation+0.004
Top resid features:
aquin
Tokenaquin
Feature activation+0.052
Top resid features:
strengthened
Token strengthened
Feature activation+0.080
Top resid features:
rapidly
Token rapidly
Feature activation-0.011
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.029
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
fair
Token fair
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
say
Token say
Feature activation-0.021
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
storm
Token storm
Feature activation+4.050
Top resid features:
is
Token is
Feature activation+0.028
Top resid features:
coming
Token coming
Feature activation-0.021
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
administration
Token administration
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.004
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.026
Top resid features:
this
Token this
Feature activation-0.000
Top resid features:
heat
Token heat
Feature activation+0.198
Top resid features:
wave
Token wave
Feature activation+3.644
Top resid features:
continues
Token continues
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
sweep
Token sweep
Feature activation+0.040
Top resid features:
across
Token across
Feature activation-0.014
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
severe
Token severe
Feature activation+0.123
Top resid features:
thunder
Token thunder
Feature activation+0.189
Top resid features:
storm
Tokenstorm
Feature activation+1.856
Top resid features:
watch
Token watch
Feature activation+0.059
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
prompted
Token prompted
Feature activation-0.010
Top resid features:
by
Token by
Feature activation-0.087
Top resid features:
a
Token a
Feature activation-0.062
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
saying
Token saying
Feature activation+0.023
Top resid features:
his
Token his
Feature activation-0.007
Top resid features:
response
Token response
Feature activation+0.017
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
Hurricane
Token Hurricane
Feature activation+2.719
Top resid features:
Maria
Token Maria
Feature activation+0.905
Top resid features:
lacks
Token lacks
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
urgency
Token urgency
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.091
Top resid features:
US
TokenUS
Feature activation+0.005
Top resid features:
Geological
Token Geological
Feature activation+0.030
Top resid features:
Survey
Token Survey
Feature activation-0.001
Top resid features:
says
Token says
Feature activation+0.002
Top resid features:
quake
Token quake
Feature activation+1.697
Top resid features:
struck
Token struck
Feature activation+0.031
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
Thursday
Token Thursday
Feature activation+0.009
Top resid features:
afternoon
Token afternoon
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
lacks
Token lacks
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
urgency
Token urgency
Feature activation+0.034
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
followed
Token followed
Feature activation-0.090
Top resid features:
Hurricanes
Token Hurricanes
Feature activation+1.061
Top resid features:
Harvey
Token Harvey
Feature activation+0.479
Top resid features:
and
Token and
Feature activation+0.198
Top resid features:
Irma
Token Irma
Feature activation+0.859
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
which
Token which
Feature activation-0.003
Top resid features:
lacks
Token lacks
Feature activation+0.101
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
urgency
Token urgency
Feature activation+0.014
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
followed
Token followed
Feature activation-0.173
Top resid features:
Hurricanes
Token Hurricanes
Feature activation+1.598
Top resid features:
Harvey
Token Harvey
Feature activation+0.664
Top resid features:
and
Token and
Feature activation-0.083
Top resid features:
Irma
Token Irma
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.005
Top resid features:
my
Token my
Feature activation+0.001
Top resid features:
childhood
Token childhood
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
dust
Token dust
Feature activation-0.002
Top resid features:
storms
Token storms
Feature activation+3.786
Top resid features:
that
Token that
Feature activation-0.170
Top resid features:
visited
Token visited
Feature activation+0.079
Top resid features:
this
Token this
Feature activation+0.010
Top resid features:
part
Token part
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
Atlantic
TokenAtlantic
Feature activation-0.002
Top resid features:
region
Token region
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
An
TokenAn
Feature activation+0.002
Top resid features:
earthquake
Token earthquake
Feature activation+1.429
Top resid features:
has
Token has
Feature activation+0.015
Top resid features:
j
Token j
Feature activation+0.007
Top resid features:
ol
Tokenol
Feature activation+0.001
Top resid features:
ted
Tokented
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
from
Token from
Feature activation-0.044
Top resid features:
my
Token my
Feature activation+0.003
Top resid features:
childhood
Token childhood
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
dust
Token dust
Feature activation-0.013
Top resid features:
storms
Token storms
Feature activation+3.742
Top resid features:
that
Token that
Feature activation-0.146
Top resid features:
visited
Token visited
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
been
Token been
Feature activation+0.003
Top resid features:
hit
Token hit
Feature activation+0.088
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
two
Token two
Feature activation+0.009
Top resid features:
hurricanes
Token hurricanes
Feature activation+2.865
Top resid features:
in
Token in
Feature activation+0.048
Top resid features:
two
Token two
Feature activation+0.003
Top resid features:
years
Token years
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
That
Token That
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.04

Head 3: 0.05

Head 4: 0.05

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.02

Head 9: 0.07

Head 10: 0.52

Head 11: 0.11

Positive logits

landfall2.40

earthqu2.19

wre2.04

devast2.02

agascar1.99

storms1.94

storms1.94

rav1.93

catast1.84

duration1.83

hurricanes1.82

caused1.77

impacting1.76

sweeps1.73

artney1.72

waters1.72

rains1.71

typh1.71

induced1.69

raged1.69

Negative logits

Socrates-1.60

faculty-1.53

lawy-1.53

Lounge-1.52

Academic-1.47

Faculty-1.47

metics-1.44

humanities-1.44

bench-1.44

Richie-1.43

McGill-1.42

Enlightenment-1.41

faculties-1.40

IQ-1.39

lounge-1.39

Unix-1.39

Labs-1.38

locker-1.38

vou-1.38

vanity-1.37

INTERVAL 5.025 - 5.584
CONTAINS 0.000%

Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345
Jo
Token Jo
Feature activation+2.807
aquin
Tokenaquin
Feature activation+5.165
reached
Token reached
Feature activation+5.584
Category
Token Category
Feature activation+4.150
3
Token 3
Feature activation+2.370
status
Token status
Feature activation+2.157
late
Token late
Feature activation+0.574
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345
Jo
Token Jo
Feature activation+2.807
aquin
Tokenaquin
Feature activation+5.165
reached
Token reached
Feature activation+5.584
Category
Token Category
Feature activation+4.150
3
Token 3
Feature activation+2.370
status
Token status
Feature activation+2.157
late
Token late
Feature activation+0.574
Wednesday
Token Wednesday
Feature activation+0.491

INTERVAL 4.467 - 5.025
CONTAINS 0.000%

INTERVAL 3.909 - 4.467
CONTAINS 0.000%

Harvey
Token Harvey
Feature activation+0.735
and
Token and
Feature activation+3.086
Irma
Token Irma
Feature activation+1.254
,
Token,
Feature activation+1.212
which
Token which
Feature activation+3.129
hit
Token hit
Feature activation+4.038
Texas
Token Texas
Feature activation+0.254
and
Token and
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
in
Token in
Feature activation+0.474
recent
Token recent
Feature activation+1.312
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hur
TokenHur
Feature activation+0.400
ricane
Tokenricane
Feature activation+0.529
Jo
Token Jo
Feature activation+2.877
aquin
Tokenaquin
Feature activation+4.260
strengthened
Token strengthened
Feature activation+4.264
rapidly
Token rapidly
Feature activation+1.422
Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
Ċ
TokenĊ
Feature activation+0.000
Hur
TokenHur
Feature activation+0.400
ricane
Tokenricane
Feature activation+0.529
Jo
Token Jo
Feature activation+2.877
aquin
Tokenaquin
Feature activation+4.260
strengthened
Token strengthened
Feature activation+4.264
rapidly
Token rapidly
Feature activation+1.422
Wednesday
Token Wednesday
Feature activation+3.316
into
Token into
Feature activation+1.085
Thursday
Token Thursday
Feature activation+0.349
.
Token.
Feature activation+1.345

INTERVAL 3.350 - 3.909
CONTAINS 0.000%

been
Token been
Feature activation+0.000
hit
Token hit
Feature activation+0.807
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.537
hurricanes
Token hurricanes
Feature activation+1.633
in
Token in
Feature activation+3.376
two
Token two
Feature activation+0.724
years
Token years
Feature activation+0.387
.
Token.
Feature activation+0.342
That
Token That
Feature activation+0.474
's
Token's
Feature activation+0.370
rates
Token rates
Feature activation+0.000
driven
Token driven
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
hurricane
Token hurricane
Feature activation+0.685
-
Token-
Feature activation+3.746
induced
Tokeninduced
Feature activation+2.866
shutdown
Token shutdown
Feature activation+0.000
of
Token of
Feature activation+0.000
refining
Token refining
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
A
Token A
Feature activation+0.000
snow
Token snow
Feature activation+0.000
storm
Tokenstorm
Feature activation+1.623
hit
Token hit
Feature activation+3.478
the
Token the
Feature activation+1.409
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
area
Token area
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 2.792 - 3.350
CONTAINS 0.002%

these
Token these
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
and
Token and
Feature activation+0.000
frequent
Token frequent
Feature activation+0.000
storms
Token storms
Feature activation+1.621
are
Token are
Feature activation+2.879
a
Token a
Feature activation+0.764
result
Token result
Feature activation+0.145
of
Token of
Feature activation+1.118
warmer
Token warmer
Feature activation+0.000
seas
Token seas
Feature activation+0.017
cover
Token cover
Feature activation+0.000
to
Token to
Feature activation+0.000
simply
Token simply
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
what
Token what
Feature activation+0.000
Sandy
Token Sandy
Feature activation+2.796
herself
Token herself
Feature activation+1.735
has
Token has
Feature activation+0.095
so
Token so
Feature activation+0.000
loudly
Token loudly
Feature activation+0.000
said
Token said
Feature activation+0.000
urgency
Token urgency
Feature activation+0.000
that
Token that
Feature activation+0.000
followed
Token followed
Feature activation+0.000
Hurricanes
Token Hurricanes
Feature activation+1.532
Harvey
Token Harvey
Feature activation+0.735
and
Token and
Feature activation+3.086
Irma
Token Irma
Feature activation+1.254
,
Token,
Feature activation+1.212
which
Token which
Feature activation+3.129
hit
Token hit
Feature activation+4.038
Texas
Token Texas
Feature activation+0.254
of
Token of
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
cycl
Token cycl
Feature activation+0.974
one
Tokenone
Feature activation+2.801
-
Token-
Feature activation+2.781
prone
Tokenprone
Feature activation+0.985
region
Token region
Feature activation+0.492
,
Token,
Feature activation+0.109
who
Token who
Feature activation+0.000
my
Token my
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
the
Token the
Feature activation+0.000
dust
Token dust
Feature activation+0.000
storms
Token storms
Feature activation+1.601
that
Token that
Feature activation+2.949
visited
Token visited
Feature activation+2.808
this
Token this
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000

INTERVAL 2.234 - 2.792
CONTAINS 0.002%

on
Token on
Feature activation+1.114
Thursday
Token Thursday
Feature activation+2.165
afternoon
Token afternoon
Feature activation+1.431
and
Token and
Feature activation+0.969
was
Token was
Feature activation+1.523
centered
Token centered
Feature activation+2.287
near
Token near
Feature activation+0.605
the
Token the
Feature activation+0.454
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Dover
Token Dover
Feature activation+0.000
the
Token the
Feature activation+0.157
state
Token state
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.051
fire
Token fire
Feature activation+1.626
has
Token has
Feature activation+2.315
been
Token been
Feature activation+1.982
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.155
times
Token times
Feature activation+0.288
,
Token,
Feature activation+0.000
struck
Token struck
Feature activation+2.528
just
Token just
Feature activation+1.437
after
Token after
Feature activation+1.294
4
Token 4
Feature activation+1.487
.
Token.
Feature activation+2.704
45
Token45
Feature activation+2.538
pm
Tokenpm
Feature activation+1.229
Thursday
Token Thursday
Feature activation+1.497
,
Token,
Feature activation+1.188
and
Token and
Feature activation+1.026
was
Token was
Feature activation+2.174
lives
Token lives
Feature activation+0.000
by
Token by
Feature activation+0.000
better
Token better
Feature activation+0.000
predicting
Token predicting
Feature activation+0.023
storms
Token storms
Feature activation+1.849
coming
Token coming
Feature activation+2.495
in
Token in
Feature activation+1.415
off
Token off
Feature activation+1.101
the
Token the
Feature activation+0.000
coast
Token coast
Feature activation+0.000
and
Token and
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
Storm
Token Storm
Feature activation+1.964
ch
Token ch
Feature activation+2.771
aser
Tokenaser
Feature activation+0.473
video
Token video
Feature activation+0.000
of
Token of
Feature activation+0.000
Tup
Token Tup
Feature activation+0.000
elo
Tokenelo
Feature activation+0.065

INTERVAL 1.675 - 2.234
CONTAINS 0.005%

state
Token state
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.051
fire
Token fire
Feature activation+1.626
has
Token has
Feature activation+2.315
been
Token been
Feature activation+1.982
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.155
times
Token times
Feature activation+0.288
,
Token,
Feature activation+0.000
moving
Token moving
Feature activation+1.437
#
Token #
Feature activation+0.000
Hur
TokenHur
Feature activation+0.000
ricane
Tokenricane
Feature activation+0.000
Har
TokenHar
Feature activation+0.723
vey
Tokenvey
Feature activation+1.948
from
Token from
Feature activation+1.890
Camp
Token Camp
Feature activation+0.000
David
Token David
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
are
Token are
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
storm
Token storm
Feature activation+0.778
that
Token that
Feature activation+1.737
was
Token was
Feature activation+0.909
cited
Token cited
Feature activation+0.383
as
Token as
Feature activation+0.078
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
seen
Token seen
Feature activation+0.000
the
Token the
Feature activation+0.007
fire
Token fire
Feature activation+1.696
and
Token and
Feature activation+0.155
fury
Token fury
Feature activation+0.742
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Tokenand
Feature activation+0.166
being
Token being
Feature activation+0.100
an
Token an
Feature activation+0.874
independent
Token independent
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
has
Tokenhas
Feature activation+1.926
given
Token given
Feature activation+0.096
New
Token New
Feature activation+0.390
York
Token York
Feature activation+0.000
Mayor
Token Mayor
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000

INTERVAL 1.117 - 1.675
CONTAINS 0.013%

broke
Token broke
Feature activation+2.062
records
Token records
Feature activation+0.000
in
Token in
Feature activation+0.494
how
Token how
Feature activation+0.000
aggressively
Token aggressively
Feature activation+0.180
it
Token it
Feature activation+1.276
pressed
Token pressed
Feature activation+0.612
forward
Token forward
Feature activation+0.115
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
moving
Token moving
Feature activation+2.535
cold
Token cold
Feature activation+0.579
front
Token front
Feature activation+3.168
,
Token,
Feature activation+0.845
continues
Token continues
Feature activation+2.319
into
Token into
Feature activation+1.225
Saturday
Token Saturday
Feature activation+1.775
evening
Token evening
Feature activation+1.505
from
Token from
Feature activation+2.610
Kingston
Token Kingston
Feature activation+0.000
to
Token to
Feature activation+0.106
ľ
Tokenľ
Feature activation+0.000
With
TokenWith
Feature activation+0.209
winter
Token winter
Feature activation+0.521
weather
Token weather
Feature activation+0.194
expected
Token expected
Feature activation+1.460
to
Token to
Feature activation+1.489
impact
Token impact
Feature activation+1.346
Alabama
Token Alabama
Feature activation+0.000
,
Token,
Feature activation+0.071
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
A
TokenA
Feature activation+0.248
cop
Token cop
Feature activation+0.000
ious
Tokenious
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
moisture
Token moisture
Feature activation+1.528
will
Token will
Feature activation+0.791
un
Token un
Feature activation+0.000
load
Tokenload
Feature activation+0.000
very
Token very
Feature activation+0.258
heavy
Token heavy
Feature activation+0.000
the
Token the
Feature activation+0.240
But
Token But
Feature activation+0.119
te
Tokente
Feature activation+0.000
Fire
Token Fire
Feature activation+0.552
is
Token is
Feature activation+2.279
the
Token the
Feature activation+1.195
number
Token number
Feature activation+0.020
one
Token one
Feature activation+0.000
priority
Token priority
Feature activation+0.000
.
Token.
Feature activation+0.071
There
Token There
Feature activation+0.000

INTERVAL 0.558 - 1.117
CONTAINS 0.038%

could
Token could
Feature activation+0.805
burn
Token burn
Feature activation+1.125
,
Token,
Feature activation+0.755
end
Token end
Feature activation+0.134
angering
Tokenangering
Feature activation+0.202
thousands
Token thousands
Feature activation+0.708
of
Token of
Feature activation+0.942
hikers
Token hikers
Feature activation+0.000
and
Token and
Feature activation+0.000
tourists
Token tourists
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+0.000
probably
Token probably
Feature activation+0.000
caused
Token caused
Feature activation+0.000
by
Token by
Feature activation+0.000
jets
Token jets
Feature activation+0.040
blowing
Token blowing
Feature activation+0.839
mass
Token mass
Feature activation+0.000
from
Token from
Feature activation+0.336
the
Token the
Feature activation+0.089
binary
Token binary
Feature activation+0.000
system
Token system
Feature activation+0.000
it
Token it
Feature activation+0.000
responds
Token responds
Feature activation+0.000
more
Token more
Feature activation+0.000
readily
Token readily
Feature activation+0.000
to
Token to
Feature activation+0.000
winds
Token winds
Feature activation+0.849
and
Token and
Feature activation+0.610
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
easily
Token easily
Feature activation+0.000
broken
Token broken
Feature activation+0.049
wonderfully
Token wonderfully
Feature activation+0.000
during
Token during
Feature activation+0.310
extreme
Token extreme
Feature activation+0.760
weather
Token weather
Feature activation+0.268
at
Token at
Feature activation+0.857
the
Token the
Feature activation+0.966
other
Token other
Feature activation+0.340
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
therm
Token therm
Feature activation+0.363
of
Token of
Feature activation+0.000
seven
Token seven
Feature activation+0.039
counties
Token counties
Feature activation+0.000
were
Token were
Feature activation+0.897
the
Token the
Feature activation+0.697
deadliest
Token deadliest
Feature activation+0.891
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.000
destructive
Token destructive
Feature activation+1.161
series
Token series
Feature activation+0.659
of
Token of
Feature activation+0.040

INTERVAL 0.000 - 0.558
CONTAINS 99.938%

of
Token of
Feature activation+0.000
sub
Token sub
Feature activation+0.000
prime
Tokenprime
Feature activation+0.000
mortgages
Token mortgages
Feature activation+0.000
than
Token than
Feature activation+0.000
sub
Token sub
Feature activation+0.000
prime
Tokenprime
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
quite
Token quite
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
her
Token her
Feature activation+0.000
other
Token other
Feature activation+0.000
protagonists
Token protagonists
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
were
Token were
Feature activation+0.000
given
Token given
Feature activation+0.000
the
Token the
Feature activation+0.000
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.000
step
Token step
Feature activation+0.000
away
Token away
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
III
Token III
Feature activation+0.000
preceding
Token preceding
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
major
Token major
Feature activation+0.000
investors
Token investors
Feature activation+0.000
doubled
Token doubled
Feature activation+0.000
their
Token their
Feature activation+0.000
money
Token money
Feature activation+0.000
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+0.000
$
Token $
Feature activation+0.000
18
Token18
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H5.10: (feature 8027)

TOP ACTIVATIONS
MAX = 3.895

-
Token-
Feature activation+0.000
good
Tokengood
Feature activation+0.000
format
Token format
Feature activation+1.190
with
Token with
Feature activation+0.405
each
Token each
Feature activation+0.143
chapter
Token chapter
Feature activation+3.895
starting
Token starting
Feature activation+0.277
with
Token with
Feature activation+0.401
an
Token an
Feature activation+0.317
anecdote
Token anecdote
Feature activation+0.021
from
Token from
Feature activation+0.000
I
Token I
Feature activation+0.065
decided
Token decided
Feature activation+0.050
to
Token to
Feature activation+0.000
listen
Token listen
Feature activation+0.569
to
Token to
Feature activation+0.667
it
Token it
Feature activation+3.425
recently
Token recently
Feature activation+0.235
,
Token,
Feature activation+0.177
and
Token and
Feature activation+0.056
am
Token am
Feature activation+0.000
so
Token so
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.521
is
Token is
Feature activation+1.938
meant
Token meant
Feature activation+3.043
for
Token for
Feature activation+3.364
all
Token all
Feature activation+0.489
ages
Token ages
Feature activation+0.000
.
Token.
Feature activation+0.953
Ċ
TokenĊ
Feature activation+0.419
Ċ
TokenĊ
Feature activation+0.611
!
Token!
Feature activation+2.781
Overall
Token Overall
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.506
Ċ
TokenĊ
Feature activation+0.294
Well
TokenWell
Feature activation+0.672
written
Token written
Feature activation+3.290
,
Token,
Feature activation+2.335
believable
Token believable
Feature activation+1.802
,
Token,
Feature activation+1.645
applicable
Token applicable
Feature activation+0.763
,
Token,
Feature activation+0.278
two
Token two
Feature activation+0.000
[
Token [
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
it
Token it
Feature activation+1.209
comes
Token comes
Feature activation+0.545
out
Token out
Feature activation+3.164
],
Token],
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.600
'll
Token'll
Feature activation+0.443
be
Token be
Feature activation+0.358
Design
Token Design
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.521
is
Token is
Feature activation+1.938
meant
Token meant
Feature activation+3.043
for
Token for
Feature activation+3.364
all
Token all
Feature activation+0.489
ages
Token ages
Feature activation+0.000
.
Token.
Feature activation+0.953
Ċ
TokenĊ
Feature activation+0.419
Path
Token Path
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
,
Token,
Feature activation+1.823
published
Token published
Feature activation+3.024
by
Token by
Feature activation+2.488
Ign
Token Ign
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ius
Tokenius
Feature activation+0.000
Press
Token Press
Feature activation+1.017
have
Token have
Feature activation+0.000
cited
Token cited
Feature activation+0.000
a
Token a
Feature activation+0.000
certain
Token certain
Feature activation+0.000
book
Token book
Feature activation+0.847
by
Token by
Feature activation+3.007
Andrew
Token Andrew
Feature activation+0.330
Nicholson
Token Nicholson
Feature activation+0.223
,
Token,
Feature activation+1.757
which
Token which
Feature activation+2.404
I
Token I
Feature activation+0.000
aker
Tokenaker
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
book
Token book
Feature activation+1.143
published
Token published
Feature activation+2.960
a
Token a
Feature activation+1.623
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
back
Token back
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.070
L
TokenL
Feature activation+0.000
oved
Tokenoved
Feature activation+0.116
this
Token this
Feature activation+0.225
book
Token book
Feature activation+1.750
!
Token!
Feature activation+2.781
Overall
Token Overall
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.506
Ċ
TokenĊ
Feature activation+0.294
Well
TokenWell
Feature activation+0.672
written
Token written
Feature activation+3.290
book
Token book
Feature activation+0.844
and
Token and
Feature activation+1.594
we
Token we
Feature activation+0.000
physically
Token physically
Feature activation+0.000
marched
Token marched
Feature activation+0.000
it
Token it
Feature activation+2.755
over
Token over
Feature activation+1.285
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Fantasy
Token Fantasy
Feature activation+0.000
section
Token section
Feature activation+0.136
the
Token the
Feature activation+0.000
book
Token book
Feature activation+1.047
No
Token No
Feature activation+0.997
Turning
Token Turning
Feature activation+0.000
Back
Token Back
Feature activation+0.000
?
Token?
Feature activation+2.695
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dan
TokenDan
Feature activation+0.000
B
Token B
Feature activation+0.000
oul
Tokenoul
Feature activation+0.000
Fab
Token Fab
Feature activation+0.000
er
Tokener
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.279
is
Token is
Feature activation+0.821
out
Token out
Feature activation+2.694
soon
Token soon
Feature activation+0.000
.
Token.
Feature activation+0.250
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
book
Token book
Feature activation+0.000
City
Token City
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Sky
Token Sky
Feature activation+0.000
(
Token (
Feature activation+2.691
Times
TokenTimes
Feature activation+0.000
Books
Token Books
Feature activation+0.000
,
Token,
Feature activation+0.696
Henry
Token Henry
Feature activation+0.241
Hold
Token Hold
Feature activation+0.064
several
Token several
Feature activation+0.000
recent
Token recent
Feature activation+0.000
books
Token books
Feature activation+0.294
âĢĶ
Token âĢĶ
Feature activation+0.908
all
Token all
Feature activation+0.681
published
Token published
Feature activation+2.684
in
Token in
Feature activation+2.470
this
Token this
Feature activation+0.000
decade
Token decade
Feature activation+0.000
and
Token and
Feature activation+0.000
intended
Token intended
Feature activation+0.184
to
Token to
Feature activation+0.476
Spirit
Token Spirit
Feature activation+0.000
uality
Tokenuality
Feature activation+0.000
without
Token without
Feature activation+0.000
Religion
Token Religion
Feature activation+0.000
.
Token.
Feature activation+2.683
Ċ
TokenĊ
Feature activation+0.521
Ċ
TokenĊ
Feature activation+0.528
To
TokenTo
Feature activation+0.528
refute
Token refute
Feature activation+0.179
this
Token this
Feature activation+0.204
true
Token true
Feature activation+0.133
ly
Tokenly
Feature activation+0.018
was
Token was
Feature activation+1.163
a
Token a
Feature activation+1.144
great
Token great
Feature activation+1.258
book
Token book
Feature activation+2.659
to
Token to
Feature activation+0.911
listen
Token listen
Feature activation+0.605
to
Token to
Feature activation+0.822
!
Token!
Feature activation+1.993
Overall
Token Overall
Feature activation+0.011
,
Token,
Feature activation+1.645
applicable
Token applicable
Feature activation+0.763
,
Token,
Feature activation+0.278
and
Token and
Feature activation+0.795
powerful
Token powerful
Feature activation+1.450
.
Token.
Feature activation+2.646
Few
Token Few
Feature activation+0.184
dry
Token dry
Feature activation+0.901
spots
Token spots
Feature activation+0.222
.
Token.
Feature activation+0.593
Overall
Token Overall
Feature activation+0.041
okes
Tokenokes
Feature activation+0.000
Like
Token Like
Feature activation+0.000
a
Token a
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+2.643
Mal
Token Mal
Feature activation+0.000
aph
Tokenaph
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.947
Ŀ
TokenĿ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
book
Token book
Feature activation+0.644
that
Token that
Feature activation+2.628
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
worth
Token worth
Feature activation+0.018

Top DFA by src position
MAX = 4.249

pepp
Token pepp
Feature activation+0.004
Top resid features:
ered
Tokenered
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
The
Token The
Feature activation+0.004
Top resid features:
book
Token book
Feature activation+4.249
Top resid features:
has
Token has
Feature activation+0.007
Top resid features:
an
Token an
Feature activation+0.007
Top resid features:
easy
Token easy
Feature activation+0.012
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
to
Tokento
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
I
TokenI
Feature activation-0.001
Top resid features:
read
Token read
Feature activation+0.001
Top resid features:
this
Token this
Feature activation+0.072
Top resid features:
book
Token book
Feature activation+4.087
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
first
Token first
Feature activation+0.014
Top resid features:
time
Token time
Feature activation-0.001
Top resid features:
at
Token at
Feature activation-0.011
Top resid features:
about
Token about
Feature activation-0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.003
Top resid features:
Harper
Token Harper
Feature activation-0.002
Top resid features:
Design
Token Design
Feature activation-0.083
Top resid features:
said
Token said
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
book
Token book
Feature activation+3.985
Top resid features:
is
Token is
Feature activation+0.118
Top resid features:
meant
Token meant
Feature activation+0.024
Top resid features:
for
Token for
Feature activation-0.133
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
ages
Token ages
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
L
TokenL
Feature activation+0.003
Top resid features:
oved
Tokenoved
Feature activation+0.009
Top resid features:
this
Token this
Feature activation+0.038
Top resid features:
book
Token book
Feature activation+3.500
Top resid features:
!
Token!
Feature activation-0.005
Top resid features:
Overall
Token Overall
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Well
TokenWell
Feature activation+0.028
Top resid features:
can
Token can
Feature activation-0.003
Top resid features:
expect
Token expect
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
see
Token see
Feature activation-0.001
Top resid features:
his
Token his
Feature activation+0.007
Top resid features:
book
Token book
Feature activation+2.963
Top resid features:
released
Token released
Feature activation+0.142
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
Campbell
Token Campbell
Feature activation+0.002
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.003
Top resid features:
Harper
Token Harper
Feature activation-0.004
Top resid features:
Design
Token Design
Feature activation-0.041
Top resid features:
said
Token said
Feature activation-0.017
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
book
Token book
Feature activation+3.376
Top resid features:
is
Token is
Feature activation+0.269
Top resid features:
meant
Token meant
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
ages
Token ages
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
new
Token new
Feature activation+0.008
Top resid features:
book
Token book
Feature activation+3.795
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
Evangel
Token Evangel
Feature activation+0.001
Top resid features:
ical
Tokenical
Feature activation-0.004
Top resid features:
Exodus
Token Exodus
Feature activation-0.005
Top resid features:
:
Token:
Feature activation+0.012
Top resid features:
should
Token should
Feature activation+0.008
Top resid features:
have
Token have
Feature activation+0.020
Top resid features:
cited
Token cited
Feature activation-0.036
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
certain
Token certain
Feature activation+0.008
Top resid features:
book
Token book
Feature activation+3.540
Top resid features:
by
Token by
Feature activation+0.092
Top resid features:
Andrew
Token Andrew
Feature activation+0.000
Top resid features:
Nicholson
Token Nicholson
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
Ch
Token Ch
Feature activation+0.009
Top resid features:
aker
Tokenaker
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
book
Token book
Feature activation+3.550
Top resid features:
published
Token published
Feature activation-0.045
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
couple
Token couple
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
L
TokenL
Feature activation+0.012
Top resid features:
oved
Tokenoved
Feature activation+0.044
Top resid features:
this
Token this
Feature activation+0.086
Top resid features:
book
Token book
Feature activation+2.870
Top resid features:
!
Token!
Feature activation+0.038
Top resid features:
Overall
Token Overall
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:
Well
TokenWell
Feature activation+0.000
Top resid features:
So
TokenSo
Feature activation-0.002
Top resid features:
Dad
Token Dad
Feature activation-0.003
Top resid features:
picked
Token picked
Feature activation+0.001
Top resid features:
up
Token up
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
book
Token book
Feature activation+3.140
Top resid features:
and
Token and
Feature activation+0.119
Top resid features:
we
Token we
Feature activation+0.008
Top resid features:
physically
Token physically
Feature activation-0.019
Top resid features:
marched
Token marched
Feature activation+0.085
Top resid features:
it
Token it
Feature activation+0.006
Top resid features:
Why
TokenWhy
Feature activation+0.072
Top resid features:
did
Token did
Feature activation+0.058
Top resid features:
you
Token you
Feature activation+0.020
Top resid features:
call
Token call
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
book
Token book
Feature activation+2.329
Top resid features:
No
Token No
Feature activation+0.024
Top resid features:
Turning
Token Turning
Feature activation-0.032
Top resid features:
Back
Token Back
Feature activation-0.004
Top resid features:
?
Token?
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Published
TokenPublished
Feature activation-0.008
Top resid features:
by
Token by
Feature activation+0.017
Top resid features:
Fab
Token Fab
Feature activation-0.010
Top resid features:
er
Tokener
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
book
Token book
Feature activation+3.303
Top resid features:
is
Token is
Feature activation+0.103
Top resid features:
out
Token out
Feature activation-0.068
Top resid features:
soon
Token soon
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
failure
Token failure
Feature activation-0.000
Top resid features:
occurs
Token occurs
Feature activation-0.000
Top resid features:
."
Token."
Feature activation+0.002
Top resid features:
From
Token From
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
book
Token book
Feature activation+3.441
Top resid features:
City
Token City
Feature activation-0.007
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Sky
Token Sky
Feature activation-0.006
Top resid features:
(
Token (
Feature activation-0.144
Top resid features:
taking
Token taking
Feature activation-0.005
Top resid features:
account
Token account
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
several
Token several
Feature activation+0.024
Top resid features:
recent
Token recent
Feature activation+0.007
Top resid features:
books
Token books
Feature activation+3.256
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.155
Top resid features:
all
Token all
Feature activation+0.007
Top resid features:
published
Token published
Feature activation-0.122
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.125
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
his
Token his
Feature activation-0.013
Top resid features:
book
Token book
Feature activation+2.606
Top resid features:
W
Token W
Feature activation+0.039
Top resid features:
aking
Tokenaking
Feature activation-0.005
Top resid features:
Up
Token Up
Feature activation-0.001
Top resid features:
:
Token:
Feature activation+0.244
Top resid features:
A
Token A
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
L
TokenL
Feature activation+0.001
Top resid features:
oved
Tokenoved
Feature activation+0.003
Top resid features:
this
Token this
Feature activation+0.013
Top resid features:
book
Token book
Feature activation+1.630
Top resid features:
!
Token!
Feature activation+0.045
Top resid features:
Overall
Token Overall
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Well
TokenWell
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
L
TokenL
Feature activation+0.004
Top resid features:
oved
Tokenoved
Feature activation+0.003
Top resid features:
this
Token this
Feature activation+0.042
Top resid features:
book
Token book
Feature activation+2.667
Top resid features:
!
Token!
Feature activation+0.025
Top resid features:
Overall
Token Overall
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Well
TokenWell
Feature activation+0.021
Top resid features:
one
Token one
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
check
Token check
Feature activation+0.003
Top resid features:
out
Token out
Feature activation+0.010
Top resid features:
my
Token my
Feature activation+0.011
Top resid features:
book
Token book
Feature activation+2.923
Top resid features:
on
Token on
Feature activation+0.140
Top resid features:
mal
Token mal
Feature activation+0.011
Top resid features:
aph
Tokenaph
Feature activation+0.000
Top resid features:
ors
Tokenors
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.051
Top resid features:
book
Token book
Feature activation+3.008
Top resid features:
that
Token that
Feature activation+0.049
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:
always
Token always
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.04

Head 3: 0.04

Head 4: 0.03

Head 5: 0.04

Head 6: 0.02

Head 7: 0.04

Head 8: 0.03

Head 9: 0.05

Head 10: 0.52

Head 11: 0.14

Positive logits

paperback1.89

Chapters1.87

itled1.86

unpublished1.84

Reviewed1.76

essays1.76

Books1.73

titled1.73

excerpts1.71

Illustrated1.68

Publishers1.66

Tablet1.63

Review1.62

chapters1.61

pdf1.60

books1.60

written1.60

Gutenberg1.60

Books1.56

Paper1.56

Negative logits

cruising-1.51

slack-1.43

airst-1.43

caller-1.43

dispatcher-1.38

punt-1.38

patrol-1.38

hiber-1.38

lyn-1.36

Tigers-1.35

patrolling-1.35

whales-1.34

nuclear-1.34

spac-1.34

slaughter-1.34

dispatch-1.33

kill-1.33

mating-1.33

aggress-1.32

retaliate-1.31

INTERVAL 3.505 - 3.895
CONTAINS 0.000%

-
Token-
Feature activation+0.000
good
Tokengood
Feature activation+0.000
format
Token format
Feature activation+1.190
with
Token with
Feature activation+0.405
each
Token each
Feature activation+0.143
chapter
Token chapter
Feature activation+3.895
starting
Token starting
Feature activation+0.277
with
Token with
Feature activation+0.401
an
Token an
Feature activation+0.317
anecdote
Token anecdote
Feature activation+0.021
from
Token from
Feature activation+0.000

INTERVAL 3.116 - 3.505
CONTAINS 0.000%

two
Token two
Feature activation+0.000
[
Token [
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
it
Token it
Feature activation+1.209
comes
Token comes
Feature activation+0.545
out
Token out
Feature activation+3.164
],
Token],
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.600
'll
Token'll
Feature activation+0.443
be
Token be
Feature activation+0.358
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.521
is
Token is
Feature activation+1.938
meant
Token meant
Feature activation+3.043
for
Token for
Feature activation+3.364
all
Token all
Feature activation+0.489
ages
Token ages
Feature activation+0.000
.
Token.
Feature activation+0.953
Ċ
TokenĊ
Feature activation+0.419
Ċ
TokenĊ
Feature activation+0.611
I
Token I
Feature activation+0.065
decided
Token decided
Feature activation+0.050
to
Token to
Feature activation+0.000
listen
Token listen
Feature activation+0.569
to
Token to
Feature activation+0.667
it
Token it
Feature activation+3.425
recently
Token recently
Feature activation+0.235
,
Token,
Feature activation+0.177
and
Token and
Feature activation+0.056
am
Token am
Feature activation+0.000
so
Token so
Feature activation+0.000
!
Token!
Feature activation+2.781
Overall
Token Overall
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.506
Ċ
TokenĊ
Feature activation+0.294
Well
TokenWell
Feature activation+0.672
written
Token written
Feature activation+3.290
,
Token,
Feature activation+2.335
believable
Token believable
Feature activation+1.802
,
Token,
Feature activation+1.645
applicable
Token applicable
Feature activation+0.763
,
Token,
Feature activation+0.278

INTERVAL 2.726 - 3.116
CONTAINS 0.001%

aker
Tokenaker
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
book
Token book
Feature activation+1.143
published
Token published
Feature activation+2.960
a
Token a
Feature activation+1.623
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
back
Token back
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.070
L
TokenL
Feature activation+0.000
oved
Tokenoved
Feature activation+0.116
this
Token this
Feature activation+0.225
book
Token book
Feature activation+1.750
!
Token!
Feature activation+2.781
Overall
Token Overall
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.506
Ċ
TokenĊ
Feature activation+0.294
Well
TokenWell
Feature activation+0.672
written
Token written
Feature activation+3.290
have
Token have
Feature activation+0.000
cited
Token cited
Feature activation+0.000
a
Token a
Feature activation+0.000
certain
Token certain
Feature activation+0.000
book
Token book
Feature activation+0.847
by
Token by
Feature activation+3.007
Andrew
Token Andrew
Feature activation+0.330
Nicholson
Token Nicholson
Feature activation+0.223
,
Token,
Feature activation+1.757
which
Token which
Feature activation+2.404
I
Token I
Feature activation+0.000
book
Token book
Feature activation+0.844
and
Token and
Feature activation+1.594
we
Token we
Feature activation+0.000
physically
Token physically
Feature activation+0.000
marched
Token marched
Feature activation+0.000
it
Token it
Feature activation+2.755
over
Token over
Feature activation+1.285
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Fantasy
Token Fantasy
Feature activation+0.000
section
Token section
Feature activation+0.136
Path
Token Path
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
,
Token,
Feature activation+1.823
published
Token published
Feature activation+3.024
by
Token by
Feature activation+2.488
Ign
Token Ign
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ius
Tokenius
Feature activation+0.000
Press
Token Press
Feature activation+1.017

INTERVAL 2.337 - 2.726
CONTAINS 0.003%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
book
Token book
Feature activation+0.644
that
Token that
Feature activation+2.628
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
worth
Token worth
Feature activation+0.018
more
Token more
Feature activation+0.000
printed
Token printed
Feature activation+0.000
copies
Token copies
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+2.409
,
Token,
Feature activation+0.403
a
Token a
Feature activation+0.000
hard
Token hard
Feature activation+0.158
cover
Token cover
Feature activation+2.452
versus
Token versus
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
table
Token table
Feature activation+0.000
book
Token book
Feature activation+0.006
called
Token called
Feature activation+2.341
Birds
Token Birds
Feature activation+0.000
of
Token of
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
in
Token in
Feature activation+0.000
homage
Token homage
Feature activation+0.468
,
Token,
Feature activation+1.645
applicable
Token applicable
Feature activation+0.763
,
Token,
Feature activation+0.278
and
Token and
Feature activation+0.795
powerful
Token powerful
Feature activation+1.450
.
Token.
Feature activation+2.646
Few
Token Few
Feature activation+0.184
dry
Token dry
Feature activation+0.901
spots
Token spots
Feature activation+0.222
.
Token.
Feature activation+0.593
Overall
Token Overall
Feature activation+0.041
Nicholson
Token Nicholson
Feature activation+1.010
âĢ
TokenâĢ
Feature activation+0.726
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.561
book
Token book
Feature activation+1.416
about
Token about
Feature activation+2.387
10
Token 10
Feature activation+0.216
times
Token times
Feature activation+0.063
in
Token in
Feature activation+0.460
the
Token the
Feature activation+0.130
main
Token main
Feature activation+0.076

INTERVAL 1.947 - 2.337
CONTAINS 0.004%

.
Token.
Feature activation+0.457
These
Token These
Feature activation+0.614
were
Token were
Feature activation+1.252
honest
Token honest
Feature activation+0.467
,
Token,
Feature activation+0.497
arresting
Token arresting
Feature activation+1.964
and
Token and
Feature activation+0.572
challenging
Token challenging
Feature activation+2.181
pieces
Token pieces
Feature activation+1.534
of
Token of
Feature activation+0.000
work
Token work
Feature activation+1.024
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
trade
Token trade
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
same
Token same
Feature activation+0.000
width
Token width
Feature activation+2.230
as
Token as
Feature activation+0.250
a
Token a
Feature activation+0.000
standard
Token standard
Feature activation+0.063
hard
Token hard
Feature activation+0.611
cover
Tokencover
Feature activation+0.812
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
book
Token book
Feature activation+1.793
is
Token is
Feature activation+1.271
based
Token based
Feature activation+2.188
on
Token on
Feature activation+1.257
a
Token a
Feature activation+0.477
class
Token class
Feature activation+0.000
I
Token I
Feature activation+0.000
taught
Token taught
Feature activation+0.104
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
academy
Token academy
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
that
Token that
Feature activation+0.246
offer
Token offer
Feature activation+2.282
a
Token a
Feature activation+0.307
multif
Token multif
Feature activation+0.000
acet
Tokenacet
Feature activation+0.000
ed
Tokened
Feature activation+0.000
case
Token case
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.099
an
Token an
Feature activation+0.472
interesting
Token interesting
Feature activation+0.212
size
Token size
Feature activation+2.255
,
Token,
Feature activation+0.470
what
Token what
Feature activation+0.120
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 1.558 - 1.947
CONTAINS 0.008%

1968
Token 1968
Feature activation+0.000
!
Token!
Feature activation+0.689
I
Token I
Feature activation+0.195
remember
Token remember
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+1.615
impacted
Token impacted
Feature activation+1.497
my
Token my
Feature activation+0.000
faith
Token faith
Feature activation+0.000
.
Token.
Feature activation+0.069
I
Token I
Feature activation+0.065
RE
Token RE
Feature activation+0.323
VIEW
TokenVIEW
Feature activation+0.463
TO
Token TO
Feature activation+0.302
BE
Token BE
Feature activation+0.095
PR
Token PR
Feature activation+0.409
INT
TokenINT
Feature activation+1.584
ED
TokenED
Feature activation+0.797
IN
Token IN
Feature activation+0.417
A
Token A
Feature activation+0.000
MAG
Token MAG
Feature activation+0.217
AZ
TokenAZ
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.336
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+1.273
2004
Token2004
Feature activation+1.159
),
Token),
Feature activation+1.559
two
Token two
Feature activation+0.221
components
Token components
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
national
Token national
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
book
Token book
Feature activation+1.143
published
Token published
Feature activation+2.960
a
Token a
Feature activation+1.623
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
back
Token back
Feature activation+0.000
.
Token.
Feature activation+0.844
Fine
Token Fine
Feature activation+0.000
-
Token-
Feature activation+0.000
T
TokenT
Feature activation+0.000
uning
Tokenuning
Feature activation+0.000
,
Token,
Feature activation+0.934
is
Token is
Feature activation+1.756
certainly
Token certainly
Feature activation+0.321
a
Token a
Feature activation+1.064
timely
Token timely
Feature activation+0.358
one
Token one
Feature activation+1.268
based
Token based
Feature activation+1.655

INTERVAL 1.168 - 1.558
CONTAINS 0.015%

find
Token find
Feature activation+0.321
more
Token more
Feature activation+0.089
information
Token information
Feature activation+0.061
about
Token about
Feature activation+0.169
the
Token the
Feature activation+0.037
books
Token books
Feature activation+1.289
there
Token there
Feature activation+0.170
.
Token.
Feature activation+0.397
This
Token This
Feature activation+0.151
is
Token is
Feature activation+0.069
my
Token my
Feature activation+0.000
new
Token new
Feature activation+0.000
paperback
Token paperback
Feature activation+0.170
edition
Token edition
Feature activation+0.916
was
Token was
Feature activation+0.319
published
Token published
Feature activation+1.388
in
Token in
Feature activation+1.286
2008
Token 2008
Feature activation+0.000
.
Token.
Feature activation+0.632
Ċ
TokenĊ
Feature activation+0.576
Ċ
TokenĊ
Feature activation+0.641
Contents
TokenContents
Feature activation+0.096
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
book
Token book
Feature activation+1.683
in
Token in
Feature activation+1.457
his
Token his
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
this
Token this
Feature activation+0.226
book
Token book
Feature activation+1.394
,
Token,
Feature activation+1.098
you
Token you
Feature activation+0.561
will
Token will
Feature activation+1.219
go
Token go
Feature activation+1.167
along
Token along
Feature activation+0.085
last
Token last
Feature activation+0.000
third
Token third
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+1.402
contains
Token contains
Feature activation+1.477
all
Token all
Feature activation+0.513
the
Token the
Feature activation+0.642
rules
Token rules
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000

INTERVAL 0.779 - 1.168
CONTAINS 0.035%

supporters
Token supporters
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
his
Token his
Feature activation+1.103
work
Token work
Feature activation+0.865
before
Token before
Feature activation+0.214
taking
Token taking
Feature activation+0.306
sides
Token sides
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.138
More
Token More
Feature activation+0.000
information
Token information
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.830
,
Token,
Feature activation+1.540
and
Token and
Feature activation+0.182
our
Token our
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
book
Token book
Feature activation+0.406
grow
Token grow
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
autobiography
Token autobiography
Feature activation+0.000
,
Token,
Feature activation+0.796
Who
Token Who
Feature activation+0.000
I
Token I
Feature activation+0.000
Am
Token Am
Feature activation+0.000
,
Token ,
Feature activation+1.646
Pete
Token Pete
Feature activation+0.000
,
Token,
Feature activation+0.278
and
Token and
Feature activation+0.795
powerful
Token powerful
Feature activation+1.450
.
Token.
Feature activation+2.646
Few
Token Few
Feature activation+0.184
dry
Token dry
Feature activation+0.901
spots
Token spots
Feature activation+0.222
.
Token.
Feature activation+0.593
Overall
Token Overall
Feature activation+0.041
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
osa
Tokenosa
Feature activation+0.000
(
Token (
Feature activation+0.000
a
Tokena
Feature activation+0.000
Sanskrit
Token Sanskrit
Feature activation+0.000
dictionary
Token dictionary
Feature activation+0.000
by
Token by
Feature activation+0.889
ancient
Token ancient
Feature activation+0.000
Buddhist
Token Buddhist
Feature activation+0.000
scholar
Token scholar
Feature activation+0.000
Amar
Token Amar
Feature activation+0.000
as
Tokenas
Feature activation+0.000

INTERVAL 0.389 - 0.779
CONTAINS 0.083%

Bird
Token Bird
Feature activation+0.000
released
Token released
Feature activation+0.307
in
Token in
Feature activation+0.363
1965
Token 1965
Feature activation+0.000
.
Token.
Feature activation+0.322
It
Token It
Feature activation+0.411
consists
Token consists
Feature activation+0.681
of
Token of
Feature activation+0.925
a
Token a
Feature activation+0.853
series
Token series
Feature activation+0.305
of
Token of
Feature activation+0.066
Ign
Token Ign
Feature activation+0.040
ite
Tokenite
Feature activation+0.225
:
Token:
Feature activation+0.000
Book
Token Book
Feature activation+0.318
Three
Token Three
Feature activation+0.158
of
Token of
Feature activation+0.710
the
Token the
Feature activation+0.506
Resistance
Token Resistance
Feature activation+0.000
Series
Token Series
Feature activation+0.000
.
Token.
Feature activation+0.000
ï
Tokenï
Feature activation+0.000
and
Token and
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
Leg
Token Leg
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.744
Ċ
TokenĊ
Feature activation+0.762
In
TokenIn
Feature activation+0.000
March
Token March
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
,
Token,
Feature activation+0.000
us
Token us
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
Your
Token Your
Feature activation+0.604
statistical
Token statistical
Feature activation+0.000
experience
Token experience
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.035
âĢ¢
TokenâĢ¢
Feature activation+0.000
mechanical
Token mechanical
Feature activation+0.000
parts
Token parts
Feature activation+0.000
.
Token.
Feature activation+0.000
Think
Token Think
Feature activation+0.000
books
Token books
Feature activation+0.000
like
Token like
Feature activation+0.752
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
20
Token20
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000

INTERVAL 0.000 - 0.389
CONTAINS 99.852%

Winter
Token Winter
Feature activation+0.000
War
Token War
Feature activation+0.000
,
Token,
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
poor
Token poor
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
and
Token and
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
steel
Token steel
Feature activation+0.000
helps
Token helps
Feature activation+0.000
to
Token to
Feature activation+0.000
straight
Token straight
Feature activation+0.000
en
Tokenen
Feature activation+0.000
it
Token it
Feature activation+0.000
between
Token between
Feature activation+0.000
shar
Token shar
Feature activation+0.000
staged
Token staged
Feature activation+0.000
a
Token a
Feature activation+0.000
dramatic
Token dramatic
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
cele
Tokencele
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
intervention
Token intervention
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.000
51
Token51
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Minnesota
TokenMinnesota
Feature activation+0.000
:
Token:
Feature activation+0.000
30
Token 30
Feature activation+0.000
cents
Token cents
Feature activation+0.000
per
Token per
Feature activation+0.000
mill
Token mill
Feature activation+0.000
to
Token to
Feature activation+0.000
liber
Token liber
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
watered
Token watered
Feature activation+0.000
golf
Token golf
Feature activation+0.000
courses
Token courses
Feature activation+0.000
,
Token,
Feature activation+0.000
c
Token c
Feature activation+0.000
em
Tokenem
Feature activation+0.000
eter
Tokeneter
Feature activation+0.000
ies
Tokenies
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H5.10: (feature 13524)

TOP ACTIVATIONS
MAX = 3.899

more
Token more
Feature activation+0.000
conservative
Token conservative
Feature activation+0.349
,
Token,
Feature activation+0.134
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+3.899
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.955
jur
Token jur
Feature activation+3.607
is
Tokenis
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+3.899
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.955
jur
Token jur
Feature activation+3.607
is
Tokenis
Feature activation+0.000
pr
Tokenpr
Feature activation+0.036
udence
Tokenudence
Feature activation+2.315
on
Token on
Feature activation+0.151
abortion
Token abortion
Feature activation+0.000
25
Token 25
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
divided
Token divided
Feature activation+3.323
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.338
Monday
Token Monday
Feature activation+1.408
that
Token that
Feature activation+2.159
it
Token it
Feature activation+0.768
would
Token would
Feature activation+0.656
not
Token not
Feature activation+0.941
hear
Token hear
Feature activation+3.165
the
Token the
Feature activation+0.772
case
Token case
Feature activation+1.226
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.242
13
Token 13
Feature activation+0.068
also
Token also
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.025
Supreme
Token Supreme
Feature activation+0.762
Court
Token Court
Feature activation+1.001
in
Token in
Feature activation+3.123
the
Token the
Feature activation+2.194
pending
Token pending
Feature activation+1.265
decision
Token decision
Feature activation+3.032
in
Token in
Feature activation+3.079
the
Token the
Feature activation+2.057
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+1.439
,
Token,
Feature activation+2.336
in
Token in
Feature activation+2.966
its
Token its
Feature activation+3.120
Parents
Token Parents
Feature activation+0.000
Inv
Token Inv
Feature activation+0.000
olved
Tokenolved
Feature activation+0.000
in
Token in
Feature activation+0.000
Community
Token Community
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.338
Court
Token Court
Feature activation+2.048
debated
Token debated
Feature activation+3.079
whether
Token whether
Feature activation+1.352
companies
Token companies
Feature activation+0.000
can
Token can
Feature activation+0.000
assert
Token assert
Feature activation+0.000
religious
Token religious
Feature activation+0.000
Court
Token Court
Feature activation+1.001
in
Token in
Feature activation+3.123
the
Token the
Feature activation+2.194
pending
Token pending
Feature activation+1.265
decision
Token decision
Feature activation+3.032
in
Token in
Feature activation+3.079
the
Token the
Feature activation+2.057
Hobby
Token Hobby
Feature activation+0.000
Lobby
Token Lobby
Feature activation+0.000
case
Token case
Feature activation+0.003
.
Token.
Feature activation+0.296
Supreme
Token Supreme
Feature activation+0.762
Court
Token Court
Feature activation+1.001
in
Token in
Feature activation+3.123
the
Token the
Feature activation+2.194
pending
Token pending
Feature activation+1.265
decision
Token decision
Feature activation+3.032
in
Token in
Feature activation+3.079
the
Token the
Feature activation+2.057
Hobby
Token Hobby
Feature activation+0.000
Lobby
Token Lobby
Feature activation+0.000
case
Token case
Feature activation+0.003
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Recent
TokenRecent
Feature activation+0.000
Supreme
Token Supreme
Feature activation+2.333
Court
Token Court
Feature activation+1.728
opinions
Token opinions
Feature activation+3.030
regarding
Token regarding
Feature activation+1.827
religion
Token religion
Feature activation+0.000
,
Token,
Feature activation+0.000
voting
Token voting
Feature activation+0.000
rights
Token rights
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+1.439
,
Token,
Feature activation+2.336
in
Token in
Feature activation+2.966
its
Token its
Feature activation+3.120
Parents
Token Parents
Feature activation+0.000
Inv
Token Inv
Feature activation+0.000
olved
Tokenolved
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+3.899
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.955
jur
Token jur
Feature activation+3.607
is
Tokenis
Feature activation+0.000
pr
Tokenpr
Feature activation+0.036
udence
Tokenudence
Feature activation+2.315
on
Token on
Feature activation+0.151
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+2.159
in
Token in
Feature activation+2.722
Washington
Token Washington
Feature activation+0.196
,
Token,
Feature activation+0.000
D
Token D
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.841
Ċ
TokenĊ
Feature activation+0.367
Ċ
TokenĊ
Feature activation+0.454
In
TokenIn
Feature activation+0.930
a
Token a
Feature activation+1.557
ruling
Token ruling
Feature activation+2.693
January
Token January
Feature activation+0.542
11
Token 11
Feature activation+0.786
that
Token that
Feature activation+1.850
constitutes
Token constitutes
Feature activation+0.425
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.004
Court
Token Court
Feature activation+0.897
delivered
Token delivered
Feature activation+3.048
a
Token a
Feature activation+2.627
landmark
Token landmark
Feature activation+0.864
judgment
Token judgment
Feature activation+0.741
regarding
Token regarding
Feature activation+1.005
leaders
Token leaders
Feature activation+0.000
with
Token with
Feature activation+0.000
political
Token political
Feature activation+0.000
makeup
Token makeup
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.408
Court
Token Court
Feature activation+2.577
had
Token had
Feature activation+0.000
turned
Token turned
Feature activation+0.000
more
Token more
Feature activation+0.000
conservative
Token conservative
Feature activation+0.349
,
Token,
Feature activation+0.134
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.704
is
Token is
Feature activation+2.246
expected
Token expected
Feature activation+0.489
to
Token to
Feature activation+1.534
rule
Token rule
Feature activation+2.526
on
Token on
Feature activation+2.395
the
Token the
Feature activation+0.154
issue
Token issue
Feature activation+0.148
of
Token of
Feature activation+0.000
same
Token same
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
six
Token six
Feature activation+0.928
-
Token-
Feature activation+0.304
justice
Tokenjustice
Feature activation+1.714
majority
Token majority
Feature activation+2.451
led
Token led
Feature activation+0.699
by
Token by
Feature activation+1.118
Ruth
Token Ruth
Feature activation+0.916
B
Token B
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
Court
Token Court
Feature activation+0.641
's
Token's
Feature activation+2.423
landmark
Token landmark
Feature activation+0.667
campaign
Token campaign
Feature activation+0.000
finance
Token finance
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
,
Token,
Feature activation+0.000
signals
Token signals
Feature activation+0.000
on
Token on
Feature activation+0.266
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.342
might
Token might
Feature activation+0.000
rule
Token rule
Feature activation+2.405
in
Token in
Feature activation+0.906
the
Token the
Feature activation+0.389
Texas
Token Texas
Feature activation+0.000
case
Token case
Feature activation+0.144
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 3.758

political
Token political
Feature activation-0.019
Top resid features:
makeup
Token makeup
Feature activation-0.038
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
Supreme
Token Supreme
Feature activation+0.774
Top resid features:
Court
Token Court
Feature activation+3.633
Top resid features:
had
Token had
Feature activation-0.059
Top resid features:
turned
Token turned
Feature activation-0.004
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
conservative
Token conservative
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
political
Token political
Feature activation-0.014
Top resid features:
makeup
Token makeup
Feature activation-0.023
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Supreme
Token Supreme
Feature activation+0.160
Top resid features:
Court
Token Court
Feature activation+2.742
Top resid features:
had
Token had
Feature activation-0.011
Top resid features:
turned
Token turned
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
conservative
Token conservative
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
U
Token U
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
S
TokenS
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Supreme
Token Supreme
Feature activation+0.266
Top resid features:
Court
Token Court
Feature activation+3.758
Top resid features:
in
Token in
Feature activation+0.030
Top resid features:
Washington
Token Washington
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
D
Token D
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
U
Token U
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
S
TokenS
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Supreme
Token Supreme
Feature activation+0.581
Top resid features:
Court
Token Court
Feature activation+3.161
Top resid features:
announced
Token announced
Feature activation+0.023
Top resid features:
Monday
Token Monday
Feature activation+0.044
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
it
Token it
Feature activation-0.003
Top resid features:
would
Token would
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
also
Token also
Feature activation+0.016
Top resid features:
at
Token at
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
Supreme
Token Supreme
Feature activation+0.576
Top resid features:
Court
Token Court
Feature activation+2.264
Top resid features:
in
Token in
Feature activation+0.138
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pending
Token pending
Feature activation+0.000
Top resid features:
decision
Token decision
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
U
Token U
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
S
TokenS
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Supreme
Token Supreme
Feature activation+1.700
Top resid features:
Court
Token Court
Feature activation+1.594
Top resid features:
,
Token,
Feature activation+0.267
Top resid features:
in
Token in
Feature activation+0.202
Top resid features:
its
Token its
Feature activation+0.055
Top resid features:
Parents
Token Parents
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
S
TokenS
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Supreme
Token Supreme
Feature activation+0.511
Top resid features:
Court
Token Court
Feature activation+1.642
Top resid features:
in
Token in
Feature activation+0.038
Top resid features:
Washington
Token Washington
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
D
Token D
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
pass
Token pass
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Supreme
Token Supreme
Feature activation+0.176
Top resid features:
Court
Token Court
Feature activation+1.655
Top resid features:
seems
Token seems
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
saying
Token saying
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
pass
Token pass
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Supreme
Token Supreme
Feature activation+0.533
Top resid features:
Court
Token Court
Feature activation+1.600
Top resid features:
seems
Token seems
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
saying
Token saying
Feature activation+0.007
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
actions
Token actions
Feature activation-0.028
Top resid features:
by
Token by
Feature activation-0.023
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
US
Token US
Feature activation-0.002
Top resid features:
Supreme
Token Supreme
Feature activation+0.631
Top resid features:
Court
Token Court
Feature activation+2.454
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
By
TokenBy
Feature activation-0.007
Top resid features:
Tom
Token Tom
Feature activation+0.001
Top resid features:
Carter
Token Carter
Feature activation+0.001
Top resid features:
U
Token U
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Supreme
Token Supreme
Feature activation+0.882
Top resid features:
Court
Token Court
Feature activation+2.027
Top resid features:
,
Token,
Feature activation+0.178
Top resid features:
in
Token in
Feature activation+0.043
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
Parents
Token Parents
Feature activation+0.000
Top resid features:
Inv
Token Inv
Feature activation+0.000
Top resid features:
political
Token political
Feature activation-0.003
Top resid features:
makeup
Token makeup
Feature activation-0.013
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Supreme
Token Supreme
Feature activation+0.207
Top resid features:
Court
Token Court
Feature activation+3.135
Top resid features:
had
Token had
Feature activation+0.018
Top resid features:
turned
Token turned
Feature activation+0.002
Top resid features:
more
Token more
Feature activation-0.001
Top resid features:
conservative
Token conservative
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
U
Token U
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
S
TokenS
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Supreme
Token Supreme
Feature activation+1.259
Top resid features:
Court
Token Court
Feature activation+2.023
Top resid features:
in
Token in
Feature activation+0.198
Top resid features:
Washington
Token Washington
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
actions
Token actions
Feature activation-0.010
Top resid features:
by
Token by
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
Supreme
Token Supreme
Feature activation+0.624
Top resid features:
Court
Token Court
Feature activation+1.980
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
By
TokenBy
Feature activation-0.004
Top resid features:
Tom
Token Tom
Feature activation+0.000
Top resid features:
Carter
Token Carter
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.214
Top resid features:
The
TokenThe
Feature activation-0.004
Top resid features:
Supreme
Token Supreme
Feature activation+0.320
Top resid features:
Court
Token Court
Feature activation+2.942
Top resid features:
delivered
Token delivered
Feature activation+0.081
Top resid features:
a
Token a
Feature activation+0.083
Top resid features:
landmark
Token landmark
Feature activation+0.000
Top resid features:
judgment
Token judgment
Feature activation+0.000
Top resid features:
regarding
Token regarding
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
political
Token political
Feature activation-0.007
Top resid features:
makeup
Token makeup
Feature activation-0.039
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
Supreme
Token Supreme
Feature activation+2.024
Top resid features:
Court
Token Court
Feature activation+1.237
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
turned
Token turned
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
conservative
Token conservative
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.009
Top resid features:
released
Token released
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
The
Token The
Feature activation+0.011
Top resid features:
US
Token US
Feature activation-0.001
Top resid features:
Supreme
Token Supreme
Feature activation+1.447
Top resid features:
Court
Token Court
Feature activation+1.421
Top resid features:
is
Token is
Feature activation+0.111
Top resid features:
expected
Token expected
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.092
Top resid features:
rule
Token rule
Feature activation+0.068
Top resid features:
On
TokenOn
Feature activation-0.004
Top resid features:
Thursday
Token Thursday
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Supreme
Token Supreme
Feature activation+0.152
Top resid features:
Court
Token Court
Feature activation+3.123
Top resid features:
ruled
Token ruled
Feature activation+0.251
Top resid features:
that
Token that
Feature activation+0.031
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
definition
Token definition
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
corporations
Token corporations
Feature activation+0.008
Top resid features:
that
Token that
Feature activation-0.029
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
make
Token make
Feature activation-0.020
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
Court
Token Court
Feature activation+3.031
Top resid features:
's
Token's
Feature activation+0.282
Top resid features:
landmark
Token landmark
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+0.000
Top resid features:
finance
Token finance
Feature activation+0.000
Top resid features:
ruling
Token ruling
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
high
Token high
Feature activation-0.001
Top resid features:
court
Token court
Feature activation+3.063
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
action
Token action
Feature activation-0.016
Top resid features:
sent
Token sent
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.05

Head 3: 0.05

Head 4: 0.03

Head 5: 0.04

Head 6: 0.03

Head 7: 0.04

Head 8: 0.03

Head 9: 0.04

Head 10: 0.51

Head 11: 0.15

Positive logits

OTUS1.89

Scalia1.83

justices1.53

parity1.51

Neutral1.41

Supreme1.39

iuses1.36

unic1.34

Phi1.31

stars1.29

plurality1.29

Ober1.28

Carey1.28

Theater1.27

Academy1.25

Stephen1.24

ropolitan1.24

witz1.24

neutrality1.23

liberals1.23

Negative logits

inav-1.80

pak-1.44

Chocobo-1.43

pain-1.39

Kaf-1.39

backpack-1.38

>>\-1.35

Filename-1.34

pkg-1.29

PW-1.29

Gum-1.28

regimen-1.27

kef-1.27

uild-1.27

harrowing-1.25

Rena-1.25

Kurd-1.24

grain-1.23

76561-1.22

chwitz-1.22

INTERVAL 3.509 - 3.899
CONTAINS 0.000%

more
Token more
Feature activation+0.000
conservative
Token conservative
Feature activation+0.349
,
Token,
Feature activation+0.134
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+3.899
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.955
jur
Token jur
Feature activation+3.607
is
Tokenis
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+3.899
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.955
jur
Token jur
Feature activation+3.607
is
Tokenis
Feature activation+0.000
pr
Tokenpr
Feature activation+0.036
udence
Tokenudence
Feature activation+2.315
on
Token on
Feature activation+0.151
abortion
Token abortion
Feature activation+0.000

INTERVAL 3.119 - 3.509
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+1.439
,
Token,
Feature activation+2.336
in
Token in
Feature activation+2.966
its
Token its
Feature activation+3.120
Parents
Token Parents
Feature activation+0.000
Inv
Token Inv
Feature activation+0.000
olved
Tokenolved
Feature activation+0.000
in
Token in
Feature activation+0.000
Community
Token Community
Feature activation+0.000
25
Token 25
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
divided
Token divided
Feature activation+3.323
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.338
Monday
Token Monday
Feature activation+1.408
that
Token that
Feature activation+2.159
it
Token it
Feature activation+0.768
would
Token would
Feature activation+0.656
not
Token not
Feature activation+0.941
hear
Token hear
Feature activation+3.165
the
Token the
Feature activation+0.772
case
Token case
Feature activation+1.226
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.242
13
Token 13
Feature activation+0.068
also
Token also
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.025
Supreme
Token Supreme
Feature activation+0.762
Court
Token Court
Feature activation+1.001
in
Token in
Feature activation+3.123
the
Token the
Feature activation+2.194
pending
Token pending
Feature activation+1.265
decision
Token decision
Feature activation+3.032
in
Token in
Feature activation+3.079
the
Token the
Feature activation+2.057

INTERVAL 2.729 - 3.119
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Recent
TokenRecent
Feature activation+0.000
Supreme
Token Supreme
Feature activation+2.333
Court
Token Court
Feature activation+1.728
opinions
Token opinions
Feature activation+3.030
regarding
Token regarding
Feature activation+1.827
religion
Token religion
Feature activation+0.000
,
Token,
Feature activation+0.000
voting
Token voting
Feature activation+0.000
rights
Token rights
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.338
Court
Token Court
Feature activation+2.048
debated
Token debated
Feature activation+3.079
whether
Token whether
Feature activation+1.352
companies
Token companies
Feature activation+0.000
can
Token can
Feature activation+0.000
assert
Token assert
Feature activation+0.000
religious
Token religious
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+3.899
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.955
jur
Token jur
Feature activation+3.607
is
Tokenis
Feature activation+0.000
pr
Tokenpr
Feature activation+0.036
udence
Tokenudence
Feature activation+2.315
on
Token on
Feature activation+0.151
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+1.439
,
Token,
Feature activation+2.336
in
Token in
Feature activation+2.966
its
Token its
Feature activation+3.120
Parents
Token Parents
Feature activation+0.000
Inv
Token Inv
Feature activation+0.000
olved
Tokenolved
Feature activation+0.000
in
Token in
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.762
Court
Token Court
Feature activation+1.001
in
Token in
Feature activation+3.123
the
Token the
Feature activation+2.194
pending
Token pending
Feature activation+1.265
decision
Token decision
Feature activation+3.032
in
Token in
Feature activation+3.079
the
Token the
Feature activation+2.057
Hobby
Token Hobby
Feature activation+0.000
Lobby
Token Lobby
Feature activation+0.000
case
Token case
Feature activation+0.003

INTERVAL 2.339 - 2.729
CONTAINS 0.001%

Court
Token Court
Feature activation+1.003
Practice
Token Practice
Feature activation+0.537
Court
Token Court
Feature activation+0.159
.
Token.
Feature activation+0.780
When
Token When
Feature activation+0.778
granting
Token granting
Feature activation+2.368
the
Token the
Feature activation+0.685
injunction
Token injunction
Feature activation+0.000
,
Token,
Feature activation+0.000
Justice
Token Justice
Feature activation+2.108
Clyde
Token Clyde
Feature activation+0.185
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+2.159
in
Token in
Feature activation+2.722
Washington
Token Washington
Feature activation+0.196
,
Token,
Feature activation+0.000
D
Token D
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
attack
Token attack
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+1.002
Court
Token Court
Feature activation+1.844
justice
Token justice
Feature activation+2.362
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
tweeted
Token tweeted
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
Court
Token Court
Feature activation+0.641
's
Token's
Feature activation+2.423
landmark
Token landmark
Feature activation+0.667
campaign
Token campaign
Feature activation+0.000
finance
Token finance
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.004
Court
Token Court
Feature activation+0.897
delivered
Token delivered
Feature activation+3.048
a
Token a
Feature activation+2.627
landmark
Token landmark
Feature activation+0.864
judgment
Token judgment
Feature activation+0.741
regarding
Token regarding
Feature activation+1.005
leaders
Token leaders
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 1.949 - 2.339
CONTAINS 0.003%

.
Token.
Feature activation+0.114
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.047
the
Token the
Feature activation+0.000
Court
Token Court
Feature activation+2.078
declined
Token declined
Feature activation+1.257
to
Token to
Feature activation+1.928
review
Token review
Feature activation+0.703
the
Token the
Feature activation+0.000
Tenth
Token Tenth
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
disgrace
Token disgrace
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+2.067
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
she
Token she
Feature activation+0.000
pass
Token pass
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.137
Court
Token Court
Feature activation+1.537
seems
Token seems
Feature activation+1.958
to
Token to
Feature activation+1.440
be
Token be
Feature activation+1.268
saying
Token saying
Feature activation+1.638
:
Token:
Feature activation+1.318
This
Token This
Feature activation+0.239
no
Token no
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+2.052
would
Token would
Feature activation+0.000
fall
Token fall
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
kind
Token kind
Feature activation+0.000
no
Token no
Feature activation+0.000
matter
Token matter
Feature activation+0.000
how
Token how
Feature activation+0.000
they
Token they
Feature activation+0.751
eventually
Token eventually
Feature activation+0.000
rule
Token rule
Feature activation+2.262
,
Token,
Feature activation+0.000
Wal
Token Wal
Feature activation+0.000
-
Token-
Feature activation+0.000
Mart
TokenMart
Feature activation+0.000
already
Token already
Feature activation+0.000

INTERVAL 1.559 - 1.949
CONTAINS 0.003%

't
Token't
Feature activation+0.000
sure
Token sure
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.806
Court
Token Court
Feature activation+1.920
should
Token should
Feature activation+1.592
have
Token have
Feature activation+0.661
even
Token even
Feature activation+0.647
taken
Token taken
Feature activation+0.783
the
Token the
Feature activation+0.499
case
Token case
Feature activation+0.881
2012
Token 2012
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Recent
TokenRecent
Feature activation+0.000
Supreme
Token Supreme
Feature activation+2.333
Court
Token Court
Feature activation+1.728
opinions
Token opinions
Feature activation+3.030
regarding
Token regarding
Feature activation+1.827
religion
Token religion
Feature activation+0.000
,
Token,
Feature activation+0.000
voting
Token voting
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
sure
Token sure
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.806
Court
Token Court
Feature activation+1.920
should
Token should
Feature activation+1.592
have
Token have
Feature activation+0.661
even
Token even
Feature activation+0.647
taken
Token taken
Feature activation+0.783
the
Token the
Feature activation+0.499
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
potential
Token potential
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.081
Court
Token Court
Feature activation+1.345
justice
Token justice
Feature activation+1.771
âĢĶ
Token âĢĶ
Feature activation+0.721
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.000
is
Token is
Feature activation+0.999
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.853
decide
Token decide
Feature activation+1.594
tomorrow
Token tomorrow
Feature activation+0.818
:
Token:
Feature activation+0.000
It
Token It
Feature activation+0.263
will
Token will
Feature activation+0.178
uphold
Token uphold
Feature activation+0.626

INTERVAL 1.170 - 1.559
CONTAINS 0.007%

.
Token.
Feature activation+0.136
The
Token The
Feature activation+0.000
5
Token 5
Feature activation+2.229
-
Token-
Feature activation+1.983
4
Token4
Feature activation+2.082
decision
Token decision
Feature activation+1.510
in
Token in
Feature activation+1.162
Citizen
Token Citizen
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
the
Token the
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.408
ruled
Token ruled
Feature activation+1.210
Thursday
Token Thursday
Feature activation+1.466
the
Token the
Feature activation+0.000
governor
Token governor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
it
Token it
Feature activation+0.768
would
Token would
Feature activation+0.656
not
Token not
Feature activation+0.941
hear
Token hear
Feature activation+3.165
the
Token the
Feature activation+0.772
case
Token case
Feature activation+1.226
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.242
13
Token 13
Feature activation+0.068
-
Token-
Feature activation+1.833
year
Tokenyear
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
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+1.451
,
Token,
Feature activation+0.144
said
Token said
Feature activation+0.497
it
Token it
Feature activation+0.203
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.000
week
Token week
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
decides
Token decides
Feature activation+1.474
on
Token on
Feature activation+1.590
the
Token the
Feature activation+0.000
outcome
Token outcome
Feature activation+0.528
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 0.780 - 1.170
CONTAINS 0.010%

the
Token the
Feature activation+0.000
removal
Token removal
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.948
Court
Token Court
Feature activation+2.100
.
Token.
Feature activation+0.114
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
V
TokenV
Feature activation+0.000
It
TokenIt
Feature activation+0.349
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.289
case
Token case
Feature activation+0.370
and
Token and
Feature activation+0.000
decided
Token decided
Feature activation+0.907
it
Token it
Feature activation+0.432
at
Token at
Feature activation+0.017
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
when
Token when
Feature activation+0.000
not
Token not
Feature activation+0.000
attending
Token attending
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
Anton
Token Anton
Feature activation+0.747
in
Tokenin
Feature activation+0.000
Scalia
Token Scalia
Feature activation+0.810
's
Token's
Feature activation+0.761
funeral
Token funeral
Feature activation+0.000
services
Token services
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.102
decision
Token decision
Feature activation+0.977
on
Token on
Feature activation+0.425
Panama
Token Panama
Feature activation+0.000
Le
Token Le
Feature activation+0.000
aks
Tokenaks
Feature activation+0.000
case
Token case
Feature activation+0.000
good
Token good
Feature activation+0.000
chance
Token chance
Feature activation+0.000
that
Token that
Feature activation+0.000
our
Token our
Feature activation+0.000
courts
Token courts
Feature activation+0.000
will
Token will
Feature activation+0.905
reject
Token reject
Feature activation+0.839
that
Token that
Feature activation+0.000
interpretation
Token interpretation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.390 - 0.780
CONTAINS 0.016%

on
Tokenon
Feature activation+0.000
,
Token,
Feature activation+0.000
writing
Token writing
Feature activation+0.197
for
Token for
Feature activation+0.212
a
Token a
Feature activation+0.000
three
Token three
Feature activation+0.493
-
Token-
Feature activation+0.250
jud
Tokenjud
Feature activation+0.507
ge
Tokenge
Feature activation+0.838
panel
Token panel
Feature activation+0.503
of
Token of
Feature activation+0.000
Court
Token Court
Feature activation+1.920
should
Token should
Feature activation+1.592
have
Token have
Feature activation+0.661
even
Token even
Feature activation+0.647
taken
Token taken
Feature activation+0.783
the
Token the
Feature activation+0.499
case
Token case
Feature activation+0.881
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
Token The
Feature activation+0.000
decision
Token decision
Feature activation+0.729
arose
Token arose
Feature activation+0.000
from
Token from
Feature activation+0.440
cases
Token cases
Feature activation+0.058
in
Token in
Feature activation+0.463
Seattle
Token Seattle
Feature activation+0.000
,
Token,
Feature activation+0.000
Wash
Token Wash
Feature activation+0.000
.,
Token.,
Feature activation+0.000
and
Token and
Feature activation+0.000
v
Token v
Feature activation+0.000
.
Token.
Feature activation+0.000
Reese
Token Reese
Feature activation+0.000
,
Token ,
Feature activation+0.000
which
Token which
Feature activation+0.000
upheld
Token upheld
Feature activation+0.707
a
Token a
Feature activation+0.000
federal
Token federal
Feature activation+0.000
law
Token law
Feature activation+0.000
prohibiting
Token prohibiting
Feature activation+0.000
persons
Token persons
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
High
TokenHigh
Feature activation+0.000
Court
Token Court
Feature activation+0.000
R
Token R
Feature activation+0.433
uling
Tokenuling
Feature activation+0.862
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
oci
Tokenoci
Feature activation+0.000

INTERVAL 0.000 - 0.390
CONTAINS 99.958%

setups
Token setups
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
at
Token at
Feature activation+0.000
just
Token just
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
kg
Tokenkg
Feature activation+0.000
(
Token (
Feature activation+0.000
4
Token4
Feature activation+0.000
working
Token working
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
crew
Token crew
Feature activation+0.000
chief
Token chief
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000
2
Token2
Feature activation+0.000
teaspoon
Token teaspoon
Feature activation+0.000
tur
Token tur
Feature activation+0.000
meric
Tokenmeric
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000
4
Token4
Feature activation+0.000
from
Token from
Feature activation+0.000
Rafael
Token Rafael
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
Robin
Token Robin
Feature activation+0.000
van
Token van
Feature activation+0.000
Pers
Token Pers
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
penalty
Token penalty
Feature activation+0.000
won
Token won
Feature activation+0.000
it
Token it
Feature activation+0.000
are
Token are
Feature activation+0.000
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
150
Token150
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
,
Token,
Feature activation+0.000
$
Token $
Feature activation+0.000
151
Token151
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H5.10: (feature 34306)

TOP ACTIVATIONS
MAX = 2.364

as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.210
Xi
Token Xi
Feature activation+0.058
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.108
economies
Token economies
Feature activation+0.000
as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.210
Xi
Token Xi
Feature activation+0.058
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+0.135
preempt
Token preempt
Feature activation+0.321
the
Token the
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+2.108
GOP
Token GOP
Feature activation+0.200
presidential
Token presidential
Feature activation+0.121
rivals
Token rivals
Feature activation+0.000
.
Token.
Feature activation+0.171
This
Token This
Feature activation+0.076
establishments
Token establishments
Feature activation+0.000
as
Token as
Feature activation+0.000
heated
Token heated
Feature activation+0.000
issues
Token issues
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+2.058
race
Token race
Feature activation+0.621
for
Token for
Feature activation+0.602
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
election
Tokenelection
Feature activation+0.730
in
Token in
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.304
's
Token's
Feature activation+1.752
second
Token second
Feature activation+2.037
term
Token term
Feature activation+1.450
.
Token.
Feature activation+0.102
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
a
Token a
Feature activation+0.222
pact
Token pact
Feature activation+0.400
that
Token that
Feature activation+0.283
he
Token he
Feature activation+1.655
and
Token and
Feature activation+1.307
his
Token his
Feature activation+2.012
supporters
Token supporters
Feature activation+0.000
say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.073
keep
Token keep
Feature activation+0.038
the
Token the
Feature activation+0.000
open
Token open
Feature activation+0.000
for
Token for
Feature activation+0.000
discussion
Token discussion
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+1.968
West
Token West
Feature activation+0.000
Point
Token Point
Feature activation+0.000
remarks
Token remarks
Feature activation+0.306
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
President
Token President
Feature activation+0.210
Xi
Token Xi
Feature activation+0.058
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
came
Token came
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+1.927
is
Token is
Feature activation+1.580
talking
Token talking
Feature activation+0.936
about
Token about
Feature activation+0.641
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
Falk
Token Falk
Feature activation+0.000
lands
Tokenlands
Feature activation+0.000
since
Token since
Feature activation+0.000
taking
Token taking
Feature activation+1.844
over
Token over
Feature activation+1.067
power
Token power
Feature activation+0.693
following
Token following
Feature activation+0.142
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.377
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.108
next
Token next
Feature activation+0.765
month
Token month
Feature activation+0.640
it
Token it
Feature activation+0.000
tricky
Token tricky
Feature activation+0.032
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.065
president
Token president
Feature activation+1.528
to
Token to
Feature activation+1.803
now
Token now
Feature activation+0.334
claim
Token claim
Feature activation+0.697
that
Token that
Feature activation+0.000
he
Token he
Feature activation+1.456
was
Token was
Feature activation+1.570
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.108
next
Token next
Feature activation+0.765
Gar
Token Gar
Feature activation+0.051
ib
Tokenib
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ili
Tokenili
Feature activation+0.000
to
Token to
Feature activation+1.787
criticize
Token criticize
Feature activation+0.524
zoo
Token zoo
Feature activation+0.000
officials
Token officials
Feature activation+0.000
for
Token for
Feature activation+0.000
providing
Token providing
Feature activation+0.000
Chance
TokenChance
Feature activation+0.000
llor
Tokenllor
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.000
has
Token has
Feature activation+1.056
promised
Token promised
Feature activation+1.785
"
Token "
Feature activation+0.000
no
Tokenno
Feature activation+0.000
giveaways
Token giveaways
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token.
Feature activation+0.008
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+1.261
pledged
Token pledged
Feature activation+1.778
an
Token an
Feature activation+0.407
'
Token '
Feature activation+0.000
et
Tokenet
Feature activation+0.000
ernal
Tokenernal
Feature activation+0.000
fight
Token fight
Feature activation+0.000
significant
Token significant
Feature activation+0.000
in
Token in
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.304
's
Token's
Feature activation+1.752
second
Token second
Feature activation+2.037
term
Token term
Feature activation+1.450
.
Token.
Feature activation+0.102
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.403
,
Token,
Feature activation+0.137
when
Token when
Feature activation+0.186
he
Token he
Feature activation+1.454
announced
Token announced
Feature activation+1.739
a
Token a
Feature activation+1.286
plan
Token plan
Feature activation+0.943
for
Token for
Feature activation+0.181
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.166
Ċ
TokenĊ
Feature activation+0.620
He
TokenHe
Feature activation+1.424
is
Token is
Feature activation+1.488
set
Token set
Feature activation+0.553
to
Token to
Feature activation+1.712
allow
Token allow
Feature activation+0.787
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

Top DFA by src position
MAX = 2.535

two
Token two
Feature activation+0.002
Top resid features:
largest
Token largest
Feature activation+0.002
Top resid features:
economies
Token economies
Feature activation+0.009
Top resid features:
as
Token as
Feature activation+0.020
Top resid features:
President
Token President
Feature activation+1.014
Top resid features:
Xi
Token Xi
Feature activation+1.074
Top resid features:
Jinping
Token Jinping
Feature activation+0.650
Top resid features:
prepares
Token prepares
Feature activation+0.027
Top resid features:
to
Token to
Feature activation-0.051
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
largest
Token largest
Feature activation+0.001
Top resid features:
economies
Token economies
Feature activation+0.008
Top resid features:
as
Token as
Feature activation+0.023
Top resid features:
President
Token President
Feature activation+1.764
Top resid features:
Xi
Token Xi
Feature activation+0.426
Top resid features:
Jinping
Token Jinping
Feature activation+0.178
Top resid features:
prepares
Token prepares
Feature activation+0.070
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
make
Token make
Feature activation+0.028
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
largest
Token largest
Feature activation+0.001
Top resid features:
economies
Token economies
Feature activation-0.002
Top resid features:
as
Token as
Feature activation+0.011
Top resid features:
President
Token President
Feature activation+0.652
Top resid features:
Xi
Token Xi
Feature activation+0.988
Top resid features:
Jinping
Token Jinping
Feature activation+0.876
Top resid features:
prepares
Token prepares
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
ammunition
Token ammunition
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.000
Top resid features:
President
Token President
Feature activation+2.535
Top resid features:
's
Token's
Feature activation+0.109
Top resid features:
campaign
Token campaign
Feature activation-0.010
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
like
Tokenlike
Feature activation+0.005
Top resid features:
appearance
Token appearance
Feature activation+0.008
Top resid features:
women
Token women
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
economy
Token economy
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
Obama
Token Obama
Feature activation+2.331
Top resid features:
noted
Token noted
Feature activation+0.017
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
there
Tokenthere
Feature activation+0.005
Top resid features:
has
Token has
Feature activation+0.006
Top resid features:
potentially
Token potentially
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
most
Token most
Feature activation+0.002
Top resid features:
significant
Token significant
Feature activation-0.013
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
President
Token President
Feature activation+0.789
Top resid features:
Barack
Token Barack
Feature activation+0.682
Top resid features:
Obama
Token Obama
Feature activation+0.753
Top resid features:
's
Token's
Feature activation+0.105
Top resid features:
second
Token second
Feature activation+0.055
Top resid features:
term
Token term
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
White
Token White
Feature activation+0.009
Top resid features:
House
Token House
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
president
Token president
Feature activation+2.295
Top resid features:
is
Token is
Feature activation+0.030
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
verge
Token verge
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
stamped
Token stamped
Feature activation+0.008
Top resid features:
out
Token out
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
president
Token president
Feature activation+1.833
Top resid features:
was
Token was
Feature activation+0.396
Top resid features:
clear
Token clear
Feature activation-0.042
Top resid features:
that
Token that
Feature activation+0.063
Top resid features:
our
Token our
Feature activation+0.011
Top resid features:
forces
Token forces
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
largest
Token largest
Feature activation+0.001
Top resid features:
economies
Token economies
Feature activation+0.004
Top resid features:
as
Token as
Feature activation+0.010
Top resid features:
President
Token President
Feature activation+1.471
Top resid features:
Xi
Token Xi
Feature activation+0.490
Top resid features:
Jinping
Token Jinping
Feature activation+0.271
Top resid features:
prepares
Token prepares
Feature activation+0.068
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
make
Token make
Feature activation+0.005
Top resid features:
ammunition
Token ammunition
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation-0.000
Top resid features:
President
Token President
Feature activation+2.276
Top resid features:
's
Token's
Feature activation+0.264
Top resid features:
campaign
Token campaign
Feature activation-0.112
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
like
Tokenlike
Feature activation+0.014
Top resid features:
appearance
Token appearance
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ar
TokenAr
Feature activation-0.000
Top resid features:
gent
Tokengent
Feature activation+0.008
Top resid features:
inian
Tokeninian
Feature activation+0.005
Top resid features:
president
Token president
Feature activation+1.605
Top resid features:
Crist
Token Crist
Feature activation+0.098
Top resid features:
ina
Tokenina
Feature activation+0.125
Top resid features:
Kir
Token Kir
Feature activation+0.078
Top resid features:
ch
Tokench
Feature activation-0.000
Top resid features:
ner
Tokenner
Feature activation+0.049
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
largest
Token largest
Feature activation+0.001
Top resid features:
economies
Token economies
Feature activation+0.013
Top resid features:
as
Token as
Feature activation+0.007
Top resid features:
President
Token President
Feature activation+0.523
Top resid features:
Xi
Token Xi
Feature activation+0.888
Top resid features:
Jinping
Token Jinping
Feature activation+0.360
Top resid features:
prepares
Token prepares
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
make
Token make
Feature activation+0.008
Top resid features:
his
Token his
Feature activation+0.022
Top resid features:
makes
Token makes
Feature activation+0.012
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
tricky
Token tricky
Feature activation+0.092
Top resid features:
for
Token for
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
president
Token president
Feature activation+1.210
Top resid features:
to
Token to
Feature activation+0.067
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
claim
Token claim
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
largest
Token largest
Feature activation-0.007
Top resid features:
economies
Token economies
Feature activation+0.003
Top resid features:
as
Token as
Feature activation+0.018
Top resid features:
President
Token President
Feature activation+0.242
Top resid features:
Xi
Token Xi
Feature activation+0.767
Top resid features:
Jinping
Token Jinping
Feature activation+0.590
Top resid features:
prepares
Token prepares
Feature activation+0.133
Top resid features:
to
Token to
Feature activation+0.116
Top resid features:
make
Token make
Feature activation+0.006
Top resid features:
his
Token his
Feature activation+0.028
Top resid features:
escaped
Token escaped
Feature activation-0.001
Top resid features:
tiger
Token tiger
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
prompting
Token prompting
Feature activation+0.051
Top resid features:
Prime
Token Prime
Feature activation+0.195
Top resid features:
Minister
Token Minister
Feature activation+1.757
Top resid features:
I
Token I
Feature activation+0.077
Top resid features:
rak
Tokenrak
Feature activation+0.004
Top resid features:
li
Tokenli
Feature activation+0.005
Top resid features:
Gar
Token Gar
Feature activation+0.028
Top resid features:
ib
Tokenib
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Chance
TokenChance
Feature activation-0.010
Top resid features:
llor
Tokenllor
Feature activation+0.519
Top resid features:
George
Token George
Feature activation+0.089
Top resid features:
Osborne
Token Osborne
Feature activation+1.187
Top resid features:
has
Token has
Feature activation+0.320
Top resid features:
promised
Token promised
Feature activation+0.062
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
no
Tokenno
Feature activation+0.000
Top resid features:
giveaways
Token giveaways
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ar
TokenAr
Feature activation-0.000
Top resid features:
gent
Tokengent
Feature activation+0.001
Top resid features:
inian
Tokeninian
Feature activation+0.002
Top resid features:
president
Token president
Feature activation+1.659
Top resid features:
Crist
Token Crist
Feature activation+0.087
Top resid features:
ina
Tokenina
Feature activation+0.049
Top resid features:
Kir
Token Kir
Feature activation+0.024
Top resid features:
ch
Tokench
Feature activation-0.000
Top resid features:
ner
Tokenner
Feature activation+0.028
Top resid features:
potentially
Token potentially
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
most
Token most
Feature activation+0.007
Top resid features:
significant
Token significant
Feature activation-0.033
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
President
Token President
Feature activation+1.011
Top resid features:
Barack
Token Barack
Feature activation+0.355
Top resid features:
Obama
Token Obama
Feature activation+0.721
Top resid features:
's
Token's
Feature activation+0.056
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
term
Token term
Feature activation+0.000
Top resid features:
In
TokenIn
Feature activation+0.002
Top resid features:
New
Token New
Feature activation+0.004
Top resid features:
York
Token York
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Democratic
Token Democratic
Feature activation-0.004
Top resid features:
Gov
Token Gov
Feature activation+0.674
Top resid features:
.
Token.
Feature activation+0.563
Top resid features:
Andrew
Token Andrew
Feature activation+0.314
Top resid features:
Cuomo
Token Cuomo
Feature activation+0.408
Top resid features:
talked
Token talked
Feature activation-0.006
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Chance
TokenChance
Feature activation-0.007
Top resid features:
llor
Tokenllor
Feature activation+0.266
Top resid features:
George
Token George
Feature activation+0.043
Top resid features:
Osborne
Token Osborne
Feature activation+0.912
Top resid features:
has
Token has
Feature activation+0.273
Top resid features:
promised
Token promised
Feature activation+0.116
Top resid features:
"
Token "
Feature activation+0.003
Top resid features:
no
Tokenno
Feature activation+0.002
Top resid features:
giveaways
Token giveaways
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.06

Head 4: 0.03

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.04

Head 9: 0.07

Head 10: 0.51

Head 11: 0.11

Positive logits

appoint2.36

appointing2.30

aides2.12

impe1.99

Spending1.96

decree1.96

approving1.94

Secretary1.91

presidential1.88

Jinping1.87

presidents1.86

congrat1.84

Presidents1.82

pard1.82

administrations1.82

appointed1.81

Ministers1.81

nominating1.80

impeachment1.79

Eisenhower1.78

Negative logits

pload-1.63

Cree-1.60

Torrent-1.59

Dill-1.57

Dek-1.54

Ort-1.54

Tek-1.53

Beir-1.49

LTD-1.48

Liberties-1.47

Leigh-1.46

Tor-1.45

Cra-1.45

Shib-1.42

cgi-1.41

Bay-1.41

rift-1.40

Missing-1.38

AGE-1.37

Kor-1.37

INTERVAL 2.127 - 2.364
CONTAINS 0.000%

as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.210
Xi
Token Xi
Feature activation+0.058
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.108

INTERVAL 1.891 - 2.127
CONTAINS 0.001%

open
Token open
Feature activation+0.000
for
Token for
Feature activation+0.000
discussion
Token discussion
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+1.968
West
Token West
Feature activation+0.000
Point
Token Point
Feature activation+0.000
remarks
Token remarks
Feature activation+0.306
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
economies
Token economies
Feature activation+0.000
as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.210
Xi
Token Xi
Feature activation+0.058
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
President
Token President
Feature activation+0.210
Xi
Token Xi
Feature activation+0.058
Jinping
Token Jinping
Feature activation+0.647
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
in
Token in
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.304
's
Token's
Feature activation+1.752
second
Token second
Feature activation+2.037
term
Token term
Feature activation+1.450
.
Token.
Feature activation+0.102
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
a
Token a
Feature activation+0.222
pact
Token pact
Feature activation+0.400
that
Token that
Feature activation+0.283
he
Token he
Feature activation+1.655
and
Token and
Feature activation+1.307
his
Token his
Feature activation+2.012
supporters
Token supporters
Feature activation+0.000
say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.073
keep
Token keep
Feature activation+0.038
the
Token the
Feature activation+0.000

INTERVAL 1.655 - 1.891
CONTAINS 0.002%

over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
Falk
Token Falk
Feature activation+0.000
lands
Tokenlands
Feature activation+0.000
since
Token since
Feature activation+0.000
taking
Token taking
Feature activation+1.844
over
Token over
Feature activation+1.067
power
Token power
Feature activation+0.693
following
Token following
Feature activation+0.142
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.377
has
Token has
Feature activation+0.000
argued
Token argued
Feature activation+0.000
that
Token that
Feature activation+0.000
President
Token President
Feature activation+0.071
Trump
Token Trump
Feature activation+0.617
's
Token's
Feature activation+1.710
comments
Token comments
Feature activation+0.662
about
Token about
Feature activation+0.590
Ber
Token Ber
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
prepares
Token prepares
Feature activation+2.115
to
Token to
Feature activation+2.364
make
Token make
Feature activation+1.963
his
Token his
Feature activation+1.620
first
Token first
Feature activation+2.213
visit
Token visit
Feature activation+1.795
to
Token to
Feature activation+1.827
the
Token the
Feature activation+0.933
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.108
next
Token next
Feature activation+0.765
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
president
Token president
Feature activation+0.462
whose
Token whose
Feature activation+1.691
allies
Token allies
Feature activation+0.000
have
Token have
Feature activation+0.000
endured
Token endured
Feature activation+0.000
crises
Token crises
Feature activation+0.000
and
Token and
Feature activation+0.000
significant
Token significant
Feature activation+0.000
in
Token in
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.304
's
Token's
Feature activation+1.752
second
Token second
Feature activation+2.037
term
Token term
Feature activation+1.450
.
Token.
Feature activation+0.102
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.418 - 1.655
CONTAINS 0.006%

consumption
Token consumption
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.270
She
TokenShe
Feature activation+1.471
said
Token said
Feature activation+1.522
that
Token that
Feature activation+1.202
one
Token one
Feature activation+0.000
million
Token million
Feature activation+0.000
"
Token "
Feature activation+0.000
e
Tokene
Feature activation+0.000
on
Token on
Feature activation+0.655
his
Token his
Feature activation+0.654
mandate
Token mandate
Feature activation+1.014
;
Token;
Feature activation+0.343
he
Token he
Feature activation+0.744
has
Token has
Feature activation+1.458
already
Token already
Feature activation+1.175
been
Token been
Feature activation+0.986
forced
Token forced
Feature activation+0.422
to
Token to
Feature activation+0.845
compromise
Token compromise
Feature activation+0.472
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.001
Tony
Token Tony
Feature activation+0.420
Abbott
Token Abbott
Feature activation+0.308
has
Token has
Feature activation+1.443
been
Token been
Feature activation+1.288
criticised
Token criticised
Feature activation+0.000
for
Token for
Feature activation+0.692
only
Token only
Feature activation+0.110
having
Token having
Feature activation+0.552
to
Token to
Feature activation+1.803
now
Token now
Feature activation+0.334
claim
Token claim
Feature activation+0.697
that
Token that
Feature activation+0.000
he
Token he
Feature activation+1.456
was
Token was
Feature activation+1.570
elected
Token elected
Feature activation+1.274
to
Token to
Feature activation+1.387
act
Token act
Feature activation+0.796
on
Token on
Feature activation+0.443
the
Token the
Feature activation+0.038
peace
Token peace
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+1.474
said
Token said
Feature activation+1.616
extra
Token extra
Feature activation+0.000
security
Token security
Feature activation+0.000
measures
Token measures
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 1.182 - 1.418
CONTAINS 0.016%

is
Token is
Feature activation+0.000
lower
Token lower
Feature activation+0.000
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
president
Token president
Feature activation+1.305
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.188
approval
Token approval
Feature activation+0.000
rating
Token rating
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.004
Ch
TokenCh
Feature activation+0.438
avez
Tokenavez
Feature activation+0.649
is
Token is
Feature activation+1.224
a
Token a
Feature activation+1.158
socialist
Token socialist
Feature activation+0.381
and
Token and
Feature activation+0.267
former
Token former
Feature activation+0.165
soldier
Token soldier
Feature activation+0.000
from
Token from
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
and
Token and
Feature activation+0.000
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.467
's
Token's
Feature activation+1.416
White
Token White
Feature activation+0.477
House
Token House
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
said
Token said
Feature activation+0.682
.
Token.
Feature activation+0.074
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.748
was
Token was
Feature activation+1.203
echoed
Token echoed
Feature activation+0.017
by
Token by
Feature activation+0.304
other
Token other
Feature activation+0.060
victims
Token victims
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
wider
Token wider
Feature activation+0.000
effort
Token effort
Feature activation+0.124
to
Token to
Feature activation+0.244
increase
Token increase
Feature activation+0.080
his
Token his
Feature activation+1.351
base
Token base
Feature activation+0.115
of
Token of
Feature activation+0.024
bilateral
Token bilateral
Feature activation+0.000
partners
Token partners
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.946 - 1.182
CONTAINS 0.037%

the
Token the
Feature activation+0.000
ways
Token ways
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.873
intends
Token intends
Feature activation+0.969
to
Token to
Feature activation+0.900
put
Token put
Feature activation+0.595
pressure
Token pressure
Feature activation+0.000
on
Token on
Feature activation+0.000
China
Token China
Feature activation+0.000
in
Token in
Feature activation+0.000
Kenya
Token Kenya
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
Obama
Token Obama
Feature activation+0.961
received
Token received
Feature activation+0.486
some
Token some
Feature activation+0.000
instruction
Token instruction
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Home
Token Home
Feature activation+0.000
Secretary
Token Secretary
Feature activation+1.027
Theresa
Token Theresa
Feature activation+0.807
May
Token May
Feature activation+0.467
announced
Token announced
Feature activation+0.990
that
Token that
Feature activation+0.282
the
Token the
Feature activation+0.037
initial
Token initial
Feature activation+0.024
decision
Token decision
Feature activation+0.463
to
Token to
Feature activation+0.155
to
Token to
Feature activation+0.000
Governor
Token Governor
Feature activation+0.000
Sus
Token Sus
Feature activation+0.237
ana
Tokenana
Feature activation+0.070
Martinez
Token Martinez
Feature activation+0.793
,
Token,
Feature activation+0.984
who
Token who
Feature activation+1.361
is
Token is
Feature activation+1.330
expected
Token expected
Feature activation+0.434
to
Token to
Feature activation+1.551
sign
Token sign
Feature activation+1.089
them
Token them
Feature activation+0.000
checks
Token checks
Feature activation+0.000
,
Token,
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.711
vowed
Token vowed
Feature activation+1.474
to
Token to
Feature activation+1.165
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
end
Tokenend
Feature activation+0.000
welfare
Token welfare
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 0.709 - 0.946
CONTAINS 0.071%

sales
Token sales
Feature activation+0.000
last
Token last
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
.
Token.
Feature activation+0.000
Cook
Token Cook
Feature activation+0.944
also
Token also
Feature activation+0.756
emphasized
Token emphasized
Feature activation+0.909
that
Token that
Feature activation+0.568
although
Token although
Feature activation+0.000
iPad
Token iPad
Feature activation+0.000
sales
Token sales
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.187
.
Token.
Feature activation+0.269
Obama
Token Obama
Feature activation+0.505
's
Token's
Feature activation+0.889
critics
Token critics
Feature activation+0.000
argue
Token argue
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.941
is
Token is
Feature activation+0.768
Tax
Token Tax
Feature activation+0.000
(
Token (
Feature activation+0.000
G
TokenG
Feature activation+0.000
ST
TokenST
Feature activation+0.000
),
Token),
Feature activation+0.000
he
Token he
Feature activation+0.912
said
Token said
Feature activation+1.011
,
Token,
Feature activation+0.308
has
Token has
Feature activation+0.000
brought
Token brought
Feature activation+0.000
more
Token more
Feature activation+0.000
can
Token can
Feature activation+0.949
't
Token't
Feature activation+0.802
bring
Token bring
Feature activation+0.715
himself
Token himself
Feature activation+0.430
to
Token to
Feature activation+0.178
reverse
Token reverse
Feature activation+0.746
his
Token his
Feature activation+0.684
VAT
Token VAT
Feature activation+0.000
mistake
Token mistake
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.713
be
Token be
Feature activation+0.000
extra
Token extra
Feature activation+0.000
careful
Token careful
Feature activation+0.000
,"
Token,"
Feature activation+0.027
he
Token he
Feature activation+0.979
said
Token said
Feature activation+0.760
.
Token.
Feature activation+0.050
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Refer
TokenRefer
Feature activation+0.300
ring
Tokenring
Feature activation+0.436

INTERVAL 0.473 - 0.709
CONTAINS 0.154%

this
Token this
Feature activation+0.000
presentation
Token presentation
Feature activation+0.000
in
Token in
Feature activation+0.000
Metro
Token Metro
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
x
Tokenx
Feature activation+0.580
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
new
Token new
Feature activation+0.000
black
Token black
Feature activation+0.000
and
Token and
Feature activation+0.000
Trump
Token Trump
Feature activation+1.146
gave
Token gave
Feature activation+1.164
a
Token a
Feature activation+1.086
moving
Token moving
Feature activation+0.228
speech
Token speech
Feature activation+1.109
to
Token to
Feature activation+0.661
the
Token the
Feature activation+0.217
nation
Token nation
Feature activation+0.000
in
Token in
Feature activation+0.268
a
Token a
Feature activation+0.549
Joint
Token Joint
Feature activation+0.229
his
Token his
Feature activation+1.079
Asia
Token Asia
Feature activation+0.000
tour
Token tour
Feature activation+0.448
,
Token,
Feature activation+0.293
Trump
Token Trump
Feature activation+0.870
turned
Token turned
Feature activation+0.630
a
Token a
Feature activation+0.209
similar
Token similar
Feature activation+0.000
trick
Token trick
Feature activation+0.246
when
Token when
Feature activation+0.246
he
Token he
Feature activation+0.323
Ļ
TokenĻ
Feature activation+0.000
By
Token By
Feature activation+0.000
Obama
Token Obama
Feature activation+0.696
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.592
Fiscal
Token Fiscal
Feature activation+0.000
Cliff
Token Cliff
Feature activation+0.392
Pro
Token Pro
Feature activation+0.000
posal
Tokenposal
Feature activation+0.094
:
Token:
Feature activation+0.000
During
TokenDuring
Feature activation+0.000
1968
Token 1968
Feature activation+0.000
-
Token-
Feature activation+0.000
1970
Token1970
Feature activation+0.000
,
Token,
Feature activation+0.000
King
Token King
Feature activation+0.519
Hussein
Token Hussein
Feature activation+0.053
provided
Token provided
Feature activation+0.393
its
Token its
Feature activation+0.000
arch
Token arch
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.236 - 0.473
CONTAINS 0.379%

or
Token or
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.019
"
Token"
Feature activation+0.273
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
desire
Token desire
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
or
Token or
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.068
concerned
Token concerned
Feature activation+0.323
about
Token about
Feature activation+0.135
the
Token the
Feature activation+0.000
steadily
Token steadily
Feature activation+0.000
declining
Token declining
Feature activation+0.000
standing
Token standing
Feature activation+0.000
he
Token he
Feature activation+0.150
has
Token has
Feature activation+0.610
been
Token been
Feature activation+0.305
conspic
Token conspic
Feature activation+0.000
uously
Tokenuously
Feature activation+0.000
silent
Token silent
Feature activation+0.453
about
Token about
Feature activation+0.370
the
Token the
Feature activation+0.000
race
Token race
Feature activation+0.000
since
Token since
Feature activation+0.164
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.000
Congress
Token Congress
Feature activation+0.745
are
Token are
Feature activation+0.246
proposing
Token proposing
Feature activation+0.437
to
Token to
Feature activation+0.264
extend
Token extend
Feature activation+0.190
and
Token and
Feature activation+0.000
enlarge
Token enlarge
Feature activation+0.000
an
Token an
Feature activation+0.000
adviser
Token adviser
Feature activation+0.000
said
Token said
Feature activation+0.000
J
Token J
Feature activation+0.000
adh
Tokenadh
Feature activation+0.000
av
Tokenav
Feature activation+0.241
's
Token's
Feature activation+0.297
conf
Token conf
Feature activation+0.000
essional
Tokenessional
Feature activation+0.000
statement
Token statement
Feature activation+0.000
had
Token had
Feature activation+0.013
been
Token been
Feature activation+0.000

INTERVAL 0.000 - 0.236
CONTAINS 99.334%

criminal
Token criminal
Feature activation+0.000
justice
Token justice
Feature activation+0.000
system
Token system
Feature activation+0.000
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.000
known
Token known
Feature activation+0.000
among
Token among
Feature activation+0.000
policy
Token policy
Feature activation+0.000
circles
Token circles
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
investigators
Token investigators
Feature activation+0.000
were
Token were
Feature activation+0.000
tracking
Token tracking
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
IRS
Token IRS
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
did
Token did
Feature activation+0.000
enough
Token enough
Feature activation+0.209
Republican
Token Republican
Feature activation+0.000
votes
Token votes
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.052
The
Token The
Feature activation+0.030
Rs
Token Rs
Feature activation+0.000
then
Token then
Feature activation+0.000
announced
Token announced
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
also
Token also
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
combining
Token combining
Feature activation+0.000
Or
Token Or
Feature activation+0.000
list
Tokenlist
Feature activation+0.000
at
Tokenat
Feature activation+0.000
with
Token with
Feature activation+0.000
behavioral
Token behavioral
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
$
Token $
Feature activation+0.000
91
Token91
Feature activation+0.000
million
Token million
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
to
Token to
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H5.10: (feature 48630)

TOP ACTIVATIONS
MAX = 3.389

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.000
family
Token family
Feature activation+0.318
have
Token have
Feature activation+3.389
insisted
Token insisted
Feature activation+0.494
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
disabled
Token disabled
Feature activation+0.000
and
Token and
Feature activation+0.000
This
Token This
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
is
Token is
Feature activation+0.000
devastating
Token devastating
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+2.750
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
of
Token of
Feature activation+0.000
concern
Token concern
Feature activation+0.000
to
Token to
Feature activation+0.000
's
Token's
Feature activation+0.000
family
Token family
Feature activation+0.324
was
Token was
Feature activation+1.961
lucky
Token lucky
Feature activation+0.000
.
Token.
Feature activation+0.220
They
Token They
Feature activation+2.716
were
Token were
Feature activation+2.437
quickly
Token quickly
Feature activation+0.079
connected
Token connected
Feature activation+0.000
with
Token with
Feature activation+0.069
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
Higgins
Token Higgins
Feature activation+0.000
family
Token family
Feature activation+1.707
,
Token,
Feature activation+2.695
five
Token five
Feature activation+2.338
kids
Token kids
Feature activation+0.891
between
Token between
Feature activation+0.556
the
Token the
Feature activation+0.098
ages
Token ages
Feature activation+0.545
qa
Tokenqa
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
family
Token family
Feature activation+0.786
is
Token is
Feature activation+2.651
from
Token from
Feature activation+1.247
Sri
Token Sri
Feature activation+0.000
Lanka
Token Lanka
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.262
has
Token has
Feature activation+2.582
filed
Token filed
Feature activation+2.479
a
Token a
Feature activation+0.165
legal
Token legal
Feature activation+0.000
claim
Token claim
Feature activation+0.000
against
Token against
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.262
has
Token has
Feature activation+2.582
filed
Token filed
Feature activation+2.479
a
Token a
Feature activation+0.165
legal
Token legal
Feature activation+0.000
claim
Token claim
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+2.440
Sou
Token Sou
Feature activation+0.000
rav
Tokenrav
Feature activation+0.000
had
Token had
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
been
Token been
Feature activation+0.000
family
Token family
Feature activation+0.324
was
Token was
Feature activation+1.961
lucky
Token lucky
Feature activation+0.000
.
Token.
Feature activation+0.220
They
Token They
Feature activation+2.716
were
Token were
Feature activation+2.437
quickly
Token quickly
Feature activation+0.079
connected
Token connected
Feature activation+0.000
with
Token with
Feature activation+0.069
a
Token a
Feature activation+0.000
specialist
Token specialist
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+0.000
family
Token family
Feature activation+1.707
,
Token,
Feature activation+2.695
five
Token five
Feature activation+2.338
kids
Token kids
Feature activation+0.891
between
Token between
Feature activation+0.556
the
Token the
Feature activation+0.098
ages
Token ages
Feature activation+0.545
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.050
Medic
Token Medic
Feature activation+0.000
i
Tokeni
Feature activation+0.000
family
Token family
Feature activation+2.336
âĢ
TokenâĢ
Feature activation+0.823
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.468
success
Token success
Feature activation+0.166
in
Token in
Feature activation+0.000
Bur
Token Bur
Feature activation+0.000
po
Tokenpo
Feature activation+0.000
family
Token family
Feature activation+1.729
âĢ
TokenâĢ
Feature activation+0.267
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.333
story
Token story
Feature activation+0.000
was
Token was
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
lived
Tokenlived
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.124
of
Token of
Feature activation+0.596
four
Token four
Feature activation+2.243
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.655
occupied
Token occupied
Feature activation+0.163
only
Token only
Feature activation+0.000
two
Token two
Feature activation+0.000
from
Token from
Feature activation+1.247
Sri
Token Sri
Feature activation+0.000
Lanka
Token Lanka
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
parents
Token parents
Feature activation+2.243
have
Token have
Feature activation+2.181
told
Token told
Feature activation+0.213
the
Token the
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Sentinel
Token Sentinel
Feature activation+0.000
-
Token-
Feature activation+0.000
years
Tokenyears
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
,
Token,
Feature activation+0.000
lived
Token lived
Feature activation+2.241
in
Token in
Feature activation+1.399
a
Token a
Feature activation+0.429
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
bedroom
Tokenbedroom
Feature activation+0.000
Sri
Token Sri
Feature activation+0.000
Lanka
Token Lanka
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
parents
Token parents
Feature activation+2.243
have
Token have
Feature activation+2.181
told
Token told
Feature activation+0.213
the
Token the
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Sentinel
Token Sentinel
Feature activation+0.000
they
Token they
Feature activation+0.350
,
Token,
Feature activation+0.000
Chao
Token Chao
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.000
's
Token's
Feature activation+2.081
bread
Token bread
Feature activation+0.000
winner
Tokenwinner
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
her
Token her
Feature activation+0.000
bankruptcy
Token bankruptcy
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.764
were
Token were
Feature activation+2.065
to
Token to
Feature activation+0.076
sell
Token sell
Feature activation+0.503
the
Token the
Feature activation+0.000
house
Token house
Feature activation+0.000
today
Token today
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+2.056
didn
Token didn
Feature activation+1.321
't
Token't
Feature activation+0.783
have
Token have
Feature activation+0.931
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
Hann
Token Hann
Feature activation+0.000
an
Tokenan
Feature activation+0.000
's
Token's
Feature activation+0.000
family
Token family
Feature activation+0.324
was
Token was
Feature activation+1.961
lucky
Token lucky
Feature activation+0.000
.
Token.
Feature activation+0.220
They
Token They
Feature activation+2.716
were
Token were
Feature activation+2.437
quickly
Token quickly
Feature activation+0.079

Top DFA by src position
MAX = 4.202

injured
Token injured
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
His
TokenHis
Feature activation-0.022
Top resid features:
family
Token family
Feature activation+4.202
Top resid features:
have
Token have
Feature activation+0.063
Top resid features:
insisted
Token insisted
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
disabled
Token disabled
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.010
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
G
Token G
Feature activation+0.020
Top resid features:
atto
Tokenatto
Feature activation+0.015
Top resid features:
family
Token family
Feature activation+3.357
Top resid features:
.
Token.
Feature activation+0.152
Top resid features:
This
Token This
Feature activation+0.083
Top resid features:
tragedy
Token tragedy
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.012
Top resid features:
devastating
Token devastating
Feature activation+0.111
Top resid features:
en
Tokenen
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
Hann
Token Hann
Feature activation+0.008
Top resid features:
an
Tokenan
Feature activation-0.005
Top resid features:
's
Token's
Feature activation-0.006
Top resid features:
family
Token family
Feature activation+3.434
Top resid features:
was
Token was
Feature activation+0.317
Top resid features:
lucky
Token lucky
Feature activation+0.082
Top resid features:
.
Token.
Feature activation+0.139
Top resid features:
They
Token They
Feature activation+0.041
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
The
TokenThe
Feature activation+0.018
Top resid features:
Higgins
Token Higgins
Feature activation-0.034
Top resid features:
family
Token family
Feature activation+2.271
Top resid features:
,
Token,
Feature activation+0.145
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
kids
Token kids
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
if
Tokenif
Feature activation-0.008
Top resid features:
qa
Tokenqa
Feature activation-0.010
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
family
Token family
Feature activation+3.451
Top resid features:
is
Token is
Feature activation+0.138
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Sri
Token Sri
Feature activation+0.000
Top resid features:
Lanka
Token Lanka
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
district
Token district
Feature activation-0.005
Top resid features:
attorney
Token attorney
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
and
Token and
Feature activation-0.016
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
family
Token family
Feature activation+3.273
Top resid features:
has
Token has
Feature activation+0.153
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
claim
Token claim
Feature activation+0.000
Top resid features:
district
Token district
Feature activation-0.002
Top resid features:
attorney
Token attorney
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
and
Token and
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.039
Top resid features:
family
Token family
Feature activation+3.068
Top resid features:
has
Token has
Feature activation+0.097
Top resid features:
filed
Token filed
Feature activation+0.047
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
claim
Token claim
Feature activation+0.000
Top resid features:
Saturday
Token Saturday
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
According
Token According
Feature activation-0.081
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
his
Token his
Feature activation+0.015
Top resid features:
family
Token family
Feature activation+3.274
Top resid features:
,
Token,
Feature activation+0.159
Top resid features:
Sou
Token Sou
Feature activation+0.000
Top resid features:
rav
Tokenrav
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
apparently
Token apparently
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
Hann
Token Hann
Feature activation+0.006
Top resid features:
an
Tokenan
Feature activation-0.005
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
family
Token family
Feature activation+3.039
Top resid features:
was
Token was
Feature activation+0.239
Top resid features:
lucky
Token lucky
Feature activation+0.223
Top resid features:
.
Token.
Feature activation+0.140
Top resid features:
They
Token They
Feature activation+0.025
Top resid features:
were
Token were
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
The
TokenThe
Feature activation+0.022
Top resid features:
Higgins
Token Higgins
Feature activation-0.019
Top resid features:
family
Token family
Feature activation+1.996
Top resid features:
,
Token,
Feature activation+0.132
Top resid features:
five
Token five
Feature activation+0.159
Top resid features:
kids
Token kids
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
As
Token As
Feature activation+0.132
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
Medic
Token Medic
Feature activation-0.073
Top resid features:
i
Tokeni
Feature activation-0.015
Top resid features:
family
Token family
Feature activation+1.896
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:
success
Token success
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
skepticism
Token skepticism
Feature activation-0.110
Top resid features:
about
Token about
Feature activation+0.050
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
Bur
Token Bur
Feature activation+0.005
Top resid features:
po
Tokenpo
Feature activation+0.003
Top resid features:
family
Token family
Feature activation+3.151
Top resid features:
âĢ
TokenâĢ
Feature activation+0.144
Top resid features:
Ļ
TokenĻ
Feature activation+0.015
Top resid features:
s
Tokens
Feature activation+0.042
Top resid features:
story
Token story
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
ement
Tokenement
Feature activation-0.000
Top resid features:
buildings
Token buildings
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
a
Token a
Feature activation+0.058
Top resid features:
family
Token family
Feature activation+3.167
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
four
Token four
Feature activation-0.026
Top resid features:
might
Token might
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
occupied
Token occupied
Feature activation+0.000
Top resid features:
if
Tokenif
Feature activation-0.005
Top resid features:
qa
Tokenqa
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
family
Token family
Feature activation+2.752
Top resid features:
is
Token is
Feature activation+0.250
Top resid features:
from
Token from
Feature activation+0.109
Top resid features:
Sri
Token Sri
Feature activation-0.023
Top resid features:
Lanka
Token Lanka
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
The
TokenThe
Feature activation-0.001
Top resid features:
Higgins
Token Higgins
Feature activation-0.014
Top resid features:
family
Token family
Feature activation+1.632
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
five
Token five
Feature activation+0.049
Top resid features:
kids
Token kids
Feature activation+0.013
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
if
Tokenif
Feature activation-0.002
Top resid features:
qa
Tokenqa
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
family
Token family
Feature activation+2.364
Top resid features:
is
Token is
Feature activation+0.030
Top resid features:
from
Token from
Feature activation+0.260
Top resid features:
Sri
Token Sri
Feature activation-0.018
Top resid features:
Lanka
Token Lanka
Feature activation-0.012
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
notes
Token notes
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.054
Top resid features:
Chao
Token Chao
Feature activation+0.007
Top resid features:
is
Token is
Feature activation-0.046
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
family
Token family
Feature activation+2.985
Top resid features:
's
Token's
Feature activation+0.111
Top resid features:
bread
Token bread
Feature activation+0.000
Top resid features:
winner
Tokenwinner
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
man
Tokenman
Feature activation-0.007
Top resid features:
bankruptcy
Token bankruptcy
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
If
Token If
Feature activation-0.046
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
family
Token family
Feature activation+2.864
Top resid features:
were
Token were
Feature activation+0.135
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sell
Token sell
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
house
Token house
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
guitars
Token guitars
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
As
Token As
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
family
Token family
Feature activation+2.568
Top resid features:
,
Token,
Feature activation+0.087
Top resid features:
we
Token we
Feature activation+0.311
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
Hann
Token Hann
Feature activation+0.016
Top resid features:
an
Tokenan
Feature activation-0.012
Top resid features:
's
Token's
Feature activation-0.019
Top resid features:
family
Token family
Feature activation+2.795
Top resid features:
was
Token was
Feature activation+0.185
Top resid features:
lucky
Token lucky
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.05

Head 3: 0.05

Head 4: 0.04

Head 5: 0.05

Head 6: 0.05

Head 7: 0.05

Head 8: 0.04

Head 9: 0.05

Head 10: 0.51

Head 11: 0.08

Positive logits

aceae2.01

arters1.90

iHUD1.88

orah1.85

ה1.85

patriarch1.80

Todd1.77

SOURCE1.76

lodge1.73

ROR1.72

uebl1.70

Russ1.69

Family1.65

owners1.63

Brow1.61

insula1.61

י�1.59

________________________________1.57

reunion1.57

Season1.57

Negative logits

cooldown-1.85

encrypted-1.84

Cooldown-1.78

weapons-1.77

takedown-1.62

teleport-1.61

Runes-1.58

Sexy-1.56

Codec-1.54

penetration-1.53

proficiency-1.52

milliseconds-1.51

machines-1.51

Cola-1.50

Clever-1.50

rollout-1.49

AoE-1.49

usability-1.48

fades-1.48

physics-1.48

INTERVAL 3.050 - 3.389
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.000
family
Token family
Feature activation+0.318
have
Token have
Feature activation+3.389
insisted
Token insisted
Feature activation+0.494
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
disabled
Token disabled
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.711 - 3.050
CONTAINS 0.000%

This
Token This
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
is
Token is
Feature activation+0.000
devastating
Token devastating
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+2.750
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
of
Token of
Feature activation+0.000
concern
Token concern
Feature activation+0.000
to
Token to
Feature activation+0.000
's
Token's
Feature activation+0.000
family
Token family
Feature activation+0.324
was
Token was
Feature activation+1.961
lucky
Token lucky
Feature activation+0.000
.
Token.
Feature activation+0.220
They
Token They
Feature activation+2.716
were
Token were
Feature activation+2.437
quickly
Token quickly
Feature activation+0.079
connected
Token connected
Feature activation+0.000
with
Token with
Feature activation+0.069
a
Token a
Feature activation+0.000

INTERVAL 2.372 - 2.711
CONTAINS 0.001%

.
Token.
Feature activation+0.000
According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+2.440
Sou
Token Sou
Feature activation+0.000
rav
Tokenrav
Feature activation+0.000
had
Token had
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
been
Token been
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.262
has
Token has
Feature activation+2.582
filed
Token filed
Feature activation+2.479
a
Token a
Feature activation+0.165
legal
Token legal
Feature activation+0.000
claim
Token claim
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+0.000
family
Token family
Feature activation+1.707
,
Token,
Feature activation+2.695
five
Token five
Feature activation+2.338
kids
Token kids
Feature activation+0.891
between
Token between
Feature activation+0.556
the
Token the
Feature activation+0.098
ages
Token ages
Feature activation+0.545
attorney
Token attorney
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.262
has
Token has
Feature activation+2.582
filed
Token filed
Feature activation+2.479
a
Token a
Feature activation+0.165
legal
Token legal
Feature activation+0.000
claim
Token claim
Feature activation+0.000
against
Token against
Feature activation+0.000
family
Token family
Feature activation+0.324
was
Token was
Feature activation+1.961
lucky
Token lucky
Feature activation+0.000
.
Token.
Feature activation+0.220
They
Token They
Feature activation+2.716
were
Token were
Feature activation+2.437
quickly
Token quickly
Feature activation+0.079
connected
Token connected
Feature activation+0.000
with
Token with
Feature activation+0.069
a
Token a
Feature activation+0.000
specialist
Token specialist
Feature activation+0.000

INTERVAL 2.033 - 2.372
CONTAINS 0.001%

-
Token-
Feature activation+0.000
years
Tokenyears
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
,
Token,
Feature activation+0.000
lived
Token lived
Feature activation+2.241
in
Token in
Feature activation+1.399
a
Token a
Feature activation+0.429
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
bedroom
Tokenbedroom
Feature activation+0.000
Bur
Token Bur
Feature activation+0.000
po
Tokenpo
Feature activation+0.000
family
Token family
Feature activation+1.729
âĢ
TokenâĢ
Feature activation+0.267
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.333
story
Token story
Feature activation+0.000
was
Token was
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
lived
Tokenlived
Feature activation+0.000
Sri
Token Sri
Feature activation+0.000
Lanka
Token Lanka
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
parents
Token parents
Feature activation+2.243
have
Token have
Feature activation+2.181
told
Token told
Feature activation+0.213
the
Token the
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Sentinel
Token Sentinel
Feature activation+0.000
they
Token they
Feature activation+0.350
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.124
of
Token of
Feature activation+0.596
four
Token four
Feature activation+2.243
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.655
occupied
Token occupied
Feature activation+0.163
only
Token only
Feature activation+0.000
two
Token two
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.050
Medic
Token Medic
Feature activation+0.000
i
Tokeni
Feature activation+0.000
family
Token family
Feature activation+2.336
âĢ
TokenâĢ
Feature activation+0.823
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.468
success
Token success
Feature activation+0.166
in
Token in
Feature activation+0.000

INTERVAL 1.694 - 2.033
CONTAINS 0.001%

End
Token End
Feature activation+0.000
area
Token area
Feature activation+0.000
of
Token of
Feature activation+0.000
Birmingham
Token Birmingham
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+1.726
had
Token had
Feature activation+0.387
had
Token had
Feature activation+0.111
no
Token no
Feature activation+0.000
confirmation
Token confirmation
Feature activation+0.000
of
Token of
Feature activation+0.000
without
Token without
Feature activation+0.553
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
portion
Token portion
Feature activation+0.032
of
Token of
Feature activation+0.000
their
Token their
Feature activation+1.845
possessions
Token possessions
Feature activation+0.086
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
Office
Token Office
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+1.828
wanted
Token wanted
Feature activation+1.224
to
Token to
Feature activation+0.331
be
Token be
Feature activation+0.000
left
Token left
Feature activation+0.000
alone
Token alone
Feature activation+0.083
a
Token a
Feature activation+0.000
bike
Token bike
Feature activation+0.000
ride
Token ride
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
they
Token they
Feature activation+1.763
did
Token did
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+0.000
family
Token family
Feature activation+1.707
,
Token,
Feature activation+2.695
five
Token five
Feature activation+2.338
kids
Token kids
Feature activation+0.891
between
Token between
Feature activation+0.556
the
Token the
Feature activation+0.098

INTERVAL 1.355 - 1.694
CONTAINS 0.001%

Medic
Token Medic
Feature activation+0.000
i
Tokeni
Feature activation+0.000
family
Token family
Feature activation+2.336
âĢ
TokenâĢ
Feature activation+0.823
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.468
success
Token success
Feature activation+0.166
in
Token in
Feature activation+0.000
finance
Token finance
Feature activation+0.000
and
Token and
Feature activation+0.000
money
Token money
Feature activation+0.000
son
Tokenson
Feature activation+0.000
twice
Token twice
Feature activation+0.000
has
Token has
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
the
Token the
Feature activation+0.000
parents
Token parents
Feature activation+1.688
to
Token to
Feature activation+0.728
hand
Token hand
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
teen
Token teen
Feature activation+0.000
M
TokenM
Feature activation+0.000
ayer
Tokenayer
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.000
is
Token is
Feature activation+1.456
just
Token just
Feature activation+0.855
going
Token going
Feature activation+0.588
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.437
it
Token it
Feature activation+0.000
bing
Tokenbing
Feature activation+0.034
"
Token"
Feature activation+0.000
Gregory
Token Gregory
Feature activation+0.000
Mayer
Token Mayer
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+1.366
Greg
Token Greg
Feature activation+0.000
Mayer
Token Mayer
Feature activation+0.000
said
Token said
Feature activation+0.000
by
Token by
Feature activation+0.000
telephone
Token telephone
Feature activation+0.000
Mayer
Token Mayer
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.631
want
Token want
Feature activation+1.452
to
Token to
Feature activation+0.371
start
Token start
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000

INTERVAL 1.017 - 1.355
CONTAINS 0.002%

l
Tokenl
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
increased
Token increased
Feature activation+0.000
,
Token,
Feature activation+0.000
other
Token other
Feature activation+0.000
families
Token families
Feature activation+1.190
assimil
Token assimil
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.540
circles
Token circles
Feature activation+0.000
children
Token children
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
private
Token private
Feature activation+0.000
family
Token family
Feature activation+0.025
that
Token that
Feature activation+1.091
kept
Token kept
Feature activation+0.313
to
Token to
Feature activation+0.000
itself
Token itself
Feature activation+0.000
with
Token with
Feature activation+0.405
no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+1.828
wanted
Token wanted
Feature activation+1.224
to
Token to
Feature activation+0.331
be
Token be
Feature activation+0.000
left
Token left
Feature activation+0.000
alone
Token alone
Feature activation+0.083
"
Token "
Feature activation+0.000
very
Token very
Feature activation+0.000
hard
Token hard
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.188
.
Token.
Feature activation+1.052
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
to
Token to
Feature activation+0.000
concern
Token concern
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.206
,
Token,
Feature activation+1.350
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
text
Token text
Feature activation+0.000
messages
Token messages
Feature activation+0.000
belonging
Token belonging
Feature activation+0.000

INTERVAL 0.678 - 1.017
CONTAINS 0.005%

after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
van
Token van
Feature activation+0.000
carrying
Token carrying
Feature activation+0.000
family
Token family
Feature activation+0.041
members
Token members
Feature activation+0.715
of
Token of
Feature activation+0.031
Kir
Token Kir
Feature activation+0.000
il
Tokenil
Feature activation+0.000
Rash
Token Rash
Feature activation+0.000
kov
Tokenkov
Feature activation+0.000
searching
Token searching
Feature activation+0.000
houses
Token houses
Feature activation+0.000
and
Token and
Feature activation+0.000
interviewing
Token interviewing
Feature activation+0.000
family
Token family
Feature activation+0.554
members
Token members
Feature activation+0.987
,
Token,
Feature activation+0.000
friends
Token friends
Feature activation+0.000
and
Token and
Feature activation+0.000
girlfriends
Token girlfriends
Feature activation+0.000
,
Token,
Feature activation+0.000
Sam
Token Sam
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.002
,
Token,
Feature activation+0.986
recognized
Token recognized
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
manner
Token manner
Feature activation+0.000
.
Token.
Feature activation+0.000
ayer
Tokenayer
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.000
is
Token is
Feature activation+1.456
just
Token just
Feature activation+0.855
going
Token going
Feature activation+0.588
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.437
it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.000
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+2.056
didn
Token didn
Feature activation+1.321
't
Token't
Feature activation+0.783
have
Token have
Feature activation+0.931
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 0.339 - 0.678
CONTAINS 0.013%

watch
Token watch
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
funeral
Token funeral
Feature activation+0.000
procession
Token procession
Feature activation+0.025
moves
Token moves
Feature activation+0.469
through
Token through
Feature activation+0.511
the
Token the
Feature activation+0.000
village
Token village
Feature activation+0.000
of
Token of
Feature activation+0.000
Pan
Token Pan
Feature activation+0.000
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
One
TokenOne
Feature activation+0.000
family
Token family
Feature activation+0.540
says
Token says
Feature activation+0.483
the
Token the
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
-
Token-
Feature activation+0.000
grab
Tokengrab
Feature activation+0.000
bing
Tokenbing
Feature activation+0.000
Those
TokenThose
Feature activation+0.000
mourning
Token mourning
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
's
Token's
Feature activation+0.000
death
Token death
Feature activation+0.000
include
Token include
Feature activation+0.359
singer
Token singer
Feature activation+0.000
Josh
Token Josh
Feature activation+0.000
Gro
Token Gro
Feature activation+0.000
ban
Tokenban
Feature activation+0.000
,
Token,
Feature activation+0.000
After
Token After
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.436
and
Token and
Feature activation+0.442
friends
Token friends
Feature activation+0.000
enlisted
Token enlisted
Feature activation+0.000
help
Token help
Feature activation+0.000
from
Token from
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
National
Token National
Feature activation+0.000
Final
Token Final
Feature activation+0.000
.
Token.
Feature activation+0.000
Mel
Token Mel
Feature activation+0.352
G
Token G
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
roy
Tokenroy
Feature activation+0.000
c
Tokenc
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.000 - 0.339
CONTAINS 99.976%

.
Token.
Feature activation+0.000
0
Token0
Feature activation+0.000
,
Token,
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
Jelly
Token Jelly
Feature activation+0.000
Bean
Token Bean
Feature activation+0.000
's
Token's
Feature activation+0.000
new
Token new
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
planet
Token planet
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
NASA
TokenNASA
Feature activation+0.000
images
Token images
Feature activation+0.000
by
Token by
Feature activation+0.000
Robert
Token Robert
Feature activation+0.000
Sim
Token Sim
Feature activation+0.000
meat
Token meat
Feature activation+0.000
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
and
Token and
Feature activation+0.000
lunch
Token lunch
Feature activation+0.000
menu
Token menu
Feature activation+0.000
,
Token,
Feature activation+0.000
made
Token made
Feature activation+0.000
at
Token at
Feature activation+0.000
no
Token no
Feature activation+0.000
inas
Tokeninas
Feature activation+0.000
occupied
Token occupied
Feature activation+0.000
by
Token by
Feature activation+0.000
people
Token people
Feature activation+0.000
living
Token living
Feature activation+0.000
on
Token on
Feature activation+0.000
boats
Token boats
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
could
Token could
Feature activation+0.000
conduct
Token conduct
Feature activation+0.000
fish
Token fish
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
caught
Token caught
Feature activation+0.000
and
Token and
Feature activation+0.000
consumed
Token consumed
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H5.10: (feature 29877)

TOP ACTIVATIONS
MAX = 3.093

transferred
Token transferred
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+3.093
native
Token native
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
wife
Token wife
Feature activation+0.011
and
Token and
Feature activation+0.000
two
Token two
Feature activation+1.356
children
Token children
Feature activation+0.000
until
Token until
Feature activation+0.000
they
Token they
Feature activation+2.953
found
Token found
Feature activation+0.635
a
Token a
Feature activation+0.000
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.247
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
ran
Token ran
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+2.779
apartment
Token apartment
Feature activation+0.000
,
Token,
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
along
Token along
Feature activation+0.000
a
Token a
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.010
Eva
Token Eva
Feature activation+0.000
Braun
Token Braun
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+2.741
corpses
Token corpses
Feature activation+0.000
were
Token were
Feature activation+0.000
taken
Token taken
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.365
,
Token,
Feature activation+0.000
Vid
Token Vid
Feature activation+0.000
ula
Tokenula
Feature activation+0.152
,
Token,
Feature activation+2.580
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
founded
Tokenfounded
Feature activation+0.000
the
Token the
Feature activation+0.000
nonprofit
Token nonprofit
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
wife
Token wife
Feature activation+0.000
is
Token is
Feature activation+0.710
expecting
Token expecting
Feature activation+0.938
their
Token their
Feature activation+2.513
second
Token second
Feature activation+1.564
child
Token child
Feature activation+0.000
any
Token any
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
told
Token told
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
he
Token he
Feature activation+0.000
though
Token though
Feature activation+0.000
their
Token their
Feature activation+2.450
house
Token house
Feature activation+0.000
was
Token was
Feature activation+0.000
bu
Token bu
Feature activation+0.000
gged
Tokengged
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.287
Linda
Token Linda
Feature activation+0.379
would
Token would
Feature activation+2.311
be
Token be
Feature activation+2.408
avoiding
Token avoiding
Feature activation+0.000
Lewis
Token Lewis
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
costs
Token costs
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
wan
Tokenwan
Feature activation+0.000
and
Token and
Feature activation+0.007
Al
Token Al
Feature activation+0.000
vi
Tokenvi
Feature activation+2.353
were
Token were
Feature activation+0.465
indicted
Token indicted
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
on
Token on
Feature activation+0.000
now
Token now
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.735
,
Token,
Feature activation+0.000
Michele
Token Michele
Feature activation+0.349
,
Token,
Feature activation+2.333
urged
Token urged
Feature activation+1.008
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
ool
Tokenool
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
aren
Token aren
Feature activation+2.321
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
blaming
Token blaming
Feature activation+0.000
the
Token the
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.287
Linda
Token Linda
Feature activation+0.379
would
Token would
Feature activation+2.311
be
Token be
Feature activation+2.408
avoiding
Token avoiding
Feature activation+0.000
Lewis
Token Lewis
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
18
Token 18
Feature activation+0.000
71
Token71
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
her
Token her
Feature activation+2.280
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
unpleasant
Token unpleasant
Feature activation+0.000
encounter
Token encounter
Feature activation+0.000
with
Token with
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
Cookie
Token Cookie
Feature activation+0.000
,
Token,
Feature activation+2.267
on
Token on
Feature activation+0.243
Monday
Token Monday
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
is
Token is
Feature activation+0.000
they
Token they
Feature activation+2.953
found
Token found
Feature activation+0.635
a
Token a
Feature activation+0.000
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.247
own
Token own
Feature activation+0.000
and
Token and
Feature activation+0.000
selecting
Token selecting
Feature activation+0.000
him
Token him
Feature activation+0.000
for
Token for
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
,
Token,
Feature activation+2.095
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
to
Tokento
Feature activation+0.128
promote
Token promote
Feature activation+0.000
the
Token the
Feature activation+0.000
wife
Token wife
Feature activation+0.409
,
Token,
Feature activation+0.148
Son
Token Son
Feature activation+0.000
ja
Tokenja
Feature activation+0.076
,
Token,
Feature activation+1.867
were
Token were
Feature activation+2.076
not
Token not
Feature activation+1.059
sure
Token sure
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+1.379
could
Token could
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.275
,
Token,
Feature activation+0.000
Vik
Token Vik
Feature activation+0.000
ki
Tokenki
Feature activation+0.000
,
Token,
Feature activation+2.024
died
Token died
Feature activation+0.685
unexpectedly
Token unexpectedly
Feature activation+0.119
of
Token of
Feature activation+0.000
natural
Token natural
Feature activation+0.000
causes
Token causes
Feature activation+0.000
.
Token.
Feature activation+1.449
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
ansom
Tokenansom
Feature activation+0.000
married
Token married
Feature activation+1.989
his
Token his
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
sweet
Token sweet
Feature activation+0.069
heart
Tokenheart
Feature activation+0.000
when
Token when
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
how
Token how
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+0.000
their
Token their
Feature activation+1.914
divorce
Token divorce
Feature activation+1.116
his
Token his
Feature activation+0.843
painful
Token painful
Feature activation+0.106
words
Token words
Feature activation+0.000
led
Token led
Feature activation+0.000

Top DFA by src position
MAX = 4.252

,
Token,
Feature activation-0.013
Top resid features:
Aw
Token Aw
Feature activation+0.001
Top resid features:
an
Tokenan
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
his
Token his
Feature activation+0.025
Top resid features:
wife
Token wife
Feature activation+4.069
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
H
Token H
Feature activation+0.001
Top resid features:
ina
Tokenina
Feature activation+0.000
Top resid features:
Al
Token Al
Feature activation+0.002
Top resid features:
vi
Tokenvi
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
housing
Token housing
Feature activation+0.010
Top resid features:
him
Token him
Feature activation-0.073
Top resid features:
and
Token and
Feature activation+0.047
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
wife
Token wife
Feature activation+3.707
Top resid features:
and
Token and
Feature activation+0.256
Top resid features:
two
Token two
Feature activation+0.105
Top resid features:
children
Token children
Feature activation+0.069
Top resid features:
until
Token until
Feature activation-0.048
Top resid features:
they
Token they
Feature activation-0.068
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
duty
Tokenduty
Feature activation+0.002
Top resid features:
policeman
Token policeman
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
his
Token his
Feature activation+0.009
Top resid features:
wife
Token wife
Feature activation+4.252
Top resid features:
ran
Token ran
Feature activation+0.024
Top resid features:
back
Token back
Feature activation-0.197
Top resid features:
to
Token to
Feature activation-0.196
Top resid features:
their
Token their
Feature activation+0.054
Top resid features:
apartment
Token apartment
Feature activation+0.000
Top resid features:
Hitler
Token Hitler
Feature activation+0.011
Top resid features:
committed
Token committed
Feature activation+0.119
Top resid features:
suicide
Token suicide
Feature activation+0.088
Top resid features:
with
Token with
Feature activation+0.035
Top resid features:
his
Token his
Feature activation+0.016
Top resid features:
wife
Token wife
Feature activation+3.549
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Eva
Token Eva
Feature activation+0.004
Top resid features:
Braun
Token Braun
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.038
Top resid features:
Their
Token Their
Feature activation-0.030
Top resid features:
School
Token School
Feature activation-0.003
Top resid features:
professor
Token professor
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
his
Token his
Feature activation+0.099
Top resid features:
wife
Token wife
Feature activation+3.701
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
Vid
Token Vid
Feature activation-0.064
Top resid features:
ula
Tokenula
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.135
Top resid features:
co
Token co
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
dad
Token dad
Feature activation-0.082
Top resid features:
himself
Token himself
Feature activation-0.026
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
His
Token His
Feature activation+0.008
Top resid features:
wife
Token wife
Feature activation+3.735
Top resid features:
is
Token is
Feature activation-0.049
Top resid features:
expecting
Token expecting
Feature activation+0.063
Top resid features:
their
Token their
Feature activation-0.011
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
child
Token child
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.002
Top resid features:
car
Token car
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.042
Top resid features:
his
Token his
Feature activation+0.008
Top resid features:
wife
Token wife
Feature activation+3.150
Top resid features:
he
Token he
Feature activation+0.065
Top resid features:
though
Token though
Feature activation+0.070
Top resid features:
their
Token their
Feature activation-0.006
Top resid features:
house
Token house
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Sometimes
Token Sometimes
Feature activation-0.046
Top resid features:
he
Token he
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.053
Top resid features:
his
Token his
Feature activation+0.030
Top resid features:
wife
Token wife
Feature activation+3.466
Top resid features:
Linda
Token Linda
Feature activation+0.019
Top resid features:
would
Token would
Feature activation+0.032
Top resid features:
be
Token be
Feature activation-0.092
Top resid features:
avoiding
Token avoiding
Feature activation+0.000
Top resid features:
Lewis
Token Lewis
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
Aw
Token Aw
Feature activation-0.007
Top resid features:
an
Tokenan
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
his
Token his
Feature activation+0.009
Top resid features:
wife
Token wife
Feature activation+2.874
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:
H
Token H
Feature activation+0.017
Top resid features:
ina
Tokenina
Feature activation+0.020
Top resid features:
Al
Token Al
Feature activation+0.090
Top resid features:
vi
Tokenvi
Feature activation-0.001
Top resid features:
point
Token point
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
his
Token his
Feature activation+0.032
Top resid features:
now
Token now
Feature activation-0.024
Top resid features:
his
Token his
Feature activation-0.073
Top resid features:
wife
Token wife
Feature activation+3.831
Top resid features:
,
Token,
Feature activation-0.060
Top resid features:
Michele
Token Michele
Feature activation-0.111
Top resid features:
,
Token,
Feature activation-0.103
Top resid features:
urged
Token urged
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
Wh
Token Wh
Feature activation+0.012
Top resid features:
ool
Tokenool
Feature activation-0.013
Top resid features:
ery
Tokenery
Feature activation+0.034
Top resid features:
and
Token and
Feature activation+0.174
Top resid features:
his
Token his
Feature activation+0.082
Top resid features:
wife
Token wife
Feature activation+3.124
Top resid features:
aren
Token aren
Feature activation+0.023
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
blaming
Token blaming
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Sometimes
Token Sometimes
Feature activation-0.046
Top resid features:
he
Token he
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.065
Top resid features:
his
Token his
Feature activation+0.066
Top resid features:
wife
Token wife
Feature activation+3.305
Top resid features:
Linda
Token Linda
Feature activation+0.020
Top resid features:
would
Token would
Feature activation-0.065
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
avoiding
Token avoiding
Feature activation+0.000
Top resid features:
Lewis
Token Lewis
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
surviving
Token surviving
Feature activation+0.004
Top resid features:
letter
Token letter
Feature activation-0.059
Top resid features:
to
Token to
Feature activation-0.015
Top resid features:
his
Token his
Feature activation+0.039
Top resid features:
wife
Token wife
Feature activation+3.060
Top resid features:
from
Token from
Feature activation+0.232
Top resid features:
August
Token August
Feature activation+0.001
Top resid features:
18
Token 18
Feature activation-0.001
Top resid features:
71
Token71
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
legend
Token legend
Feature activation+0.017
Top resid features:
Magic
Token Magic
Feature activation-0.016
Top resid features:
Johnson
Token Johnson
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
his
Token his
Feature activation+0.102
Top resid features:
wife
Token wife
Feature activation+3.075
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Cookie
Token Cookie
Feature activation-0.043
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Monday
Token Monday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
housing
Token housing
Feature activation-0.002
Top resid features:
him
Token him
Feature activation-0.035
Top resid features:
and
Token and
Feature activation+0.041
Top resid features:
his
Token his
Feature activation+0.010
Top resid features:
wife
Token wife
Feature activation+3.213
Top resid features:
and
Token and
Feature activation+0.191
Top resid features:
two
Token two
Feature activation+0.042
Top resid features:
children
Token children
Feature activation+0.013
Top resid features:
until
Token until
Feature activation+0.085
Top resid features:
they
Token they
Feature activation+0.006
Top resid features:
L
Token L
Feature activation-0.015
Top resid features:
eland
Tokeneland
Feature activation+0.003
Top resid features:
Stanford
Token Stanford
Feature activation-0.019
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
his
Token his
Feature activation+0.105
Top resid features:
wife
Token wife
Feature activation+2.693
Top resid features:
,
Token,
Feature activation+0.116
Top resid features:
Jane
Token Jane
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
first
Token first
Feature activation-0.131
Top resid features:
,
Token,
Feature activation-0.053
Top resid features:
he
Token he
Feature activation+0.034
Top resid features:
and
Token and
Feature activation+0.149
Top resid features:
his
Token his
Feature activation+0.050
Top resid features:
wife
Token wife
Feature activation+2.834
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
Son
Token Son
Feature activation+0.018
Top resid features:
ja
Tokenja
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
were
Token were
Feature activation+0.026
Top resid features:
blow
Token blow
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
2009
Token 2009
Feature activation+0.022
Top resid features:
when
Token when
Feature activation+0.014
Top resid features:
his
Token his
Feature activation+0.082
Top resid features:
wife
Token wife
Feature activation+3.081
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
Vik
Token Vik
Feature activation-0.049
Top resid features:
ki
Tokenki
Feature activation+0.010
Top resid features:
,
Token,
Feature activation-0.116
Top resid features:
died
Token died
Feature activation+0.000
Top resid features:
following
Token following
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
divorce
Token divorce
Feature activation+0.210
Top resid features:
from
Token from
Feature activation-0.031
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
wife
Token wife
Feature activation+2.900
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
29
Token 29
Feature activation+0.005
Top resid features:
years
Token years
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
Elaine
Token Elaine
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
tell
Token tell
Feature activation+0.004
Top resid features:
you
Token you
Feature activation-0.007
Top resid features:
how
Token how
Feature activation-0.001
Top resid features:
her
Token her
Feature activation+0.003
Top resid features:
husband
Token husband
Feature activation+3.118
Top resid features:
cheated
Token cheated
Feature activation+0.027
Top resid features:
on
Token on
Feature activation-0.003
Top resid features:
her
Token her
Feature activation-0.020
Top resid features:
because
Token because
Feature activation-0.028
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.06

Head 3: 0.05

Head 4: 0.04

Head 5: 0.05

Head 6: 0.04

Head 7: 0.04

Head 8: 0.04

Head 9: 0.06

Head 10: 0.51

Head 11: 0.05

Positive logits

Owner2.10

��2.03

coupling2.03

iHUD2.00

Cater1.96

Schn1.89

Seym1.86

careg1.86

husband1.85

wed1.81

husband1.78

Doodle1.77

dow1.77

Toast1.75

convertible1.74

orah1.72

emade1.70

Wife1.69

homeowner1.68

Dolphin1.67

Negative logits

rank-2.19

rank-2.01

disciplines-2.00

Classification-1.98

trope-1.95

Rank-1.94

ranks-1.91

mutants-1.88

ranked-1.88

rage-1.87

chants-1.84

Universities-1.83

pmwiki-1.82

gangs-1.81

classification-1.81

slang-1.79

tropes-1.78

Ranking-1.77

societies-1.76

syll-1.73

INTERVAL 2.784 - 3.093
CONTAINS 0.000%

wife
Token wife
Feature activation+0.011
and
Token and
Feature activation+0.000
two
Token two
Feature activation+1.356
children
Token children
Feature activation+0.000
until
Token until
Feature activation+0.000
they
Token they
Feature activation+2.953
found
Token found
Feature activation+0.635
a
Token a
Feature activation+0.000
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.247
transferred
Token transferred
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+3.093
native
Token native
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.475 - 2.784
CONTAINS 0.000%

.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
wife
Token wife
Feature activation+0.000
is
Token is
Feature activation+0.710
expecting
Token expecting
Feature activation+0.938
their
Token their
Feature activation+2.513
second
Token second
Feature activation+1.564
child
Token child
Feature activation+0.000
any
Token any
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
ran
Token ran
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+2.779
apartment
Token apartment
Feature activation+0.000
,
Token,
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
along
Token along
Feature activation+0.000
a
Token a
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.010
Eva
Token Eva
Feature activation+0.000
Braun
Token Braun
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+2.741
corpses
Token corpses
Feature activation+0.000
were
Token were
Feature activation+0.000
taken
Token taken
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.365
,
Token,
Feature activation+0.000
Vid
Token Vid
Feature activation+0.000
ula
Tokenula
Feature activation+0.152
,
Token,
Feature activation+2.580
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
founded
Tokenfounded
Feature activation+0.000
the
Token the
Feature activation+0.000
nonprofit
Token nonprofit
Feature activation+0.000

INTERVAL 2.165 - 2.475
CONTAINS 0.001%

told
Token told
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
he
Token he
Feature activation+0.000
though
Token though
Feature activation+0.000
their
Token their
Feature activation+2.450
house
Token house
Feature activation+0.000
was
Token was
Feature activation+0.000
bu
Token bu
Feature activation+0.000
gged
Tokengged
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+2.953
found
Token found
Feature activation+0.635
a
Token a
Feature activation+0.000
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.247
own
Token own
Feature activation+0.000
and
Token and
Feature activation+0.000
selecting
Token selecting
Feature activation+0.000
him
Token him
Feature activation+0.000
for
Token for
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.287
Linda
Token Linda
Feature activation+0.379
would
Token would
Feature activation+2.311
be
Token be
Feature activation+2.408
avoiding
Token avoiding
Feature activation+0.000
Lewis
Token Lewis
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
costs
Token costs
Feature activation+0.000
18
Token 18
Feature activation+0.000
71
Token71
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
her
Token her
Feature activation+2.280
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
unpleasant
Token unpleasant
Feature activation+0.000
encounter
Token encounter
Feature activation+0.000
with
Token with
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.287
Linda
Token Linda
Feature activation+0.379
would
Token would
Feature activation+2.311
be
Token be
Feature activation+2.408
avoiding
Token avoiding
Feature activation+0.000
Lewis
Token Lewis
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000

INTERVAL 1.856 - 2.165
CONTAINS 0.001%

his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.275
,
Token,
Feature activation+0.000
Vik
Token Vik
Feature activation+0.000
ki
Tokenki
Feature activation+0.000
,
Token,
Feature activation+2.024
died
Token died
Feature activation+0.685
unexpectedly
Token unexpectedly
Feature activation+0.119
of
Token of
Feature activation+0.000
natural
Token natural
Feature activation+0.000
causes
Token causes
Feature activation+0.000
.
Token.
Feature activation+1.449
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
ansom
Tokenansom
Feature activation+0.000
married
Token married
Feature activation+1.989
his
Token his
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
sweet
Token sweet
Feature activation+0.069
heart
Tokenheart
Feature activation+0.000
when
Token when
Feature activation+0.000
wife
Token wife
Feature activation+0.409
,
Token,
Feature activation+0.148
Son
Token Son
Feature activation+0.000
ja
Tokenja
Feature activation+0.076
,
Token,
Feature activation+1.867
were
Token were
Feature activation+2.076
not
Token not
Feature activation+1.059
sure
Token sure
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+1.379
could
Token could
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
,
Token,
Feature activation+2.095
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
to
Tokento
Feature activation+0.128
promote
Token promote
Feature activation+0.000
the
Token the
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.409
,
Token,
Feature activation+0.148
Son
Token Son
Feature activation+0.000
ja
Tokenja
Feature activation+0.076
,
Token,
Feature activation+1.867
were
Token were
Feature activation+2.076
not
Token not
Feature activation+1.059
sure
Token sure
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+1.379

INTERVAL 1.547 - 1.856
CONTAINS 0.000%

His
Token His
Feature activation+0.000
wife
Token wife
Feature activation+0.000
is
Token is
Feature activation+0.710
expecting
Token expecting
Feature activation+0.938
their
Token their
Feature activation+2.513
second
Token second
Feature activation+1.564
child
Token child
Feature activation+0.000
any
Token any
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
Gi
Token Gi
Feature activation+0.000
ud
Tokenud
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+1.618
will
Token will
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
when
Token when
Feature activation+0.000
sure
Token sure
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+1.379
could
Token could
Feature activation+0.000
believe
Token believe
Feature activation+0.000
their
Token their
Feature activation+1.635
son
Token son
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
story
Token story
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.520
and
Token and
Feature activation+0.084
two
Token two
Feature activation+1.616
small
Token small
Feature activation+0.500
children
Token children
Feature activation+0.000
(
Token (
Feature activation+0.000
including
Tokenincluding
Feature activation+0.000
yours
Token yours
Feature activation+0.000

INTERVAL 1.237 - 1.547
CONTAINS 0.001%

had
Token had
Feature activation+1.377
three
Token three
Feature activation+0.779
children
Token children
Feature activation+0.000
together
Token together
Feature activation+0.004
,
Token,
Feature activation+0.000
Kate
Token Kate
Feature activation+1.322
,
Token,
Feature activation+0.016
Natalie
Token Natalie
Feature activation+0.000
and
Token and
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
29
Token 29
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
Elaine
Token Elaine
Feature activation+0.000
.
Token.
Feature activation+1.449
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
ansom
Tokenansom
Feature activation+0.000
married
Token married
Feature activation+1.989
a
Token a
Feature activation+0.000
facade
Token facade
Feature activation+0.000
of
Token of
Feature activation+0.000
unity
Token unity
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+1.508
people
Token people
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
al
Tokenal
Feature activation+0.000
said
Token said
Feature activation+0.000
Tam
Token Tam
Feature activation+0.000
ara
Tokenara
Feature activation+1.900
Den
Token Den
Feature activation+0.979
ne
Tokenne
Feature activation+1.246
hy
Tokenhy
Feature activation+1.115
,
Token,
Feature activation+1.426
who
Token who
Feature activation+1.066
teaches
Token teaches
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Bel
Token Bel
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
Tam
Token Tam
Feature activation+0.000
ara
Tokenara
Feature activation+1.900
Den
Token Den
Feature activation+0.979
ne
Tokenne
Feature activation+1.246
hy
Tokenhy
Feature activation+1.115
,
Token,
Feature activation+1.426
who
Token who
Feature activation+1.066
teaches
Token teaches
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.928 - 1.237
CONTAINS 0.002%

's
Token's
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
Tam
Token Tam
Feature activation+0.000
ara
Tokenara
Feature activation+1.900
Den
Token Den
Feature activation+0.979
ne
Tokenne
Feature activation+1.246
hy
Tokenhy
Feature activation+1.115
,
Token,
Feature activation+1.426
who
Token who
Feature activation+1.066
teaches
Token teaches
Feature activation+0.000
ara
Tokenara
Feature activation+1.900
Den
Token Den
Feature activation+0.979
ne
Tokenne
Feature activation+1.246
hy
Tokenhy
Feature activation+1.115
,
Token,
Feature activation+1.426
who
Token who
Feature activation+1.066
teaches
Token teaches
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Bel
Token Bel
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
,
Token,
Feature activation+0.148
Son
Token Son
Feature activation+0.000
ja
Tokenja
Feature activation+0.076
,
Token,
Feature activation+1.867
were
Token were
Feature activation+2.076
not
Token not
Feature activation+1.059
sure
Token sure
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+1.379
could
Token could
Feature activation+0.000
believe
Token believe
Feature activation+0.000
ikes
Tokenikes
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
Amy
Token Amy
Feature activation+0.000
for
Token for
Feature activation+1.044
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
Bre
TokenBre
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
Health
Token Health
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
chose
Token chose
Feature activation+0.065
to
Token to
Feature activation+1.155
breast
Token breast
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
their
Token their
Feature activation+1.121
baby
Token baby
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.619 - 0.928
CONTAINS 0.003%

izing
Tokenizing
Feature activation+0.000
5
Token 5
Feature activation+0.000
hour
Token hour
Feature activation+0.000
wait
Token wait
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.924
got
Token got
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.791
children
Token children
Feature activation+0.000
to
Token to
Feature activation+0.084
be
Token be
Feature activation+0.023
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
how
Token how
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+0.000
their
Token their
Feature activation+1.914
divorce
Token divorce
Feature activation+1.116
his
Token his
Feature activation+0.843
painful
Token painful
Feature activation+0.106
words
Token words
Feature activation+0.000
led
Token led
Feature activation+0.000
her
Token her
Feature activation+0.000
to
Token to
Feature activation+0.000
elder
Token elder
Feature activation+0.000
Zimmer
Token Zimmer
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
relationship
Token relationship
Feature activation+0.713
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Red
Token Red
Feature activation+0.000
bird
Tokenbird
Feature activation+0.000
coaches
Token coaches
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
wife
Token wife
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.887
always
Token always
Feature activation+0.000
been
Token been
Feature activation+0.271
amazed
Token amazed
Feature activation+0.000
at
Token at
Feature activation+0.000
how
Token how
Feature activation+0.000

INTERVAL 0.309 - 0.619
CONTAINS 0.006%

Texas
Token Texas
Feature activation+0.000
;
Token;
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.009
and
Token and
Feature activation+0.000
four
Token four
Feature activation+0.350
children
Token children
Feature activation+0.000
live
Token live
Feature activation+0.104
in
Token in
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.000
.
Token.
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.283
from
Token from
Feature activation+0.446
recovering
Token recovering
Feature activation+0.028
marital
Token marital
Feature activation+0.068
assets
Token assets
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
cheated
Token cheated
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
because
Token because
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.581
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
H
Token H
Feature activation+0.000
ina
Tokenina
Feature activation+0.424
Al
Token Al
Feature activation+0.000
vi
Tokenvi
Feature activation+0.598
,
Token,
Feature activation+1.304
frantically
Token frantically
Feature activation+0.000
transferred
Token transferred
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
they
Token they
Feature activation+0.119
got
Token got
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.464
took
Token took
Feature activation+0.612
all
Token all
Feature activation+0.000
his
Token his
Feature activation+0.000
money
Token money
Feature activation+0.000
and
Token and
Feature activation+0.000
Stead
Token Stead
Feature activation+0.000

INTERVAL 0.000 - 0.309
CONTAINS 99.985%

New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
last
Token last
Feature activation+0.000
fall
Token fall
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
about
Token about
Feature activation+0.000
200
Token 200
Feature activation+0.000
fast
Token fast
Feature activation+0.000
-
Token-
Feature activation+0.000
food
Tokenfood
Feature activation+0.000
of
Token of
Feature activation+0.000
F
Token F
Feature activation+0.000
ools
Tokenools
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
rich
Token rich
Feature activation+0.000
and
Token and
Feature activation+0.000
exciting
Token exciting
Feature activation+0.000
piece
Token piece
Feature activation+0.000
day
Token day
Feature activation+0.000
from
Token from
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
London
Token London
Feature activation+0.000
,
Token,
Feature activation+0.000
Berkshire
Token Berkshire
Feature activation+0.000
,
Token,
Feature activation+0.000
Oxford
Token Oxford
Feature activation+0.000
shire
Tokenshire
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
4
Token 4
Feature activation+0.000
%
Token%
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
plan
Token plan
Feature activation+0.000
may
Token may
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.000
itself
Token itself
Feature activation+0.000
20
Token 20
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
,
Token,
Feature activation+0.000
outlining
Token outlining
Feature activation+0.000
his
Token his
Feature activation+0.000
"
Token "
Feature activation+0.000
America
TokenAmerica
Feature activation+0.000
first
Token first
Feature activation+0.000
"
Token"
Feature activation+0.000
vision
Token vision
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H5.10: (feature 1282)

TOP ACTIVATIONS
MAX = 3.841

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.552
that
Token that
Feature activation+2.103
resulted
Token resulted
Feature activation+2.584
in
Token in
Feature activation+3.841
Thursday
Token Thursday
Feature activation+0.213
's
Token's
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
that
Token that
Feature activation+0.000
Chrysler
Token Chrysler
Feature activation+0.000
in
Token in
Feature activation+3.229
Geneva
Token Geneva
Feature activation+1.636
,
Token,
Feature activation+1.468
Switzerland
Token Switzerland
Feature activation+0.403
,
Token,
Feature activation+0.539
involving
Token involving
Feature activation+3.257
Iran
Token Iran
Feature activation+0.000
and
Token and
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
This
TokenThis
Feature activation+0.000
week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
talks
Token talks
Feature activation+0.887
in
Token in
Feature activation+3.229
Geneva
Token Geneva
Feature activation+1.636
,
Token,
Feature activation+1.468
Switzerland
Token Switzerland
Feature activation+0.403
,
Token,
Feature activation+0.539
involving
Token involving
Feature activation+3.257
the
Token the
Feature activation+0.187
role
Token role
Feature activation+0.000
played
Token played
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.565
talks
Token talks
Feature activation+3.048
by
Token by
Feature activation+1.195
the
Token the
Feature activation+1.131
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
launching
Token launching
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
the
Token the
Feature activation+0.058
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
taken
Token taken
Feature activation+0.000
place
Token place
Feature activation+2.685
on
Token on
Feature activation+0.317
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
before
Token before
Feature activation+0.000
launching
Token launching
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
evident
Token evident
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.552
that
Token that
Feature activation+2.103
resulted
Token resulted
Feature activation+2.584
in
Token in
Feature activation+3.841
Thursday
Token Thursday
Feature activation+0.213
's
Token's
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
that
Token that
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
taking
Token taking
Feature activation+1.061
place
Token place
Feature activation+2.570
on
Token on
Feature activation+0.361
this
Token this
Feature activation+0.000
issue
Token issue
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
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
both
Token both
Feature activation+0.513
sides
Token sides
Feature activation+2.559
wish
Token wish
Feature activation+0.272
to
Token to
Feature activation+0.554
approach
Token approach
Feature activation+2.149
these
Token these
Feature activation+0.047
talks
Token talks
Feature activation+0.594
so
Tokenso
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
talks
Token talks
Feature activation+0.761
had
Token had
Feature activation+1.754
failed
Token failed
Feature activation+2.480
owing
Token owing
Feature activation+0.000
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
important
Tokenimportant
Feature activation+0.905
differences
Token differences
Feature activation+1.271
talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
the
Token the
Feature activation+0.058
most
Token most
Feature activation+0.000
complicated
Token complicated
Feature activation+0.706
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.136
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.217
in
Token in
Feature activation+2.286
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.129
,
Token,
Feature activation+0.000
ices
Tokenices
Feature activation+0.000
in
Token in
Feature activation+0.294
Geneva
Token Geneva
Feature activation+0.000
were
Token were
Feature activation+0.773
not
Token not
Feature activation+0.355
progressing
Token progressing
Feature activation+2.280
.
Token.
Feature activation+0.064
Local
Token Local
Feature activation+0.000
reconciliation
Token reconciliation
Feature activation+0.000
deals
Token deals
Feature activation+0.205
that
Token that
Feature activation+1.006
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.129
,
Token,
Feature activation+0.000
are
Token are
Feature activation+2.243
a
Token a
Feature activation+1.220
hopeful
Token hopeful
Feature activation+0.539
sign
Token sign
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
clear
Token clear
Feature activation+0.000
both
Token both
Feature activation+0.513
sides
Token sides
Feature activation+2.559
wish
Token wish
Feature activation+0.272
to
Token to
Feature activation+0.554
approach
Token approach
Feature activation+2.149
these
Token these
Feature activation+0.047
talks
Token talks
Feature activation+0.594
construct
Token construct
Feature activation+0.027
ively
Tokenively
Feature activation+0.188
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
once
Token once
Feature activation+0.832
they
Token they
Feature activation+1.601
have
Token have
Feature activation+2.133
been
Token been
Feature activation+0.246
formally
Token formally
Feature activation+0.000
agreed
Token agreed
Feature activation+0.141
by
Token by
Feature activation+0.418
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hours
TokenHours
Feature activation+0.000
of
Token of
Feature activation+0.000
talks
Token talks
Feature activation+0.284
failed
Token failed
Feature activation+2.118
to
Token to
Feature activation+0.760
bridge
Token bridge
Feature activation+1.469
big
Token big
Feature activation+0.000
gaps
Token gaps
Feature activation+0.218
between
Token between
Feature activation+0.000
also
Token also
Feature activation+0.000
evident
Token evident
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.552
that
Token that
Feature activation+2.103
resulted
Token resulted
Feature activation+2.584
in
Token in
Feature activation+3.841
Thursday
Token Thursday
Feature activation+0.213
's
Token's
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
the
Token the
Feature activation+0.058
most
Token most
Feature activation+0.000
complicated
Token complicated
Feature activation+0.706
Britain
Token Britain
Feature activation+0.000

Top DFA by src position
MAX = 5.041

was
Token was
Feature activation+0.011
Top resid features:
also
Token also
Feature activation+0.030
Top resid features:
evident
Token evident
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
negotiations
Token negotiations
Feature activation+5.041
Top resid features:
that
Token that
Feature activation+0.057
Top resid features:
resulted
Token resulted
Feature activation+0.115
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
This
TokenThis
Feature activation-0.008
Top resid features:
week
Token week
Feature activation-0.032
Top resid features:
's
Token's
Feature activation-0.024
Top resid features:
nuclear
Token nuclear
Feature activation+0.044
Top resid features:
talks
Token talks
Feature activation+4.480
Top resid features:
in
Token in
Feature activation+0.113
Top resid features:
Geneva
Token Geneva
Feature activation-0.018
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
Switzerland
Token Switzerland
Feature activation-0.041
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
This
TokenThis
Feature activation-0.015
Top resid features:
week
Token week
Feature activation-0.023
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
nuclear
Token nuclear
Feature activation+0.015
Top resid features:
talks
Token talks
Feature activation+4.358
Top resid features:
in
Token in
Feature activation+0.051
Top resid features:
Geneva
Token Geneva
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Switzerland
Token Switzerland
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
administration
Token administration
Feature activation-0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
Iran
Token Iran
Feature activation-0.022
Top resid features:
talks
Token talks
Feature activation+4.096
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.216
Top resid features:
in
Tokenin
Feature activation+0.033
Top resid features:
particular
Token particular
Feature activation-0.050
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
foreign
Token foreign
Feature activation+0.010
Top resid features:
support
Token support
Feature activation-0.040
Top resid features:
before
Token before
Feature activation+0.027
Top resid features:
launching
Token launching
Feature activation+0.010
Top resid features:
Brexit
Token Brexit
Feature activation+0.010
Top resid features:
talks
Token talks
Feature activation+3.891
Top resid features:
,
Token,
Feature activation+0.263
Top resid features:
which
Token which
Feature activation+0.184
Top resid features:
are
Token are
Feature activation-0.094
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
administration
Token administration
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
Iran
Token Iran
Feature activation-0.000
Top resid features:
talks
Token talks
Feature activation+2.787
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.015
Top resid features:
in
Tokenin
Feature activation+0.007
Top resid features:
particular
Token particular
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
foreign
Token foreign
Feature activation+0.005
Top resid features:
support
Token support
Feature activation-0.053
Top resid features:
before
Token before
Feature activation+0.119
Top resid features:
launching
Token launching
Feature activation+0.012
Top resid features:
Brexit
Token Brexit
Feature activation+0.034
Top resid features:
talks
Token talks
Feature activation+3.699
Top resid features:
,
Token,
Feature activation+0.233
Top resid features:
which
Token which
Feature activation-0.059
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.010
Top resid features:
also
Token also
Feature activation+0.027
Top resid features:
evident
Token evident
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
negotiations
Token negotiations
Feature activation+3.646
Top resid features:
that
Token that
Feature activation+0.108
Top resid features:
resulted
Token resulted
Feature activation-0.023
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
]
Token]
Feature activation-0.009
Top resid features:
attempts
Token attempts
Feature activation+0.048
Top resid features:
to
Token to
Feature activation+0.030
Top resid features:
prevent
Token prevent
Feature activation+0.067
Top resid features:
negotiations
Token negotiations
Feature activation+4.057
Top resid features:
taking
Token taking
Feature activation-0.321
Top resid features:
place
Token place
Feature activation-0.122
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
issue
Token issue
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.027
Top resid features:
look
Token look
Feature activation+0.005
Top resid features:
forward
Token forward
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
beginning
Token beginning
Feature activation+0.007
Top resid features:
negotiations
Token negotiations
Feature activation+1.941
Top resid features:
once
Token once
Feature activation+0.008
Top resid features:
they
Token they
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
formally
Token formally
Feature activation+0.004
Top resid features:
Bar
Token Bar
Feature activation-0.003
Top resid features:
ro
Tokenro
Feature activation-0.001
Top resid features:
so
Tokenso
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.080
Top resid features:
the
Token the
Feature activation-0.028
Top resid features:
talks
Token talks
Feature activation+3.708
Top resid features:
had
Token had
Feature activation+0.013
Top resid features:
failed
Token failed
Feature activation-0.103
Top resid features:
owing
Token owing
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
foreign
Token foreign
Feature activation+0.006
Top resid features:
support
Token support
Feature activation-0.010
Top resid features:
before
Token before
Feature activation+0.016
Top resid features:
launching
Token launching
Feature activation+0.030
Top resid features:
Brexit
Token Brexit
Feature activation+0.048
Top resid features:
talks
Token talks
Feature activation+2.994
Top resid features:
,
Token,
Feature activation+0.184
Top resid features:
which
Token which
Feature activation+0.083
Top resid features:
are
Token are
Feature activation+0.092
Top resid features:
set
Token set
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
This
TokenThis
Feature activation-0.002
Top resid features:
week
Token week
Feature activation-0.013
Top resid features:
's
Token's
Feature activation-0.012
Top resid features:
nuclear
Token nuclear
Feature activation+0.020
Top resid features:
talks
Token talks
Feature activation+3.255
Top resid features:
in
Token in
Feature activation+0.306
Top resid features:
Geneva
Token Geneva
Feature activation+0.095
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Switzerland
Token Switzerland
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
al
Tokenal
Feature activation-0.002
Top resid features:
em
Tokenem
Feature activation-0.004
Top resid features:
said
Token said
Feature activation+0.005
Top resid features:
separate
Token separate
Feature activation+0.013
Top resid features:
peace
Token peace
Feature activation+0.092
Top resid features:
talks
Token talks
Feature activation+2.297
Top resid features:
under
Token under
Feature activation+0.040
Top resid features:
U
Token U
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
N
TokenN
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
This
TokenThis
Feature activation-0.018
Top resid features:
week
Token week
Feature activation-0.002
Top resid features:
's
Token's
Feature activation-0.006
Top resid features:
nuclear
Token nuclear
Feature activation+0.006
Top resid features:
talks
Token talks
Feature activation+2.927
Top resid features:
in
Token in
Feature activation+0.322
Top resid features:
Geneva
Token Geneva
Feature activation+0.095
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
Switzerland
Token Switzerland
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
we
Token we
Feature activation+0.002
Top resid features:
look
Token look
Feature activation-0.003
Top resid features:
forward
Token forward
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
beginning
Token beginning
Feature activation+0.004
Top resid features:
negotiations
Token negotiations
Feature activation+1.557
Top resid features:
once
Token once
Feature activation+0.003
Top resid features:
they
Token they
Feature activation+0.010
Top resid features:
have
Token have
Feature activation+0.005
Top resid features:
been
Token been
Feature activation+0.004
Top resid features:
formally
Token formally
Feature activation+0.013
Top resid features:
we
Token we
Feature activation+0.017
Top resid features:
look
Token look
Feature activation+0.024
Top resid features:
forward
Token forward
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
beginning
Token beginning
Feature activation+0.104
Top resid features:
negotiations
Token negotiations
Feature activation+2.779
Top resid features:
once
Token once
Feature activation+0.235
Top resid features:
they
Token they
Feature activation+0.016
Top resid features:
have
Token have
Feature activation-0.157
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
formally
Token formally
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Hours
TokenHours
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.056
Top resid features:
talks
Token talks
Feature activation+2.703
Top resid features:
failed
Token failed
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
bridge
Token bridge
Feature activation+0.000
Top resid features:
big
Token big
Feature activation+0.000
Top resid features:
gaps
Token gaps
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.028
Top resid features:
also
Token also
Feature activation+0.031
Top resid features:
evident
Token evident
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
negotiations
Token negotiations
Feature activation+3.149
Top resid features:
that
Token that
Feature activation-0.010
Top resid features:
resulted
Token resulted
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
foreign
Token foreign
Feature activation+0.005
Top resid features:
support
Token support
Feature activation-0.009
Top resid features:
before
Token before
Feature activation+0.015
Top resid features:
launching
Token launching
Feature activation+0.029
Top resid features:
Brexit
Token Brexit
Feature activation+0.028
Top resid features:
talks
Token talks
Feature activation+2.615
Top resid features:
,
Token,
Feature activation+0.287
Top resid features:
which
Token which
Feature activation+0.065
Top resid features:
are
Token are
Feature activation+0.065
Top resid features:
set
Token set
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.117
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.06

Head 3: 0.05

Head 4: 0.05

Head 5: 0.04

Head 6: 0.03

Head 7: 0.08

Head 8: 0.03

Head 9: 0.04

Head 10: 0.51

Head 11: 0.07

Positive logits

negotiators2.82

negotiations2.57

negotiation2.38

negotiating2.33

negotiator2.25

negotiated2.23

challeng2.19

progress2.14

emate2.12

Talks2.12

arrang2.12

deleg2.05

deadline2.04

talks2.02

dismant2.01

finalized1.98

ebus1.97

procedural1.96

progressing1.96

prepar1.95

Negative logits

Hero-2.03

Gamer-1.88

commenter-1.76

onym-1.74

McA-1.70

Hate-1.69

Millenn-1.69

Gallagher-1.66

Readers-1.65

Candy-1.64

allele-1.62

Attribute-1.61

Magazine-1.60

Kills-1.59

Trigger-1.59

esity-1.57

Eminem-1.57

Winchester-1.55

Halloween-1.55

columnist-1.54

INTERVAL 3.457 - 3.841
CONTAINS 0.000%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.552
that
Token that
Feature activation+2.103
resulted
Token resulted
Feature activation+2.584
in
Token in
Feature activation+3.841
Thursday
Token Thursday
Feature activation+0.213
's
Token's
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
that
Token that
Feature activation+0.000
Chrysler
Token Chrysler
Feature activation+0.000

INTERVAL 3.072 - 3.457
CONTAINS 0.000%

This
TokenThis
Feature activation+0.000
week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
talks
Token talks
Feature activation+0.887
in
Token in
Feature activation+3.229
Geneva
Token Geneva
Feature activation+1.636
,
Token,
Feature activation+1.468
Switzerland
Token Switzerland
Feature activation+0.403
,
Token,
Feature activation+0.539
involving
Token involving
Feature activation+3.257
in
Token in
Feature activation+3.229
Geneva
Token Geneva
Feature activation+1.636
,
Token,
Feature activation+1.468
Switzerland
Token Switzerland
Feature activation+0.403
,
Token,
Feature activation+0.539
involving
Token involving
Feature activation+3.257
Iran
Token Iran
Feature activation+0.000
and
Token and
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

INTERVAL 2.688 - 3.072
CONTAINS 0.000%

the
Token the
Feature activation+0.187
role
Token role
Feature activation+0.000
played
Token played
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.565
talks
Token talks
Feature activation+3.048
by
Token by
Feature activation+1.195
the
Token the
Feature activation+1.131
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
launching
Token launching
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
the
Token the
Feature activation+0.058

INTERVAL 2.304 - 2.688
CONTAINS 0.001%

evident
Token evident
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.552
that
Token that
Feature activation+2.103
resulted
Token resulted
Feature activation+2.584
in
Token in
Feature activation+3.841
Thursday
Token Thursday
Feature activation+0.213
's
Token's
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
that
Token that
Feature activation+0.000
before
Token before
Feature activation+0.000
launching
Token launching
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
so
Tokenso
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
talks
Token talks
Feature activation+0.761
had
Token had
Feature activation+1.754
failed
Token failed
Feature activation+2.480
owing
Token owing
Feature activation+0.000
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
important
Tokenimportant
Feature activation+0.905
differences
Token differences
Feature activation+1.271
talks
Token talks
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
the
Token the
Feature activation+0.058
most
Token most
Feature activation+0.000
complicated
Token complicated
Feature activation+0.706
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
taken
Token taken
Feature activation+0.000
place
Token place
Feature activation+2.685
on
Token on
Feature activation+0.317
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000

INTERVAL 1.920 - 2.304
CONTAINS 0.001%

ices
Tokenices
Feature activation+0.000
in
Token in
Feature activation+0.294
Geneva
Token Geneva
Feature activation+0.000
were
Token were
Feature activation+0.773
not
Token not
Feature activation+0.355
progressing
Token progressing
Feature activation+2.280
.
Token.
Feature activation+0.064
Local
Token Local
Feature activation+0.000
reconciliation
Token reconciliation
Feature activation+0.000
deals
Token deals
Feature activation+0.205
that
Token that
Feature activation+1.006
issue
Token issue
Feature activation+0.430
was
Token was
Feature activation+0.333
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
being
Tokenbeing
Feature activation+0.000
discussed
Token discussed
Feature activation+2.010
on
Token on
Feature activation+0.863
a
Token a
Feature activation+0.189
separate
Token separate
Feature activation+0.092
track
Token track
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.622
are
Token are
Feature activation+2.870
set
Token set
Feature activation+0.691
to
Token to
Feature activation+2.324
be
Token be
Feature activation+2.091
among
Token among
Feature activation+0.012
the
Token the
Feature activation+0.058
most
Token most
Feature activation+0.000
complicated
Token complicated
Feature activation+0.706
Britain
Token Britain
Feature activation+0.000
after
Token after
Feature activation+0.000
closed
Token closed
Feature activation+0.000
-
Token-
Feature activation+0.000
door
Tokendoor
Feature activation+0.000
talks
Token talks
Feature activation+0.000
at
Token at
Feature activation+2.060
UN
Token UN
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
clear
Token clear
Feature activation+0.000
both
Token both
Feature activation+0.513
sides
Token sides
Feature activation+2.559
wish
Token wish
Feature activation+0.272
to
Token to
Feature activation+0.554
approach
Token approach
Feature activation+2.149
these
Token these
Feature activation+0.047
talks
Token talks
Feature activation+0.594
construct
Token construct
Feature activation+0.027
ively
Tokenively
Feature activation+0.188
,
Token,
Feature activation+0.000

INTERVAL 1.536 - 1.920
CONTAINS 0.001%

week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
talks
Token talks
Feature activation+0.887
in
Token in
Feature activation+3.229
Geneva
Token Geneva
Feature activation+1.636
,
Token,
Feature activation+1.468
Switzerland
Token Switzerland
Feature activation+0.403
,
Token,
Feature activation+0.539
involving
Token involving
Feature activation+3.257
Iran
Token Iran
Feature activation+0.000
two
Token two
Feature activation+0.000
countries
Token countries
Feature activation+0.000
met
Token met
Feature activation+0.000
for
Token for
Feature activation+0.000
talks
Token talks
Feature activation+0.000
in
Token in
Feature activation+1.568
Beijing
Token Beijing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
em
Tokenem
Feature activation+0.000
said
Token said
Feature activation+0.000
separate
Token separate
Feature activation+0.159
peace
Token peace
Feature activation+0.000
talks
Token talks
Feature activation+0.301
under
Token under
Feature activation+1.582
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
ausp
Token ausp
Feature activation+0.000
forward
Token forward
Feature activation+0.000
to
Token to
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
once
Token once
Feature activation+0.832
they
Token they
Feature activation+1.601
have
Token have
Feature activation+2.133
been
Token been
Feature activation+0.246
formally
Token formally
Feature activation+0.000
agreed
Token agreed
Feature activation+0.141
by
Token by
Feature activation+0.418
GF
TokenGF
Feature activation+0.000
W
TokenW
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiating
Token negotiating
Feature activation+0.000
table
Token table
Feature activation+1.561
is
Token is
Feature activation+0.188
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 1.152 - 1.536
CONTAINS 0.002%

on
Token on
Feature activation+0.000
House
Token House
Feature activation+0.000
and
Token and
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
negotiators
Token negotiators
Feature activation+0.000
working
Token working
Feature activation+1.403
on
Token on
Feature activation+0.984
the
Token the
Feature activation+0.149
bill
Token bill
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
...
Token ...
Feature activation+0.000
on
Token on
Feature activation+0.395
how
Token how
Feature activation+0.366
to
Token to
Feature activation+0.241
resolve
Token resolve
Feature activation+1.265
all
Token all
Feature activation+0.007
the
Token the
Feature activation+0.000
problems
Token problems
Feature activation+0.062
and
Token and
Feature activation+0.000
outstanding
Token outstanding
Feature activation+0.261
atories
Tokenatories
Feature activation+0.973
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
ceasefire
Token ceasefire
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
reached
Token reached
Feature activation+1.194
in
Token in
Feature activation+1.010
December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.105
excluded
Token excluded
Feature activation+0.851
bilateral
Token bilateral
Feature activation+0.000
meetings
Token meetings
Feature activation+0.000
that
Token that
Feature activation+0.401
will
Token will
Feature activation+0.116
take
Token take
Feature activation+0.284
place
Token place
Feature activation+1.239
with
Token with
Feature activation+0.106
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
of
Token of
Feature activation+0.000
President
Token President
Feature activation+0.000
be
Token be
Feature activation+0.000
identified
Token identified
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
talks
Token talks
Feature activation+0.237
are
Token are
Feature activation+1.491
private
Token private
Feature activation+1.592
.
Token.
Feature activation+0.000
S
Token S
Feature activation+0.000
ES
TokenES
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.768 - 1.152
CONTAINS 0.005%

progressing
Token progressing
Feature activation+2.280
.
Token.
Feature activation+0.064
Local
Token Local
Feature activation+0.000
reconciliation
Token reconciliation
Feature activation+0.000
deals
Token deals
Feature activation+0.205
that
Token that
Feature activation+1.006
the
Token the
Feature activation+0.013
government
Token government
Feature activation+0.000
is
Token is
Feature activation+0.000
pursuing
Token pursuing
Feature activation+0.000
with
Token with
Feature activation+0.000
peace
Token peace
Feature activation+0.000
talks
Token talks
Feature activation+0.000
with
Token with
Feature activation+1.067
Pakistan
Token Pakistan
Feature activation+0.000
don
Token don
Feature activation+0.228
't
Token't
Feature activation+0.929
make
Token make
Feature activation+0.863
any
Token any
Feature activation+0.515
sense
Token sense
Feature activation+0.854
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ing
Tokening
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+1.003
approval
Token approval
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
please
Token please
Feature activation+0.000
the
Token the
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
,
Token,
Feature activation+0.543
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
never
Token never
Feature activation+0.000
helpful
Token helpful
Feature activation+1.058
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
undermines
Token undermines
Feature activation+0.000
public
Token public
Feature activation+0.000
confidence
Token confidence
Feature activation+0.000
there
Token there
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.069
dialogue
Token dialogue
Feature activation+1.061
,
Token,
Feature activation+0.877
as
Token as
Feature activation+0.000
difficult
Token difficult
Feature activation+0.904
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.205
challenges
Token challenges
Feature activation+0.021

INTERVAL 0.384 - 0.768
CONTAINS 0.011%

')
Token')
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Over
TokenOver
Feature activation+0.401
a
Token a
Feature activation+0.001
shaky
Token shaky
Feature activation+0.638
line
Token line
Feature activation+0.206
âĢĶ
Token âĢĶ
Feature activation+0.000
they
Token they
Feature activation+0.598
had
Token had
Feature activation+0.123
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.129
,
Token,
Feature activation+0.000
are
Token are
Feature activation+2.243
a
Token a
Feature activation+1.220
hopeful
Token hopeful
Feature activation+0.539
sign
Token sign
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
Kurdish
Token Kurdish
Feature activation+0.000
region
Token region
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.508
a
Token a
Feature activation+0.203
document
Token document
Feature activation+0.580
seen
Token seen
Feature activation+0.000
by
Token by
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
administration
Token administration
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
talks
Token talks
Feature activation+0.561
âĢĶ
TokenâĢĶ
Feature activation+0.000
in
Tokenin
Feature activation+0.803
particular
Token particular
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.187
border
Tokenborder
Feature activation+0.000
surge
Token surge
Feature activation+0.000
')
Token')
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Over
TokenOver
Feature activation+0.401
a
Token a
Feature activation+0.001
shaky
Token shaky
Feature activation+0.638
line
Token line
Feature activation+0.206
âĢĶ
Token âĢĶ
Feature activation+0.000
they
Token they
Feature activation+0.598

INTERVAL 0.000 - 0.384
CONTAINS 99.979%

California
Token California
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
states
Token states
Feature activation+0.000
like
Token like
Feature activation+0.000
Idaho
Token Idaho
Feature activation+0.000
and
Token and
Feature activation+0.000
Alaska
Token Alaska
Feature activation+0.000
and
Token and
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
,
Token,
Feature activation+0.000
annual
Token annual
Feature activation+0.000
delegation
Token delegation
Feature activation+0.000
to
Token to
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
for
Token for
Feature activation+0.000
talks
Token talks
Feature activation+0.000
with
Token with
Feature activation+0.000
Vatican
Token Vatican
Feature activation+0.000
officials
Token officials
Feature activation+0.000
.
Token.
Feature activation+0.000
During
Token During
Feature activation+0.300
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
version
Token version
Feature activation+0.000
for
Token for
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
least
Token least
Feature activation+0.000
;
Token;
Feature activation+0.000
I
Token I
Feature activation+0.000
men
Tokenmen
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
joining
Token joining
Feature activation+0.000
the
Token the
Feature activation+0.000
missile
Token missile
Feature activation+0.000
defence
Token defence
Feature activation+0.000
system
Token system
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Such
TokenSuch
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
declared
Token declared
Feature activation+0.000
by
Token by
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H5.10: (feature 24498)

TOP ACTIVATIONS
MAX = 5.230

scheme
Token scheme
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+2.578
frequently
Token frequently
Feature activation+5.038
targets
Token targets
Feature activation+1.222
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
blasting
Token blasting
Feature activation+3.722
begin
Token begin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+1.690
has
Token has
Feature activation+4.933
expressed
Token expressed
Feature activation+4.473
sympathy
Token sympathy
Feature activation+0.590
for
Token for
Feature activation+1.036
the
Token the
Feature activation+0.000
so
Token so
Feature activation+0.000
networks
Token networks
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+4.890
administration
Token administration
Feature activation+1.568
.
Token.
Feature activation+0.973
Ċ
TokenĊ
Feature activation+0.590
Ċ
TokenĊ
Feature activation+1.012
Earlier
TokenEarlier
Feature activation+0.305
press
Token press
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.428
The
TokenThe
Feature activation+0.163
billionaire
Token billionaire
Feature activation+4.143
businessman
Token businessman
Feature activation+4.761
has
Token has
Feature activation+3.963
voc
Token voc
Feature activation+0.224
ifer
Tokenifer
Feature activation+0.000
ously
Tokenously
Feature activation+1.174
defended
Token defended
Feature activation+1.790
own
Token own
Feature activation+0.000
separate
Token separate
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+2.861
has
Token has
Feature activation+4.645
repeatedly
Token repeatedly
Feature activation+4.002
denied
Token denied
Feature activation+4.055
any
Token any
Feature activation+0.344
knowledge
Token knowledge
Feature activation+0.019
of
Token of
Feature activation+0.000
plan
Token plan
Feature activation+0.000
a
Token a
Feature activation+0.000
central
Token central
Feature activation+0.000
point
Token point
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+4.632
campaign
Token campaign
Feature activation+4.121
,
Token,
Feature activation+0.438
branding
Token branding
Feature activation+2.882
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
made
Token made
Feature activation+3.938
repeal
Token repeal
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+4.613
predecessor
Token predecessor
Feature activation+0.645
's
Token's
Feature activation+0.320
signature
Token signature
Feature activation+0.173
plan
Token plan
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000
tape
Token tape
Feature activation+0.000
of
Token of
Feature activation+0.000
Trump
Token Trump
Feature activation+1.239
describing
Token describing
Feature activation+3.541
his
Token his
Feature activation+4.529
pursuit
Token pursuit
Feature activation+1.520
of
Token of
Feature activation+2.930
women
Token women
Feature activation+0.000
in
Token in
Feature activation+0.000
lur
Token lur
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+1.690
has
Token has
Feature activation+4.933
expressed
Token expressed
Feature activation+4.473
sympathy
Token sympathy
Feature activation+0.590
for
Token for
Feature activation+1.036
the
Token the
Feature activation+0.000
so
Token so
Feature activation+0.000
-
Token-
Feature activation+0.000
grown
Token grown
Feature activation+0.000
as
Token as
Feature activation+0.000
Mr
Token Mr
Feature activation+0.605
.
Token.
Feature activation+0.490
Trump
Token Trump
Feature activation+2.106
has
Token has
Feature activation+4.433
praised
Token praised
Feature activation+2.960
Russian
Token Russian
Feature activation+0.057
President
Token President
Feature activation+0.039
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
to
Token to
Feature activation+0.000
accept
Token accept
Feature activation+0.000
that
Token that
Feature activation+0.000
Donald
Token Donald
Feature activation+0.024
Trump
Token Trump
Feature activation+1.124
's
Token's
Feature activation+4.426
rise
Token rise
Feature activation+2.082
to
Token to
Feature activation+2.052
power
Token power
Feature activation+2.606
is
Token is
Feature activation+0.583
not
Token not
Feature activation+0.057
supposedly
Token supposedly
Feature activation+0.000
accounted
Token accounted
Feature activation+0.000
for
Token for
Feature activation+0.000
Donald
Token Donald
Feature activation+0.282
Trump
Token Trump
Feature activation+0.968
's
Token's
Feature activation+4.375
victory
Token victory
Feature activation+1.090
.
Token.
Feature activation+0.000
Absolutely
Token Absolutely
Feature activation+0.000
not
Token not
Feature activation+0.000
his
Token his
Feature activation+0.406
im
Tokenim
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
,
Token,
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
Trump
Token Trump
Feature activation+0.802
's
Token's
Feature activation+4.374
decision
Token decision
Feature activation+1.520
,
Token,
Feature activation+0.240
while
Token while
Feature activation+0.000
also
Token also
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+1.479
,
Token,
Feature activation+1.859
who
Token who
Feature activation+4.374
is
Token is
Feature activation+2.744
yet
Token yet
Feature activation+0.012
to
Token to
Feature activation+0.933
accept
Token accept
Feature activation+1.298
the
Token the
Feature activation+0.664
.
Token.
Feature activation+0.066
Ċ
TokenĊ
Feature activation+0.214
Ċ
TokenĊ
Feature activation+0.077
Trump
TokenTrump
Feature activation+2.319
has
Token has
Feature activation+3.896
promised
Token promised
Feature activation+4.366
to
Token to
Feature activation+3.691
âĢ
Token âĢ
Feature activation+0.556
ľ
Tokenľ
Feature activation+0.000
put
Tokenput
Feature activation+1.224
America
Token America
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.691
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.533
tweets
Token tweets
Feature activation+4.359
on
Token on
Feature activation+0.460
the
Token the
Feature activation+0.215
issue
Token issue
Feature activation+0.000
on
Token on
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
spinning
Token spinning
Feature activation+0.680
conspiracy
Token conspiracy
Feature activation+0.000
theories
Token theories
Feature activation+0.399
to
Token to
Feature activation+0.027
keep
Token keep
Feature activation+0.000
his
Token his
Feature activation+4.359
campaign
Token campaign
Feature activation+0.680
afloat
Token afloat
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
different
Token different
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
man
Token man
Feature activation+4.342
is
Token is
Feature activation+3.920
a
Token a
Feature activation+2.043
liar
Token liar
Feature activation+3.004
,
Token,
Feature activation+0.355
a
Token a
Feature activation+0.167
Ċ
TokenĊ
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.047
Trump
Token Trump
Feature activation+0.391
,
Token,
Feature activation+1.246
the
Token the
Feature activation+2.079
presumptive
Token presumptive
Feature activation+4.325
Republican
Token Republican
Feature activation+1.737
nominee
Token nominee
Feature activation+3.702
for
Token for
Feature activation+2.426
president
Token president
Feature activation+2.883
,
Token,
Feature activation+2.439
act
Token act
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.541
has
Token has
Feature activation+4.300
recognized
Token recognized
Feature activation+1.969
repeatedly
Token repeatedly
Feature activation+0.637
the
Token the
Feature activation+0.196
threat
Token threat
Feature activation+0.023
that
Token that
Feature activation+0.000

Top DFA by src position
MAX = 5.119

the
Token the
Feature activation+0.001
Top resid features:
scheme
Token scheme
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Trump
TokenTrump
Feature activation+2.477
Top resid features:
frequently
Token frequently
Feature activation+0.214
Top resid features:
targets
Token targets
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
media
Token media
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:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation+0.000
Top resid features:
illegally
Token illegally
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Trump
Token Trump
Feature activation+2.939
Top resid features:
suspended
Token suspended
Feature activation-0.115
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
program
Token program
Feature activation+0.006
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
month
Token month
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
scheme
Token scheme
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Trump
TokenTrump
Feature activation+4.470
Top resid features:
frequently
Token frequently
Feature activation-0.076
Top resid features:
targets
Token targets
Feature activation-0.109
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
media
Token media
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
problem
Token problem
Feature activation-0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Donald
TokenDonald
Feature activation+0.273
Top resid features:
Trump
Token Trump
Feature activation+4.793
Top resid features:
takes
Token takes
Feature activation-0.030
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
press
Token press
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
its
Token its
Feature activation+0.019
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
separate
Token separate
Feature activation-0.004
Top resid features:
investigation
Token investigation
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
Trump
Token Trump
Feature activation+2.507
Top resid features:
has
Token has
Feature activation+0.193
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.000
Top resid features:
denied
Token denied
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
knowledge
Token knowledge
Feature activation+0.000
Top resid features:
Care
Token Care
Feature activation+0.002
Top resid features:
Act
Token Act
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Trump
TokenTrump
Feature activation+4.711
Top resid features:
made
Token made
Feature activation+0.275
Top resid features:
repeal
Token repeal
Feature activation+0.010
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
replace
Token replace
Feature activation+0.004
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Care
Token Care
Feature activation+0.005
Top resid features:
Act
Token Act
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Trump
TokenTrump
Feature activation+4.526
Top resid features:
made
Token made
Feature activation+0.194
Top resid features:
repeal
Token repeal
Feature activation-0.159
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
replace
Token replace
Feature activation+0.035
Top resid features:
of
Token of
Feature activation+0.250
Top resid features:
wake
Token wake
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
tape
Token tape
Feature activation+0.054
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
Trump
Token Trump
Feature activation+5.119
Top resid features:
describing
Token describing
Feature activation-0.007
Top resid features:
his
Token his
Feature activation+0.075
Top resid features:
pursuit
Token pursuit
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation-0.000
Top resid features:
illegally
Token illegally
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Trump
Token Trump
Feature activation+2.834
Top resid features:
suspended
Token suspended
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
program
Token program
Feature activation+0.006
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
month
Token month
Feature activation+0.003
Top resid features:
GOP
Token GOP
Feature activation+0.029
Top resid features:
concerns
Token concerns
Feature activation-0.004
Top resid features:
about
Token about
Feature activation+0.019
Top resid features:
Mr
Token Mr
Feature activation+0.045
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Trump
Token Trump
Feature activation+2.955
Top resid features:
on
Token on
Feature activation-0.067
Top resid features:
foreign
Token foreign
Feature activation+0.010
Top resid features:
policy
Token policy
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
which
Token which
Feature activation+0.024
Top resid features:
chiefs
Token chiefs
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
accept
Token accept
Feature activation+0.014
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
Donald
Token Donald
Feature activation+1.101
Top resid features:
Trump
Token Trump
Feature activation+3.724
Top resid features:
's
Token's
Feature activation+0.099
Top resid features:
rise
Token rise
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.075
Top resid features:
supposedly
Token supposedly
Feature activation+0.028
Top resid features:
accounted
Token accounted
Feature activation+0.101
Top resid features:
for
Token for
Feature activation+0.098
Top resid features:
Donald
Token Donald
Feature activation+1.407
Top resid features:
Trump
Token Trump
Feature activation+3.195
Top resid features:
's
Token's
Feature activation+0.053
Top resid features:
victory
Token victory
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Absolutely
Token Absolutely
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
un
Tokenun
Feature activation-0.002
Top resid features:
im
Tokenim
Feature activation-0.006
Top resid features:
ah
Tokenah
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
criticized
Token criticized
Feature activation+0.111
Top resid features:
Trump
Token Trump
Feature activation+4.818
Top resid features:
's
Token's
Feature activation+0.112
Top resid features:
decision
Token decision
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.015
Top resid features:
successor
Token successor
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Trump
TokenTrump
Feature activation+3.755
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
who
Token who
Feature activation+0.042
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
nonsense
Token nonsense
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Trump
TokenTrump
Feature activation+3.685
Top resid features:
has
Token has
Feature activation+0.115
Top resid features:
promised
Token promised
Feature activation+0.047
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
wake
Token wake
Feature activation-0.006
Top resid features:
of
Token of
Feature activation+0.040
Top resid features:
US
Token US
Feature activation-0.037
Top resid features:
President
Token President
Feature activation+0.008
Top resid features:
Donald
Token Donald
Feature activation+1.501
Top resid features:
Trump
Token Trump
Feature activation+3.318
Top resid features:
âĢ
TokenâĢ
Feature activation+0.022
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
s
Tokens
Feature activation+0.042
Top resid features:
tweets
Token tweets
Feature activation+0.080
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
memo
Token memo
Feature activation+0.022
Top resid features:
accusing
Token accusing
Feature activation+0.025
Top resid features:
Mr
Token Mr
Feature activation+0.187
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Trump
Token Trump
Feature activation+4.388
Top resid features:
of
Token of
Feature activation+0.040
Top resid features:
spinning
Token spinning
Feature activation-0.002
Top resid features:
conspiracy
Token conspiracy
Feature activation+0.018
Top resid features:
theories
Token theories
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
has
Token has
Feature activation-0.002
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
highly
Token highly
Feature activation-0.002
Top resid features:
critical
Token critical
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
Trump
Token Trump
Feature activation+4.683
Top resid features:
and
Token and
Feature activation+0.173
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Donald
TokenDonald
Feature activation+0.449
Top resid features:
Trump
Token Trump
Feature activation+4.238
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
presumptive
Token presumptive
Feature activation-0.021
Top resid features:
Republican
Token Republican
Feature activation+0.000
Top resid features:
nominee
Token nominee
Feature activation+0.000
Top resid features:
like
Tokenlike
Feature activation+0.007
Top resid features:
act
Token act
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Trump
TokenTrump
Feature activation+4.625
Top resid features:
has
Token has
Feature activation+0.196
Top resid features:
recognized
Token recognized
Feature activation+0.000
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
threat
Token threat
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.02

Head 2: 0.03

Head 3: 0.04

Head 4: 0.03

Head 5: 0.05

Head 6: 0.02

Head 7: 0.02

Head 8: 0.03

Head 9: 0.09

Head 10: 0.51

Head 11: 0.15

Positive logits

mania1.63

realDonaldTrump1.58

boasting1.54

bragging1.52

tweeting1.52

tweets1.49

boast1.48

voters1.48

dispar1.43

frontrunner1.41

tweet1.39

campaigned1.38

Tweet1.38

misogyn1.37

unpredict1.37

retweet1.37

cand1.36

falsely1.36

prejud1.35

Tweet1.35

Negative logits

NAD-1.64

ASA-1.61

Sisters-1.59

Brill-1.47

AGES-1.40

[&-1.40

Uriel-1.34

Nag-1.33

Seraph-1.33

TPS-1.33

Scythe-1.33

ACS-1.31

Okin-1.31

convent-1.30

tein-1.28

ENCY-1.27

UNESCO-1.27

Sac-1.26

lineback-1.26

tel-1.25

INTERVAL 4.707 - 5.230
CONTAINS 0.001%

begin
Token begin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+1.690
has
Token has
Feature activation+4.933
expressed
Token expressed
Feature activation+4.473
sympathy
Token sympathy
Feature activation+0.590
for
Token for
Feature activation+1.036
the
Token the
Feature activation+0.000
so
Token so
Feature activation+0.000
press
Token press
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.428
The
TokenThe
Feature activation+0.163
billionaire
Token billionaire
Feature activation+4.143
businessman
Token businessman
Feature activation+4.761
has
Token has
Feature activation+3.963
voc
Token voc
Feature activation+0.224
ifer
Tokenifer
Feature activation+0.000
ously
Tokenously
Feature activation+1.174
defended
Token defended
Feature activation+1.790
scheme
Token scheme
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+2.578
frequently
Token frequently
Feature activation+5.038
targets
Token targets
Feature activation+1.222
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
blasting
Token blasting
Feature activation+3.722
networks
Token networks
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+4.890
administration
Token administration
Feature activation+1.568
.
Token.
Feature activation+0.973
Ċ
TokenĊ
Feature activation+0.590
Ċ
TokenĊ
Feature activation+1.012
Earlier
TokenEarlier
Feature activation+0.305

INTERVAL 4.184 - 4.707
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+1.479
,
Token,
Feature activation+1.859
who
Token who
Feature activation+4.374
is
Token is
Feature activation+2.744
yet
Token yet
Feature activation+0.012
to
Token to
Feature activation+0.933
accept
Token accept
Feature activation+1.298
the
Token the
Feature activation+0.664
grown
Token grown
Feature activation+0.000
as
Token as
Feature activation+0.000
Mr
Token Mr
Feature activation+0.605
.
Token.
Feature activation+0.490
Trump
Token Trump
Feature activation+2.106
has
Token has
Feature activation+4.433
praised
Token praised
Feature activation+2.960
Russian
Token Russian
Feature activation+0.057
President
Token President
Feature activation+0.039
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
become
Token become
Feature activation+0.000
more
Token more
Feature activation+0.000
contentious
Token contentious
Feature activation+0.000
since
Token since
Feature activation+0.000
Trump
Token Trump
Feature activation+1.231
entered
Token entered
Feature activation+4.261
the
Token the
Feature activation+2.459
White
Token White
Feature activation+0.485
House
Token House
Feature activation+1.146
half
Token half
Feature activation+0.000
a
Token a
Feature activation+0.000
spinning
Token spinning
Feature activation+0.680
conspiracy
Token conspiracy
Feature activation+0.000
theories
Token theories
Feature activation+0.399
to
Token to
Feature activation+0.027
keep
Token keep
Feature activation+0.000
his
Token his
Feature activation+4.359
campaign
Token campaign
Feature activation+0.680
afloat
Token afloat
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
have
Token have
Feature activation+1.464
concerns
Token concerns
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+3.772
's
Token's
Feature activation+4.224
comments
Token comments
Feature activation+3.450
are
Token are
Feature activation+0.637
affecting
Token affecting
Feature activation+0.437
public
Token public
Feature activation+0.000
perceptions
Token perceptions
Feature activation+0.000

INTERVAL 3.661 - 4.184
CONTAINS 0.007%

Ċ
TokenĊ
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.428
The
TokenThe
Feature activation+0.163
billionaire
Token billionaire
Feature activation+4.143
businessman
Token businessman
Feature activation+4.761
has
Token has
Feature activation+3.963
voc
Token voc
Feature activation+0.224
ifer
Tokenifer
Feature activation+0.000
ously
Tokenously
Feature activation+1.174
defended
Token defended
Feature activation+1.790
Second
Token Second
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+2.861
has
Token has
Feature activation+4.645
repeatedly
Token repeatedly
Feature activation+4.002
denied
Token denied
Feature activation+4.055
any
Token any
Feature activation+0.344
knowledge
Token knowledge
Feature activation+0.019
of
Token of
Feature activation+0.000
improper
Token improper
Feature activation+0.000
contacts
Token contacts
Feature activation+0.000
supposedly
Token supposedly
Feature activation+0.000
appalled
Token appalled
Feature activation+0.000
by
Token by
Feature activation+0.000
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.896
's
Token's
Feature activation+3.823
antics
Token antics
Feature activation+2.804
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.000
elections
Token elections
Feature activation+0.000
frequently
Token frequently
Feature activation+5.038
targets
Token targets
Feature activation+1.222
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
blasting
Token blasting
Feature activation+3.722
networks
Token networks
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
of
Token of
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+0.000
everyday
Token everyday
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+4.153
side
Token side
Feature activation+0.236
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
remind
Token remind
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 3.138 - 3.661
CONTAINS 0.011%

turned
Token turned
Feature activation+1.304
a
Token a
Feature activation+0.096
similar
Token similar
Feature activation+0.000
trick
Token trick
Feature activation+0.256
when
Token when
Feature activation+0.800
he
Token he
Feature activation+3.296
cited
Token cited
Feature activation+2.720
Russian
Token Russian
Feature activation+0.000
President
Token President
Feature activation+0.000
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.081
it
Token it
Feature activation+0.000
back
Token back
Feature activation+0.000
in
Token in
Feature activation+0.221
December
Token December
Feature activation+1.558
while
Token while
Feature activation+0.117
speaking
Token speaking
Feature activation+3.499
before
Token before
Feature activation+0.628
the
Token the
Feature activation+0.130
Republican
Token Republican
Feature activation+0.747
Jewish
Token Jewish
Feature activation+0.000
Coalition
Token Coalition
Feature activation+0.000
Trump
Token Trump
Feature activation+0.978
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.782
outlandish
Token outlandish
Feature activation+2.607
tweets
Token tweets
Feature activation+3.378
âĢĶ
Token âĢĶ
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.122
outlandish
Token outlandish
Feature activation+0.930
in
Token in
Feature activation+0.000
London
Token London
Feature activation+0.000
to
Token to
Feature activation+0.000
oppose
Token oppose
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+3.625
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.684
temporary
Token temporary
Feature activation+0.577
travel
Token travel
Feature activation+0.028
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
told
Token told
Feature activation+1.112
us
Token us
Feature activation+0.000
he
Token he
Feature activation+3.355
will
Token will
Feature activation+2.356
be
Token be
Feature activation+1.370
.
Token.
Feature activation+0.521
As
Token As
Feature activation+0.107
he
Token he
Feature activation+3.160

INTERVAL 2.615 - 3.138
CONTAINS 0.017%

AC
TokenAC
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+3.016
says
Token says
Feature activation+2.046
he
Token he
Feature activation+2.949
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.140
thinking
Token thinking
Feature activation+0.340
about
Token about
Feature activation+0.199
around
Token around
Feature activation+0.000
Donald
Token Donald
Feature activation+1.475
Trump
Token Trump
Feature activation+0.853
knows
Token knows
Feature activation+0.000
he
Token he
Feature activation+2.265
's
Token's
Feature activation+2.960
not
Token not
Feature activation+2.442
stable
Token stable
Feature activation+0.497
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
bold
Token bold
Feature activation+0.544
statements
Token statements
Feature activation+2.753
about
Token about
Feature activation+1.169
his
Token his
Feature activation+3.566
plans
Token plans
Feature activation+2.437
to
Token to
Feature activation+2.924
set
Token set
Feature activation+0.309
climate
Token climate
Feature activation+0.000
policy
Token policy
Feature activation+0.000
back
Token back
Feature activation+0.000
by
Token by
Feature activation+0.000
det
Token det
Feature activation+0.000
ested
Tokenested
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+3.026
is
Token is
Feature activation+2.928
sending
Token sending
Feature activation+0.716
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.076
message
Token message
Feature activation+0.268
the
Token the
Feature activation+0.000
as
Token as
Feature activation+0.000
Mr
Token Mr
Feature activation+0.605
.
Token.
Feature activation+0.490
Trump
Token Trump
Feature activation+2.106
has
Token has
Feature activation+4.433
praised
Token praised
Feature activation+2.960
Russian
Token Russian
Feature activation+0.057
President
Token President
Feature activation+0.039
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
and
Token and
Feature activation+0.060

INTERVAL 2.092 - 2.615
CONTAINS 0.021%

candidate
Token candidate
Feature activation+2.184
,
Token,
Feature activation+0.631
Mr
Token Mr
Feature activation+0.311
Duterte
Token Duterte
Feature activation+0.758
promised
Token promised
Feature activation+2.032
to
Token to
Feature activation+2.270
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
end
Tokenend
Feature activation+0.000
crime
Token crime
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
campaign
Token campaign
Feature activation+3.171
,
Token,
Feature activation+0.389
the
Token the
Feature activation+0.383
Republican
Token Republican
Feature activation+1.935
presidential
Token presidential
Feature activation+1.052
candidate
Token candidate
Feature activation+2.323
was
Token was
Feature activation+1.952
dubbed
Token dubbed
Feature activation+0.609
a
Token a
Feature activation+0.398
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
and
Token and
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.075
backed
Token backed
Feature activation+0.080
by
Token by
Feature activation+0.166
his
Token his
Feature activation+2.513
former
Token former
Feature activation+0.415
political
Token political
Feature activation+0.113
guru
Token guru
Feature activation+0.126
,
Token,
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.228
City
Token City
Feature activation+0.076
that
Token that
Feature activation+0.085
he
Token he
Feature activation+2.535
is
Token is
Feature activation+2.301
seeking
Token seeking
Feature activation+1.068
the
Token the
Feature activation+0.408
Republican
Token Republican
Feature activation+0.535
presidential
Token presidential
Feature activation+1.055
and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
fails
Token fails
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+2.375
is
Token is
Feature activation+1.671
âĢ
Token âĢ
Feature activation+0.444
ľ
Tokenľ
Feature activation+0.000
done
Tokendone
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 1.569 - 2.092
CONTAINS 0.033%

a
Token a
Feature activation+0.000
White
Token White
Feature activation+0.546
House
Token House
Feature activation+0.431
ceremony
Token ceremony
Feature activation+0.000
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+1.995
him
Token him
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
brave
Token brave
Feature activation+0.000
guy
Token guy
Feature activation+0.000
for
Token for
Feature activation+0.967
a
Token a
Feature activation+0.409
nominee
Token nominee
Feature activation+1.276
who
Token who
Feature activation+1.558
has
Token has
Feature activation+1.521
behaved
Token behaved
Feature activation+1.695
in
Token in
Feature activation+0.001
a
Token a
Feature activation+0.257
manner
Token manner
Feature activation+0.000
that
Token that
Feature activation+0.000
reflects
Token reflects
Feature activation+0.115
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ivot
Tokenivot
Feature activation+0.000
Trump
Token Trump
Feature activation+0.120
needs
Token needs
Feature activation+1.666
to
Token to
Feature activation+1.705
be
Token be
Feature activation+1.910
more
Token more
Feature activation+0.230
presidential
Token presidential
Feature activation+1.527
:
Token:
Feature activation+0.107
better
Token better
Feature activation+0.236
gave
Token gave
Feature activation+0.000
her
Token her
Feature activation+0.000
own
Token own
Feature activation+0.071
speech
Token speech
Feature activation+0.000
attacking
Token attacking
Feature activation+0.189
Trump
Token Trump
Feature activation+1.938
on
Token on
Feature activation+1.223
his
Token his
Feature activation+3.535
business
Token business
Feature activation+0.494
record
Token record
Feature activation+0.711
,
Token,
Feature activation+0.308
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+1.076
also
Token also
Feature activation+0.802
discussed
Token discussed
Feature activation+1.672
his
Token his
Feature activation+2.713
new
Token new
Feature activation+1.229
tax
Token tax
Feature activation+0.024
proposal
Token proposal
Feature activation+0.209
,
Token,
Feature activation+0.000

INTERVAL 1.046 - 1.569
CONTAINS 0.056%

to
Token to
Feature activation+2.957
put
Token put
Feature activation+0.953
distance
Token distance
Feature activation+0.000
between
Token between
Feature activation+0.042
himself
Token himself
Feature activation+3.639
and
Token and
Feature activation+1.372
his
Token his
Feature activation+3.814
own
Token own
Feature activation+2.753
son
Token son
Feature activation+0.376
âĢĶ
Token âĢĶ
Feature activation+0.103
especially
Token especially
Feature activation+0.167
and
Token and
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.000
while
Token while
Feature activation+0.000
campaigning
Token campaigning
Feature activation+3.741
for
Token for
Feature activation+1.572
November
Token November
Feature activation+1.120
's
Token's
Feature activation+0.592
election
Token election
Feature activation+1.191
,
Token,
Feature activation+0.499
quickly
Token quickly
Feature activation+0.514
ret
Token ret
Feature activation+0.256
s
Tokens
Feature activation+0.000
highest
Token highest
Feature activation+0.136
priority
Token priority
Feature activation+0.000
in
Token in
Feature activation+0.043
his
Token his
Feature activation+0.451
first
Token first
Feature activation+1.363
100
Token 100
Feature activation+0.000
days
Token days
Feature activation+0.948
in
Token in
Feature activation+0.961
office
Token office
Feature activation+0.629
,
Token,
Feature activation+0.120
in
Token in
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.016
's
Token's
Feature activation+0.955
second
Token second
Feature activation+1.101
term
Token term
Feature activation+0.602
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
.
Token.
Feature activation+0.000
Here
Token Here
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Trump
Token Trump
Feature activation+1.556
senior
Token senior
Feature activation+0.013
advisor
Token advisor
Feature activation+0.131
and
Token and
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.014

INTERVAL 0.523 - 1.046
CONTAINS 0.104%

announced
Token announced
Feature activation+1.626
June
Token June
Feature activation+0.570
16
Token 16
Feature activation+0.385
at
Token at
Feature activation+0.970
his
Token his
Feature activation+3.018
Trump
Token Trump
Feature activation+0.984
Tower
Token Tower
Feature activation+0.246
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.228
City
Token City
Feature activation+0.076
Netanyahu
Token Netanyahu
Feature activation+0.000
.
Token.
Feature activation+0.287
A
Token A
Feature activation+0.456
planned
Token planned
Feature activation+0.655
trip
Token trip
Feature activation+0.586
to
Token to
Feature activation+0.637
Israel
Token Israel
Feature activation+0.000
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.571
the
Token the
Feature activation+0.000
prime
Token prime
Feature activation+0.000
making
Token making
Feature activation+0.000
dispar
Token dispar
Feature activation+0.000
aging
Tokenaging
Feature activation+0.000
remarks
Token remarks
Feature activation+0.102
aimed
Token aimed
Feature activation+0.666
at
Token at
Feature activation+0.771
Argentine
Token Argentine
Feature activation+0.000
counterpart
Token counterpart
Feature activation+0.000
Crist
Token Crist
Feature activation+0.000
ina
Tokenina
Feature activation+0.000
Kir
Token Kir
Feature activation+0.000
sent
Token sent
Feature activation+0.000
a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.735
calling
Token calling
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
believe
Token believe
Feature activation+0.000
âĢĶ
Token âĢĶ
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
president
Token president
Feature activation+0.746
believes
Token believes
Feature activation+0.214
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
former
Token former
Feature activation+0.000

INTERVAL 0.000 - 0.523
CONTAINS 99.748%

've
Token've
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
,
Token,
Feature activation+0.000
arguing
Token arguing
Feature activation+0.000
that
Token that
Feature activation+0.000
bus
Token bus
Feature activation+0.000
k
Tokenk
Feature activation+0.000
yet
Token yet
Feature activation+0.000
I
Token I
Feature activation+0.000
'll
Token'll
Feature activation+0.000
let
Token let
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
"
Token"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Carter
TokenCarter
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
sell
Token sell
Feature activation+0.000
and
Token and
Feature activation+0.000
distribute
Token distribute
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
first
Token first
Feature activation+0.000
victim
Token victim
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
who
Token who
Feature activation+0.000
later
Token later
Feature activation+0.000
publicly
Token publicly
Feature activation+0.000
identified
Token identified
Feature activation+0.000
herself
Token herself
Feature activation+0.000
as
Token as
Feature activation+0.000
actor
Token actor
Feature activation+0.000
,
Token,
Feature activation+0.000
singer
Token singer
Feature activation+0.000
find
Token find
Feature activation+0.000
new
Token new
Feature activation+0.000
framing
Token framing
Feature activation+0.000
to
Token to
Feature activation+0.000
express
Token express
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
Strategic
Token Strategic
Feature activation+0.000
Sor
Token Sor
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