H10.6 top features

Top feature 0 in H10.6: (feature 18159)

TOP ACTIVATIONS
MAX = 10.855

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
swipe
Token swipe
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
with
Token with
Feature activation+0.000
former
Token former
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+8.435
and
Token and
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
activist
Token activist
Feature activation+5.483
Al
Token Al
Feature activation+0.000
Gore
Token Gore
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
-
Token-
Feature activation+1.835
President
TokenPresident
Feature activation+7.530
Joe
Token Joe
Feature activation+4.217
Biden
Token Biden
Feature activation+0.000
has
Token has
Feature activation+0.000
called
Token called
Feature activation+0.000
him
Token him
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
swipe
Token swipe
Feature activation+0.000
at
Token at
Feature activation+0.000
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
TokenK
Feature activation+0.000
former
Token former
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+8.435
and
Token and
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
activist
Token activist
Feature activation+5.483
Al
Token Al
Feature activation+0.000
Gore
Token Gore
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
-
Token-
Feature activation+1.835
President
TokenPresident
Feature activation+7.530
Joe
Token Joe
Feature activation+4.217
Biden
Token Biden
Feature activation+0.000
has
Token has
Feature activation+0.000
called
Token called
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.282
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
younger
Token younger
Feature activation+0.000
son
Token son
Feature activation+0.000
of
Token of
Feature activation+0.000
late
Token late
Feature activation+0.000
Vice
Token Vice
Feature activation+0.111
President
Token President
Feature activation+3.966
Nelson
Token Nelson
Feature activation+0.000
Rockefeller
Token Rockefeller
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
in
Tokenin
Feature activation+0.000
ceremony
Token ceremony
Feature activation+0.000
of
Token of
Feature activation+0.000
First
Token First
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+3.711
Tab
Token Tab
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Deng
Token Deng
Feature activation+0.000
G
Token G
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
three
Token three
Feature activation+0.000
big
Token big
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
selected
Token selected
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+3.643
Mike
Token Mike
Feature activation+2.106
cooking
Token cooking
Feature activation+0.000
pans
Token pans
Feature activation+0.000
were
Token were
Feature activation+0.000
children
Token children
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Vice
TokenVice
Feature activation+0.000
President
Token President
Feature activation+3.309
Cheney
Token Cheney
Feature activation+0.000
invited
Token invited
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
country
Token country
Feature activation+0.000
's
Token's
Feature activation+0.000
ousted
Token ousted
Feature activation+0.000
vice
Token vice
Feature activation+0.000
-
Token-
Feature activation+0.265
president
Tokenpresident
Feature activation+2.874
have
Token have
Feature activation+0.000
def
Token def
Feature activation+0.000
ected
Tokenected
Feature activation+0.000
and
Token and
Feature activation+0.000
say
Token say
Feature activation+0.000
's
Token's
Feature activation+0.000
running
Token running
Feature activation+0.000
mate
Token mate
Feature activation+1.636
that
Token that
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+2.770
Win
Token Win
Feature activation+0.000
ona
Tokenona
Feature activation+0.000
La
Token La
Feature activation+0.000
D
TokenD
Feature activation+0.000
uke
Tokenuke
Feature activation+0.000
é
Tokené
Feature activation+0.000
g
Tokeng
Feature activation+0.000
é
Tokené
Feature activation+0.039
and
Token and
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
successor
Token successor
Feature activation+2.329
,
Token,
Feature activation+0.652
William
Token William
Feature activation+0.000
Howard
Token Howard
Feature activation+0.000
Ta
Token Ta
Feature activation+0.000
ft
Tokenft
Feature activation+0.000

Top DFA by src position
MAX = 11.764

Images
Token Images
Feature activation-0.000
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
GOP
TokenGOP
Feature activation-0.184
Top resid features:
vice
Token vice
Feature activation+11.764
Top resid features:
presidential
Token presidential
Feature activation+0.088
Top resid features:
candidate
Token candidate
Feature activation+0.007
Top resid features:
Paul
Token Paul
Feature activation+0.000
Top resid features:
Ryan
Token Ryan
Feature activation+0.000
Top resid features:
took
Token took
Feature activation+0.000
Top resid features:
Images
Token Images
Feature activation-0.000
Top resid features:
)
Token)
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
GOP
TokenGOP
Feature activation-0.018
Top resid features:
vice
Token vice
Feature activation+9.996
Top resid features:
presidential
Token presidential
Feature activation+0.116
Top resid features:
candidate
Token candidate
Feature activation+0.000
Top resid features:
Paul
Token Paul
Feature activation+0.000
Top resid features:
Ryan
Token Ryan
Feature activation+0.000
Top resid features:
took
Token took
Feature activation+0.000
Top resid features:
Hillary
Token Hillary
Feature activation-0.049
Top resid features:
Clinton
Token Clinton
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation-0.031
Top resid features:
Ļ
TokenĻ
Feature activation-0.010
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
vice
Token vice
Feature activation+9.728
Top resid features:
president
Token president
Feature activation+0.280
Top resid features:
pick
Token pick
Feature activation+0.035
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
Virginia
Token Virginia
Feature activation-0.721
Top resid features:
Senator
Token Senator
Feature activation-0.013
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
Monday
Token Monday
Feature activation+0.001
Top resid features:
meeting
Token meeting
Feature activation-0.006
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
former
Token former
Feature activation+0.041
Top resid features:
Vice
Token Vice
Feature activation+8.918
Top resid features:
President
Token President
Feature activation+0.247
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
environmental
Token environmental
Feature activation+0.000
Top resid features:
activist
Token activist
Feature activation+0.000
Top resid features:
Al
Token Al
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
United
Token United
Feature activation-0.021
Top resid features:
States
Token States
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
where
Token where
Feature activation-0.012
Top resid features:
Vice
Token Vice
Feature activation+7.092
Top resid features:
-
Token-
Feature activation+0.631
Top resid features:
President
TokenPresident
Feature activation+0.525
Top resid features:
Joe
Token Joe
Feature activation+0.000
Top resid features:
Biden
Token Biden
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
Hillary
Token Hillary
Feature activation-0.129
Top resid features:
Clinton
Token Clinton
Feature activation+0.046
Top resid features:
âĢ
TokenâĢ
Feature activation-0.042
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
vice
Token vice
Feature activation+7.538
Top resid features:
president
Token president
Feature activation+0.802
Top resid features:
pick
Token pick
Feature activation+0.127
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
Virginia
Token Virginia
Feature activation+0.000
Top resid features:
Senator
Token Senator
Feature activation+0.000
Top resid features:
Hillary
Token Hillary
Feature activation-0.047
Top resid features:
Clinton
Token Clinton
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.216
Top resid features:
Ļ
TokenĻ
Feature activation-0.013
Top resid features:
s
Tokens
Feature activation+0.019
Top resid features:
vice
Token vice
Feature activation+7.687
Top resid features:
president
Token president
Feature activation+0.397
Top resid features:
pick
Token pick
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Virginia
Token Virginia
Feature activation+0.000
Top resid features:
Senator
Token Senator
Feature activation+0.000
Top resid features:
Images
Token Images
Feature activation-0.000
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:
GOP
TokenGOP
Feature activation-0.031
Top resid features:
vice
Token vice
Feature activation+6.910
Top resid features:
presidential
Token presidential
Feature activation+0.217
Top resid features:
candidate
Token candidate
Feature activation+0.037
Top resid features:
Paul
Token Paul
Feature activation-0.020
Top resid features:
Ryan
Token Ryan
Feature activation+0.000
Top resid features:
took
Token took
Feature activation+0.000
Top resid features:
Hillary
Token Hillary
Feature activation-0.032
Top resid features:
Clinton
Token Clinton
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:
vice
Token vice
Feature activation+5.747
Top resid features:
president
Token president
Feature activation+0.897
Top resid features:
pick
Token pick
Feature activation+0.158
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
Virginia
Token Virginia
Feature activation-0.218
Top resid features:
Senator
Token Senator
Feature activation-0.071
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
Monday
Token Monday
Feature activation-0.000
Top resid features:
meeting
Token meeting
Feature activation-0.024
Top resid features:
with
Token with
Feature activation-0.006
Top resid features:
former
Token former
Feature activation+0.107
Top resid features:
Vice
Token Vice
Feature activation+5.851
Top resid features:
President
Token President
Feature activation+0.283
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
environmental
Token environmental
Feature activation+0.101
Top resid features:
activist
Token activist
Feature activation+0.014
Top resid features:
Al
Token Al
Feature activation+0.000
Top resid features:
Images
Token Images
Feature activation-0.000
Top resid features:
)
Token)
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
GOP
TokenGOP
Feature activation+0.013
Top resid features:
vice
Token vice
Feature activation+5.194
Top resid features:
presidential
Token presidential
Feature activation+0.000
Top resid features:
candidate
Token candidate
Feature activation+0.000
Top resid features:
Paul
Token Paul
Feature activation+0.000
Top resid features:
Ryan
Token Ryan
Feature activation+0.000
Top resid features:
took
Token took
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
United
Token United
Feature activation-0.025
Top resid features:
States
Token States
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
where
Token where
Feature activation-0.002
Top resid features:
Vice
Token Vice
Feature activation+2.655
Top resid features:
-
Token-
Feature activation+1.112
Top resid features:
President
TokenPresident
Feature activation+1.079
Top resid features:
Joe
Token Joe
Feature activation+0.049
Top resid features:
Biden
Token Biden
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
Hillary
Token Hillary
Feature activation-0.095
Top resid features:
Clinton
Token Clinton
Feature activation+0.031
Top resid features:
âĢ
TokenâĢ
Feature activation-0.131
Top resid features:
Ļ
TokenĻ
Feature activation-0.032
Top resid features:
s
Tokens
Feature activation+0.022
Top resid features:
vice
Token vice
Feature activation+4.846
Top resid features:
president
Token president
Feature activation+0.390
Top resid features:
pick
Token pick
Feature activation+0.092
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Virginia
Token Virginia
Feature activation+0.000
Top resid features:
Senator
Token Senator
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
younger
Token younger
Feature activation-0.001
Top resid features:
son
Token son
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
late
Token late
Feature activation+0.011
Top resid features:
Vice
Token Vice
Feature activation+4.929
Top resid features:
President
Token President
Feature activation+0.236
Top resid features:
Nelson
Token Nelson
Feature activation+0.000
Top resid features:
Rockefeller
Token Rockefeller
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
in
Tokenin
Feature activation+0.004
Top resid features:
ceremony
Token ceremony
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
First
Token First
Feature activation+0.198
Top resid features:
Vice
Token Vice
Feature activation+4.068
Top resid features:
President
Token President
Feature activation+0.175
Top resid features:
Tab
Token Tab
Feature activation+0.000
Top resid features:
an
Tokenan
Feature activation+0.000
Top resid features:
Deng
Token Deng
Feature activation+0.000
Top resid features:
G
Token G
Feature activation+0.000
Top resid features:
from
Token from
Feature activation-0.010
Top resid features:
three
Token three
Feature activation-0.002
Top resid features:
big
Token big
Feature activation-0.003
Top resid features:
Trump
Token Trump
Feature activation-0.103
Top resid features:
selected
Token selected
Feature activation+0.027
Top resid features:
Vice
Token Vice
Feature activation+4.494
Top resid features:
President
Token President
Feature activation+0.376
Top resid features:
Mike
Token Mike
Feature activation+0.000
Top resid features:
cooking
Token cooking
Feature activation+0.000
Top resid features:
pans
Token pans
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
say
Token say
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.008
Top resid features:
ľ
Tokenľ
Feature activation-0.004
Top resid features:
Vice
TokenVice
Feature activation+3.477
Top resid features:
President
Token President
Feature activation+0.845
Top resid features:
Cheney
Token Cheney
Feature activation+0.000
Top resid features:
invited
Token invited
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
country
Token country
Feature activation+0.146
Top resid features:
's
Token's
Feature activation-0.024
Top resid features:
ousted
Token ousted
Feature activation+0.014
Top resid features:
vice
Token vice
Feature activation+3.730
Top resid features:
-
Token-
Feature activation+0.072
Top resid features:
president
Tokenpresident
Feature activation+0.048
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
def
Token def
Feature activation+0.000
Top resid features:
ected
Tokenected
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
N
Token N
Feature activation-0.008
Top resid features:
ader
Tokenader
Feature activation-0.001
Top resid features:
's
Token's
Feature activation+0.018
Top resid features:
running
Token running
Feature activation+0.047
Top resid features:
mate
Token mate
Feature activation+3.466
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
year
Token year
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Win
Token Win
Feature activation+0.000
Top resid features:
ona
Tokenona
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Roosevelt
Token Roosevelt
Feature activation-0.189
Top resid features:
had
Token had
Feature activation-0.005
Top resid features:
been
Token been
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Vice
Token Vice
Feature activation+2.755
Top resid features:
President
Token President
Feature activation+0.321
Top resid features:
of
Token of
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
United
Token United
Feature activation-0.003
Top resid features:
States
Token States
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.03

Head 3: 0.04

Head 4: 0.06

Head 5: 0.03

Head 6: 0.49

Head 7: 0.08

Head 8: 0.03

Head 9: 0.05

Head 10: 0.04

Head 11: 0.03

Positive logits

Vice5.38

vice4.82

Vice4.68

VP4.62

vice4.36

Biden4.22

Pence3.72

Cheney3.68

gments3.22

hatch2.97

exec2.93

VP2.91

indisc2.90

Cabin2.81

conduit2.81

running2.74

Gore2.68

Running2.67

cum2.66

running2.66

Negative logits

REG-3.02

landlord-2.94

rent-2.82

taxation-2.78

landlords-2.71

rental-2.68

Meter-2.68

ajo-2.64

Ort-2.63

taxing-2.60

Wass-2.56

Meta-2.56

sear-2.55

Rent-2.54

Zup-2.54

REG-2.53

Mech-2.53

Residents-2.53

Hunt-2.52

rents-2.48

INTERVAL 9.770 - 10.855
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
swipe
Token swipe
Feature activation+0.000

INTERVAL 8.684 - 9.770
CONTAINS 0.000%

)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 7.599 - 8.684
CONTAINS 0.000%

Monday
Token Monday
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
with
Token with
Feature activation+0.000
former
Token former
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+8.435
and
Token and
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
activist
Token activist
Feature activation+5.483
Al
Token Al
Feature activation+0.000
Gore
Token Gore
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 6.513 - 7.599
CONTAINS 0.000%

Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
.
Token.
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
-
Token-
Feature activation+1.835
President
TokenPresident
Feature activation+7.530
Joe
Token Joe
Feature activation+4.217
Biden
Token Biden
Feature activation+0.000
has
Token has
Feature activation+0.000
called
Token called
Feature activation+0.000
him
Token him
Feature activation+0.000

INTERVAL 5.428 - 6.513
CONTAINS 0.000%

former
Token former
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+8.435
and
Token and
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
activist
Token activist
Feature activation+5.483
Al
Token Al
Feature activation+0.000
Gore
Token Gore
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
TokenK
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
swipe
Token swipe
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 4.342 - 5.428
CONTAINS 0.000%

Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
vice
Token vice
Feature activation+4.611
presidential
Token presidential
Feature activation+9.477
candidate
Token candidate
Feature activation+10.855
Paul
Token Paul
Feature activation+6.432
Ryan
Token Ryan
Feature activation+0.000
took
Token took
Feature activation+0.000

INTERVAL 3.257 - 4.342
CONTAINS 0.001%

younger
Token younger
Feature activation+0.000
son
Token son
Feature activation+0.000
of
Token of
Feature activation+0.000
late
Token late
Feature activation+0.000
Vice
Token Vice
Feature activation+0.111
President
Token President
Feature activation+3.966
Nelson
Token Nelson
Feature activation+0.000
Rockefeller
Token Rockefeller
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.726
president
Token president
Feature activation+7.009
pick
Token pick
Feature activation+4.200
,
Token,
Feature activation+7.297
Virginia
Token Virginia
Feature activation+0.256
Senator
Token Senator
Feature activation+8.473
Tim
Token Tim
Feature activation+5.770
Kaine
Token Kaine
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
-
Token-
Feature activation+1.835
President
TokenPresident
Feature activation+7.530
Joe
Token Joe
Feature activation+4.217
Biden
Token Biden
Feature activation+0.000
has
Token has
Feature activation+0.000
called
Token called
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.282
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Vice
TokenVice
Feature activation+0.000
President
Token President
Feature activation+3.309
Cheney
Token Cheney
Feature activation+0.000
invited
Token invited
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
in
Tokenin
Feature activation+0.000
ceremony
Token ceremony
Feature activation+0.000
of
Token of
Feature activation+0.000
First
Token First
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+3.711
Tab
Token Tab
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Deng
Token Deng
Feature activation+0.000
G
Token G
Feature activation+0.000
ai
Tokenai
Feature activation+0.000

INTERVAL 2.171 - 3.257
CONTAINS 0.001%

country
Token country
Feature activation+0.000
's
Token's
Feature activation+0.000
ousted
Token ousted
Feature activation+0.000
vice
Token vice
Feature activation+0.000
-
Token-
Feature activation+0.265
president
Tokenpresident
Feature activation+2.874
have
Token have
Feature activation+0.000
def
Token def
Feature activation+0.000
ected
Tokenected
Feature activation+0.000
and
Token and
Feature activation+0.000
say
Token say
Feature activation+0.000
as
Tokenas
Feature activation+0.000
would
Token would
Feature activation+0.000
his
Token his
Feature activation+0.000
running
Token running
Feature activation+0.000
mate
Token mate
Feature activation+2.052
,
Token,
Feature activation+2.188
former
Token former
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
strategist
Token strategist
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
Former
TokenFormer
Feature activation+0.000
President
Token President
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
,
Token,
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
President
Token President
Feature activation+2.213
Biden
Token Biden
Feature activation+0.000
and
Token and
Feature activation+0.000
Kerry
Token Kerry
Feature activation+0.000
sought
Token sought
Feature activation+0.000
to
Token to
Feature activation+0.000
week
Token week
Feature activation+0.000
in
Token in
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000
,
Token,
Feature activation+0.000
presumptive
Token presumptive
Feature activation+0.000
nominee
Token nominee
Feature activation+2.225
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
will
Token will
Feature activation+0.000
showcase
Token showcase
Feature activation+0.000
an
Token an
Feature activation+0.000
's
Token's
Feature activation+0.000
running
Token running
Feature activation+0.000
mate
Token mate
Feature activation+1.636
that
Token that
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+2.770
Win
Token Win
Feature activation+0.000
ona
Tokenona
Feature activation+0.000
La
Token La
Feature activation+0.000
D
TokenD
Feature activation+0.000
uke
Tokenuke
Feature activation+0.000

INTERVAL 1.086 - 2.171
CONTAINS 0.002%

ual
Tokenual
Feature activation+0.000
reports
Token reports
Feature activation+0.000
show
Token show
Feature activation+0.000
presidents
Token presidents
Feature activation+0.000
and
Token and
Feature activation+0.000
vice
Token vice
Feature activation+1.106
-
Token-
Feature activation+1.671
pres
Tokenpres
Feature activation+0.301
idents
Tokenidents
Feature activation+0.000
at
Token at
Feature activation+0.000
several
Token several
Feature activation+0.000
to
Token to
Feature activation+0.000
generate
Token generate
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+1.093
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
nuclear
Token nuclear
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
as
Tokenas
Feature activation+0.000
would
Token would
Feature activation+0.000
his
Token his
Feature activation+0.000
running
Token running
Feature activation+0.000
mate
Token mate
Feature activation+2.052
,
Token,
Feature activation+2.188
former
Token former
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
strategist
Token strategist
Feature activation+0.000
(
Token (
Feature activation+0.000
his
Token his
Feature activation+0.000
absence
Token absence
Feature activation+0.000
,
Token,
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
-
Token-
Feature activation+0.305
President
TokenPresident
Feature activation+1.303
Good
Token Good
Feature activation+0.000
luck
Tokenluck
Feature activation+0.000
Jonathan
Token Jonathan
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
not
Token not
Feature activation+0.000
unlike
Token unlike
Feature activation+0.000
an
Token an
Feature activation+0.000
American
Token American
Feature activation+0.000
vice
Token vice
Feature activation+0.665
-
Token-
Feature activation+1.453
president
Tokenpresident
Feature activation+0.751
:
Token:
Feature activation+0.000
be
Token be
Feature activation+0.000
available
Token available
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.000 - 1.086
CONTAINS 99.995%

refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
interviewed
Token interviewed
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
prev
Token prev
Feature activation+0.000
ails
Tokenails
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Turn
TokenTurn
Feature activation+0.000
ing
Tokening
Feature activation+0.000
back
Token back
Feature activation+0.000
the
Token the
Feature activation+0.000
clock
Token clock
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
a
Token a
Feature activation+0.000
difference
Token difference
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
.
Token.
Feature activation+0.000
Still
Token Still
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
prospect
Token prospect
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.000
shows
Token shows
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
-
Token-
Feature activation+0.000
than
Tokenthan
Feature activation+0.000
-
Token-
Feature activation+0.000
expected
Tokenexpected
Feature activation+0.000
said
Token said
Feature activation+0.000
about
Token about
Feature activation+0.000
cannabis
Token cannabis
Feature activation+0.000
law
Token law
Feature activation+0.000
reform
Token reform
Feature activation+0.000
,
Token,
Feature activation+0.000
check
Token check
Feature activation+0.000
out
Token out
Feature activation+0.000
Marijuana
Token Marijuana
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H10.6: (feature 14029)

TOP ACTIVATIONS
MAX = 7.246

device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
caption
Token caption
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.273
Minister
Token Minister
Feature activation+7.246
David
Token David
Feature activation+1.906
Cameron
Token Cameron
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
NET
TokenNET
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
British
TokenBritish
Feature activation+0.000
Prime
Token Prime
Feature activation+0.556
Minister
Token Minister
Feature activation+6.896
David
Token David
Feature activation+2.173
Cameron
Token Cameron
Feature activation+0.000
has
Token has
Feature activation+0.495
joined
Token joined
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
summit
Token summit
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.814
Minister
Token Minister
Feature activation+6.339
David
Token David
Feature activation+3.378
Cameron
Token Cameron
Feature activation+0.000
will
Token will
Feature activation+0.000
meet
Token meet
Feature activation+0.000
EU
Token EU
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+5.146
,
Token,
Feature activation+6.087
Narendra
Token Narendra
Feature activation+2.319
Modi
Token Modi
Feature activation+0.000
,
Token,
Feature activation+0.000
condemned
Token condemned
Feature activation+0.000
the
Token the
Feature activation+0.000
shakes
Token shakes
Feature activation+0.000
hand
Token hand
Feature activation+0.000
with
Token with
Feature activation+1.253
British
Token British
Feature activation+2.545
Prime
Token Prime
Feature activation+1.856
Minister
Token Minister
Feature activation+5.386
Theresa
Token Theresa
Feature activation+3.346
May
Token May
Feature activation+0.105
before
Token before
Feature activation+1.346
their
Token their
Feature activation+2.604
meeting
Token meeting
Feature activation+0.001
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
British
TokenBritish
Feature activation+0.162
Prime
Token Prime
Feature activation+0.239
Minister
Token Minister
Feature activation+5.294
Theresa
Token Theresa
Feature activation+1.166
May
Token May
Feature activation+0.379
attends
Token attends
Feature activation+0.495
the
Token the
Feature activation+0.434
European
Token European
Feature activation+0.000
China
Token China
Feature activation+0.000
has
Token has
Feature activation+0.000
invited
Token invited
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.082
Minister
Token Minister
Feature activation+5.164
Theresa
Token Theresa
Feature activation+0.706
May
Token May
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.000
a
Token a
Feature activation+0.191
India
TokenIndia
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+5.146
,
Token,
Feature activation+6.087
Narendra
Token Narendra
Feature activation+2.319
Modi
Token Modi
Feature activation+0.000
,
Token,
Feature activation+0.000
condemned
Token condemned
Feature activation+0.000
sign
Token sign
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.160
Minister
Token Minister
Feature activation+4.745
David
Token David
Feature activation+1.672
Cameron
Token Cameron
Feature activation+0.000
said
Token said
Feature activation+0.000
his
Token his
Feature activation+1.336
government
Token government
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
then
Token then
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+4.539
David
Token David
Feature activation+2.559
Cameron
Token Cameron
Feature activation+0.000
who
Token who
Feature activation+0.000
a
Token a
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
Canada
TokenCanada
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.933
,
Token,
Feature activation+4.517
Sir
Token Sir
Feature activation+0.418
John
Token John
Feature activation+0.836
A
Token A
Feature activation+0.115
.
Token.
Feature activation+0.106
Mac
Token Mac
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.042
Ex
Token Ex
Feature activation+0.000
che
Tokenche
Feature activation+0.000
quer
Tokenquer
Feature activation+2.955
,
Token,
Feature activation+4.338
Philip
Token Philip
Feature activation+1.918
Hammond
Token Hammond
Feature activation+0.000
PA
Token PA
Feature activation+0.000
8
Token 8
Feature activation+0.000
/
Token/
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000
calls
Token calls
Feature activation+0.000
from
Token from
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+4.304
Justin
Token Justin
Feature activation+0.345
Trudeau
Token Trudeau
Feature activation+0.000
and
Token and
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.027
President
Token President
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+3.588
Benjamin
Token Benjamin
Feature activation+0.522
Netanyahu
Token Netanyahu
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
Parliament
Token Parliament
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+3.560
Tony
Token Tony
Feature activation+2.944
Abbott
Token Abbott
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
criticised
Token criticised
Feature activation+0.000
will
Token will
Feature activation+0.000
face
Token face
Feature activation+0.000
a
Token a
Feature activation+0.000
cliff
Token cliff
Feature activation+0.000
edge
Token edge
Feature activation+0.000
,"
Token,"
Feature activation+3.489
she
Token she
Feature activation+0.316
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.215
Obama
TokenObama
Feature activation+0.000
also
Token also
Feature activation+0.000
joined
Token joined
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+3.478
David
Token David
Feature activation+1.411
Cameron
Token Cameron
Feature activation+0.000
,
Token,
Feature activation+0.000
German
Token German
Feature activation+0.021
Chancellor
Token Chancellor
Feature activation+2.335
the
Token the
Feature activation+0.015
footsteps
Token footsteps
Feature activation+0.000
of
Token of
Feature activation+0.000
dozens
Token dozens
Feature activation+0.000
of
Token of
Feature activation+1.249
other
Token other
Feature activation+3.409
global
Token global
Feature activation+2.534
leaders
Token leaders
Feature activation+0.000
.
Token.
Feature activation+1.053
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.204
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.814
Minister
Token Minister
Feature activation+6.339
David
Token David
Feature activation+3.378
Cameron
Token Cameron
Feature activation+0.000
will
Token will
Feature activation+0.000
meet
Token meet
Feature activation+0.000
EU
Token EU
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
hand
Token hand
Feature activation+0.000
with
Token with
Feature activation+1.253
British
Token British
Feature activation+2.545
Prime
Token Prime
Feature activation+1.856
Minister
Token Minister
Feature activation+5.386
Theresa
Token Theresa
Feature activation+3.346
May
Token May
Feature activation+0.105
before
Token before
Feature activation+1.346
their
Token their
Feature activation+2.604
meeting
Token meeting
Feature activation+0.001
at
Token at
Feature activation+2.523

Top DFA by src position
MAX = 4.482

your
Token your
Feature activation-0.001
Top resid features:
device
Token device
Feature activation-0.002
Top resid features:
Media
Token Media
Feature activation-0.001
Top resid features:
caption
Token caption
Feature activation-0.009
Top resid features:
UK
Token UK
Feature activation+0.181
Top resid features:
Prime
Token Prime
Feature activation+4.482
Top resid features:
Minister
Token Minister
Feature activation+3.038
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
C
TokenC
Feature activation-0.007
Top resid features:
NET
TokenNET
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.049
Top resid features:
British
TokenBritish
Feature activation+0.064
Top resid features:
Prime
Token Prime
Feature activation+4.419
Top resid features:
Minister
Token Minister
Feature activation+2.917
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
joined
Token joined
Feature activation+0.000
Top resid features:
summit
Token summit
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
where
Token where
Feature activation-0.014
Top resid features:
British
Token British
Feature activation+1.377
Top resid features:
Prime
Token Prime
Feature activation+2.085
Top resid features:
Minister
Token Minister
Feature activation+3.299
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
meet
Token meet
Feature activation+0.000
Top resid features:
EU
Token EU
Feature activation+0.000
Top resid features:
India
TokenIndia
Feature activation+0.073
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
s
Tokens
Feature activation-0.017
Top resid features:
prime
Token prime
Feature activation+1.912
Top resid features:
minister
Token minister
Feature activation+4.281
Top resid features:
,
Token,
Feature activation+0.110
Top resid features:
Narendra
Token Narendra
Feature activation+0.000
Top resid features:
Modi
Token Modi
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
condemned
Token condemned
Feature activation+0.000
Top resid features:
shakes
Token shakes
Feature activation+0.001
Top resid features:
hand
Token hand
Feature activation-0.002
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
British
Token British
Feature activation+0.069
Top resid features:
Prime
Token Prime
Feature activation+0.821
Top resid features:
Minister
Token Minister
Feature activation+2.268
Top resid features:
Theresa
Token Theresa
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
meeting
Token meeting
Feature activation+0.000
Top resid features:
links
Token links
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
British
TokenBritish
Feature activation+0.242
Top resid features:
Prime
Token Prime
Feature activation+3.475
Top resid features:
Minister
Token Minister
Feature activation+1.900
Top resid features:
Theresa
Token Theresa
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
attends
Token attends
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
China
Token China
Feature activation+0.010
Top resid features:
has
Token has
Feature activation+0.004
Top resid features:
invited
Token invited
Feature activation-0.014
Top resid features:
British
Token British
Feature activation+0.221
Top resid features:
Prime
Token Prime
Feature activation+2.592
Top resid features:
Minister
Token Minister
Feature activation+2.685
Top resid features:
Theresa
Token Theresa
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
attend
Token attend
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
India
TokenIndia
Feature activation+0.053
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.118
Top resid features:
s
Tokens
Feature activation-0.022
Top resid features:
prime
Token prime
Feature activation+2.196
Top resid features:
minister
Token minister
Feature activation+3.130
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Narendra
Token Narendra
Feature activation+0.000
Top resid features:
Modi
Token Modi
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
condemned
Token condemned
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
sign
Token sign
Feature activation-0.000
Top resid features:
up
Token up
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
UK
Token UK
Feature activation+0.202
Top resid features:
Prime
Token Prime
Feature activation+2.716
Top resid features:
Minister
Token Minister
Feature activation+2.188
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
award
Token award
Feature activation-0.022
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
then
Token then
Feature activation-0.006
Top resid features:
UK
Token UK
Feature activation+0.024
Top resid features:
Prime
Token Prime
Feature activation+3.652
Top resid features:
Minister
Token Minister
Feature activation+1.323
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Canada
TokenCanada
Feature activation-0.045
Top resid features:
's
Token's
Feature activation-0.013
Top resid features:
first
Token first
Feature activation-0.013
Top resid features:
prime
Token prime
Feature activation+2.909
Top resid features:
minister
Token minister
Feature activation+1.936
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Sir
Token Sir
Feature activation+0.000
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
/
Token/
Feature activation-0.001
Top resid features:
8
Token8
Feature activation-0.002
Top resid features:
Britain
Token Britain
Feature activation-0.001
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
Prime
Token Prime
Feature activation+1.476
Top resid features:
Minister
Token Minister
Feature activation+2.668
Top resid features:
Theresa
Token Theresa
Feature activation+0.381
Top resid features:
May
Token May
Feature activation-0.015
Top resid features:
Getty
Token Getty
Feature activation+0.001
Top resid features:
Images
Token Images
Feature activation-0.000
Top resid features:
7
Token 7
Feature activation-0.003
Top resid features:
received
Token received
Feature activation-0.004
Top resid features:
friendly
Token friendly
Feature activation+0.014
Top resid features:
calls
Token calls
Feature activation-0.004
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
Canadian
Token Canadian
Feature activation+0.168
Top resid features:
Prime
Token Prime
Feature activation+2.824
Top resid features:
Minister
Token Minister
Feature activation+2.169
Top resid features:
Justin
Token Justin
Feature activation+0.000
Top resid features:
Trudeau
Token Trudeau
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Mexican
Token Mexican
Feature activation+0.000
Top resid features:
allow
Token allow
Feature activation-0.003
Top resid features:
terrorists
Token terrorists
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Prime
TokenPrime
Feature activation+2.568
Top resid features:
Minister
Token Minister
Feature activation+0.895
Top resid features:
Benjamin
Token Benjamin
Feature activation+0.000
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
Parliament
Token Parliament
Feature activation-0.027
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Prime
TokenPrime
Feature activation+2.740
Top resid features:
Minister
Token Minister
Feature activation+1.397
Top resid features:
Tony
Token Tony
Feature activation+0.000
Top resid features:
Abbott
Token Abbott
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
general
Token general
Feature activation+0.001
Top resid features:
election
Token election
Feature activation+0.079
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
prime
Token prime
Feature activation+0.719
Top resid features:
minister
Token minister
Feature activation+3.145
Top resid features:
said
Token said
Feature activation+0.005
Top resid features:
she
Token she
Feature activation+0.001
Top resid features:
did
Token did
Feature activation-0.001
Top resid features:
not
Token not
Feature activation-0.002
Top resid features:
want
Token want
Feature activation-0.002
Top resid features:
Obama
TokenObama
Feature activation+0.030
Top resid features:
also
Token also
Feature activation-0.013
Top resid features:
joined
Token joined
Feature activation-0.013
Top resid features:
UK
Token UK
Feature activation+0.237
Top resid features:
Prime
Token Prime
Feature activation+1.796
Top resid features:
Minister
Token Minister
Feature activation+1.802
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
German
Token German
Feature activation+0.000
Top resid features:
Chancellor
Token Chancellor
Feature activation+0.000
Top resid features:
NET
TokenNET
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
British
TokenBritish
Feature activation+0.138
Top resid features:
Prime
Token Prime
Feature activation+1.189
Top resid features:
Minister
Token Minister
Feature activation+1.960
Top resid features:
David
Token David
Feature activation+0.023
Top resid features:
Cameron
Token Cameron
Feature activation+0.633
Top resid features:
has
Token has
Feature activation+0.014
Top resid features:
joined
Token joined
Feature activation+0.008
Top resid features:
Twitter
Token Twitter
Feature activation-0.083
Top resid features:
summit
Token summit
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
where
Token where
Feature activation-0.004
Top resid features:
British
Token British
Feature activation+0.482
Top resid features:
Prime
Token Prime
Feature activation+0.473
Top resid features:
Minister
Token Minister
Feature activation+2.686
Top resid features:
David
Token David
Feature activation+0.084
Top resid features:
Cameron
Token Cameron
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
meet
Token meet
Feature activation+0.000
Top resid features:
EU
Token EU
Feature activation+0.000
Top resid features:
shakes
Token shakes
Feature activation+0.000
Top resid features:
hand
Token hand
Feature activation-0.002
Top resid features:
with
Token with
Feature activation-0.000
Top resid features:
British
Token British
Feature activation+0.053
Top resid features:
Prime
Token Prime
Feature activation+0.333
Top resid features:
Minister
Token Minister
Feature activation+1.487
Top resid features:
Theresa
Token Theresa
Feature activation+0.146
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
meeting
Token meeting
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.03

Head 3: 0.06

Head 4: 0.06

Head 5: 0.03

Head 6: 0.45

Head 7: 0.10

Head 8: 0.02

Head 9: 0.06

Head 10: 0.04

Head 11: 0.04

Positive logits

Prime6.56

Prime6.01

prime5.15

ministers4.70

PM4.68

prime4.57

minister4.52

Ministers4.44

Minister4.39

Cabinet4.21

cabinet4.17

Prem4.10

prem4.08

udeau4.04

Parliament3.97

ministerial3.96

premier3.96

Liberals3.87

Downing3.86

Theresa3.83

Negative logits

UA-3.46

UCS-3.26

dues-2.93

licens-2.91

NCAA-2.87

Boise-2.83

checks-2.76

Willis-2.73

suit-2.72

olulu-2.70

Weiss-2.67

Fargo-2.65

aukee-2.65

SIGN-2.64

UCLA-2.61

UNC-2.60

Sullivan-2.60

incorpor-2.57

USC-2.57

Myr-2.56

INTERVAL 6.521 - 7.246
CONTAINS 0.000%

device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
caption
Token caption
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.273
Minister
Token Minister
Feature activation+7.246
David
Token David
Feature activation+1.906
Cameron
Token Cameron
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
NET
TokenNET
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
British
TokenBritish
Feature activation+0.000
Prime
Token Prime
Feature activation+0.556
Minister
Token Minister
Feature activation+6.896
David
Token David
Feature activation+2.173
Cameron
Token Cameron
Feature activation+0.000
has
Token has
Feature activation+0.495
joined
Token joined
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000

INTERVAL 5.797 - 6.521
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+5.146
,
Token,
Feature activation+6.087
Narendra
Token Narendra
Feature activation+2.319
Modi
Token Modi
Feature activation+0.000
,
Token,
Feature activation+0.000
condemned
Token condemned
Feature activation+0.000
the
Token the
Feature activation+0.000
summit
Token summit
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.814
Minister
Token Minister
Feature activation+6.339
David
Token David
Feature activation+3.378
Cameron
Token Cameron
Feature activation+0.000
will
Token will
Feature activation+0.000
meet
Token meet
Feature activation+0.000
EU
Token EU
Feature activation+0.000

INTERVAL 5.072 - 5.797
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
British
TokenBritish
Feature activation+0.162
Prime
Token Prime
Feature activation+0.239
Minister
Token Minister
Feature activation+5.294
Theresa
Token Theresa
Feature activation+1.166
May
Token May
Feature activation+0.379
attends
Token attends
Feature activation+0.495
the
Token the
Feature activation+0.434
European
Token European
Feature activation+0.000
China
Token China
Feature activation+0.000
has
Token has
Feature activation+0.000
invited
Token invited
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.082
Minister
Token Minister
Feature activation+5.164
Theresa
Token Theresa
Feature activation+0.706
May
Token May
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.000
a
Token a
Feature activation+0.191
shakes
Token shakes
Feature activation+0.000
hand
Token hand
Feature activation+0.000
with
Token with
Feature activation+1.253
British
Token British
Feature activation+2.545
Prime
Token Prime
Feature activation+1.856
Minister
Token Minister
Feature activation+5.386
Theresa
Token Theresa
Feature activation+3.346
May
Token May
Feature activation+0.105
before
Token before
Feature activation+1.346
their
Token their
Feature activation+2.604
meeting
Token meeting
Feature activation+0.001
India
TokenIndia
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+5.146
,
Token,
Feature activation+6.087
Narendra
Token Narendra
Feature activation+2.319
Modi
Token Modi
Feature activation+0.000
,
Token,
Feature activation+0.000
condemned
Token condemned
Feature activation+0.000

INTERVAL 4.348 - 5.072
CONTAINS 0.000%

sign
Token sign
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.160
Minister
Token Minister
Feature activation+4.745
David
Token David
Feature activation+1.672
Cameron
Token Cameron
Feature activation+0.000
said
Token said
Feature activation+0.000
his
Token his
Feature activation+1.336
government
Token government
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
then
Token then
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+4.539
David
Token David
Feature activation+2.559
Cameron
Token Cameron
Feature activation+0.000
who
Token who
Feature activation+0.000
a
Token a
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
Canada
TokenCanada
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.933
,
Token,
Feature activation+4.517
Sir
Token Sir
Feature activation+0.418
John
Token John
Feature activation+0.836
A
Token A
Feature activation+0.115
.
Token.
Feature activation+0.106
Mac
Token Mac
Feature activation+0.000

INTERVAL 3.623 - 4.348
CONTAINS 0.000%

friendly
Token friendly
Feature activation+0.000
calls
Token calls
Feature activation+0.000
from
Token from
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+4.304
Justin
Token Justin
Feature activation+0.345
Trudeau
Token Trudeau
Feature activation+0.000
and
Token and
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.027
President
Token President
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.042
Ex
Token Ex
Feature activation+0.000
che
Tokenche
Feature activation+0.000
quer
Tokenquer
Feature activation+2.955
,
Token,
Feature activation+4.338
Philip
Token Philip
Feature activation+1.918
Hammond
Token Hammond
Feature activation+0.000
PA
Token PA
Feature activation+0.000
8
Token 8
Feature activation+0.000
/
Token/
Feature activation+0.000

INTERVAL 2.898 - 3.623
CONTAINS 0.002%

recent
Token recent
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
about
Token about
Feature activation+0.240
his
Token his
Feature activation+0.309
health
Token health
Feature activation+0.000
,
Token,
Feature activation+3.088
Mr
Token Mr
Feature activation+2.756
Brown
Token Brown
Feature activation+0.000
emphatically
Token emphatically
Feature activation+0.000
denied
Token denied
Feature activation+0.000
rumours
Token rumours
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+0.925
Israeli
Token Israeli
Feature activation+0.511
PM
Token PM
Feature activation+2.920
Benjamin
Token Benjamin
Feature activation+0.127
Netanyahu
Token Netanyahu
Feature activation+0.019
visits
Token visits
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
the
Token the
Feature activation+0.015
footsteps
Token footsteps
Feature activation+0.000
of
Token of
Feature activation+0.000
dozens
Token dozens
Feature activation+0.000
of
Token of
Feature activation+1.249
other
Token other
Feature activation+3.409
global
Token global
Feature activation+2.534
leaders
Token leaders
Feature activation+0.000
.
Token.
Feature activation+1.053
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.204
Parliament
Token Parliament
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+3.560
Tony
Token Tony
Feature activation+2.944
Abbott
Token Abbott
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
criticised
Token criticised
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+3.560
Tony
Token Tony
Feature activation+2.944
Abbott
Token Abbott
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
criticised
Token criticised
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 2.174 - 2.898
CONTAINS 0.003%

president
Token president
Feature activation+0.038
of
Token of
Feature activation+0.306
Mexico
Token Mexico
Feature activation+0.684
,
Token,
Feature activation+1.008
prime
Token prime
Feature activation+0.079
minister
Token minister
Feature activation+2.299
of
Token of
Feature activation+0.929
Canada
Token Canada
Feature activation+0.250
,
Token,
Feature activation+0.366
they
Token they
Feature activation+0.000
called
Token called
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+2.578
Kevin
Token Kevin
Feature activation+0.404
Rudd
Token Rudd
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
about
Token about
Feature activation+0.240
his
Token his
Feature activation+0.309
health
Token health
Feature activation+0.000
,
Token,
Feature activation+3.088
Mr
Token Mr
Feature activation+2.756
Brown
Token Brown
Feature activation+0.000
emphatically
Token emphatically
Feature activation+0.000
denied
Token denied
Feature activation+0.000
rumours
Token rumours
Feature activation+0.000
that
Token that
Feature activation+0.458
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+2.756
".
Token".
Feature activation+0.000
Eh
Token Eh
Feature activation+0.000
ud
Tokenud
Feature activation+0.910
Ol
Token Ol
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
,
Token,
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+2.417
Narendra
Token Narendra
Feature activation+1.151
Modi
Token Modi
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.644
world
Token world
Feature activation+0.049

INTERVAL 1.449 - 2.174
CONTAINS 0.003%

band
Tokenband
Feature activation+0.000
Network
Token Network
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
Prime
Token Prime
Feature activation+0.129
Minister
Token Minister
Feature activation+2.048
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+2.689
Tony
Token Tony
Feature activation+1.129
Abbott
Token Abbott
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
apology
Token apology
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
Premier
Token Premier
Feature activation+0.175
,
Token,
Feature activation+1.576
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
as
Token as
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
British
TokenBritish
Feature activation+0.000
Prime
Token Prime
Feature activation+0.556
Minister
Token Minister
Feature activation+6.896
David
Token David
Feature activation+2.173
Cameron
Token Cameron
Feature activation+0.000
has
Token has
Feature activation+0.495
joined
Token joined
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
,
Token,
Feature activation+0.000
PM
Token PM
Feature activation+0.719
Lee
Token Lee
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.774
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.509
Young
TokenYoung
Feature activation+1.042
er
Tokener
Feature activation+1.151
Singapore
Token Singapore
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
,
Token,
Feature activation+0.805
in
Token in
Feature activation+0.216
his
Token his
Feature activation+0.525
first
Token first
Feature activation+0.386
100
Token 100
Feature activation+0.000
days
Token days
Feature activation+0.394
in
Token in
Feature activation+1.921
office
Token office
Feature activation+0.000
,
Token,
Feature activation+0.000
eclips
Token eclips
Feature activation+0.000
ing
Tokening
Feature activation+0.064
issues
Token issues
Feature activation+0.000

INTERVAL 0.725 - 1.449
CONTAINS 0.019%

In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
post
Token post
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.273
minister
Token minister
Feature activation+0.000
also
Token also
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.537
early
Token early
Feature activation+0.000
morning
Token morning
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
show
Token show
Feature activation+0.000
.
Token.
Feature activation+1.372
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.209
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.077
time
Token time
Feature activation+1.306
caption
Token caption
Feature activation+0.000
Opposition
Token Opposition
Feature activation+0.000
politician
Token politician
Feature activation+0.217
Imran
Token Imran
Feature activation+0.000
Khan
Token Khan
Feature activation+0.000
wants
Token wants
Feature activation+0.762
Mr
Token Mr
Feature activation+1.258
Sharif
Token Sharif
Feature activation+0.000
to
Token to
Feature activation+0.000
resign
Token resign
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
factor
Token factor
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
.
Token.
Feature activation+0.565
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.751
All
TokenAll
Feature activation+1.343
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+0.000
new
Token new
Feature activation+0.000
role
Token role
Feature activation+0.000
as
Token as
Feature activation+0.000
trade
Token trade
Feature activation+0.000
minister
Token minister
Feature activation+0.000
,
Token,
Feature activation+1.057
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000

INTERVAL 0.000 - 0.725
CONTAINS 99.973%

exactly
Token exactly
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+0.000
is
Token is
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
and
Token and
Feature activation+0.000
ing
Tokening
Feature activation+0.000
or
Token or
Feature activation+0.000
Baby
Token Baby
Feature activation+0.000
W
Token W
Feature activation+0.000
ipes
Tokenipes
Feature activation+0.000
after
Token after
Feature activation+0.000
rebate
Token rebate
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Free
TokenFree
Feature activation+0.000
C
Token C
Feature activation+0.000
Austin
Token Austin
Feature activation+0.000
Anderson
Token Anderson
Feature activation+0.000
(.
Token (.
Feature activation+0.000
300
Token300
Feature activation+0.000
/
Token/
Feature activation+0.000
3
Token3
Feature activation+0.000
/
Token/
Feature activation+0.000
38
Token38
Feature activation+0.000
)
Token)
Feature activation+0.000
also
Token also
Feature activation+0.000
have
Token have
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
national
Token national
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
appears
Token appears
Feature activation+0.000
the
Token the
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
Union
Token Union
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.000
provisions
Token provisions
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
appoint
Token appoint
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
one
Token one
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 2 in H10.6: (feature 6840)

TOP ACTIVATIONS
MAX = 4.505

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
exist
Token exist
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.609
the
Token the
Feature activation+4.082
Republican
Token Republican
Feature activation+4.505
governor
Token governor
Feature activation+0.117
brist
Token brist
Feature activation+0.000
led
Tokenled
Feature activation+0.000
in
Token in
Feature activation+0.000
response
Token response
Feature activation+0.000
A
Token A
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
.
Token.
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+4.285
The
TokenThe
Feature activation+0.615
American
Token American
Feature activation+0.000
Family
Token Family
Feature activation+0.000
Association
Token Association
Feature activation+0.000
is
Token is
Feature activation+0.000
footed
Tokenfooted
Feature activation+0.000
on
Token on
Feature activation+0.000
another
Token another
Feature activation+1.478
issue
Token issue
Feature activation+0.082
,
Token,
Feature activation+1.509
the
Token the
Feature activation+4.173
pur
Token pur
Feature activation+0.000
vey
Tokenvey
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
of
Token of
Feature activation+0.003
Hudson
Token Hudson
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+2.360
Until
Token Until
Feature activation+1.397
then
Token then
Feature activation+1.943
,
Token,
Feature activation+4.140
Walker
Token Walker
Feature activation+0.009
said
Token said
Feature activation+0.118
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
exist
Token exist
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.609
the
Token the
Feature activation+4.082
Republican
Token Republican
Feature activation+4.505
governor
Token governor
Feature activation+0.117
brist
Token brist
Feature activation+0.000
led
Tokenled
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
call
Token call
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
governor
Token governor
Feature activation+0.209
,
Token,
Feature activation+4.001
and
Token and
Feature activation+2.301
he
Token he
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
a
Token a
Feature activation+0.713
particular
Token particular
Feature activation+0.144
,
Token,
Feature activation+0.000
Lt
Token Lt
Feature activation+0.000
.
Token.
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.062
David
Token David
Feature activation+3.993
Dew
Token Dew
Feature activation+0.000
hurst
Tokenhurst
Feature activation+0.000
personally
Token personally
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.180
on
Token on
Feature activation+0.213
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.700
according
Token according
Feature activation+0.000
to
Token to
Feature activation+1.630
a
Token a
Feature activation+3.833
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+1.887
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.413
I
TokenI
Feature activation+0.302
Wisconsin
Token Wisconsin
Feature activation+0.389
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
ruled
Token ruled
Feature activation+0.142
Thursday
Token Thursday
Feature activation+0.000
the
Token the
Feature activation+3.824
governor
Token governor
Feature activation+1.473
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.450
s
Tokens
Feature activation+2.948
campaign
Token campaign
Feature activation+0.065
redist
Token redist
Feature activation+0.000
ricting
Tokenricting
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
helped
Token helped
Feature activation+0.000
his
Token his
Feature activation+3.606
party
Token party
Feature activation+0.000
stay
Token stay
Feature activation+0.000
in
Token in
Feature activation+0.000
office
Token office
Feature activation+0.000
and
Token and
Feature activation+0.000
told
Token told
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Express
Token Express
Feature activation+0.000
.
Token.
Feature activation+0.593
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.595
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
S
TokenS
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
war
Tokenwar
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
New
TokenNew
Feature activation+0.000
Jersey
Token Jersey
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
Chris
Token Chris
Feature activation+3.448
Christie
Token Christie
Feature activation+0.000
,
Token,
Feature activation+0.293
known
Token known
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
Token
Feature activation+0.000
a
Tokena
Feature activation+0.000
>
Token>
Feature activation+1.080
is
Token is
Feature activation+1.696
our
Token our
Feature activation+1.771
next
Token next
Feature activation+3.339
Governor
Token Governor
Feature activation+0.361
General
Token General
Feature activation+0.671
-
Token -
Feature activation+0.632
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.104
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.930
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
pleased
Token pleased
Feature activation+3.329
to
Token to
Feature activation+0.198
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Cre
TokenCre
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
iest
Tokeniest
Feature activation+0.000
million
Token million
Feature activation+0.075
of
Token of
Feature activation+0.364
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
to
Token to
Feature activation+0.000
oust
Token oust
Feature activation+3.281
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.724
Russ
Token Russ
Feature activation+0.000
Fe
Token Fe
Feature activation+0.000
ing
Tokening
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.436
Kelly
TokenKelly
Feature activation+0.000
was
Token was
Feature activation+0.844
with
Token with
Feature activation+0.334
the
Token the
Feature activation+3.279
large
Token large
Feature activation+0.590
Milwaukee
Token Milwaukee
Feature activation+0.000
law
Token law
Feature activation+0.000
firm
Token firm
Feature activation+0.000
Rein
Token Rein
Feature activation+0.000
.
Token.
Feature activation+0.070
Jerry
Token Jerry
Feature activation+3.129
Brown
Token Brown
Feature activation+0.949
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.064
s
Tokens
Feature activation+3.261
administration
Token administration
Feature activation+0.110
released
Token released
Feature activation+0.057
GDP
Token GDP
Feature activation+0.000
figures
Token figures
Feature activation+0.000
in
Token in
Feature activation+0.000
EY
TokenEY
Feature activation+0.000
CITY
Token CITY
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.799
Chris
Token Chris
Feature activation+3.235
Christie
Token Christie
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+3.173
bury
Token bury
Feature activation+0.000
the
Token the
Feature activation+0.416
adds
Token adds
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Govern
TokenGovern
Feature activation+0.000
or
Tokenor
Feature activation+3.215
Jindal
Token Jindal
Feature activation+0.000
said
Token said
Feature activation+0.047
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.255
Congratulations
TokenCongratulations
Feature activation+2.421
to
Token to
Feature activation+3.024
the
Token the
Feature activation+2.043
new
Token new
Feature activation+3.182
governor
Token governor
Feature activation+1.446
general
Token general
Feature activation+2.684
Julie
Token Julie
Feature activation+1.099
Pay
Token Pay
Feature activation+0.000
ette
Tokenette
Feature activation+0.641

Top DFA by src position
MAX = 5.104

nation
Token nation
Feature activation-0.001
Top resid features:
earlier
Token earlier
Feature activation-0.001
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
year
Token year
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Gov
Token Gov
Feature activation+2.961
Top resid features:
.
Token.
Feature activation+1.190
Top resid features:
Pat
Token Pat
Feature activation+0.257
Top resid features:
McC
Token McC
Feature activation+0.011
Top resid features:
r
Tokenr
Feature activation+0.005
Top resid features:
ory
Tokenory
Feature activation+0.217
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
Perry
Token Perry
Feature activation+0.146
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
defended
Token defended
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
governor
Token governor
Feature activation+5.104
Top resid features:
's
Token's
Feature activation+0.009
Top resid features:
association
Token association
Feature activation-0.054
Top resid features:
with
Token with
Feature activation+0.009
Top resid features:
A
Token A
Feature activation-0.165
Top resid features:
FA
TokenFA
Feature activation-0.095
Top resid features:
J
TokenJ
Feature activation-0.019
Top resid features:
ERS
TokenERS
Feature activation+0.031
Top resid features:
EY
TokenEY
Feature activation-0.025
Top resid features:
CITY
Token CITY
Feature activation-0.033
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.017
Top resid features:
Gov
Token Gov
Feature activation+2.038
Top resid features:
.
Token.
Feature activation+1.861
Top resid features:
Chris
Token Chris
Feature activation+0.011
Top resid features:
Christie
Token Christie
Feature activation+0.645
Top resid features:
came
Token came
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.128
Top resid features:
,
Token,
Feature activation-0.147
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
Republican
Token Republican
Feature activation+0.024
Top resid features:
governor
Token governor
Feature activation+4.369
Top resid features:
stressed
Token stressed
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
he
Token he
Feature activation+0.023
Top resid features:
's
Token's
Feature activation+0.012
Top resid features:
going
Token going
Feature activation+0.001
Top resid features:
nation
Token nation
Feature activation-0.002
Top resid features:
earlier
Token earlier
Feature activation-0.002
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
year
Token year
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Gov
Token Gov
Feature activation+2.641
Top resid features:
.
Token.
Feature activation+1.040
Top resid features:
Pat
Token Pat
Feature activation+0.208
Top resid features:
McC
Token McC
Feature activation+0.036
Top resid features:
r
Tokenr
Feature activation+0.004
Top resid features:
ory
Tokenory
Feature activation+0.193
Top resid features:
got
Token got
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
call
Token call
Feature activation-0.045
Top resid features:
from
Token from
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
governor
Token governor
Feature activation+4.754
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
mentioned
Token mentioned
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
grocery
Token grocery
Feature activation+0.001
Top resid features:
store
Token store
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
Lt
Token Lt
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Gov
Token Gov
Feature activation+3.382
Top resid features:
.
Token.
Feature activation+1.016
Top resid features:
David
Token David
Feature activation+0.025
Top resid features:
Dew
Token Dew
Feature activation+0.000
Top resid features:
hurst
Tokenhurst
Feature activation+0.000
Top resid features:
personally
Token personally
Feature activation+0.000
Top resid features:
scene
Token scene
Feature activation-0.050
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Govern
TokenGovern
Feature activation+0.791
Top resid features:
or
Tokenor
Feature activation+2.849
Top resid features:
Mark
Token Mark
Feature activation+0.094
Top resid features:
Dayton
Token Dayton
Feature activation+0.340
Top resid features:
will
Token will
Feature activation+0.087
Top resid features:
travel
Token travel
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
D
TokenD
Feature activation+0.000
Top resid features:
ealing
Tokenealing
Feature activation-0.006
Top resid features:
Gov
Token Gov
Feature activation+1.375
Top resid features:
.
Token.
Feature activation+2.313
Top resid features:
Scott
Token Scott
Feature activation+0.107
Top resid features:
Walker
Token Walker
Feature activation+0.497
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
victory
Token victory
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.005
Top resid features:
ago
Token ago
Feature activation-0.004
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Massachusetts
Token Massachusetts
Feature activation+0.486
Top resid features:
Gov
Token Gov
Feature activation+1.644
Top resid features:
.
Token.
Feature activation+1.835
Top resid features:
El
Token El
Feature activation+0.001
Top resid features:
bridge
Tokenbridge
Feature activation+0.002
Top resid features:
Gerry
Token Gerry
Feature activation+0.022
Top resid features:
signed
Token signed
Feature activation+0.022
Top resid features:
an
Token an
Feature activation+0.005
Top resid features:
LA
TokenLA
Feature activation-0.010
Top resid features:
H
TokenH
Feature activation+0.002
Top resid features:
ORE
TokenORE
Feature activation-0.004
Top resid features:
:
Token:
Feature activation+0.012
Top resid features:
Punjab
Token Punjab
Feature activation-0.004
Top resid features:
governor
Token governor
Feature activation+4.184
Top resid features:
Ch
Token Ch
Feature activation+0.288
Top resid features:
aud
Tokenaud
Feature activation+0.014
Top resid features:
h
Tokenh
Feature activation+0.007
Top resid features:
ry
Tokenry
Feature activation-0.006
Top resid features:
Sar
Token Sar
Feature activation-0.064
Top resid features:
10
Token 10
Feature activation-0.001
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
New
TokenNew
Feature activation-0.005
Top resid features:
Jersey
Token Jersey
Feature activation-0.121
Top resid features:
Gov
Token Gov
Feature activation+2.681
Top resid features:
.
Token.
Feature activation+1.310
Top resid features:
Chris
Token Chris
Feature activation+0.035
Top resid features:
Christie
Token Christie
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
known
Token known
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.107
Top resid features:
Canada
Token Canada
Feature activation-0.285
Top resid features:
's
Token's
Feature activation-0.043
Top resid features:
next
Token next
Feature activation-0.257
Top resid features:
governor
Token governor
Feature activation+4.154
Top resid features:
general
Token general
Feature activation+0.149
Top resid features:
."
Token."
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
If
TokenIf
Feature activation+0.005
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
Perry
Token Perry
Feature activation+0.269
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
defended
Token defended
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
governor
Token governor
Feature activation+3.692
Top resid features:
's
Token's
Feature activation+0.013
Top resid features:
association
Token association
Feature activation-0.006
Top resid features:
with
Token with
Feature activation+0.006
Top resid features:
A
Token A
Feature activation-0.094
Top resid features:
FA
TokenFA
Feature activation-0.012
Top resid features:
own
Token own
Feature activation-0.004
Top resid features:
money
Token money
Feature activation-0.017
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
California
Token California
Feature activation-0.095
Top resid features:
gubernatorial
Token gubernatorial
Feature activation+3.772
Top resid features:
contest
Token contest
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.083
Top resid features:
Some
Token Some
Feature activation+0.000
Top resid features:
multim
Token multim
Feature activation-0.007
Top resid features:
illion
Tokenillion
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
very
Token very
Feature activation-0.000
Top resid features:
pleased
Token pleased
Feature activation-0.003
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
governor
Token governor
Feature activation+3.818
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
appointment
Token appointment
Feature activation-0.027
Top resid features:
,"
Token,"
Feature activation+0.001
Top resid features:
she
Token she
Feature activation-0.004
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
Kingdom
Token Kingdom
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
California
TokenCalifornia
Feature activation+0.115
Top resid features:
Gov
Token Gov
Feature activation+2.156
Top resid features:
.
Token.
Feature activation+1.030
Top resid features:
Jerry
Token Jerry
Feature activation+0.076
Top resid features:
Brown
Token Brown
Feature activation+0.174
Top resid features:
âĢ
TokenâĢ
Feature activation+0.058
Top resid features:
Ļ
TokenĻ
Feature activation+0.136
Top resid features:
J
TokenJ
Feature activation-0.039
Top resid features:
ERS
TokenERS
Feature activation-0.065
Top resid features:
EY
TokenEY
Feature activation-0.449
Top resid features:
CITY
Token CITY
Feature activation-0.016
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.017
Top resid features:
Gov
Token Gov
Feature activation+2.488
Top resid features:
.
Token.
Feature activation+1.701
Top resid features:
Chris
Token Chris
Feature activation+0.070
Top resid features:
Christie
Token Christie
Feature activation+0.000
Top resid features:
came
Token came
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
adds
Token adds
Feature activation-0.002
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Govern
TokenGovern
Feature activation+0.261
Top resid features:
or
Tokenor
Feature activation+3.507
Top resid features:
Jindal
Token Jindal
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
,
Token,
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.141
Top resid features:
Canada
Token Canada
Feature activation-0.259
Top resid features:
's
Token's
Feature activation-0.038
Top resid features:
next
Token next
Feature activation-0.163
Top resid features:
governor
Token governor
Feature activation+2.439
Top resid features:
general
Token general
Feature activation+0.123
Top resid features:
."
Token."
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
If
TokenIf
Feature activation+0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.03

Head 2: 0.03

Head 3: 0.06

Head 4: 0.05

Head 5: 0.02

Head 6: 0.44

Head 7: 0.09

Head 8: 0.02

Head 9: 0.06

Head 10: 0.05

Head 11: 0.06

Positive logits

governor9.09

Governor8.29

gubernatorial8.11

governors7.93

Govern7.29

Gov7.12

Gov7.01

bernatorial6.45

Governors6.41

govern5.93

Jindal5.90

Cuomo5.62

statewide5.45

govern5.14

state5.13

Legislature5.02

legislature4.88

McAuliffe4.75

Kasich4.72

Christie4.69

Negative logits

Soc-3.26

Clubs-3.04

Disco-3.02

itch-2.98

Stras-2.95

Euro-2.93

LCS-2.90

hops-2.85

soc-2.83

club-2.81

Wiki-2.81

Counter-2.78

Seller-2.77

RFC-2.76

Artemis-2.76

orno-2.74

Squad-2.70

WTO-2.69

Trafford-2.65

Wenger-2.61

INTERVAL 4.054 - 4.505
CONTAINS 0.001%

A
Token A
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
.
Token.
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+4.285
The
TokenThe
Feature activation+0.615
American
Token American
Feature activation+0.000
Family
Token Family
Feature activation+0.000
Association
Token Association
Feature activation+0.000
is
Token is
Feature activation+0.000
footed
Tokenfooted
Feature activation+0.000
on
Token on
Feature activation+0.000
another
Token another
Feature activation+1.478
issue
Token issue
Feature activation+0.082
,
Token,
Feature activation+1.509
the
Token the
Feature activation+4.173
pur
Token pur
Feature activation+0.000
vey
Tokenvey
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
of
Token of
Feature activation+0.003
Hudson
Token Hudson
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
exist
Token exist
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.609
the
Token the
Feature activation+4.082
Republican
Token Republican
Feature activation+4.505
governor
Token governor
Feature activation+0.117
brist
Token brist
Feature activation+0.000
led
Tokenled
Feature activation+0.000
in
Token in
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
exist
Token exist
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.609
the
Token the
Feature activation+4.082
Republican
Token Republican
Feature activation+4.505
governor
Token governor
Feature activation+0.117
brist
Token brist
Feature activation+0.000
led
Tokenled
Feature activation+0.000
in
Token in
Feature activation+0.000
response
Token response
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+2.360
Until
Token Until
Feature activation+1.397
then
Token then
Feature activation+1.943
,
Token,
Feature activation+4.140
Walker
Token Walker
Feature activation+0.009
said
Token said
Feature activation+0.118
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000

INTERVAL 3.604 - 4.054
CONTAINS 0.001%

,
Token,
Feature activation+0.000
Lt
Token Lt
Feature activation+0.000
.
Token.
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.062
David
Token David
Feature activation+3.993
Dew
Token Dew
Feature activation+0.000
hurst
Tokenhurst
Feature activation+0.000
personally
Token personally
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.180
a
Token a
Feature activation+0.000
call
Token call
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
governor
Token governor
Feature activation+0.209
,
Token,
Feature activation+4.001
and
Token and
Feature activation+2.301
he
Token he
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
a
Token a
Feature activation+0.713
particular
Token particular
Feature activation+0.144
redist
Token redist
Feature activation+0.000
ricting
Tokenricting
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
helped
Token helped
Feature activation+0.000
his
Token his
Feature activation+3.606
party
Token party
Feature activation+0.000
stay
Token stay
Feature activation+0.000
in
Token in
Feature activation+0.000
office
Token office
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.213
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.700
according
Token according
Feature activation+0.000
to
Token to
Feature activation+1.630
a
Token a
Feature activation+3.833
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+1.887
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.413
I
TokenI
Feature activation+0.302
Wisconsin
Token Wisconsin
Feature activation+0.389
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
ruled
Token ruled
Feature activation+0.142
Thursday
Token Thursday
Feature activation+0.000
the
Token the
Feature activation+3.824
governor
Token governor
Feature activation+1.473
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.450
s
Tokens
Feature activation+2.948
campaign
Token campaign
Feature activation+0.065

INTERVAL 3.153 - 3.604
CONTAINS 0.001%

EY
TokenEY
Feature activation+0.000
CITY
Token CITY
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.799
Chris
Token Chris
Feature activation+3.235
Christie
Token Christie
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+3.173
bury
Token bury
Feature activation+0.000
the
Token the
Feature activation+0.416
told
Token told
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Express
Token Express
Feature activation+0.000
.
Token.
Feature activation+0.593
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.595
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
S
TokenS
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
war
Tokenwar
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.930
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
pleased
Token pleased
Feature activation+3.329
to
Token to
Feature activation+0.198
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Cre
TokenCre
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
iest
Tokeniest
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.436
Kelly
TokenKelly
Feature activation+0.000
was
Token was
Feature activation+0.844
with
Token with
Feature activation+0.334
the
Token the
Feature activation+3.279
large
Token large
Feature activation+0.590
Milwaukee
Token Milwaukee
Feature activation+0.000
law
Token law
Feature activation+0.000
firm
Token firm
Feature activation+0.000
Rein
Token Rein
Feature activation+0.000
A
TokenA
Feature activation+0.000
jury
Token jury
Feature activation+0.000
unanimously
Token unanimously
Feature activation+0.000
found
Token found
Feature activation+0.730
former
Token former
Feature activation+0.676
Connecticut
Token Connecticut
Feature activation+3.164
Gov
Token Gov
Feature activation+1.035
.
Token.
Feature activation+1.461
John
Token John
Feature activation+2.100
Row
Token Row
Feature activation+0.000
land
Tokenland
Feature activation+0.000

INTERVAL 2.703 - 3.153
CONTAINS 0.001%

This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.999
first
Token first
Feature activation+0.251
time
Token time
Feature activation+3.147
that
Token that
Feature activation+1.926
Roy
Token Roy
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.393
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
If
TokenIf
Feature activation+2.751
you
Token you
Feature activation+0.001
think
Token think
Feature activation+2.979
Cro
Token Cro
Feature activation+0.000
oked
Tokenoked
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
and
Token and
Feature activation+0.000
Cor
Token Cor
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
Pat
Token Pat
Feature activation+3.009
McC
Token McC
Feature activation+0.024
r
Tokenr
Feature activation+0.000
ory
Tokenory
Feature activation+0.293
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
Governor
Token Governor
Feature activation+0.000
and
Token and
Feature activation+0.243
Sec
Token Sec
Feature activation+0.000
.
Token.
Feature activation+0.667
of
Token of
Feature activation+1.775
State
Token State
Feature activation+3.049
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
ame
Tokename
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
religion
Token religion
Feature activation+0.000
,
Token,
Feature activation+0.744
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.628
the
Token the
Feature activation+2.200
Republican
Token Republican
Feature activation+2.734
governor
Token governor
Feature activation+0.320
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.805
Sept
Token Sept
Feature activation+0.000

INTERVAL 2.252 - 2.703
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Cloud
Token Cloud
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.643
If
Token If
Feature activation+2.498
true
Token true
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
motivated
Token motivated
Feature activation+0.000
found
Token found
Feature activation+0.000
former
Token former
Feature activation+0.000
Connecticut
Token Connecticut
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
John
Token John
Feature activation+2.270
Row
Token Row
Feature activation+0.000
land
Tokenland
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
on
Token on
Feature activation+0.000
all
Token all
Feature activation+0.000
call
Token call
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
governor
Token governor
Feature activation+0.209
,
Token,
Feature activation+4.001
and
Token and
Feature activation+2.301
he
Token he
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
a
Token a
Feature activation+0.713
particular
Token particular
Feature activation+0.144
project
Token project
Feature activation+0.000
conviction
Token conviction
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.039
governor
Token governor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.458
s
Tokens
Feature activation+0.597
office
Token office
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+1.926
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
about
Token about
Feature activation+0.000
early
Token early
Feature activation+0.000
voting
Token voting
Feature activation+0.000
.
Token.
Feature activation+2.366
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.853
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.174
We
TokenWe
Feature activation+0.000

INTERVAL 1.802 - 2.252
CONTAINS 0.003%

religious
Token religious
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
,
Token,
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.002
Pat
Token Pat
Feature activation+2.123
McC
Token McC
Feature activation+0.084
r
Tokenr
Feature activation+0.000
ory
Tokenory
Feature activation+0.000
vetoed
Token vetoed
Feature activation+0.000
the
Token the
Feature activation+0.499
.
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
"
Token"
Feature activation+2.089
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
only
Token only
Feature activation+0.069
fitting
Token fitting
Feature activation+0.625
that
Token that
Feature activation+1.681
governor
Token governor
Feature activation+0.250
general
Token general
Feature activation+0.153
."
Token."
Feature activation+0.233
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.950
If
TokenIf
Feature activation+1.988
<
Token <
Feature activation+0.000
a
Tokena
Feature activation+0.000
href
Token href
Feature activation+0.000
="
Token="
Feature activation+0.000
https
Tokenhttps
Feature activation+0.000
early
Token early
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+2.360
Until
Token Until
Feature activation+1.397
then
Token then
Feature activation+1.943
,
Token,
Feature activation+4.140
Walker
Token Walker
Feature activation+0.009
said
Token said
Feature activation+0.118
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
found
Token found
Feature activation+0.730
former
Token former
Feature activation+0.676
Connecticut
Token Connecticut
Feature activation+3.164
Gov
Token Gov
Feature activation+1.035
.
Token.
Feature activation+1.461
John
Token John
Feature activation+2.100
Row
Token Row
Feature activation+0.000
land
Tokenland
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
on
Token on
Feature activation+0.000
all
Token all
Feature activation+0.000

INTERVAL 1.351 - 1.802
CONTAINS 0.006%

J
Token J
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
(@
Token (@
Feature activation+0.000
realDonaldTrump
TokenrealDonaldTrump
Feature activation+0.000
)
Token)
Feature activation+1.672
July
Token July
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.023
2016
Token 2016
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.731
Governor
Token Governor
Feature activation+1.896
Robert
Token Robert
Feature activation+0.643
Bentley
Token Bentley
Feature activation+0.417
said
Token said
Feature activation+0.258
.
Token.
Feature activation+0.499
,
Token,
Feature activation+0.000
Massachusetts
Token Massachusetts
Feature activation+0.000
Gov
Token Gov
Feature activation+0.000
.
Token.
Feature activation+0.000
El
Token El
Feature activation+0.000
bridge
Tokenbridge
Feature activation+1.536
Gerry
Token Gerry
Feature activation+0.934
signed
Token signed
Feature activation+0.871
an
Token an
Feature activation+1.054
obscure
Token obscure
Feature activation+0.387
redist
Token redist
Feature activation+0.000
.
Token.
Feature activation+0.285
The
Token The
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
means
Token means
Feature activation+1.626
the
Token the
Feature activation+2.333
likely
Token likely
Feature activation+1.391
end
Token end
Feature activation+0.000
of
Token of
Feature activation+1.730
the
Token the
Feature activation+2.090
investigation
Token investigation
Feature activation+0.062
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.061
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
appeals
Token appeals
Feature activation+0.000
court
Token court
Feature activation+0.000
.
Token.
Feature activation+1.356
Brian
Token Brian
Feature activation+0.000
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.901 - 1.351
CONTAINS 0.012%

deficit
Token deficit
Feature activation+0.000
,
Token,
Feature activation+0.000
Governor
Token Governor
Feature activation+0.800
Scott
Token Scott
Feature activation+0.883
Walker
Token Walker
Feature activation+0.000
has
Token has
Feature activation+0.967
taken
Token taken
Feature activation+0.000
a
Token a
Feature activation+0.000
radical
Token radical
Feature activation+0.000
and
Token and
Feature activation+0.000
unprecedented
Token unprecedented
Feature activation+0.000
drops
Token drops
Feature activation+0.000
several
Token several
Feature activation+0.000
places
Token places
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
led
Token led
Feature activation+1.088
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
our
Token our
Feature activation+0.000
Mostly
Token Mostly
Feature activation+0.000
True
Token True
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ax
Tokenax
Feature activation+0.874
gift
Token gift
Feature activation+0.000
laws
Token laws
Feature activation+0.000
.
Token.
Feature activation+1.268
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.160
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.393
âĢ
TokenâĢ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
plan
Token plan
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+1.220
his
Token his
Feature activation+0.000
,
Token,
Feature activation+0.000
really
Token really
Feature activation+0.000
expands
Token expands
Feature activation+0.000
Medicare
Token Medicare
Feature activation+0.000
that
Token that
Feature activation+0.096
year
Token year
Feature activation+0.178
,
Token,
Feature activation+0.377
the
Token the
Feature activation+1.036
Secretary
Token Secretary
Feature activation+0.211
of
Token of
Feature activation+1.347
Higher
Token Higher
Feature activation+0.000
Education
Token Education
Feature activation+0.446
went
Token went
Feature activation+0.000
before
Token before
Feature activation+0.354
the
Token the
Feature activation+0.823

INTERVAL 0.450 - 0.901
CONTAINS 0.027%

cdn
Tokencdn
Feature activation+0.000
p
Tokenp
Feature activation+0.000
oli
Tokenoli
Feature activation+0.000
Token
Feature activation+0.000
a
Tokena
Feature activation+0.000
>
Token>
Feature activation+0.610
âĢĶ
Token âĢĶ
Feature activation+0.000
@
Token@
Feature activation+1.305
l
Tokenl
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
itt
Tokenitt
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
during
Token during
Feature activation+0.000
his
Token his
Feature activation+0.000
years
Token years
Feature activation+0.000
as
Token as
Feature activation+0.469
a
Token a
Feature activation+0.000
Sask
Token Sask
Feature activation+0.000
tel
Tokentel
Feature activation+0.000
employee
Token employee
Feature activation+0.000
,
Token,
Feature activation+0.000
floated
Token floated
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
possible
Token possible
Feature activation+0.000
challenger
Token challenger
Feature activation+0.000
to
Token to
Feature activation+0.623
Democratic
Token Democratic
Feature activation+0.351
Mayor
Token Mayor
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
de
Token de
Feature activation+0.000
Blasio
Token Blasio
Feature activation+0.000
India
TokenIndia
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.664
,
Token,
Feature activation+1.262
Narendra
Token Narendra
Feature activation+0.090
Modi
Token Modi
Feature activation+0.000
,
Token,
Feature activation+0.000
condemned
Token condemned
Feature activation+0.000
passing
Token passing
Feature activation+0.000
a
Token a
Feature activation+0.000
bill
Token bill
Feature activation+0.000
.
Token.
Feature activation+0.050
The
Token The
Feature activation+0.157
losing
Token losing
Feature activation+0.534
candidate
Token candidate
Feature activation+0.000
files
Token files
Feature activation+0.000
a
Token a
Feature activation+0.000
petition
Token petition
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.000 - 0.450
CONTAINS 99.947%

the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
person
Token person
Feature activation+0.000
who
Token who
Feature activation+0.000
pest
Token pest
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
and
Token and
Feature activation+0.000
ãĤ
TokenãĤ
Feature activation+0.000
Ī
TokenĪ
Feature activation+0.000
ãĤ
TokenãĤ
Feature activation+0.000
į
Tokenį
Feature activation+0.000
ãģĹ
TokenãģĹ
Feature activation+0.000
ãģı
Tokenãģı
Feature activation+0.000
ãģ
Tokenãģ
Feature activation+0.000
Ĭ
TokenĬ
Feature activation+0.000
é
Tokené
Feature activation+0.000
¡
Token¡
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
former
Token former
Feature activation+0.000
at
Token at
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
's
Token's
Feature activation+0.000
inauguration
Token inauguration
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
At
TokenAt
Feature activation+0.000
to
Token to
Feature activation+0.000
cite
Token cite
Feature activation+0.000
this
Token this
Feature activation+0.000
statute
Token statute
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
forms
Token forms
Feature activation+0.000
the
Token the
Feature activation+0.000
principal
Token principal
Feature activation+0.000
statutory
Token statutory
Feature activation+0.000
basis
Token basis
Feature activation+0.000
eness
Tokeneness
Feature activation+0.000
hides
Token hides
Feature activation+0.000
another
Token another
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
donald
Tokendonald
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
indeed
Token indeed
Feature activation+0.000
an
Token an
Feature activation+0.000
avid
Token avid
Feature activation+0.000
reader
Token reader
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H10.6: (feature 18946)

TOP ACTIVATIONS
MAX = 6.357

Ċ
TokenĊ
Feature activation+0.949
Ċ
TokenĊ
Feature activation+0.000
Based
TokenBased
Feature activation+1.873
on
Token on
Feature activation+3.336
reporting
Token reporting
Feature activation+0.544
by
Token by
Feature activation+6.357
Reuters
Token Reuters
Feature activation+3.242
,
Token,
Feature activation+3.343
Inter
Token Inter
Feature activation+0.226
fax
Tokenfax
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rights
Token rights
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
Julian
Token Julian
Feature activation+0.000
Burn
Token Burn
Feature activation+0.000
side
Tokenside
Feature activation+0.000
told
Token told
Feature activation+6.274
Australian
Token Australian
Feature activation+0.229
radio
Token radio
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
David
TokenDavid
Feature activation+0.000
D
Token D
Feature activation+0.000
ickson
Tokenickson
Feature activation+6.060
,
Token,
Feature activation+0.236
route
Token route
Feature activation+0.000
managing
Token managing
Feature activation+0.000
director
Token director
Feature activation+0.000
for
Token for
Feature activation+0.000
Fab
Token Fab
Feature activation+0.000
io
Tokenio
Feature activation+0.000
Meng
Token Meng
Feature activation+0.000
are
Tokenare
Feature activation+0.000
lli
Tokenlli
Feature activation+0.000
told
Token told
Feature activation+5.631
Reuters
Token Reuters
Feature activation+1.334
.
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
Ċ
TokenĊ
Feature activation+0.407
Ċ
TokenĊ
Feature activation+0.000
Media
TokenMedia
Feature activation+0.236
playback
Token playback
Feature activation+0.010
is
Token is
Feature activation+4.921
unsupported
Token unsupported
Feature activation+0.552
on
Token on
Feature activation+0.499
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
less
Token less
Feature activation+0.000
impressed
Token impressed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.558
Ċ
TokenĊ
Feature activation+0.000
Read
TokenRead
Feature activation+4.878
more
Token more
Feature activation+1.375
:
Token:
Feature activation+0.000
Student
Token Student
Feature activation+0.000
comm
Token comm
Feature activation+0.000
utes
Tokenutes
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Anthony
TokenAnthony
Feature activation+0.650
Zur
Token Zur
Feature activation+0.000
cher
Tokencher
Feature activation+4.489
,
Token,
Feature activation+2.199
BBC
Token BBC
Feature activation+0.000
News
Token News
Feature activation+0.000
,
Token,
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.000
from
Token from
Feature activation+4.335
the
Token the
Feature activation+1.869
FT
Token FT
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Media
TokenMedia
Feature activation+0.446
playback
Token playback
Feature activation+0.341
is
Token is
Feature activation+4.317
unsupported
Token unsupported
Feature activation+0.948
on
Token on
Feature activation+1.397
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.313
Ċ
TokenĊ
Feature activation+0.000
Media
TokenMedia
Feature activation+0.263
playback
Token playback
Feature activation+0.000
is
Token is
Feature activation+4.137
unsupported
Token unsupported
Feature activation+0.620
on
Token on
Feature activation+0.972
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
a
Tokena
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
endez
Tokenendez
Feature activation+3.900
,
Token,
Feature activation+0.223
another
Token another
Feature activation+0.000
participant
Token participant
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+2.151
part
Token part
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
rally
Token rally
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+3.885
Reuters
Token Reuters
Feature activation+2.239
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
ICK
TokenICK
Feature activation+0.000
Y
TokenY
Feature activation+0.000
W
Token W
Feature activation+0.000
IL
TokenIL
Feature activation+0.000
SON
TokenSON
Feature activation+2.756
/
Token/
Feature activation+3.879
ST
TokenST
Feature activation+0.000
UFF
TokenUFF
Feature activation+0.000
Arc
Token Arc
Feature activation+0.000
adia
Tokenadia
Feature activation+0.000
,
Token,
Feature activation+0.000
Congo
Token Congo
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
decades
Token decades
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.861
Ċ
TokenĊ
Feature activation+2.087
J
TokenJ
Feature activation+0.000
oint
Tokenoint
Feature activation+0.000
force
Token force
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
told
Token told
Feature activation+0.000
AFP
Token AFP
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+3.786
stories
Token stories
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.497
Ċ
TokenĊ
Feature activation+0.000
Federal
TokenFederal
Feature activation+0.000
officials
Token officials
Feature activation+0.000
told
Token told
Feature activation+3.519
Al
Token Al
Feature activation+0.356
Jazeera
Token Jazeera
Feature activation+0.444
they
Token they
Feature activation+0.000
still
Token still
Feature activation+0.000
don
Token don
Feature activation+0.000
's
Token's
Feature activation+0.000
R
Token R
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
Abdel
Token Abdel
Feature activation+0.000
Rahman
Token Rahman
Feature activation+0.173
told
Token told
Feature activation+3.517
AFP
Token AFP
Feature activation+2.951
news
Token news
Feature activation+0.000
agency
Token agency
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Based
TokenBased
Feature activation+1.873
on
Token on
Feature activation+3.336
reporting
Token reporting
Feature activation+0.544
by
Token by
Feature activation+6.357
Reuters
Token Reuters
Feature activation+3.242
,
Token,
Feature activation+3.343
Inter
Token Inter
Feature activation+0.226
fax
Tokenfax
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
S
TokenS
Feature activation+0.000
AC
TokenAC
Feature activation+0.000
Nicolas
Token Nicolas
Feature activation+0.000
Sark
Token Sark
Feature activation+0.000
ozy
Tokenozy
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.339
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
zech
Tokenzech
Feature activation+0.000
President
Token President
Feature activation+0.000
Vac
Token Vac
Feature activation+0.000
sanctions
Token sanctions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.949
Ċ
TokenĊ
Feature activation+0.000
Based
TokenBased
Feature activation+1.873
on
Token on
Feature activation+3.336
reporting
Token reporting
Feature activation+0.544
by
Token by
Feature activation+6.357
Reuters
Token Reuters
Feature activation+3.242
,
Token,
Feature activation+3.343
Inter
Token Inter
Feature activation+0.226

Top DFA by src position
MAX = 6.392

series
Token series
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
economic
Token economic
Feature activation-0.000
Top resid features:
sanctions
Token sanctions
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.040
Top resid features:
Ċ
TokenĊ
Feature activation+3.421
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Based
TokenBased
Feature activation-0.008
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
reporting
Token reporting
Feature activation-0.288
Top resid features:
by
Token by
Feature activation+0.062
Top resid features:
advocates
Token advocates
Feature activation-0.001
Top resid features:
criticised
Token criticised
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
move
Token move
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation+3.329
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
"
Token"
Feature activation+0.002
Top resid features:
I
TokenI
Feature activation+0.001
Top resid features:
don
Token don
Feature activation-0.000
Top resid features:
't
Token't
Feature activation-0.000
Top resid features:
keep
Token keep
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
tracks
Token tracks
Feature activation-0.003
Top resid features:
clear
Token clear
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+6.392
Top resid features:
Ċ
TokenĊ
Feature activation+0.101
Top resid features:
David
TokenDavid
Feature activation+0.074
Top resid features:
D
Token D
Feature activation+0.036
Top resid features:
ickson
Tokenickson
Feature activation+0.022
Top resid features:
,
Token,
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:
safe
Token safe
Feature activation+0.003
Top resid features:
side
Token side
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+1.699
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
There
TokenThere
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
reports
Token reports
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
them
Token them
Feature activation+0.001
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
illegal
Tokenillegal
Feature activation+0.004
Top resid features:
".
Token".
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+2.547
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
Later
TokenLater
Feature activation+0.000
Top resid features:
Ukrainian
Token Ukrainian
Feature activation+0.014
Top resid features:
authorities
Token authorities
Feature activation+0.002
Top resid features:
said
Token said
Feature activation-0.002
Top resid features:
students
Token students
Feature activation+0.019
Top resid features:
were
Token were
Feature activation-0.000
Top resid features:
less
Token less
Feature activation-0.000
Top resid features:
impressed
Token impressed
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+2.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.056
Top resid features:
Read
TokenRead
Feature activation+0.010
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Student
Token Student
Feature activation+0.000
Top resid features:
US
TokenUS
Feature activation+0.003
Top resid features:
pay
Token pay
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
price
Token price
Feature activation-0.000
Top resid features:
".
Token".
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+1.632
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
heated
Token heated
Feature activation+0.000
Top resid features:
rhetoric
Token rhetoric
Feature activation-0.000
Top resid features:
between
Token between
Feature activation-0.000
Top resid features:
office
Token office
Feature activation-0.000
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+2.905
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
More
TokenMore
Feature activation+0.015
Top resid features:
from
Token from
Feature activation+0.068
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
FT
Token FT
Feature activation+0.000
Top resid features:
kin
Tokenkin
Feature activation-0.002
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
pencil
Token pencil
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+1.985
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
Media
TokenMedia
Feature activation+0.108
Top resid features:
playback
Token playback
Feature activation+0.083
Top resid features:
is
Token is
Feature activation+0.054
Top resid features:
unsupported
Token unsupported
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
025
Token025
Feature activation+0.000
Top resid features:
tn
Tokentn
Feature activation+0.003
Top resid features:
euros
Token euros
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+2.338
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Media
TokenMedia
Feature activation+0.090
Top resid features:
playback
Token playback
Feature activation+0.075
Top resid features:
is
Token is
Feature activation+0.042
Top resid features:
unsupported
Token unsupported
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
vote
Token vote
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
illegal
Token illegal
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+1.417
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
"
Token"
Feature activation+0.007
Top resid features:
We
TokenWe
Feature activation+0.001
Top resid features:
want
Token want
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
waved
Token waved
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Scottish
Token Scottish
Feature activation-0.015
Top resid features:
flag
Token flag
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+2.079
Top resid features:
Ċ
TokenĊ
Feature activation+0.215
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
regional
Token regional
Feature activation+0.003
Top resid features:
government
Token government
Feature activation+0.015
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
slot
Token slot
Feature activation+0.001
Top resid features:
into
Token into
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
machines
Token machines
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+3.515
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
R
TokenR
Feature activation-0.002
Top resid features:
ICK
TokenICK
Feature activation+0.007
Top resid features:
Y
TokenY
Feature activation+0.006
Top resid features:
W
Token W
Feature activation+0.020
Top resid features:
Congo
Token Congo
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.007
Top resid features:
two
Token two
Feature activation-0.002
Top resid features:
decades
Token decades
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+1.251
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
J
TokenJ
Feature activation+0.000
Top resid features:
oint
Tokenoint
Feature activation+0.000
Top resid features:
force
Token force
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
ari
Tokenari
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
told
Token told
Feature activation+0.003
Top resid features:
AFP
Token AFP
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+4.295
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Related
TokenRelated
Feature activation-0.191
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
violence
Token violence
Feature activation-0.007
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+1.742
Top resid features:
Ċ
TokenĊ
Feature activation+0.168
Top resid features:
To
TokenTo
Feature activation+0.002
Top resid features:
try
Token try
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
close
Token close
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+3.056
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
"
Token"
Feature activation+0.003
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
air
Token air
Feature activation+0.000
Top resid features:
strikes
Token strikes
Feature activation-0.000
Top resid features:
series
Token series
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
economic
Token economic
Feature activation-0.001
Top resid features:
sanctions
Token sanctions
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation+1.732
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Based
TokenBased
Feature activation-0.011
Top resid features:
on
Token on
Feature activation+0.023
Top resid features:
reporting
Token reporting
Feature activation-0.241
Top resid features:
by
Token by
Feature activation+0.031
Top resid features:
Nicolas
Token Nicolas
Feature activation+0.000
Top resid features:
Sark
Token Sark
Feature activation+0.002
Top resid features:
ozy
Tokenozy
Feature activation+0.006
Top resid features:
said
Token said
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+1.690
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
zech
Tokenzech
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
Vac
Token Vac
Feature activation+0.000
Top resid features:
series
Token series
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
economic
Token economic
Feature activation+0.000
Top resid features:
sanctions
Token sanctions
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+2.128
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Based
TokenBased
Feature activation-0.002
Top resid features:
on
Token on
Feature activation-0.010
Top resid features:
reporting
Token reporting
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.04

Head 3: 0.11

Head 4: 0.04

Head 5: 0.04

Head 6: 0.43

Head 7: 0.05

Head 8: 0.08

Head 9: 0.05

Head 10: 0.04

Head 11: 0.04

Positive logits

BBC4.40

presenter4.02

BBC3.70

Reporting3.47

Reporting3.39

Accounts3.31

Programme3.07

budget3.03

programme2.97

apologise2.97

correspondent2.94

Reports2.94

Report2.90

levy2.89

Budget2.87

Constable2.85

reporting2.83

reporter2.77

broadcaster2.72

Unit2.69

Negative logits

Arbor-3.33

patented-2.70

********************************-2.66

otom-2.59

************-2.59

COR-2.59

bar-2.58

Barber-2.57

****************-2.57

Ivy-2.52

OPT-2.51

Coulter-2.48

-2.47

Scalia-2.45

Whitman-2.45

Cato-2.44

Locke-2.38

Patent-2.37

enfranch-2.37

--+-2.36

INTERVAL 5.721 - 6.357
CONTAINS 0.000%

rights
Token rights
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
Julian
Token Julian
Feature activation+0.000
Burn
Token Burn
Feature activation+0.000
side
Tokenside
Feature activation+0.000
told
Token told
Feature activation+6.274
Australian
Token Australian
Feature activation+0.229
radio
Token radio
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.949
Ċ
TokenĊ
Feature activation+0.000
Based
TokenBased
Feature activation+1.873
on
Token on
Feature activation+3.336
reporting
Token reporting
Feature activation+0.544
by
Token by
Feature activation+6.357
Reuters
Token Reuters
Feature activation+3.242
,
Token,
Feature activation+3.343
Inter
Token Inter
Feature activation+0.226
fax
Tokenfax
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
David
TokenDavid
Feature activation+0.000
D
Token D
Feature activation+0.000
ickson
Tokenickson
Feature activation+6.060
,
Token,
Feature activation+0.236
route
Token route
Feature activation+0.000
managing
Token managing
Feature activation+0.000
director
Token director
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 5.085 - 5.721
CONTAINS 0.000%

Fab
Token Fab
Feature activation+0.000
io
Tokenio
Feature activation+0.000
Meng
Token Meng
Feature activation+0.000
are
Tokenare
Feature activation+0.000
lli
Tokenlli
Feature activation+0.000
told
Token told
Feature activation+5.631
Reuters
Token Reuters
Feature activation+1.334
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 4.450 - 5.085
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.407
Ċ
TokenĊ
Feature activation+0.000
Media
TokenMedia
Feature activation+0.236
playback
Token playback
Feature activation+0.010
is
Token is
Feature activation+4.921
unsupported
Token unsupported
Feature activation+0.552
on
Token on
Feature activation+0.499
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Anthony
TokenAnthony
Feature activation+0.650
Zur
Token Zur
Feature activation+0.000
cher
Tokencher
Feature activation+4.489
,
Token,
Feature activation+2.199
BBC
Token BBC
Feature activation+0.000
News
Token News
Feature activation+0.000
,
Token,
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
less
Token less
Feature activation+0.000
impressed
Token impressed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.558
Ċ
TokenĊ
Feature activation+0.000
Read
TokenRead
Feature activation+4.878
more
Token more
Feature activation+1.375
:
Token:
Feature activation+0.000
Student
Token Student
Feature activation+0.000
comm
Token comm
Feature activation+0.000
utes
Tokenutes
Feature activation+0.000

INTERVAL 3.814 - 4.450
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Media
TokenMedia
Feature activation+0.446
playback
Token playback
Feature activation+0.341
is
Token is
Feature activation+4.317
unsupported
Token unsupported
Feature activation+0.948
on
Token on
Feature activation+1.397
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Congo
Token Congo
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
decades
Token decades
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.861
Ċ
TokenĊ
Feature activation+2.087
J
TokenJ
Feature activation+0.000
oint
Tokenoint
Feature activation+0.000
force
Token force
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.000
from
Token from
Feature activation+4.335
the
Token the
Feature activation+1.869
FT
Token FT
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
a
Tokena
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
endez
Tokenendez
Feature activation+3.900
,
Token,
Feature activation+0.223
another
Token another
Feature activation+0.000
participant
Token participant
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+2.151
part
Token part
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
rally
Token rally
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+3.885
Reuters
Token Reuters
Feature activation+2.239
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000

INTERVAL 3.178 - 3.814
CONTAINS 0.001%

sanctions
Token sanctions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.949
Ċ
TokenĊ
Feature activation+0.000
Based
TokenBased
Feature activation+1.873
on
Token on
Feature activation+3.336
reporting
Token reporting
Feature activation+0.544
by
Token by
Feature activation+6.357
Reuters
Token Reuters
Feature activation+3.242
,
Token,
Feature activation+3.343
Inter
Token Inter
Feature activation+0.226
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.497
Ċ
TokenĊ
Feature activation+0.000
Federal
TokenFederal
Feature activation+0.000
officials
Token officials
Feature activation+0.000
told
Token told
Feature activation+3.519
Al
Token Al
Feature activation+0.356
Jazeera
Token Jazeera
Feature activation+0.444
they
Token they
Feature activation+0.000
still
Token still
Feature activation+0.000
don
Token don
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Based
TokenBased
Feature activation+1.873
on
Token on
Feature activation+3.336
reporting
Token reporting
Feature activation+0.544
by
Token by
Feature activation+6.357
Reuters
Token Reuters
Feature activation+3.242
,
Token,
Feature activation+3.343
Inter
Token Inter
Feature activation+0.226
fax
Tokenfax
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
S
TokenS
Feature activation+0.000
force
Token force
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
whole
Token whole
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.254
Ċ
TokenĊ
Feature activation+1.045
Police
TokenPolice
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
officers
Token officers
Feature activation+0.000
's
Token's
Feature activation+0.000
R
Token R
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
Abdel
Token Abdel
Feature activation+0.000
Rahman
Token Rahman
Feature activation+0.173
told
Token told
Feature activation+3.517
AFP
Token AFP
Feature activation+2.951
news
Token news
Feature activation+0.000
agency
Token agency
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.543 - 3.178
CONTAINS 0.002%

obligatory
Token obligatory
Feature activation+0.000
for
Token for
Feature activation+0.000
drug
Token drug
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.875
Ċ
TokenĊ
Feature activation+0.000
Am
TokenAm
Feature activation+0.000
nesty
Tokennesty
Feature activation+0.000
figures
Token figures
Feature activation+0.000
released
Token released
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Media
TokenMedia
Feature activation+0.182
playback
Token playback
Feature activation+0.000
is
Token is
Feature activation+2.884
unsupported
Token unsupported
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
declined
Token declined
Feature activation+0.000
to
Token to
Feature activation+0.000
tour
Token tour
Feature activation+0.000
Bethlehem
Token Bethlehem
Feature activation+0.000
[
Token [
Feature activation+0.000
AFP
TokenAFP
Feature activation+2.827
]
Token]
Feature activation+0.000
"
Token "
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
very
Token very
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
time
Token time
Feature activation+0.000
."
Token."
Feature activation+0.454
Ċ
TokenĊ
Feature activation+0.809
Ċ
TokenĊ
Feature activation+2.697
Topics
TokenTopics
Feature activation+0.486
:
Token:
Feature activation+0.076
floods
Token floods
Feature activation+0.000
,
Token,
Feature activation+0.000
disasters
Token disasters
Feature activation+0.000
bol
Tokenbol
Feature activation+0.000
hi
Tokenhi
Feature activation+0.000
declined
Token declined
Feature activation+0.000
comment
Token comment
Feature activation+0.000
for
Token for
Feature activation+0.080
this
Token this
Feature activation+2.860
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
told
Token told
Feature activation+0.139

INTERVAL 1.907 - 2.543
CONTAINS 0.003%

's
Token's
Feature activation+0.000
Lower
Token Lower
Feature activation+0.000
Dir
Token Dir
Feature activation+0.000
district
Token district
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+2.401
CNN
Token CNN
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
killed
Token killed
Feature activation+0.000
endez
Tokenendez
Feature activation+3.900
,
Token,
Feature activation+0.223
another
Token another
Feature activation+0.000
participant
Token participant
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+2.151
the
Token the
Feature activation+0.918
BBC
Token BBC
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
"
Token "
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
document
Token document
Feature activation+0.000
seen
Token seen
Feature activation+0.000
by
Token by
Feature activation+2.150
Ag
Token Ag
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
France
Token France
Feature activation+0.000
-
Token-
Feature activation+0.000
Pres
TokenPres
Feature activation+0.000
I
Token I
Feature activation+0.000
give
Token give
Feature activation+0.000
permission
Token permission
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
tells
Token tells
Feature activation+2.332
Al
Token Al
Feature activation+0.510
Jazeera
Token Jazeera
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
low
Tokenlow
Feature activation+0.000
pop
Token pop
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.394
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
went
Token went
Feature activation+0.000
outside
Token outside
Feature activation+0.000

INTERVAL 1.271 - 1.907
CONTAINS 0.005%

Ċ
TokenĊ
Feature activation+0.000
Con
TokenCon
Feature activation+0.000
way
Tokenway
Feature activation+0.000
,
Token,
Feature activation+0.039
speaking
Token speaking
Feature activation+0.000
to
Token to
Feature activation+1.376
Ro
Token Ro
Feature activation+0.000
vers
Tokenvers
Feature activation+0.000
Player
Token Player
Feature activation+0.000
HD
Token HD
Feature activation+0.000
,
Token,
Feature activation+0.000
goals
Token goals
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Manz
Token Manz
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
ila
Tokenila
Feature activation+0.000
told
Token told
Feature activation+1.312
the
Token the
Feature activation+0.183
Sport
Token Sport
Feature activation+0.000
bl
Tokenbl
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
et
Tokenet
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+1.654
unions
Token unions
Feature activation+0.000
are
Token are
Feature activation+0.000
concerned
Token concerned
Feature activation+0.000
the
Token the
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
Media
Token Media
Feature activation+0.000
caption
Token caption
Feature activation+0.735
Christian
Token Christian
Feature activation+0.000
Fraser
Token Fraser
Feature activation+1.339
says
Token says
Feature activation+0.000
barriers
Token barriers
Feature activation+0.000
and
Token and
Feature activation+0.000
armed
Token armed
Feature activation+0.000
men
Token men
Feature activation+0.000
since
Token since
Feature activation+0.000
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
Two
Token Two
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.685
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.312
chancellor
Token chancellor
Feature activation+0.000
and
Token and
Feature activation+0.000
shadow
Token shadow
Feature activation+0.033

INTERVAL 0.636 - 1.271
CONTAINS 0.012%

back
Token back
Feature activation+0.000
okay
Token okay
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Originally
TokenOriginally
Feature activation+0.704
published
Token published
Feature activation+0.773
as
Token as
Feature activation+0.000
Em
Token Em
Feature activation+0.000
otional
Tokenotional
Feature activation+0.000
UK
Token UK
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
officials
Token officials
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.723
Associated
Token Associated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
,
Token,
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
on
Token on
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.353
Ċ
TokenĊ
Feature activation+0.940
"
Token"
Feature activation+0.000
But
TokenBut
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
rely
Token rely
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.045
S
TokenS
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
Ibrahim
Token Ibrahim
Feature activation+0.464
,
Token,
Feature activation+0.994
an
Token an
Feature activation+0.000
activist
Token activist
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
public
Token public
Feature activation+0.000
since
Token since
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.995
Ċ
TokenĊ
Feature activation+0.873
This
TokenThis
Feature activation+0.888
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.000
political
Token political
Feature activation+0.000
vacuum
Token vacuum
Feature activation+0.000

INTERVAL 0.000 - 0.636
CONTAINS 99.977%

China
Token China
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
exchanges
Token exchanges
Feature activation+0.000
there
Token there
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
have
Tokenhave
Feature activation+0.000
very
Token very
Feature activation+0.000
high
Token high
Feature activation+0.000
retail
Token retail
Feature activation+0.000
use
Token use
Feature activation+0.000
that
Token that
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
hire
Token hire
Feature activation+0.000
a
Token a
Feature activation+0.000
snow
Token snow
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
ow
Tokenow
Feature activation+0.000
contractor
Token contractor
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Ghana
Token Ghana
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
capital
Token capital
Feature activation+0.000
,
Token,
Feature activation+0.000
Acc
Token Acc
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
-
Token-
Feature activation+0.000
century
Tokencentury
Feature activation+0.000
:
Token:
Feature activation+0.000
America
Token America
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
divest
Token divest
Feature activation+0.000
ment
Tokenment
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
affects
Token affects
Feature activation+0.000
overseas
Token overseas
Feature activation+0.000
talent
Token talent
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H10.6: (feature 5038)

TOP ACTIVATIONS
MAX = 4.686

,"
Token,"
Feature activation+2.588
Judge
Token Judge
Feature activation+0.801
Carm
Token Carm
Feature activation+0.000
ody
Tokenody
Feature activation+0.396
said
Token said
Feature activation+0.000
.
Token.
Feature activation+4.686
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.641
This
TokenThis
Feature activation+0.411
,
Token,
Feature activation+4.590
he
Token he
Feature activation+0.200
trauma
Token trauma
Feature activation+0.000
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
.
Token.
Feature activation+4.469
"
Token "
Feature activation+0.000
Your
TokenYour
Feature activation+1.391
prospects
Token prospects
Feature activation+0.000
of
Token of
Feature activation+0.000
rehabilitation
Token rehabilitation
Feature activation+0.000
told
Token told
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
News
TokenNews
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+4.118
"
Token "
Feature activation+0.000
My
TokenMy
Feature activation+0.000
members
Token members
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.451
I
Token I
Feature activation+0.173
give
Token give
Feature activation+0.000
permission
Token permission
Feature activation+0.000
,"
Token,"
Feature activation+3.432
she
Token she
Feature activation+1.602
tells
Token tells
Feature activation+0.118
Al
Token Al
Feature activation+0.000
Jazeera
Token Jazeera
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
District
Token District
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+3.301
Keith
Token Keith
Feature activation+0.000
Watkins
Token Watkins
Feature activation+0.000
.
Token.
Feature activation+0.060
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.047
of
Token of
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
.
Token.
Feature activation+3.290
He
Token He
Feature activation+0.348
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
concerned
Token concerned
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+1.928
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.815
In
TokenIn
Feature activation+0.092
fact
Token fact
Feature activation+2.236
,
Token,
Feature activation+3.243
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+1.716
has
Token has
Feature activation+1.476
precious
Token precious
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
ban
Token ban
Feature activation+3.138
Islamic
Token Islamic
Feature activation+0.407
law
Token law
Feature activation+0.725
.
Token.
Feature activation+0.868
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+1.437
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+3.114
resignation
Token resignation
Feature activation+0.000
is
Token is
Feature activation+0.000
enough
Token enough
Feature activation+0.000
.
Token.
Feature activation+1.218
He
Token He
Feature activation+0.000
time
Token time
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+2.831
The
TokenThe
Feature activation+0.000
judge
Token judge
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
in
Token in
Feature activation+0.000
orders
Token orders
Feature activation+0.000
.
Token.
Feature activation+1.394
Just
Token Just
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+2.519
,
Token,
Feature activation+2.808
Paul
Token Paul
Feature activation+0.073
Hans
Token Hans
Feature activation+0.000
meier
Tokenmeier
Feature activation+0.012
,
Token,
Feature activation+0.031
Paul
Token Paul
Feature activation+0.000
Times
Token Times
Feature activation+0.000
.
Token.
Feature activation+0.724
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.057
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+2.711
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
own
Token own
Feature activation+0.000
grandchildren
Token grandchildren
Feature activation+0.000
?
Token?
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.804
a
Token a
Feature activation+2.667
government
Token government
Feature activation+1.961
official
Token official
Feature activation+0.000
actually
Token actually
Feature activation+0.009
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.186
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.342
opinion
Token opinion
Feature activation+0.000
,
Token,
Feature activation+0.000
low
Token low
Feature activation+0.000
,"
Token,"
Feature activation+2.588
Judge
Token Judge
Feature activation+0.801
Carm
Token Carm
Feature activation+0.000
ody
Tokenody
Feature activation+0.396
said
Token said
Feature activation+0.000
.
Token.
Feature activation+4.686
existing
Token existing
Feature activation+0.000
wife
Token wife
Feature activation+0.000
agrees
Token agrees
Feature activation+0.000
.
Token.
Feature activation+1.419
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.584
"
Token"
Feature activation+0.000
If
TokenIf
Feature activation+0.000
the
Token the
Feature activation+0.194
wife
Token wife
Feature activation+0.000
agrees
Token agrees
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
previous
Token previous
Feature activation+0.000
partner
Token partner
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.558
11
Token11
Feature activation+2.239
She
Token She
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
sentenced
Token sentenced
Feature activation+0.000
sanction
Token sanction
Feature activation+0.000
orders
Token orders
Feature activation+0.000
.
Token.
Feature activation+1.394
Just
Token Just
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+2.519
,
Token,
Feature activation+2.808
Paul
Token Paul
Feature activation+0.073
Hans
Token Hans
Feature activation+0.000
meier
Tokenmeier
Feature activation+0.012
,
Token,
Feature activation+0.031
a
Token a
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
officer
Token officer
Feature activation+0.000
?
Token?
Feature activation+0.809
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.498
"
Token"
Feature activation+0.927
I
TokenI
Feature activation+0.000
'm
Token'm
Feature activation+0.014
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Quinn
Token Quinn
Feature activation+0.000
told
Token told
Feature activation+0.794
the
Token the
Feature activation+2.436
court
Token court
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
when
Token when
Feature activation+1.067
I
Token I
Feature activation+0.000
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.057
comply
Token comply
Feature activation+0.000
with
Token with
Feature activation+2.375
the
Token the
Feature activation+0.039
order
Token order
Feature activation+0.000
,
Token,
Feature activation+1.546
my
Token my
Feature activation+0.000
emails
Token emails
Feature activation+0.000

Top DFA by src position
MAX = 4.809

his
Token his
Feature activation-0.006
Top resid features:
actions
Token actions
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
But
Token But
Feature activation-0.034
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
Judge
Token Judge
Feature activation+3.240
Top resid features:
Carm
Token Carm
Feature activation+0.058
Top resid features:
ody
Tokenody
Feature activation+0.006
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
he
Token he
Feature activation-0.006
Top resid features:
his
Token his
Feature activation-0.004
Top resid features:
actions
Token actions
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
But
Token But
Feature activation-0.046
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
Judge
Token Judge
Feature activation+4.607
Top resid features:
Carm
Token Carm
Feature activation+0.050
Top resid features:
ody
Tokenody
Feature activation+0.014
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
he
Token he
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
local
Token local
Feature activation+0.002
Top resid features:
firefighters
Token firefighters
Feature activation-0.031
Top resid features:
union
Token union
Feature activation-0.039
Top resid features:
John
Token John
Feature activation-0.017
Top resid features:
Judge
Token Judge
Feature activation+4.809
Top resid features:
told
Token told
Feature activation-0.008
Top resid features:
Fox
Token Fox
Feature activation-0.002
Top resid features:
News
TokenNews
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
com
Tokencom
Feature activation-0.008
Top resid features:
hearing
Token hearing
Feature activation+0.059
Top resid features:
such
Token such
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
Judge
Token Judge
Feature activation+2.529
Top resid features:
N
Token N
Feature activation+0.033
Top resid features:
en
Tokenen
Feature activation-0.010
Top resid features:
ney
Tokenney
Feature activation-0.032
Top resid features:
says
Token says
Feature activation+0.015
Top resid features:
she
Token she
Feature activation-0.006
Top resid features:
U
Token U
Feature activation-0.018
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
S
TokenS
Feature activation+0.027
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
District
Token District
Feature activation+0.280
Top resid features:
Judge
Token Judge
Feature activation+3.684
Top resid features:
W
Token W
Feature activation-0.091
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Keith
Token Keith
Feature activation+0.000
Top resid features:
Watkins
Token Watkins
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.006
Top resid features:
actions
Token actions
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
But
Token But
Feature activation-0.048
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
Judge
Token Judge
Feature activation+3.542
Top resid features:
Carm
Token Carm
Feature activation+0.011
Top resid features:
ody
Tokenody
Feature activation+0.049
Top resid features:
said
Token said
Feature activation+0.037
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
he
Token he
Feature activation+0.012
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.065
Top resid features:
court
Token court
Feature activation+0.359
Top resid features:
judge
Token judge
Feature activation+2.659
Top resid features:
even
Token even
Feature activation-0.012
Top resid features:
though
Token though
Feature activation+0.007
Top resid features:
he
Token he
Feature activation-0.006
Top resid features:
has
Token has
Feature activation-0.002
Top resid features:
never
Token never
Feature activation-0.011
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
an
Token an
Feature activation-0.017
Top resid features:
Oklahoma
Token Oklahoma
Feature activation+0.008
Top resid features:
initiative
Token initiative
Feature activation-0.021
Top resid features:
barring
Token barring
Feature activation-0.006
Top resid features:
judges
Token judges
Feature activation+2.393
Top resid features:
there
Token there
Feature activation-0.012
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
considering
Token considering
Feature activation+0.016
Top resid features:
Islamic
Token Islamic
Feature activation+0.483
Top resid features:
law
Token law
Feature activation+0.126
Top resid features:
ana
Tokenana
Feature activation-0.027
Top resid features:
citizens
Token citizens
Feature activation-0.020
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
calling
Token calling
Feature activation-0.038
Top resid features:
for
Token for
Feature activation-0.008
Top resid features:
Judge
Token Judge
Feature activation+3.778
Top resid features:
B
Token B
Feature activation+0.024
Top resid features:
augh
Tokenaugh
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
resign
Token resign
Feature activation-0.206
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
local
Token local
Feature activation+0.004
Top resid features:
firefighters
Token firefighters
Feature activation-0.027
Top resid features:
union
Token union
Feature activation-0.019
Top resid features:
John
Token John
Feature activation-0.025
Top resid features:
Judge
Token Judge
Feature activation+3.639
Top resid features:
told
Token told
Feature activation-0.001
Top resid features:
Fox
Token Fox
Feature activation-0.004
Top resid features:
News
TokenNews
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
com
Tokencom
Feature activation-0.005
Top resid features:
Since
Token Since
Feature activation+0.001
Top resid features:
then
Token then
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
several
Token several
Feature activation-0.002
Top resid features:
other
Token other
Feature activation-0.018
Top resid features:
judges
Token judges
Feature activation+3.134
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
pounded
Token pounded
Feature activation-0.001
Top resid features:
Pre
Token Pre
Feature activation-0.148
Top resid features:
nda
Tokennda
Feature activation-0.019
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
United
Token United
Feature activation-0.029
Top resid features:
States
Token States
Feature activation+0.009
Top resid features:
Supreme
Token Supreme
Feature activation+0.042
Top resid features:
Court
Token Court
Feature activation+0.054
Top resid features:
judge
Token judge
Feature activation+2.924
Top resid features:
gets
Token gets
Feature activation-0.003
Top resid features:
involved
Token involved
Feature activation-0.035
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
political
Token political
Feature activation-0.029
Top resid features:
supposedly
Token supposedly
Feature activation+0.008
Top resid features:
free
Token free
Feature activation+0.021
Top resid features:
country
Token country
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
judge
Token judge
Feature activation+2.233
Top resid features:
can
Token can
Feature activation+0.001
Top resid features:
tell
Token tell
Feature activation+0.002
Top resid features:
someone
Token someone
Feature activation+0.012
Top resid features:
who
Token who
Feature activation+0.005
Top resid features:
hasn
Token hasn
Feature activation-0.003
Top resid features:
his
Token his
Feature activation-0.001
Top resid features:
actions
Token actions
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
But
Token But
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
Judge
Token Judge
Feature activation+2.939
Top resid features:
Carm
Token Carm
Feature activation+0.042
Top resid features:
ody
Tokenody
Feature activation+0.027
Top resid features:
said
Token said
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
hearing
Token hearing
Feature activation+0.014
Top resid features:
such
Token such
Feature activation-0.010
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
case
Token case
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Judge
Token Judge
Feature activation+2.235
Top resid features:
N
Token N
Feature activation+0.012
Top resid features:
en
Tokenen
Feature activation-0.000
Top resid features:
ney
Tokenney
Feature activation+0.037
Top resid features:
says
Token says
Feature activation+0.013
Top resid features:
she
Token she
Feature activation+0.005
Top resid features:
disclosed
Token disclosed
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
11
Token11
Feature activation+0.028
Top resid features:
Judge
Token Judge
Feature activation+2.737
Top resid features:
Ian
Token Ian
Feature activation+0.029
Top resid features:
Pr
Token Pr
Feature activation+0.084
Top resid features:
ingle
Tokeningle
Feature activation+0.005
Top resid features:
said
Token said
Feature activation+0.017
Top resid features:
it
Token it
Feature activation-0.005
Top resid features:
Since
Token Since
Feature activation-0.004
Top resid features:
then
Token then
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
several
Token several
Feature activation+0.002
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
judges
Token judges
Feature activation+2.719
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
pounded
Token pounded
Feature activation-0.000
Top resid features:
Pre
Token Pre
Feature activation-0.163
Top resid features:
nda
Tokennda
Feature activation-0.032
Top resid features:
with
Token with
Feature activation-0.000
Top resid features:
KEY
TokenKEY
Feature activation+0.078
Top resid features:
E
TokenE
Feature activation-0.006
Top resid features:
TV
Token TV
Feature activation-0.006
Top resid features:
asked
Token asked
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
judge
Token judge
Feature activation+1.865
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
he
Token he
Feature activation+0.012
Top resid features:
elected
Token elected
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.023
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
judge
Token judge
Feature activation+2.863
Top resid features:
who
Token who
Feature activation+0.087
Top resid features:
was
Token was
Feature activation+0.031
Top resid features:
behind
Token behind
Feature activation-0.012
Top resid features:
these
Token these
Feature activation-0.002
Top resid features:
threats
Token threats
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Basically
TokenBasically
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Judge
Token Judge
Feature activation+2.791
Top resid features:
Ellis
Token Ellis
Feature activation+0.216
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
who
Token who
Feature activation-0.002
Top resid features:
was
Token was
Feature activation-0.008
Top resid features:
overseeing
Token overseeing
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.05

Head 3: 0.04

Head 4: 0.04

Head 5: 0.03

Head 6: 0.43

Head 7: 0.11

Head 8: 0.02

Head 9: 0.07

Head 10: 0.05

Head 11: 0.06

Positive logits

Judge9.76

Judge9.14

judge8.95

Judges8.52

judges8.21

courtroom6.64

jud6.13

rulings6.00

judicial5.97

court5.85

courthouse5.77

judiciary5.67

jurors5.54

judging5.48

Judicial5.41

Jud5.39

Prosecut5.11

Court5.10

courts5.09

appellate5.08

Negative logits

ーク-3.24

marketers-2.98

ptives-2.72

diseng-2.70

cap-2.67

DATA-2.65

sponsored-2.63

gans-2.62

76561-2.58

CAP-2.56

productive-2.51

caps-2.51

Enterprises-2.48

323-2.42

enterprises-2.42

NIC-2.41

engagement-2.41

prov-2.40

sack-2.39

Cap-2.39

INTERVAL 4.217 - 4.686
CONTAINS 0.000%

trauma
Token trauma
Feature activation+0.000
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
.
Token.
Feature activation+4.469
"
Token "
Feature activation+0.000
Your
TokenYour
Feature activation+1.391
prospects
Token prospects
Feature activation+0.000
of
Token of
Feature activation+0.000
rehabilitation
Token rehabilitation
Feature activation+0.000
,"
Token,"
Feature activation+2.588
Judge
Token Judge
Feature activation+0.801
Carm
Token Carm
Feature activation+0.000
ody
Tokenody
Feature activation+0.396
said
Token said
Feature activation+0.000
.
Token.
Feature activation+4.686
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.641
This
TokenThis
Feature activation+0.411
,
Token,
Feature activation+4.590
he
Token he
Feature activation+0.200

INTERVAL 3.749 - 4.217
CONTAINS 0.000%

told
Token told
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
News
TokenNews
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+4.118
"
Token "
Feature activation+0.000
My
TokenMy
Feature activation+0.000
members
Token members
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000

INTERVAL 3.280 - 3.749
CONTAINS 0.000%

it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.451
I
Token I
Feature activation+0.173
give
Token give
Feature activation+0.000
permission
Token permission
Feature activation+0.000
,"
Token,"
Feature activation+3.432
she
Token she
Feature activation+1.602
tells
Token tells
Feature activation+0.118
Al
Token Al
Feature activation+0.000
Jazeera
Token Jazeera
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
District
Token District
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+3.301
Keith
Token Keith
Feature activation+0.000
Watkins
Token Watkins
Feature activation+0.000
.
Token.
Feature activation+0.060
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.047
of
Token of
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
.
Token.
Feature activation+3.290
He
Token He
Feature activation+0.348
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
concerned
Token concerned
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 2.812 - 3.280
CONTAINS 0.000%

ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+1.437
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+3.114
resignation
Token resignation
Feature activation+0.000
is
Token is
Feature activation+0.000
enough
Token enough
Feature activation+0.000
.
Token.
Feature activation+1.218
He
Token He
Feature activation+0.000
time
Token time
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+2.831
The
TokenThe
Feature activation+0.000
judge
Token judge
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
in
Token in
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
ban
Token ban
Feature activation+3.138
Islamic
Token Islamic
Feature activation+0.407
law
Token law
Feature activation+0.725
.
Token.
Feature activation+0.868
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
.
Token.
Feature activation+1.928
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.815
In
TokenIn
Feature activation+0.092
fact
Token fact
Feature activation+2.236
,
Token,
Feature activation+3.243
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+1.716
has
Token has
Feature activation+1.476
precious
Token precious
Feature activation+0.000

INTERVAL 2.343 - 2.812
CONTAINS 0.001%

,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Quinn
Token Quinn
Feature activation+0.000
told
Token told
Feature activation+0.794
the
Token the
Feature activation+2.436
court
Token court
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
sanction
Token sanction
Feature activation+0.000
orders
Token orders
Feature activation+0.000
.
Token.
Feature activation+1.394
Just
Token Just
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+2.519
,
Token,
Feature activation+2.808
Paul
Token Paul
Feature activation+0.073
Hans
Token Hans
Feature activation+0.000
meier
Tokenmeier
Feature activation+0.012
,
Token,
Feature activation+0.031
Times
Token Times
Feature activation+0.000
.
Token.
Feature activation+0.724
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.057
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+2.711
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
previous
Token previous
Feature activation+0.000
partner
Token partner
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.558
11
Token11
Feature activation+2.239
She
Token She
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
sentenced
Token sentenced
Feature activation+0.000
own
Token own
Feature activation+0.000
grandchildren
Token grandchildren
Feature activation+0.000
?
Token?
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.804
a
Token a
Feature activation+2.667
government
Token government
Feature activation+1.961
official
Token official
Feature activation+0.000
actually
Token actually
Feature activation+0.009
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.186

INTERVAL 1.874 - 2.343
CONTAINS 0.002%

found
Token found
Feature activation+0.000
unconstitutional
Token unconstitutional
Feature activation+0.000
because
Token because
Feature activation+2.065
it
Token it
Feature activation+0.000
singles
Token singles
Feature activation+1.586
out
Token out
Feature activation+1.998
Islam
Token Islam
Feature activation+0.000
for
Token for
Feature activation+0.017
discrimination
Token discrimination
Feature activation+0.000
.
Token.
Feature activation+0.341
The
Token The
Feature activation+0.000
other
Token other
Feature activation+0.000
family
Token family
Feature activation+0.000
members
Token members
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
directly
Token directly
Feature activation+0.000
to
Token to
Feature activation+1.905
Fin
Token Fin
Feature activation+0.000
ney
Tokenney
Feature activation+0.000
,
Token,
Feature activation+0.000
encouraging
Token encouraging
Feature activation+0.000
him
Token him
Feature activation+0.000
judge
Token judge
Feature activation+0.034
.
Token.
Feature activation+1.928
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.815
In
TokenIn
Feature activation+0.092
fact
Token fact
Feature activation+2.236
,
Token,
Feature activation+3.243
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+1.716
has
Token has
Feature activation+1.476
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.179
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
judge
Token judge
Feature activation+0.034
.
Token.
Feature activation+1.928
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.815
In
TokenIn
Feature activation+0.092
fact
Token fact
Feature activation+2.236
,
Token,
Feature activation+3.243
the
Token the
Feature activation+0.196
advice
Token advice
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
interrog
Token interrog
Feature activation+0.000
ate
Tokenate
Feature activation+2.179
him
Token him
Feature activation+0.000
without
Token without
Feature activation+0.000
counsel
Token counsel
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.406 - 1.874
CONTAINS 0.005%

fact
Token fact
Feature activation+2.236
,
Token,
Feature activation+3.243
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+1.716
has
Token has
Feature activation+1.476
precious
Token precious
Feature activation+0.000
little
Token little
Feature activation+0.988
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.582
way
Token way
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
disgrace
Token disgrace
Feature activation+0.000
to
Token to
Feature activation+1.443
the
Token the
Feature activation+0.762
court
Token court
Feature activation+0.084
,
Token,
Feature activation+0.349
and
Token and
Feature activation+0.009
I
Token I
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
judge
Token judge
Feature activation+0.032
Gerald
Token Gerald
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
Dav
Token Dav
Feature activation+0.000
ison
Tokenison
Feature activation+1.841
yesterday
Token yesterday
Feature activation+0.739
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
buy
Token buy
Feature activation+0.000
the
Token the
Feature activation+0.367
to
Token to
Feature activation+0.249
resign
Token resign
Feature activation+0.000
.
Token.
Feature activation+0.796
Frank
Token Frank
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+1.437
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+3.114
resignation
Token resignation
Feature activation+0.000
,
Token,
Feature activation+0.451
I
Token I
Feature activation+0.173
give
Token give
Feature activation+0.000
permission
Token permission
Feature activation+0.000
,"
Token,"
Feature activation+3.432
she
Token she
Feature activation+1.602
tells
Token tells
Feature activation+0.118
Al
Token Al
Feature activation+0.000
Jazeera
Token Jazeera
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.937 - 1.406
CONTAINS 0.010%

to
Token to
Feature activation+0.828
offic
Token offic
Feature activation+0.000
iate
Tokeniate
Feature activation+0.275
marriages
Token marriages
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+1.140
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
minister
Token minister
Feature activation+0.036
,
Token,
Feature activation+0.000
priest
Token priest
Feature activation+0.000
said
Token said
Feature activation+1.057
that
Token that
Feature activation+1.013
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
convinced
Token convinced
Feature activation+1.075
that
Token that
Feature activation+1.003
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.452
only
Token only
Feature activation+0.000
way
Token way
Feature activation+0.000
's
Token's
Feature activation+0.000
story
Token story
Feature activation+0.000
.
Token.
Feature activation+0.168
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.602
"
Token"
Feature activation+0.939
You
TokenYou
Feature activation+0.000
have
Token have
Feature activation+0.903
been
Token been
Feature activation+1.188
caught
Token caught
Feature activation+0.000
not
Token not
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+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+1.179
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.871
the
Token the
Feature activation+0.169
initiative
Token initiative
Feature activation+0.000
The
Token The
Feature activation+0.807
Deputy
Token Deputy
Feature activation+0.502
state
Token state
Feature activation+0.257
secretary
Token secretary
Feature activation+0.000
said
Token said
Feature activation+1.057
that
Token that
Feature activation+1.013
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
convinced
Token convinced
Feature activation+1.075
that
Token that
Feature activation+1.003
it
Token it
Feature activation+0.000

INTERVAL 0.469 - 0.937
CONTAINS 0.019%

Scale
TokenScale
Feature activation+0.000
.
Token.
Feature activation+0.000
Com
TokenCom
Feature activation+0.000
,
Token,
Feature activation+0.320
the
Token the
Feature activation+0.093
average
Token average
Feature activation+0.603
national
Token national
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
bonuses
Token bonuses
Feature activation+0.000
issued
Token issued
Feature activation+0.000
her
Token her
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
passport
Token passport
Feature activation+0.000
.
Token.
Feature activation+0.724
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.454
The
TokenThe
Feature activation+1.146
Somalia
Token Somalia
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
personal
Token personal
Feature activation+0.000
experiences
Token experiences
Feature activation+0.180
of
Token of
Feature activation+0.971
nearly
Token nearly
Feature activation+0.000
150
Token 150
Feature activation+0.603
lawyers
Token lawyers
Feature activation+0.000
,
Token,
Feature activation+0.068
witnesses
Token witnesses
Feature activation+0.000
,
Token,
Feature activation+0.000
victims
Token victims
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
wishes
Token wishes
Feature activation+0.000
.
Token.
Feature activation+0.460
How
Token How
Feature activation+0.000
can
Token can
Feature activation+0.504
the
Token the
Feature activation+0.092
court
Token court
Feature activation+0.000
determine
Token determine
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
Court
Token Court
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+1.179
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.871
the
Token the
Feature activation+0.169
initiative
Token initiative
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
found
Token found
Feature activation+0.000

INTERVAL 0.000 - 0.469
CONTAINS 99.962%

2016
Token 2016
Feature activation+0.000
I
Token I
Feature activation+0.000
acquired
Token acquired
Feature activation+0.000
the
Token the
Feature activation+0.000
Cyprus
Token Cyprus
Feature activation+0.000
citizenship
Token citizenship
Feature activation+0.000
by
Token by
Feature activation+0.000
investment
Token investment
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
and
Token and
Feature activation+0.000
presently
Token presently
Feature activation+0.000
(
Token (
Feature activation+0.000
can
Tokencan
Feature activation+0.000
't
Token't
Feature activation+0.000
blame
Token blame
Feature activation+0.000
you
Token you
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
version
Token version
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
courage
Token courage
Feature activation+0.000
and
Token and
Feature activation+0.000
complexity
Token complexity
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
mission
Token mission
Feature activation+0.000
:
Token:
Feature activation+0.000
take
Token take
Feature activation+0.000
captive
Token captive
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
inc
Token inc
Feature activation+0.000
ogn
Tokenogn
Feature activation+0.000
ito
Tokenito
Feature activation+0.000
live
Token live
Feature activation+0.000
system
Token system
Feature activation+0.000
continues
Token continues
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000
January
Token January
Feature activation+0.000
13
Token 13
Feature activation+0.000
to
Token to
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
ice
Token ice
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
recent
Token recent
Feature activation+0.000
statistics
Token statistics
Feature activation+0.000
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H10.6: (feature 17854)

TOP ACTIVATIONS
MAX = 7.137

the
Token the
Feature activation+1.947
wife
Token wife
Feature activation+0.376
of
Token of
Feature activation+1.246
Senate
Token Senate
Feature activation+0.460
Majority
Token Majority
Feature activation+0.179
Leader
Token Leader
Feature activation+7.137
Mitch
Token Mitch
Feature activation+1.555
McConnell
Token McConnell
Feature activation+0.000
,
Token,
Feature activation+0.801
for
Token for
Feature activation+1.299
Secretary
Token Secretary
Feature activation+0.000
video
Token video
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.322
Senate
TokenSenate
Feature activation+1.234
Majority
Token Majority
Feature activation+1.124
Leader
Token Leader
Feature activation+6.218
Mitch
Token Mitch
Feature activation+1.429
McConnell
Token McConnell
Feature activation+0.209
,
Token,
Feature activation+0.317
R
Token R
Feature activation+0.000
-
Token-
Feature activation+0.000
at
Token at
Feature activation+0.000
odds
Token odds
Feature activation+0.000
with
Token with
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
majority
Token majority
Feature activation+0.139
leader
Token leader
Feature activation+5.737
Mitch
Token Mitch
Feature activation+2.442
McConnell
Token McConnell
Feature activation+0.000
Add
Token Add
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
(
Token (
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
senator
Token senator
Feature activation+0.000
,
Token,
Feature activation+5.725
Bob
Token Bob
Feature activation+3.209
Men
Token Men
Feature activation+0.000
endez
Tokenendez
Feature activation+0.000
of
Token of
Feature activation+0.000
New
Token New
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sen
TokenSen
Feature activation+0.000
.
Token.
Feature activation+3.616
Bob
Token Bob
Feature activation+5.604
Men
Token Men
Feature activation+0.000
endez
Tokenendez
Feature activation+0.412
addresses
Token addresses
Feature activation+1.232
a
Token a
Feature activation+1.167
gathering
Token gathering
Feature activation+0.000
this
Token this
Feature activation+0.000
morning
Token morning
Feature activation+0.000
when
Token when
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+2.620
John
Token John
Feature activation+5.446
McCain
Token McCain
Feature activation+0.000
grew
Token grew
Feature activation+0.000
frustrated
Token frustrated
Feature activation+0.000
with
Token with
Feature activation+0.000
host
Token host
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+5.368
Richard
Token Richard
Feature activation+3.788
Blumenthal
Token Blumenthal
Feature activation+0.110
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
sponsor
Token sponsor
Feature activation+2.914
Sen
Token Sen
Feature activation+0.056
.
Token.
Feature activation+3.813
Pat
Token Pat
Feature activation+5.345
To
Token To
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
y
Tokeny
Feature activation+0.191
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
took
Token took
Feature activation+0.000
him
Token him
Feature activation+0.000
off
Token off
Feature activation+4.218
of
Token of
Feature activation+5.295
the
Token the
Feature activation+4.558
senate
Token senate
Feature activation+1.217
judiciary
Token judiciary
Feature activation+0.182
committee
Token committee
Feature activation+0.000
.
Token.
Feature activation+2.569
M
TokenM
Feature activation+0.000
d
Tokend
Feature activation+0.000
.)
Token.)
Feature activation+0.000
and
Token and
Feature activation+0.372
Sen
Token Sen
Feature activation+0.287
.
Token.
Feature activation+5.099
Elizabeth
Token Elizabeth
Feature activation+2.675
Warren
Token Warren
Feature activation+0.687
Elizabeth
Token Elizabeth
Feature activation+0.000
Ann
Token Ann
Feature activation+0.992
Warren
Token Warren
Feature activation+0.072
.
Token.
Feature activation+0.858
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.358
Sen
TokenSen
Feature activation+0.350
.
Token.
Feature activation+3.838
Ben
Token Ben
Feature activation+5.098
S
Token S
Feature activation+0.593
asse
Tokenasse
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Senate
Token Senate
Feature activation+0.246
seat
Token seat
Feature activation+0.673
occupied
Token occupied
Feature activation+0.000
by
Token by
Feature activation+3.414
Democratic
Token Democratic
Feature activation+2.262
icon
Token icon
Feature activation+5.077
Robert
Token Robert
Feature activation+2.490
F
Token F
Feature activation+0.052
.
Token.
Feature activation+1.038
Kennedy
Token Kennedy
Feature activation+0.000
.
Token.
Feature activation+0.432
't
Token't
Feature activation+0.527
backing
Token backing
Feature activation+1.635
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
as
Token as
Feature activation+5.054
Senate
Token Senate
Feature activation+1.382
GOP
Token GOP
Feature activation+2.945
leaders
Token leaders
Feature activation+0.000
announced
Token announced
Feature activation+0.777
his
Token his
Feature activation+1.263
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
Senators
Token Senators
Feature activation+4.023
Carl
Token Carl
Feature activation+4.421
Levin
Token Levin
Feature activation+0.000
and
Token and
Feature activation+5.011
John
Token John
Feature activation+4.878
McCain
Token McCain
Feature activation+0.173
confirming
Token confirming
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Token s
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
association
Token association
Feature activation+0.000
wrote
Token wrote
Feature activation+0.860
to
Token to
Feature activation+5.002
Mul
Token Mul
Feature activation+0.000
v
Tokenv
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
needs
Token needs
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sen
TokenSen
Feature activation+0.000
.
Token.
Feature activation+3.272
John
Token John
Feature activation+4.988
McCain
Token McCain
Feature activation+0.000
John
Token John
Feature activation+0.000
Sidney
Token Sidney
Feature activation+0.000
McCain
Token McCain
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
Sen
Token Sen
Feature activation+0.260
.
Token.
Feature activation+4.985
Lindsey
Token Lindsey
Feature activation+1.528
Graham
Token Graham
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.079
WASHINGTON
TokenWASHINGTON
Feature activation+2.032
âĢĵ
Token âĢĵ
Feature activation+3.600
Tea
Token Tea
Feature activation+0.000
party
Token party
Feature activation+2.211
favorite
Token favorite
Feature activation+4.921
Sen
Token Sen
Feature activation+2.886
.
Token.
Feature activation+4.797
Rand
Token Rand
Feature activation+2.868
Paul
Token Paul
Feature activation+0.388
(
Token (
Feature activation+0.000
to
Token to
Feature activation+0.000
Senators
Token Senators
Feature activation+4.023
Carl
Token Carl
Feature activation+4.421
Levin
Token Levin
Feature activation+0.000
and
Token and
Feature activation+5.011
John
Token John
Feature activation+4.878
McCain
Token McCain
Feature activation+0.173
confirming
Token confirming
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Token s
Feature activation+0.000
arin
Tokenarin
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
H
TokenH
Feature activation+0.000
.),
Token.),
Feature activation+4.819
Amy
Token Amy
Feature activation+2.120
Kl
Token Kl
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
uch
Tokenuch
Feature activation+0.000
ar
Tokenar
Feature activation+0.000

Top DFA by src position
MAX = 7.504

Chao
Token Chao
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wife
Token wife
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Senate
Token Senate
Feature activation+7.504
Top resid features:
Majority
Token Majority
Feature activation+0.188
Top resid features:
Leader
Token Leader
Feature activation+0.039
Top resid features:
Mitch
Token Mitch
Feature activation+0.000
Top resid features:
McConnell
Token McConnell
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
video
Token video
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Senate
TokenSenate
Feature activation+5.575
Top resid features:
Majority
Token Majority
Feature activation+0.832
Top resid features:
Leader
Token Leader
Feature activation+0.102
Top resid features:
Mitch
Token Mitch
Feature activation+0.000
Top resid features:
McConnell
Token McConnell
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
putting
Token putting
Feature activation+0.001
Top resid features:
him
Token him
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
odds
Token odds
Feature activation+0.008
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
Senate
Token Senate
Feature activation+6.037
Top resid features:
majority
Token majority
Feature activation+0.072
Top resid features:
leader
Token leader
Feature activation+0.087
Top resid features:
Mitch
Token Mitch
Feature activation+0.000
Top resid features:
McConnell
Token McConnell
Feature activation+0.000
Top resid features:
Add
Token Add
Feature activation+0.000
Top resid features:
On
TokenOn
Feature activation+0.002
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.004
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
second
Token second
Feature activation-0.002
Top resid features:
Democratic
Token Democratic
Feature activation-0.238
Top resid features:
senator
Token senator
Feature activation+6.193
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
Bob
Token Bob
Feature activation+0.000
Top resid features:
Men
Token Men
Feature activation+0.000
Top resid features:
endez
Tokenendez
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ite
Tokenite
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
com
Tokencom
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.052
Top resid features:
Sen
TokenSen
Feature activation+2.743
Top resid features:
.
Token.
Feature activation+3.211
Top resid features:
Bob
Token Bob
Feature activation+0.020
Top resid features:
Men
Token Men
Feature activation+0.000
Top resid features:
endez
Tokenendez
Feature activation+0.000
Top resid features:
addresses
Token addresses
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Press
Token Press
Feature activation-0.074
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
morning
Token morning
Feature activation+0.005
Top resid features:
when
Token when
Feature activation+0.001
Top resid features:
Sen
Token Sen
Feature activation+1.181
Top resid features:
.
Token.
Feature activation+4.396
Top resid features:
John
Token John
Feature activation+0.228
Top resid features:
McCain
Token McCain
Feature activation+0.000
Top resid features:
grew
Token grew
Feature activation+0.000
Top resid features:
frustrated
Token frustrated
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ŀ
TokenĿ
Feature activation-0.000
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
Sen
Token Sen
Feature activation+2.262
Top resid features:
.
Token.
Feature activation+3.695
Top resid features:
Richard
Token Richard
Feature activation+0.000
Top resid features:
Blumenthal
Token Blumenthal
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
D
TokenD
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:
2011
Token 2011
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Bill
Token Bill
Feature activation+0.001
Top resid features:
sponsor
Token sponsor
Feature activation+0.084
Top resid features:
Sen
Token Sen
Feature activation+3.079
Top resid features:
.
Token.
Feature activation+1.843
Top resid features:
Pat
Token Pat
Feature activation-0.008
Top resid features:
To
Token To
Feature activation+0.000
Top resid features:
ome
Tokenome
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
been
Token been
Feature activation-0.002
Top resid features:
removed
Token removed
Feature activation-0.006
Top resid features:
from
Token from
Feature activation-0.007
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
Senate
Token Senate
Feature activation+3.612
Top resid features:
committee
Token committee
Feature activation+0.514
Top resid features:
because
Token because
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
anti
Token anti
Feature activation+0.009
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
M
TokenM
Feature activation+0.002
Top resid features:
d
Tokend
Feature activation+0.000
Top resid features:
.)
Token.)
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.069
Top resid features:
Sen
Token Sen
Feature activation+2.007
Top resid features:
.
Token.
Feature activation+3.590
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.000
Top resid features:
Warren
Token Warren
Feature activation+0.000
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.000
Top resid features:
Ann
Token Ann
Feature activation+0.000
Top resid features:
Warren
Token Warren
Feature activation+0.000
Top resid features:
without
Token without
Feature activation-0.001
Top resid features:
coverage
Token coverage
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Sen
TokenSen
Feature activation+3.163
Top resid features:
.
Token.
Feature activation+1.929
Top resid features:
Ben
Token Ben
Feature activation-0.033
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
asse
Tokenasse
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Brock
Token Brock
Feature activation-0.010
Top resid features:
adds
Token adds
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
Senate
Token Senate
Feature activation+5.591
Top resid features:
seat
Token seat
Feature activation+0.023
Top resid features:
occupied
Token occupied
Feature activation-0.012
Top resid features:
by
Token by
Feature activation+0.039
Top resid features:
Democratic
Token Democratic
Feature activation-0.101
Top resid features:
icon
Token icon
Feature activation+0.027
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
removed
Token removed
Feature activation-0.008
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
Senate
Token Senate
Feature activation+4.179
Top resid features:
committee
Token committee
Feature activation+0.455
Top resid features:
because
Token because
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
anti
Token anti
Feature activation+0.019
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
letter
Token letter
Feature activation+0.000
Top resid features:
(.
Token (.
Feature activation+0.004
Top resid features:
pdf
Tokenpdf
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
Senators
Token Senators
Feature activation+5.228
Top resid features:
Carl
Token Carl
Feature activation+0.184
Top resid features:
Levin
Token Levin
Feature activation+0.027
Top resid features:
and
Token and
Feature activation+0.165
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
McCain
Token McCain
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
letter
Token letter
Feature activation+0.008
Top resid features:
this
Token this
Feature activation+0.009
Top resid features:
week
Token week
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
senators
Token senators
Feature activation+5.417
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
White
Token White
Feature activation+0.082
Top resid features:
House
Token House
Feature activation-0.055
Top resid features:
budget
Token budget
Feature activation+0.012
Top resid features:
medical
Token medical
Feature activation+0.000
Top resid features:
needs
Token needs
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.074
Top resid features:
Sen
TokenSen
Feature activation+0.903
Top resid features:
.
Token.
Feature activation+4.151
Top resid features:
John
Token John
Feature activation+0.268
Top resid features:
McCain
Token McCain
Feature activation+0.000
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
Sidney
Token Sidney
Feature activation+0.000
Top resid features:
McCain
Token McCain
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.005
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
told
Token told
Feature activation+0.006
Top resid features:
Sen
Token Sen
Feature activation+2.173
Top resid features:
.
Token.
Feature activation+3.176
Top resid features:
Lindsey
Token Lindsey
Feature activation+0.000
Top resid features:
Graham
Token Graham
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
final
Token final
Feature activation-0.000
Top resid features:
judgment
Token judgment
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.050
Top resid features:
Senator
TokenSenator
Feature activation+5.319
Top resid features:
dec
Token dec
Feature activation-0.032
Top resid features:
ries
Tokenries
Feature activation-0.003
Top resid features:
US
Token US
Feature activation+0.014
Top resid features:
aid
Token aid
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
letter
Token letter
Feature activation+0.000
Top resid features:
(.
Token (.
Feature activation-0.002
Top resid features:
pdf
Tokenpdf
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
Senators
Token Senators
Feature activation+4.486
Top resid features:
Carl
Token Carl
Feature activation+0.089
Top resid features:
Levin
Token Levin
Feature activation+0.021
Top resid features:
and
Token and
Feature activation+0.717
Top resid features:
John
Token John
Feature activation+0.044
Top resid features:
McCain
Token McCain
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
group
Token group
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
Sens
Token Sens
Feature activation+2.108
Top resid features:
.
Token.
Feature activation+2.722
Top resid features:
Lisa
Token Lisa
Feature activation+0.019
Top resid features:
Mur
Token Mur
Feature activation-0.035
Top resid features:
kowski
Tokenkowski
Feature activation+0.051
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
R
TokenR
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.05

Head 3: 0.08

Head 4: 0.06

Head 5: 0.02

Head 6: 0.43

Head 7: 0.09

Head 8: 0.02

Head 9: 0.05

Head 10: 0.04

Head 11: 0.05

Positive logits

senators8.57

Senate8.35

Senate8.25

Senator7.92

senator7.73

Senators7.62

Senator7.58

Sen7.54

Sen7.13

senate7.02

filibuster6.57

filib5.99

SEN5.76

Corker5.13

Sens4.93

McConnell4.89

Feinstein4.89

Judiciary4.83

Grassley4.74

Majority4.66

Negative logits

Clicker-3.33

Cop-3.06

manuals-2.70

Beckham-2.67

spr-2.65

Spo-2.64

eele-2.63

emet-2.60

ebook-2.60

tabl-2.59

Pep-2.55

Blessing-2.54

Enix-2.50

Ubisoft-2.48

Peel-2.47

Grimoire-2.45

bnb-2.43

?????--2.43

vertisements-2.41

illon-2.40

INTERVAL 6.423 - 7.137
CONTAINS 0.000%

the
Token the
Feature activation+1.947
wife
Token wife
Feature activation+0.376
of
Token of
Feature activation+1.246
Senate
Token Senate
Feature activation+0.460
Majority
Token Majority
Feature activation+0.179
Leader
Token Leader
Feature activation+7.137
Mitch
Token Mitch
Feature activation+1.555
McConnell
Token McConnell
Feature activation+0.000
,
Token,
Feature activation+0.801
for
Token for
Feature activation+1.299
Secretary
Token Secretary
Feature activation+0.000

INTERVAL 5.709 - 6.423
CONTAINS 0.000%

Tuesday
Token Tuesday
Feature activation+0.000
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
senator
Token senator
Feature activation+0.000
,
Token,
Feature activation+5.725
Bob
Token Bob
Feature activation+3.209
Men
Token Men
Feature activation+0.000
endez
Tokenendez
Feature activation+0.000
of
Token of
Feature activation+0.000
New
Token New
Feature activation+0.000
at
Token at
Feature activation+0.000
odds
Token odds
Feature activation+0.000
with
Token with
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
majority
Token majority
Feature activation+0.139
leader
Token leader
Feature activation+5.737
Mitch
Token Mitch
Feature activation+2.442
McConnell
Token McConnell
Feature activation+0.000
Add
Token Add
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
(
Token (
Feature activation+0.000
video
Token video
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.322
Senate
TokenSenate
Feature activation+1.234
Majority
Token Majority
Feature activation+1.124
Leader
Token Leader
Feature activation+6.218
Mitch
Token Mitch
Feature activation+1.429
McConnell
Token McConnell
Feature activation+0.209
,
Token,
Feature activation+0.317
R
Token R
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 4.996 - 5.709
CONTAINS 0.001%

M
TokenM
Feature activation+0.000
d
Tokend
Feature activation+0.000
.)
Token.)
Feature activation+0.000
and
Token and
Feature activation+0.372
Sen
Token Sen
Feature activation+0.287
.
Token.
Feature activation+5.099
Elizabeth
Token Elizabeth
Feature activation+2.675
Warren
Token Warren
Feature activation+0.687
Elizabeth
Token Elizabeth
Feature activation+0.000
Ann
Token Ann
Feature activation+0.992
Warren
Token Warren
Feature activation+0.072
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+5.368
Richard
Token Richard
Feature activation+3.788
Blumenthal
Token Blumenthal
Feature activation+0.110
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sen
TokenSen
Feature activation+0.000
.
Token.
Feature activation+3.616
Bob
Token Bob
Feature activation+5.604
Men
Token Men
Feature activation+0.000
endez
Tokenendez
Feature activation+0.412
addresses
Token addresses
Feature activation+1.232
a
Token a
Feature activation+1.167
gathering
Token gathering
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
took
Token took
Feature activation+0.000
him
Token him
Feature activation+0.000
off
Token off
Feature activation+4.218
of
Token of
Feature activation+5.295
the
Token the
Feature activation+4.558
senate
Token senate
Feature activation+1.217
judiciary
Token judiciary
Feature activation+0.182
committee
Token committee
Feature activation+0.000
.
Token.
Feature activation+2.569
.
Token.
Feature activation+0.858
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.358
Sen
TokenSen
Feature activation+0.350
.
Token.
Feature activation+3.838
Ben
Token Ben
Feature activation+5.098
S
Token S
Feature activation+0.593
asse
Tokenasse
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 4.282 - 4.996
CONTAINS 0.003%

(.
Token (.
Feature activation+0.000
pdf
Tokenpdf
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
Senators
Token Senators
Feature activation+4.023
Carl
Token Carl
Feature activation+4.421
Levin
Token Levin
Feature activation+0.000
and
Token and
Feature activation+5.011
John
Token John
Feature activation+4.878
McCain
Token McCain
Feature activation+0.173
confirming
Token confirming
Feature activation+0.000
-
Token-
Feature activation+0.000
commerce
Tokencommerce
Feature activation+0.000
giant
Token giant
Feature activation+0.000
.
Token.
Feature activation+1.475
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.639
The
TokenThe
Feature activation+1.552
Senate
Token Senate
Feature activation+0.241
on
Token on
Feature activation+0.663
Monday
Token Monday
Feature activation+0.887
approved
Token approved
Feature activation+1.845
Michael
Token Michael
Feature activation+3.987
W
Token W
Feature activation+0.000
add
Tokenadd
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
ps
Tokenps
Feature activation+0.562
says
Token says
Feature activation+4.396
he
Token he
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+1.027
take
Token take
Feature activation+0.442
the
Token the
Feature activation+2.745
the
Token the
Feature activation+0.089
bipartisan
Token bipartisan
Feature activation+0.000
duo
Token duo
Feature activation+0.000
of
Token of
Feature activation+0.000
Sens
Token Sens
Feature activation+0.000
.
Token.
Feature activation+4.705
Joe
Token Joe
Feature activation+3.183
Man
Token Man
Feature activation+0.214
chin
Tokenchin
Feature activation+0.000
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
needs
Token needs
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sen
TokenSen
Feature activation+0.000
.
Token.
Feature activation+3.272
John
Token John
Feature activation+4.988
McCain
Token McCain
Feature activation+0.000
John
Token John
Feature activation+0.000
Sidney
Token Sidney
Feature activation+0.000
McCain
Token McCain
Feature activation+0.000
GOP
TokenGOP
Feature activation+0.000

INTERVAL 3.568 - 4.282
CONTAINS 0.004%

political
Token political
Feature activation+0.000
action
Token action
Feature activation+0.000
committee
Token committee
Feature activation+0.000
for
Token for
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+4.158
Kirst
Token Kirst
Feature activation+1.876
en
Tokenen
Feature activation+2.351
Gill
Token Gill
Feature activation+0.356
ibr
Tokenibr
Feature activation+0.000
and
Tokenand
Feature activation+0.565
island
Token island
Feature activation+0.000
were
Token were
Feature activation+0.000
on
Token on
Feature activation+1.021
hand
Token hand
Feature activation+0.000
to
Token to
Feature activation+0.000
witness
Token witness
Feature activation+3.686
the
Token the
Feature activation+1.227
moment
Token moment
Feature activation+1.071
.
Token.
Feature activation+2.386
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.077
add
Tokenadd
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
took
Token took
Feature activation+0.000
him
Token him
Feature activation+0.000
off
Token off
Feature activation+4.218
of
Token of
Feature activation+5.295
the
Token the
Feature activation+4.558
senate
Token senate
Feature activation+1.217
judiciary
Token judiciary
Feature activation+0.182
committee
Token committee
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.743
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.209
I
TokenI
Feature activation+0.000
applaud
Token applaud
Feature activation+3.717
the
Token the
Feature activation+1.504
mayor
Token mayor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.365
officially
Token officially
Feature activation+0.389
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
elected
Tokenelected
Feature activation+0.663
to
Token to
Feature activation+2.832
the
Token the
Feature activation+3.820
12
Token 12
Feature activation+0.000
th
Tokenth
Feature activation+1.414
and
Token and
Feature activation+0.059
final
Token final
Feature activation+0.652
spot
Token spot
Feature activation+0.000

INTERVAL 2.855 - 3.568
CONTAINS 0.009%

un
Tokenun
Feature activation+0.000
constitutional
Tokenconstitutional
Feature activation+0.000
.
Token.
Feature activation+1.823
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.633
Under
Token Under
Feature activation+3.294
the
Token the
Feature activation+2.432
House
Token House
Feature activation+0.446
bill
Token bill
Feature activation+0.051
,
Token,
Feature activation+0.000
Native
Token Native
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+0.263
coincidence
Token coincidence
Feature activation+1.936
that
Token that
Feature activation+3.540
women
Token women
Feature activation+3.662
were
Token were
Feature activation+0.912
so
Token so
Feature activation+0.959
heavily
Token heavily
Feature activation+0.586
involved
Token involved
Feature activation+0.000
.
Token.
Feature activation+0.217
Please
Token Please
Feature activation+0.000
pray
Token pray
Feature activation+0.000
for
Token for
Feature activation+1.491
me
Token me
Feature activation+0.000
,"
Token,"
Feature activation+3.056
De
Token De
Feature activation+0.000
Lima
Token Lima
Feature activation+0.000
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+0.000
outside
Token outside
Feature activation+1.182
Senate
Token Senate
Feature activation+2.121
has
Token has
Feature activation+2.022
not
Token not
Feature activation+2.769
yet
Token yet
Feature activation+2.788
taken
Token taken
Feature activation+0.420
up
Token up
Feature activation+2.979
the
Token the
Feature activation+1.809
subject
Token subject
Feature activation+0.000
but
Token but
Feature activation+2.740
if
Token if
Feature activation+3.751
it
Token it
Feature activation+0.585
Ċ
TokenĊ
Feature activation+0.464
(
Token(
Feature activation+0.000
Also
Token Also
Feature activation+0.000
on
Token on
Feature activation+0.000
POLITICO
Token POLITICO
Feature activation+0.000
:
Token:
Feature activation+3.458
Gang
Token Gang
Feature activation+0.136
of
Token of
Feature activation+0.014
Eight
Token Eight
Feature activation+1.626
introduces
Token introduces
Feature activation+1.782
'
Token '
Feature activation+1.893

INTERVAL 2.141 - 2.855
CONTAINS 0.016%

manship
Tokenmanship
Feature activation+0.000
by
Token by
Feature activation+1.972
the
Token the
Feature activation+0.410
new
Token new
Feature activation+1.008
class
Token class
Feature activation+0.000
of
Token of
Feature activation+2.287
House
Token House
Feature activation+0.175
Republicans
Token Republicans
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
brought
Token brought
Feature activation+1.554
about
Token about
Feature activation+1.589
a
Token a
Feature activation+0.348
repeal
Token repeal
Feature activation+0.000
.
Token.
Feature activation+2.599
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.880
But
TokenBut
Feature activation+2.541
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+1.786
he
Token he
Feature activation+0.000
took
Token took
Feature activation+0.000
even
Token even
Feature activation+0.000
for
Token for
Feature activation+1.265
reelection
Token reelection
Feature activation+0.000
.
Token.
Feature activation+0.193
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Senator
TokenSenator
Feature activation+2.329
Bob
Token Bob
Feature activation+3.140
Corker
Token Corker
Feature activation+0.869
"
Token "
Feature activation+0.198
be
Tokenbe
Feature activation+0.000
gged
Tokengged
Feature activation+0.228
Joe
Token Joe
Feature activation+2.710
Man
Token Man
Feature activation+0.012
chin
Tokenchin
Feature activation+0.000
.
Token.
Feature activation+0.887
But
Token But
Feature activation+2.764
perhaps
Token perhaps
Feature activation+2.766
in
Token in
Feature activation+0.859
Joe
Token Joe
Feature activation+1.464
Man
Token Man
Feature activation+0.520
chin
Tokenchin
Feature activation+0.369
âĢ
TokenâĢ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.935
a
Token a
Feature activation+0.348
repeal
Token repeal
Feature activation+0.000
.
Token.
Feature activation+2.599
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.880
But
TokenBut
Feature activation+2.541
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+1.786

INTERVAL 1.427 - 2.141
CONTAINS 0.035%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.111
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.674
OP
TokenOP
Feature activation+0.177
EN
TokenEN
Feature activation+1.432
Act
Token Act
Feature activation+0.935
First
Token First
Feature activation+0.235
Circ
Token Circ
Feature activation+0.000
ulated
Tokenulated
Feature activation+0.175
Dec
Token Dec
Feature activation+0.000
one
Token one
Feature activation+0.000
more
Token more
Feature activation+0.000
example
Token example
Feature activation+0.000
of
Token of
Feature activation+0.592
how
Token how
Feature activation+0.479
Sam
Token Sam
Feature activation+1.821
Brown
Token Brown
Feature activation+0.000
back
Tokenback
Feature activation+0.000
is
Token is
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Senate
Token Senate
Feature activation+0.465
Minority
Token Minority
Feature activation+1.957
Leader
Token Leader
Feature activation+3.566
Anthony
Token Anthony
Feature activation+1.471
H
Token H
Feature activation+0.640
ens
Tokenens
Feature activation+0.048
ley
Tokenley
Feature activation+0.000
,
Token,
Feature activation+0.277
D
Token D
Feature activation+0.000
address
Token address
Feature activation+0.000
to
Token to
Feature activation+0.207
a
Token a
Feature activation+0.367
Joint
Token Joint
Feature activation+0.000
Session
Token Session
Feature activation+0.000
of
Token of
Feature activation+1.462
Congress
Token Congress
Feature activation+0.000
:
Token:
Feature activation+1.180
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.840
âĢ
TokenâĢ
Feature activation+0.000
published
Token published
Feature activation+0.000
last
Token last
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
clear
Token clear
Feature activation+1.978
that
Token that
Feature activation+2.013
Jefferson
Token Jefferson
Feature activation+0.000
Be
Token Be
Feature activation+0.000
a
Tokena
Feature activation+0.000
ure
Tokenure
Feature activation+0.000

INTERVAL 0.714 - 1.427
CONTAINS 0.085%

to
Token to
Feature activation+0.000
influence
Token influence
Feature activation+0.000
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
election
Token election
Feature activation+0.000
.
Token.
Feature activation+0.946
And
Token And
Feature activation+0.439
he
Token he
Feature activation+0.000
believes
Token believes
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.455
,"
Token,"
Feature activation+0.946
Sanders
Token Sanders
Feature activation+0.000
said
Token said
Feature activation+0.000
before
Token before
Feature activation+0.339
reading
Token reading
Feature activation+0.463
the
Token the
Feature activation+0.907
letter
Token letter
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.564
I
TokenI
Feature activation+0.093
want
Token want
Feature activation+2.770
lying
Tokenlying
Feature activation+0.385
pressure
Token pressure
Feature activation+0.000
on
Token on
Feature activation+1.011
House
Token House
Feature activation+0.141
and
Token and
Feature activation+0.000
Senate
Token Senate
Feature activation+0.746
negotiators
Token negotiators
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.449
the
Token the
Feature activation+0.187
bill
Token bill
Feature activation+0.000
come
Token come
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.468
a
Token a
Feature activation+0.606
vote
Token vote
Feature activation+0.000
in
Token in
Feature activation+1.406
the
Token the
Feature activation+1.182
upper
Token upper
Feature activation+1.611
chamber
Token chamber
Feature activation+0.000
later
Token later
Feature activation+0.000
this
Token this
Feature activation+0.000
still
Token still
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.167
be
Tokenbe
Feature activation+0.143
-
Token-
Feature activation+1.189
named
Tokennamed
Feature activation+0.187
pick
Token pick
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000

INTERVAL 0.000 - 0.714
CONTAINS 99.847%

three
Token three
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
19
Token 19
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
athlete
Token athlete
Feature activation+0.000
class
Token class
Feature activation+0.000
morph
Token morph
Feature activation+0.000
isms
Tokenisms
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
post
Token post
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
that
Token that
Feature activation+0.000
semantic
Token semantic
Feature activation+0.000
functions
Token functions
Feature activation+0.000
in
Token in
Feature activation+0.000
heart
Token heart
Feature activation+0.000
attack
Token attack
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
room
Token room
Feature activation+0.000
just
Token just
Feature activation+0.000
hours
Token hours
Feature activation+0.000
later
Token later
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
marching
Token marching
Feature activation+0.000
band
Token band
Feature activation+0.000
has
Token has
Feature activation+0.000
participated
Token participated
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
five
Token five
Feature activation+0.000
inaugural
Token inaugural
Feature activation+0.000
par
Token par
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
energy
Token energy
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
maxim
Token maxim
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Williams
TokenWilliams
Feature activation+0.000
gives
Token gives
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H10.6: (feature 10081)

TOP ACTIVATIONS
MAX = 5.800

put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.101
No
Token No
Feature activation+5.800
campaign
Token campaign
Feature activation+0.000
has
Token has
Feature activation+0.000
signed
Token signed
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
Congressional
Token Congressional
Feature activation+0.000
Campaign
Token Campaign
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
(
Token (
Feature activation+0.060
D
TokenD
Feature activation+5.094
CCC
TokenCCC
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
like
Token like
Feature activation+0.000
Chen
Token Chen
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+1.928
demolition
Token demolition
Feature activation+4.379
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
merely
Token merely
Feature activation+0.000
a
Token a
Feature activation+0.268
front
Token front
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.257
the
Token the
Feature activation+3.615
awareness
Token awareness
Feature activation+4.296
campaign
Token campaign
Feature activation+0.797
,
Token,
Feature activation+0.000
notices
Token notices
Feature activation+0.000
and
Token and
Feature activation+0.000
banners
Token banners
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.351
To
TokenTo
Feature activation+1.086
learn
Token learn
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+2.614
the
Token the
Feature activation+3.961
crowd
Token crowd
Feature activation+0.000
-
Token-
Feature activation+0.000
funding
Tokenfunding
Feature activation+1.863
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.000
For
Token For
Feature activation+2.079
example
Token example
Feature activation+1.594
,
Token,
Feature activation+2.538
I
Token I
Feature activation+0.000
claim
Token claim
Feature activation+3.242
that
Token that
Feature activation+3.735
the
Token the
Feature activation+2.026
long
Token long
Feature activation+0.000
list
Token list
Feature activation+0.254
of
Token of
Feature activation+1.329
non
Token non
Feature activation+0.138
(
Token (
Feature activation+0.000
In
TokenIn
Feature activation+0.000
return
Token return
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
ceased
Token ceased
Feature activation+3.702
campaigning
Token campaigning
Feature activation+0.000
in
Token in
Feature activation+0.000
Oregon
Token Oregon
Feature activation+0.000
and
Token and
Feature activation+0.000
New
Token New
Feature activation+0.000
land
Token land
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.257
the
Token the
Feature activation+3.615
awareness
Token awareness
Feature activation+4.296
campaign
Token campaign
Feature activation+0.797
,
Token,
Feature activation+0.000
notices
Token notices
Feature activation+0.000
and
Token and
Feature activation+0.000
s
Tokens
Feature activation+0.000
an
Token an
Feature activation+0.000
early
Token early
Feature activation+0.000
trailer
Token trailer
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+3.535
game
Token game
Feature activation+0.000
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢĭ
TokenâĢĭ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
.
Token.
Feature activation+1.506
For
Token For
Feature activation+2.079
example
Token example
Feature activation+1.594
,
Token,
Feature activation+2.538
I
Token I
Feature activation+0.000
claim
Token claim
Feature activation+3.242
that
Token that
Feature activation+3.735
the
Token the
Feature activation+2.026
long
Token long
Feature activation+0.000
list
Token list
Feature activation+0.254
of
Token of
Feature activation+1.329
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
arm
Token arm
Feature activation+2.981
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
structures
Token structures
Feature activation+0.000
through
Token through
Feature activation+0.207
their
Token their
Feature activation+0.238
digital
Token digital
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
.
Token.
Feature activation+2.968
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.536
"
Token"
Feature activation+2.086
I
TokenI
Feature activation+0.406
think
Token think
Feature activation+2.633
John
Token John
Feature activation+0.000
stown
Tokenstown
Feature activation+0.000
,
Token,
Feature activation+0.000
Ont
Token Ont
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+2.844
group
Token group
Feature activation+0.000
of
Token of
Feature activation+1.509
Colombian
Token Colombian
Feature activation+0.000
miners
Token miners
Feature activation+0.000
sat
Token sat
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.647
If
TokenIf
Feature activation+0.864
one
Token one
Feature activation+1.502
or
Token or
Feature activation+0.000
both
Token both
Feature activation+2.835
of
Token of
Feature activation+0.447
them
Token them
Feature activation+0.000
makes
Token makes
Feature activation+0.000
the
Token the
Feature activation+0.237
ballot
Token ballot
Feature activation+0.000
our
Token our
Feature activation+0.000
most
Token most
Feature activation+0.000
precious
Token precious
Feature activation+0.000
resource
Token resource
Feature activation+0.000
."
Token."
Feature activation+0.541
The
Token The
Feature activation+2.832
petition
Token petition
Feature activation+0.095
is
Token is
Feature activation+0.000
gaining
Token gaining
Feature activation+0.000
traction
Token traction
Feature activation+0.000
again
Token again
Feature activation+0.000
custom
Token custom
Feature activation+0.505
art
Token art
Feature activation+0.038
sleeves
Token sleeves
Feature activation+0.000
are
Token are
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+2.825
He
Token He
Feature activation+0.000
g
Tokeng
Feature activation+0.000
emonic
Tokenemonic
Feature activation+0.780
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.800
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.983
province
Token province
Feature activation+0.000
.
Token.
Feature activation+2.559
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.727
Correct
TokenCorrect
Feature activation+0.000
ed
Tokened
Feature activation+0.000
sound
Token sound
Feature activation+0.000
effect
Token effect
Feature activation+0.000
for
Token for
Feature activation+0.589
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Circ
TokenCirc
Feature activation+0.000
ulate
Tokenulate
Feature activation+0.000
this
Token this
Feature activation+2.718
Youtube
Token Youtube
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
friends
Token friends
Feature activation+0.000
and
Token and
Feature activation+0.031
Friday
Token Friday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Row
TokenRow
Feature activation+0.000
land
Tokenland
Feature activation+2.677
,
Token,
Feature activation+0.000
57
Token 57
Feature activation+0.000
,
Token,
Feature activation+1.305
was
Token was
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
B
Token B
Feature activation+0.000
anners
Tokenanners
Feature activation+0.184
shooting
Token shooting
Feature activation+0.000
.
Token.
Feature activation+0.645
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.645
Correct
TokenCorrect
Feature activation+0.000
ed
Tokened
Feature activation+0.000
troop
Token troop
Feature activation+0.000
description
Token description
Feature activation+0.000
of
Token of
Feature activation+0.297

Top DFA by src position
MAX = 6.415

the
Token the
Feature activation+0.001
Top resid features:
list
Token list
Feature activation+0.003
Top resid features:
together
Token together
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
No
Token No
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+6.415
Top resid features:
has
Token has
Feature activation-0.011
Top resid features:
signed
Token signed
Feature activation+0.005
Top resid features:
off
Token off
Feature activation+0.006
Top resid features:
on
Token on
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
email
Token email
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
Democratic
Token Democratic
Feature activation-0.003
Top resid features:
Congressional
Token Congressional
Feature activation-0.112
Top resid features:
Campaign
Token Campaign
Feature activation+5.489
Top resid features:
Committee
Token Committee
Feature activation+0.408
Top resid features:
(
Token (
Feature activation-0.006
Top resid features:
D
TokenD
Feature activation+0.001
Top resid features:
CCC
TokenCCC
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
ifications
Tokenifications
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
one
Token one
Feature activation+0.001
Top resid features:
demolition
Token demolition
Feature activation-0.007
Top resid features:
"
Token"
Feature activation+0.030
Top resid features:
campaign
Token campaign
Feature activation+3.377
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
And
Token And
Feature activation+0.012
Top resid features:
church
Token church
Feature activation+0.001
Top resid features:
leaders
Token leaders
Feature activation+0.006
Top resid features:
like
Token like
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
will
Token will
Feature activation+0.003
Top resid features:
launch
Token launch
Feature activation+0.125
Top resid features:
an
Token an
Feature activation+0.015
Top resid features:
awareness
Token awareness
Feature activation+0.006
Top resid features:
campaign
Token campaign
Feature activation+4.501
Top resid features:
in
Token in
Feature activation+0.062
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
illegal
Token illegal
Feature activation+0.002
Top resid features:
sl
Token sl
Feature activation-0.000
Top resid features:
ums
Tokenums
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
soon
Token soon
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
because
Token because
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
campaign
Token campaign
Feature activation+4.100
Top resid features:
has
Token has
Feature activation+0.027
Top resid features:
less
Token less
Feature activation+0.005
Top resid features:
than
Token than
Feature activation+0.002
Top resid features:
two
Token two
Feature activation-0.000
Top resid features:
weeks
Token weeks
Feature activation+0.006
Top resid features:
on
Tokenon
Feature activation+0.008
Top resid features:
when
Token when
Feature activation+0.005
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
wonders
Token wonders
Feature activation-0.007
Top resid features:
whether
Token whether
Feature activation-0.000
Top resid features:
campaigns
Token campaigns
Feature activation+4.356
Top resid features:
using
Token using
Feature activation+0.001
Top resid features:
relatively
Token relatively
Feature activation+0.005
Top resid features:
simple
Token simple
Feature activation+0.040
Top resid features:
rules
Token rules
Feature activation-0.006
Top resid features:
have
Token have
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.200
Top resid features:
Ohio
Token Ohio
Feature activation+0.028
Top resid features:
has
Token has
Feature activation+0.026
Top resid features:
ceased
Token ceased
Feature activation+0.015
Top resid features:
campaigning
Token campaigning
Feature activation+4.482
Top resid features:
in
Token in
Feature activation+0.057
Top resid features:
Indiana
Token Indiana
Feature activation-0.143
Top resid features:
thanks
Token thanks
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
will
Token will
Feature activation+0.001
Top resid features:
launch
Token launch
Feature activation+0.233
Top resid features:
an
Token an
Feature activation+0.018
Top resid features:
awareness
Token awareness
Feature activation-0.299
Top resid features:
campaign
Token campaign
Feature activation+4.067
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
illegal
Token illegal
Feature activation+0.000
Top resid features:
sl
Token sl
Feature activation-0.009
Top resid features:
ums
Tokenums
Feature activation+0.004
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
soon
Token soon
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
because
Token because
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
campaign
Token campaign
Feature activation+3.916
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
less
Token less
Feature activation+0.004
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
two
Token two
Feature activation-0.000
Top resid features:
weeks
Token weeks
Feature activation+0.002
Top resid features:
on
Tokenon
Feature activation+0.005
Top resid features:
when
Token when
Feature activation+0.011
Top resid features:
he
Token he
Feature activation+0.006
Top resid features:
wonders
Token wonders
Feature activation-0.008
Top resid features:
whether
Token whether
Feature activation-0.010
Top resid features:
campaigns
Token campaigns
Feature activation+3.822
Top resid features:
using
Token using
Feature activation+0.005
Top resid features:
relatively
Token relatively
Feature activation+0.011
Top resid features:
simple
Token simple
Feature activation+0.019
Top resid features:
rules
Token rules
Feature activation-0.018
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
.)
Token.)
Feature activation+0.098
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
Republican
Token Republican
Feature activation-0.167
Top resid features:
Senate
Token Senate
Feature activation-0.451
Top resid features:
campaign
Token campaign
Feature activation+4.323
Top resid features:
arm
Token arm
Feature activation+0.319
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
different
Token different
Feature activation+0.031
Top resid features:
parties
Token parties
Feature activation-0.196
Top resid features:
'
Token'
Feature activation+0.035
Top resid features:
campaign
Token campaign
Feature activation+1.882
Top resid features:
structures
Token structures
Feature activation-0.004
Top resid features:
through
Token through
Feature activation-0.001
Top resid features:
their
Token their
Feature activation+0.035
Top resid features:
digital
Token digital
Feature activation+0.344
Top resid features:
campaigns
Token campaigns
Feature activation+1.420
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
week
Token week
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
campaign
Token campaign
Feature activation+2.463
Top resid features:
spot
Token spot
Feature activation-0.034
Top resid features:
talked
Token talked
Feature activation-0.007
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
ship
Token ship
Feature activation-0.039
Top resid features:
building
Tokenbuilding
Feature activation-0.003
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
currently
Token currently
Feature activation-0.001
Top resid features:
four
Token four
Feature activation+0.006
Top resid features:
different
Token different
Feature activation+0.035
Top resid features:
initiative
Token initiative
Feature activation+0.272
Top resid features:
campaigns
Token campaigns
Feature activation+2.929
Top resid features:
underway
Token underway
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
but
Token but
Feature activation+0.012
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.193
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
The
TokenThe
Feature activation+0.028
Top resid features:
campaign
Token campaign
Feature activation+2.521
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
titled
Token titled
Feature activation+0.031
Top resid features:
"
Token "
Feature activation+0.009
Top resid features:
N
TokenN
Feature activation+0.004
Top resid features:
est
Tokenest
Feature activation+0.037
Top resid features:
At
Token At
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
end
Token end
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
this
Token this
Feature activation+0.006
Top resid features:
campaign
Token campaign
Feature activation+3.257
Top resid features:
you
Token you
Feature activation+0.012
Top resid features:
'll
Token'll
Feature activation+0.003
Top resid features:
get
Token get
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
survey
Token survey
Feature activation+0.085
Top resid features:
)
Token)
Feature activation+0.006
Top resid features:
battles
Token battles
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
Campaign
TokenCampaign
Feature activation+2.955
Top resid features:
s
Tokens
Feature activation+0.167
Top resid features:
:
Token:
Feature activation+0.020
Top resid features:
Correct
Token Correct
Feature activation-0.013
Top resid features:
ed
Tokened
Feature activation+0.021
Top resid features:
bug
Token bug
Feature activation-0.020
Top resid features:
ling
Tokenling
Feature activation-0.028
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
This
TokenThis
Feature activation+0.009
Top resid features:
campaign
Token campaign
Feature activation+3.200
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
cle
Token cle
Feature activation-0.002
Top resid features:
all
Token all
Feature activation-0.004
Top resid features:
seven
Token seven
Feature activation-0.001
Top resid features:
counts
Token counts
Feature activation+0.014
Top resid features:
in
Token in
Feature activation+0.020
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
campaign
Token campaign
Feature activation+3.325
Top resid features:
finance
Token finance
Feature activation+0.121
Top resid features:
conspiracy
Token conspiracy
Feature activation+0.050
Top resid features:
scheme
Token scheme
Feature activation+0.071
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
New
Token New
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.002
Top resid features:
battles
Token battles
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Campaign
TokenCampaign
Feature activation+3.008
Top resid features:
s
Tokens
Feature activation+0.130
Top resid features:
:
Token:
Feature activation+0.008
Top resid features:
Correct
Token Correct
Feature activation-0.029
Top resid features:
ed
Tokened
Feature activation+0.008
Top resid features:
bug
Token bug
Feature activation-0.020
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.05

Head 3: 0.07

Head 4: 0.04

Head 5: 0.03

Head 6: 0.43

Head 7: 0.10

Head 8: 0.02

Head 9: 0.04

Head 10: 0.05

Head 11: 0.07

Positive logits

Campaign9.75

campaign9.05

campaign8.97

Campaign8.66

campaigns8.21

campaigning7.23

campaigners5.61

canv5.46

campaigned5.40

campaigner5.18

PACs4.65

FEC4.60

fundraising4.55

voter4.48

cand4.47

candidate4.32

Election4.29

fundra4.29

Elections4.28

PAC4.17

Negative logits

aylor-2.92

license-2.92

Gleaming-2.88

vu-2.80

grain-2.77

exam-2.77

Bench-2.68

academ-2.59

exams-2.57

rie-2.55

envy-2.55

bane-2.48

ifle-2.47

ItemTracker-2.45

License-2.41

examiner-2.35

Reviewed-2.34

property-2.31

Examination-2.31

bilt-2.30

INTERVAL 5.220 - 5.800
CONTAINS 0.000%

put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.101
No
Token No
Feature activation+5.800
campaign
Token campaign
Feature activation+0.000
has
Token has
Feature activation+0.000
signed
Token signed
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 4.640 - 5.220
CONTAINS 0.000%

Democratic
Token Democratic
Feature activation+0.000
Congressional
Token Congressional
Feature activation+0.000
Campaign
Token Campaign
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
(
Token (
Feature activation+0.060
D
TokenD
Feature activation+5.094
CCC
TokenCCC
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

INTERVAL 4.060 - 4.640
CONTAINS 0.000%

like
Token like
Feature activation+0.000
Chen
Token Chen
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+1.928
demolition
Token demolition
Feature activation+4.379
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
merely
Token merely
Feature activation+0.000
a
Token a
Feature activation+0.268
front
Token front
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.257
the
Token the
Feature activation+3.615
awareness
Token awareness
Feature activation+4.296
campaign
Token campaign
Feature activation+0.797
,
Token,
Feature activation+0.000
notices
Token notices
Feature activation+0.000
and
Token and
Feature activation+0.000
banners
Token banners
Feature activation+0.000

INTERVAL 3.480 - 4.060
CONTAINS 0.001%

(
Token (
Feature activation+0.000
In
TokenIn
Feature activation+0.000
return
Token return
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
ceased
Token ceased
Feature activation+3.702
campaigning
Token campaigning
Feature activation+0.000
in
Token in
Feature activation+0.000
Oregon
Token Oregon
Feature activation+0.000
and
Token and
Feature activation+0.000
New
Token New
Feature activation+0.000
For
Token For
Feature activation+2.079
example
Token example
Feature activation+1.594
,
Token,
Feature activation+2.538
I
Token I
Feature activation+0.000
claim
Token claim
Feature activation+3.242
that
Token that
Feature activation+3.735
the
Token the
Feature activation+2.026
long
Token long
Feature activation+0.000
list
Token list
Feature activation+0.254
of
Token of
Feature activation+1.329
non
Token non
Feature activation+0.138
Ċ
TokenĊ
Feature activation+1.351
To
TokenTo
Feature activation+1.086
learn
Token learn
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+2.614
the
Token the
Feature activation+3.961
crowd
Token crowd
Feature activation+0.000
-
Token-
Feature activation+0.000
funding
Tokenfunding
Feature activation+1.863
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.000
s
Tokens
Feature activation+0.000
an
Token an
Feature activation+0.000
early
Token early
Feature activation+0.000
trailer
Token trailer
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+3.535
game
Token game
Feature activation+0.000
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢĭ
TokenâĢĭ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
land
Token land
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.257
the
Token the
Feature activation+3.615
awareness
Token awareness
Feature activation+4.296
campaign
Token campaign
Feature activation+0.797
,
Token,
Feature activation+0.000
notices
Token notices
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.900 - 3.480
CONTAINS 0.000%

.
Token.
Feature activation+1.506
For
Token For
Feature activation+2.079
example
Token example
Feature activation+1.594
,
Token,
Feature activation+2.538
I
Token I
Feature activation+0.000
claim
Token claim
Feature activation+3.242
that
Token that
Feature activation+3.735
the
Token the
Feature activation+2.026
long
Token long
Feature activation+0.000
list
Token list
Feature activation+0.254
of
Token of
Feature activation+1.329
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
arm
Token arm
Feature activation+2.981
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
structures
Token structures
Feature activation+0.000
through
Token through
Feature activation+0.207
their
Token their
Feature activation+0.238
digital
Token digital
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
.
Token.
Feature activation+2.968
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.536
"
Token"
Feature activation+2.086
I
TokenI
Feature activation+0.406
think
Token think
Feature activation+2.633

INTERVAL 2.320 - 2.900
CONTAINS 0.003%

B
Token B
Feature activation+0.000
anners
Tokenanners
Feature activation+0.184
shooting
Token shooting
Feature activation+0.000
.
Token.
Feature activation+0.645
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.645
Correct
TokenCorrect
Feature activation+0.000
ed
Tokened
Feature activation+0.000
troop
Token troop
Feature activation+0.000
description
Token description
Feature activation+0.000
of
Token of
Feature activation+0.297
media
Token media
Feature activation+0.492
sponsors
Token sponsors
Feature activation+0.000
.
Token.
Feature activation+0.348
Leading
Token Leading
Feature activation+0.279
Republican
Token Republican
Feature activation+0.822
presidential
Token presidential
Feature activation+2.349
campaigns
Token campaigns
Feature activation+0.000
and
Token and
Feature activation+0.077
attorney
Token attorney
Feature activation+0.000
Ben
Token Ben
Feature activation+0.000
Gins
Token Gins
Feature activation+0.000
on
Token on
Feature activation+0.000
all
Token all
Feature activation+0.000
seven
Token seven
Feature activation+0.000
counts
Token counts
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+2.594
campaign
Token campaign
Feature activation+0.487
finance
Token finance
Feature activation+0.619
conspiracy
Token conspiracy
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
in
Token in
Feature activation+0.000
custom
Token custom
Feature activation+0.505
art
Token art
Feature activation+0.038
sleeves
Token sleeves
Feature activation+0.000
are
Token are
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+2.825
He
Token He
Feature activation+0.000
g
Tokeng
Feature activation+0.000
emonic
Tokenemonic
Feature activation+0.780
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.800
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.647
If
TokenIf
Feature activation+0.864
one
Token one
Feature activation+1.502
or
Token or
Feature activation+0.000
both
Token both
Feature activation+2.835
of
Token of
Feature activation+0.447
them
Token them
Feature activation+0.000
makes
Token makes
Feature activation+0.000
the
Token the
Feature activation+0.237
ballot
Token ballot
Feature activation+0.000

INTERVAL 1.740 - 2.320
CONTAINS 0.005%

leaders
Token leaders
Feature activation+0.000
like
Token like
Feature activation+0.000
Chen
Token Chen
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+1.928
demolition
Token demolition
Feature activation+4.379
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
merely
Token merely
Feature activation+0.000
a
Token a
Feature activation+0.268
clarification
Token clarification
Feature activation+0.000
,
Token,
Feature activation+0.000
N
Token N
Feature activation+0.000
GP
TokenGP
Feature activation+1.501
V
Token V
Feature activation+0.042
AN
TokenAN
Feature activation+2.002
played
Token played
Feature activation+0.000
no
Token no
Feature activation+0.000
part
Token part
Feature activation+0.000
in
Token in
Feature activation+0.337
the
Token the
Feature activation+0.807
Pike
Token Pike
Feature activation+0.000
and
Token and
Feature activation+0.000
Shot
Token Shot
Feature activation+0.259
:
Token:
Feature activation+0.268
Campaign
Token Campaign
Feature activation+0.000
s
Tokens
Feature activation+1.951
from
Token from
Feature activation+1.997
its
Token its
Feature activation+0.596
official
Token official
Feature activation+0.442
Product
Token Product
Feature activation+0.000
Page
Token Page
Feature activation+0.000
than
Token than
Feature activation+0.000
two
Token two
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.528
the
Token the
Feature activation+1.950
goal
Token goal
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+1.473
raise
Token raise
Feature activation+0.000
45
Token 45
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
.
Token.
Feature activation+1.101
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.792
The
TokenThe
Feature activation+1.696
result
Token result
Feature activation+0.000
is
Token is
Feature activation+0.049
cross
Token cross
Feature activation+0.245
between
Token between
Feature activation+0.610

INTERVAL 1.160 - 1.740
CONTAINS 0.011%

candidates
Token candidates
Feature activation+0.000
are
Token are
Feature activation+0.000
comparable
Token comparable
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.171
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.084
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.811
To
TokenTo
Feature activation+0.000
bought
Token bought
Feature activation+0.000
five
Token five
Feature activation+0.000
copies
Token copies
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+1.197
Paul
Token Paul
Feature activation+1.614
campaign
Token campaign
Feature activation+0.000
officially
Token officially
Feature activation+0.000
is
Token is
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.826
her
Token her
Feature activation+1.028
events
Token events
Feature activation+0.000
.
Token.
Feature activation+1.829
At
Token At
Feature activation+1.227
event
Token event
Feature activation+0.000
after
Token after
Feature activation+0.000
event
Token event
Feature activation+0.609
,
Token,
Feature activation+2.189
Fiorina
Token Fiorina
Feature activation+0.000
payments
Token payments
Feature activation+0.000
were
Token were
Feature activation+0.000
for
Token for
Feature activation+0.071
.
Token.
Feature activation+0.353
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.242
NOTE
TokenNOTE
Feature activation+0.000
:
Token:
Feature activation+0.716
The
Token The
Feature activation+1.102
custom
Token custom
Feature activation+0.505
art
Token art
Feature activation+0.038
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
appropriate
Token appropriate
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
the
Token the
Feature activation+1.407
super
Token super
Feature activation+0.050
PAC
Token PAC
Feature activation+0.000
a
Token a
Feature activation+0.000
walk
Token walk
Feature activation+0.000
through
Tokenthrough
Feature activation+0.000

INTERVAL 0.580 - 1.160
CONTAINS 0.037%

are
Token are
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+2.825
He
Token He
Feature activation+0.000
g
Tokeng
Feature activation+0.000
emonic
Tokenemonic
Feature activation+0.780
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.800
H
TokenH
Feature activation+0.000
eg
Tokeneg
Feature activation+0.000
emonic
Tokenemonic
Feature activation+0.665
,
Token,
Feature activation+0.000
Boris
Token Boris
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
,
Token,
Feature activation+0.554
the
Token the
Feature activation+1.188
British
Token British
Feature activation+1.135
Foreign
Token Foreign
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
for
Token for
Feature activation+0.000
Group
Token Group
Feature activation+0.000
,
Token,
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
American
Token American
Feature activation+1.127
Research
Token Research
Feature activation+0.000
Group
Token Group
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
conducting
Token conducting
Feature activation+0.000
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.000
seeing
Token seeing
Feature activation+0.601
the
Token the
Feature activation+0.529
beginnings
Token beginnings
Feature activation+0.000
of
Token of
Feature activation+0.811
a
Token a
Feature activation+0.824
small
Token small
Feature activation+0.000
target
Token target
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
,"
Token,"
Feature activation+0.184
Coalition
Token Coalition
Feature activation+0.000
side
Token side
Feature activation+0.440
we
Token we
Feature activation+0.082
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.000
seeing
Token seeing
Feature activation+0.601
the
Token the
Feature activation+0.529
beginnings
Token beginnings
Feature activation+0.000
of
Token of
Feature activation+0.811
a
Token a
Feature activation+0.824
small
Token small
Feature activation+0.000

INTERVAL 0.000 - 0.580
CONTAINS 99.943%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
business
Token business
Feature activation+0.000
.
Token.
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
Anthony
Token Anthony
Feature activation+0.000
Le
Token Le
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
approval
Token approval
Feature activation+0.000
follows
Token follows
Feature activation+0.000
a
Token a
Feature activation+0.000
site
Token site
Feature activation+0.000
visit
Token visit
Feature activation+0.000
and
Token and
Feature activation+0.000
report
Token report
Feature activation+0.000
by
Token by
Feature activation+0.000
has
Token has
Feature activation+0.000
anchored
Token anchored
Feature activation+0.000
the
Token the
Feature activation+0.000
Butter
Token Butter
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
Square
Token Square
Feature activation+0.000
shopping
Token shopping
Feature activation+0.000
center
Token center
Feature activation+0.000
on
Token on
Feature activation+0.000
Liberty
Token Liberty
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
pay
Tokenpay
Feature activation+0.000
ments
Tokenments
Feature activation+0.000
"
Token"
Feature activation+0.000
at
Token at
Feature activation+0.000
9
Token 9
Feature activation+0.000
08
Token08
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
billion
Token billion
Feature activation+0.000
euros
Token euros
Feature activation+0.000
($
Token ($
Feature activation+0.000
A
TokenA
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
Oil
Token Oil
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H10.6: (feature 20979)

TOP ACTIVATIONS
MAX = 4.743

situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
,
Token,
Feature activation+1.766
the
Token the
Feature activation+4.743
President
Token President
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
time
Token time
Feature activation+0.000
playing
Token playing
Feature activation+3.199
the
Token the
Feature activation+4.428
president
Token president
Feature activation+0.639
on
Token on
Feature activation+1.050
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.280
The
TokenThe
Feature activation+0.623
ers
Tokeners
Feature activation+0.000
of
Token of
Feature activation+2.682
U
Token U
Feature activation+0.885
.
Token.
Feature activation+2.367
S
TokenS
Feature activation+2.641
.
Token.
Feature activation+4.231
President
Token President
Feature activation+0.411
Barack
Token Barack
Feature activation+0.495
Obama
Token Obama
Feature activation+0.000
,
Token,
Feature activation+0.000
made
Token made
Feature activation+0.000
first
Token first
Feature activation+0.000
70
Token 70
Feature activation+0.000
days
Token days
Feature activation+0.681
See
Token See
Feature activation+0.000
Gallery
Token Gallery
Feature activation+3.869
Inside
Token Inside
Feature activation+4.028
President
Token President
Feature activation+1.162
Trump
Token Trump
Feature activation+0.271
's
Token's
Feature activation+1.260
first
Token first
Feature activation+0.397
70
Token 70
Feature activation+0.199
the
Token the
Feature activation+1.000
first
Token first
Feature activation+3.845
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.242
S
TokenS
Feature activation+1.998
.
Token.
Feature activation+4.012
President
Token President
Feature activation+0.000
to
Token to
Feature activation+0.593
be
Token be
Feature activation+0.000
given
Token given
Feature activation+0.403
a
Token a
Feature activation+0.554
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.403
s
Tokens
Feature activation+0.400
father
Token father
Feature activation+3.114
,
Token,
Feature activation+3.918
Barack
Token Barack
Feature activation+0.103
Obama
Token Obama
Feature activation+0.255
Sr
Token Sr
Feature activation+0.000
.,
Token.,
Feature activation+0.908
and
Token and
Feature activation+2.804
's
Token's
Feature activation+0.312
first
Token first
Feature activation+0.000
70
Token 70
Feature activation+0.000
days
Token days
Feature activation+0.681
See
Token See
Feature activation+0.000
Gallery
Token Gallery
Feature activation+3.869
Inside
Token Inside
Feature activation+4.028
President
Token President
Feature activation+1.162
Trump
Token Trump
Feature activation+0.271
's
Token's
Feature activation+1.260
first
Token first
Feature activation+0.397
to
Token to
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
that
Token that
Feature activation+1.014
the
Token the
Feature activation+3.857
president
Token president
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
ignore
Token ignore
Feature activation+0.000
her
Token her
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.366
s
Tokens
Feature activation+0.210
also
Token also
Feature activation+0.048
the
Token the
Feature activation+1.000
first
Token first
Feature activation+3.845
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.242
S
TokenS
Feature activation+1.998
.
Token.
Feature activation+4.012
President
Token President
Feature activation+0.000
of
Token of
Feature activation+0.000
critical
Token critical
Feature activation+0.000
tweets
Token tweets
Feature activation+0.000
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+0.000
the
Token the
Feature activation+3.679
president
Token president
Feature activation+0.000
a
Token a
Feature activation+0.303
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
monster
Tokenmonster
Feature activation+0.000
Esc
Token Esc
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
edo
Tokenedo
Feature activation+0.000
drug
Token drug
Feature activation+0.000
cartel
Token cartel
Feature activation+0.000
,
Token,
Feature activation+3.562
the
Token the
Feature activation+2.634
White
Token White
Feature activation+0.197
House
Token House
Feature activation+0.639
wants
Token wants
Feature activation+1.516
to
Token to
Feature activation+0.832
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
(@
Token (@
Feature activation+0.251
Hillary
TokenHillary
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
)
Token)
Feature activation+3.541
October
Token October
Feature activation+0.049
26
Token 26
Feature activation+0.000
,
Token,
Feature activation+1.936
2016
Token 2016
Feature activation+0.174
Ċ
TokenĊ
Feature activation+0.000
hits
Token hits
Feature activation+0.000
LA
Token LA
Feature activation+0.000
,
Token,
Feature activation+0.000
Atlanta
Token Atlanta
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.589
Ċ
TokenĊ
Feature activation+3.309
Post
TokenPost
Feature activation+0.125
ers
Tokeners
Feature activation+0.000
of
Token of
Feature activation+2.682
U
Token U
Feature activation+0.885
.
Token.
Feature activation+2.367
things
Token things
Feature activation+0.000
.
Token.
Feature activation+1.228
Back
Token Back
Feature activation+0.000
in
Token in
Feature activation+0.233
August
Token August
Feature activation+0.139
,
Token,
Feature activation+3.243
an
Token an
Feature activation+1.375
inf
Token inf
Feature activation+0.000
latable
Tokenlatable
Feature activation+1.216
chicken
Token chicken
Feature activation+0.000
made
Token made
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
time
Token time
Feature activation+0.000
playing
Token playing
Feature activation+3.199
the
Token the
Feature activation+4.428
president
Token president
Feature activation+0.639
on
Token on
Feature activation+1.050
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.280
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
via
Token via
Feature activation+0.000
Getty
Token Getty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+3.181
(
Token (
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
by
Token by
Feature activation+0.000
Sarah
Token Sarah
Feature activation+0.000
L
Token L
Feature activation+0.000
felt
Token felt
Feature activation+0.237
that
Token that
Feature activation+0.365
instead
Token instead
Feature activation+0.320
the
Token the
Feature activation+0.452
Congress
Token Congress
Feature activation+0.000
and
Token and
Feature activation+3.165
the
Token the
Feature activation+2.799
president
Token president
Feature activation+0.000
were
Token were
Feature activation+0.000
pursuing
Token pursuing
Feature activation+0.000
an
Token an
Feature activation+0.000
The
TokenThe
Feature activation+0.697
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.403
s
Tokens
Feature activation+0.400
father
Token father
Feature activation+3.114
,
Token,
Feature activation+3.918
Barack
Token Barack
Feature activation+0.103
Obama
Token Obama
Feature activation+0.255
Sr
Token Sr
Feature activation+0.000
.,
Token.,
Feature activation+0.908
.
Token.
Feature activation+0.132
Hillary
Token Hillary
Feature activation+0.285
Clinton
Token Clinton
Feature activation+1.231
is
Token is
Feature activation+0.677
the
Token the
Feature activation+0.703
rightful
Token rightful
Feature activation+3.104
president
Token president
Feature activation+0.315
-
Token-
Feature activation+0.077
elect
Tokenelect
Feature activation+1.139
,
Token,
Feature activation+0.534
and
Token and
Feature activation+0.771
onite
Tokenonite
Feature activation+0.000
Christian
Token Christian
Feature activation+0.823
.
Token.
Feature activation+0.358
The
Token The
Feature activation+0.748
post
Token post
Feature activation+0.000
of
Token of
Feature activation+3.056
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
goes
Token goes
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000

Top DFA by src position
MAX = 5.396

German
Token German
Feature activation-0.113
Top resid features:
"
Token "
Feature activation+0.034
Top resid features:
B
TokenB
Feature activation-0.009
Top resid features:
ild
Tokenild
Feature activation-0.023
Top resid features:
",
Token",
Feature activation-0.027
Top resid features:
President
Token President
Feature activation+5.396
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Armenia
Token Armenia
Feature activation-0.006
Top resid features:
Ser
Token Ser
Feature activation-0.105
Top resid features:
zh
Tokenzh
Feature activation-0.020
Top resid features:
S
Token S
Feature activation-0.004
Top resid features:
actor
Token actor
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
who
Token who
Feature activation+0.014
Top resid features:
played
Token played
Feature activation+0.009
Top resid features:
fictional
Token fictional
Feature activation+0.305
Top resid features:
President
Token President
Feature activation+4.324
Top resid features:
Jos
Token Jos
Feature activation+0.047
Top resid features:
iah
Tokeniah
Feature activation-0.007
Top resid features:
Bart
Token Bart
Feature activation+0.007
Top resid features:
let
Tokenlet
Feature activation+0.008
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Auth
TokenAuth
Feature activation+0.001
Top resid features:
ors
Tokenors
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.095
Top resid features:
Obama
TokenObama
Feature activation+4.637
Top resid features:
Joker
Token Joker
Feature activation-0.035
Top resid features:
poster
Token poster
Feature activation+0.016
Top resid features:
hits
Token hits
Feature activation-0.001
Top resid features:
LA
Token LA
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
32
Token32
Feature activation-0.011
Top resid features:
PH
Token PH
Feature activation+0.001
Top resid features:
OTOS
TokenOTOS
Feature activation+0.027
Top resid features:
Inside
Token Inside
Feature activation+0.102
Top resid features:
President
Token President
Feature activation+4.027
Top resid features:
Trump
Token Trump
Feature activation+0.331
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
first
Token first
Feature activation+0.073
Top resid features:
70
Token 70
Feature activation+0.043
Top resid features:
days
Token days
Feature activation+0.051
Top resid features:
ALD
TokenALD
Feature activation-0.003
Top resid features:
TRUMP
Token TRUMP
Feature activation+0.125
Top resid features:
Is
Token Is
Feature activation+0.001
Top resid features:
First
Token First
Feature activation+0.099
Top resid features:
US
Token US
Feature activation+0.096
Top resid features:
President
Token President
Feature activation+1.304
Top resid features:
Inv
Token Inv
Feature activation-0.004
Top resid features:
ited
Tokenited
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
D
Token D
Feature activation+0.014
Top resid features:
ine
Tokenine
Feature activation+0.008
Top resid features:
1972
Token 1972
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
president
Token president
Feature activation+4.284
Top resid features:
âĢ
TokenâĢ
Feature activation-0.062
Top resid features:
Ļ
TokenĻ
Feature activation+0.015
Top resid features:
s
Tokens
Feature activation+0.038
Top resid features:
father
Token father
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
32
Token32
Feature activation-0.026
Top resid features:
PH
Token PH
Feature activation+0.006
Top resid features:
OTOS
TokenOTOS
Feature activation+0.114
Top resid features:
Inside
Token Inside
Feature activation-0.180
Top resid features:
President
Token President
Feature activation+4.170
Top resid features:
Trump
Token Trump
Feature activation+0.342
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.062
Top resid features:
70
Token 70
Feature activation-0.002
Top resid features:
days
Token days
Feature activation+0.039
Top resid features:
critical
Token critical
Feature activation-0.026
Top resid features:
tweets
Token tweets
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
calling
Token calling
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
president
Token president
Feature activation+1.505
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
monster
Tokenmonster
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
ALD
TokenALD
Feature activation-0.013
Top resid features:
TRUMP
Token TRUMP
Feature activation+0.083
Top resid features:
Is
Token Is
Feature activation+0.001
Top resid features:
First
Token First
Feature activation+0.121
Top resid features:
US
Token US
Feature activation+0.261
Top resid features:
President
Token President
Feature activation+1.288
Top resid features:
Inv
Token Inv
Feature activation-0.025
Top resid features:
ited
Tokenited
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
D
Token D
Feature activation+0.025
Top resid features:
ine
Tokenine
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
tweets
Token tweets
Feature activation-0.012
Top resid features:
about
Token about
Feature activation+0.003
Top resid features:
US
Token US
Feature activation+0.049
Top resid features:
President
Token President
Feature activation+2.875
Top resid features:
Donald
Token Donald
Feature activation+0.031
Top resid features:
Trump
Token Trump
Feature activation+0.623
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+0.013
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
friend
Token friend
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
President
Token President
Feature activation+4.043
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
involved
Token involved
Feature activation-0.002
Top resid features:
with
Token with
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Esc
Token Esc
Feature activation-0.017
Top resid features:
Happy
TokenHappy
Feature activation+0.002
Top resid features:
birthday
Token birthday
Feature activation+0.329
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
future
Token future
Feature activation-0.001
Top resid features:
president
Token president
Feature activation+3.479
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
pic
Token pic
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
twitter
Tokentwitter
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Auth
TokenAuth
Feature activation-0.002
Top resid features:
ors
Tokenors
Feature activation-0.005
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.158
Top resid features:
Obama
TokenObama
Feature activation+3.582
Top resid features:
Joker
Token Joker
Feature activation-0.053
Top resid features:
poster
Token poster
Feature activation+0.018
Top resid features:
hits
Token hits
Feature activation-0.005
Top resid features:
LA
Token LA
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
isn
Token isn
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation-0.031
Top resid features:
Ļ
TokenĻ
Feature activation+0.018
Top resid features:
t
Tokent
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
president
Token president
Feature activation+3.605
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
first
Token first
Feature activation+0.011
Top resid features:
ludicrous
Token ludicrous
Feature activation-0.010
Top resid features:
actor
Token actor
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
who
Token who
Feature activation+0.009
Top resid features:
played
Token played
Feature activation-0.000
Top resid features:
fictional
Token fictional
Feature activation+0.228
Top resid features:
President
Token President
Feature activation+3.129
Top resid features:
Jos
Token Jos
Feature activation+0.118
Top resid features:
iah
Tokeniah
Feature activation-0.047
Top resid features:
Bart
Token Bart
Feature activation+0.054
Top resid features:
let
Tokenlet
Feature activation+0.036
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
Trump
Token Trump
Feature activation+0.228
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
sworn
Token sworn
Feature activation+0.068
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
president
Token president
Feature activation+1.515
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
United
Token United
Feature activation-0.011
Top resid features:
States
Token States
Feature activation+0.148
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
People
TokenPeople
Feature activation-0.008
Top resid features:
wanted
Token wanted
Feature activation+0.003
Top resid features:
Congress
Token Congress
Feature activation+0.179
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.091
Top resid features:
president
Token president
Feature activation+3.428
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
address
Token address
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
economy
Token economy
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
1972
Token 1972
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
The
TokenThe
Feature activation+0.019
Top resid features:
president
Token president
Feature activation+2.038
Top resid features:
âĢ
TokenâĢ
Feature activation-0.133
Top resid features:
Ļ
TokenĻ
Feature activation+0.038
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
father
Token father
Feature activation+0.073
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.042
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
Leg
Token Leg
Feature activation+0.019
Top resid features:
itimate
Tokenitimate
Feature activation+0.056
Top resid features:
President
Token President
Feature activation+3.316
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Â
TokenÂ
Feature activation+0.014
Top resid features:
Ķ
TokenĶ
Feature activation-0.000
Top resid features:
saying
Token saying
Feature activation-0.000
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
deal
Token deal
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Lebanon
Token Lebanon
Feature activation-0.031
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
presidency
Token presidency
Feature activation+3.522
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
reserved
Token reserved
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
Mar
Token Mar
Feature activation-0.156
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.03

Head 3: 0.08

Head 4: 0.03

Head 5: 0.02

Head 6: 0.43

Head 7: 0.10

Head 8: 0.02

Head 9: 0.06

Head 10: 0.04

Head 11: 0.08

Positive logits

presidents7.46

president7.18

President6.92

President6.77

Obama6.72

Obama6.63

OTUS6.53

Presidents6.40

presidency6.34

Barack6.24

presidential6.19

PRESIDENT6.14

Presidential6.12

president5.95

administrations5.42

Oval5.40

Presidency5.39

administration5.37

inauguration5.18

Administration5.11

Negative logits

iHUD-3.28

Detect-2.98

Albion-2.86

ammers-2.83

Ont-2.81

Vill-2.81

Detect-2.81

Bram-2.80

heet-2.79

detective-2.71

atown-2.65

Cardiff-2.64

Constable-2.63

Gladiator-2.57

alys-2.57

finder-2.56

Sheffield-2.56

ondon-2.56

detectives-2.55

liga-2.55

INTERVAL 4.268 - 4.743
CONTAINS 0.000%

situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
,
Token,
Feature activation+1.766
the
Token the
Feature activation+4.743
President
Token President
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
time
Token time
Feature activation+0.000
playing
Token playing
Feature activation+3.199
the
Token the
Feature activation+4.428
president
Token president
Feature activation+0.639
on
Token on
Feature activation+1.050
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.280
The
TokenThe
Feature activation+0.623

INTERVAL 3.794 - 4.268
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.366
s
Tokens
Feature activation+0.210
also
Token also
Feature activation+0.048
the
Token the
Feature activation+1.000
first
Token first
Feature activation+3.845
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.242
S
TokenS
Feature activation+1.998
.
Token.
Feature activation+4.012
President
Token President
Feature activation+0.000
's
Token's
Feature activation+0.312
first
Token first
Feature activation+0.000
70
Token 70
Feature activation+0.000
days
Token days
Feature activation+0.681
See
Token See
Feature activation+0.000
Gallery
Token Gallery
Feature activation+3.869
Inside
Token Inside
Feature activation+4.028
President
Token President
Feature activation+1.162
Trump
Token Trump
Feature activation+0.271
's
Token's
Feature activation+1.260
first
Token first
Feature activation+0.397
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.403
s
Tokens
Feature activation+0.400
father
Token father
Feature activation+3.114
,
Token,
Feature activation+3.918
Barack
Token Barack
Feature activation+0.103
Obama
Token Obama
Feature activation+0.255
Sr
Token Sr
Feature activation+0.000
.,
Token.,
Feature activation+0.908
and
Token and
Feature activation+2.804
first
Token first
Feature activation+0.000
70
Token 70
Feature activation+0.000
days
Token days
Feature activation+0.681
See
Token See
Feature activation+0.000
Gallery
Token Gallery
Feature activation+3.869
Inside
Token Inside
Feature activation+4.028
President
Token President
Feature activation+1.162
Trump
Token Trump
Feature activation+0.271
's
Token's
Feature activation+1.260
first
Token first
Feature activation+0.397
70
Token 70
Feature activation+0.199
to
Token to
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
that
Token that
Feature activation+1.014
the
Token the
Feature activation+3.857
president
Token president
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
ignore
Token ignore
Feature activation+0.000
her
Token her
Feature activation+0.000

INTERVAL 3.320 - 3.794
CONTAINS 0.000%

of
Token of
Feature activation+0.000
critical
Token critical
Feature activation+0.000
tweets
Token tweets
Feature activation+0.000
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+0.000
the
Token the
Feature activation+3.679
president
Token president
Feature activation+0.000
a
Token a
Feature activation+0.303
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
monster
Tokenmonster
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
(@
Token (@
Feature activation+0.251
Hillary
TokenHillary
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
)
Token)
Feature activation+3.541
October
Token October
Feature activation+0.049
26
Token 26
Feature activation+0.000
,
Token,
Feature activation+1.936
2016
Token 2016
Feature activation+0.174
Ċ
TokenĊ
Feature activation+0.000
Esc
Token Esc
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
edo
Tokenedo
Feature activation+0.000
drug
Token drug
Feature activation+0.000
cartel
Token cartel
Feature activation+0.000
,
Token,
Feature activation+3.562
the
Token the
Feature activation+2.634
White
Token White
Feature activation+0.197
House
Token House
Feature activation+0.639
wants
Token wants
Feature activation+1.516
to
Token to
Feature activation+0.832

INTERVAL 2.846 - 3.320
CONTAINS 0.001%

things
Token things
Feature activation+0.000
.
Token.
Feature activation+1.228
Back
Token Back
Feature activation+0.000
in
Token in
Feature activation+0.233
August
Token August
Feature activation+0.139
,
Token,
Feature activation+3.243
an
Token an
Feature activation+1.375
inf
Token inf
Feature activation+0.000
latable
Tokenlatable
Feature activation+1.216
chicken
Token chicken
Feature activation+0.000
made
Token made
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
time
Token time
Feature activation+0.000
playing
Token playing
Feature activation+3.199
the
Token the
Feature activation+4.428
president
Token president
Feature activation+0.639
on
Token on
Feature activation+1.050
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.280
The
TokenThe
Feature activation+0.697
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.403
s
Tokens
Feature activation+0.400
father
Token father
Feature activation+3.114
,
Token,
Feature activation+3.918
Barack
Token Barack
Feature activation+0.103
Obama
Token Obama
Feature activation+0.255
Sr
Token Sr
Feature activation+0.000
.,
Token.,
Feature activation+0.908
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.261
s
Tokens
Feature activation+1.400
version
Token version
Feature activation+0.000
of
Token of
Feature activation+1.158
the
Token the
Feature activation+3.025
Joker
Token Joker
Feature activation+0.000
in
Token in
Feature activation+1.244
The
Token The
Feature activation+1.800
Dark
Token Dark
Feature activation+0.000
Knight
Token Knight
Feature activation+0.000
up
Token up
Feature activation+0.000
within
Token within
Feature activation+0.000
visual
Token visual
Feature activation+0.000
range
Token range
Feature activation+0.000
of
Token of
Feature activation+1.938
the
Token the
Feature activation+2.971
White
Token White
Feature activation+0.039
House
Token House
Feature activation+0.000
,
Token,
Feature activation+0.000
thereby
Token thereby
Feature activation+0.197
causing
Token causing
Feature activation+0.936

INTERVAL 2.371 - 2.846
CONTAINS 0.004%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.565
Trump
TokenTrump
Feature activation+1.115
era
Token era
Feature activation+0.019
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.602
,
Token,
Feature activation+0.510
65
Token 65
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.549
Americans
Token Americans
Feature activation+0.000
more
Token more
Feature activation+1.741
like
Token like
Feature activation+1.194
a
Token a
Feature activation+0.667
mafia
Token mafia
Feature activation+0.000
boss
Token boss
Feature activation+0.000
than
Token than
Feature activation+2.709
the
Token the
Feature activation+1.102
president
Token president
Feature activation+0.000
of
Token of
Feature activation+1.286
a
Token a
Feature activation+0.237
free
Token free
Feature activation+0.000
President
Token President
Feature activation+0.374
Recep
Token Recep
Feature activation+0.835
Tayyip
Token Tayyip
Feature activation+0.294
Erdogan
Token Erdogan
Feature activation+0.255
and
Token and
Feature activation+0.661
Indonesian
Token Indonesian
Feature activation+2.571
President
Token President
Feature activation+0.000
J
Token J
Feature activation+0.000
oko
Tokenoko
Feature activation+0.000
Wid
Token Wid
Feature activation+0.000
odo
Tokenodo
Feature activation+0.000
The
Token The
Feature activation+0.609
77
Token 77
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+2.068
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+2.450
has
Token has
Feature activation+0.000
advocated
Token advocated
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
end
Token end
Feature activation+0.000
validity
Token validity
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.476
s
Tokens
Feature activation+0.640
premise
Token premise
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
150
Token 150
Feature activation+0.000

INTERVAL 1.897 - 2.371
CONTAINS 0.007%

to
Token to
Feature activation+0.476
post
Token post
Feature activation+0.913
this
Token this
Feature activation+0.445
freedom
Token freedom
Feature activation+0.000
anthem
Token anthem
Feature activation+0.000
on
Token on
Feature activation+2.033
this
Token this
Feature activation+1.467
particular
Token particular
Feature activation+1.027
bank
Token bank
Feature activation+0.000
holiday
Token holiday
Feature activation+0.000
.
Token.
Feature activation+0.661
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
in
Token in
Feature activation+1.193
his
Token his
Feature activation+1.969
inaugural
Token inaugural
Feature activation+0.287
address
Token address
Feature activation+0.000
.
Token.
Feature activation+0.319
(
Token (
Feature activation+0.100
Photo
TokenPhoto
Feature activation+0.000
"
Token "
Feature activation+0.000
Part
TokenPart
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
,"
Token,"
Feature activation+2.164
said
Token said
Feature activation+1.987
Obama
Token Obama
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
is
Tokenis
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
also
Token also
Feature activation+0.048
the
Token the
Feature activation+1.000
first
Token first
Feature activation+3.845
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.242
S
TokenS
Feature activation+1.998
.
Token.
Feature activation+4.012
President
Token President
Feature activation+0.000
to
Token to
Feature activation+0.593
be
Token be
Feature activation+0.000
given
Token given
Feature activation+0.403
tacos
Token tacos
Feature activation+0.000
!
Token!
Feature activation+0.000
President
Token President
Feature activation+0.198
@
Token @
Feature activation+2.273
EP
TokenEP
Feature activation+0.907
N
TokenN
Feature activation+2.227
and
Token and
Feature activation+0.000
PM
Token PM
Feature activation+0.051
@
Token @
Feature activation+0.151
n
Tokenn
Feature activation+0.000
are
Tokenare
Feature activation+0.000

INTERVAL 1.423 - 1.897
CONTAINS 0.014%

BRE
TokenBRE
Feature activation+0.000
AKING
TokenAKING
Feature activation+0.000
:
Token:
Feature activation+0.278
Morris
Token Morris
Feature activation+0.000
sey
Tokensey
Feature activation+1.440
being
Token being
Feature activation+1.495
sworn
Token sworn
Feature activation+0.000
in
Token in
Feature activation+1.056
by
Token by
Feature activation+0.330
House
Token House
Feature activation+0.000
Clerk
Token Clerk
Feature activation+0.000
made
Token made
Feature activation+0.001
the
Token the
Feature activation+0.819
transformation
Token transformation
Feature activation+0.000
from
Token from
Feature activation+0.793
campaigner
Token campaigner
Feature activation+0.000
to
Token to
Feature activation+1.456
chief
Token chief
Feature activation+0.600
executive
Token executive
Feature activation+0.269
.
Token.
Feature activation+0.190
Cont
Token Cont
Feature activation+0.000
rovers
Tokenrovers
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
is
Token is
Feature activation+0.558
the
Token the
Feature activation+0.712
worst
Token worst
Feature activation+1.759
and
Token and
Feature activation+0.136
Trump
Token Trump
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.950
Melania
Token Melania
Feature activation+0.010
were
Token were
Feature activation+0.000
treated
Token treated
Feature activation+0.000
like
Token like
Feature activation+0.264
royalty
Token royalty
Feature activation+0.000
during
Token during
Feature activation+1.478
their
Token their
Feature activation+0.802
visit
Token visit
Feature activation+0.000
to
Token to
Feature activation+0.179
Beijing
Token Beijing
Feature activation+0.000
.
Token.
Feature activation+0.968
letter
Token letter
Feature activation+0.000
is
Token is
Feature activation+0.000
below
Token below
Feature activation+0.000
:
Token:
Feature activation+0.650
Ċ
TokenĊ
Feature activation+0.011
Ċ
TokenĊ
Feature activation+1.855
Contact
TokenContact
Feature activation+0.000
us
Token us
Feature activation+0.000
at
Token at
Feature activation+0.000
editors
Token editors
Feature activation+0.000
@
Token@
Feature activation+0.000

INTERVAL 0.949 - 1.423
CONTAINS 0.038%

,'
Token,'
Feature activation+1.508
she
Token she
Feature activation+0.254
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.837
her
Token her
Feature activation+1.522
first
Token first
Feature activation+0.978
direct
Token direct
Feature activation+0.221
response
Token response
Feature activation+0.000
to
Token to
Feature activation+0.373
the
Token the
Feature activation+1.341
November
Token November
Feature activation+0.329
convinced
Token convinced
Feature activation+0.362
that
Token that
Feature activation+0.067
he
Token he
Feature activation+0.000
remains
Token remains
Feature activation+0.268
our
Token our
Feature activation+0.937
greatest
Token greatest
Feature activation+0.957
hope
Token hope
Feature activation+0.000
.
Token.
Feature activation+0.390
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.287
Yet
TokenYet
Feature activation+0.707
move
Token move
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.370
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.064
'
Token'
Feature activation+1.192
Now
TokenNow
Feature activation+0.516
we
Token we
Feature activation+0.000
're
Token're
Feature activation+1.030
feeling
Token feeling
Feature activation+0.000
what
Token what
Feature activation+0.394
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.155
bring
Token bring
Feature activation+0.313
WWII
Token WWII
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
to
Token to
Feature activation+1.394
the
Token the
Feature activation+2.462
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.031
s
Tokens
Feature activation+0.623
2016
Token 2016
Feature activation+0.000
:
Token:
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.086
s
Tokens
Feature activation+1.110
America
Token America
Feature activation+0.082
,
Token,
Feature activation+0.000
arch
Token arch
Feature activation+0.000
-
Token-
Feature activation+0.820
conservative
Tokenconservative
Feature activation+0.068

INTERVAL 0.474 - 0.949
CONTAINS 0.101%

thinks
Token thinks
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
men
Token men
Feature activation+0.000
's
Token's
Feature activation+0.498
basketball
Token basketball
Feature activation+0.294
team
Token team
Feature activation+0.000
plays
Token plays
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
46
Token46
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.697
States
Token States
Feature activation+0.000
received
Token received
Feature activation+0.000
the
Token the
Feature activation+0.000
vast
Token vast
Feature activation+0.000
exp
Token exp
Feature activation+0.000
for
Token for
Feature activation+1.978
President
Token President
Feature activation+0.063
and
Token and
Feature activation+0.576
refuses
Token refuses
Feature activation+0.269
to
Token to
Feature activation+0.000
answer
Token answer
Feature activation+0.522
on
Token on
Feature activation+0.275
key
Token key
Feature activation+0.000
issues
Token issues
Feature activation+0.000
that
Token that
Feature activation+0.166
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.254
billionaire
Token billionaire
Feature activation+0.585
businessman
Token businessman
Feature activation+0.000
has
Token has
Feature activation+0.000
voc
Token voc
Feature activation+0.000
ifer
Tokenifer
Feature activation+0.000
ously
Tokenously
Feature activation+0.000
question
Token question
Feature activation+0.000
about
Token about
Feature activation+0.390
what
Token what
Feature activation+0.413
powers
Token powers
Feature activation+1.168
an
Token an
Feature activation+0.353
Acting
Token Acting
Feature activation+0.633
AG
Token AG
Feature activation+0.000
can
Token can
Feature activation+0.045
perform
Token perform
Feature activation+0.000
.
Token.
Feature activation+0.087
But
Token But
Feature activation+0.289

INTERVAL 0.000 - 0.474
CONTAINS 99.834%

jet
Token jet
Feature activation+0.000
or
Token or
Feature activation+0.000
bomber
Token bomber
Feature activation+0.000
has
Token has
Feature activation+0.000
gone
Token gone
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
21
Token 21
Feature activation+0.000
st
Tokenst
Feature activation+0.000
century
Token century
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
strange
Token strange
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
closure
Token closure
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
legacy
Token legacy
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
residential
Token residential
Feature activation+0.000
fun
Token fun
Feature activation+0.000
color
Token color
Feature activation+0.000
g
Token g
Feature activation+0.000
els
Tokenels
Feature activation+0.000
in
Token in
Feature activation+0.000
blue
Token blue
Feature activation+0.000
,
Token,
Feature activation+0.000
red
Token red
Feature activation+0.000
,
Token,
Feature activation+0.000
purple
Token purple
Feature activation+0.000
and
Token and
Feature activation+0.000
Jer
Token Jer
Feature activation+0.000
mel
Tokenmel
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Con
TokenCon
Feature activation+0.000
v
Tokenv
Feature activation+0.000
iction
Tokeniction
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 8 in H10.6: (feature 15442)

TOP ACTIVATIONS
MAX = 6.993

"
Token"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.986
General
Token General
Feature activation+6.993
Eric
Token Eric
Feature activation+4.378
Holder
Token Holder
Feature activation+1.114
has
Token has
Feature activation+0.712
been
Token been
Feature activation+0.331
held
Token held
Feature activation+0.000
The
TokenThe
Feature activation+3.468
Nevada
Token Nevada
Feature activation+3.212
U
Token U
Feature activation+2.134
.
Token.
Feature activation+0.788
S
TokenS
Feature activation+2.462
.
Token.
Feature activation+5.802
Attorney
Token Attorney
Feature activation+1.377
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.178
s
Tokens
Feature activation+1.306
Office
Token Office
Feature activation+0.706
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.105
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.964
s
Tokens
Feature activation+1.244
Office
Token Office
Feature activation+1.543
says
Token says
Feature activation+0.867
collections
Token collections
Feature activation+0.000
exceed
Token exceed
Feature activation+0.000
ed
Tokened
Feature activation+0.000
soph
Token soph
Feature activation+0.000
istry
Tokenistry
Feature activation+0.000
,
Token,
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.836
General
Token General
Feature activation+4.793
Eric
Token Eric
Feature activation+3.927
Holder
Token Holder
Feature activation+0.225
told
Token told
Feature activation+0.148
an
Token an
Feature activation+0.261
audience
Token audience
Feature activation+0.000
Mr
TokenMr
Feature activation+0.888
Holder
Token Holder
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+2.342
first
Token first
Feature activation+4.556
sitting
Token sitting
Feature activation+4.577
attorney
Token attorney
Feature activation+1.916
general
Token general
Feature activation+1.961
and
Token and
Feature activation+0.405
US
Token US
Feature activation+1.432
presidential
Token presidential
Feature activation+0.549
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.888
Holder
Token Holder
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+2.342
first
Token first
Feature activation+4.556
sitting
Token sitting
Feature activation+4.577
attorney
Token attorney
Feature activation+1.916
general
Token general
Feature activation+1.961
and
Token and
Feature activation+0.405
US
Token US
Feature activation+1.432
.
Token.
Feature activation+3.486
But
Token But
Feature activation+4.062
the
Token the
Feature activation+3.825
partisan
Token partisan
Feature activation+1.935
grip
Token grip
Feature activation+0.000
squeezing
Token squeezing
Feature activation+4.488
Washington
Token Washington
Feature activation+1.548
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.166
the
Token the
Feature activation+0.406
agency
Token agency
Feature activation+0.000
to
Token to
Feature activation+0.000
gender
Token gender
Feature activation+0.000
identity
Token identity
Feature activation+0.000
,
Token,
Feature activation+1.485
the
Token the
Feature activation+2.618
attorneys
Token attorneys
Feature activation+4.474
general
Token general
Feature activation+0.000
also
Token also
Feature activation+0.028
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.986
General
Token General
Feature activation+6.993
Eric
Token Eric
Feature activation+4.378
Holder
Token Holder
Feature activation+1.114
has
Token has
Feature activation+0.712
been
Token been
Feature activation+0.331
held
Token held
Feature activation+0.000
in
Token in
Feature activation+0.000
is
Token is
Feature activation+0.394
quick
Token quick
Feature activation+0.000
to
Token to
Feature activation+0.000
blame
Token blame
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+4.232
Liberal
Token Liberal
Feature activation+2.250
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.669
Liberal
Token Liberal
Feature activation+1.460
MLA
Token MLA
Feature activation+0.000
.
Token.
Feature activation+0.000
Leading
Token Leading
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
and
Token and
Feature activation+4.068
attorney
Token attorney
Feature activation+0.000
Ben
Token Ben
Feature activation+0.000
Gins
Token Gins
Feature activation+0.000
berg
Tokenberg
Feature activation+0.000
put
Token put
Feature activation+0.000
of
Token of
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
general
Token general
Feature activation+2.514
.
Token.
Feature activation+3.486
But
Token But
Feature activation+4.062
the
Token the
Feature activation+3.825
partisan
Token partisan
Feature activation+1.935
grip
Token grip
Feature activation+0.000
squeezing
Token squeezing
Feature activation+4.488
Washington
Token Washington
Feature activation+1.548
super
Token super
Feature activation+0.000
charged
Tokencharged
Feature activation+0.426
politics
Token politics
Feature activation+0.000
,
Token,
Feature activation+0.000
mean
Token mean
Feature activation+3.932
that
Token that
Feature activation+4.005
anyone
Token anyone
Feature activation+1.836
chosen
Token chosen
Feature activation+0.466
for
Token for
Feature activation+2.594
the
Token the
Feature activation+2.265
job
Token job
Feature activation+0.000
s
Tokens
Feature activation+0.000
super
Token super
Feature activation+0.000
charged
Tokencharged
Feature activation+0.426
politics
Token politics
Feature activation+0.000
,
Token,
Feature activation+0.000
mean
Token mean
Feature activation+3.932
that
Token that
Feature activation+4.005
anyone
Token anyone
Feature activation+1.836
chosen
Token chosen
Feature activation+0.466
for
Token for
Feature activation+2.594
the
Token the
Feature activation+2.265
soph
Token soph
Feature activation+0.000
istry
Tokenistry
Feature activation+0.000
,
Token,
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.836
General
Token General
Feature activation+4.793
Eric
Token Eric
Feature activation+3.927
Holder
Token Holder
Feature activation+0.225
told
Token told
Feature activation+0.148
an
Token an
Feature activation+0.261
audience
Token audience
Feature activation+0.000
at
Token at
Feature activation+0.918
Johnson
Token Johnson
Feature activation+0.000
,
Token,
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.000
General
Token General
Feature activation+1.834
Lore
Token Lore
Feature activation+0.000
tta
Tokentta
Feature activation+3.915
Lynch
Token Lynch
Feature activation+0.000
,
Token,
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
Director
Token Director
Feature activation+0.000
James
Token James
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
general
Token general
Feature activation+2.514
.
Token.
Feature activation+3.486
But
Token But
Feature activation+4.062
the
Token the
Feature activation+3.825
partisan
Token partisan
Feature activation+1.935
grip
Token grip
Feature activation+0.000
squeezing
Token squeezing
Feature activation+4.488
Washington
Token Washington
Feature activation+1.548
,
Token,
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.282
s
Tokens
Feature activation+1.803
biggest
Token biggest
Feature activation+1.139
foe
Token foe
Feature activation+3.556
,
Token,
Feature activation+2.813
House
Token House
Feature activation+1.866
Financial
Token Financial
Feature activation+0.000
Services
Token Services
Feature activation+0.000
Chairman
Token Chairman
Feature activation+0.000
ranks
Token ranks
Feature activation+0.000
of
Token of
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
general
Token general
Feature activation+2.514
.
Token.
Feature activation+3.486
But
Token But
Feature activation+4.062
the
Token the
Feature activation+3.825
partisan
Token partisan
Feature activation+1.935
grip
Token grip
Feature activation+0.000
squeezing
Token squeezing
Feature activation+4.488
exceed
Token exceed
Feature activation+0.000
appropriated
Token appropriated
Feature activation+0.000
budget
Token budget
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.059
Ċ
TokenĊ
Feature activation+1.898
The
TokenThe
Feature activation+3.468
Nevada
Token Nevada
Feature activation+3.212
U
Token U
Feature activation+2.134
.
Token.
Feature activation+0.788
S
TokenS
Feature activation+2.462
.
Token.
Feature activation+5.802

Top DFA by src position
MAX = 5.679

ue
Tokenue
Feature activation-0.003
Top resid features:
"
Token"
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
US
TokenUS
Feature activation-0.027
Top resid features:
Attorney
Token Attorney
Feature activation+3.624
Top resid features:
General
Token General
Feature activation+3.547
Top resid features:
Eric
Token Eric
Feature activation+0.000
Top resid features:
Holder
Token Holder
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
ada
Tokenada
Feature activation+0.011
Top resid features:
U
Token U
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
S
TokenS
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Attorney
Token Attorney
Feature activation+5.679
Top resid features:
âĢ
TokenâĢ
Feature activation+0.041
Top resid features:
Ļ
TokenĻ
Feature activation+0.043
Top resid features:
s
Tokens
Feature activation+0.084
Top resid features:
Office
Token Office
Feature activation+0.150
Top resid features:
says
Token says
Feature activation-0.030
Top resid features:
ada
Tokenada
Feature activation-0.027
Top resid features:
U
Token U
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
S
TokenS
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Attorney
Token Attorney
Feature activation+5.039
Top resid features:
âĢ
TokenâĢ
Feature activation+0.099
Top resid features:
Ļ
TokenĻ
Feature activation+0.283
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
Office
Token Office
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation-0.003
Top resid features:
soph
Token soph
Feature activation-0.005
Top resid features:
istry
Tokenistry
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.053
Top resid features:
Attorney
Token Attorney
Feature activation+1.891
Top resid features:
General
Token General
Feature activation+3.347
Top resid features:
Eric
Token Eric
Feature activation+0.000
Top resid features:
Holder
Token Holder
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
audience
Token audience
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
US
TokenUS
Feature activation-0.064
Top resid features:
Attorney
Token Attorney
Feature activation+1.133
Top resid features:
General
Token General
Feature activation+3.202
Top resid features:
Eric
Token Eric
Feature activation+0.019
Top resid features:
Holder
Token Holder
Feature activation+0.127
Top resid features:
has
Token has
Feature activation+0.006
Top resid features:
been
Token been
Feature activation+0.003
Top resid features:
held
Token held
Feature activation-0.003
Top resid features:
"
Token"
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
US
TokenUS
Feature activation-0.106
Top resid features:
Attorney
Token Attorney
Feature activation+1.677
Top resid features:
General
Token General
Feature activation+3.070
Top resid features:
Eric
Token Eric
Feature activation+0.030
Top resid features:
Holder
Token Holder
Feature activation+0.137
Top resid features:
has
Token has
Feature activation+0.014
Top resid features:
been
Token been
Feature activation+0.009
Top resid features:
held
Token held
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
ranks
Token ranks
Feature activation-0.010
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
Republican
Token Republican
Feature activation-0.128
Top resid features:
attorneys
Token attorneys
Feature activation+1.646
Top resid features:
general
Token general
Feature activation+3.424
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
But
Token But
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
partisan
Token partisan
Feature activation-0.114
Top resid features:
grip
Token grip
Feature activation-0.025
Top resid features:
law
Token law
Feature activation-0.001
Top resid features:
."
Token."
Feature activation+0.038
Top resid features:
But
Token But
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
attorneys
Token attorneys
Feature activation+0.148
Top resid features:
general
Token general
Feature activation+4.492
Top resid features:
asked
Token asked
Feature activation+0.013
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.001
Top resid features:
existing
Tokenexisting
Feature activation-0.001
Top resid features:
statute
Token statute
Feature activation-0.000
Top resid features:
"
Token"
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
US
TokenUS
Feature activation-0.016
Top resid features:
Attorney
Token Attorney
Feature activation+1.732
Top resid features:
General
Token General
Feature activation+2.839
Top resid features:
Eric
Token Eric
Feature activation+0.040
Top resid features:
Holder
Token Holder
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
held
Token held
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
While
TokenWhile
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
new
Token new
Feature activation-0.005
Top resid features:
attorney
Token attorney
Feature activation+0.723
Top resid features:
general
Token general
Feature activation+4.146
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
quick
Token quick
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
blame
Token blame
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
Leading
Token Leading
Feature activation-0.015
Top resid features:
Republican
Token Republican
Feature activation-0.019
Top resid features:
presidential
Token presidential
Feature activation-0.022
Top resid features:
campaigns
Token campaigns
Feature activation-0.009
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
attorney
Token attorney
Feature activation+4.611
Top resid features:
Ben
Token Ben
Feature activation-0.019
Top resid features:
Gins
Token Gins
Feature activation+0.002
Top resid features:
berg
Tokenberg
Feature activation-0.007
Top resid features:
put
Token put
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
ranks
Token ranks
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
Republican
Token Republican
Feature activation-0.165
Top resid features:
attorneys
Token attorneys
Feature activation+1.850
Top resid features:
general
Token general
Feature activation+2.617
Top resid features:
.
Token.
Feature activation+0.081
Top resid features:
But
Token But
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
partisan
Token partisan
Feature activation+0.000
Top resid features:
grip
Token grip
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ranks
Token ranks
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
Republican
Token Republican
Feature activation-0.098
Top resid features:
attorneys
Token attorneys
Feature activation+1.696
Top resid features:
general
Token general
Feature activation+3.025
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
But
Token But
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
partisan
Token partisan
Feature activation-0.078
Top resid features:
grip
Token grip
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
ranks
Token ranks
Feature activation-0.007
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
Republican
Token Republican
Feature activation-0.099
Top resid features:
attorneys
Token attorneys
Feature activation+1.843
Top resid features:
general
Token general
Feature activation+2.922
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
But
Token But
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
partisan
Token partisan
Feature activation-0.078
Top resid features:
grip
Token grip
Feature activation-0.004
Top resid features:
ed
Tokened
Feature activation-0.007
Top resid features:
soph
Token soph
Feature activation-0.004
Top resid features:
istry
Tokenistry
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
Attorney
Token Attorney
Feature activation+1.422
Top resid features:
General
Token General
Feature activation+2.757
Top resid features:
Eric
Token Eric
Feature activation+0.059
Top resid features:
Holder
Token Holder
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
audience
Token audience
Feature activation+0.000
Top resid features:
Secretary
Token Secretary
Feature activation-0.002
Top resid features:
Je
Token Je
Feature activation-0.007
Top resid features:
h
Tokenh
Feature activation-0.003
Top resid features:
Johnson
Token Johnson
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
Attorney
Token Attorney
Feature activation+2.816
Top resid features:
General
Token General
Feature activation+1.151
Top resid features:
Lore
Token Lore
Feature activation+0.233
Top resid features:
tta
Tokentta
Feature activation+0.039
Top resid features:
Lynch
Token Lynch
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
ranks
Token ranks
Feature activation-0.045
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Republican
Token Republican
Feature activation-0.115
Top resid features:
attorneys
Token attorneys
Feature activation+0.952
Top resid features:
general
Token general
Feature activation+3.049
Top resid features:
.
Token.
Feature activation+0.146
Top resid features:
But
Token But
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
partisan
Token partisan
Feature activation+0.000
Top resid features:
grip
Token grip
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
ranks
Token ranks
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Republican
Token Republican
Feature activation-0.033
Top resid features:
attorneys
Token attorneys
Feature activation+1.358
Top resid features:
general
Token general
Feature activation+2.239
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
But
Token But
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
partisan
Token partisan
Feature activation-0.008
Top resid features:
grip
Token grip
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
ranks
Token ranks
Feature activation-0.018
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
Republican
Token Republican
Feature activation-0.135
Top resid features:
attorneys
Token attorneys
Feature activation+1.643
Top resid features:
general
Token general
Feature activation+2.154
Top resid features:
.
Token.
Feature activation+0.080
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
partisan
Token partisan
Feature activation+0.000
Top resid features:
grip
Token grip
Feature activation+0.000
Top resid features:
ada
Tokenada
Feature activation-0.090
Top resid features:
U
Token U
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
S
TokenS
Feature activation-0.026
Top resid features:
.
Token.
Feature activation-0.039
Top resid features:
Attorney
Token Attorney
Feature activation+3.195
Top resid features:
âĢ
TokenâĢ
Feature activation+0.094
Top resid features:
Ļ
TokenĻ
Feature activation+0.033
Top resid features:
s
Tokens
Feature activation+0.053
Top resid features:
Office
Token Office
Feature activation+0.449
Top resid features:
says
Token says
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.03

Head 2: 0.04

Head 3: 0.04

Head 4: 0.04

Head 5: 0.03

Head 6: 0.43

Head 7: 0.10

Head 8: 0.02

Head 9: 0.05

Head 10: 0.08

Head 11: 0.04

Positive logits

Attorney7.09

Attorney7.08

DOJ6.18

attorney5.98

prosecut5.77

AG5.57

attorneys5.29

orneys5.07

prosecutor4.88

Justice4.87

prosecutors4.76

Justice4.74

lawy4.73

prosecutions4.69

prosecuting4.66

Holder4.46

Prosecutors4.46

Prosecut4.36

Prosecutor4.29

lawyer4.24

Negative logits

obyl-2.86

Pole-2.68

price-2.64

Panc-2.60

Contest-2.60

pole-2.57

quickShipAvailable-2.53

Trident-2.52

Condition-2.49

Curve-2.49

inea-2.48

orthodox-2.45

pole-2.43

winner-2.41

Fest-2.38

Haku-2.37

PASS-2.36

condition-2.35

Chest-2.35

Entry-2.34

INTERVAL 6.293 - 6.993
CONTAINS 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
Attorney
Token Attorney
Feature activation+0.986
General
Token General
Feature activation+6.993
Eric
Token Eric
Feature activation+4.378
Holder
Token Holder
Feature activation+1.114
has
Token has
Feature activation+0.712
been
Token been
Feature activation+0.331
held
Token held
Feature activation+0.000

INTERVAL 5.594 - 6.293
CONTAINS 0.000%

The
TokenThe
Feature activation+3.468
Nevada
Token Nevada
Feature activation+3.212
U
Token U
Feature activation+2.134
.
Token.
Feature activation+0.788
S
TokenS
Feature activation+2.462
.
Token.
Feature activation+5.802
Attorney
Token Attorney
Feature activation+1.377
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.178
s
Tokens
Feature activation+1.306
Office
Token Office
Feature activation+0.706

INTERVAL 4.895 - 5.594
CONTAINS 0.000%

.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.105
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.964
s
Tokens
Feature activation+1.244
Office
Token Office
Feature activation+1.543
says
Token says
Feature activation+0.867
collections
Token collections
Feature activation+0.000
exceed
Token exceed
Feature activation+0.000

INTERVAL 4.196 - 4.895
CONTAINS 0.001%

ed
Tokened
Feature activation+0.000
soph
Token soph
Feature activation+0.000
istry
Tokenistry
Feature activation+0.000
,
Token,
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.836
General
Token General
Feature activation+4.793
Eric
Token Eric
Feature activation+3.927
Holder
Token Holder
Feature activation+0.225
told
Token told
Feature activation+0.148
an
Token an
Feature activation+0.261
audience
Token audience
Feature activation+0.000
Mr
TokenMr
Feature activation+0.888
Holder
Token Holder
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+2.342
first
Token first
Feature activation+4.556
sitting
Token sitting
Feature activation+4.577
attorney
Token attorney
Feature activation+1.916
general
Token general
Feature activation+1.961
and
Token and
Feature activation+0.405
US
Token US
Feature activation+1.432
presidential
Token presidential
Feature activation+0.549
.
Token.
Feature activation+3.486
But
Token But
Feature activation+4.062
the
Token the
Feature activation+3.825
partisan
Token partisan
Feature activation+1.935
grip
Token grip
Feature activation+0.000
squeezing
Token squeezing
Feature activation+4.488
Washington
Token Washington
Feature activation+1.548
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.166
the
Token the
Feature activation+0.406
agency
Token agency
Feature activation+0.000
is
Token is
Feature activation+0.394
quick
Token quick
Feature activation+0.000
to
Token to
Feature activation+0.000
blame
Token blame
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+4.232
Liberal
Token Liberal
Feature activation+2.250
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.669
Liberal
Token Liberal
Feature activation+1.460
MLA
Token MLA
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.986
General
Token General
Feature activation+6.993
Eric
Token Eric
Feature activation+4.378
Holder
Token Holder
Feature activation+1.114
has
Token has
Feature activation+0.712
been
Token been
Feature activation+0.331
held
Token held
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 3.496 - 4.196
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
super
Token super
Feature activation+0.000
charged
Tokencharged
Feature activation+0.426
politics
Token politics
Feature activation+0.000
,
Token,
Feature activation+0.000
mean
Token mean
Feature activation+3.932
that
Token that
Feature activation+4.005
anyone
Token anyone
Feature activation+1.836
chosen
Token chosen
Feature activation+0.466
for
Token for
Feature activation+2.594
the
Token the
Feature activation+2.265
soph
Token soph
Feature activation+0.000
istry
Tokenistry
Feature activation+0.000
,
Token,
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.836
General
Token General
Feature activation+4.793
Eric
Token Eric
Feature activation+3.927
Holder
Token Holder
Feature activation+0.225
told
Token told
Feature activation+0.148
an
Token an
Feature activation+0.261
audience
Token audience
Feature activation+0.000
at
Token at
Feature activation+0.918
ray
Tokenray
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.282
s
Tokens
Feature activation+1.803
biggest
Token biggest
Feature activation+1.139
foe
Token foe
Feature activation+3.556
,
Token,
Feature activation+2.813
House
Token House
Feature activation+1.866
Financial
Token Financial
Feature activation+0.000
Services
Token Services
Feature activation+0.000
Chairman
Token Chairman
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
general
Token general
Feature activation+2.514
.
Token.
Feature activation+3.486
But
Token But
Feature activation+4.062
the
Token the
Feature activation+3.825
partisan
Token partisan
Feature activation+1.935
grip
Token grip
Feature activation+0.000
squeezing
Token squeezing
Feature activation+4.488
Washington
Token Washington
Feature activation+1.548
,
Token,
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
,
Token,
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.000
General
Token General
Feature activation+1.834
Lore
Token Lore
Feature activation+0.000
tta
Tokentta
Feature activation+3.915
Lynch
Token Lynch
Feature activation+0.000
,
Token,
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
Director
Token Director
Feature activation+0.000
James
Token James
Feature activation+0.000

INTERVAL 2.797 - 3.496
CONTAINS 0.001%

contenders
Token contenders
Feature activation+0.000
for
Token for
Feature activation+0.496
the
Token the
Feature activation+0.368
post
Token post
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+3.008
Cord
Token Cord
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.282
s
Tokens
Feature activation+1.803
the
Token the
Feature activation+1.733
nation
Token nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.014
s
Tokens
Feature activation+0.914
chief
Token chief
Feature activation+2.839
law
Token law
Feature activation+0.462
-
Token-
Feature activation+0.000
enforcement
Tokenenforcement
Feature activation+0.337
officer
Token officer
Feature activation+0.000
.
Token.
Feature activation+0.064
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.282
s
Tokens
Feature activation+1.803
biggest
Token biggest
Feature activation+1.139
foe
Token foe
Feature activation+3.556
,
Token,
Feature activation+2.813
House
Token House
Feature activation+1.866
Financial
Token Financial
Feature activation+0.000
Services
Token Services
Feature activation+0.000
Chairman
Token Chairman
Feature activation+0.000
Jeb
Token Jeb
Feature activation+0.000
sections
Token sections
Feature activation+0.000
of
Token of
Feature activation+0.000
talking
Token talking
Feature activation+0.000
points
Token points
Feature activation+0.000
prepared
Token prepared
Feature activation+0.000
for
Token for
Feature activation+3.072
ministers
Token ministers
Feature activation+0.000
and
Token and
Feature activation+0.576
officials
Token officials
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+2.081
Department
Token Department
Feature activation+0.222
of
Token of
Feature activation+0.660
Justice
Token Justice
Feature activation+0.000
(
Token (
Feature activation+2.562
DO
TokenDO
Feature activation+3.324
J
TokenJ
Feature activation+0.700
),
Token),
Feature activation+0.408
pursuant
Token pursuant
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.098 - 2.797
CONTAINS 0.002%

back
Token back
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+0.000
saying
Token saying
Feature activation+1.071
the
Token the
Feature activation+2.631
NDP
Token NDP
Feature activation+0.593
are
Token are
Feature activation+0.000
offering
Token offering
Feature activation+0.000
no
Token no
Feature activation+0.000
new
Token new
Feature activation+0.511
of
Token of
Feature activation+0.522
the
Token the
Feature activation+2.081
Department
Token Department
Feature activation+0.222
of
Token of
Feature activation+0.660
Justice
Token Justice
Feature activation+0.000
(
Token (
Feature activation+2.562
DO
TokenDO
Feature activation+3.324
J
TokenJ
Feature activation+0.700
),
Token),
Feature activation+0.408
pursuant
Token pursuant
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.888
Holder
Token Holder
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+2.342
first
Token first
Feature activation+4.556
sitting
Token sitting
Feature activation+4.577
attorney
Token attorney
Feature activation+1.916
general
Token general
Feature activation+1.961
and
Token and
Feature activation+0.405
road
Token road
Feature activation+0.000
to
Token to
Feature activation+1.092
confirmation
Token confirmation
Feature activation+0.000
.
Token.
Feature activation+2.192
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.368
Republicans
TokenRepublicans
Feature activation+1.464
are
Token are
Feature activation+0.000
floating
Token floating
Feature activation+0.368
a
Token a
Feature activation+0.000
handful
Token handful
Feature activation+0.000
quick
Token quick
Feature activation+0.000
to
Token to
Feature activation+0.000
blame
Token blame
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+4.232
Liberal
Token Liberal
Feature activation+2.250
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.669
Liberal
Token Liberal
Feature activation+1.460
MLA
Token MLA
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000

INTERVAL 1.399 - 2.098
CONTAINS 0.004%

.
Token.
Feature activation+0.872
That
Token That
Feature activation+0.529
document
Token document
Feature activation+0.000
was
Token was
Feature activation+0.000
withheld
Token withheld
Feature activation+0.000
from
Token from
Feature activation+1.424
release
Token release
Feature activation+0.000
by
Token by
Feature activation+1.926
the
Token the
Feature activation+2.920
Attorney
Token Attorney
Feature activation+1.053
General
Token General
Feature activation+0.000
the
Token the
Feature activation+0.000
Philippines
Token Philippines
Feature activation+0.000
'
Token'
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.000
of
Token of
Feature activation+0.522
the
Token the
Feature activation+2.081
Department
Token Department
Feature activation+0.222
of
Token of
Feature activation+0.660
Justice
Token Justice
Feature activation+0.000
(
Token (
Feature activation+2.562
DO
TokenDO
Feature activation+3.324
first
Token first
Feature activation+4.556
sitting
Token sitting
Feature activation+4.577
attorney
Token attorney
Feature activation+1.916
general
Token general
Feature activation+1.961
and
Token and
Feature activation+0.405
US
Token US
Feature activation+1.432
presidential
Token presidential
Feature activation+0.549
cabinet
Token cabinet
Feature activation+0.372
member
Token member
Feature activation+1.270
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
Ter
TokenTer
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Kar
Token Kar
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
on
Tokenon
Feature activation+0.000
ik
Tokenik
Feature activation+1.456
:
Token:
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
including
Token including
Feature activation+3.008
Cord
Token Cord
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.282
s
Tokens
Feature activation+1.803
biggest
Token biggest
Feature activation+1.139
foe
Token foe
Feature activation+3.556
,
Token,
Feature activation+2.813
House
Token House
Feature activation+1.866
Financial
Token Financial
Feature activation+0.000

INTERVAL 0.699 - 1.399
CONTAINS 0.012%

"
Token"
Feature activation+0.056
Many
TokenMany
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
actions
Token actions
Feature activation+0.000
the
Token the
Feature activation+0.950
NDP
Token NDP
Feature activation+0.000
are
Token are
Feature activation+0.000
proposing
Token proposing
Feature activation+0.000
today
Token today
Feature activation+0.000
were
Token were
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
"
Token "
Feature activation+0.000
our
Tokenour
Feature activation+1.218
plea
Token plea
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
"
Token"
Feature activation+0.000
lived
Token lived
Feature activation+0.133
under
Token under
Feature activation+0.000
armed
Token armed
Feature activation+0.000
guard
Token guard
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.812
past
Token past
Feature activation+0.000
26
Token 26
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+0.000
death
Token death
Feature activation+0.000
ue
Tokenue
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
Attorney
Token Attorney
Feature activation+0.986
General
Token General
Feature activation+6.993
Eric
Token Eric
Feature activation+4.378
Holder
Token Holder
Feature activation+1.114
has
Token has
Feature activation+0.712
been
Token been
Feature activation+0.331
government
Token government
Feature activation+0.000
)
Token)
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
accepted
Token accepted
Feature activation+0.000
,"
Token,"
Feature activation+1.104
Me
Token Me
Feature activation+0.000
ht
Tokenht
Feature activation+0.000
a
Tokena
Feature activation+0.207
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.699
CONTAINS 99.979%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Spring
TokenSpring
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Social
TokenSocial
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
and
Token and
Feature activation+0.000
progressives
Token progressives
Feature activation+0.000
who
Token who
Feature activation+0.000
employees
Token employees
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
around
Token around
Feature activation+0.000
a
Token a
Feature activation+0.000
desk
Token desk
Feature activation+0.000
,
Token,
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
un
Token un
Feature activation+0.000
al
Tokenal
Feature activation+0.000
tered
Tokentered
Feature activation+0.000
on
Token on
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
1957
Token 1957
Feature activation+0.000
launching
Token launching
Feature activation+0.000
of
Token of
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
nik
Tokennik
Feature activation+0.000
provoked
Token provoked
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
measurement
Token measurement
Feature activation+0.000
of
Token of
Feature activation+0.000
polarization
Token polarization
Feature activation+0.000
is
Token is
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
larger
Token larger
Feature activation+0.000
than
Token than
Feature activation+0.000
prior
Token prior
Feature activation+0.000
observations
Token observations
Feature activation+0.000
have
Token have
Feature activation+0.000
come
Token come
Feature activation+0.000
a
Token a
Feature activation+0.000
massive
Token massive
Feature activation+0.000
$
Token $
Feature activation+0.000
293
Token293
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H10.6: (feature 8926)

TOP ACTIVATIONS
MAX = 5.913

.
Token.
Feature activation+0.481
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.640
House
TokenHouse
Feature activation+0.653
Minority
Token Minority
Feature activation+1.203
Leader
Token Leader
Feature activation+5.913
Nancy
Token Nancy
Feature activation+2.579
Pelosi
Token Pelosi
Feature activation+0.000
(
Token (
Feature activation+0.696
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.714
.
Token.
Feature activation+2.552
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.056
Introduced
TokenIntroduced
Feature activation+0.599
Tuesday
Token Tuesday
Feature activation+0.892
by
Token by
Feature activation+5.879
Reps
Token Reps
Feature activation+0.456
.
Token.
Feature activation+4.653
Mark
Token Mark
Feature activation+3.842
Poc
Token Poc
Feature activation+0.000
an
Tokenan
Feature activation+0.288
(
Token (
Feature activation+0.293
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.137
Fla
TokenFla
Feature activation+0.000
.)
Token.)
Feature activation+0.538
and
Token and
Feature activation+5.531
Luc
Token Luc
Feature activation+0.000
ille
Tokenille
Feature activation+1.142
Roy
Token Roy
Feature activation+0.010
bal
Tokenbal
Feature activation+0.821
All
Token All
Feature activation+0.000
top
Token top
Feature activation+2.103
aide
Token aide
Feature activation+0.000
to
Token to
Feature activation+3.607
House
Token House
Feature activation+0.893
Speaker
Token Speaker
Feature activation+1.900
Michael
Token Michael
Feature activation+5.493
E
Token E
Feature activation+0.628
.
Token.
Feature activation+4.724
Bus
Token Bus
Feature activation+0.095
ch
Tokench
Feature activation+0.000
said
Token said
Feature activation+0.000
D
TokenD
Feature activation+0.122
-
Token-
Feature activation+0.272
W
TokenW
Feature activation+0.027
isc
Tokenisc
Feature activation+0.000
.)
Token.)
Feature activation+0.413
and
Token and
Feature activation+5.421
Thomas
Token Thomas
Feature activation+4.890
Mass
Token Mass
Feature activation+0.237
ie
Tokenie
Feature activation+0.543
(
Token (
Feature activation+0.148
R
TokenR
Feature activation+0.000
.
Token.
Feature activation+3.012
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.410
The
TokenThe
Feature activation+1.572
resolution
Token resolution
Feature activation+0.192
from
Token from
Feature activation+5.305
Reps
Token Reps
Feature activation+0.568
.
Token.
Feature activation+3.389
Rush
Token Rush
Feature activation+0.840
Holt
Token Holt
Feature activation+0.000
Rush
Token Rush
Feature activation+0.787
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
MN
TokenMN
Feature activation+0.000
)
Token)
Feature activation+0.510
and
Token and
Feature activation+5.237
Ron
Token Ron
Feature activation+4.948
Kind
Token Kind
Feature activation+0.000
(
Token (
Feature activation+0.066
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
ADVERTISEMENT
TokenADVERTISEMENT
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.883
House
TokenHouse
Feature activation+1.572
Minority
Token Minority
Feature activation+1.670
Leader
Token Leader
Feature activation+5.228
Nancy
Token Nancy
Feature activation+2.816
Pelosi
Token Pelosi
Feature activation+0.405
(
Token (
Feature activation+0.295
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+1.081
Philip
Token Philip
Feature activation+0.000
R
Token R
Feature activation+0.000
ucker
Tokenucker
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
Rep
Token Rep
Feature activation+0.443
.
Token.
Feature activation+5.044
Steve
Token Steve
Feature activation+0.903
King
Token King
Feature activation+0.000
(
Token (
Feature activation+0.111
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.181
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
House
Token House
Feature activation+0.000
by
Token by
Feature activation+4.328
Reps
Token Reps
Feature activation+0.937
.
Token.
Feature activation+4.980
Erik
Token Erik
Feature activation+3.225
Paul
Token Paul
Feature activation+2.408
sen
Tokensen
Feature activation+0.068
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
MN
TokenMN
Feature activation+0.000
)
Token)
Feature activation+0.510
and
Token and
Feature activation+5.237
Ron
Token Ron
Feature activation+4.948
Kind
Token Kind
Feature activation+0.000
(
Token (
Feature activation+0.066
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
WI
TokenWI
Feature activation+0.427
-
Token-
Feature activation+0.272
W
TokenW
Feature activation+0.027
isc
Tokenisc
Feature activation+0.000
.)
Token.)
Feature activation+0.413
and
Token and
Feature activation+5.421
Thomas
Token Thomas
Feature activation+4.890
Mass
Token Mass
Feature activation+0.237
ie
Tokenie
Feature activation+0.543
(
Token (
Feature activation+0.148
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
apart
Token apart
Feature activation+0.000
after
Token after
Feature activation+0.903
Democratic
Token Democratic
Feature activation+0.913
House
Token House
Feature activation+0.000
minority
Token minority
Feature activation+1.322
leader
Token leader
Feature activation+4.787
Nancy
Token Nancy
Feature activation+1.928
Pelosi
Token Pelosi
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.899
colleagues
Token colleagues
Feature activation+0.476
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+0.000
,"
Token,"
Feature activation+2.199
Rep
Token Rep
Feature activation+0.396
.
Token.
Feature activation+4.751
Bobby
Token Bobby
Feature activation+1.450
Scott
Token Scott
Feature activation+0.201
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.036
to
Token to
Feature activation+3.607
House
Token House
Feature activation+0.893
Speaker
Token Speaker
Feature activation+1.900
Michael
Token Michael
Feature activation+5.493
E
Token E
Feature activation+0.628
.
Token.
Feature activation+4.724
Bus
Token Bus
Feature activation+0.095
ch
Tokench
Feature activation+0.000
said
Token said
Feature activation+0.000
late
Token late
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
likely
Token likely
Feature activation+1.095
to
Token to
Feature activation+1.110
replace
Token replace
Feature activation+0.897
Rep
Token Rep
Feature activation+0.862
.
Token.
Feature activation+4.222
Mike
Token Mike
Feature activation+4.659
Rogers
Token Rogers
Feature activation+0.000
as
Token as
Feature activation+0.962
the
Token the
Feature activation+1.083
next
Token next
Feature activation+1.082
chairman
Token chairman
Feature activation+0.179
Ċ
TokenĊ
Feature activation+4.056
Introduced
TokenIntroduced
Feature activation+0.599
Tuesday
Token Tuesday
Feature activation+0.892
by
Token by
Feature activation+5.879
Reps
Token Reps
Feature activation+0.456
.
Token.
Feature activation+4.653
Mark
Token Mark
Feature activation+3.842
Poc
Token Poc
Feature activation+0.000
an
Tokenan
Feature activation+0.288
(
Token (
Feature activation+0.571
D
TokenD
Feature activation+0.122
some
Token some
Feature activation+0.000
early
Token early
Feature activation+0.000
returns
Token returns
Feature activation+0.000
.
Token.
Feature activation+3.822
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.522
B
TokenB
Feature activation+0.000
anks
Tokenanks
Feature activation+0.000
that
Token that
Feature activation+0.000
received
Token received
Feature activation+0.000
money
Token money
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
chaired
Token chaired
Feature activation+0.000
by
Token by
Feature activation+0.000
Rep
Token Rep
Feature activation+0.100
.
Token.
Feature activation+4.513
Marc
Token Marc
Feature activation+0.082
ia
Tokenia
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+1.299
F
Token F
Feature activation+0.000
has
Token has
Feature activation+1.358
led
Token led
Feature activation+2.831
a
Token a
Feature activation+1.859
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
woman
Tokenwoman
Feature activation+4.483
whip
Token whip
Feature activation+0.374
operation
Token operation
Feature activation+0.433
on
Token on
Feature activation+2.118
the
Token the
Feature activation+4.204
budget
Token budget
Feature activation+0.467

Top DFA by src position
MAX = 5.914

sick
Token sick
Feature activation+0.001
Top resid features:
people
Token people
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
House
TokenHouse
Feature activation+5.695
Top resid features:
Minority
Token Minority
Feature activation+0.301
Top resid features:
Leader
Token Leader
Feature activation+0.125
Top resid features:
Nancy
Token Nancy
Feature activation+0.000
Top resid features:
Pelosi
Token Pelosi
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
begun
Token begun
Feature activation+0.000
Top resid features:
its
Token its
Feature activation-0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
House
Token House
Feature activation+5.914
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
thanks
Token thanks
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
bipartisan
Token bipartisan
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
earlier
Token earlier
Feature activation+0.001
Top resid features:
this
Token this
Feature activation-0.000
Top resid features:
week
Token week
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Reps
Token Reps
Feature activation+2.681
Top resid features:
.
Token.
Feature activation+2.660
Top resid features:
I
Token I
Feature activation-0.036
Top resid features:
le
Tokenle
Feature activation-0.011
Top resid features:
ana
Tokenana
Feature activation+0.037
Top resid features:
Ros
Token Ros
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
top
Token top
Feature activation+0.001
Top resid features:
aide
Token aide
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
House
Token House
Feature activation+2.264
Top resid features:
Speaker
Token Speaker
Feature activation+2.377
Top resid features:
Michael
Token Michael
Feature activation+0.003
Top resid features:
E
Token E
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Bus
Token Bus
Feature activation+0.000
Top resid features:
ch
Tokench
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Introduced
TokenIntroduced
Feature activation-0.001
Top resid features:
Tuesday
Token Tuesday
Feature activation-0.001
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
Reps
Token Reps
Feature activation+1.303
Top resid features:
.
Token.
Feature activation+3.604
Top resid features:
Mark
Token Mark
Feature activation+0.066
Top resid features:
Poc
Token Poc
Feature activation+0.037
Top resid features:
an
Tokenan
Feature activation+0.014
Top resid features:
(
Token (
Feature activation+0.014
Top resid features:
D
TokenD
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.055
Top resid features:
Three
TokenThree
Feature activation+0.001
Top resid features:
House
Token House
Feature activation+4.944
Top resid features:
Democrats
Token Democrats
Feature activation+0.350
Top resid features:
have
Token have
Feature activation+0.011
Top resid features:
proposed
Token proposed
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
resolution
Token resolution
Feature activation+0.023
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.325
Top resid features:
by
Token by
Feature activation-0.003
Top resid features:
Reps
Token Reps
Feature activation+1.801
Top resid features:
.
Token.
Feature activation+3.248
Top resid features:
Erik
Token Erik
Feature activation-0.015
Top resid features:
Paul
Token Paul
Feature activation+0.009
Top resid features:
sen
Tokensen
Feature activation+0.018
Top resid features:
(
Token (
Feature activation+0.027
Top resid features:
R
TokenR
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
ADVERTISEMENT
TokenADVERTISEMENT
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
House
TokenHouse
Feature activation+4.127
Top resid features:
Minority
Token Minority
Feature activation+0.449
Top resid features:
Leader
Token Leader
Feature activation+0.215
Top resid features:
Nancy
Token Nancy
Feature activation+0.000
Top resid features:
Pelosi
Token Pelosi
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Philip
Token Philip
Feature activation-0.038
Top resid features:
R
Token R
Feature activation+0.005
Top resid features:
ucker
Tokenucker
Feature activation+0.003
Top resid features:
interviews
Token interviews
Feature activation-0.015
Top resid features:
Rep
Token Rep
Feature activation+1.931
Top resid features:
.
Token.
Feature activation+3.375
Top resid features:
Steve
Token Steve
Feature activation+0.000
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
House
Token House
Feature activation+0.574
Top resid features:
by
Token by
Feature activation+0.005
Top resid features:
Reps
Token Reps
Feature activation+1.779
Top resid features:
.
Token.
Feature activation+2.922
Top resid features:
Erik
Token Erik
Feature activation+0.000
Top resid features:
Paul
Token Paul
Feature activation+0.000
Top resid features:
sen
Tokensen
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.207
Top resid features:
by
Token by
Feature activation+0.003
Top resid features:
Reps
Token Reps
Feature activation+1.642
Top resid features:
.
Token.
Feature activation+2.957
Top resid features:
Erik
Token Erik
Feature activation-0.007
Top resid features:
Paul
Token Paul
Feature activation+0.017
Top resid features:
sen
Tokensen
Feature activation+0.019
Top resid features:
(
Token (
Feature activation+0.014
Top resid features:
R
TokenR
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Introduced
TokenIntroduced
Feature activation+0.004
Top resid features:
Tuesday
Token Tuesday
Feature activation-0.000
Top resid features:
by
Token by
Feature activation+0.014
Top resid features:
Reps
Token Reps
Feature activation+1.870
Top resid features:
.
Token.
Feature activation+2.594
Top resid features:
Mark
Token Mark
Feature activation-0.003
Top resid features:
Poc
Token Poc
Feature activation+0.022
Top resid features:
an
Tokenan
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.030
Top resid features:
D
TokenD
Feature activation+0.009
Top resid features:
TPP
Token TPP
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation-0.001
Top resid features:
House
Token House
Feature activation+3.053
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
Friday
Token Friday
Feature activation-0.006
Top resid features:
tried
Token tried
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
pass
Token pass
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
situation
Token situation
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
,"
Token,"
Feature activation+0.004
Top resid features:
Rep
Token Rep
Feature activation+1.710
Top resid features:
.
Token.
Feature activation+2.850
Top resid features:
Bobby
Token Bobby
Feature activation+0.000
Top resid features:
Scott
Token Scott
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
top
Token top
Feature activation+0.003
Top resid features:
aide
Token aide
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
House
Token House
Feature activation+2.022
Top resid features:
Speaker
Token Speaker
Feature activation+2.099
Top resid features:
Michael
Token Michael
Feature activation+0.012
Top resid features:
E
Token E
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
Bus
Token Bus
Feature activation+0.000
Top resid features:
ch
Tokench
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation+0.036
Top resid features:
likely
Token likely
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
replace
Token replace
Feature activation+0.034
Top resid features:
Rep
Token Rep
Feature activation+1.445
Top resid features:
.
Token.
Feature activation+2.100
Top resid features:
Mike
Token Mike
Feature activation+0.032
Top resid features:
Rogers
Token Rogers
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Introduced
TokenIntroduced
Feature activation+0.003
Top resid features:
Tuesday
Token Tuesday
Feature activation-0.001
Top resid features:
by
Token by
Feature activation+0.006
Top resid features:
Reps
Token Reps
Feature activation+0.885
Top resid features:
.
Token.
Feature activation+2.791
Top resid features:
Mark
Token Mark
Feature activation+0.000
Top resid features:
Poc
Token Poc
Feature activation+0.000
Top resid features:
an
Tokenan
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
some
Token some
Feature activation+0.035
Top resid features:
members
Token members
Feature activation+0.087
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
House
Token House
Feature activation+3.852
Top resid features:
subcommittee
Token subcommittee
Feature activation+0.839
Top resid features:
questioned
Token questioned
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
head
Token head
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
which
Token which
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
chaired
Token chaired
Feature activation+0.003
Top resid features:
by
Token by
Feature activation-0.036
Top resid features:
Rep
Token Rep
Feature activation+1.323
Top resid features:
.
Token.
Feature activation+3.564
Top resid features:
Marc
Token Marc
Feature activation+0.000
Top resid features:
ia
Tokenia
Feature activation+0.000
Top resid features:
L
Token L
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+0.000
Top resid features:
reprint
Token reprint
Feature activation-0.000
Top resid features:
permission
Token permission
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.057
Top resid features:
Rep
TokenRep
Feature activation+0.299
Top resid features:
.
Token.
Feature activation+4.254
Top resid features:
Diane
Token Diane
Feature activation+0.022
Top resid features:
Black
Token Black
Feature activation+0.005
Top resid features:
who
Token who
Feature activation+0.039
Top resid features:
has
Token has
Feature activation+0.046
Top resid features:
led
Token led
Feature activation+0.091
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.04

Head 3: 0.07

Head 4: 0.06

Head 5: 0.02

Head 6: 0.42

Head 7: 0.10

Head 8: 0.02

Head 9: 0.05

Head 10: 0.05

Head 11: 0.05

Positive logits

House7.26

Reps7.18

Congressman7.10

congressman6.99

Representative6.74

congressional6.71

Congressional6.67

Rep6.61

lawmakers6.48

House6.41

lawmaker6.37

Congress6.36

congress6.29

Rep6.09

Boehner6.08

Pelosi6.04

legislators5.84

Speaker5.84

Capitol5.80

Congress5.76

Negative logits

Entry-2.84

entries-2.72

runway-2.62

arant-2.59

Pound-2.50

Valiant-2.48

DragonMagazine-2.41

entrants-2.41

guard-2.38

admissions-2.38

ainment-2.34

Buyable-2.33

Duration-2.33

rown-2.32

entry-2.32

Jericho-2.30

liner-2.30

manic-2.28

GGGGGGGG-2.27

DIT-2.26

INTERVAL 5.322 - 5.913
CONTAINS 0.001%

top
Token top
Feature activation+2.103
aide
Token aide
Feature activation+0.000
to
Token to
Feature activation+3.607
House
Token House
Feature activation+0.893
Speaker
Token Speaker
Feature activation+1.900
Michael
Token Michael
Feature activation+5.493
E
Token E
Feature activation+0.628
.
Token.
Feature activation+4.724
Bus
Token Bus
Feature activation+0.095
ch
Tokench
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.481
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.640
House
TokenHouse
Feature activation+0.653
Minority
Token Minority
Feature activation+1.203
Leader
Token Leader
Feature activation+5.913
Nancy
Token Nancy
Feature activation+2.579
Pelosi
Token Pelosi
Feature activation+0.000
(
Token (
Feature activation+0.696
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.714
.
Token.
Feature activation+2.552
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.056
Introduced
TokenIntroduced
Feature activation+0.599
Tuesday
Token Tuesday
Feature activation+0.892
by
Token by
Feature activation+5.879
Reps
Token Reps
Feature activation+0.456
.
Token.
Feature activation+4.653
Mark
Token Mark
Feature activation+3.842
Poc
Token Poc
Feature activation+0.000
an
Tokenan
Feature activation+0.288
D
TokenD
Feature activation+0.122
-
Token-
Feature activation+0.272
W
TokenW
Feature activation+0.027
isc
Tokenisc
Feature activation+0.000
.)
Token.)
Feature activation+0.413
and
Token and
Feature activation+5.421
Thomas
Token Thomas
Feature activation+4.890
Mass
Token Mass
Feature activation+0.237
ie
Tokenie
Feature activation+0.543
(
Token (
Feature activation+0.148
R
TokenR
Feature activation+0.000
(
Token (
Feature activation+0.293
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.137
Fla
TokenFla
Feature activation+0.000
.)
Token.)
Feature activation+0.538
and
Token and
Feature activation+5.531
Luc
Token Luc
Feature activation+0.000
ille
Tokenille
Feature activation+1.142
Roy
Token Roy
Feature activation+0.010
bal
Tokenbal
Feature activation+0.821
All
Token All
Feature activation+0.000

INTERVAL 4.730 - 5.322
CONTAINS 0.001%

(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
MN
TokenMN
Feature activation+0.000
)
Token)
Feature activation+0.510
and
Token and
Feature activation+5.237
Ron
Token Ron
Feature activation+4.948
Kind
Token Kind
Feature activation+0.000
(
Token (
Feature activation+0.066
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+0.000
,"
Token,"
Feature activation+2.199
Rep
Token Rep
Feature activation+0.396
.
Token.
Feature activation+4.751
Bobby
Token Bobby
Feature activation+1.450
Scott
Token Scott
Feature activation+0.201
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.036
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
MN
TokenMN
Feature activation+0.000
)
Token)
Feature activation+0.510
and
Token and
Feature activation+5.237
Ron
Token Ron
Feature activation+4.948
Kind
Token Kind
Feature activation+0.000
(
Token (
Feature activation+0.066
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
WI
TokenWI
Feature activation+0.427
Philip
Token Philip
Feature activation+0.000
R
Token R
Feature activation+0.000
ucker
Tokenucker
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
Rep
Token Rep
Feature activation+0.443
.
Token.
Feature activation+5.044
Steve
Token Steve
Feature activation+0.903
King
Token King
Feature activation+0.000
(
Token (
Feature activation+0.111
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.181
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
House
Token House
Feature activation+0.000
by
Token by
Feature activation+4.328
Reps
Token Reps
Feature activation+0.937
.
Token.
Feature activation+4.980
Erik
Token Erik
Feature activation+3.225
Paul
Token Paul
Feature activation+2.408
sen
Tokensen
Feature activation+0.068
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000

INTERVAL 4.139 - 4.730
CONTAINS 0.001%

which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
chaired
Token chaired
Feature activation+0.000
by
Token by
Feature activation+0.000
Rep
Token Rep
Feature activation+0.100
.
Token.
Feature activation+4.513
Marc
Token Marc
Feature activation+0.082
ia
Tokenia
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+1.299
F
Token F
Feature activation+0.000
some
Token some
Feature activation+0.000
early
Token early
Feature activation+0.000
returns
Token returns
Feature activation+0.000
.
Token.
Feature activation+3.822
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.522
B
TokenB
Feature activation+0.000
anks
Tokenanks
Feature activation+0.000
that
Token that
Feature activation+0.000
received
Token received
Feature activation+0.000
money
Token money
Feature activation+0.000
anti
Token anti
Feature activation+0.065
-
Token-
Feature activation+0.000
science
Tokenscience
Feature activation+0.253
.
Token.
Feature activation+3.012
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.410
The
TokenThe
Feature activation+1.572
resolution
Token resolution
Feature activation+0.192
from
Token from
Feature activation+5.305
Reps
Token Reps
Feature activation+0.568
.
Token.
Feature activation+3.389
Ċ
TokenĊ
Feature activation+4.056
Introduced
TokenIntroduced
Feature activation+0.599
Tuesday
Token Tuesday
Feature activation+0.892
by
Token by
Feature activation+5.879
Reps
Token Reps
Feature activation+0.456
.
Token.
Feature activation+4.653
Mark
Token Mark
Feature activation+3.842
Poc
Token Poc
Feature activation+0.000
an
Tokenan
Feature activation+0.288
(
Token (
Feature activation+0.571
D
TokenD
Feature activation+0.122
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.181
Iowa
TokenIowa
Feature activation+0.000
)
Token)
Feature activation+0.224
at
Token at
Feature activation+3.195
the
Token the
Feature activation+4.452
Republican
Token Republican
Feature activation+0.994
National
Token National
Feature activation+0.000
Convention
Token Convention
Feature activation+0.000
in
Token in
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000

INTERVAL 3.548 - 4.139
CONTAINS 0.003%

terrorist
Token terrorist
Feature activation+0.000
attack
Token attack
Feature activation+0.000
given
Token given
Feature activation+0.058
House
Token House
Feature activation+0.000
Majority
Token Majority
Feature activation+0.619
Leader
Token Leader
Feature activation+3.581
Kevin
Token Kevin
Feature activation+2.374
McCarthy
Token McCarthy
Feature activation+0.000
Kevin
Token Kevin
Feature activation+0.012
Owen
Token Owen
Feature activation+0.290
McCarthy
Token McCarthy
Feature activation+0.000
results
Token results
Feature activation+0.000
on
Token on
Feature activation+0.000
some
Token some
Feature activation+0.000
early
Token early
Feature activation+0.000
returns
Token returns
Feature activation+0.000
.
Token.
Feature activation+3.822
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.522
B
TokenB
Feature activation+0.000
anks
Tokenanks
Feature activation+0.000
that
Token that
Feature activation+0.000
Ill
TokenIll
Feature activation+0.000
.)
Token.)
Feature activation+0.610
told
Token told
Feature activation+0.624
reporters
Token reporters
Feature activation+0.007
in
Token in
Feature activation+2.247
the
Token the
Feature activation+3.603
Capitol
Token Capitol
Feature activation+0.000
.
Token.
Feature activation+1.014
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.774
âĢ
TokenâĢ
Feature activation+0.000
legates
Tokenlegates
Feature activation+0.000
,
Token,
Feature activation+1.897
a
Token a
Feature activation+1.520
top
Token top
Feature activation+2.103
aide
Token aide
Feature activation+0.000
to
Token to
Feature activation+3.607
House
Token House
Feature activation+0.893
Speaker
Token Speaker
Feature activation+1.900
Michael
Token Michael
Feature activation+5.493
E
Token E
Feature activation+0.628
.
Token.
Feature activation+4.724
The
Token The
Feature activation+0.000
Wire
Token Wire
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Rep
TokenRep
Feature activation+0.000
.
Token.
Feature activation+4.057
St
Token St
Feature activation+1.090
eny
Tokeneny
Feature activation+0.000
H
Token H
Feature activation+0.000
oyer
Tokenoyer
Feature activation+0.062
(
Token (
Feature activation+0.417

INTERVAL 2.956 - 3.548
CONTAINS 0.007%

stated
Token stated
Feature activation+0.433
.
Token.
Feature activation+1.801
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.744
He
TokenHe
Feature activation+0.000
knows
Token knows
Feature activation+2.981
how
Token how
Feature activation+1.252
to
Token to
Feature activation+0.068
take
Token take
Feature activation+0.652
care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.872
ative
Tokenative
Feature activation+3.721
of
Token of
Feature activation+0.978
the
Token the
Feature activation+0.866
Korean
Token Korean
Feature activation+0.000
entertainment
Token entertainment
Feature activation+0.000
industry
Token industry
Feature activation+3.375
are
Token are
Feature activation+0.755
stating
Token stating
Feature activation+0.877
that
Token that
Feature activation+2.933
many
Token many
Feature activation+1.191
people
Token people
Feature activation+0.000
ement
Tokenement
Feature activation+0.000
program
Token program
Feature activation+0.004
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.235
to
Token to
Feature activation+1.895
the
Token the
Feature activation+3.140
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+1.001
Justice
Token Justice
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
pushing
Token pushing
Feature activation+0.850
for
Token for
Feature activation+0.201
more
Token more
Feature activation+0.000
profound
Token profound
Feature activation+0.000
reforms
Token reforms
Feature activation+0.000
.
Token.
Feature activation+3.150
They
Token They
Feature activation+0.000
include
Token include
Feature activation+3.688
Republican
Token Republican
Feature activation+3.614
James
Token James
Feature activation+1.225
Sens
Token Sens
Feature activation+0.000
the
Token the
Feature activation+0.370
first
Token first
Feature activation+0.012
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.245
HELP
Token HELP
Feature activation+0.000
Chairman
Token Chairman
Feature activation+2.958
Lamar
Token Lamar
Feature activation+1.501
Alexander
Token Alexander
Feature activation+0.000
is
Token is
Feature activation+0.000
working
Token working
Feature activation+0.000
hard
Token hard
Feature activation+0.000

INTERVAL 2.365 - 2.956
CONTAINS 0.010%

credibility
Token credibility
Feature activation+0.006
of
Token of
Feature activation+1.157
the
Token the
Feature activation+1.368
committee
Token committee
Feature activation+0.015
and
Token and
Feature activation+0.000
subjects
Token subjects
Feature activation+2.473
the
Token the
Feature activation+1.472
committee
Token committee
Feature activation+0.000
to
Token to
Feature activation+0.000
accusations
Token accusations
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.230
first
Token first
Feature activation+1.257
-
Token-
Feature activation+0.301
ever
Tokenever
Feature activation+0.726
visually
Token visually
Feature activation+0.000
impaired
Token impaired
Feature activation+2.600
person
Token person
Feature activation+0.899
to
Token to
Feature activation+1.621
head
Token head
Feature activation+0.000
the
Token the
Feature activation+0.587
Senate
Token Senate
Feature activation+0.000
of
Token of
Feature activation+0.380
the
Token the
Feature activation+1.436
Bush
Token Bush
Feature activation+0.000
tax
Token tax
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
.
Token.
Feature activation+2.543
Citizens
Token Citizens
Feature activation+0.311
protested
Token protested
Feature activation+0.887
at
Token at
Feature activation+1.071
a
Token a
Feature activation+1.088
town
Token town
Feature activation+0.000
,"
Token,"
Feature activation+2.749
she
Token she
Feature activation+0.421
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.129
referring
Token referring
Feature activation+0.000
to
Token to
Feature activation+2.895
the
Token the
Feature activation+1.386
grid
Token grid
Feature activation+0.000
lock
Tokenlock
Feature activation+0.576
that
Token that
Feature activation+0.398
has
Token has
Feature activation+0.000
Hem
Token Hem
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
that
Token that
Feature activation+2.910
she
Token she
Feature activation+0.000
thought
Token thought
Feature activation+3.354
the
Token the
Feature activation+2.473
GOP
Token GOP
Feature activation+1.684
was
Token was
Feature activation+0.000
negotiating
Token negotiating
Feature activation+0.134
with
Token with
Feature activation+0.335
President
Token President
Feature activation+0.029

INTERVAL 1.774 - 2.365
CONTAINS 0.027%

),
Token),
Feature activation+0.063
sponsored
Token sponsored
Feature activation+0.132
by
Token by
Feature activation+3.298
Rep
Token Rep
Feature activation+0.000
.
Token.
Feature activation+0.721
Rick
Token Rick
Feature activation+1.802
Roth
Token Roth
Feature activation+0.000
,
Token,
Feature activation+0.826
R
Token R
Feature activation+0.513
-
Token-
Feature activation+0.000
L
TokenL
Feature activation+0.000
this
Token this
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Representative
Token Representative
Feature activation+2.314
Elijah
Token Elijah
Feature activation+0.809
Cummings
Token Cummings
Feature activation+0.083
wrote
Token wrote
Feature activation+0.354
in
Token in
Feature activation+0.664
a
Token a
Feature activation+0.814
the
Token the
Feature activation+2.268
network
Token network
Feature activation+0.000
as
Token as
Feature activation+1.250
a
Token a
Feature activation+0.827
result
Token result
Feature activation+0.000
.
Token.
Feature activation+2.048
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.759
The
TokenThe
Feature activation+1.739
senior
Token senior
Feature activation+1.279
official
Token official
Feature activation+0.000
To
Token To
Feature activation+0.000
contact
Token contact
Feature activation+1.069
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
visit
Token visit
Feature activation+3.445
his
Token his
Feature activation+1.994
website
Token website
Feature activation+0.872
at
Token at
Feature activation+2.456
www
Token www
Feature activation+0.000
.
Token.
Feature activation+2.148
sam
Tokensam
Feature activation+1.089
within
Token within
Feature activation+0.965
the
Token the
Feature activation+2.926
Democratic
Token Democratic
Feature activation+1.213
Caucus
Token Caucus
Feature activation+0.068
,
Token,
Feature activation+0.074
so
Token so
Feature activation+1.994
far
Token far
Feature activation+0.014
.
Token.
Feature activation+2.351
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.723
And
TokenAnd
Feature activation+1.018

INTERVAL 1.183 - 1.774
CONTAINS 0.054%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.477
But
TokenBut
Feature activation+1.652
where
Token where
Feature activation+1.609
there
Token there
Feature activation+0.046
are
Token are
Feature activation+1.600
no
Token no
Feature activation+1.362
gatherings
Token gatherings
Feature activation+0.194
,
Token,
Feature activation+1.490
some
Token some
Feature activation+1.876
groups
Token groups
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.383
release
Token release
Feature activation+0.741
a
Token a
Feature activation+0.286
score
Token score
Feature activation+0.000
for
Token for
Feature activation+1.254
how
Token how
Feature activation+0.466
much
Token much
Feature activation+0.077
the
Token the
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
would
Token would
Feature activation+0.000
an
Token an
Feature activation+0.000
alternative
Token alternative
Feature activation+0.242
option
Token option
Feature activation+0.000
to
Token to
Feature activation+0.085
impeachment
Token impeachment
Feature activation+0.000
.
Token.
Feature activation+1.451
It
Token It
Feature activation+0.000
says
Token says
Feature activation+1.374
that
Token that
Feature activation+1.312
the
Token the
Feature activation+0.617
vice
Token vice
Feature activation+0.595
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
on
Token on
Feature activation+0.972
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.211
when
Token when
Feature activation+1.197
he
Token he
Feature activation+0.366
test
Token test
Feature activation+0.000
ifies
Tokenifies
Feature activation+0.000
before
Token before
Feature activation+0.285
the
Token the
Feature activation+0.175
Companies
Token Companies
Feature activation+0.241
.
Token.
Feature activation+1.348
I
Token I
Feature activation+0.000
started
Token started
Feature activation+1.623
growing
Token growing
Feature activation+0.872
in
Token in
Feature activation+1.598
'
Token '
Feature activation+0.008
85
Token85
Feature activation+0.000
.
Token.
Feature activation+0.901
I
Token I
Feature activation+0.000
grew
Token grew
Feature activation+0.000

INTERVAL 0.591 - 1.183
CONTAINS 0.176%

to
Token to
Feature activation+2.370
a
Token a
Feature activation+0.780
bipartisan
Token bipartisan
Feature activation+0.326
duo
Token duo
Feature activation+0.005
calling
Token calling
Feature activation+0.209
for
Token for
Feature activation+1.115
an
Token an
Feature activation+0.185
end
Token end
Feature activation+0.000
to
Token to
Feature activation+0.154
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
University
Token University
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Bronx
Token Bronx
Feature activation+0.000
who
Token who
Feature activation+0.363
attended
Token attended
Feature activation+1.135
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.310
girlfriend
Token girlfriend
Feature activation+0.000
,
Token,
Feature activation+0.000
Christine
Token Christine
Feature activation+0.000
Five
TokenFive
Feature activation+1.427
Washington
Token Washington
Feature activation+0.905
state
Token state
Feature activation+1.738
representatives
Token representatives
Feature activation+0.145
have
Token have
Feature activation+1.089
introduced
Token introduced
Feature activation+0.799
legislation
Token legislation
Feature activation+0.000
in
Token in
Feature activation+0.545
an
Token an
Feature activation+0.499
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.239
The
Token The
Feature activation+0.000
lawmaker
Token lawmaker
Feature activation+0.000
,
Token,
Feature activation+0.594
who
Token who
Feature activation+0.509
heads
Token heads
Feature activation+0.389
the
Token the
Feature activation+0.854
state
Token state
Feature activation+0.197
's
Token's
Feature activation+0.024
Senate
Token Senate
Feature activation+0.000
Judiciary
Token Judiciary
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
ative
Tokenative
Feature activation+2.703
Joe
Token Joe
Feature activation+3.095
Barton
Token Barton
Feature activation+0.371
of
Token of
Feature activation+0.014
Texas
Token Texas
Feature activation+1.327
introduced
Token introduced
Feature activation+1.036
a
Token a
Feature activation+1.539
bill
Token bill
Feature activation+0.000
Friday
Token Friday
Feature activation+0.145
that
Token that
Feature activation+0.048
would
Token would
Feature activation+0.000

INTERVAL 0.000 - 0.591
CONTAINS 99.720%

transl
Token transl
Feature activation+0.000
ational
Tokenational
Feature activation+0.000
research
Token research
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
our
Token our
Feature activation+0.000
rust
Token rust
Feature activation+0.000
-
Token-
Feature activation+0.000
proof
Tokenproof
Feature activation+0.000
ing
Tokening
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
US
Token US
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.000
echoing
Token echoing
Feature activation+0.000
statements
Token statements
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
protagonists
Token protagonists
Feature activation+0.000
bluntly
Token bluntly
Feature activation+0.000
speak
Token speak
Feature activation+0.000
their
Token their
Feature activation+0.000
October
Token October
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
)
Token)
Feature activation+0.000
though
Token though
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
stories
Token stories
Feature activation+0.000
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.000
p
Tokenp
Feature activation+0.000
8
Token8
Feature activation+0.000
w
Tokenw
Feature activation+0.000
X
TokenX
Feature activation+0.000
WM
TokenWM
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
Es
TokenEs
Feature activation+0.000
âĢĶ
Token âĢĶ
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