H9.10 top features

Top feature 0 in H9.10: (feature 3057)

TOP ACTIVATIONS
MAX = 3.287

would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
floor
Token floor
Feature activation+3.287
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+2.022
and
Token and
Feature activation+0.634
the
Token the
Feature activation+0.000
characters
Token characters
Feature activation+3.242
to
Token to
Feature activation+0.567
start
Token start
Feature activation+0.000
going
Token going
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
it
Token it
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
his
Token his
Feature activation+0.000
place
Token place
Feature activation+0.000
"
Token "
Feature activation+2.554
to
Tokento
Feature activation+0.000
judge
Token judge
Feature activation+0.000
our
Token our
Feature activation+0.000
current
Token current
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
mantle
Token mantle
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
spot
Token spot
Feature activation+2.413
of
Token of
Feature activation+0.000
expression
Token expression
Feature activation+2.351
,
Token,
Feature activation+2.141
and
Token and
Feature activation+0.000
diff
Token diff
Feature activation+0.000
s
Tokens
Feature activation+0.000
probably
Token probably
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
exaggeration
Token exaggeration
Feature activation+0.568
to
Token to
Feature activation+2.401
say
Token say
Feature activation+0.312
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.000
of
Token of
Feature activation+0.000
mantle
Token mantle
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
spot
Token spot
Feature activation+2.413
of
Token of
Feature activation+0.000
expression
Token expression
Feature activation+2.351
,
Token,
Feature activation+2.141
and
Token and
Feature activation+0.000
diff
Token diff
Feature activation+0.000
uses
Tokenuses
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
duty
Token duty
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.167
progressive
Token progressive
Feature activation+0.107
site
Token site
Feature activation+2.331
to
Token to
Feature activation+0.547
live
Token live
Feature activation+0.000
out
Token out
Feature activation+0.000
its
Token its
Feature activation+0.000
pro
Token pro
Feature activation+0.000
been
Token been
Feature activation+0.000
directed
Token directed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.151
White
Token White
Feature activation+0.000
House
Token House
Feature activation+2.329
to
Token to
Feature activation+0.216
create
Token create
Feature activation+0.000
specific
Token specific
Feature activation+0.000
recommendations
Token recommendations
Feature activation+0.278
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.403
133
Token133
Feature activation+1.586
in
Token in
Feature activation+0.740
the
Token the
Feature activation+0.814
draft
Token draft
Feature activation+1.197
notification
Token notification
Feature activation+2.302
to
Token to
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
254
Token254
Feature activation+0.000
in
Token in
Feature activation+0.000
G
TokenG
Feature activation+0.000
roups
Tokenroups
Feature activation+0.000
ranging
Token ranging
Feature activation+0.000
from
Token from
Feature activation+0.000
Amnesty
Token Amnesty
Feature activation+0.605
International
Token International
Feature activation+2.295
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
David
Token David
Feature activation+0.000
Suzuki
Token Suzuki
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.551
move
Token move
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.109
opportunity
Token opportunity
Feature activation+2.196
to
Token to
Feature activation+0.149
another
Token another
Feature activation+0.061
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
highways
Token highways
Feature activation+0.000
,
Token,
Feature activation+0.000
switching
Token switching
Feature activation+0.000
from
Token from
Feature activation+0.000
cell
Token cell
Feature activation+0.614
tower
Token tower
Feature activation+2.188
to
Token to
Feature activation+0.000
cell
Token cell
Feature activation+0.000
tower
Token tower
Feature activation+0.346
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
panels
Token panels
Feature activation+0.000
and
Token and
Feature activation+0.000
produce
Token produce
Feature activation+0.000
enough
Token enough
Feature activation+0.000
renewable
Token renewable
Feature activation+0.197
electricity
Token electricity
Feature activation+2.160
to
Token to
Feature activation+0.056
power
Token power
Feature activation+0.000
4
Token 4
Feature activation+0.000
,
Token,
Feature activation+0.000
400
Token400
Feature activation+0.000
interest
Token interest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
wider
Token wider
Feature activation+0.000
Java
Token Java
Feature activation+0.035
ecosystem
Token ecosystem
Feature activation+2.155
to
Token to
Feature activation+0.215
proceed
Token proceed
Feature activation+0.000
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
Sharks
Token Sharks
Feature activation+0.000
,
Token,
Feature activation+0.835
from
Token from
Feature activation+0.000
Worcester
Token Worcester
Feature activation+1.541
,
Token,
Feature activation+1.069
Massachusetts
Token Massachusetts
Feature activation+2.155
to
Token to
Feature activation+0.000
San
Token San
Feature activation+0.000
Jose
Token Jose
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
spot
Token spot
Feature activation+2.413
of
Token of
Feature activation+0.000
expression
Token expression
Feature activation+2.351
,
Token,
Feature activation+2.141
and
Token and
Feature activation+0.000
diff
Token diff
Feature activation+0.000
uses
Tokenuses
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
British
Token British
Feature activation+0.000
Columbia
Token Columbia
Feature activation+0.440
[
Token[
Feature activation+0.146
4
Token4
Feature activation+0.000
]
Token]
Feature activation+2.141
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
sub
Token sub
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ctic
Tokenctic
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
enough
Token enough
Feature activation+0.000
program
Token program
Feature activation+0.201
ing
Tokening
Feature activation+2.135
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
rich
Token rich
Feature activation+0.000
prototypes
Token prototypes
Feature activation+0.000
and
Token and
Feature activation+0.000
years
Token years
Feature activation+0.000
"
Token"
Feature activation+1.438
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
enough
Token enough
Feature activation+0.141
money
Token money
Feature activation+2.118
for
Token for
Feature activation+0.173
launch
Token launch
Feature activation+0.468
.
Token.
Feature activation+0.015
"
Token "
Feature activation+0.432
Americans
TokenAmericans
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
have
Token have
Feature activation+0.000
until
Token until
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+1.315
night
Token night
Feature activation+2.112
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
a
Token a
Feature activation+0.000

Top DFA by src position
MAX = 3.477

This
Token This
Feature activation-0.002
Top resid features:
would
Token would
Feature activation-0.000
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
repeated
Token repeated
Feature activation-0.000
Top resid features:
from
Token from
Feature activation+0.119
Top resid features:
one
Token one
Feature activation+3.477
Top resid features:
floor
Token floor
Feature activation+0.067
Top resid features:
to
Token to
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:
to
Token to
Feature activation+0.000
Top resid features:
acceptable
Token acceptable
Feature activation+0.005
Top resid features:
fashion
Token fashion
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
You
Token You
Feature activation+0.002
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
enough
Token enough
Feature activation+3.300
Top resid features:
about
Token about
Feature activation+0.089
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
world
Token world
Feature activation+0.065
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.033
Top resid features:
isn
Token isn
Feature activation+0.013
Top resid features:
't
Token't
Feature activation+0.004
Top resid features:
his
Token his
Feature activation+0.086
Top resid features:
place
Token place
Feature activation+2.830
Top resid features:
"
Token "
Feature activation+0.008
Top resid features:
to
Tokento
Feature activation+0.000
Top resid features:
judge
Token judge
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
current
Token current
Feature activation+0.000
Top resid features:
gradient
Token gradient
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
mantle
Token mantle
Feature activation+0.008
Top resid features:
from
Token from
Feature activation+0.121
Top resid features:
one
Token one
Feature activation+2.575
Top resid features:
spot
Token spot
Feature activation+0.079
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
expression
Token expression
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
probably
Token probably
Feature activation+0.011
Top resid features:
not
Token not
Feature activation-0.001
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
exaggeration
Token exaggeration
Feature activation+2.745
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
study
Token study
Feature activation+0.000
Top resid features:
gradient
Token gradient
Feature activation-0.005
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
mantle
Token mantle
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.095
Top resid features:
one
Token one
Feature activation+2.225
Top resid features:
spot
Token spot
Feature activation+0.348
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
expression
Token expression
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
Salon
Token Salon
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
duty
Token duty
Feature activation+2.351
Top resid features:
as
Token as
Feature activation+0.097
Top resid features:
a
Token a
Feature activation+0.108
Top resid features:
progressive
Token progressive
Feature activation+0.147
Top resid features:
site
Token site
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
been
Token been
Feature activation-0.022
Top resid features:
directed
Token directed
Feature activation+0.263
Top resid features:
by
Token by
Feature activation+2.318
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
White
Token White
Feature activation+0.007
Top resid features:
House
Token House
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
create
Token create
Feature activation+0.000
Top resid features:
ESA
Token ESA
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
from
Token from
Feature activation+0.302
Top resid features:
2
Token 2
Feature activation+0.394
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
133
Token133
Feature activation+1.710
Top resid features:
in
Token in
Feature activation+0.184
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
draft
Token draft
Feature activation+0.071
Top resid features:
notification
Token notification
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
G
TokenG
Feature activation+0.001
Top resid features:
roups
Tokenroups
Feature activation+0.001
Top resid features:
ranging
Token ranging
Feature activation+0.015
Top resid features:
from
Token from
Feature activation+2.578
Top resid features:
Amnesty
Token Amnesty
Feature activation+0.033
Top resid features:
International
Token International
Feature activation+0.054
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
move
Token move
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
business
Token business
Feature activation-0.002
Top resid features:
from
Token from
Feature activation+0.372
Top resid features:
one
Token one
Feature activation+2.173
Top resid features:
opportunity
Token opportunity
Feature activation+0.037
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation+0.000
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
speed
Token speed
Feature activation-0.002
Top resid features:
down
Token down
Feature activation-0.001
Top resid features:
highways
Token highways
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
switching
Token switching
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+2.549
Top resid features:
cell
Token cell
Feature activation+0.012
Top resid features:
tower
Token tower
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
cell
Token cell
Feature activation+0.000
Top resid features:
tower
Token tower
Feature activation+0.000
Top resid features:
olt
Tokenolt
Feature activation-0.001
Top resid features:
aic
Tokenaic
Feature activation-0.007
Top resid features:
panels
Token panels
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
produce
Token produce
Feature activation-0.025
Top resid features:
enough
Token enough
Feature activation+2.599
Top resid features:
renewable
Token renewable
Feature activation-0.061
Top resid features:
electricity
Token electricity
Feature activation+0.055
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
4
Token 4
Feature activation+0.000
Top resid features:
however
Token however
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
best
Token best
Feature activation+0.012
Top resid features:
interest
Token interest
Feature activation+2.361
Top resid features:
of
Token of
Feature activation+0.073
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
wider
Token wider
Feature activation+0.029
Top resid features:
Java
Token Java
Feature activation+0.012
Top resid features:
ecosystem
Token ecosystem
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
Worcester
Token Worcester
Feature activation+0.007
Top resid features:
Sharks
Token Sharks
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
from
Token from
Feature activation+2.123
Top resid features:
Worcester
Token Worcester
Feature activation+0.042
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Massachusetts
Token Massachusetts
Feature activation+0.048
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
San
Token San
Feature activation+0.000
Top resid features:
gradient
Token gradient
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
mantle
Token mantle
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.214
Top resid features:
one
Token one
Feature activation+1.831
Top resid features:
spot
Token spot
Feature activation+0.380
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
expression
Token expression
Feature activation+0.051
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
west
Token west
Feature activation+0.184
Top resid features:
coast
Token coast
Feature activation+0.368
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
British
Token British
Feature activation+0.003
Top resid features:
Columbia
Token Columbia
Feature activation+0.730
Top resid features:
[
Token[
Feature activation+0.005
Top resid features:
4
Token4
Feature activation-0.003
Top resid features:
]
Token]
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
ve
Tokenve
Feature activation-0.000
Top resid features:
ever
Token ever
Feature activation+0.003
Top resid features:
wanted
Token wanted
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
learn
Token learn
Feature activation-0.093
Top resid features:
enough
Token enough
Feature activation+2.599
Top resid features:
program
Token program
Feature activation+0.011
Top resid features:
ing
Tokening
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
create
Token create
Feature activation+0.000
Top resid features:
rich
Token rich
Feature activation+0.000
Top resid features:
seven
Tokenseven
Feature activation+0.001
Top resid features:
years
Token years
Feature activation+0.031
Top resid features:
"
Token"
Feature activation+0.025
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
raise
Token raise
Feature activation+0.025
Top resid features:
enough
Token enough
Feature activation+2.174
Top resid features:
money
Token money
Feature activation+0.241
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
launch
Token launch
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
ll
Tokenll
Feature activation-0.002
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
until
Token until
Feature activation+1.880
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.336
Top resid features:
night
Token night
Feature activation+0.283
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:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.03

Head 3: 0.07

Head 4: 0.02

Head 5: 0.03

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.01

Head 10: 0.68

Head 11: 0.03

Positive logits

to4.21

to3.41

To2.64

TO2.49

To2.43

unto2.21

onto2.05

ta1.81

onward1.80

thereto1.74

eto1.73

toget1.60

arat1.59

1.57

appers1.56

1.53

into1.52

eks1.50

Enix1.47

itives1.46

Negative logits

retty-2.37

natureconservancy-1.96

vae-1.86

ench-1.85

uesday-1.83

ById-1.72

aired-1.65

EStream-1.65

everal-1.64

misunder-1.63

ategory-1.62

ickr-1.55

cffff-1.55

++;-1.55

hend-1.53

CLASSIFIED-1.52

hov-1.51

extent-1.50

Reloaded-1.50

Haunted-1.47

INTERVAL 2.958 - 3.287
CONTAINS 0.000%

would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
floor
Token floor
Feature activation+3.287
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+2.022
and
Token and
Feature activation+0.634
the
Token the
Feature activation+0.000
characters
Token characters
Feature activation+3.242
to
Token to
Feature activation+0.567
start
Token start
Feature activation+0.000
going
Token going
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.630 - 2.958
CONTAINS 0.000%

INTERVAL 2.301 - 2.630
CONTAINS 0.001%

been
Token been
Feature activation+0.000
directed
Token directed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.151
White
Token White
Feature activation+0.000
House
Token House
Feature activation+2.329
to
Token to
Feature activation+0.216
create
Token create
Feature activation+0.000
specific
Token specific
Feature activation+0.000
recommendations
Token recommendations
Feature activation+0.278
for
Token for
Feature activation+0.000
s
Tokens
Feature activation+0.000
probably
Token probably
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
exaggeration
Token exaggeration
Feature activation+0.568
to
Token to
Feature activation+2.401
say
Token say
Feature activation+0.312
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
his
Token his
Feature activation+0.000
place
Token place
Feature activation+0.000
"
Token "
Feature activation+2.554
to
Tokento
Feature activation+0.000
judge
Token judge
Feature activation+0.000
our
Token our
Feature activation+0.000
current
Token current
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
,
Token,
Feature activation+0.403
133
Token133
Feature activation+1.586
in
Token in
Feature activation+0.740
the
Token the
Feature activation+0.814
draft
Token draft
Feature activation+1.197
notification
Token notification
Feature activation+2.302
to
Token to
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
254
Token254
Feature activation+0.000
in
Token in
Feature activation+0.000
mantle
Token mantle
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
spot
Token spot
Feature activation+2.413
of
Token of
Feature activation+0.000
expression
Token expression
Feature activation+2.351
,
Token,
Feature activation+2.141
and
Token and
Feature activation+0.000
diff
Token diff
Feature activation+0.000
uses
Tokenuses
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.972 - 2.301
CONTAINS 0.002%

Plus
TokenPlus
Feature activation+2.017
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+1.409
/
Token/
Feature activation+0.640
leg
Tokenleg
Feature activation+0.000
ends
Tokenends
Feature activation+2.104
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000
one
Token one
Feature activation+0.000
month
Token month
Feature activation+0.000
of
Token of
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
enough
Token enough
Feature activation+0.000
program
Token program
Feature activation+0.201
ing
Tokening
Feature activation+2.135
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
rich
Token rich
Feature activation+0.000
prototypes
Token prototypes
Feature activation+0.000
and
Token and
Feature activation+0.000
years
Token years
Feature activation+0.000
"
Token"
Feature activation+1.438
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
enough
Token enough
Feature activation+0.141
money
Token money
Feature activation+2.118
for
Token for
Feature activation+0.173
launch
Token launch
Feature activation+0.468
.
Token.
Feature activation+0.015
"
Token "
Feature activation+0.432
Americans
TokenAmericans
Feature activation+0.000
Sharks
Token Sharks
Feature activation+0.000
,
Token,
Feature activation+0.835
from
Token from
Feature activation+0.000
Worcester
Token Worcester
Feature activation+1.541
,
Token,
Feature activation+1.069
Massachusetts
Token Massachusetts
Feature activation+2.155
to
Token to
Feature activation+0.000
San
Token San
Feature activation+0.000
Jose
Token Jose
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
enough
Token enough
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+2.022
and
Token and
Feature activation+0.634
the
Token the
Feature activation+0.000
characters
Token characters
Feature activation+3.242
to
Token to
Feature activation+0.567
start
Token start
Feature activation+0.000

INTERVAL 1.644 - 1.972
CONTAINS 0.006%

alert
Token alert
Feature activation+0.000
sites
Token sites
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
from
Token from
Feature activation+0.000
about
Token about
Feature activation+0.418
two
Token two
Feature activation+1.676
dozen
Token dozen
Feature activation+1.633
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
pit
Token pit
Feature activation+0.000
iful
Tokeniful
Feature activation+0.000
gradually
Token gradually
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
from
Token from
Feature activation+0.000
11
Token 11
Feature activation+0.876
this
Token this
Feature activation+0.259
year
Token year
Feature activation+1.727
to
Token to
Feature activation+0.000
5
Token 5
Feature activation+0.000
in
Token in
Feature activation+0.000
2025
Token 2025
Feature activation+0.228
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.035
be
Token be
Feature activation+0.000
homosexual
Token homosexual
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.861
is
Token is
Feature activation+1.774
to
Token to
Feature activation+0.307
be
Token be
Feature activation+0.084
heterosexual
Token heterosexual
Feature activation+0.000
or
Token or
Feature activation+0.000
any
Token any
Feature activation+0.307
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
his
Token his
Feature activation+0.000
authority
Token authority
Feature activation+0.183
as
Token as
Feature activation+0.000
president
Token president
Feature activation+1.813
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
termin
Tokentermin
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
days
Token days
Feature activation+0.000
from
Token from
Feature activation+0.000
10
Token 10
Feature activation+1.084
,
Token,
Feature activation+0.229
500
Token500
Feature activation+1.667
to
Token to
Feature activation+0.000
over
Token over
Feature activation+0.000
28
Token 28
Feature activation+0.000
,
Token,
Feature activation+0.000
200
Token200
Feature activation+0.000

INTERVAL 1.315 - 1.644
CONTAINS 0.016%

improved
Token improved
Feature activation+0.000
from
Token from
Feature activation+0.000
2
Token 2
Feature activation+0.611
.
Token.
Feature activation+0.172
05
Token05
Feature activation+1.181
%
Token%
Feature activation+1.373
to
Token to
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
89
Token89
Feature activation+0.000
%
Token%
Feature activation+0.000
Oklahoma
Token Oklahoma
Feature activation+0.000
State
Token State
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.000
General
Token General
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
Pruitt
Token Pruitt
Feature activation+1.319
to
Token to
Feature activation+0.000
lead
Token lead
Feature activation+0.000
the
Token the
Feature activation+0.000
Environmental
Token Environmental
Feature activation+0.000
Protection
Token Protection
Feature activation+0.000
220
Token 220
Feature activation+0.000
km
Tokenkm
Feature activation+0.000
line
Token line
Feature activation+0.000
from
Token from
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.403
City
Token City
Feature activation+1.417
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
rapidly
Token rapidly
Feature activation+0.000
growing
Token growing
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
several
Token several
Feature activation+1.256
days
Token days
Feature activation+1.544
to
Token to
Feature activation+0.000
weeks
Token weeks
Feature activation+0.075
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
Hard
Token Hard
Feature activation+0.000
Rock
Token Rock
Feature activation+0.000
and
Token and
Feature activation+0.000
Spring
Token Spring
Feature activation+0.000
steen
Tokensteen
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.348
to
Token to
Feature activation+0.277
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
terms
Token terms
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.986 - 1.315
CONTAINS 0.048%

be
Token be
Feature activation+0.000
too
Token too
Feature activation+0.000
grav
Token grav
Feature activation+0.000
itation
Tokenitation
Feature activation+0.000
ally
Tokenally
Feature activation+0.318
chaotic
Token chaotic
Feature activation+1.114
to
Token to
Feature activation+0.000
host
Token host
Feature activation+0.000
planets
Token planets
Feature activation+0.000
(
Token (
Feature activation+0.000
see
Tokensee
Feature activation+0.000
vast
Token vast
Feature activation+0.280
areas
Token areas
Feature activation+0.405
of
Token of
Feature activation+0.000
France
Token France
Feature activation+0.584
and
Token and
Feature activation+0.000
Belgium
Token Belgium
Feature activation+1.025
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
one
Token one
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
layered
Token layered
Feature activation+0.559
clothing
Token clothing
Feature activation+1.179
to
Token to
Feature activation+0.000
dual
Token dual
Feature activation+0.000
-
Token-
Feature activation+0.000
function
Tokenfunction
Feature activation+0.000
support
Token support
Feature activation+0.000
$
Token $
Feature activation+0.000
27
Token27
Feature activation+0.000
,
Token,
Feature activation+0.000
500
Token500
Feature activation+0.710
in
Token in
Feature activation+0.095
1972
Token 1972
Feature activation+1.296
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000
90
Token90
Feature activation+0.000
,
Token,
Feature activation+0.000
102
Token102
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
reass
Token reass
Feature activation+0.000
igned
Tokenigned
Feature activation+0.000
in
Token in
Feature activation+0.198
2003
Token 2003
Feature activation+1.232
from
Token from
Feature activation+0.000
Mississippi
Token Mississippi
Feature activation+0.396
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
small
Token small
Feature activation+0.000

INTERVAL 0.657 - 0.986
CONTAINS 0.126%

the
Token the
Feature activation+0.000
horror
Token horror
Feature activation+0.000
video
Token video
Feature activation+0.281
game
Token game
Feature activation+0.727
adaptation
Token adaptation
Feature activation+0.914
title
Token title
Feature activation+0.811
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
billion
Token billion
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
this
Token this
Feature activation+0.359
product
Token product
Feature activation+0.776
.
Token.
Feature activation+0.000
Ver
Token Ver
Feature activation+0.000
ified
Tokenified
Feature activation+0.000
Purchase
Token Purchase
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.370
Tuesday
Token Tuesday
Feature activation+0.833
morning
Token morning
Feature activation+0.979
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
him
Token him
Feature activation+0.088
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
15
Token 15
Feature activation+0.000
April
Token April
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.787
behind
Token behind
Feature activation+0.385
,
Token,
Feature activation+0.586
escaping
Token escaping
Feature activation+0.000
Syria
Token Syria
Feature activation+0.087
to
Token to
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
in
Token in
Feature activation+0.708
the
Token the
Feature activation+0.443
end
Token end
Feature activation+0.712
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bob
TokenBob
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000

INTERVAL 0.329 - 0.657
CONTAINS 0.411%

Handler
TokenHandler
Feature activation+0.182
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
log
Token log
Feature activation+0.000
messages
Token messages
Feature activation+0.346
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
remote
Token remote
Feature activation+0.000
server
Token server
Feature activation+0.000
via
Token via
Feature activation+0.000
ing
Tokening
Feature activation+0.182
and
Token and
Feature activation+0.179
a
Token a
Feature activation+0.216
much
Token much
Feature activation+0.000
weaker
Token weaker
Feature activation+0.000
yen
Token yen
Feature activation+0.472
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
the
Token the
Feature activation+0.000
Dow
Token Dow
Feature activation+0.000
a
Token a
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.073
best
Token best
Feature activation+0.262
to
Token to
Feature activation+0.374
show
Token show
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
an
Token an
Feature activation+0.000
authority
Token authority
Feature activation+0.000
live
Token live
Feature activation+0.000
mar
Token mar
Feature activation+0.000
i
Tokeni
Feature activation+0.000
achi
Tokenachi
Feature activation+0.289
band
Token band
Feature activation+0.560
on
Token on
Feature activation+0.477
Monday
Token Monday
Feature activation+0.323
as
Token as
Feature activation+0.270
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
amend
Token amend
Feature activation+0.000
the
Token the
Feature activation+0.000
1964
Token 1964
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Act
Token Act
Feature activation+0.453
to
Token to
Feature activation+0.000
ban
Token ban
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.329
CONTAINS 99.390%

Several
TokenSeveral
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
given
Token given
Feature activation+0.000
dates
Token dates
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
therapy
Token therapy
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
cool
Token cool
Feature activation+0.000
little
Token little
Feature activation+0.000
extras
Token extras
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
printed
Token printed
Feature activation+0.000
copies
Token copies
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.000
standards
Token standards
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
put
Token put
Feature activation+0.000
on
Token on
Feature activation+0.063
hold
Token hold
Feature activation+0.000
by
Token by
Feature activation+0.000
courts
Token courts
Feature activation+0.232
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
B
TokenB
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
passenger
Token passenger
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
was
Token was
Feature activation+0.000
diverted
Token diverted
Feature activation+0.000
following
Token following
Feature activation+0.000
an
Token an
Feature activation+0.000
incident
Token incident
Feature activation+0.000
on
Token on
Feature activation+0.000
board
Token board
Feature activation+0.000
('
Token('
Feature activation+0.000
oops
Tokenoops
Feature activation+0.000
');
Token');
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
say
Token say
Feature activation+0.000
someone
Token someone
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 H9.10: (feature 11339)

TOP ACTIVATIONS
MAX = 3.622

to
Token to
Feature activation+0.000
honestly
Token honestly
Feature activation+0.000
square
Token square
Feature activation+0.000
this
Token this
Feature activation+2.516
zombie
Token zombie
Feature activation+1.724
pact
Token pact
Feature activation+3.622
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
genuinely
Token genuinely
Feature activation+0.000
progressive
Token progressive
Feature activation+0.000
trade
Token trade
Feature activation+0.000
Pair
Token Pair
Feature activation+0.000
ing
Tokening
Feature activation+0.000
the
Token the
Feature activation+0.070
tablet
Token tablet
Feature activation+2.529
form
Token form
Feature activation+0.962
factor
Token factor
Feature activation+3.597
up
Token up
Feature activation+1.870
with
Token with
Feature activation+0.000
LTE
Token LTE
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
this
Token this
Feature activation+0.000
coincides
Token coincides
Feature activation+0.307
suspicious
Token suspicious
Feature activation+2.073
ly
Tokenly
Feature activation+3.537
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
estimates
Token estimates
Feature activation+0.000
National
Token National
Feature activation+0.000
Rape
Token Rape
Feature activation+0.000
Day
Token Day
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
it
Token it
Feature activation+3.511
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
deserving
Token deserving
Feature activation+0.000
federal
Token federal
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
adjust
Tokenadjust
Feature activation+0.000
ing
Tokening
Feature activation+0.227
head
Token head
Feature activation+0.210
band
Tokenband
Feature activation+3.498
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
quick
Token quick
Feature activation+0.000
-
Token-
Feature activation+0.000
v
Tokenv
Feature activation+0.000
oting
Tokenoting
Feature activation+0.963
your
Token your
Feature activation+0.000
conscience
Token conscience
Feature activation+1.126
âĢ
TokenâĢ
Feature activation+1.509
Ŀ
TokenĿ
Feature activation+3.397
with
Token with
Feature activation+0.000
giving
Token giving
Feature activation+0.000
away
Token away
Feature activation+0.000
the
Token the
Feature activation+0.000
presidency
Token presidency
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
(
Token (
Feature activation+0.000
who
Tokenwho
Feature activation+0.000
associated
Token associated
Feature activation+0.000
the
Token the
Feature activation+0.000
agency
Token agency
Feature activation+3.383
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
health
Token health
Feature activation+0.000
-
Token-
Feature activation+0.000
cultures
Token cultures
Feature activation+0.000
have
Token have
Feature activation+0.000
equ
Token equ
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
human
Token human
Feature activation+0.000
nudity
Token nudity
Feature activation+3.264
with
Token with
Feature activation+0.000
sexuality
Token sexuality
Feature activation+0.000
,
Token,
Feature activation+0.000
inherently
Token inherently
Feature activation+0.000
stimulating
Token stimulating
Feature activation+0.000
cost
Token cost
Feature activation+0.000
is
Token is
Feature activation+0.000
shared
Token shared
Feature activation+0.000
25
Token 25
Feature activation+2.812
-
Token-
Feature activation+0.917
75
Token75
Feature activation+3.226
%
Token%
Feature activation+2.964
by
Token by
Feature activation+0.000
Es
Token Es
Feature activation+0.000
a
Tokena
Feature activation+0.389
and
Token and
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ambition
Token ambition
Feature activation+0.000
in
Token in
Feature activation+0.000
mixing
Token mixing
Feature activation+0.000
fantasy
Token fantasy
Feature activation+3.194
and
Token and
Feature activation+0.000
politics
Token politics
Feature activation+0.663
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Do
Token Do
Feature activation+0.000
not
Token not
Feature activation+0.000
confuse
Token confuse
Feature activation+0.000
conformity
Token conformity
Feature activation+3.103
with
Token with
Feature activation+0.000
superficial
Token superficial
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
or
Token or
Feature activation+0.000
ignorance
Token ignorance
Feature activation+0.666
long
Token long
Feature activation+0.513
turn
Token turn
Feature activation+0.880
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Kat
Token Kat
Feature activation+0.000
ana
Tokenana
Feature activation+3.043
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
smooth
Token smooth
Feature activation+0.000
fade
Token fade
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+2.686
's
Token's
Feature activation+1.171
jazz
Token jazz
Feature activation+1.139
and
Token and
Feature activation+0.238
jungle
Token jungle
Feature activation+1.645
roots
Token roots
Feature activation+3.035
with
Token with
Feature activation+0.000
Berlin
Token Berlin
Feature activation+0.000
's
Token's
Feature activation+0.000
musical
Token musical
Feature activation+0.000
history
Token history
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
equate
Token equate
Feature activation+0.000
it
Token it
Feature activation+2.998
even
Token even
Feature activation+1.633
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ant
Token ant
Feature activation+0.000
,"
Token,"
Feature activation+0.000
is
Token is
Feature activation+0.000
shared
Token shared
Feature activation+0.000
25
Token 25
Feature activation+2.812
-
Token-
Feature activation+0.917
75
Token75
Feature activation+3.226
%
Token%
Feature activation+2.964
by
Token by
Feature activation+0.000
Es
Token Es
Feature activation+0.000
a
Tokena
Feature activation+0.389
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
The
TokenThe
Feature activation+0.000
state
Token state
Feature activation+0.000
party
Token party
Feature activation+0.000
shares
Token shares
Feature activation+0.031
these
Token these
Feature activation+0.705
receipts
Token receipts
Feature activation+2.944
with
Token with
Feature activation+0.000
such
Token such
Feature activation+0.000
groups
Token groups
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
ining
Tokenining
Feature activation+0.000
R
Token R
Feature activation+0.394
-
Token-
Feature activation+0.025
p
Tokenp
Feature activation+0.759
and
Tokenand
Feature activation+0.000
oc
Tokenoc
Feature activation+2.943
and
Token and
Feature activation+0.000
diagrams
Token diagrams
Feature activation+0.569
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
and
Tokenand
Feature activation+0.000
pling
Tokenpling
Feature activation+0.000
this
Token this
Feature activation+1.432
level
Token level
Feature activation+1.517
of
Token of
Feature activation+0.000
aerial
Token aerial
Feature activation+0.170
surveillance
Token surveillance
Feature activation+2.930
with
Token with
Feature activation+0.000
cellphone
Token cellphone
Feature activation+0.000
data
Token data
Feature activation+0.000
provided
Token provided
Feature activation+0.000
by
Token by
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
associate
Token associate
Feature activation+0.000
file
Token file
Feature activation+0.000
sharing
Token sharing
Feature activation+2.822
with
Token with
Feature activation+0.000
child
Token child
Feature activation+0.000
pornography
Token pornography
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
-
Token-
Feature activation+0.000
euro
Tokeneuro
Feature activation+0.000
cost
Token cost
Feature activation+0.000
is
Token is
Feature activation+0.000
shared
Token shared
Feature activation+0.000
25
Token 25
Feature activation+2.812
-
Token-
Feature activation+0.917
75
Token75
Feature activation+3.226
%
Token%
Feature activation+2.964
by
Token by
Feature activation+0.000
Es
Token Es
Feature activation+0.000

Top DFA by src position
MAX = 3.941

the
Token the
Feature activation+0.001
Top resid features:
Trudeau
Token Trudeau
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
honestly
Token honestly
Feature activation+0.009
Top resid features:
square
Token square
Feature activation+3.896
Top resid features:
this
Token this
Feature activation+0.171
Top resid features:
zombie
Token zombie
Feature activation-0.004
Top resid features:
pact
Token pact
Feature activation+0.006
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
take
Token take
Feature activation-0.000
Top resid features:
notes
Token notes
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Pair
Token Pair
Feature activation+0.715
Top resid features:
ing
Tokening
Feature activation+2.823
Top resid features:
the
Token the
Feature activation+0.323
Top resid features:
tablet
Token tablet
Feature activation+0.035
Top resid features:
form
Token form
Feature activation+0.078
Top resid features:
factor
Token factor
Feature activation+0.036
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
six
Token six
Feature activation-0.001
Top resid features:
years
Token years
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
though
Token though
Feature activation+0.002
Top resid features:
this
Token this
Feature activation-0.000
Top resid features:
coincides
Token coincides
Feature activation+3.835
Top resid features:
suspicious
Token suspicious
Feature activation+0.093
Top resid features:
ly
Tokenly
Feature activation+0.045
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
tax
Token tax
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
National
Token National
Feature activation+0.015
Top resid features:
Rape
Token Rape
Feature activation-0.003
Top resid features:
Day
Token Day
Feature activation-0.038
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
replace
Token replace
Feature activation+3.934
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
deserving
Token deserving
Feature activation+0.000
Top resid features:
standard
Token standard
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
K
Token K
Feature activation-0.000
Top resid features:
8
Token8
Feature activation-0.001
Top resid features:
72
Token72
Feature activation-0.005
Top resid features:
combines
Token combines
Feature activation+3.941
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
comfort
Token comfort
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.028
Top resid features:
our
Token our
Feature activation-0.018
Top resid features:
legendary
Token legendary
Feature activation-0.035
Top resid features:
remember
Token remember
Feature activation+0.002
Top resid features:
2000
Token 2000
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.009
Top resid features:
likely
Token likely
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
associate
Token associate
Feature activation+3.604
Top resid features:
âĢ
Token âĢ
Feature activation+0.024
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
v
Tokenv
Feature activation+0.003
Top resid features:
oting
Tokenoting
Feature activation+0.074
Top resid features:
your
Token your
Feature activation-0.006
Top resid features:
Republicans
Token Republicans
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
Congress
Token Congress
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
who
Tokenwho
Feature activation-0.001
Top resid features:
associated
Token associated
Feature activation+3.712
Top resid features:
the
Token the
Feature activation+0.179
Top resid features:
agency
Token agency
Feature activation+0.015
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
Some
TokenSome
Feature activation+0.001
Top resid features:
modern
Token modern
Feature activation+0.003
Top resid features:
cultures
Token cultures
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.009
Top resid features:
equ
Token equ
Feature activation+0.015
Top resid features:
ated
Tokenated
Feature activation+3.582
Top resid features:
human
Token human
Feature activation+0.025
Top resid features:
nudity
Token nudity
Feature activation+0.018
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
sexuality
Token sexuality
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
billion
Tokenbillion
Feature activation-0.006
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
euro
Tokeneuro
Feature activation-0.001
Top resid features:
cost
Token cost
Feature activation-0.033
Top resid features:
is
Token is
Feature activation-0.027
Top resid features:
shared
Token shared
Feature activation+3.730
Top resid features:
25
Token 25
Feature activation+0.050
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
75
Token75
Feature activation+0.010
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
ambition
Token ambition
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
mixing
Token mixing
Feature activation+3.688
Top resid features:
fantasy
Token fantasy
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
politics
Token politics
Feature activation+0.000
Top resid features:
remains
Token remains
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.003
Top resid features:
are
Token are
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Do
Token Do
Feature activation-0.002
Top resid features:
not
Token not
Feature activation-0.002
Top resid features:
confuse
Token confuse
Feature activation+3.466
Top resid features:
conformity
Token conformity
Feature activation+0.083
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
superficial
Token superficial
Feature activation+0.000
Top resid features:
ity
Tokenity
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
new
Token new
Feature activation-0.002
Top resid features:
distance
Token distance
Feature activation-0.026
Top resid features:
driver
Token driver
Feature activation-0.007
Top resid features:
that
Token that
Feature activation-0.004
Top resid features:
blends
Token blends
Feature activation+3.410
Top resid features:
the
Token the
Feature activation+0.267
Top resid features:
graceful
Token graceful
Feature activation-0.009
Top resid features:
long
Token long
Feature activation-0.006
Top resid features:
turn
Token turn
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
p
Tokenp
Feature activation+0.000
Top resid features:
usher
Tokenusher
Feature activation+0.000
Top resid features:
records
Token records
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Just
Token Just
Feature activation+0.002
Top resid features:
replace
Token replace
Feature activation+3.382
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
former
Token former
Feature activation+0.015
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
jazz
Token jazz
Feature activation-0.008
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
wouldn
Token wouldn
Feature activation+0.005
Top resid features:
't
Token't
Feature activation+0.004
Top resid features:
want
Token want
Feature activation-0.007
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
equate
Token equate
Feature activation+3.353
Top resid features:
it
Token it
Feature activation+0.025
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ant
Token ant
Feature activation+0.000
Top resid features:
billion
Tokenbillion
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
euro
Tokeneuro
Feature activation-0.004
Top resid features:
cost
Token cost
Feature activation-0.026
Top resid features:
is
Token is
Feature activation-0.028
Top resid features:
shared
Token shared
Feature activation+3.376
Top resid features:
25
Token 25
Feature activation+0.016
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
75
Token75
Feature activation+0.010
Top resid features:
%
Token%
Feature activation+0.030
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
state
Token state
Feature activation+0.003
Top resid features:
party
Token party
Feature activation+0.001
Top resid features:
shares
Token shares
Feature activation+2.668
Top resid features:
these
Token these
Feature activation+0.576
Top resid features:
receipts
Token receipts
Feature activation+0.039
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
groups
Token groups
Feature activation+0.000
Top resid features:
iler
Tokeniler
Feature activation-0.002
Top resid features:
R
TokenR
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Comb
TokenComb
Feature activation+0.054
Top resid features:
ining
Tokenining
Feature activation+3.214
Top resid features:
R
Token R
Feature activation+0.072
Top resid features:
-
Token-
Feature activation+0.032
Top resid features:
p
Tokenp
Feature activation+0.001
Top resid features:
and
Tokenand
Feature activation+0.006
Top resid features:
oc
Tokenoc
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
ou
Tokenou
Feature activation+0.002
Top resid features:
pling
Tokenpling
Feature activation+3.065
Top resid features:
this
Token this
Feature activation+0.122
Top resid features:
level
Token level
Feature activation+0.078
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
aerial
Token aerial
Feature activation+0.008
Top resid features:
surveillance
Token surveillance
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Therefore
Token Therefore
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
we
Token we
Feature activation-0.000
Top resid features:
must
Token must
Feature activation-0.003
Top resid features:
associate
Token associate
Feature activation+3.147
Top resid features:
file
Token file
Feature activation+0.054
Top resid features:
sharing
Token sharing
Feature activation+0.087
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
child
Token child
Feature activation+0.000
Top resid features:
pornography
Token pornography
Feature activation+0.000
Top resid features:
billion
Tokenbillion
Feature activation-0.005
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
euro
Tokeneuro
Feature activation-0.005
Top resid features:
cost
Token cost
Feature activation-0.023
Top resid features:
is
Token is
Feature activation-0.040
Top resid features:
shared
Token shared
Feature activation+3.348
Top resid features:
25
Token 25
Feature activation+0.012
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
75
Token75
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.01

Head 2: 0.05

Head 3: 0.06

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.04

Head 8: 0.03

Head 9: 0.02

Head 10: 0.66

Head 11: 0.02

Positive logits

with4.60

with4.03

withd3.73

WITH3.57

With3.56

With3.18

together2.20

dots2.14

between2.10

alongside2.06

wi2.06

wit2.01

icut1.98

along1.89

amongst1.88

against1.87

ulner1.85

chenko1.85

anium1.84

WithNo1.84

Negative logits

hindsight-2.38

inventoryQuantity-2.23

itary-2.21

needed-1.98

impunity-1.95

warning-1.90

cember-1.85

wolves-1.80

redacted-1.78

doubted-1.75

FORE-1.70

delayed-1.68

atorium-1.66

��-1.66

��-1.65

dylib-1.62

-1.60

anticipated-1.59

grave-1.58

intention-1.55

INTERVAL 3.260 - 3.622
CONTAINS 0.001%

National
Token National
Feature activation+0.000
Rape
Token Rape
Feature activation+0.000
Day
Token Day
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
it
Token it
Feature activation+3.511
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
deserving
Token deserving
Feature activation+0.000
federal
Token federal
Feature activation+0.000
Pair
Token Pair
Feature activation+0.000
ing
Tokening
Feature activation+0.000
the
Token the
Feature activation+0.070
tablet
Token tablet
Feature activation+2.529
form
Token form
Feature activation+0.962
factor
Token factor
Feature activation+3.597
up
Token up
Feature activation+1.870
with
Token with
Feature activation+0.000
LTE
Token LTE
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
adjust
Tokenadjust
Feature activation+0.000
ing
Tokening
Feature activation+0.227
head
Token head
Feature activation+0.210
band
Tokenband
Feature activation+3.498
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
quick
Token quick
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Token to
Feature activation+0.000
honestly
Token honestly
Feature activation+0.000
square
Token square
Feature activation+0.000
this
Token this
Feature activation+2.516
zombie
Token zombie
Feature activation+1.724
pact
Token pact
Feature activation+3.622
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
genuinely
Token genuinely
Feature activation+0.000
progressive
Token progressive
Feature activation+0.000
trade
Token trade
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
this
Token this
Feature activation+0.000
coincides
Token coincides
Feature activation+0.307
suspicious
Token suspicious
Feature activation+2.073
ly
Tokenly
Feature activation+3.537
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
estimates
Token estimates
Feature activation+0.000

INTERVAL 2.898 - 3.260
CONTAINS 0.001%

long
Token long
Feature activation+0.513
turn
Token turn
Feature activation+0.880
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Kat
Token Kat
Feature activation+0.000
ana
Tokenana
Feature activation+3.043
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
smooth
Token smooth
Feature activation+0.000
fade
Token fade
Feature activation+0.000
of
Token of
Feature activation+0.000
The
TokenThe
Feature activation+0.000
state
Token state
Feature activation+0.000
party
Token party
Feature activation+0.000
shares
Token shares
Feature activation+0.031
these
Token these
Feature activation+0.705
receipts
Token receipts
Feature activation+2.944
with
Token with
Feature activation+0.000
such
Token such
Feature activation+0.000
groups
Token groups
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
pling
Tokenpling
Feature activation+0.000
this
Token this
Feature activation+1.432
level
Token level
Feature activation+1.517
of
Token of
Feature activation+0.000
aerial
Token aerial
Feature activation+0.170
surveillance
Token surveillance
Feature activation+2.930
with
Token with
Feature activation+0.000
cellphone
Token cellphone
Feature activation+0.000
data
Token data
Feature activation+0.000
provided
Token provided
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+2.686
's
Token's
Feature activation+1.171
jazz
Token jazz
Feature activation+1.139
and
Token and
Feature activation+0.238
jungle
Token jungle
Feature activation+1.645
roots
Token roots
Feature activation+3.035
with
Token with
Feature activation+0.000
Berlin
Token Berlin
Feature activation+0.000
's
Token's
Feature activation+0.000
musical
Token musical
Feature activation+0.000
history
Token history
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
equate
Token equate
Feature activation+0.000
it
Token it
Feature activation+2.998
even
Token even
Feature activation+1.633
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ant
Token ant
Feature activation+0.000
,"
Token,"
Feature activation+0.000

INTERVAL 2.535 - 2.898
CONTAINS 0.001%

records
Token records
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
replace
Token replace
Feature activation+0.000
the
Token the
Feature activation+0.090
former
Token former
Feature activation+2.686
's
Token's
Feature activation+1.171
jazz
Token jazz
Feature activation+1.139
and
Token and
Feature activation+0.238
jungle
Token jungle
Feature activation+1.645
roots
Token roots
Feature activation+3.035
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
associate
Token associate
Feature activation+0.000
file
Token file
Feature activation+0.000
sharing
Token sharing
Feature activation+2.822
with
Token with
Feature activation+0.000
child
Token child
Feature activation+0.000
pornography
Token pornography
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
-
Token-
Feature activation+0.000
euro
Tokeneuro
Feature activation+0.000
cost
Token cost
Feature activation+0.000
is
Token is
Feature activation+0.000
shared
Token shared
Feature activation+0.000
25
Token 25
Feature activation+2.812
-
Token-
Feature activation+0.917
75
Token75
Feature activation+3.226
%
Token%
Feature activation+2.964
by
Token by
Feature activation+0.000
Es
Token Es
Feature activation+0.000
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.000
your
Token your
Feature activation+0.000
finds
Token finds
Feature activation+2.603
with
Token with
Feature activation+0.000
others
Token others
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
the
Token the
Feature activation+1.222
bot
Token bot
Feature activation+0.613
lane
Tokenlane
Feature activation+2.643
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.000
different
Token different
Feature activation+0.000
supports
Token supports
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 2.173 - 2.535
CONTAINS 0.003%

Ŀ
TokenĿ
Feature activation+2.070
(
Token (
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
terrified
Token terrified
Feature activation+0.000
)
Token)
Feature activation+2.206
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
w
Tokenw
Feature activation+0.000
or
Tokenor
Feature activation+0.000
but
Token but
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.205
session
Token session
Feature activation+0.685
data
Token data
Feature activation+2.241
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
have
Token have
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
those
Token those
Feature activation+0.000
which
Token which
Feature activation+0.000
combine
Token combine
Feature activation+0.019
glucose
Token glucose
Feature activation+2.198
and
Token and
Feature activation+0.435
fructose
Token fructose
Feature activation+1.464
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
soft
Token soft
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
creatively
Token creatively
Feature activation+0.000
combine
Token combine
Feature activation+0.000
those
Token those
Feature activation+0.610
themes
Token themes
Feature activation+2.364
into
Token into
Feature activation+0.000
your
Token your
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
fusion
Token fusion
Feature activation+0.000
map
Token map
Feature activation+0.000
that
Token that
Feature activation+0.000
information
Token information
Feature activation+0.000
to
Token to
Feature activation+0.000
match
Token match
Feature activation+0.000
potential
Token potential
Feature activation+0.000
advertisers
Token advertisers
Feature activation+2.367
program
Token program
Feature activation+0.842
matically
Tokenmatically
Feature activation+1.028
,
Token,
Feature activation+0.409
mentioning
Token mentioning
Feature activation+0.000
relevant
Token relevant
Feature activation+0.000

INTERVAL 1.811 - 2.173
CONTAINS 0.006%

.
Token.
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.000
shares
Token shares
Feature activation+0.000
a
Token a
Feature activation+0.553
draft
Token draft
Feature activation+0.798
position
Token position
Feature activation+2.067
with
Token with
Feature activation+0.000
Ball
Token Ball
Feature activation+0.000
,
Token,
Feature activation+0.000
being
Token being
Feature activation+0.000
selected
Token selected
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
led
Token led
Feature activation+0.000
Real
Token Real
Feature activation+0.000
Salt
Token Salt
Feature activation+0.000
Lake
Token Lake
Feature activation+1.972
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
title
Token title
Feature activation+0.000
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
K
Token K
Feature activation+0.000
ombat
Tokenombat
Feature activation+0.000
X
Token X
Feature activation+0.000
combines
Token combines
Feature activation+0.000
cinematic
Token cinematic
Feature activation+0.091
presentation
Token presentation
Feature activation+2.095
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
new
Token new
Feature activation+0.000
gameplay
Token gameplay
Feature activation+0.000
to
Token to
Feature activation+0.000
participants
Token participants
Feature activation+0.000
to
Token to
Feature activation+0.000
compare
Token compare
Feature activation+0.000
wound
Token wound
Feature activation+0.000
healing
Token healing
Feature activation+0.933
times
Token times
Feature activation+2.065
between
Token between
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
treatment
Token treatment
Feature activation+0.128
alone
Token alone
Feature activation+0.832
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
discussing
Token discussing
Feature activation+0.000
that
Token that
Feature activation+1.902
question
Token question
Feature activation+1.281
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
representatives
Token representatives
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.449 - 1.811
CONTAINS 0.009%

Christian
Token Christian
Feature activation+0.000
belief
Token belief
Feature activation+0.000
and
Token and
Feature activation+0.000
equ
Token equ
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
them
Token them
Feature activation+1.799
both
Token both
Feature activation+2.285
as
Token as
Feature activation+0.000
fictional
Token fictional
Feature activation+0.000
characters
Token characters
Feature activation+0.036
.
Token.
Feature activation+0.000
B
Token B
Feature activation+0.000
izz
Tokenizz
Feature activation+0.000
will
Token will
Feature activation+0.000
share
Token share
Feature activation+0.000
the
Token the
Feature activation+0.086
app
Token app
Feature activation+1.469
's
Token's
Feature activation+0.372
"
Token "
Feature activation+0.000
women
Tokenwomen
Feature activation+0.000
first
Token first
Feature activation+0.000
"
Token"
Feature activation+0.210
that
Token that
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
shares
Token shares
Feature activation+1.863
in
Token in
Feature activation+2.276
common
Token common
Feature activation+1.631
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
renowned
Token renowned
Feature activation+0.000
ideological
Token ideological
Feature activation+0.000
rivals
Token rivals
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
the
Token the
Feature activation+0.000
function
Token function
Feature activation+0.069
environment
Token environment
Feature activation+1.665
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+0.000
up
Token up
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
equate
Token equate
Feature activation+0.000
it
Token it
Feature activation+2.998
even
Token even
Feature activation+1.633
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ant
Token ant
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 1.087 - 1.449
CONTAINS 0.017%

Who
TokenWho
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.000
a
Token a
Feature activation+0.000
story
Token story
Feature activation+1.090
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
misunderstood
Token misunderstood
Feature activation+0.000
?
Token?
Feature activation+0.000
following
Token following
Feature activation+0.000
a
Token a
Feature activation+0.000
heated
Token heated
Feature activation+0.000
dispute
Token dispute
Feature activation+0.133
on
Token on
Feature activation+0.253
Wednesday
Token Wednesday
Feature activation+1.271
involving
Token involving
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+0.000
's
Token's
Feature activation+0.000
answer
Token answer
Feature activation+0.000
in
Token in
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
connects
Token connects
Feature activation+0.000
hosts
Token hosts
Feature activation+1.210
and
Token and
Feature activation+0.000
travellers
Token travellers
Feature activation+0.827
all
Token all
Feature activation+0.511
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
Dozens
Token Dozens
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
share
Token share
Feature activation+0.000
this
Token this
Feature activation+0.128
space
Token space
Feature activation+1.389
,
Token,
Feature activation+0.625
not
Token not
Feature activation+0.060
eating
Token eating
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
o
Tokeno
Feature activation+0.567
-
Token-
Feature activation+0.000
U
TokenU
Feature activation+0.000
g
Tokeng
Feature activation+0.000
ric
Tokenric
Feature activation+0.826
languages
Token languages
Feature activation+1.321
with
Token with
Feature activation+0.000
Al
Token Al
Feature activation+0.000
ta
Tokenta
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
languages
Token languages
Feature activation+0.000

INTERVAL 0.724 - 1.087
CONTAINS 0.039%

the
Token the
Feature activation+0.000
Capitals
Token Capitals
Feature activation+0.000
,
Token,
Feature activation+0.000
leading
Token leading
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.790
with
Token with
Feature activation+0.000
53
Token 53
Feature activation+0.000
assists
Token assists
Feature activation+0.000
and
Token and
Feature activation+0.000
73
Token 73
Feature activation+0.000
Finn
Token Finn
Feature activation+0.000
o
Tokeno
Feature activation+0.567
-
Token-
Feature activation+0.000
U
TokenU
Feature activation+0.000
g
Tokeng
Feature activation+0.000
ric
Tokenric
Feature activation+0.826
languages
Token languages
Feature activation+1.321
with
Token with
Feature activation+0.000
Al
Token Al
Feature activation+0.000
ta
Tokenta
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
celebrate
Token celebrate
Feature activation+0.000
it
Token it
Feature activation+0.775
all
Token all
Feature activation+0.935
the
Token the
Feature activation+0.902
same
Token same
Feature activation+0.523
way
Token way
Feature activation+0.017
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
.
Token.
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
replace
Token replace
Feature activation+0.000
them
Token them
Feature activation+1.470
regularly
Token regularly
Feature activation+0.817
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
buy
Token buy
Feature activation+0.000
new
Token new
Feature activation+0.000
laptops
Token laptops
Feature activation+0.000
show
Token show
Feature activation+0.000
impress
Token impress
Feature activation+0.000
es
Tokenes
Feature activation+0.154
the
Token the
Feature activation+0.135
exec
Token exec
Feature activation+0.000
s
Tokens
Feature activation+0.850
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
Revolution
Token Revolution
Feature activation+0.000
could
Token could
Feature activation+0.000
get
Token get
Feature activation+0.000

INTERVAL 0.362 - 0.724
CONTAINS 0.127%

American
Token American
Feature activation+0.000
Special
Token Special
Feature activation+0.000
Operations
Token Operations
Feature activation+0.000
troops
Token troops
Feature activation+0.000
always
Token always
Feature activation+0.000
coordinate
Token coordinate
Feature activation+0.472
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
men
Token men
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.000
encia
Tokenencia
Feature activation+0.000
agree
Token agree
Feature activation+0.000
K
Token K
Feature activation+0.000
ond
Tokenond
Feature activation+0.000
og
Tokenog
Feature activation+0.000
bia
Tokenbia
Feature activation+0.536
loan
Token loan
Feature activation+0.560
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
usually
Token usually
Feature activation+0.000
win
Token win
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.380
can
Token can
Feature activation+0.142
get
Token get
Feature activation+0.131
it
Token it
Feature activation+0.098
out
Token out
Feature activation+0.051
on
Token on
Feature activation+0.000
patrol
Token patrol
Feature activation+0.000
car
Token car
Feature activation+0.000
collided
Token collided
Feature activation+0.085
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
intersection
Token intersection
Feature activation+0.700
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
Pleasant
Token Pleasant
Feature activation+0.000
burg
Tokenburg
Feature activation+0.000
Drive
Token Drive
Feature activation+0.729
concerns
Token concerns
Feature activation+0.000
soon
Token soon
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
discuss
Token discuss
Feature activation+0.000
them
Token them
Feature activation+0.648
with
Token with
Feature activation+0.000
President
Token President
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.362
CONTAINS 99.797%

to
Token to
Feature activation+0.000
omit
Token omit
Feature activation+0.000
his
Token his
Feature activation+0.000
references
Token references
Feature activation+0.000
to
Token to
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+0.000
short
Token short
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
War
TokenWar
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
Bros
Token Bros
Feature activation+0.000
.
Token.
Feature activation+0.000
released
Token released
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Battle
TokenBattle
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
Party
Token Party
Feature activation+0.000
ruled
Token ruled
Feature activation+0.000
State
Token State
Feature activation+0.000
of
Token of
Feature activation+0.000
Missouri
Token Missouri
Feature activation+0.000
whose
Token whose
Feature activation+0.000
property
Token property
Feature activation+0.000
tax
Token tax
Feature activation+0.000
these
Token these
Feature activation+0.000
sick
Token sick
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
blood
Token blood
Feature activation+0.000
is
Token is
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
hands
Token hands
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
overly
Token overly
Feature activation+0.000
use
Token use
Feature activation+0.000
chocolate
Token chocolate
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
prone
Token prone
Feature activation+0.000
to
Token to
Feature activation+0.000
depression
Token depression
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 H9.10: (feature 11223)

TOP ACTIVATIONS
MAX = 6.233

He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.951
in
Token in
Feature activation+1.781
this
Token this
Feature activation+3.643
quest
Token quest
Feature activation+6.233
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
Louise
Token Louise
Feature activation+0.000
two
Token two
Feature activation+0.000
were
Token were
Feature activation+0.000
joined
Token joined
Feature activation+0.213
at
Token at
Feature activation+1.115
the
Token the
Feature activation+1.368
hip
Token hip
Feature activation+5.422
.
Token.
Feature activation+0.000
Bunny
Token Bunny
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
ret
Token ret
Feature activation+0.000
the
Token the
Feature activation+0.000
extinction
Token extinction
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
driven
Token driven
Feature activation+0.000
ultimately
Token ultimately
Feature activation+5.162
by
Token by
Feature activation+0.000
human
Token human
Feature activation+0.000
population
Token population
Feature activation+0.000
growth
Token growth
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.622
sixth
Token sixth
Feature activation+0.904
week
Token week
Feature activation+4.076
of
Token of
Feature activation+0.607
the
Token the
Feature activation+0.316
split
Token split
Feature activation+4.691
âĢĶ
Token âĢĶ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
owner
Token owner
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+3.969
only
Token only
Feature activation+4.409
by
Token by
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
changes
Token changes
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
joined
Token joined
Feature activation+0.000
in
Token in
Feature activation+0.802
Hawaii
Token Hawaii
Feature activation+4.378
by
Token by
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
Adrian
Token Adrian
Feature activation+0.000
Peterson
Token Peterson
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.911
next
Token next
Feature activation+1.349
year
Token year
Feature activation+4.168
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Perhaps
TokenPerhaps
Feature activation+0.000
unsurprisingly
Token unsurprisingly
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.341
in
Token in
Feature activation+1.986
the
Token the
Feature activation+1.622
sixth
Token sixth
Feature activation+0.904
week
Token week
Feature activation+4.076
of
Token of
Feature activation+0.607
the
Token the
Feature activation+0.316
split
Token split
Feature activation+4.691
âĢĶ
Token âĢĶ
Feature activation+0.000
,
Token,
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
prompted
Token prompted
Feature activation+0.000
in
Token in
Feature activation+2.889
part
Token part
Feature activation+3.984
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
throb
Token throb
Feature activation+0.000
bing
Tokenbing
Feature activation+0.000
light
Token light
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+3.969
only
Token only
Feature activation+4.409
by
Token by
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
a
Token a
Feature activation+0.000
resurgence
Token resurgence
Feature activation+0.000
in
Token in
Feature activation+0.000
democracy
Token democracy
Feature activation+0.000
brought
Token brought
Feature activation+0.000
about
Token about
Feature activation+3.965
by
Token by
Feature activation+0.000
new
Token new
Feature activation+0.000
technology
Token technology
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
supported
Token supported
Feature activation+0.000
almost
Token almost
Feature activation+3.167
entirely
Token entirely
Feature activation+3.891
by
Token by
Feature activation+0.000
people
Token people
Feature activation+0.000
whose
Token whose
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
have
Token have
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
overshadowed
Token overshadowed
Feature activation+0.457
in
Token in
Feature activation+2.138
recent
Token recent
Feature activation+0.349
years
Token years
Feature activation+3.811
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
50
Token 50
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.951
in
Token in
Feature activation+1.781
this
Token this
Feature activation+3.643
quest
Token quest
Feature activation+6.233
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
typing
Token typing
Feature activation+0.000
mistake
Token mistake
Feature activation+0.000
brought
Token brought
Feature activation+0.000
about
Token about
Feature activation+3.527
by
Token by
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
.
Token.
Feature activation+0.000
govern
Token govern
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+0.000
handed
Token handed
Feature activation+0.000
them
Token them
Feature activation+3.511
,
Token,
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
bidding
Token bidding
Feature activation+0.000
of
Token of
Feature activation+0.000
they
Token they
Feature activation+0.000
weren
Token weren
Feature activation+0.000
't
Token't
Feature activation+0.000
helped
Token helped
Feature activation+1.452
or
Token or
Feature activation+1.023
hurt
Token hurt
Feature activation+3.392
by
Token by
Feature activation+0.725
turnover
Token turnover
Feature activation+0.513
margin
Token margin
Feature activation+0.458
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
rier
Tokenrier
Feature activation+0.000
was
Token was
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+2.318
base
Token base
Feature activation+3.365
by
Token by
Feature activation+0.000
Damon
Token Damon
Feature activation+0.000
H
Token H
Feature activation+0.000
ae
Tokenae
Feature activation+0.000
cker
Tokencker
Feature activation+0.000
until
Token until
Feature activation+0.000
1945
Token 1945
Feature activation+0.000
-
Token -
Feature activation+0.000
were
Token were
Feature activation+0.000
inhabited
Token inhabited
Feature activation+0.773
mostly
Token mostly
Feature activation+3.295
by
Token by
Feature activation+0.252
German
Token German
Feature activation+0.000
speakers
Token speakers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
picked
Tokenpicked
Feature activation+1.625
for
Token for
Feature activation+0.076
the
Token the
Feature activation+1.178
trade
Token trade
Feature activation+0.915
minister
Token minister
Feature activation+1.536
job
Token job
Feature activation+3.208
by
Token by
Feature activation+0.000
Cameron
Token Cameron
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000

Top DFA by src position
MAX = 5.685

figured
Tokenfigured
Feature activation+0.001
Top resid features:
face
Token face
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
He
Token He
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
aided
Token aided
Feature activation+5.685
Top resid features:
in
Token in
Feature activation+0.694
Top resid features:
this
Token this
Feature activation+0.133
Top resid features:
quest
Token quest
Feature activation+0.029
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
attorney
Token attorney
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
were
Token were
Feature activation+0.004
Top resid features:
joined
Token joined
Feature activation+5.581
Top resid features:
at
Token at
Feature activation+0.115
Top resid features:
the
Token the
Feature activation+0.039
Top resid features:
hip
Token hip
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Bunny
Token Bunny
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
extinction
Token extinction
Feature activation-0.001
Top resid features:
crisis
Token crisis
Feature activation-0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.016
Top resid features:
driven
Token driven
Feature activation+5.378
Top resid features:
ultimately
Token ultimately
Feature activation+0.090
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
human
Token human
Feature activation+0.000
Top resid features:
population
Token population
Feature activation+0.000
Top resid features:
growth
Token growth
Feature activation+0.000
Top resid features:
onen
Tokenonen
Feature activation-0.001
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.036
Top resid features:
who
Token who
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.007
Top resid features:
be
Token be
Feature activation+0.008
Top resid features:
replaced
Token replaced
Feature activation+4.981
Top resid features:
in
Token in
Feature activation+0.056
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
sixth
Token sixth
Feature activation+0.001
Top resid features:
week
Token week
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
evolution
Token evolution
Feature activation-0.007
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
these
Token these
Feature activation+0.004
Top resid features:
organisms
Token organisms
Feature activation+0.029
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
driven
Token driven
Feature activation+4.730
Top resid features:
not
Token not
Feature activation+0.015
Top resid features:
only
Token only
Feature activation+0.015
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
single
Token single
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
surgery
Token surgery
Feature activation+0.022
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
He
Token He
Feature activation+0.015
Top resid features:
was
Token was
Feature activation+0.017
Top resid features:
joined
Token joined
Feature activation+4.003
Top resid features:
in
Token in
Feature activation+0.709
Top resid features:
Hawaii
Token Hawaii
Feature activation+0.009
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
running
Token running
Feature activation+0.000
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
leadership
Token leadership
Feature activation+0.011
Top resid features:
vote
Token vote
Feature activation+0.023
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
will
Token will
Feature activation+0.009
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
replaced
Token replaced
Feature activation+4.392
Top resid features:
next
Token next
Feature activation+0.013
Top resid features:
year
Token year
Feature activation+0.035
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:
onen
Tokenonen
Feature activation-0.002
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.006
Top resid features:
who
Token who
Feature activation+0.001
Top resid features:
would
Token would
Feature activation-0.006
Top resid features:
be
Token be
Feature activation+0.008
Top resid features:
replaced
Token replaced
Feature activation+4.333
Top resid features:
in
Token in
Feature activation+0.071
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
sixth
Token sixth
Feature activation+0.007
Top resid features:
week
Token week
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
acle
Tokenacle
Feature activation+0.000
Top resid features:
hallucinations
Token hallucinations
Feature activation+0.006
Top resid features:
may
Token may
Feature activation+0.002
Top resid features:
have
Token have
Feature activation-0.003
Top resid features:
been
Token been
Feature activation+0.020
Top resid features:
prompted
Token prompted
Feature activation+4.187
Top resid features:
in
Token in
Feature activation+0.085
Top resid features:
part
Token part
Feature activation+0.026
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
throb
Token throb
Feature activation+0.000
Top resid features:
evolution
Token evolution
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
these
Token these
Feature activation+0.003
Top resid features:
organisms
Token organisms
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
driven
Token driven
Feature activation+4.289
Top resid features:
not
Token not
Feature activation+0.024
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
single
Token single
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
resurgence
Token resurgence
Feature activation+0.009
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
democracy
Token democracy
Feature activation+0.005
Top resid features:
brought
Token brought
Feature activation+3.819
Top resid features:
about
Token about
Feature activation+0.532
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
technology
Token technology
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Mitt
Token Mitt
Feature activation-0.003
Top resid features:
Romney
Token Romney
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+0.008
Top resid features:
is
Token is
Feature activation-0.011
Top resid features:
supported
Token supported
Feature activation+4.225
Top resid features:
almost
Token almost
Feature activation+0.018
Top resid features:
entirely
Token entirely
Feature activation+0.011
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
whose
Token whose
Feature activation+0.000
Top resid features:
father
Token father
Feature activation-0.003
Top resid features:
ly
Tokenly
Feature activation+0.006
Top resid features:
figure
Token figure
Feature activation-0.000
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
been
Token been
Feature activation+0.005
Top resid features:
overshadowed
Token overshadowed
Feature activation+4.095
Top resid features:
in
Token in
Feature activation+0.046
Top resid features:
recent
Token recent
Feature activation+0.013
Top resid features:
years
Token years
Feature activation+0.037
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
face
Token face
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
He
Token He
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
aided
Token aided
Feature activation+1.721
Top resid features:
in
Token in
Feature activation+2.214
Top resid features:
this
Token this
Feature activation+0.123
Top resid features:
quest
Token quest
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
loyal
Token loyal
Feature activation+0.000
Top resid features:
That
Token That
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
typing
Token typing
Feature activation-0.004
Top resid features:
mistake
Token mistake
Feature activation+0.010
Top resid features:
brought
Token brought
Feature activation+3.187
Top resid features:
about
Token about
Feature activation+0.695
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
lack
Token lack
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
sleep
Token sleep
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.020
Top resid features:
govern
Token govern
Feature activation+0.012
Top resid features:
by
Token by
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
script
Token script
Feature activation+0.020
Top resid features:
handed
Token handed
Feature activation+3.754
Top resid features:
them
Token them
Feature activation+0.111
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bidding
Token bidding
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
so
Token so
Feature activation+0.003
Top resid features:
they
Token they
Feature activation+0.006
Top resid features:
weren
Token weren
Feature activation+0.012
Top resid features:
't
Token't
Feature activation+0.038
Top resid features:
helped
Token helped
Feature activation+3.535
Top resid features:
or
Token or
Feature activation+0.046
Top resid features:
hurt
Token hurt
Feature activation+0.141
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
turnover
Token turnover
Feature activation+0.000
Top resid features:
margin
Token margin
Feature activation+0.000
Top resid features:
rally
Token rally
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
G
Token G
Feature activation-0.000
Top resid features:
rier
Tokenrier
Feature activation-0.000
Top resid features:
was
Token was
Feature activation+0.015
Top resid features:
replaced
Token replaced
Feature activation+3.546
Top resid features:
at
Token at
Feature activation+0.192
Top resid features:
first
Token first
Feature activation+0.051
Top resid features:
base
Token base
Feature activation+0.032
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Damon
Token Damon
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.008
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
1945
Token 1945
Feature activation+0.002
Top resid features:
-
Token -
Feature activation+0.014
Top resid features:
were
Token were
Feature activation+0.005
Top resid features:
inhabited
Token inhabited
Feature activation+3.543
Top resid features:
mostly
Token mostly
Feature activation+0.033
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
German
Token German
Feature activation+0.000
Top resid features:
speakers
Token speakers
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
was
Token was
Feature activation+0.015
Top resid features:
personally
Token personally
Feature activation+0.039
Top resid features:
hand
Token hand
Feature activation+0.014
Top resid features:
picked
Tokenpicked
Feature activation+2.839
Top resid features:
for
Token for
Feature activation+0.592
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
trade
Token trade
Feature activation+0.001
Top resid features:
minister
Token minister
Feature activation+0.003
Top resid features:
job
Token job
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.01

Head 2: 0.04

Head 3: 0.08

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.66

Head 11: 0.02

Positive logits

by5.68

by4.85

By4.29

By4.12

BY3.99

bys3.48

byter2.70

BY2.58

harshly2.29

via2.19

aback2.16

terness2.14

ribly2.02

ategory1.99

ById1.96

��1.86

裏�1.85

metic1.84

sacrific1.82

RIPT1.79

Negative logits

orescence-1.99

urai-1.96

interstitial-1.88

Poké-1.86

lore-1.86

Narr-1.85

\":-1.83

ouf-1.81

marine-1.80

SPONSORED-1.80

Certified-1.71

ilibrium-1.68

etermin-1.68

enance-1.67

EEP-1.64

────-1.64

Kinnikuman-1.60

acement-1.59

enos-1.58

sidx-1.57

INTERVAL 5.610 - 6.233
CONTAINS 0.000%

He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.951
in
Token in
Feature activation+1.781
this
Token this
Feature activation+3.643
quest
Token quest
Feature activation+6.233
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
Louise
Token Louise
Feature activation+0.000

INTERVAL 4.987 - 5.610
CONTAINS 0.000%

two
Token two
Feature activation+0.000
were
Token were
Feature activation+0.000
joined
Token joined
Feature activation+0.213
at
Token at
Feature activation+1.115
the
Token the
Feature activation+1.368
hip
Token hip
Feature activation+5.422
.
Token.
Feature activation+0.000
Bunny
Token Bunny
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
ret
Token ret
Feature activation+0.000
the
Token the
Feature activation+0.000
extinction
Token extinction
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
driven
Token driven
Feature activation+0.000
ultimately
Token ultimately
Feature activation+5.162
by
Token by
Feature activation+0.000
human
Token human
Feature activation+0.000
population
Token population
Feature activation+0.000
growth
Token growth
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 4.363 - 4.987
CONTAINS 0.000%

.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
joined
Token joined
Feature activation+0.000
in
Token in
Feature activation+0.802
Hawaii
Token Hawaii
Feature activation+4.378
by
Token by
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
Adrian
Token Adrian
Feature activation+0.000
Peterson
Token Peterson
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+3.969
only
Token only
Feature activation+4.409
by
Token by
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
changes
Token changes
Feature activation+0.000
the
Token the
Feature activation+1.622
sixth
Token sixth
Feature activation+0.904
week
Token week
Feature activation+4.076
of
Token of
Feature activation+0.607
the
Token the
Feature activation+0.316
split
Token split
Feature activation+4.691
âĢĶ
Token âĢĶ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
owner
Token owner
Feature activation+0.000

INTERVAL 3.740 - 4.363
CONTAINS 0.001%

may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
prompted
Token prompted
Feature activation+0.000
in
Token in
Feature activation+2.889
part
Token part
Feature activation+3.984
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
throb
Token throb
Feature activation+0.000
bing
Tokenbing
Feature activation+0.000
light
Token light
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
supported
Token supported
Feature activation+0.000
almost
Token almost
Feature activation+3.167
entirely
Token entirely
Feature activation+3.891
by
Token by
Feature activation+0.000
people
Token people
Feature activation+0.000
whose
Token whose
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
have
Token have
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
overshadowed
Token overshadowed
Feature activation+0.457
in
Token in
Feature activation+2.138
recent
Token recent
Feature activation+0.349
years
Token years
Feature activation+3.811
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
50
Token 50
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+3.969
only
Token only
Feature activation+4.409
by
Token by
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.341
in
Token in
Feature activation+1.986
the
Token the
Feature activation+1.622
sixth
Token sixth
Feature activation+0.904
week
Token week
Feature activation+4.076
of
Token of
Feature activation+0.607
the
Token the
Feature activation+0.316
split
Token split
Feature activation+4.691
âĢĶ
Token âĢĶ
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.117 - 3.740
CONTAINS 0.001%

rier
Tokenrier
Feature activation+0.000
was
Token was
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+2.318
base
Token base
Feature activation+3.365
by
Token by
Feature activation+0.000
Damon
Token Damon
Feature activation+0.000
H
Token H
Feature activation+0.000
ae
Tokenae
Feature activation+0.000
cker
Tokencker
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.951
in
Token in
Feature activation+1.781
this
Token this
Feature activation+3.643
quest
Token quest
Feature activation+6.233
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
typing
Token typing
Feature activation+0.000
mistake
Token mistake
Feature activation+0.000
brought
Token brought
Feature activation+0.000
about
Token about
Feature activation+3.527
by
Token by
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
.
Token.
Feature activation+0.000
govern
Token govern
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+0.000
handed
Token handed
Feature activation+0.000
them
Token them
Feature activation+3.511
,
Token,
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
bidding
Token bidding
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.114
t
Tokent
Feature activation+0.054
put
Token put
Feature activation+0.020
off
Token off
Feature activation+1.161
too
Token too
Feature activation+3.159
much
Token much
Feature activation+1.550
by
Token by
Feature activation+0.000
my
Token my
Feature activation+0.000
occasional
Token occasional
Feature activation+0.000
m
Token m
Feature activation+0.000

INTERVAL 2.493 - 3.117
CONTAINS 0.005%

then
Token then
Feature activation+0.056
swept
Token swept
Feature activation+1.202
in
Token in
Feature activation+1.708
the
Token the
Feature activation+0.279
Second
Token Second
Feature activation+0.449
Round
Token Round
Feature activation+2.954
by
Token by
Feature activation+0.000
eventual
Token eventual
Feature activation+0.000
Quarter
Token Quarter
Feature activation+0.000
final
Tokenfinal
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
yet
Token yet
Feature activation+0.000
pushed
Token pushed
Feature activation+0.000
upon
Token upon
Feature activation+1.386
the
Token the
Feature activation+0.826
working
Token working
Feature activation+0.573
classes
Token classes
Feature activation+2.635
who
Token who
Feature activation+0.000
simply
Token simply
Feature activation+0.179
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
as
Token as
Feature activation+0.408
Word
Token Word
Feature activation+0.225
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Year
Token Year
Feature activation+2.158
2013
Token 2013
Feature activation+2.516
âĢĵ
Token âĢĵ
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.187
the
Token the
Feature activation+0.000
challenges
Token challenges
Feature activation+0.000
facing
Token facing
Feature activation+0.000
patients
Token patients
Feature activation+0.000
are
Token are
Feature activation+0.000
compounded
Token compounded
Feature activation+0.585
dramatically
Token dramatically
Feature activation+2.574
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
New
Token New
Feature activation+0.000
other
Token other
Feature activation+0.000
intricate
Token intricate
Feature activation+0.000
rhythms
Token rhythms
Feature activation+0.000
manipulated
Token manipulated
Feature activation+1.283
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.093
by
Tokenby
Feature activation+0.000
per
Token per
Feature activation+0.000
c
Tokenc
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
ive
Tokenive
Feature activation+0.000

INTERVAL 1.870 - 2.493
CONTAINS 0.014%

made
Token made
Feature activation+0.000
slightly
Token slightly
Feature activation+0.935
easier
Token easier
Feature activation+0.898
down
Token down
Feature activation+1.903
the
Token the
Feature activation+0.000
line
Token line
Feature activation+2.156
when
Token when
Feature activation+0.000
extra
Token extra
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
are
Token are
Feature activation+0.000
unlocked
Token unlocked
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
to
Token to
Feature activation+0.000
games
Token games
Feature activation+2.229
through
Token through
Feature activation+0.000
fleeting
Token fleeting
Feature activation+0.000
encounters
Token encounters
Feature activation+0.000
with
Token with
Feature activation+0.000
arcade
Token arcade
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
quoted
Token quoted
Feature activation+0.094
as
Token as
Feature activation+0.034
saying
Token saying
Feature activation+2.019
by
Token by
Feature activation+0.000
The
Token The
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
vertis
Tokenvertis
Feature activation+0.000
er
Tokener
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
students
Token students
Feature activation+2.703
in
Token in
Feature activation+1.952
the
Token the
Feature activation+0.655
program
Token program
Feature activation+2.255
as
Token as
Feature activation+0.048
a
Token a
Feature activation+0.026
"
Token "
Feature activation+0.000
respected
Tokenrespected
Feature activation+0.000
public
Token public
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
impact
Token impact
Feature activation+0.000
of
Token of
Feature activation+0.000
WikiLeaks
Token WikiLeaks
Feature activation+0.000
revelations
Token revelations
Feature activation+0.000
)
Token)
Feature activation+1.950
was
Token was
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.212
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
damaging
Token damaging
Feature activation+0.000

INTERVAL 1.247 - 1.870
CONTAINS 0.047%

lected
Tokenlected
Feature activation+0.517
from
Token from
Feature activation+0.000
an
Token an
Feature activation+0.104
otherwise
Token otherwise
Feature activation+0.000
straight
Token straight
Feature activation+0.112
path
Token path
Feature activation+1.357
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
effect
Token effect
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
given
Token given
Feature activation+0.000
a
Token a
Feature activation+0.226
state
Token state
Feature activation+0.000
dinner
Token dinner
Feature activation+1.345
in
Token in
Feature activation+0.018
the
Token the
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+0.000
City
Token City
Feature activation+0.046
,
Token,
Feature activation+0.074
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
declared
Token declared
Feature activation+0.000
and
Token and
Feature activation+0.000
made
Token made
Feature activation+0.002
valid
Token valid
Feature activation+1.488
,
Token,
Feature activation+1.025
or
Token or
Feature activation+0.000
it
Token it
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
rated
Token rated
Feature activation+0.000
in
Token in
Feature activation+0.578
poor
Token poor
Feature activation+0.066
condition
Token condition
Feature activation+1.843
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
justify
Token justify
Feature activation+0.000
a
Token a
Feature activation+0.390
cloud
Token cloud
Feature activation+0.000
-
Token-
Feature activation+0.000
only
Tokenonly
Feature activation+0.000
model
Token model
Feature activation+1.284
by
Token by
Feature activation+0.000
trump
Token trump
Feature activation+0.000
ing
Tokening
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.623 - 1.247
CONTAINS 0.211%

Thursday
Token Thursday
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
postponed
Token postponed
Feature activation+0.656
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Morning
TokenMorning
Feature activation+0.000
Read
Token Read
Feature activation+0.000
Killed
Token Killed
Feature activation+0.157
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.421
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.952
.
Token.
Feature activation+0.893
Every
Token Every
Feature activation+0.000
28
Token 28
Feature activation+0.000
Hours
Token Hours
Feature activation+0.415
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
occupation
Token occupation
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
nation
Token nation
Feature activation+0.775
,
Token,
Feature activation+0.000
using
Token using
Feature activation+0.000
Key
Token Key
Feature activation+0.000
West
Token West
Feature activation+0.000
as
Token as
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
office
Token office
Feature activation+1.267
of
Token of
Feature activation+0.000
human
Token human
Feature activation+0.000
resources
Token resources
Feature activation+0.802
manager
Token manager
Feature activation+0.436
Raj
Token Raj
Feature activation+0.000
s
Tokens
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
De
Token De
Feature activation+0.000
multiplying
Token multiplying
Feature activation+0.000
10
Token 10
Feature activation+0.000
69
Token69
Feature activation+0.000
340
Token340
Feature activation+0.000
58
Token58
Feature activation+0.740
relations
Token relations
Feature activation+1.114
Tue
Token Tue
Feature activation+0.000
Sep
Token Sep
Feature activation+0.000
24
Token 24
Feature activation+0.000
11
Token 11
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.000 - 0.623
CONTAINS 99.721%

compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
1990
Token 1990
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
predicted
Token predicted
Feature activation+0.000
rats
Tokenrats
Feature activation+0.000
ch
Tokench
Feature activation+0.000
k
Tokenk
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
S
TokenS
Feature activation+0.000
oda
Tokenoda
Feature activation+0.000
fountain
Token fountain
Feature activation+0.000
?
Token?
Feature activation+0.000
and
Token and
Feature activation+0.000
ATF
Token ATF
Feature activation+0.000
policy
Token policy
Feature activation+0.000
attaching
Token attaching
Feature activation+0.000
a
Token a
Feature activation+0.000
stock
Token stock
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
pistol
Token pistol
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
or
Token or
Feature activation+0.000
could
Token could
Feature activation+0.000
suit
Token suit
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
needs
Token needs
Feature activation+0.000
in
Token in
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
Beast
Token Beast
Feature activation+0.128
)
Token)
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
in
Token in
Feature activation+0.000
William
Token William
Feature activation+0.000
Gibson
Token Gibson
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.710
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+0.710
by
Token by
Feature activation+0.000
headed
Token headed
Feature activation+0.710
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.710
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.710
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.710
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.710
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.710
by
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+0.710
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+0.710
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 3 in H9.10: (feature 4022)

TOP ACTIVATIONS
MAX = 4.364

He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.468
in
Token in
Feature activation+1.120
this
Token this
Feature activation+3.227
quest
Token quest
Feature activation+4.364
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
Louise
Token Louise
Feature activation+0.000
bor
Tokenbor
Feature activation+0.000
icultural
Tokenicultural
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
get
Token get
Feature activation+0.000
around
Token around
Feature activation+0.000
this
Token this
Feature activation+3.391
by
Token by
Feature activation+0.000
using
Token using
Feature activation+0.000
an
Token an
Feature activation+0.000
increment
Token increment
Feature activation+0.000
b
Token b
Feature activation+0.000
owners
Token owners
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
around
Token around
Feature activation+0.165
the
Token the
Feature activation+0.551
requirements
Token requirements
Feature activation+3.307
by
Token by
Feature activation+0.009
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
det
Token det
Feature activation+0.000
achable
Tokenachable
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.468
in
Token in
Feature activation+1.120
this
Token this
Feature activation+3.227
quest
Token quest
Feature activation+4.364
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
territory
Token territory
Feature activation+0.000
pred
Token pred
Feature activation+0.000
ates
Tokenates
Feature activation+0.136
the
Token the
Feature activation+0.257
Dancing
Token Dancing
Feature activation+0.299
Camel
Token Camel
Feature activation+3.098
by
Token by
Feature activation+0.387
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+0.000
,
Token,
Feature activation+0.000
brewing
Token brewing
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+2.724
only
Token only
Feature activation+3.049
by
Token by
Feature activation+0.001
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
changes
Token changes
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
He
Token He
Feature activation+0.000
backed
Token backed
Feature activation+0.000
up
Token up
Feature activation+0.000
those
Token those
Feature activation+0.620
words
Token words
Feature activation+2.958
with
Token with
Feature activation+0.195
a
Token a
Feature activation+0.000
counter
Token counter
Feature activation+0.000
-
Token-
Feature activation+0.000
stri
Tokenstri
Feature activation+0.000
the
Token the
Feature activation+0.000
extinction
Token extinction
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
driven
Token driven
Feature activation+0.000
ultimately
Token ultimately
Feature activation+2.951
by
Token by
Feature activation+0.000
human
Token human
Feature activation+0.000
population
Token population
Feature activation+0.000
growth
Token growth
Feature activation+0.113
and
Token and
Feature activation+0.000
National
Token National
Feature activation+0.000
Rape
Token Rape
Feature activation+0.000
Day
Token Day
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
it
Token it
Feature activation+2.731
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
deserving
Token deserving
Feature activation+0.000
federal
Token federal
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+2.724
only
Token only
Feature activation+3.049
by
Token by
Feature activation+0.001
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
and
Token and
Feature activation+0.410
my
Token my
Feature activation+0.000
new
Token new
Feature activation+0.000
beer
Token beer
Feature activation+0.468
b
Token b
Feature activation+0.000
ff
Tokenff
Feature activation+2.579
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.565
s
Tokens
Feature activation+2.495
with
Token with
Feature activation+0.041
pulling
Token pulling
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
Morris
Token Morris
Feature activation+0.000
made
Token made
Feature activation+0.000
history
Token history
Feature activation+0.071
in
Token in
Feature activation+1.751
1998
Token 1998
Feature activation+2.558
by
Token by
Feature activation+0.248
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
blind
Token blind
Feature activation+0.000
the
Token the
Feature activation+0.714
sixth
Token sixth
Feature activation+0.280
week
Token week
Feature activation+2.127
of
Token of
Feature activation+0.127
the
Token the
Feature activation+0.067
split
Token split
Feature activation+2.524
âĢĶ
Token âĢĶ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
owner
Token owner
Feature activation+0.000
made
Token made
Feature activation+0.000
slightly
Token slightly
Feature activation+0.616
easier
Token easier
Feature activation+0.724
down
Token down
Feature activation+2.198
the
Token the
Feature activation+0.288
line
Token line
Feature activation+2.507
when
Token when
Feature activation+0.000
extra
Token extra
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
are
Token are
Feature activation+0.000
unlocked
Token unlocked
Feature activation+0.000
beer
Token beer
Feature activation+0.468
b
Token b
Feature activation+0.000
ff
Tokenff
Feature activation+2.579
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.565
s
Tokens
Feature activation+2.495
with
Token with
Feature activation+0.041
pulling
Token pulling
Feature activation+0.000
some
Token some
Feature activation+0.000
ra
Token ra
Feature activation+0.000
res
Tokenres
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.281
next
Token next
Feature activation+0.550
year
Token year
Feature activation+2.450
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Perhaps
TokenPerhaps
Feature activation+0.000
unsurprisingly
Token unsurprisingly
Feature activation+0.000
systems
Token systems
Feature activation+0.000
of
Token of
Feature activation+0.000
violence
Token violence
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.387
them
Token them
Feature activation+2.444
with
Token with
Feature activation+0.000
equitable
Token equitable
Feature activation+0.000
and
Token and
Feature activation+0.000
just
Token just
Feature activation+0.000
communities
Token communities
Feature activation+0.000
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.000
store
Token store
Feature activation+0.000
impress
Token impress
Feature activation+0.000
es
Tokenes
Feature activation+0.585
you
Token you
Feature activation+2.389
with
Token with
Feature activation+0.073
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
first
Token first
Feature activation+0.000
bargain
Token bargain
Feature activation+0.000
to
Token to
Feature activation+0.169
revelations
Token revelations
Feature activation+1.339
concerning
Token concerning
Feature activation+0.000
the
Token the
Feature activation+0.229
torture
Token torture
Feature activation+0.431
cells
Token cells
Feature activation+2.367
by
Token by
Feature activation+0.005
pleading
Token pleading
Feature activation+0.000
ignorance
Token ignorance
Feature activation+0.000
and
Token and
Feature activation+0.000
declaring
Token declaring
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
supplement
Token supplement
Feature activation+0.000
ing
Tokening
Feature activation+0.000
its
Token its
Feature activation+0.020
lineup
Token lineup
Feature activation+2.341
as
Token as
Feature activation+1.161
it
Token it
Feature activation+0.380
does
Token does
Feature activation+0.419
every
Token every
Feature activation+0.270
year
Token year
Feature activation+0.403

Top DFA by src position
MAX = 3.849

figured
Tokenfigured
Feature activation+0.001
Top resid features:
face
Token face
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
He
Token He
Feature activation+0.010
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
aided
Token aided
Feature activation+3.849
Top resid features:
in
Token in
Feature activation+0.741
Top resid features:
this
Token this
Feature activation+0.201
Top resid features:
quest
Token quest
Feature activation+0.034
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
Ar
TokenAr
Feature activation+0.002
Top resid features:
bor
Tokenbor
Feature activation+0.001
Top resid features:
icultural
Tokenicultural
Feature activation+0.001
Top resid features:
ists
Tokenists
Feature activation+0.015
Top resid features:
get
Token get
Feature activation+0.035
Top resid features:
around
Token around
Feature activation+3.757
Top resid features:
this
Token this
Feature activation+0.100
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
using
Token using
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
increment
Token increment
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.006
Top resid features:
gun
Token gun
Feature activation+0.002
Top resid features:
owners
Token owners
Feature activation+0.002
Top resid features:
can
Token can
Feature activation+0.070
Top resid features:
get
Token get
Feature activation+0.056
Top resid features:
around
Token around
Feature activation+3.542
Top resid features:
the
Token the
Feature activation+0.061
Top resid features:
requirements
Token requirements
Feature activation+0.041
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
face
Token face
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
He
Token He
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
aided
Token aided
Feature activation+1.159
Top resid features:
in
Token in
Feature activation+2.372
Top resid features:
this
Token this
Feature activation+0.187
Top resid features:
quest
Token quest
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
loyal
Token loyal
Feature activation+0.000
Top resid features:
Brewing
Token Brewing
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.012
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.004
Top resid features:
territory
Token territory
Feature activation+0.004
Top resid features:
pred
Token pred
Feature activation+0.010
Top resid features:
ates
Tokenates
Feature activation+3.486
Top resid features:
the
Token the
Feature activation+0.082
Top resid features:
Dancing
Token Dancing
Feature activation+0.037
Top resid features:
Camel
Token Camel
Feature activation+0.005
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
evolution
Token evolution
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
these
Token these
Feature activation+0.008
Top resid features:
organisms
Token organisms
Feature activation+0.075
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
driven
Token driven
Feature activation+3.451
Top resid features:
not
Token not
Feature activation+0.008
Top resid features:
only
Token only
Feature activation+0.009
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
single
Token single
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ŀ
TokenĿ
Feature activation+0.016
Top resid features:
He
Token He
Feature activation+0.010
Top resid features:
backed
Token backed
Feature activation+0.104
Top resid features:
up
Token up
Feature activation+3.148
Top resid features:
those
Token those
Feature activation+0.080
Top resid features:
words
Token words
Feature activation+0.032
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
counter
Token counter
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
extinction
Token extinction
Feature activation+0.012
Top resid features:
crisis
Token crisis
Feature activation+0.005
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.003
Top resid features:
driven
Token driven
Feature activation+3.308
Top resid features:
ultimately
Token ultimately
Feature activation+0.087
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
human
Token human
Feature activation+0.000
Top resid features:
population
Token population
Feature activation+0.000
Top resid features:
growth
Token growth
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
National
Token National
Feature activation+0.005
Top resid features:
Rape
Token Rape
Feature activation-0.003
Top resid features:
Day
Token Day
Feature activation-0.010
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
replace
Token replace
Feature activation+3.181
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
deserving
Token deserving
Feature activation+0.000
Top resid features:
evolution
Token evolution
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
these
Token these
Feature activation+0.006
Top resid features:
organisms
Token organisms
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.020
Top resid features:
driven
Token driven
Feature activation+3.152
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
single
Token single
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
tour
Token tour
Feature activation+0.003
Top resid features:
Dr
Token Dr
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Bill
Token Bill
Feature activation+0.010
Top resid features:
dazz
Token dazz
Feature activation+0.034
Top resid features:
led
Tokenled
Feature activation+2.765
Top resid features:
me
Token me
Feature activation+0.189
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
my
Token my
Feature activation+0.028
Top resid features:
new
Token new
Feature activation+0.004
Top resid features:
beer
Token beer
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Senator
TokenSenator
Feature activation+0.043
Top resid features:
Morris
Token Morris
Feature activation-0.000
Top resid features:
made
Token made
Feature activation+0.021
Top resid features:
history
Token history
Feature activation+2.417
Top resid features:
in
Token in
Feature activation+0.427
Top resid features:
1998
Token 1998
Feature activation+0.121
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
becoming
Token becoming
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
onen
Tokenonen
Feature activation-0.005
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.012
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
would
Token would
Feature activation+0.007
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
replaced
Token replaced
Feature activation+3.009
Top resid features:
in
Token in
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
sixth
Token sixth
Feature activation-0.010
Top resid features:
week
Token week
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
only
Token only
Feature activation+0.007
Top resid features:
made
Token made
Feature activation+0.345
Top resid features:
slightly
Token slightly
Feature activation+0.139
Top resid features:
easier
Token easier
Feature activation+2.205
Top resid features:
down
Token down
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
line
Token line
Feature activation+0.080
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
extra
Token extra
Feature activation+0.000
Top resid features:
tour
Token tour
Feature activation+0.005
Top resid features:
Dr
Token Dr
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Bill
Token Bill
Feature activation+0.018
Top resid features:
dazz
Token dazz
Feature activation+0.095
Top resid features:
led
Tokenled
Feature activation+2.594
Top resid features:
me
Token me
Feature activation+0.152
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
my
Token my
Feature activation+0.033
Top resid features:
new
Token new
Feature activation-0.002
Top resid features:
beer
Token beer
Feature activation+0.028
Top resid features:
leadership
Token leadership
Feature activation-0.000
Top resid features:
vote
Token vote
Feature activation+0.015
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
will
Token will
Feature activation+0.007
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
replaced
Token replaced
Feature activation+2.930
Top resid features:
next
Token next
Feature activation+0.014
Top resid features:
year
Token year
Feature activation+0.034
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:
down
Token down
Feature activation+0.041
Top resid features:
systems
Token systems
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
violence
Token violence
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
replace
Token replace
Feature activation+2.705
Top resid features:
them
Token them
Feature activation+0.127
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
equitable
Token equitable
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
if
Token if
Feature activation+0.013
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
store
Token store
Feature activation+0.053
Top resid features:
impress
Token impress
Feature activation+0.879
Top resid features:
es
Tokenes
Feature activation+1.693
Top resid features:
you
Token you
Feature activation+0.130
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Romanian
Token Romanian
Feature activation+0.005
Top resid features:
parliament
Token parliament
Feature activation+0.003
Top resid features:
arians
Tokenarians
Feature activation+0.003
Top resid features:
responded
Token responded
Feature activation+0.765
Top resid features:
to
Token to
Feature activation+1.797
Top resid features:
revelations
Token revelations
Feature activation+0.215
Top resid features:
concerning
Token concerning
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
torture
Token torture
Feature activation+0.020
Top resid features:
cells
Token cells
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
LG
Token LG
Feature activation+0.038
Top resid features:
is
Token is
Feature activation+0.031
Top resid features:
now
Token now
Feature activation+0.025
Top resid features:
supplement
Token supplement
Feature activation+0.617
Top resid features:
ing
Tokening
Feature activation+1.664
Top resid features:
its
Token its
Feature activation+0.296
Top resid features:
lineup
Token lineup
Feature activation+0.087
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.04

Head 3: 0.08

Head 4: 0.02

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.01

Head 10: 0.64

Head 11: 0.02

Positive logits

by4.42

via3.75

by3.57

By3.55

By3.25

with3.24

BY3.14

using2.99

through2.92

with2.83

via2.82

WITH2.72

With2.62

thanks2.55

With2.41

Via2.36

withd2.26

Via2.26

indirectly2.21

courtesy2.21

Negative logits

cler-1.87

interstitial-1.84

};-1.76

SPONSORED-1.74

guiName-1.73

BuyableInstoreAndOnline-1.70

ITNESS-1.67

eded-1.66

arro-1.65

\":-1.59

Magikarp-1.58

shadow-1.58

utan-1.56

redacted-1.56

pired-1.56

Uncommon-1.55

pires-1.54

discrep-1.54

ldon-1.53

kered-1.53

INTERVAL 3.928 - 4.364
CONTAINS 0.000%

He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.468
in
Token in
Feature activation+1.120
this
Token this
Feature activation+3.227
quest
Token quest
Feature activation+4.364
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
Louise
Token Louise
Feature activation+0.000

INTERVAL 3.491 - 3.928
CONTAINS 0.000%

INTERVAL 3.055 - 3.491
CONTAINS 0.000%

owners
Token owners
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
around
Token around
Feature activation+0.165
the
Token the
Feature activation+0.551
requirements
Token requirements
Feature activation+3.307
by
Token by
Feature activation+0.009
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
det
Token det
Feature activation+0.000
achable
Tokenachable
Feature activation+0.000
bor
Tokenbor
Feature activation+0.000
icultural
Tokenicultural
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
get
Token get
Feature activation+0.000
around
Token around
Feature activation+0.000
this
Token this
Feature activation+3.391
by
Token by
Feature activation+0.000
using
Token using
Feature activation+0.000
an
Token an
Feature activation+0.000
increment
Token increment
Feature activation+0.000
b
Token b
Feature activation+0.000
territory
Token territory
Feature activation+0.000
pred
Token pred
Feature activation+0.000
ates
Tokenates
Feature activation+0.136
the
Token the
Feature activation+0.257
Dancing
Token Dancing
Feature activation+0.299
Camel
Token Camel
Feature activation+3.098
by
Token by
Feature activation+0.387
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+0.000
,
Token,
Feature activation+0.000
brewing
Token brewing
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
aided
Token aided
Feature activation+0.468
in
Token in
Feature activation+1.120
this
Token this
Feature activation+3.227
quest
Token quest
Feature activation+4.364
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000

INTERVAL 2.619 - 3.055
CONTAINS 0.001%

Ŀ
TokenĿ
Feature activation+0.000
He
Token He
Feature activation+0.000
backed
Token backed
Feature activation+0.000
up
Token up
Feature activation+0.000
those
Token those
Feature activation+0.620
words
Token words
Feature activation+2.958
with
Token with
Feature activation+0.195
a
Token a
Feature activation+0.000
counter
Token counter
Feature activation+0.000
-
Token-
Feature activation+0.000
stri
Tokenstri
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+2.724
only
Token only
Feature activation+3.049
by
Token by
Feature activation+0.001
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
these
Token these
Feature activation+0.000
organisms
Token organisms
Feature activation+0.000
is
Token is
Feature activation+0.000
driven
Token driven
Feature activation+0.000
not
Token not
Feature activation+2.724
only
Token only
Feature activation+3.049
by
Token by
Feature activation+0.001
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
letter
Tokenletter
Feature activation+0.000
changes
Token changes
Feature activation+0.000
the
Token the
Feature activation+0.000
extinction
Token extinction
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
driven
Token driven
Feature activation+0.000
ultimately
Token ultimately
Feature activation+2.951
by
Token by
Feature activation+0.000
human
Token human
Feature activation+0.000
population
Token population
Feature activation+0.000
growth
Token growth
Feature activation+0.113
and
Token and
Feature activation+0.000
National
Token National
Feature activation+0.000
Rape
Token Rape
Feature activation+0.000
Day
Token Day
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
it
Token it
Feature activation+2.731
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
deserving
Token deserving
Feature activation+0.000
federal
Token federal
Feature activation+0.000

INTERVAL 2.182 - 2.619
CONTAINS 0.002%

beer
Token beer
Feature activation+0.468
b
Token b
Feature activation+0.000
ff
Tokenff
Feature activation+2.579
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.565
s
Tokens
Feature activation+2.495
with
Token with
Feature activation+0.041
pulling
Token pulling
Feature activation+0.000
some
Token some
Feature activation+0.000
ra
Token ra
Feature activation+0.000
res
Tokenres
Feature activation+0.000
justify
Token justify
Feature activation+0.000
a
Token a
Feature activation+1.199
cloud
Token cloud
Feature activation+0.493
-
Token-
Feature activation+0.000
only
Tokenonly
Feature activation+0.630
model
Token model
Feature activation+2.302
by
Token by
Feature activation+0.042
trump
Token trump
Feature activation+0.000
ing
Tokening
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.273
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.000
store
Token store
Feature activation+0.000
impress
Token impress
Feature activation+0.000
es
Tokenes
Feature activation+0.585
you
Token you
Feature activation+2.389
with
Token with
Feature activation+0.073
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
first
Token first
Feature activation+0.000
bargain
Token bargain
Feature activation+0.000
and
Token and
Feature activation+0.410
my
Token my
Feature activation+0.000
new
Token new
Feature activation+0.000
beer
Token beer
Feature activation+0.468
b
Token b
Feature activation+0.000
ff
Tokenff
Feature activation+2.579
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.565
s
Tokens
Feature activation+2.495
with
Token with
Feature activation+0.041
pulling
Token pulling
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000
made
Token made
Feature activation+0.000
slightly
Token slightly
Feature activation+0.616
easier
Token easier
Feature activation+0.724
down
Token down
Feature activation+2.198
the
Token the
Feature activation+0.288
line
Token line
Feature activation+2.507
when
Token when
Feature activation+0.000
extra
Token extra
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000

INTERVAL 1.746 - 2.182
CONTAINS 0.004%

it
Token it
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
convince
Token convince
Feature activation+0.000
the
Token the
Feature activation+0.205
recipient
Token recipient
Feature activation+1.771
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
install
Token install
Feature activation+0.000
an
Token an
Feature activation+0.000
organization
Token organization
Feature activation+0.000
funded
Token funded
Feature activation+0.000
in
Token in
Feature activation+0.977
large
Token large
Feature activation+1.072
part
Token part
Feature activation+1.906
by
Token by
Feature activation+0.000
George
Token George
Feature activation+0.000
Soros
Token Soros
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
in
Token in
Feature activation+0.793
the
Token the
Feature activation+0.714
sixth
Token sixth
Feature activation+0.280
week
Token week
Feature activation+2.127
of
Token of
Feature activation+0.127
the
Token the
Feature activation+0.067
split
Token split
Feature activation+2.524
âĢĶ
Token âĢĶ
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
Morris
Token Morris
Feature activation+0.000
made
Token made
Feature activation+0.000
history
Token history
Feature activation+0.071
in
Token in
Feature activation+1.751
1998
Token 1998
Feature activation+2.558
by
Token by
Feature activation+0.248
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
support
Token support
Feature activation+0.000
us
Token us
Feature activation+1.227
too
Token too
Feature activation+1.815
by
Token by
Feature activation+0.000
signing
Token signing
Feature activation+0.000
our
Token our
Feature activation+0.000
petition
Token petition
Feature activation+0.000
demanding
Token demanding
Feature activation+0.000

INTERVAL 1.309 - 1.746
CONTAINS 0.010%

to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.000
over
Token over
Feature activation+0.120
its
Token its
Feature activation+0.000
musician
Token musician
Feature activation+0.473
critics
Token critics
Feature activation+1.453
by
Token by
Feature activation+0.087
launching
Token launching
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
Spotify
Token Spotify
Feature activation+0.000
previous
Token previous
Feature activation+0.000
government
Token government
Feature activation+0.000
in
Token in
Feature activation+0.000
being
Token being
Feature activation+0.000
led
Token led
Feature activation+0.000
around
Token around
Feature activation+1.336
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Greens
Token Greens
Feature activation+0.220
,''
Token,''
Feature activation+0.000
he
Token he
Feature activation+0.000
.
Token.
Feature activation+0.000
Mood
Token Mood
Feature activation+0.000
was
Token was
Feature activation+0.000
assessed
Token assessed
Feature activation+0.000
at
Token at
Feature activation+0.000
baseline
Token baseline
Feature activation+1.647
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
10
Token 10
Feature activation+0.000
-,
Token-,
Feature activation+0.000
35
Token 35
Feature activation+0.000
former
Token former
Feature activation+0.000
University
Token University
Feature activation+0.000
of
Token of
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
associate
Token associate
Feature activation+0.501
dean
Token dean
Feature activation+1.451
in
Token in
Feature activation+0.478
a
Token a
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
magazine
Token magazine
Feature activation+0.000
article
Token article
Feature activation+0.162
el
Tokenel
Feature activation+0.000
osi
Tokenosi
Feature activation+0.000
made
Token made
Feature activation+0.000
headlines
Token headlines
Feature activation+0.038
on
Token on
Feature activation+0.381
Tuesday
Token Tuesday
Feature activation+1.340
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
told
Token told
Feature activation+0.000
CNN
Token CNN
Feature activation+0.000
Gingrich
Token Gingrich
Feature activation+0.000

INTERVAL 0.873 - 1.309
CONTAINS 0.035%

al
Tokenal
Feature activation+0.000
noise
Token noise
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
show
Token show
Feature activation+0.274
,
Token,
Feature activation+1.293
by
Token by
Feature activation+0.000
comparative
Token comparative
Feature activation+0.000
transcript
Token transcript
Feature activation+0.000
omics
Tokenomics
Feature activation+0.000
of
Token of
Feature activation+0.000
media
Token media
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
hit
Token hit
Feature activation+0.000
Donald
Token Donald
Feature activation+0.141
Trump
Token Trump
Feature activation+1.221
with
Token with
Feature activation+0.092
a
Token a
Feature activation+0.000
fabricated
Token fabricated
Feature activation+0.000
hit
Token hit
Feature activation+0.000
piece
Token piece
Feature activation+0.000
kin
Tokenkin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
justifies
Token justifies
Feature activation+0.000
this
Token this
Feature activation+1.102
relationship
Token relationship
Feature activation+1.127
,
Token,
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
the
Token the
Feature activation+0.232
dozen
Token dozen
Feature activation+0.000
Range
Token Range
Feature activation+0.000
Rover
Token Rover
Feature activation+0.000
got
Token got
Feature activation+0.000
traction
Token traction
Feature activation+0.019
at
Token at
Feature activation+0.577
launch
Token launch
Feature activation+1.264
in
Token in
Feature activation+1.205
part
Token part
Feature activation+1.115
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
By
TokenBy
Feature activation+0.000
empowering
Token empowering
Feature activation+0.000
women
Token women
Feature activation+0.883
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
move
Token move
Feature activation+0.000

INTERVAL 0.436 - 0.873
CONTAINS 0.159%

in
Token in
Feature activation+0.000
1922
Token 1922
Feature activation+0.458
on
Token on
Feature activation+0.221
Bunker
Token Bunker
Feature activation+0.000
Hill
Token Hill
Feature activation+0.357
in
Token in
Feature activation+0.441
Downtown
Token Downtown
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.210
,
Token,
Feature activation+0.034
California
Token California
Feature activation+0.180
Python
Token Python
Feature activation+0.000
Tutorial
Token Tutorial
Feature activation+0.000
:
Token:
Feature activation+0.000
Sharing
Token Sharing
Feature activation+0.000
Django
Token Django
Feature activation+0.116
Sessions
Token Sessions
Feature activation+0.791
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
goal
Token goal
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.376
and
Tokenand
Feature activation+0.272
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.450
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
our
Token our
Feature activation+0.000
grandchildren
Token grandchildren
Feature activation+0.000
will
Token will
Feature activation+0.000
people
Token people
Feature activation+0.000
against
Token against
Feature activation+0.000
oppression
Token oppression
Feature activation+0.000
was
Token was
Feature activation+0.000
recognised
Token recognised
Feature activation+0.000
personally
Token personally
Feature activation+0.733
by
Token by
Feature activation+0.000
King
Token King
Feature activation+0.000
George
Token George
Feature activation+0.000
VI
Token VI
Feature activation+0.000
,
Token,
Feature activation+0.000
against
Token against
Feature activation+0.000
their
Token their
Feature activation+0.000
seat
Token seat
Feature activation+0.000
this
Token this
Feature activation+0.275
game
Token game
Feature activation+0.259
,
Token,
Feature activation+0.439
feeling
Token feeling
Feature activation+0.000
the
Token the
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.436
CONTAINS 99.790%

action
Token action
Feature activation+0.000
on
Token on
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
business
Token business
Feature activation+0.000
imperative
Token imperative
Feature activation+0.000
.
Token.
Feature activation+0.000
Failure
Token Failure
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Back
Token Back
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
hal
Token hal
Feature activation+0.000
cy
Tokency
Feature activation+0.000
on
Tokenon
Feature activation+0.000
days
Token days
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
opioid
Token opioid
Feature activation+0.000
in
Token in
Feature activation+0.000
Bangladesh
Token Bangladesh
Feature activation+0.000
sold
Token sold
Feature activation+0.000
everything
Token everything
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
and
Token and
Feature activation+0.000
gave
Token gave
Feature activation+0.000
him
Token him
Feature activation+0.000
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.000
minor
Token minor
Feature activation+0.041
,
Token,
Feature activation+0.000
child
Token child
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
and
Token and
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
minor
Token minor
Feature activation+0.000
.
Token.
Feature activation+0.000
for
Token for
Feature activation+0.000
peace
Token peace
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
Israeli
TokenIsraeli
Feature activation+0.000
women
Token women
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.072
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+0.072
by
Token by
Feature activation+0.000
headed
Token headed
Feature activation+0.072
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.072
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.072
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.072
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.072
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.072
by
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+0.072
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+0.072
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 4 in H9.10: (feature 3703)

TOP ACTIVATIONS
MAX = 2.764

sources
Token sources
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
derive
Token derive
Feature activation+0.000
their
Token their
Feature activation+0.000
theories
Token theories
Feature activation+2.764
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
so
Token so
Feature activation+0.000
-
Token-
Feature activation+0.000
called
Tokencalled
Feature activation+0.000
months
Token months
Feature activation+0.000
earlier
Token earlier
Feature activation+0.026
,
Token,
Feature activation+0.000
rescued
Token rescued
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+2.159
and
Token and
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
led
Token led
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
experts
Token experts
Feature activation+0.000
to
Token to
Feature activation+0.000
distinguish
Token distinguish
Feature activation+0.000
one
Token one
Feature activation+1.331
species
Token species
Feature activation+2.070
from
Token from
Feature activation+0.146
another
Token another
Feature activation+0.567
.
Token.
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
soft
Token soft
Feature activation+0.000
college
Token college
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
borrowed
Token borrowed
Feature activation+0.000
the
Token the
Feature activation+0.000
equipment
Token equipment
Feature activation+2.060
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
cafe
Token cafe
Feature activation+0.000
in
Token in
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
5
Token 5
Feature activation+0.000
by
Token by
Feature activation+0.000
Sand
Token Sand
Feature activation+0.000
ia
Tokenia
Feature activation+1.933
from
Token from
Feature activation+0.000
does
Token does
Feature activation+0.000
the
Token the
Feature activation+0.000
job
Token job
Feature activation+0.000
!
Token!
Feature activation+0.000
have
Token have
Feature activation+0.000
attempted
Token attempted
Feature activation+0.000
to
Token to
Feature activation+0.000
distinguish
Token distinguish
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.093
c
Tokenc
Feature activation+1.841
and
Token and
Feature activation+0.000
Skype
Token Skype
Feature activation+1.661
by
Token by
Feature activation+0.000
describing
Token describing
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
learned
Token learned
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+1.834
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.244
weekend
Token weekend
Feature activation+0.462
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
extracted
Token extracted
Feature activation+0.000
£
Token £
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
bn
Tokenbn
Feature activation+1.745
from
Token from
Feature activation+0.000
Priv
Token Priv
Feature activation+0.000
at
Tokenat
Feature activation+0.000
Bank
TokenBank
Feature activation+0.000
.
Token.
Feature activation+0.000
who
Token who
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
collect
Token collect
Feature activation+0.000
money
Token money
Feature activation+0.524
directly
Token directly
Feature activation+1.735
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
freaking
Token freaking
Feature activation+0.000
government
Token government
Feature activation+0.611
?
Token?
Feature activation+0.000
_
Token_
Feature activation+0.084
id
Tokenid
Feature activation+1.689
,
Token ,
Feature activation+0.172
name
Token name
Feature activation+1.706
,
Token ,
Feature activation+0.184
passage
Token passage
Feature activation+1.716
,
Token ,
Feature activation+0.793
t
Token t
Feature activation+0.008
sv
Tokensv
Feature activation+1.445
FROM
Token FROM
Feature activation+0.000
(
Token (
Feature activation+0.000
od
Tokenod
Feature activation+1.082
b
Tokenb
Feature activation+1.144
_
Token_
Feature activation+0.084
id
Tokenid
Feature activation+1.689
,
Token ,
Feature activation+0.172
name
Token name
Feature activation+1.706
,
Token ,
Feature activation+0.184
passage
Token passage
Feature activation+1.716
,
Token ,
Feature activation+0.793
t
Token t
Feature activation+0.008
sv
Tokensv
Feature activation+1.445
may
Token may
Feature activation+0.000
recognize
Token recognize
Feature activation+0.000
some
Token some
Feature activation+0.227
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.344
ideas
Token ideas
Feature activation+1.697
as
Token as
Feature activation+0.000
things
Token things
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
automate
Token automate
Feature activation+0.000
SELECT
TokenSELECT
Feature activation+0.000
cart
Token cart
Feature activation+0.678
od
Tokenod
Feature activation+1.082
b
Tokenb
Feature activation+1.144
_
Token_
Feature activation+0.084
id
Tokenid
Feature activation+1.689
,
Token ,
Feature activation+0.172
name
Token name
Feature activation+1.706
,
Token ,
Feature activation+0.184
passage
Token passage
Feature activation+1.716
,
Token ,
Feature activation+0.793
to
Token to
Feature activation+0.000
distinguish
Token distinguish
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.093
c
Tokenc
Feature activation+1.841
and
Token and
Feature activation+0.000
Skype
Token Skype
Feature activation+1.661
by
Token by
Feature activation+0.000
describing
Token describing
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.000
c
Tokenc
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
stole
Token stole
Feature activation+0.000
that
Token that
Feature activation+0.333
n
Token n
Feature activation+0.000
ug
Tokenug
Feature activation+0.000
get
Tokenget
Feature activation+1.624
from
Token from
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Sand
Token Sand
Feature activation+0.000
o
Tokeno
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
borrow
Token borrow
Feature activation+0.000
s
Tokens
Feature activation+0.000
heavily
Token heavily
Feature activation+1.621
from
Token from
Feature activation+0.000
Pixar
Token Pixar
Feature activation+0.000
and
Token and
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
he
Token he
Feature activation+0.000
learned
Token learned
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
allegations
Token allegations
Feature activation+1.610
Monday
Token Monday
Feature activation+0.366
,
Token,
Feature activation+0.230
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
od
Tokenod
Feature activation+0.377
b
Tokenb
Feature activation+1.429
_
Token_
Feature activation+0.201
id
Tokenid
Feature activation+1.575
,
Token ,
Feature activation+0.000
name
Token name
Feature activation+1.596
,
Token ,
Feature activation+0.433
passage
Token passage
Feature activation+1.586
,
Token ,
Feature activation+0.415
t
Token t
Feature activation+0.000
sv
Tokensv
Feature activation+1.546
we
Token we
Feature activation+0.000
gain
Token gain
Feature activation+0.007
more
Token more
Feature activation+1.115
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.139
aesthetic
Token aesthetic
Feature activation+1.587
pleasure
Token pleasure
Feature activation+1.283
--
Token --
Feature activation+0.287
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.427
physical
Token physical
Feature activation+0.000
_
Token_
Feature activation+0.201
id
Tokenid
Feature activation+1.575
,
Token ,
Feature activation+0.000
name
Token name
Feature activation+1.596
,
Token ,
Feature activation+0.433
passage
Token passage
Feature activation+1.586
,
Token ,
Feature activation+0.415
t
Token t
Feature activation+0.000
sv
Tokensv
Feature activation+1.546
FROM
Token FROM
Feature activation+0.000
tw
Token tw
Feature activation+0.000

Top DFA by src position
MAX = 2.438

in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
sources
Token sources
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
They
Token They
Feature activation+0.016
Top resid features:
derive
Token derive
Feature activation+2.331
Top resid features:
their
Token their
Feature activation+0.868
Top resid features:
theories
Token theories
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
Juventus
Token Juventus
Feature activation+0.003
Top resid features:
months
Token months
Feature activation+0.002
Top resid features:
earlier
Token earlier
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
rescued
Token rescued
Feature activation+2.263
Top resid features:
the
Token the
Feature activation+0.317
Top resid features:
team
Token team
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
nearly
Token nearly
Feature activation+0.000
Top resid features:
led
Token led
Feature activation+0.000
Top resid features:
detail
Token detail
Feature activation+0.003
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
allow
Token allow
Feature activation-0.000
Top resid features:
experts
Token experts
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
distinguish
Token distinguish
Feature activation+1.456
Top resid features:
one
Token one
Feature activation+1.029
Top resid features:
species
Token species
Feature activation+0.046
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.003
Top resid features:
journalism
Token journalism
Feature activation+0.001
Top resid features:
college
Token college
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
had
Token had
Feature activation-0.002
Top resid features:
borrowed
Token borrowed
Feature activation+1.818
Top resid features:
the
Token the
Feature activation+0.722
Top resid features:
equipment
Token equipment
Feature activation+0.009
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
cafe
Token cafe
Feature activation+0.000
Top resid features:
Rated
TokenRated
Feature activation-0.002
Top resid features:
4
Token 4
Feature activation+0.002
Top resid features:
out
Token out
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
5
Token 5
Feature activation+0.015
Top resid features:
by
Token by
Feature activation+2.438
Top resid features:
Sand
Token Sand
Feature activation-0.003
Top resid features:
ia
Tokenia
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Microsoft
TokenMicrosoft
Feature activation+0.002
Top resid features:
officials
Token officials
Feature activation+0.002
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
attempted
Token attempted
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
distinguish
Token distinguish
Feature activation+2.433
Top resid features:
Lyn
Token Lyn
Feature activation-0.010
Top resid features:
c
Tokenc
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Skype
Token Skype
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
He
TokenHe
Feature activation-0.002
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
he
Token he
Feature activation+0.004
Top resid features:
learned
Token learned
Feature activation+2.073
Top resid features:
about
Token about
Feature activation+0.288
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
video
Token video
Feature activation+0.001
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
two
Token two
Feature activation-0.005
Top resid features:
partners
Token partners
Feature activation-0.012
Top resid features:
had
Token had
Feature activation-0.013
Top resid features:
illicit
Token illicit
Feature activation+0.023
Top resid features:
ly
Tokenly
Feature activation+0.023
Top resid features:
extracted
Token extracted
Feature activation+1.933
Top resid features:
£
Token £
Feature activation+0.146
Top resid features:
4
Token4
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
2
Token2
Feature activation+0.010
Top resid features:
bn
Tokenbn
Feature activation+0.133
Top resid features:
camp
Token camp
Feature activation-0.001
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
don
Token don
Feature activation+0.002
Top resid features:
't
Token't
Feature activation-0.004
Top resid features:
collect
Token collect
Feature activation+0.302
Top resid features:
money
Token money
Feature activation+1.662
Top resid features:
directly
Token directly
Feature activation+0.143
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
freaking
Token freaking
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
river
Token river
Feature activation+0.003
Top resid features:
,
Token ,
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
SELECT
TokenSELECT
Feature activation+2.097
Top resid features:
cart
Token cart
Feature activation+0.005
Top resid features:
od
Tokenod
Feature activation-0.001
Top resid features:
b
Tokenb
Feature activation+0.006
Top resid features:
_
Token_
Feature activation+0.006
Top resid features:
id
Tokenid
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
river
Token river
Feature activation+0.003
Top resid features:
,
Token ,
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
SELECT
TokenSELECT
Feature activation+2.048
Top resid features:
cart
Token cart
Feature activation-0.000
Top resid features:
od
Tokenod
Feature activation-0.001
Top resid features:
b
Tokenb
Feature activation+0.006
Top resid features:
_
Token_
Feature activation+0.002
Top resid features:
id
Tokenid
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
you
Token you
Feature activation-0.007
Top resid features:
Android
Token Android
Feature activation+0.004
Top resid features:
fans
Token fans
Feature activation-0.004
Top resid features:
may
Token may
Feature activation-0.002
Top resid features:
recognize
Token recognize
Feature activation+2.034
Top resid features:
some
Token some
Feature activation+0.082
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
these
Token these
Feature activation+0.019
Top resid features:
ideas
Token ideas
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
river
Token river
Feature activation+0.002
Top resid features:
,
Token ,
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
SELECT
TokenSELECT
Feature activation+2.101
Top resid features:
cart
Token cart
Feature activation+0.020
Top resid features:
od
Tokenod
Feature activation-0.001
Top resid features:
b
Tokenb
Feature activation+0.012
Top resid features:
_
Token_
Feature activation+0.008
Top resid features:
id
Tokenid
Feature activation-0.000
Top resid features:
Microsoft
TokenMicrosoft
Feature activation-0.001
Top resid features:
officials
Token officials
Feature activation+0.001
Top resid features:
have
Token have
Feature activation-0.006
Top resid features:
attempted
Token attempted
Feature activation-0.023
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
distinguish
Token distinguish
Feature activation+2.120
Top resid features:
Lyn
Token Lyn
Feature activation-0.006
Top resid features:
c
Tokenc
Feature activation+0.053
Top resid features:
and
Token and
Feature activation-0.021
Top resid features:
Skype
Token Skype
Feature activation-0.006
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
league
Token league
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
I
Token I
Feature activation-0.018
Top resid features:
stole
Token stole
Feature activation+1.872
Top resid features:
that
Token that
Feature activation+0.247
Top resid features:
n
Token n
Feature activation-0.007
Top resid features:
ug
Tokenug
Feature activation-0.002
Top resid features:
get
Tokenget
Feature activation+0.009
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
fun
Token fun
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Yes
Token Yes
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
it
Token it
Feature activation+0.014
Top resid features:
borrow
Token borrow
Feature activation+1.448
Top resid features:
s
Tokens
Feature activation+0.545
Top resid features:
heavily
Token heavily
Feature activation+0.128
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Pixar
Token Pixar
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
ancy
Tokenancy
Feature activation-0.000
Top resid features:
has
Token has
Feature activation-0.010
Top resid features:
told
Token told
Feature activation-0.004
Top resid features:
lawmakers
Token lawmakers
Feature activation-0.000
Top resid features:
he
Token he
Feature activation-0.003
Top resid features:
learned
Token learned
Feature activation+2.038
Top resid features:
of
Token of
Feature activation+0.056
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
allegations
Token allegations
Feature activation-0.003
Top resid features:
Monday
Token Monday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token ,
Feature activation+0.002
Top resid features:
t
Token t
Feature activation-0.000
Top resid features:
sv
Tokensv
Feature activation+0.002
Top resid features:
FROM
Token FROM
Feature activation-0.015
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
SELECT
Token SELECT
Feature activation+2.055
Top resid features:
cart
Token cart
Feature activation+0.000
Top resid features:
od
Tokenod
Feature activation-0.000
Top resid features:
b
Tokenb
Feature activation+0.000
Top resid features:
_
Token_
Feature activation-0.001
Top resid features:
id
Tokenid
Feature activation+0.008
Top resid features:
we
Token we
Feature activation+0.001
Top resid features:
build
Token build
Feature activation+0.004
Top resid features:
?
Token?
Feature activation+0.004
Top resid features:
Do
Token Do
Feature activation-0.000
Top resid features:
we
Token we
Feature activation+0.006
Top resid features:
gain
Token gain
Feature activation+1.692
Top resid features:
more
Token more
Feature activation+0.227
Top resid features:
than
Token than
Feature activation+0.111
Top resid features:
just
Token just
Feature activation+0.123
Top resid features:
aesthetic
Token aesthetic
Feature activation+0.013
Top resid features:
pleasure
Token pleasure
Feature activation+0.000
Top resid features:
,
Token ,
Feature activation+0.003
Top resid features:
t
Token t
Feature activation-0.002
Top resid features:
sv
Tokensv
Feature activation+0.002
Top resid features:
FROM
Token FROM
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
SELECT
Token SELECT
Feature activation+2.040
Top resid features:
cart
Token cart
Feature activation-0.000
Top resid features:
od
Tokenod
Feature activation-0.000
Top resid features:
b
Tokenb
Feature activation+0.000
Top resid features:
_
Token_
Feature activation-0.000
Top resid features:
id
Tokenid
Feature activation+0.006
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.04

Head 3: 0.08

Head 4: 0.02

Head 5: 0.04

Head 6: 0.01

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.64

Head 11: 0.02

Positive logits

from4.61

FROM4.24

from3.94

From3.60

From3.58

hift2.36

needed2.15

through2.02

fro1.93

via1.93

owed1.92

courtesy1.92

SAY1.80

derived1.78

SET1.75

thanks1.74

1.74

glean1.72

onse1.70

ccording1.69

Negative logits

dstg-1.86

acha-1.78

icators-1.77

forth-1.70

mes-1.60

llah-1.59

Leilan-1.55

ilic-1.51

emo-1.48

etheus-1.47

iola-1.46

evaluate-1.44

icon-1.43

prosper-1.41

oppy-1.40

ondon-1.39

ongevity-1.39

uther-1.36

ney-1.36

Stead-1.35

INTERVAL 2.488 - 2.764
CONTAINS 0.000%

sources
Token sources
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
derive
Token derive
Feature activation+0.000
their
Token their
Feature activation+0.000
theories
Token theories
Feature activation+2.764
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
so
Token so
Feature activation+0.000
-
Token-
Feature activation+0.000
called
Tokencalled
Feature activation+0.000

INTERVAL 2.211 - 2.488
CONTAINS 0.000%

INTERVAL 1.935 - 2.211
CONTAINS 0.000%

months
Token months
Feature activation+0.000
earlier
Token earlier
Feature activation+0.026
,
Token,
Feature activation+0.000
rescued
Token rescued
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+2.159
and
Token and
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
led
Token led
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
college
Token college
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
borrowed
Token borrowed
Feature activation+0.000
the
Token the
Feature activation+0.000
equipment
Token equipment
Feature activation+2.060
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
cafe
Token cafe
Feature activation+0.000
in
Token in
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
allow
Token allow
Feature activation+0.000
experts
Token experts
Feature activation+0.000
to
Token to
Feature activation+0.000
distinguish
Token distinguish
Feature activation+0.000
one
Token one
Feature activation+1.331
species
Token species
Feature activation+2.070
from
Token from
Feature activation+0.146
another
Token another
Feature activation+0.567
.
Token.
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
soft
Token soft
Feature activation+0.000

INTERVAL 1.659 - 1.935
CONTAINS 0.001%

SELECT
TokenSELECT
Feature activation+0.000
cart
Token cart
Feature activation+0.678
od
Tokenod
Feature activation+1.082
b
Tokenb
Feature activation+1.144
_
Token_
Feature activation+0.084
id
Tokenid
Feature activation+1.689
,
Token ,
Feature activation+0.172
name
Token name
Feature activation+1.706
,
Token ,
Feature activation+0.184
passage
Token passage
Feature activation+1.716
,
Token ,
Feature activation+0.793
_
Token_
Feature activation+0.084
id
Tokenid
Feature activation+1.689
,
Token ,
Feature activation+0.172
name
Token name
Feature activation+1.706
,
Token ,
Feature activation+0.184
passage
Token passage
Feature activation+1.716
,
Token ,
Feature activation+0.793
t
Token t
Feature activation+0.008
sv
Tokensv
Feature activation+1.445
FROM
Token FROM
Feature activation+0.000
(
Token (
Feature activation+0.000
have
Token have
Feature activation+0.000
attempted
Token attempted
Feature activation+0.000
to
Token to
Feature activation+0.000
distinguish
Token distinguish
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.093
c
Tokenc
Feature activation+1.841
and
Token and
Feature activation+0.000
Skype
Token Skype
Feature activation+1.661
by
Token by
Feature activation+0.000
describing
Token describing
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.000
extracted
Token extracted
Feature activation+0.000
£
Token £
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
bn
Tokenbn
Feature activation+1.745
from
Token from
Feature activation+0.000
Priv
Token Priv
Feature activation+0.000
at
Tokenat
Feature activation+0.000
Bank
TokenBank
Feature activation+0.000
.
Token.
Feature activation+0.000
who
Token who
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
collect
Token collect
Feature activation+0.000
money
Token money
Feature activation+0.524
directly
Token directly
Feature activation+1.735
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
freaking
Token freaking
Feature activation+0.000
government
Token government
Feature activation+0.611
?
Token?
Feature activation+0.000

INTERVAL 1.382 - 1.659
CONTAINS 0.003%

we
Token we
Feature activation+0.000
gain
Token gain
Feature activation+0.007
more
Token more
Feature activation+1.115
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.139
aesthetic
Token aesthetic
Feature activation+1.587
pleasure
Token pleasure
Feature activation+1.283
--
Token --
Feature activation+0.287
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.427
physical
Token physical
Feature activation+0.000
They
Token They
Feature activation+0.000
get
Token get
Feature activation+0.000
their
Token their
Feature activation+0.000
j
Token j
Feature activation+0.000
oll
Tokenoll
Feature activation+0.000
ies
Tokenies
Feature activation+1.568
murdering
Token murdering
Feature activation+0.000
,
Token,
Feature activation+0.000
beating
Token beating
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
ret
Token ret
Feature activation+0.000
ook
Tokenook
Feature activation+0.000
the
Token the
Feature activation+0.000
western
Token western
Feature activation+0.000
city
Token city
Feature activation+1.472
of
Token of
Feature activation+0.000
Ram
Token Ram
Feature activation+0.000
adi
Tokenadi
Feature activation+1.474
,
Token,
Feature activation+0.357
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
almost
Token almost
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
to
Token to
Feature activation+0.000
separate
Token separate
Feature activation+0.000
Amy
Token Amy
Feature activation+1.553
Wine
Token Wine
Feature activation+0.000
house
Tokenhouse
Feature activation+0.749
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
creator
Token creator
Feature activation+0.000
er
Tokener
Feature activation+0.000
inherited
Token inherited
Feature activation+0.139
a
Token a
Feature activation+0.597
wealth
Token wealth
Feature activation+0.000
of
Token of
Feature activation+0.840
talent
Token talent
Feature activation+1.495
and
Token and
Feature activation+0.030
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.106 - 1.382
CONTAINS 0.007%

party
Token party
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
reclaim
Token reclaim
Feature activation+0.000
the
Token the
Feature activation+0.000
symbol
Token symbol
Feature activation+1.125
to
Token to
Feature activation+0.000
represent
Token represent
Feature activation+0.000
the
Token the
Feature activation+0.000
LGBTQ
Token LGBTQ
Feature activation+0.000
community
Token community
Feature activation+0.000
learned
Token learned
Feature activation+0.000
a
Token a
Feature activation+0.859
small
Token small
Feature activation+0.808
amount
Token amount
Feature activation+0.564
of
Token of
Feature activation+0.154
Latin
Token Latin
Feature activation+1.378
in
Token in
Feature activation+0.286
the
Token the
Feature activation+0.119
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
cost
Token cost
Feature activation+0.000
it
Token it
Feature activation+0.000
takes
Token takes
Feature activation+0.000
to
Token to
Feature activation+0.000
extract
Token extract
Feature activation+0.000
gold
Token gold
Feature activation+1.217
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
at
Token at
Feature activation+0.000
many
Token many
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
another
Token another
Feature activation+0.671
Gladiator
Token Gladiator
Feature activation+0.000
Beast
Token Beast
Feature activation+1.316
from
Token from
Feature activation+0.000
your
Token your
Feature activation+0.064
Graveyard
Token Graveyard
Feature activation+0.000
then
Token then
Feature activation+0.000
fuse
Token fuse
Feature activation+0.000
representative
Token representative
Feature activation+0.000
of
Token of
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.434
in
Token in
Feature activation+0.464
the
Token the
Feature activation+0.000
CIS
Token CIS
Feature activation+1.145
Executive
Token Executive
Feature activation+0.650
Committee
Token Committee
Feature activation+0.986
Anat
Token Anat
Feature activation+0.000
oly
Tokenoly
Feature activation+0.000
D
Token D
Feature activation+0.000

INTERVAL 0.829 - 1.106
CONTAINS 0.018%

-
Token-
Feature activation+0.000
T
TokenT
Feature activation+0.000
uner
Tokenuner
Feature activation+0.000
,
Token,
Feature activation+1.275
or
Token or
Feature activation+0.000
both
Token both
Feature activation+1.013
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
Syn
Token Syn
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
all
Token all
Feature activation+0.000
came
Token came
Feature activation+0.000
about
Token about
Feature activation+0.317
in
Token in
Feature activation+0.910
an
Token an
Feature activation+0.389
age
Token age
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
empt
Tokenempt
Feature activation+0.000
ing
Tokening
Feature activation+0.239
to
Token to
Feature activation+0.000
steal
Token steal
Feature activation+0.000
information
Token information
Feature activation+0.895
on
Token on
Feature activation+0.073
how
Token how
Feature activation+0.000
our
Token our
Feature activation+0.000
systems
Token systems
Feature activation+0.000
are
Token are
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
really
Token really
Feature activation+0.000
learn
Token learn
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+1.069
much
Token much
Feature activation+0.890
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
game
Token game
Feature activation+0.109
because
Token because
Feature activation+0.000
website
Token website
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
purchased
Token purchased
Feature activation+0.000
your
Token your
Feature activation+0.000
system
Token system
Feature activation+0.976
outside
Token outside
Feature activation+0.000
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.553 - 0.829
CONTAINS 0.051%

6
Token6
Feature activation+0.000
34
Token34
Feature activation+0.406
in
Token in
Feature activation+0.241
taxpayer
Token taxpayer
Feature activation+0.189
hand
Token hand
Feature activation+0.000
outs
Tokenouts
Feature activation+0.675
from
Token from
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
through
Token through
Feature activation+0.000
2011
Token 2011
Feature activation+0.375
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Nazis
Token Nazis
Feature activation+0.000
'
Token'
Feature activation+0.000
theft
Token theft
Feature activation+0.000
of
Token of
Feature activation+0.000
treasures
Token treasures
Feature activation+0.692
from
Token from
Feature activation+0.000
Jews
Token Jews
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.057
often
Token often
Feature activation+0.058
before
Token before
Feature activation+0.000
is
Token is
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000
"
Token "
Feature activation+0.228
verbal
Tokenverbal
Feature activation+0.057
reports
Token reports
Feature activation+0.081
"
Token"
Feature activation+0.563
of
Token of
Feature activation+0.000
higher
Token higher
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
radiation
Token radiation
Feature activation+0.000
fuels
Token fuels
Feature activation+0.000
.
Token.
Feature activation+0.000
POLITICO
Token POLITICO
Feature activation+0.000
obtained
Token obtained
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.707
Friday
Token Friday
Feature activation+0.505
,
Token,
Feature activation+0.381
after
Token after
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
es
Tokenes
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
dissu
Token dissu
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
you
Token you
Feature activation+0.731
from
Token from
Feature activation+0.000
marriage
Token marriage
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.276 - 0.553
CONTAINS 0.174%

had
Token had
Feature activation+0.000
originally
Token originally
Feature activation+0.000
acquired
Token acquired
Feature activation+0.000
a
Token a
Feature activation+0.224
data
Token data
Feature activation+0.000
set
Token set
Feature activation+0.546
of
Token of
Feature activation+0.000
17
Token 17
Feature activation+0.249
million
Token million
Feature activation+0.000
reader
Token reader
Feature activation+0.000
comments
Token comments
Feature activation+0.098
is
Token is
Feature activation+0.000
taken
Token taken
Feature activation+0.000
-
Token -
Feature activation+0.000
G
Token G
Feature activation+0.000
aining
Tokenaining
Feature activation+0.000
a
Token a
Feature activation+0.509
title
Token title
Feature activation+0.171
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
fabric
Token fabric
Feature activation+0.000
ating
Tokenating
Feature activation+0.119
in
Token in
Feature activation+0.000
principle
Token principle
Feature activation+0.000
to
Token to
Feature activation+0.000
obtain
Token obtain
Feature activation+0.000
the
Token the
Feature activation+0.100
information
Token information
Feature activation+0.334
sought
Token sought
Feature activation+0.313
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+0.000
ite
Tokenite
Feature activation+0.000
the
Token the
Feature activation+0.000
animals
Token animals
Feature activation+0.527
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
family
Token family
Feature activation+0.000
unit
Token unit
Feature activation+0.038
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
access
Token access
Feature activation+0.000
the
Token the
Feature activation+0.000
Prom
Token Prom
Feature activation+0.000
en
Tokenen
Feature activation+0.000
ade
Tokenade
Feature activation+0.464
from
Token from
Feature activation+0.000
Route
Token Route
Feature activation+0.000
208
Token 208
Feature activation+0.000
north
Token north
Feature activation+0.000
bound
Tokenbound
Feature activation+0.000

INTERVAL 0.000 - 0.276
CONTAINS 99.745%

per
Tokenper
Feature activation+0.000
l
Tokenl
Feature activation+0.000
,
Token ,
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
different
Token different
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Match
TokenMatch
Feature activation+0.000
fans
Token fans
Feature activation+0.080
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
flash
Token flash
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
grant
Token grant
Feature activation+0.000
you
Token you
Feature activation+0.000
the
Token the
Feature activation+0.000
buff
Token buff
Feature activation+0.000
for
Token for
Feature activation+0.000
5
Token 5
Feature activation+0.000
sec
Tokensec
Feature activation+0.000
per
Token per
Feature activation+0.000
soul
Token soul
Feature activation+0.000
consumed
Token consumed
Feature activation+0.000
.
Token.
Feature activation+0.000
bright
Token bright
Feature activation+0.000
green
Token green
Feature activation+0.000
NVIDIA
Token NVIDIA
Feature activation+0.000
logo
Token logo
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Advanced
TokenAdvanced
Feature activation+0.000
Micro
Token Micro
Feature activation+0.000
Devices
Token Devices
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
substitute
Token substitute
Feature activation+0.000
N
Token N
Feature activation+0.000
aby
Tokenaby
Feature activation+0.000
Ke
Token Ke
Feature activation+0.000
ita
Tokenita
Feature activation+0.397
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.049
s
Tokens
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 H9.10: (feature 5443)

TOP ACTIVATIONS
MAX = 4.234

they
Token they
Feature activation+0.000
caught
Token caught
Feature activation+0.000
fl
Token fl
Feature activation+0.000
ak
Tokenak
Feature activation+1.574
this
Token this
Feature activation+2.249
time
Token time
Feature activation+4.234
for
Token for
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
A
Token A
Feature activation+0.000
big
Token big
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
Frank
Token Frank
Feature activation+3.175
King
Token King
Feature activation+3.370
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
!
Token!
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
big
Token big
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
Frank
Token Frank
Feature activation+3.175
King
Token King
Feature activation+3.370
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
Lieberman
Token Lieberman
Feature activation+2.644
and
Token and
Feature activation+0.000
Riley
Token Riley
Feature activation+2.289
Nick
Token Nick
Feature activation+1.008
laus
Tokenlaus
Feature activation+2.884
Evans
Token Evans
Feature activation+3.125
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
O
Token O
Feature activation+0.000
cho
Tokencho
Feature activation+2.816
for
Token for
Feature activation+0.000
ing
Tokening
Feature activation+0.000
groups
Token groups
Feature activation+1.229
(
Token (
Feature activation+0.000
CC
TokenCC
Feature activation+0.000
G
TokenG
Feature activation+0.000
),
Token),
Feature activation+3.101
after
Token after
Feature activation+0.000
borough
Token borough
Feature activation+0.000
residents
Token residents
Feature activation+0.000
received
Token received
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
k
Token k
Feature activation+0.000
udos
Tokenudos
Feature activation+0.000
to
Token to
Feature activation+0.000
you
Token you
Feature activation+3.023
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.371
do
Token do
Feature activation+0.215
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
the
Token the
Feature activation+0.047
agency
Token agency
Feature activation+2.970
's
Token's
Feature activation+0.813
overall
Token overall
Feature activation+0.426
handling
Token handling
Feature activation+0.577
of
Token of
Feature activation+0.000
officer
Token officer
Feature activation+0.000
One
Token One
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
blame
Token blame
Feature activation+0.000
Barack
Token Barack
Feature activation+0.034
Obama
Token Obama
Feature activation+2.940
administration
Token administration
Feature activation+2.949
to
Token to
Feature activation+0.548
keep
Token keep
Feature activation+0.371
trying
Token trying
Feature activation+0.172
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
blame
Token blame
Feature activation+0.000
Barack
Token Barack
Feature activation+0.034
Obama
Token Obama
Feature activation+2.940
administration
Token administration
Feature activation+2.949
to
Token to
Feature activation+0.548
keep
Token keep
Feature activation+0.371
trying
Token trying
Feature activation+0.172
to
Token to
Feature activation+0.000
stars
Token stars
Feature activation+2.585
,
Token,
Feature activation+0.000
Luis
Token Luis
Feature activation+0.000
Gu
Token Gu
Feature activation+0.000
zman
Tokenzman
Feature activation+0.151
,
Token,
Feature activation+2.897
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.085
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
him
Token him
Feature activation+0.647
and
Token and
Feature activation+0.080
Stewart
Token Stewart
Feature activation+1.279
-
Token-
Feature activation+0.000
Ha
TokenHa
Feature activation+0.000
as
Tokenas
Feature activation+2.897
Racing
Token Racing
Feature activation+2.712
for
Token for
Feature activation+0.000
remembering
Token remembering
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Aaron
Token Aaron
Feature activation+2.874
Lieberman
Token Lieberman
Feature activation+2.644
and
Token and
Feature activation+0.000
Riley
Token Riley
Feature activation+2.289
Nick
Token Nick
Feature activation+1.008
laus
Tokenlaus
Feature activation+2.884
Evans
Token Evans
Feature activation+3.125
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
O
Token O
Feature activation+0.000
cho
Tokencho
Feature activation+2.816
(
Token (
Feature activation+0.000
huge
Tokenhuge
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
Aaron
Token Aaron
Feature activation+2.874
Lieberman
Token Lieberman
Feature activation+2.644
and
Token and
Feature activation+0.000
Riley
Token Riley
Feature activation+2.289
Nick
Token Nick
Feature activation+1.008
laus
Tokenlaus
Feature activation+2.884
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+0.000
Liberal
Token Liberal
Feature activation+0.135
government
Token government
Feature activation+2.870
,
Token,
Feature activation+0.103
Liberal
Token Liberal
Feature activation+0.000
MLA
Token MLA
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
Wilkinson
Token Wilkinson
Feature activation+0.084
within
Token within
Feature activation+0.190
liberal
Token liberal
Feature activation+0.000
pro
Token pro
Feature activation+0.000
-
Token-
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.036
circles
Token circles
Feature activation+2.869
for
Token for
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.044
big
Token big
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
John
Token John
Feature activation+1.696
Ko
Token Ko
Feature activation+0.006
oser
Tokenoser
Feature activation+2.853
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
suspended
Token suspended
Feature activation+0.000
in
Token in
Feature activation+0.232
May
Token May
Feature activation+2.744
2012
Token 2012
Feature activation+2.827
for
Token for
Feature activation+0.000
awarding
Token awarding
Feature activation+0.000
z
Token z
Feature activation+0.000
eros
Tokeneros
Feature activation+0.000
for
Token for
Feature activation+0.000
laus
Tokenlaus
Feature activation+2.884
Evans
Token Evans
Feature activation+3.125
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
O
Token O
Feature activation+0.000
cho
Tokencho
Feature activation+2.816
for
Token for
Feature activation+0.000
helping
Token helping
Feature activation+0.000
me
Token me
Feature activation+0.000
get
Token get
Feature activation+0.000
started
Token started
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
kid
Token kid
Feature activation+1.073
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
block
Token block
Feature activation+2.776
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.262
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
Jeff
Token Jeff
Feature activation+2.271
N
Token N
Feature activation+0.000
app
Tokenapp
Feature activation+0.813
i
Tokeni
Feature activation+2.775
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Its
TokenIts
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 4.698

economics
Token economics
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
they
Token they
Feature activation+0.029
Top resid features:
caught
Token caught
Feature activation+0.022
Top resid features:
fl
Token fl
Feature activation+0.030
Top resid features:
ak
Tokenak
Feature activation+4.698
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
time
Token time
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
continuing
Token continuing
Feature activation+0.000
Top resid features:
service
Token service
Feature activation+0.000
Top resid features:
up
Tokenup
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
A
Token A
Feature activation+0.003
Top resid features:
big
Token big
Feature activation+0.002
Top resid features:
thanks
Token thanks
Feature activation+0.136
Top resid features:
to
Token to
Feature activation+3.763
Top resid features:
Frank
Token Frank
Feature activation+0.021
Top resid features:
King
Token King
Feature activation+0.018
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
hearing
Token hearing
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
up
Tokenup
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
A
Token A
Feature activation+0.005
Top resid features:
big
Token big
Feature activation+0.003
Top resid features:
thanks
Token thanks
Feature activation+0.153
Top resid features:
to
Token to
Feature activation+3.615
Top resid features:
Frank
Token Frank
Feature activation+0.008
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
hearing
Token hearing
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
cho
Tokencho
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.034
Top resid features:
huge
Tokenhuge
Feature activation+0.001
Top resid features:
thanks
Token thanks
Feature activation+0.211
Top resid features:
go
Token go
Feature activation+0.048
Top resid features:
to
Token to
Feature activation+3.342
Top resid features:
Aaron
Token Aaron
Feature activation+0.013
Top resid features:
Lieberman
Token Lieberman
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.048
Top resid features:
Riley
Token Riley
Feature activation+0.003
Top resid features:
Nick
Token Nick
Feature activation-0.001
Top resid features:
r
Tokenr
Feature activation-0.003
Top resid features:
Cow
Token Cow
Feature activation-0.002
Top resid features:
an
Tokenan
Feature activation+0.002
Top resid features:
has
Token has
Feature activation+0.010
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
criticised
Token criticised
Feature activation+2.690
Top resid features:
by
Token by
Feature activation+0.768
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
chief
Token chief
Feature activation-0.000
Top resid features:
executive
Token executive
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
decade
Token decade
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
k
Token k
Feature activation+0.009
Top resid features:
udos
Tokenudos
Feature activation+2.674
Top resid features:
to
Token to
Feature activation+0.804
Top resid features:
you
Token you
Feature activation+0.055
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
sufficient
Token sufficient
Feature activation-0.002
Top resid features:
provocation
Token provocation
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
it
Token it
Feature activation+0.010
Top resid features:
criticized
Token criticized
Feature activation+3.260
Top resid features:
the
Token the
Feature activation+0.208
Top resid features:
agency
Token agency
Feature activation+0.020
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
overall
Token overall
Feature activation+0.000
Top resid features:
handling
Token handling
Feature activation+0.000
Top resid features:
China
Token China
Feature activation-0.001
Top resid features:
recently
Token recently
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
One
Token One
Feature activation+0.001
Top resid features:
cannot
Token cannot
Feature activation-0.000
Top resid features:
blame
Token blame
Feature activation+3.489
Top resid features:
Barack
Token Barack
Feature activation+0.007
Top resid features:
Obama
Token Obama
Feature activation+0.078
Top resid features:
administration
Token administration
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
keep
Token keep
Feature activation+0.000
Top resid features:
China
Token China
Feature activation-0.001
Top resid features:
recently
Token recently
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
One
Token One
Feature activation+0.006
Top resid features:
cannot
Token cannot
Feature activation+0.004
Top resid features:
blame
Token blame
Feature activation+3.486
Top resid features:
Barack
Token Barack
Feature activation+0.008
Top resid features:
Obama
Token Obama
Feature activation+0.041
Top resid features:
administration
Token administration
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
keep
Token keep
Feature activation+0.000
Top resid features:
interesting
Token interesting
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.003
Top resid features:
thank
Token thank
Feature activation+3.180
Top resid features:
one
Token one
Feature activation+0.059
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
film
Token film
Feature activation+0.006
Top resid features:
's
Token's
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
2
Token 2
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
thank
Token thank
Feature activation+2.985
Top resid features:
him
Token him
Feature activation+0.428
Top resid features:
and
Token and
Feature activation+0.061
Top resid features:
Stewart
Token Stewart
Feature activation+0.071
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
Ha
TokenHa
Feature activation-0.009
Top resid features:
cho
Tokencho
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.026
Top resid features:
huge
Tokenhuge
Feature activation+0.002
Top resid features:
thanks
Token thanks
Feature activation+0.323
Top resid features:
go
Token go
Feature activation+0.086
Top resid features:
to
Token to
Feature activation+2.888
Top resid features:
Aaron
Token Aaron
Feature activation+0.023
Top resid features:
Lieberman
Token Lieberman
Feature activation+0.053
Top resid features:
and
Token and
Feature activation+0.086
Top resid features:
Riley
Token Riley
Feature activation+0.009
Top resid features:
Nick
Token Nick
Feature activation-0.001
Top resid features:
cho
Tokencho
Feature activation-0.002
Top resid features:
(
Token (
Feature activation-0.006
Top resid features:
huge
Tokenhuge
Feature activation+0.005
Top resid features:
thanks
Token thanks
Feature activation+0.246
Top resid features:
go
Token go
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+3.212
Top resid features:
Aaron
Token Aaron
Feature activation-0.007
Top resid features:
Lieberman
Token Lieberman
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Riley
Token Riley
Feature activation+0.000
Top resid features:
Nick
Token Nick
Feature activation+0.000
Top resid features:
attorney
Token attorney
Feature activation+0.000
Top resid features:
general
Token general
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
quick
Token quick
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
blame
Token blame
Feature activation+3.338
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
previous
Token previous
Feature activation+0.012
Top resid features:
Liberal
Token Liberal
Feature activation+0.003
Top resid features:
government
Token government
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Democratic
Token Democratic
Feature activation+0.002
Top resid features:
Party
Token Party
Feature activation+0.004
Top resid features:
has
Token has
Feature activation+0.007
Top resid features:
been
Token been
Feature activation+0.029
Top resid features:
facing
Token facing
Feature activation+0.059
Top resid features:
criticism
Token criticism
Feature activation+3.145
Top resid features:
within
Token within
Feature activation+0.071
Top resid features:
liberal
Token liberal
Feature activation+0.016
Top resid features:
pro
Token pro
Feature activation+0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
Israel
TokenIsrael
Feature activation-0.008
Top resid features:
follower
Token follower
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
A
Token A
Feature activation+0.005
Top resid features:
big
Token big
Feature activation+0.003
Top resid features:
thanks
Token thanks
Feature activation+0.095
Top resid features:
to
Token to
Feature activation+3.316
Top resid features:
John
Token John
Feature activation+0.029
Top resid features:
Ko
Token Ko
Feature activation-0.027
Top resid features:
oser
Tokenoser
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
hearing
Token hearing
Feature activation+0.000
Top resid features:
ppard
Tokenppard
Feature activation+0.003
Top resid features:
High
Token High
Feature activation+0.004
Top resid features:
School
Token School
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
suspended
Token suspended
Feature activation+2.507
Top resid features:
in
Token in
Feature activation+0.740
Top resid features:
May
Token May
Feature activation+0.044
Top resid features:
2012
Token 2012
Feature activation+0.082
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
awarding
Token awarding
Feature activation+0.000
Top resid features:
cho
Tokencho
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.042
Top resid features:
huge
Tokenhuge
Feature activation+0.003
Top resid features:
thanks
Token thanks
Feature activation+0.498
Top resid features:
go
Token go
Feature activation+0.078
Top resid features:
to
Token to
Feature activation+1.904
Top resid features:
Aaron
Token Aaron
Feature activation+0.001
Top resid features:
Lieberman
Token Lieberman
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
Riley
Token Riley
Feature activation+0.001
Top resid features:
Nick
Token Nick
Feature activation-0.001
Top resid features:
spring
Token spring
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
you
Token you
Feature activation+0.002
Top resid features:
can
Token can
Feature activation-0.000
Top resid features:
thank
Token thank
Feature activation+3.025
Top resid features:
the
Token the
Feature activation+0.268
Top resid features:
new
Token new
Feature activation-0.038
Top resid features:
kid
Token kid
Feature activation+0.012
Top resid features:
on
Token on
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.001
Top resid features:
can
Token can
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Thanks
Token Thanks
Feature activation+0.065
Top resid features:
to
Token to
Feature activation+3.235
Top resid features:
Jeff
Token Jeff
Feature activation+0.061
Top resid features:
N
Token N
Feature activation-0.010
Top resid features:
app
Tokenapp
Feature activation+0.024
Top resid features:
i
Tokeni
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.01

Head 2: 0.05

Head 3: 0.07

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.64

Head 11: 0.02

Positive logits

for4.21

for3.71

FOR2.85

For2.54

For2.46

FOR2.15

because2.12

harshly2.03

1.90

arag1.82

accused1.81

eda1.78

mishand1.73

cussion1.68

guilty1.68

behalf1.67

aith1.64

negligent1.64

indefinitely1.64

retaliation1.63

Negative logits

ゼウス-2.22

isSpecialOrderable-2.19

Introduced-2.03

Untitled-2.00

Unsure-1.97

BuyableInstoreAndOnline-1.92

opian-1.91

-1.84

recess-1.83

vantage-1.82

-1.82

shenan-1.77

ERE-1.72

awa-1.71

Alive-1.71

inka-1.68

reon-1.68

-1.67

Reviewed-1.66

inois-1.65

INTERVAL 3.810 - 4.234
CONTAINS 0.000%

they
Token they
Feature activation+0.000
caught
Token caught
Feature activation+0.000
fl
Token fl
Feature activation+0.000
ak
Tokenak
Feature activation+1.574
this
Token this
Feature activation+2.249
time
Token time
Feature activation+4.234
for
Token for
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000

INTERVAL 3.387 - 3.810
CONTAINS 0.000%

INTERVAL 2.964 - 3.387
CONTAINS 0.001%

Lieberman
Token Lieberman
Feature activation+2.644
and
Token and
Feature activation+0.000
Riley
Token Riley
Feature activation+2.289
Nick
Token Nick
Feature activation+1.008
laus
Tokenlaus
Feature activation+2.884
Evans
Token Evans
Feature activation+3.125
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
O
Token O
Feature activation+0.000
cho
Tokencho
Feature activation+2.816
for
Token for
Feature activation+0.000
A
Token A
Feature activation+0.000
big
Token big
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
Frank
Token Frank
Feature activation+3.175
King
Token King
Feature activation+3.370
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
!
Token!
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
the
Token the
Feature activation+0.047
agency
Token agency
Feature activation+2.970
's
Token's
Feature activation+0.813
overall
Token overall
Feature activation+0.426
handling
Token handling
Feature activation+0.577
of
Token of
Feature activation+0.000
officer
Token officer
Feature activation+0.000
ing
Tokening
Feature activation+0.000
groups
Token groups
Feature activation+1.229
(
Token (
Feature activation+0.000
CC
TokenCC
Feature activation+0.000
G
TokenG
Feature activation+0.000
),
Token),
Feature activation+3.101
after
Token after
Feature activation+0.000
borough
Token borough
Feature activation+0.000
residents
Token residents
Feature activation+0.000
received
Token received
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
big
Token big
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
Frank
Token Frank
Feature activation+3.175
King
Token King
Feature activation+3.370
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000

INTERVAL 2.540 - 2.964
CONTAINS 0.002%

also
Token also
Feature activation+0.000
fault
Token fault
Feature activation+0.000
ed
Tokened
Feature activation+0.561
state
Token state
Feature activation+0.341
election
Token election
Feature activation+0.000
officials
Token officials
Feature activation+2.673
'
Token'
Feature activation+0.678
handling
Token handling
Feature activation+0.273
of
Token of
Feature activation+0.000
issues
Token issues
Feature activation+0.000
including
Token including
Feature activation+0.000
to
Token to
Feature activation+0.000
thank
Token thank
Feature activation+0.000
the
Token the
Feature activation+0.000
F
Token F
Feature activation+0.000
FR
TokenFR
Feature activation+2.202
F
TokenF
Feature activation+2.640
for
Token for
Feature activation+0.017
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.224
help
Token help
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+0.000
Liberal
Token Liberal
Feature activation+0.135
government
Token government
Feature activation+2.870
,
Token,
Feature activation+0.103
Liberal
Token Liberal
Feature activation+0.000
MLA
Token MLA
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
Wilkinson
Token Wilkinson
Feature activation+0.084
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
me
Token me
Feature activation+2.731
,
Token,
Feature activation+1.266
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+1.106
Why
TokenWhy
Feature activation+0.000
can
Token can
Feature activation+0.000
big
Token big
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
John
Token John
Feature activation+1.696
Ko
Token Ko
Feature activation+0.006
oser
Tokenoser
Feature activation+2.853
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.117 - 2.540
CONTAINS 0.004%

doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
blame
Token blame
Feature activation+0.000
herself
Token herself
Feature activation+2.453
for
Token for
Feature activation+0.317
it
Token it
Feature activation+0.295
.
Token.
Feature activation+0.000
Perhaps
Token Perhaps
Feature activation+0.000
my
Token my
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Thanks
TokenThanks
Feature activation+0.000
@
Token @
Feature activation+0.000
Rock
TokenRock
Feature activation+0.000
star
Tokenstar
Feature activation+0.466
Games
TokenGames
Feature activation+2.465
pic
Token pic
Feature activation+0.000
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
tip
Token tip
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hat
Token hat
Feature activation+0.000
to
Token to
Feature activation+0.000
Lori
Token Lori
Feature activation+2.139
Sn
Token Sn
Feature activation+0.000
ider
Tokenider
Feature activation+1.643
for
Token for
Feature activation+0.000
sending
Token sending
Feature activation+0.000
this
Token this
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
credit
Token credit
Feature activation+0.000
in
Token in
Feature activation+0.286
the
Token the
Feature activation+0.781
world
Token world
Feature activation+2.517
for
Token for
Feature activation+0.000
not
Token not
Feature activation+0.000
giving
Token giving
Feature activation+0.000
up
Token up
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
caught
Token caught
Feature activation+0.000
fl
Token fl
Feature activation+0.000
ak
Tokenak
Feature activation+1.574
this
Token this
Feature activation+2.249
time
Token time
Feature activation+4.234
for
Token for
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.693 - 2.117
CONTAINS 0.007%

the
Token the
Feature activation+0.000
trust
Token trust
Feature activation+2.256
which
Token which
Feature activation+0.029
runs
Token runs
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+1.742
,
Token,
Feature activation+1.667
and
Token and
Feature activation+1.345
the
Token the
Feature activation+0.021
chief
Token chief
Feature activation+0.000
officer
Token officer
Feature activation+0.538
but
Token but
Feature activation+0.000
was
Token was
Feature activation+0.000
criticised
Token criticised
Feature activation+0.970
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Speaker
Token Speaker
Feature activation+2.043
,
Token,
Feature activation+0.648
John
Token John
Feature activation+0.000
B
Token B
Feature activation+0.000
erc
Tokenerc
Feature activation+0.000
ow
Tokenow
Feature activation+0.384
.
Token.
Feature activation+0.000
F
Token F
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
that
Token that
Feature activation+0.000
blames
Token blames
Feature activation+0.000
capitalism
Token capitalism
Feature activation+2.083
for
Token for
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.312
?
Token?
Feature activation+0.943
The
Token The
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.879
quite
Token quite
Feature activation+1.792
often
Token often
Feature activation+1.665
recently
Token recently
Feature activation+1.480
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
served
Token served
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
thank
Token thank
Feature activation+0.000
the
Token the
Feature activation+0.000
big
Token big
Feature activation+0.110
guy
Token guy
Feature activation+2.068
in
Token in
Feature activation+1.240
the
Token the
Feature activation+0.330
sky
Token sky
Feature activation+2.177
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.516

INTERVAL 1.270 - 1.693
CONTAINS 0.014%

sentenced
Token sentenced
Feature activation+0.175
to
Token to
Feature activation+0.000
seven
Token seven
Feature activation+0.000
months
Token months
Feature activation+0.565
in
Token in
Feature activation+0.389
prison
Token prison
Feature activation+1.537
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
had
Token had
Feature activation+0.199
ticket
Token ticket
Feature activation+0.000
ed
Tokened
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+1.348
member
Token member
Feature activation+1.420
for
Token for
Feature activation+0.000
drunk
Token drunk
Feature activation+0.000
driving
Token driving
Feature activation+0.272
,
Token,
Feature activation+0.256
authorities
Token authorities
Feature activation+0.000
old
Tokenold
Feature activation+0.000
man
Token man
Feature activation+0.000
was
Token was
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
on
Token on
Feature activation+0.026
Wednesday
Token Wednesday
Feature activation+1.357
and
Token and
Feature activation+0.000
remains
Token remains
Feature activation+0.000
in
Token in
Feature activation+0.000
custody
Token custody
Feature activation+0.000
.
Token.
Feature activation+0.000
counts
Token counts
Feature activation+0.000
of
Token of
Feature activation+0.000
def
Token def
Feature activation+0.000
am
Tokenam
Feature activation+0.000
atory
Tokenatory
Feature activation+0.000
libel
Token libel
Feature activation+1.349
by
Token by
Feature activation+0.000
officers
Token officers
Feature activation+0.252
in
Token in
Feature activation+0.346
the
Token the
Feature activation+0.130
O
Token O
Feature activation+0.000
1999
Token 1999
Feature activation+0.000
,
Token,
Feature activation+0.000
AOL
Token AOL
Feature activation+0.000
bought
Token bought
Feature activation+0.000
Null
Token Null
Feature activation+0.000
soft
Tokensoft
Feature activation+1.320
and
Token and
Feature activation+0.000
everything
Token everything
Feature activation+0.000
changed
Token changed
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000

INTERVAL 0.847 - 1.270
CONTAINS 0.039%

they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
charging
Token charging
Feature activation+0.000
F
Token F
Feature activation+0.000
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+1.060
with
Token with
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
using
Token using
Feature activation+0.000
a
Token a
Feature activation+0.000
section
Token section
Feature activation+0.000
author
Token author
Feature activation+0.000
of
Token of
Feature activation+0.000
Order
Token Order
Feature activation+0.000
Out
Token Out
Feature activation+0.000
Of
Token Of
Feature activation+0.000
Chaos
Token Chaos
Feature activation+0.879
.
Token.
Feature activation+0.006
Watson
Token Watson
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
able
Tokenable
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
blamed
Token blamed
Feature activation+0.000
the
Token the
Feature activation+0.000
protestors
Token protestors
Feature activation+1.228
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
out
Tokenout
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
State
Token State
Feature activation+0.000
Athletic
Token Athletic
Feature activation+0.000
Commission
Token Commission
Feature activation+1.299
on
Token on
Feature activation+1.125
Monday
Token Monday
Feature activation+1.308
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Daniel
TokenDaniel
Feature activation+0.000
Iris
Token Iris
Feature activation+0.000
Guard
TokenGuard
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
selected
Token selected
Feature activation+0.000
technology
Token technology
Feature activation+0.948
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000

INTERVAL 0.423 - 0.847
CONTAINS 0.123%

been
Token been
Feature activation+0.000
previously
Token previously
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.108
felony
Token felony
Feature activation+0.457
burglary
Token burglary
Feature activation+0.450
charge
Token charge
Feature activation+0.399
.
Token.
Feature activation+0.000
Alt
Token Alt
Feature activation+0.000
am
Tokenam
Feature activation+0.000
to
Token to
Feature activation+0.000
five
Token five
Feature activation+0.000
years
Token years
Feature activation+0.000
behind
Token behind
Feature activation+0.000
bars
Token bars
Feature activation+0.724
,
Token,
Feature activation+0.817
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
information
Token information
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
to
Token to
Feature activation+0.000
shoot
Token shoot
Feature activation+0.000
me
Token me
Feature activation+0.000
in
Token in
Feature activation+0.255
the
Token the
Feature activation+0.000
eyes
Token eyes
Feature activation+0.690
to
Token to
Feature activation+0.785
achieve
Token achieve
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
slew
Token slew
Feature activation+0.000
of
Token of
Feature activation+0.000
subpoen
Token subpoen
Feature activation+0.000
as
Tokenas
Feature activation+0.163
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.550
,
Token,
Feature activation+0.054
a
Token a
Feature activation+0.000
sign
Token sign
Feature activation+0.000
their
Token their
Feature activation+0.000
investigations
Token investigations
Feature activation+0.000
prepares
Token prepares
Feature activation+0.000
a
Token a
Feature activation+0.000
collection
Token collection
Feature activation+0.773
of
Token of
Feature activation+0.005
stories
Token stories
Feature activation+1.222
,
Token,
Feature activation+0.436
written
Token written
Feature activation+0.000
by
Token by
Feature activation+0.000
teens
Token teens
Feature activation+0.000
,
Token,
Feature activation+0.782
about
Token about
Feature activation+0.000

INTERVAL 0.000 - 0.423
CONTAINS 99.810%

a
Tokena
Feature activation+0.000
Har
Token Har
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
Chandra
Token Chandra
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
home
Token home
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
weather
Token weather
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
each
Token each
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000
began
Token began
Feature activation+0.000
to
Token to
Feature activation+0.000
feel
Token feel
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
barely
Token barely
Feature activation+0.000
knew
Token knew
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
that
Token that
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
because
Token because
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
hard
Token hard
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 6 in H9.10: (feature 8127)

TOP ACTIVATIONS
MAX = 3.438

strictly
Token strictly
Feature activation+0.000
between
Token between
Feature activation+0.234
â
Token â
Feature activation+1.330
Ħ
TokenĦ
Feature activation+0.242
µ
Tokenµ
Feature activation+2.761
0
Token 0
Feature activation+3.438
{\
Token {\
Feature activation+0.000
display
Tokendisplay
Feature activation+0.000
style
Tokenstyle
Feature activation+0.154
\
Token \
Feature activation+0.273
al
Tokenal
Feature activation+0.000
but
Token but
Feature activation+0.000
serve
Token serve
Feature activation+0.000
between
Token between
Feature activation+0.000
10
Token 10
Feature activation+2.877
,
Token,
Feature activation+0.275
000
Token000
Feature activation+2.952
and
Token and
Feature activation+0.000
17
Token 17
Feature activation+0.046
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
riders
Token riders
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
threads
Token threads
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
alive
Token alive
Feature activation+2.916
and
Token and
Feature activation+0.000
dead
Token dead
Feature activation+0.245
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+0.001
enumer
Token enumer
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
between
Token between
Feature activation+0.000
14
Token 14
Feature activation+2.896
years
Token years
Feature activation+2.477
and
Token and
Feature activation+0.202
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
400
Token400
Feature activation+0.000
m
Tokenm
Feature activation+0.000
but
Token but
Feature activation+0.000
serve
Token serve
Feature activation+0.000
between
Token between
Feature activation+0.000
10
Token 10
Feature activation+2.877
,
Token,
Feature activation+0.275
000
Token000
Feature activation+2.952
and
Token and
Feature activation+0.000
17
Token 17
Feature activation+0.046
,
Token,
Feature activation+0.000
study
Token study
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+1.492
theory
Token theory
Feature activation+2.839
and
Token and
Feature activation+0.000
right
Token right
Feature activation+0.000
wing
Token wing
Feature activation+0.000
violence
Token violence
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
book
Token book
Feature activation+0.000
is
Token is
Feature activation+0.000
between
Token between
Feature activation+0.000
50
Token 50
Feature activation+2.835
and
Token and
Feature activation+0.208
150
Token 150
Feature activation+0.000
pages
Token pages
Feature activation+0.000
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
has
Token has
Feature activation+0.000
spr
Token spr
Feature activation+0.000
outed
Tokenouted
Feature activation+0.000
between
Token between
Feature activation+0.000
20
Token 20
Feature activation+2.796
and
Token and
Feature activation+0.083
30
Token 30
Feature activation+0.115
micro
Token micro
Feature activation+0.000
brew
Tokenbrew
Feature activation+0.000
eries
Tokeneries
Feature activation+0.000
committee
Token committee
Feature activation+0.000
people
Tokenpeople
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
generally
Token generally
Feature activation+0.000
between
Token between
Feature activation+0.000
20
Token 20
Feature activation+2.784
and
Token and
Feature activation+0.000
100
Token 100
Feature activation+0.000
per
Token per
Feature activation+0.000
ward
Token ward
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
al
Tokenal
Feature activation+0.000
eph
Tokeneph
Feature activation+0.102
_
Token _
Feature activation+0.000
{
Token{
Feature activation+0.000
0
Token0
Feature activation+0.000
}}
Token}}
Feature activation+2.769
and
Token and
Feature activation+0.000
c
Token c
Feature activation+0.251
{\
Token {\
Feature activation+0.000
display
Tokendisplay
Feature activation+0.000
style
Tokenstyle
Feature activation+0.000
is
Token is
Feature activation+0.000
strictly
Token strictly
Feature activation+0.000
between
Token between
Feature activation+0.234
â
Token â
Feature activation+1.330
Ħ
TokenĦ
Feature activation+0.242
µ
Tokenµ
Feature activation+2.761
0
Token 0
Feature activation+3.438
{\
Token {\
Feature activation+0.000
display
Tokendisplay
Feature activation+0.000
style
Tokenstyle
Feature activation+0.154
\
Token \
Feature activation+0.273
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
received
Token received
Feature activation+0.000
between
Token between
Feature activation+0.000
zero
Token zero
Feature activation+2.758
and
Token and
Feature activation+0.000
249
Token 249
Feature activation+0.000
national
Token national
Feature activation+0.000
security
Token security
Feature activation+0.000
requests
Token requests
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
ber
Tokenber
Feature activation+0.000
ian
Tokenian
Feature activation+0.826
Peninsula
Token Peninsula
Feature activation+2.720
and
Token and
Feature activation+0.000
huge
Token huge
Feature activation+0.000
swath
Token swath
Feature activation+0.000
of
Token of
Feature activation+0.000
lands
Token lands
Feature activation+0.000
s
Tokens
Feature activation+0.000
weighing
Token weighing
Feature activation+0.000
between
Token between
Feature activation+0.000
2
Token 2
Feature activation+2.411
metric
Token metric
Feature activation+0.362
tons
Token tons
Feature activation+2.717
and
Token and
Feature activation+0.029
24
Token 24
Feature activation+0.505
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.696
metric
Token metric
Feature activation+0.000
is
Token is
Feature activation+0.000
worth
Token worth
Feature activation+0.000
between
Token between
Feature activation+0.000
$
Token $
Feature activation+0.044
25
Token25
Feature activation+1.845
million
Token million
Feature activation+2.716
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
million
Token million
Feature activation+0.000
;
Token;
Feature activation+0.000
close
Token close
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
colon
Token colon
Feature activation+0.098
ials
Tokenials
Feature activation+2.699
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
neighboring
Token neighboring
Feature activation+0.000
Wang
Token Wang
Feature activation+0.000
unk
Tokenunk
Feature activation+0.000
peace
Token peace
Feature activation+0.000
-
Token-
Feature activation+0.000
maker
Tokenmaker
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
Israelis
Token Israelis
Feature activation+2.586
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
W
Token W
Feature activation+0.000
ight
Tokenight
Feature activation+0.594
,
Token,
Feature activation+0.363
yet
Token yet
Feature activation+0.000
between
Token between
Feature activation+0.000
1940
Token 1940
Feature activation+2.566
and
Token and
Feature activation+0.024
1942
Token 1942
Feature activation+0.000
more
Token more
Feature activation+0.000
bombs
Token bombs
Feature activation+0.000
fell
Token fell
Feature activation+0.000
Int
TokenInt
Feature activation+0.000
ellectual
Tokenellectual
Feature activation+0.000
contacts
Token contacts
Feature activation+0.000
between
Token between
Feature activation+0.000
prolet
Token prolet
Feature activation+0.000
arians
Tokenarians
Feature activation+2.537
of
Token of
Feature activation+0.000
various
Token various
Feature activation+0.000
countries
Token countries
Feature activation+1.294
in
Token in
Feature activation+0.159
reality
Token reality
Feature activation+0.328
the
Token the
Feature activation+0.000
30
Token 30
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
playing
Token playing
Feature activation+0.000
between
Token between
Feature activation+0.000
87
Token 87
Feature activation+2.521
(
Token (
Feature activation+0.907
Baltimore
TokenBaltimore
Feature activation+0.089
,
Token,
Feature activation+0.000
Boston
Token Boston
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 3.572

whose
Token whose
Feature activation+0.003
Top resid features:
cardinal
Token cardinal
Feature activation+0.012
Top resid features:
ity
Tokenity
Feature activation+0.014
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
strictly
Token strictly
Feature activation+0.010
Top resid features:
between
Token between
Feature activation+3.572
Top resid features:
â
Token â
Feature activation+0.040
Top resid features:
Ħ
TokenĦ
Feature activation+0.039
Top resid features:
µ
Tokenµ
Feature activation+0.073
Top resid features:
0
Token 0
Feature activation+0.061
Top resid features:
{\
Token {\
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.050
Top resid features:
400
Token400
Feature activation-0.001
Top resid features:
m
Tokenm
Feature activation-0.009
Top resid features:
but
Token but
Feature activation-0.001
Top resid features:
serve
Token serve
Feature activation-0.004
Top resid features:
between
Token between
Feature activation+3.225
Top resid features:
10
Token 10
Feature activation+0.176
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
000
Token000
Feature activation+0.033
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
17
Token 17
Feature activation+0.000
Top resid features:
number
Token number
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
all
Token all
Feature activation+0.006
Top resid features:
threads
Token threads
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
both
Token both
Feature activation+3.146
Top resid features:
alive
Token alive
Feature activation+0.037
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
whereas
Token whereas
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.003
Top resid features:
is
Token is
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
sentence
Token sentence
Feature activation+0.018
Top resid features:
anywhere
Token anywhere
Feature activation+0.011
Top resid features:
between
Token between
Feature activation+3.360
Top resid features:
14
Token 14
Feature activation+0.027
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.048
Top resid features:
400
Token400
Feature activation+0.001
Top resid features:
m
Tokenm
Feature activation-0.023
Top resid features:
but
Token but
Feature activation+0.001
Top resid features:
serve
Token serve
Feature activation-0.004
Top resid features:
between
Token between
Feature activation+3.313
Top resid features:
10
Token 10
Feature activation+0.079
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
000
Token000
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
17
Token 17
Feature activation+0.000
Top resid features:
Experts
TokenExperts
Feature activation-0.003
Top resid features:
who
Token who
Feature activation-0.004
Top resid features:
study
Token study
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
relationship
Token relationship
Feature activation+0.021
Top resid features:
between
Token between
Feature activation+3.271
Top resid features:
conspiracy
Token conspiracy
Feature activation+0.013
Top resid features:
theory
Token theory
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
wing
Token wing
Feature activation+0.000
Top resid features:
Congo
Token Congo
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Each
Token Each
Feature activation+0.004
Top resid features:
book
Token book
Feature activation-0.067
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
between
Token between
Feature activation+3.435
Top resid features:
50
Token 50
Feature activation+0.072
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
150
Token 150
Feature activation+0.000
Top resid features:
pages
Token pages
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Israel
Token Israel
Feature activation+0.035
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
spr
Token spr
Feature activation-0.000
Top resid features:
outed
Tokenouted
Feature activation+0.007
Top resid features:
between
Token between
Feature activation+3.255
Top resid features:
20
Token 20
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
micro
Token micro
Feature activation+0.000
Top resid features:
brew
Tokenbrew
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
committee
Token committee
Feature activation-0.002
Top resid features:
people
Tokenpeople
Feature activation+0.008
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.007
Top resid features:
generally
Token generally
Feature activation+0.003
Top resid features:
between
Token between
Feature activation+3.293
Top resid features:
20
Token 20
Feature activation+0.050
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
ward
Token ward
Feature activation+0.000
Top resid features:
whose
Token whose
Feature activation-0.001
Top resid features:
cardinal
Token cardinal
Feature activation+0.003
Top resid features:
ity
Tokenity
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
strictly
Token strictly
Feature activation+0.008
Top resid features:
between
Token between
Feature activation+3.017
Top resid features:
â
Token â
Feature activation+0.011
Top resid features:
Ħ
TokenĦ
Feature activation+0.004
Top resid features:
µ
Tokenµ
Feature activation+0.008
Top resid features:
0
Token 0
Feature activation+0.040
Top resid features:
{\
Token {\
Feature activation+0.010
Top resid features:
whose
Token whose
Feature activation+0.001
Top resid features:
cardinal
Token cardinal
Feature activation+0.011
Top resid features:
ity
Tokenity
Feature activation+0.010
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
strictly
Token strictly
Feature activation+0.010
Top resid features:
between
Token between
Feature activation+2.963
Top resid features:
â
Token â
Feature activation+0.045
Top resid features:
Ħ
TokenĦ
Feature activation+0.062
Top resid features:
µ
Tokenµ
Feature activation+0.067
Top resid features:
0
Token 0
Feature activation+0.000
Top resid features:
{\
Token {\
Feature activation+0.000
Top resid features:
disclosed
Token disclosed
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
it
Token it
Feature activation-0.002
Top resid features:
had
Token had
Feature activation-0.002
Top resid features:
received
Token received
Feature activation-0.022
Top resid features:
between
Token between
Feature activation+3.288
Top resid features:
zero
Token zero
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
249
Token 249
Feature activation+0.000
Top resid features:
national
Token national
Feature activation+0.000
Top resid features:
security
Token security
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
centuries
Token centuries
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
old
Tokenold
Feature activation+0.005
Top resid features:
links
Token links
Feature activation+0.020
Top resid features:
between
Token between
Feature activation+2.751
Top resid features:
the
Token the
Feature activation+0.316
Top resid features:
I
Token I
Feature activation+0.018
Top resid features:
ber
Tokenber
Feature activation+0.044
Top resid features:
ian
Tokenian
Feature activation+0.026
Top resid features:
Peninsula
Token Peninsula
Feature activation+0.047
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
placing
Token placing
Feature activation+0.003
Top resid features:
payload
Token payload
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.014
Top resid features:
weighing
Token weighing
Feature activation-0.011
Top resid features:
between
Token between
Feature activation+2.955
Top resid features:
2
Token 2
Feature activation+0.106
Top resid features:
metric
Token metric
Feature activation+0.029
Top resid features:
tons
Token tons
Feature activation+0.044
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
24
Token 24
Feature activation+0.000
Top resid features:
each
Token each
Feature activation-0.002
Top resid features:
;
Token;
Feature activation+0.001
Top resid features:
one
Token one
Feature activation-0.006
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
worth
Token worth
Feature activation+0.002
Top resid features:
between
Token between
Feature activation+3.027
Top resid features:
$
Token $
Feature activation+0.068
Top resid features:
25
Token25
Feature activation+0.012
Top resid features:
million
Token million
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
proof
Token proof
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
relationship
Token relationship
Feature activation+0.032
Top resid features:
between
Token between
Feature activation+2.724
Top resid features:
the
Token the
Feature activation+0.336
Top resid features:
colon
Token colon
Feature activation+0.026
Top resid features:
ials
Tokenials
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
peace
Token peace
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
maker
Tokenmaker
Feature activation-0.007
Top resid features:
between
Token between
Feature activation+2.158
Top resid features:
the
Token the
Feature activation+0.833
Top resid features:
Israelis
Token Israelis
Feature activation+0.041
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Palestinians
Token Palestinians
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
W
Token W
Feature activation+0.002
Top resid features:
ight
Tokenight
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
yet
Token yet
Feature activation+0.010
Top resid features:
between
Token between
Feature activation+2.857
Top resid features:
1940
Token 1940
Feature activation+0.080
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
1942
Token 1942
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
bombs
Token bombs
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
Int
TokenInt
Feature activation+0.001
Top resid features:
ellectual
Tokenellectual
Feature activation-0.000
Top resid features:
contacts
Token contacts
Feature activation+0.010
Top resid features:
between
Token between
Feature activation+2.938
Top resid features:
prolet
Token prolet
Feature activation+0.015
Top resid features:
arians
Tokenarians
Feature activation+0.022
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
various
Token various
Feature activation+0.000
Top resid features:
countries
Token countries
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
30
Token 30
Feature activation-0.001
Top resid features:
clubs
Token clubs
Feature activation-0.004
Top resid features:
playing
Token playing
Feature activation+0.016
Top resid features:
between
Token between
Feature activation+2.845
Top resid features:
87
Token 87
Feature activation+0.103
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Baltimore
TokenBaltimore
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Boston
Token Boston
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.01

Head 2: 0.03

Head 3: 0.09

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.64

Head 11: 0.03

Positive logits

and3.02

and2.54

AND2.15

And1.96

sexes1.86

utral1.82

ubric1.80

uez1.79

And1.77

roup1.68

genders1.68

anding1.67

Ares1.64

acion1.54

populations1.53

bows1.50

yea1.50

&1.48

utive1.45

modes1.41

Negative logits

Pwr-2.91

anytime-2.30

��-2.28

anywhere-2.16

slightest-2.05

somew-2.03

unfocusedRange-2.00

nowhere-1.97

too-1.92

��極-1.87

understatement-1.84

Years-1.82

Wrong-1.82

MIT-1.81

unnecessarily-1.81

Retrieved-1.80

}}-1.78

uggest-1.75

)}-1.74

itism-1.72

INTERVAL 3.094 - 3.438
CONTAINS 0.000%

strictly
Token strictly
Feature activation+0.000
between
Token between
Feature activation+0.234
â
Token â
Feature activation+1.330
Ħ
TokenĦ
Feature activation+0.242
µ
Tokenµ
Feature activation+2.761
0
Token 0
Feature activation+3.438
{\
Token {\
Feature activation+0.000
display
Tokendisplay
Feature activation+0.000
style
Tokenstyle
Feature activation+0.154
\
Token \
Feature activation+0.273
al
Tokenal
Feature activation+0.000

INTERVAL 2.750 - 3.094
CONTAINS 0.001%

is
Token is
Feature activation+0.000
strictly
Token strictly
Feature activation+0.000
between
Token between
Feature activation+0.234
â
Token â
Feature activation+1.330
Ħ
TokenĦ
Feature activation+0.242
µ
Tokenµ
Feature activation+2.761
0
Token 0
Feature activation+3.438
{\
Token {\
Feature activation+0.000
display
Tokendisplay
Feature activation+0.000
style
Tokenstyle
Feature activation+0.154
\
Token \
Feature activation+0.273
.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
book
Token book
Feature activation+0.000
is
Token is
Feature activation+0.000
between
Token between
Feature activation+0.000
50
Token 50
Feature activation+2.835
and
Token and
Feature activation+0.208
150
Token 150
Feature activation+0.000
pages
Token pages
Feature activation+0.000
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
committee
Token committee
Feature activation+0.000
people
Tokenpeople
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
generally
Token generally
Feature activation+0.000
between
Token between
Feature activation+0.000
20
Token 20
Feature activation+2.784
and
Token and
Feature activation+0.000
100
Token 100
Feature activation+0.000
per
Token per
Feature activation+0.000
ward
Token ward
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
threads
Token threads
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
alive
Token alive
Feature activation+2.916
and
Token and
Feature activation+0.000
dead
Token dead
Feature activation+0.245
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+0.001
enumer
Token enumer
Feature activation+0.000
study
Token study
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+1.492
theory
Token theory
Feature activation+2.839
and
Token and
Feature activation+0.000
right
Token right
Feature activation+0.000
wing
Token wing
Feature activation+0.000
violence
Token violence
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.407 - 2.750
CONTAINS 0.002%

between
Token between
Feature activation+0.000
data
Token data
Feature activation+0.285
transmitted
Token transmitted
Feature activation+0.342
between
Token between
Feature activation+0.016
POS
Token POS
Feature activation+0.332
devices
Token devices
Feature activation+2.408
and
Token and
Feature activation+0.058
the
Token the
Feature activation+0.034
data
Token data
Feature activation+0.000
center
Token center
Feature activation+0.000
and
Tokenand
Feature activation+0.000
Int
TokenInt
Feature activation+0.000
ellectual
Tokenellectual
Feature activation+0.000
contacts
Token contacts
Feature activation+0.000
between
Token between
Feature activation+0.000
prolet
Token prolet
Feature activation+0.000
arians
Tokenarians
Feature activation+2.537
of
Token of
Feature activation+0.000
various
Token various
Feature activation+0.000
countries
Token countries
Feature activation+1.294
in
Token in
Feature activation+0.159
reality
Token reality
Feature activation+0.328
placing
Token placing
Feature activation+0.000
payload
Token payload
Feature activation+0.000
s
Tokens
Feature activation+0.000
weighing
Token weighing
Feature activation+0.000
between
Token between
Feature activation+0.000
2
Token 2
Feature activation+2.411
metric
Token metric
Feature activation+0.362
tons
Token tons
Feature activation+2.717
and
Token and
Feature activation+0.029
24
Token 24
Feature activation+0.505
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
between
Token between
Feature activation+0.000
14
Token 14
Feature activation+2.896
years
Token years
Feature activation+2.477
and
Token and
Feature activation+0.202
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
in
Token in
Feature activation+0.000
prison
Token prison
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
or
Token or
Feature activation+0.000
between
Token between
Feature activation+0.000
10
Token 10
Feature activation+2.416
and
Token and
Feature activation+0.101
20
Token 20
Feature activation+0.047
years
Token years
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.063 - 2.407
CONTAINS 0.004%

strong
Token strong
Feature activation+0.000
association
Token association
Feature activation+0.000
between
Token between
Feature activation+0.000
black
Token black
Feature activation+0.000
humour
Token humour
Feature activation+1.598
comprehension
Token comprehension
Feature activation+2.159
and
Token and
Feature activation+0.000
preference
Token preference
Feature activation+0.000
for
Token for
Feature activation+0.000
black
Token black
Feature activation+0.000
humour
Token humour
Feature activation+0.000
while
Token while
Feature activation+0.000
NAS
Token NAS
Feature activation+0.000
H
TokenH
Feature activation+0.000
affects
Token affects
Feature activation+0.000
between
Token between
Feature activation+0.000
2
Token 2
Feature activation+2.298
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+0.000
%
Token%
Feature activation+0.000
.[
Token.[
Feature activation+0.000
12
Token12
Feature activation+0.000
s
Tokens
Feature activation+0.000
orbiting
Token orbiting
Feature activation+0.000
between
Token between
Feature activation+0.000
43
Token 43
Feature activation+1.683
.
Token.
Feature activation+0.551
5
Token5
Feature activation+2.357
degrees
Token degrees
Feature activation+0.720
north
Token north
Feature activation+0.398
latitude
Token latitude
Feature activation+1.268
to
Token to
Feature activation+0.000
43
Token 43
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
inf
Token inf
Feature activation+0.000
idel
Tokenidel
Feature activation+2.210
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
.
Token.
Feature activation+0.000
Battle
Token Battle
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
between
Token between
Feature activation+0.000
$
Token $
Feature activation+0.116
80
Token80
Feature activation+1.855
,
Token,
Feature activation+0.000
000
Token000
Feature activation+2.254
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000
100
Token100
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000

INTERVAL 1.719 - 2.063
CONTAINS 0.009%

and
Token and
Feature activation+0.000
cost
Token cost
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
between
Token between
Feature activation+0.000
$
Token $
Feature activation+0.116
80
Token80
Feature activation+1.855
,
Token,
Feature activation+0.000
000
Token000
Feature activation+2.254
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000
100
Token100
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+1.895
and
Token and
Feature activation+0.052
long
Token long
Feature activation+0.031
terms
Token terms
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
between
Token between
Feature activation+0.000
Bill
Token Bill
Feature activation+1.638
Clinton
Token Clinton
Feature activation+1.722
and
Token and
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
President
Token President
Feature activation+0.000
Assad
Token Assad
Feature activation+0.000
.
Token.
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.630
(
Token (
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
terrified
Token terrified
Feature activation+0.068
)
Token)
Feature activation+1.729
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
w
Tokenw
Feature activation+0.000
or
Tokenor
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
between
Token between
Feature activation+0.000
February
Token February
Feature activation+1.552
2016
Token 2016
Feature activation+1.924
and
Token and
Feature activation+0.000
January
Token January
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.375 - 1.719
CONTAINS 0.016%

in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
between
Token between
Feature activation+0.000
Div
Token Div
Feature activation+0.000
illy
Tokenilly
Feature activation+1.587
and
Token and
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Party
Token Party
Feature activation+0.000
leader
Token leader
Feature activation+0.000
E
Token E
Feature activation+0.000
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
both
Token both
Feature activation+0.000
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+1.615
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
home
Token home
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+0.120
the
Token the
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
region
Token region
Feature activation+1.379
and
Token and
Feature activation+0.000
across
Token across
Feature activation+0.000
India
Token India
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
registered
Token registered
Feature activation+0.000
female
Token female
Feature activation+0.078
players
Token players
Feature activation+1.528
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
registered
Token registered
Feature activation+0.000
able
Tokenable
Feature activation+0.000
by
Token by
Feature activation+0.000
using
Token using
Feature activation+0.000
both
Token both
Feature activation+0.000
ind
Token ind
Feature activation+0.000
igo
Tokenigo
Feature activation+1.431
dyed
Token dyed
Feature activation+0.781
warp
Token warp
Feature activation+0.629
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
ft
Tokenft
Feature activation+0.000

INTERVAL 1.031 - 1.375
CONTAINS 0.020%

and
Token and
Feature activation+0.000
starting
Token starting
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
between
Token between
Feature activation+0.000
a
Token a
Feature activation+0.000
friend
Token friend
Feature activation+1.202
of
Token of
Feature activation+0.000
mine
Token mine
Feature activation+1.468
and
Token and
Feature activation+0.000
myself
Token myself
Feature activation+0.000
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
links
Token links
Feature activation+0.000
between
Token between
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
weather
Token weather
Feature activation+1.136
events
Token events
Feature activation+2.249
and
Token and
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
.
Token.
Feature activation+0.000
both
Token both
Feature activation+0.000
facilitate
Token facilitate
Feature activation+0.021
local
Token local
Feature activation+0.434
economic
Token economic
Feature activation+0.777
growth
Token growth
Feature activation+1.758
and
Token and
Feature activation+1.069
alleviate
Token alleviate
Feature activation+0.000
pressures
Token pressures
Feature activation+0.000
in
Token in
Feature activation+0.000
other
Token other
Feature activation+0.000
parts
Token parts
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
clash
Token clash
Feature activation+0.000
between
Token between
Feature activation+0.000
AFC
Token AFC
Feature activation+0.000
Wim
Token Wim
Feature activation+0.000
bledon
Tokenbledon
Feature activation+1.203
and
Token and
Feature activation+0.000
Liverpool
Token Liverpool
Feature activation+0.000
Jamie
Token Jamie
Feature activation+0.000
Red
Token Red
Feature activation+0.000
kn
Tokenkn
Feature activation+0.000
seven
Token seven
Feature activation+0.000
were
Token were
Feature activation+0.000
worth
Token worth
Feature activation+0.000
between
Token between
Feature activation+0.000
$
Token $
Feature activation+0.000
5
Token5
Feature activation+1.106
million
Token million
Feature activation+2.030
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
25
Token25
Feature activation+0.000
million
Token million
Feature activation+0.000

INTERVAL 0.688 - 1.031
CONTAINS 0.024%

your
Token your
Feature activation+0.000
desired
Token desired
Feature activation+0.000
one
Token one
Feature activation+0.000
both
Token both
Feature activation+0.000
sleep
Token sleep
Feature activation+0.666
beneath
Token beneath
Feature activation+0.817
,
Token,
Feature activation+0.000
serve
Token serve
Feature activation+0.000
to
Token to
Feature activation+0.000
connect
Token connect
Feature activation+0.000
you
Token you
Feature activation+0.000
sets
Token sets
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Between
TokenBetween
Feature activation+0.000
1972
Token 1972
Feature activation+0.856
and
Token and
Feature activation+0.000
1979
Token 1979
Feature activation+0.000
,
Token,
Feature activation+0.000
Samsung
Token Samsung
Feature activation+0.000
began
Token began
Feature activation+0.000
to
Token to
Feature activation+0.000
transport
Token transport
Feature activation+0.000
data
Token data
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+1.006
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
hand
Token hand
Feature activation+0.000
,
Token,
Feature activation+1.009
and
Token and
Feature activation+0.106
industrial
Token industrial
Feature activation+0.024
policies
Token policies
Feature activation+0.545
,
Token,
Feature activation+0.311
on
Token on
Feature activation+0.107
convicted
Token convicted
Feature activation+0.000
on
Token on
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
minor
Token minor
Feature activation+0.000
state
Token state
Feature activation+0.000
charges
Token charges
Feature activation+0.737
and
Token and
Feature activation+0.000
served
Token served
Feature activation+0.000
just
Token just
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.344 - 0.688
CONTAINS 0.072%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
between
Token between
Feature activation+0.000
all
Token all
Feature activation+0.319
the
Token the
Feature activation+0.275
screens
Token screens
Feature activation+0.581
,
Token,
Feature activation+0.136
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
system
Token system
Feature activation+0.000
on
Token on
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Reuters
TokenReuters
Feature activation+0.433
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.000
East
Token East
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.451
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.119
s
Tokens
Feature activation+0.224
,
Token,
Feature activation+0.000
confront
Token confront
Feature activation+0.000
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
British
Token British
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
Army
Token Army
Feature activation+0.434
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
world
Token world
Feature activation+0.000
wars
Token wars
Feature activation+0.000
and
Token and
Feature activation+0.000
Kan
Token Kan
Feature activation+0.000
ien
Tokenien
Feature activation+0.184
'
Token'
Feature activation+0.000
ke
Tokenke
Feature activation+0.246
h
Tokenh
Feature activation+0.362
á
Tokená
Feature activation+0.488
:
Token:
Feature activation+0.000
ka
Tokenka
Feature activation+0.786
(
Token (
Feature activation+0.000
Moh
TokenMoh
Feature activation+0.000

INTERVAL 0.000 - 0.344
CONTAINS 99.851%

years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
book
Token book
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
what
Token what
Feature activation+0.000
M
Token M
Feature activation+0.000
ugg
Tokenugg
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
AV
TokenAV
Feature activation+0.000
B
TokenB
Feature activation+0.000
is
Token is
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
a
Token a
Feature activation+0.000
firm
Token firm
Feature activation+0.000
believer
Token believer
Feature activation+0.000
in
Token in
Feature activation+0.000
changes
Token changes
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Clean
Token Clean
Feature activation+0.000
Air
Token Air
Feature activation+0.000
Act
Token Act
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
decade
Token decade
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
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.000
's
Token's
Feature activation+0.000
decision
Token decision
Feature activation+0.000
then
Token then
Feature activation+0.000
escaped
Token escaped
Feature activation+0.000
custody
Token custody
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+0.000
2007
Token 2007
Feature activation+0.000
while
Token while
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
way
Token way
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 H9.10: (feature 17292)

TOP ACTIVATIONS
MAX = 4.966

it
Token it
Feature activation+0.013
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.254
t
Tokent
Feature activation+2.185
for
Token for
Feature activation+4.966
a
Token a
Feature activation+4.268
generation
Token generation
Feature activation+2.221
.
Token.
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.000
trail
Token trail
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.847
done
Token done
Feature activation+4.520
to
Token to
Feature activation+2.285
former
Token former
Feature activation+0.000
rail
Token rail
Feature activation+0.000
roads
Tokenroads
Feature activation+1.208
throughout
Token throughout
Feature activation+0.604
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+1.371
to
Token to
Feature activation+0.237
share
Token share
Feature activation+2.629
for
Token for
Feature activation+4.316
some
Token some
Feature activation+1.637
time
Token time
Feature activation+0.885
,
Token,
Feature activation+0.577
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.254
t
Tokent
Feature activation+2.185
for
Token for
Feature activation+4.966
a
Token a
Feature activation+4.268
generation
Token generation
Feature activation+2.221
.
Token.
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.000
Center
Token Center
Feature activation+0.000
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+1.366
been
Token been
Feature activation+4.249
since
Token since
Feature activation+0.000
1976
Token 1976
Feature activation+0.000
.
Token.
Feature activation+0.000
Conservatives
Token Conservatives
Feature activation+0.000
managed
Token managed
Feature activation+0.000
Interior
Token Interior
Feature activation+0.822
Design
Token Design
Feature activation+1.545
&
Token &
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
oration
Tokenoration
Feature activation+1.924
industry
Token industry
Feature activation+4.187
for
Token for
Feature activation+1.905
the
Token the
Feature activation+2.312
past
Token past
Feature activation+1.401
13
Token 13
Feature activation+0.605
years
Token years
Feature activation+1.363
I
TokenI
Feature activation+0.000
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+0.904
i
Tokeni
Feature activation+4.044
a
Token a
Feature activation+3.326
long
Token long
Feature activation+3.470
time
Token time
Feature activation+3.129
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
activists
Token activists
Feature activation+0.000
have
Token have
Feature activation+0.000
battled
Token battled
Feature activation+0.428
the
Token the
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.647
service
Token service
Feature activation+3.798
in
Token in
Feature activation+3.373
court
Token court
Feature activation+3.206
for
Token for
Feature activation+2.494
several
Token several
Feature activation+3.392
years
Token years
Feature activation+2.460
a
Token a
Feature activation+1.100
source
Token source
Feature activation+0.465
of
Token of
Feature activation+1.151
pride
Token pride
Feature activation+1.740
for
Token for
Feature activation+2.075
many
Token many
Feature activation+3.763
conservatives
Token conservatives
Feature activation+3.075
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sep
TokenSep
Feature activation+0.000
I
Token I
Feature activation+0.000
haven
Token haven
Feature activation+0.000
't
Token't
Feature activation+0.000
been
Token been
Feature activation+0.000
back
Token back
Feature activation+0.490
here
Token here
Feature activation+3.738
for
Token for
Feature activation+3.428
a
Token a
Feature activation+1.332
while
Token while
Feature activation+2.355
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
's
Token's
Feature activation+0.851
courts
Token courts
Feature activation+2.906
and
Token and
Feature activation+0.645
legislature
Token legislature
Feature activation+2.927
for
Token for
Feature activation+1.968
a
Token a
Feature activation+3.603
decade
Token decade
Feature activation+2.529
.
Token.
Feature activation+0.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.409
"
Token"
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
occupied
Token occupied
Feature activation+2.517
a
Token a
Feature activation+2.462
little
Token little
Feature activation+3.420
over
Token over
Feature activation+3.574
a
Token a
Feature activation+1.604
month
Token month
Feature activation+2.318
--
Token --
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
owned
Token owned
Feature activation+0.000
and
Token and
Feature activation+0.045
operated
Token operated
Feature activation+0.381
Di
Token Di
Feature activation+0.000
F
Token F
Feature activation+0.000
ara
Tokenara
Feature activation+3.523
since
Token since
Feature activation+0.133
1964
Token 1964
Feature activation+0.389
,
Token,
Feature activation+0.660
hailed
Token hailed
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.872
shots
Token shots
Feature activation+2.984
atop
Token atop
Feature activation+1.199
the
Token the
Feature activation+0.523
pit
Token pit
Feature activation+0.109
box
Token box
Feature activation+3.490
since
Token since
Feature activation+0.169
getting
Token getting
Feature activation+0.000
his
Token his
Feature activation+0.000
start
Token start
Feature activation+0.000
in
Token in
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+0.904
i
Tokeni
Feature activation+4.044
a
Token a
Feature activation+3.326
long
Token long
Feature activation+3.470
time
Token time
Feature activation+3.129
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
Pap
Token Pap
Feature activation+0.000
ran
Tokenran
Feature activation+0.000
haven
Token haven
Feature activation+0.000
't
Token't
Feature activation+0.000
been
Token been
Feature activation+0.000
back
Token back
Feature activation+0.490
here
Token here
Feature activation+3.738
for
Token for
Feature activation+3.428
a
Token a
Feature activation+1.332
while
Token while
Feature activation+2.355
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
occupied
Token occupied
Feature activation+2.517
a
Token a
Feature activation+2.462
little
Token little
Feature activation+3.420
over
Token over
Feature activation+3.574
a
Token a
Feature activation+1.604
month
Token month
Feature activation+2.318
--
Token --
Feature activation+0.000
is
Token is
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.647
service
Token service
Feature activation+3.798
in
Token in
Feature activation+3.373
court
Token court
Feature activation+3.206
for
Token for
Feature activation+2.494
several
Token several
Feature activation+3.392
years
Token years
Feature activation+2.460
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.013
controversial
Token controversial
Feature activation+0.000
practice
Token practice
Feature activation+0.628
have
Token have
Feature activation+0.000
battled
Token battled
Feature activation+0.428
the
Token the
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.647
service
Token service
Feature activation+3.798
in
Token in
Feature activation+3.373
court
Token court
Feature activation+3.206
for
Token for
Feature activation+2.494
several
Token several
Feature activation+3.392
years
Token years
Feature activation+2.460
over
Token over
Feature activation+0.000
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+0.904
i
Tokeni
Feature activation+4.044
a
Token a
Feature activation+3.326
long
Token long
Feature activation+3.470
time
Token time
Feature activation+3.129
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
Pap
Token Pap
Feature activation+0.000

Top DFA by src position
MAX = 4.378

way
Token way
Feature activation+0.016
Top resid features:
it
Token it
Feature activation+0.073
Top resid features:
hasn
Token hasn
Feature activation+0.793
Top resid features:
âĢ
TokenâĢ
Feature activation-0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
t
Tokent
Feature activation+4.378
Top resid features:
for
Token for
Feature activation+0.023
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
generation
Token generation
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Pew
Token Pew
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.015
Top resid features:
trail
Token trail
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
as
Token as
Feature activation-0.029
Top resid features:
it
Token it
Feature activation+0.122
Top resid features:
has
Token has
Feature activation+3.585
Top resid features:
done
Token done
Feature activation+1.310
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
rail
Token rail
Feature activation+0.000
Top resid features:
roads
Tokenroads
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
vision
Token vision
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
have
Token have
Feature activation+0.072
Top resid features:
wanted
Token wanted
Feature activation+4.246
Top resid features:
to
Token to
Feature activation+0.202
Top resid features:
share
Token share
Feature activation+0.054
Top resid features:
for
Token for
Feature activation+0.029
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.012
Top resid features:
it
Token it
Feature activation+0.049
Top resid features:
hasn
Token hasn
Feature activation+0.496
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation-0.010
Top resid features:
t
Tokent
Feature activation+3.059
Top resid features:
for
Token for
Feature activation+0.964
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
generation
Token generation
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Pew
Token Pew
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
popular
Token popular
Feature activation+0.001
Top resid features:
than
Token than
Feature activation+0.032
Top resid features:
it
Token it
Feature activation+0.199
Top resid features:
has
Token has
Feature activation+3.858
Top resid features:
been
Token been
Feature activation+0.440
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
1976
Token 1976
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Conservatives
Token Conservatives
Feature activation+0.000
Top resid features:
Professional
Token Professional
Feature activation+0.000
Top resid features:
Interior
Token Interior
Feature activation-0.000
Top resid features:
Designer
Token Designer
Feature activation-0.003
Top resid features:
Adelaide
Token Adelaide
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.104
Top resid features:
worked
Token worked
Feature activation+2.425
Top resid features:
in
Token in
Feature activation+1.643
Top resid features:
the
Token the
Feature activation+0.156
Top resid features:
Interior
Token Interior
Feature activation+0.003
Top resid features:
Design
Token Design
Feature activation+0.008
Top resid features:
&
Token &
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.004
Top resid features:
I
TokenI
Feature activation-0.002
Top resid features:
've
Token've
Feature activation+0.005
Top resid features:
known
Token known
Feature activation+4.318
Top resid features:
S
Token S
Feature activation-0.007
Top resid features:
atch
Tokenatch
Feature activation-0.008
Top resid features:
i
Tokeni
Feature activation+0.055
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Wild
TokenWild
Feature activation-0.001
Top resid features:
life
Tokenlife
Feature activation-0.001
Top resid features:
activists
Token activists
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.152
Top resid features:
battled
Token battled
Feature activation+3.824
Top resid features:
the
Token the
Feature activation+0.141
Top resid features:
fisheries
Token fisheries
Feature activation-0.003
Top resid features:
service
Token service
Feature activation+0.021
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
court
Token court
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.090
Top resid features:
a
Token a
Feature activation+0.041
Top resid features:
source
Token source
Feature activation+0.081
Top resid features:
of
Token of
Feature activation+0.071
Top resid features:
pride
Token pride
Feature activation+0.357
Top resid features:
for
Token for
Feature activation+3.324
Top resid features:
many
Token many
Feature activation+0.087
Top resid features:
conservatives
Token conservatives
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
haven
Token haven
Feature activation+0.019
Top resid features:
't
Token't
Feature activation+0.696
Top resid features:
been
Token been
Feature activation+0.887
Top resid features:
back
Token back
Feature activation+2.336
Top resid features:
here
Token here
Feature activation+0.143
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
Jersey
Token Jersey
Feature activation+0.024
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
courts
Token courts
Feature activation+0.294
Top resid features:
and
Token and
Feature activation+0.053
Top resid features:
legislature
Token legislature
Feature activation+0.128
Top resid features:
for
Token for
Feature activation+2.820
Top resid features:
a
Token a
Feature activation+0.089
Top resid features:
decade
Token decade
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
office
Token office
Feature activation+0.013
Top resid features:
--
Token --
Feature activation+0.011
Top resid features:
which
Token which
Feature activation+0.001
Top resid features:
he
Token he
Feature activation+0.017
Top resid features:
's
Token's
Feature activation+0.204
Top resid features:
occupied
Token occupied
Feature activation+3.308
Top resid features:
a
Token a
Feature activation+0.298
Top resid features:
little
Token little
Feature activation+0.022
Top resid features:
over
Token over
Feature activation+0.023
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
local
Token local
Feature activation-0.003
Top resid features:
legend
Token legend
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
having
Token having
Feature activation+0.066
Top resid features:
owned
Token owned
Feature activation+2.098
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
operated
Token operated
Feature activation+1.523
Top resid features:
Di
Token Di
Feature activation+0.003
Top resid features:
F
Token F
Feature activation+0.012
Top resid features:
ara
Tokenara
Feature activation+0.056
Top resid features:
ig
Tokenig
Feature activation+0.001
Top resid features:
has
Token has
Feature activation+0.165
Top resid features:
been
Token been
Feature activation+0.503
Top resid features:
calling
Token calling
Feature activation+1.201
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
shots
Token shots
Feature activation+1.520
Top resid features:
atop
Token atop
Feature activation+0.176
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
pit
Token pit
Feature activation+0.006
Top resid features:
box
Token box
Feature activation+0.029
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
've
Token've
Feature activation+0.083
Top resid features:
known
Token known
Feature activation+1.386
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
atch
Tokenatch
Feature activation-0.015
Top resid features:
i
Tokeni
Feature activation+0.079
Top resid features:
a
Token a
Feature activation+2.233
Top resid features:
long
Token long
Feature activation+0.027
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
Pap
Token Pap
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.029
Top resid features:
I
Token I
Feature activation-0.011
Top resid features:
haven
Token haven
Feature activation+0.014
Top resid features:
't
Token't
Feature activation+0.575
Top resid features:
been
Token been
Feature activation+0.521
Top resid features:
back
Token back
Feature activation+2.286
Top resid features:
here
Token here
Feature activation+0.486
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
office
Token office
Feature activation+0.005
Top resid features:
--
Token --
Feature activation+0.011
Top resid features:
which
Token which
Feature activation+0.006
Top resid features:
he
Token he
Feature activation+0.042
Top resid features:
's
Token's
Feature activation+0.216
Top resid features:
occupied
Token occupied
Feature activation+2.752
Top resid features:
a
Token a
Feature activation+0.688
Top resid features:
little
Token little
Feature activation+0.020
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
fisheries
Token fisheries
Feature activation+0.007
Top resid features:
service
Token service
Feature activation+0.070
Top resid features:
in
Token in
Feature activation+0.582
Top resid features:
court
Token court
Feature activation+0.291
Top resid features:
for
Token for
Feature activation+2.002
Top resid features:
several
Token several
Feature activation+0.111
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
controversial
Token controversial
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Wild
TokenWild
Feature activation+0.002
Top resid features:
life
Tokenlife
Feature activation-0.006
Top resid features:
activists
Token activists
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.654
Top resid features:
battled
Token battled
Feature activation+2.825
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
fisheries
Token fisheries
Feature activation+0.008
Top resid features:
service
Token service
Feature activation+0.118
Top resid features:
in
Token in
Feature activation+0.062
Top resid features:
court
Token court
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
"
Token"
Feature activation-0.001
Top resid features:
I
TokenI
Feature activation-0.009
Top resid features:
've
Token've
Feature activation+0.146
Top resid features:
known
Token known
Feature activation+3.377
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
atch
Tokenatch
Feature activation-0.010
Top resid features:
i
Tokeni
Feature activation+0.019
Top resid features:
a
Token a
Feature activation+0.120
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.03

Head 3: 0.09

Head 4: 0.02

Head 5: 0.06

Head 6: 0.01

Head 7: 0.06

Head 8: 0.02

Head 9: 0.01

Head 10: 0.63

Head 11: 0.02

Positive logits

since5.00

lately4.66

since4.56

decades3.47

recent3.28

past3.24

recently3.15

millennia3.13

years3.12

recent3.12

hitherto2.80

Since2.75

centuries2.75

Since2.74

dating2.74

awhile2.74

years2.68

historically2.66

previously2.66

previous2.64

Negative logits

"},{"-2.16

$$$$-2.15

FAULT-1.97

))))-1.90

LLOW-1.88

igible-1.85

Balance-1.83

"}],"-1.81

IBLE-1.81

igate-1.76

umbledore-1.72

decide-1.71

OULD-1.69

obey-1.67

inki-1.66

iru-1.66

interstitial-1.66

lication-1.65

FLAG-1.65

-1.65

INTERVAL 4.469 - 4.966
CONTAINS 0.000%

trail
Token trail
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.847
done
Token done
Feature activation+4.520
to
Token to
Feature activation+2.285
former
Token former
Feature activation+0.000
rail
Token rail
Feature activation+0.000
roads
Tokenroads
Feature activation+1.208
throughout
Token throughout
Feature activation+0.604
it
Token it
Feature activation+0.013
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.254
t
Tokent
Feature activation+2.185
for
Token for
Feature activation+4.966
a
Token a
Feature activation+4.268
generation
Token generation
Feature activation+2.221
.
Token.
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.000

INTERVAL 3.972 - 4.469
CONTAINS 0.001%

I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+1.371
to
Token to
Feature activation+0.237
share
Token share
Feature activation+2.629
for
Token for
Feature activation+4.316
some
Token some
Feature activation+1.637
time
Token time
Feature activation+0.885
,
Token,
Feature activation+0.577
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
I
TokenI
Feature activation+0.000
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+0.904
i
Tokeni
Feature activation+4.044
a
Token a
Feature activation+3.326
long
Token long
Feature activation+3.470
time
Token time
Feature activation+3.129
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.254
t
Tokent
Feature activation+2.185
for
Token for
Feature activation+4.966
a
Token a
Feature activation+4.268
generation
Token generation
Feature activation+2.221
.
Token.
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.000
Center
Token Center
Feature activation+0.000
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+1.366
been
Token been
Feature activation+4.249
since
Token since
Feature activation+0.000
1976
Token 1976
Feature activation+0.000
.
Token.
Feature activation+0.000
Conservatives
Token Conservatives
Feature activation+0.000
managed
Token managed
Feature activation+0.000
Interior
Token Interior
Feature activation+0.822
Design
Token Design
Feature activation+1.545
&
Token &
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
oration
Tokenoration
Feature activation+1.924
industry
Token industry
Feature activation+4.187
for
Token for
Feature activation+1.905
the
Token the
Feature activation+2.312
past
Token past
Feature activation+1.401
13
Token 13
Feature activation+0.605
years
Token years
Feature activation+1.363

INTERVAL 3.476 - 3.972
CONTAINS 0.001%

owned
Token owned
Feature activation+0.000
and
Token and
Feature activation+0.045
operated
Token operated
Feature activation+0.381
Di
Token Di
Feature activation+0.000
F
Token F
Feature activation+0.000
ara
Tokenara
Feature activation+3.523
since
Token since
Feature activation+0.133
1964
Token 1964
Feature activation+0.389
,
Token,
Feature activation+0.660
hailed
Token hailed
Feature activation+0.000
from
Token from
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
occupied
Token occupied
Feature activation+2.517
a
Token a
Feature activation+2.462
little
Token little
Feature activation+3.420
over
Token over
Feature activation+3.574
a
Token a
Feature activation+1.604
month
Token month
Feature activation+2.318
--
Token --
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
's
Token's
Feature activation+0.851
courts
Token courts
Feature activation+2.906
and
Token and
Feature activation+0.645
legislature
Token legislature
Feature activation+2.927
for
Token for
Feature activation+1.968
a
Token a
Feature activation+3.603
decade
Token decade
Feature activation+2.529
.
Token.
Feature activation+0.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.409
"
Token"
Feature activation+0.000
a
Token a
Feature activation+1.100
source
Token source
Feature activation+0.465
of
Token of
Feature activation+1.151
pride
Token pride
Feature activation+1.740
for
Token for
Feature activation+2.075
many
Token many
Feature activation+3.763
conservatives
Token conservatives
Feature activation+3.075
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sep
TokenSep
Feature activation+0.000
activists
Token activists
Feature activation+0.000
have
Token have
Feature activation+0.000
battled
Token battled
Feature activation+0.428
the
Token the
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.647
service
Token service
Feature activation+3.798
in
Token in
Feature activation+3.373
court
Token court
Feature activation+3.206
for
Token for
Feature activation+2.494
several
Token several
Feature activation+3.392
years
Token years
Feature activation+2.460

INTERVAL 2.979 - 3.476
CONTAINS 0.003%

have
Token have
Feature activation+0.000
battled
Token battled
Feature activation+0.428
the
Token the
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.647
service
Token service
Feature activation+3.798
in
Token in
Feature activation+3.373
court
Token court
Feature activation+3.206
for
Token for
Feature activation+2.494
several
Token several
Feature activation+3.392
years
Token years
Feature activation+2.460
over
Token over
Feature activation+0.000
expert
Token expert
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.789
doing
Token doing
Feature activation+0.059
this
Token this
Feature activation+3.044
my
Token my
Feature activation+1.193
entire
Token entire
Feature activation+0.000
life
Token life
Feature activation+0.619
and
Token and
Feature activation+0.000
have
Token have
Feature activation+0.009
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
her
Token her
Feature activation+2.933
and
Token and
Feature activation+0.224
her
Token her
Feature activation+1.092
husband
Token husband
Feature activation+3.175
for
Token for
Feature activation+0.669
years
Token years
Feature activation+1.997
.
Token.
Feature activation+0.289
And
Token And
Feature activation+0.124
I
Token I
Feature activation+0.003
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
known
Token known
Feature activation+0.573
for
Token for
Feature activation+2.549
quite
Token quite
Feature activation+1.590
a
Token a
Feature activation+2.983
few
Token few
Feature activation+1.282
years
Token years
Feature activation+1.639
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
its
Token its
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+0.904
i
Tokeni
Feature activation+4.044
a
Token a
Feature activation+3.326
long
Token long
Feature activation+3.470
time
Token time
Feature activation+3.129
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
Pap
Token Pap
Feature activation+0.000
ran
Tokenran
Feature activation+0.000
iku
Tokeniku
Feature activation+0.000

INTERVAL 2.483 - 2.979
CONTAINS 0.008%

's
Token's
Feature activation+0.685
ar
Token ar
Feature activation+0.000
chen
Tokenchen
Feature activation+0.000
emy
Tokenemy
Feature activation+1.532
quite
Token quite
Feature activation+2.248
as
Token as
Feature activation+2.536
much
Token much
Feature activation+0.810
as
Token as
Feature activation+0.135
Ham
Token Ham
Feature activation+0.000
ill
Tokenill
Feature activation+0.120
mastered
Token mastered
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
rates
Token rates
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.533
seen
Token seen
Feature activation+2.552
in
Token in
Feature activation+2.046
its
Token its
Feature activation+1.787
dating
Token dating
Feature activation+1.287
and
Token and
Feature activation+0.000
friendship
Token friendship
Feature activation+0.906
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+1.371
to
Token to
Feature activation+0.237
share
Token share
Feature activation+2.629
for
Token for
Feature activation+4.316
some
Token some
Feature activation+1.637
time
Token time
Feature activation+0.885
,
Token,
Feature activation+0.577
and
Token and
Feature activation+0.000
-
Token-
Feature activation+2.139
known
Tokenknown
Feature activation+0.837
for
Token for
Feature activation+2.178
many
Token many
Feature activation+3.019
,
Token,
Feature activation+1.468
many
Token many
Feature activation+2.903
years
Token years
Feature activation+2.092
.
Token.
Feature activation+0.318
So
Token So
Feature activation+0.000
our
Token our
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.023
for
Token for
Feature activation+0.378
a
Token a
Feature activation+1.770
"
Token "
Feature activation+1.950
very
Tokenvery
Feature activation+2.725
,
Token,
Feature activation+0.239
very
Token very
Feature activation+3.060
long
Token long
Feature activation+0.395
time
Token time
Feature activation+0.666
",
Token",
Feature activation+0.002

INTERVAL 1.986 - 2.483
CONTAINS 0.025%

.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
done
Token done
Feature activation+0.619
so
Token so
Feature activation+2.213
,
Token,
Feature activation+0.185
and
Token and
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ae
Tokenae
Feature activation+0.000
ologists
Tokenologists
Feature activation+0.000
have
Token have
Feature activation+0.000
studied
Token studied
Feature activation+0.001
Cah
Token Cah
Feature activation+0.000
okia
Tokenokia
Feature activation+2.231
since
Token since
Feature activation+0.253
the
Token the
Feature activation+0.000
late
Token late
Feature activation+0.000
19
Token 19
Feature activation+0.000
th
Tokenth
Feature activation+0.000
variety
Token variety
Feature activation+0.794
of
Token of
Feature activation+1.492
tasks
Token tasks
Feature activation+1.686
by
Token by
Feature activation+0.647
indigenous
Token indigenous
Feature activation+0.296
peoples
Token peoples
Feature activation+2.084
around
Token around
Feature activation+1.049
the
Token the
Feature activation+0.475
world
Token world
Feature activation+2.174
.
Token.
Feature activation+0.009
Even
Token Even
Feature activation+0.000
a
Token a
Feature activation+1.265
lot
Token lot
Feature activation+1.420
on
Token on
Feature activation+1.031
its
Token its
Feature activation+1.489
cloud
Token cloud
Feature activation+0.877
solution
Token solution
Feature activation+2.081
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Haven
Token Haven
Feature activation+0.000
't
Token't
Feature activation+0.000
you
Token you
Feature activation+0.638
all
Token all
Feature activation+2.311
felt
Token felt
Feature activation+0.440
it
Token it
Feature activation+1.254
?
Token?
Feature activation+0.000
She
Token She
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 1.490 - 1.986
CONTAINS 0.059%

many
Token many
Feature activation+0.000
sectors
Token sectors
Feature activation+0.000
has
Token has
Feature activation+0.000
declined
Token declined
Feature activation+1.145
sharply
Token sharply
Feature activation+1.531
in
Token in
Feature activation+1.522
recent
Token recent
Feature activation+1.451
years
Token years
Feature activation+1.292
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Financial
Token Financial
Feature activation+0.000
has
Token has
Feature activation+0.000
given
Token given
Feature activation+0.347
to
Token to
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
investigation
Token investigation
Feature activation+1.050
over
Token over
Feature activation+1.777
the
Token the
Feature activation+2.210
centuries
Token centuries
Feature activation+0.706
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
Token We
Feature activation+0.185
have
Token have
Feature activation+0.334
been
Token been
Feature activation+0.108
banning
Token banning
Feature activation+0.000
films
Token films
Feature activation+1.608
for
Token for
Feature activation+1.591
a
Token a
Feature activation+2.088
few
Token few
Feature activation+2.664
years
Token years
Feature activation+0.581
now
Token now
Feature activation+0.390
.
Token.
Feature activation+0.000
entangled
Token entangled
Feature activation+0.000
on
Token on
Feature activation+0.077
numerous
Token numerous
Feature activation+0.421
occasions
Token occasions
Feature activation+0.565
over
Token over
Feature activation+1.031
the
Token the
Feature activation+1.573
past
Token past
Feature activation+1.004
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.469
.
Token.
Feature activation+0.000
Conservatives
Token Conservatives
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
war
Token war
Feature activation+0.000
ring
Tokenring
Feature activation+0.973
for
Token for
Feature activation+1.591
years
Token years
Feature activation+1.966
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.204
Hartford
Token Hartford
Feature activation+0.000
Soldiers
Token Soldiers
Feature activation+0.390
gang
Token gang
Feature activation+0.961

INTERVAL 0.993 - 1.490
CONTAINS 0.138%

severely
Token severely
Feature activation+0.179
deval
Token deval
Feature activation+0.000
ued
Tokenued
Feature activation+0.000
ad
Token ad
Feature activation+0.000
tech
Tokentech
Feature activation+0.935
startups
Token startups
Feature activation+1.026
in
Token in
Feature activation+0.874
their
Token their
Feature activation+0.379
portfolio
Token portfolio
Feature activation+0.771
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.315
plenty
Token plenty
Feature activation+0.354
of
Token of
Feature activation+1.011
difficult
Token difficult
Feature activation+0.330
situations
Token situations
Feature activation+1.285
and
Token and
Feature activation+0.218
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
though
Token though
Feature activation+0.000
Arabs
Token Arabs
Feature activation+0.000
have
Token have
Feature activation+0.000
charged
Token charged
Feature activation+0.299
Israeli
Token Israeli
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+1.350
intend
Token intend
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.000
prayer
Token prayer
Feature activation+0.000
with
Token with
Feature activation+0.000
us
Token us
Feature activation+2.458
for
Token for
Feature activation+0.901
a
Token a
Feature activation+1.796
couple
Token couple
Feature activation+1.835
of
Token of
Feature activation+1.419
days
Token days
Feature activation+1.327
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
players
Token players
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.006
running
Tokenrunning
Feature activation+1.030
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.589
in
Token in
Feature activation+1.166
the
Token the
Feature activation+1.657
loos
Token loos
Feature activation+0.000
est
Tokenest
Feature activation+1.521
sense
Token sense
Feature activation+1.498
.
Token.
Feature activation+0.211

INTERVAL 0.497 - 0.993
CONTAINS 0.371%

had
Token had
Feature activation+0.000
researched
Token researched
Feature activation+0.000
IQ
Token IQ
Feature activation+0.598
test
Token test
Feature activation+0.639
websites
Token websites
Feature activation+1.233
herself
Token herself
Feature activation+0.830
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
I
Token I
Feature activation+0.000
rence
Tokenrence
Feature activation+0.000
lit
Token lit
Feature activation+0.000
up
Token up
Feature activation+0.000
Port
Token Port
Feature activation+0.000
man
Tokenman
Feature activation+0.000
Road
Token Road
Feature activation+0.505
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
stunning
Token stunning
Feature activation+0.000
run
Token run
Feature activation+0.000
of
Token of
Feature activation+0.000
had
Token had
Feature activation+0.000
two
Token two
Feature activation+0.473
group
Token group
Feature activation+0.024
victories
Token victories
Feature activation+0.885
in
Token in
Feature activation+0.674
the
Token the
Feature activation+0.886
World
Token World
Feature activation+0.124
Cup
Token Cup
Feature activation+2.197
up
Token up
Feature activation+0.270
to
Token to
Feature activation+1.055
now
Token now
Feature activation+1.133
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
has
Token has
Feature activation+0.000
lasted
Token lasted
Feature activation+0.170
in
Token in
Feature activation+0.846
Tunisia
Token Tunisia
Feature activation+0.930
,
Token,
Feature activation+0.319
but
Token but
Feature activation+0.000
Syria
Token Syria
Feature activation+0.014
and
Token and
Feature activation+0.000
Libya
Token Libya
Feature activation+0.377
in
Token in
Feature activation+0.224
.
Token .
Feature activation+0.000
40
Token40
Feature activation+0.000
S
Token S
Feature activation+0.000
&
Token&
Feature activation+0.000
W
TokenW
Feature activation+0.739
and
Token and
Feature activation+0.000
found
Token found
Feature activation+0.000
it
Token it
Feature activation+0.000
outstanding
Token outstanding
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.497
CONTAINS 99.396%

of
Token of
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
,
Token,
Feature activation+0.000
urging
Token urging
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
cab
Token cab
Feature activation+0.000
service
Token service
Feature activation+0.000
provider
Token provider
Feature activation+0.000
'
Token '
Feature activation+0.000
S
TokenS
Feature activation+0.000
ere
Tokenere
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
Inf
Token Inf
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
was
Token was
Feature activation+0.000
1995
Token 1995
Feature activation+0.000
and
Token and
Feature activation+0.000
Vaughan
Token Vaughan
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
glac
Token glac
Feature activation+0.000
iologist
Tokeniologist
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.000
pubs
Token pubs
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
11
Token 11
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
Yahoo
Token Yahoo
Feature activation+0.000
!
Token!
Feature activation+0.000
buy
Token buy
Feature activation+0.000
out
Tokenout
Feature activation+0.000
was
Token was
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 H9.10: (feature 20261)

TOP ACTIVATIONS
MAX = 4.542

oil
Token oil
Feature activation+0.000
prices
Token prices
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
low
Token low
Feature activation+4.474
far
Token far
Feature activation+3.393
longer
Token longer
Feature activation+1.253
than
Token than
Feature activation+0.000
most
Token most
Feature activation+0.000
expected
Token expected
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
movies
Token movies
Feature activation+0.000
stay
Token stay
Feature activation+0.000
together
Token together
Feature activation+4.405
into
Token into
Feature activation+0.405
the
Token the
Feature activation+0.242
foreseeable
Token foreseeable
Feature activation+0.000
future
Token future
Feature activation+1.342
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
remained
Token remained
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.083
team
Token team
Feature activation+4.108
and
Token and
Feature activation+0.305
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
added
Token added
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
shelters
Token shelters
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.469
open
Token open
Feature activation+4.044
until
Token until
Feature activation+0.000
March
Token March
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
officials
Token officials
Feature activation+0.000
I
Token I
Feature activation+0.000
hope
Token hope
Feature activation+0.000
it
Token it
Feature activation+0.000
remains
Token remains
Feature activation+0.000
that
Token that
Feature activation+1.588
way
Token way
Feature activation+3.923
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Ab
Token Ab
Feature activation+0.000
his
Tokenhis
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
will
Token will
Feature activation+0.018
stay
Token stay
Feature activation+0.657
in
Token in
Feature activation+1.113
prison
Token prison
Feature activation+3.880
,
Token,
Feature activation+0.030
though
Token though
Feature activation+0.000
.
Token.
Feature activation+0.000
Former
Token Former
Feature activation+0.000
prosecutors
Token prosecutors
Feature activation+0.000
The
TokenThe
Feature activation+0.000
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.365
the
Token the
Feature activation+0.367
bar
Token bar
Feature activation+3.830
kissing
Token kissing
Feature activation+1.857
each
Token each
Feature activation+0.055
other
Token other
Feature activation+1.704
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+1.807
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
wish
Token wish
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+1.684
around
Token around
Feature activation+3.635
and
Token and
Feature activation+0.636
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.000
hands
Token hands
Feature activation+0.000
on
Token on
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
that
Token that
Feature activation+0.000
remained
Token remained
Feature activation+0.135
on
Token on
Feature activation+1.668
the
Token the
Feature activation+0.614
books
Token books
Feature activation+3.627
even
Token even
Feature activation+2.555
though
Token though
Feature activation+0.085
they
Token they
Feature activation+0.000
violated
Token violated
Feature activation+0.000
state
Token state
Feature activation+0.000
support
Token support
Feature activation+0.000
she
Token she
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.110
there
Token there
Feature activation+3.592
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ental
Tokenental
Feature activation+0.000
rules
Token rules
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
stays
Token stays
Feature activation+0.181
frozen
Token frozen
Feature activation+1.967
in
Token in
Feature activation+0.324
place
Token place
Feature activation+3.569
for
Token for
Feature activation+1.809
now
Token now
Feature activation+2.050
.
Token.
Feature activation+0.244
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
computers
Token computers
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
open
Token open
Feature activation+3.261
much
Token much
Feature activation+3.489
longer
Token longer
Feature activation+1.030
than
Token than
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
ones
Token ones
Feature activation+0.584
,
Token,
Feature activation+0.017
bronze
Token bronze
Feature activation+0.000
medal
Token medal
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
in
Token in
Feature activation+0.482
Cleveland
Token Cleveland
Feature activation+3.397
and
Token and
Feature activation+0.355
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
league
Token league
Feature activation+0.000
prices
Token prices
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
low
Token low
Feature activation+4.474
far
Token far
Feature activation+3.393
longer
Token longer
Feature activation+1.253
than
Token than
Feature activation+0.000
most
Token most
Feature activation+0.000
expected
Token expected
Feature activation+0.000
.
Token.
Feature activation+0.000
no
Token no
Feature activation+0.000
assurances
Token assurances
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
remain
Token remain
Feature activation+0.211
there
Token there
Feature activation+3.380
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
testing
Token testing
Feature activation+0.000
period
Token period
Feature activation+0.366
.
Token.
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.519
at
Token at
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+3.365
in
Token in
Feature activation+1.187
January
Token January
Feature activation+1.654
window
Token window
Feature activation+0.931
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Many
Token Many
Feature activation+0.000
families
Token families
Feature activation+0.000
have
Token have
Feature activation+0.000
stayed
Token stayed
Feature activation+0.036
here
Token here
Feature activation+3.295
for
Token for
Feature activation+0.999
decades
Token decades
Feature activation+1.307
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
Linux
Token Linux
Feature activation+0.000
computers
Token computers
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
open
Token open
Feature activation+3.261
much
Token much
Feature activation+3.489
longer
Token longer
Feature activation+1.030
than
Token than
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
ones
Token ones
Feature activation+0.584
ceans
Tokenceans
Feature activation+0.000
and
Token and
Feature activation+0.000
hope
Token hope
Feature activation+0.000
it
Token it
Feature activation+0.000
stays
Token stays
Feature activation+0.138
afloat
Token afloat
Feature activation+3.258
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
it
Token it
Feature activation+0.000
hired
Token hired
Feature activation+0.000
Dock
Token Dock
Feature activation+0.000
"
Token "
Feature activation+0.000
Sym
TokenSym
Feature activation+0.000
ptoms
Tokenptoms
Feature activation+0.000
can
Token can
Feature activation+0.000
remain
Token remain
Feature activation+0.461
mild
Token mild
Feature activation+3.243
,
Token,
Feature activation+0.857
worsen
Token worsen
Feature activation+0.041
or
Token or
Feature activation+0.000
,
Token,
Feature activation+0.000
occasionally
Token occasionally
Feature activation+0.000

Top DFA by src position
MAX = 4.778

of
Token of
Feature activation-0.000
Top resid features:
oil
Token oil
Feature activation+0.002
Top resid features:
prices
Token prices
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.030
Top resid features:
have
Token have
Feature activation+0.008
Top resid features:
stayed
Token stayed
Feature activation+4.778
Top resid features:
low
Token low
Feature activation+0.154
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
longer
Token longer
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
end
Token end
Feature activation+0.032
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
movies
Token movies
Feature activation+0.013
Top resid features:
stay
Token stay
Feature activation+4.719
Top resid features:
together
Token together
Feature activation+0.195
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
foreseeable
Token foreseeable
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
May
Token May
Feature activation+0.001
Top resid features:
1
Token 1
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
has
Token has
Feature activation-0.038
Top resid features:
remained
Token remained
Feature activation+4.175
Top resid features:
with
Token with
Feature activation+0.426
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
team
Token team
Feature activation+0.036
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
Most
TokenMost
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
shelters
Token shelters
Feature activation+0.021
Top resid features:
will
Token will
Feature activation+0.074
Top resid features:
remain
Token remain
Feature activation+4.385
Top resid features:
open
Token open
Feature activation+0.089
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
March
Token March
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
hope
Token hope
Feature activation+0.066
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
remains
Token remains
Feature activation+4.166
Top resid features:
that
Token that
Feature activation+0.091
Top resid features:
way
Token way
Feature activation+0.064
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
Ab
Token Ab
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Not
TokenNot
Feature activation+0.003
Top resid features:
everyone
Token everyone
Feature activation+0.010
Top resid features:
will
Token will
Feature activation+0.049
Top resid features:
stay
Token stay
Feature activation+3.664
Top resid features:
in
Token in
Feature activation+0.439
Top resid features:
prison
Token prison
Feature activation+0.195
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
couple
Token couple
Feature activation-0.008
Top resid features:
remained
Token remained
Feature activation+3.384
Top resid features:
at
Token at
Feature activation+0.741
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
bar
Token bar
Feature activation+0.043
Top resid features:
kissing
Token kissing
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.008
Top resid features:
those
Token those
Feature activation+0.020
Top resid features:
who
Token who
Feature activation+0.018
Top resid features:
wish
Token wish
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
stay
Token stay
Feature activation+4.022
Top resid features:
around
Token around
Feature activation+0.216
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
hands
Token hands
Feature activation+0.000
Top resid features:
ordinances
Token ordinances
Feature activation+0.004
Top resid features:
dating
Token dating
Feature activation-0.007
Top resid features:
from
Token from
Feature activation-0.013
Top resid features:
1950
Token 1950
Feature activation-0.007
Top resid features:
that
Token that
Feature activation-0.003
Top resid features:
remained
Token remained
Feature activation+3.940
Top resid features:
on
Token on
Feature activation+0.143
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
books
Token books
Feature activation+0.063
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
support
Token support
Feature activation+0.011
Top resid features:
she
Token she
Feature activation+0.009
Top resid features:
needs
Token needs
Feature activation+0.018
Top resid features:
to
Token to
Feature activation-0.029
Top resid features:
stay
Token stay
Feature activation+3.976
Top resid features:
there
Token there
Feature activation+0.147
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:
M
TokenM
Feature activation+0.000
Top resid features:
certain
Token certain
Feature activation-0.001
Top resid features:
set
Token set
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
rules
Token rules
Feature activation+0.004
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.008
Top resid features:
stays
Token stays
Feature activation+2.737
Top resid features:
frozen
Token frozen
Feature activation+0.828
Top resid features:
in
Token in
Feature activation+0.284
Top resid features:
place
Token place
Feature activation+0.283
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Linux
Token Linux
Feature activation-0.002
Top resid features:
computers
Token computers
Feature activation-0.000
Top resid features:
tend
Token tend
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
stay
Token stay
Feature activation+3.490
Top resid features:
open
Token open
Feature activation+0.458
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
longer
Token longer
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
Windows
Token Windows
Feature activation+0.000
Top resid features:
world
Token world
Feature activation-0.002
Top resid features:
junior
Token junior
Feature activation+0.007
Top resid features:
bronze
Token bronze
Feature activation-0.005
Top resid features:
medal
Token medal
Feature activation+0.002
Top resid features:
ist
Tokenist
Feature activation-0.011
Top resid features:
stayed
Token stayed
Feature activation+2.899
Top resid features:
in
Token in
Feature activation+1.009
Top resid features:
Cleveland
Token Cleveland
Feature activation+0.058
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
won
Token won
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
oil
Token oil
Feature activation-0.007
Top resid features:
prices
Token prices
Feature activation+0.027
Top resid features:
that
Token that
Feature activation+0.020
Top resid features:
have
Token have
Feature activation+0.009
Top resid features:
stayed
Token stayed
Feature activation+3.344
Top resid features:
low
Token low
Feature activation+0.495
Top resid features:
far
Token far
Feature activation+0.038
Top resid features:
longer
Token longer
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.002
Top resid features:
no
Token no
Feature activation-0.002
Top resid features:
assurances
Token assurances
Feature activation-0.011
Top resid features:
it
Token it
Feature activation+0.010
Top resid features:
would
Token would
Feature activation+0.054
Top resid features:
remain
Token remain
Feature activation+3.727
Top resid features:
there
Token there
Feature activation+0.095
Top resid features:
throughout
Token throughout
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
testing
Token testing
Feature activation+0.000
Top resid features:
period
Token period
Feature activation+0.000
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
án
Tokenán
Feature activation+0.002
Top resid features:
che
Tokenche
Feature activation-0.001
Top resid features:
z
Tokenz
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
stay
Token stay
Feature activation+3.035
Top resid features:
at
Token at
Feature activation+0.839
Top resid features:
Arsenal
Token Arsenal
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:
window
Token window
Feature activation+0.000
Top resid features:
towns
Token towns
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Many
Token Many
Feature activation+0.007
Top resid features:
families
Token families
Feature activation+0.028
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
stayed
Token stayed
Feature activation+3.647
Top resid features:
here
Token here
Feature activation+0.096
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
decades
Token decades
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
Linux
Token Linux
Feature activation-0.004
Top resid features:
computers
Token computers
Feature activation+0.005
Top resid features:
tend
Token tend
Feature activation-0.023
Top resid features:
to
Token to
Feature activation+0.034
Top resid features:
stay
Token stay
Feature activation+3.567
Top resid features:
open
Token open
Feature activation+0.193
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
longer
Token longer
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
Windows
Token Windows
Feature activation+0.000
Top resid features:
O
Token O
Feature activation+0.000
Top resid features:
ceans
Tokenceans
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
hope
Token hope
Feature activation+0.007
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
stays
Token stays
Feature activation+3.432
Top resid features:
afloat
Token afloat
Feature activation+0.243
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
So
Token So
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
hired
Token hired
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
"
Token "
Feature activation+0.056
Top resid features:
Sym
TokenSym
Feature activation-0.002
Top resid features:
ptoms
Tokenptoms
Feature activation+0.001
Top resid features:
can
Token can
Feature activation-0.033
Top resid features:
remain
Token remain
Feature activation+3.760
Top resid features:
mild
Token mild
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
worsen
Token worsen
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.04

Head 3: 0.08

Head 4: 0.02

Head 5: 0.05

Head 6: 0.01

Head 7: 0.06

Head 8: 0.02

Head 9: 0.02

Head 10: 0.61

Head 11: 0.03

Positive logits

until3.81

indefinitely3.73

till3.71

until3.51

intact3.10

forever3.08

withstanding3.00

longer3.00

til2.89

untouched2.84

unchanged2.82

despite2.74

uninterrupted2.71

remain2.66

unaffected2.63

remaining2.61

steadfast2.61

persist2.56

persists2.55

longest2.54

Negative logits

interstitial-2.22

naire-1.95

rocal-1.88

collided-1.88

��-1.87

introduction-1.85

Introdu-1.81

uese-1.79

ocious-1.78

eco-1.77

arranted-1.77

catentry-1.73

Rivals-1.69

rupture-1.68

exclaimed-1.67

Suddenly-1.67

Monstrous-1.66

ymes-1.66

anan-1.64

());-1.64

INTERVAL 4.088 - 4.542
CONTAINS 0.000%

the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
movies
Token movies
Feature activation+0.000
stay
Token stay
Feature activation+0.000
together
Token together
Feature activation+4.405
into
Token into
Feature activation+0.405
the
Token the
Feature activation+0.242
foreseeable
Token foreseeable
Feature activation+0.000
future
Token future
Feature activation+1.342
,
Token,
Feature activation+0.000
oil
Token oil
Feature activation+0.000
prices
Token prices
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
low
Token low
Feature activation+4.474
far
Token far
Feature activation+3.393
longer
Token longer
Feature activation+1.253
than
Token than
Feature activation+0.000
most
Token most
Feature activation+0.000
expected
Token expected
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
remained
Token remained
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.083
team
Token team
Feature activation+4.108
and
Token and
Feature activation+0.305
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
added
Token added
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 3.634 - 4.088
CONTAINS 0.001%

I
Token I
Feature activation+0.000
hope
Token hope
Feature activation+0.000
it
Token it
Feature activation+0.000
remains
Token remains
Feature activation+0.000
that
Token that
Feature activation+1.588
way
Token way
Feature activation+3.923
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Ab
Token Ab
Feature activation+0.000
his
Tokenhis
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
The
TokenThe
Feature activation+0.000
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.365
the
Token the
Feature activation+0.367
bar
Token bar
Feature activation+3.830
kissing
Token kissing
Feature activation+1.857
each
Token each
Feature activation+0.055
other
Token other
Feature activation+1.704
affection
Token affection
Feature activation+0.000
ately
Tokenately
Feature activation+1.807
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
wish
Token wish
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+1.684
around
Token around
Feature activation+3.635
and
Token and
Feature activation+0.636
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.000
hands
Token hands
Feature activation+0.000
on
Token on
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
will
Token will
Feature activation+0.018
stay
Token stay
Feature activation+0.657
in
Token in
Feature activation+1.113
prison
Token prison
Feature activation+3.880
,
Token,
Feature activation+0.030
though
Token though
Feature activation+0.000
.
Token.
Feature activation+0.000
Former
Token Former
Feature activation+0.000
prosecutors
Token prosecutors
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
shelters
Token shelters
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.469
open
Token open
Feature activation+4.044
until
Token until
Feature activation+0.000
March
Token March
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
officials
Token officials
Feature activation+0.000

INTERVAL 3.179 - 3.634
CONTAINS 0.002%

rules
Token rules
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
stays
Token stays
Feature activation+0.181
frozen
Token frozen
Feature activation+1.967
in
Token in
Feature activation+0.324
place
Token place
Feature activation+3.569
for
Token for
Feature activation+1.809
now
Token now
Feature activation+2.050
.
Token.
Feature activation+0.244
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
hold
Token hold
Feature activation+0.000
on
Token on
Feature activation+0.061
well
Token well
Feature activation+3.197
but
Token but
Feature activation+0.000
probably
Token probably
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.008
bronze
Token bronze
Feature activation+0.000
medal
Token medal
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
in
Token in
Feature activation+0.482
Cleveland
Token Cleveland
Feature activation+3.397
and
Token and
Feature activation+0.355
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
league
Token league
Feature activation+0.000
Linux
Token Linux
Feature activation+0.000
computers
Token computers
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
open
Token open
Feature activation+3.261
much
Token much
Feature activation+3.489
longer
Token longer
Feature activation+1.030
than
Token than
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
ones
Token ones
Feature activation+0.584
"
Token "
Feature activation+0.000
Sym
TokenSym
Feature activation+0.000
ptoms
Tokenptoms
Feature activation+0.000
can
Token can
Feature activation+0.000
remain
Token remain
Feature activation+0.461
mild
Token mild
Feature activation+3.243
,
Token,
Feature activation+0.857
worsen
Token worsen
Feature activation+0.041
or
Token or
Feature activation+0.000
,
Token,
Feature activation+0.000
occasionally
Token occasionally
Feature activation+0.000

INTERVAL 2.725 - 3.179
CONTAINS 0.002%

body
Token body
Feature activation+0.000
remained
Token remained
Feature activation+0.000
in
Token in
Feature activation+0.122
the
Token the
Feature activation+0.164
outdoor
Token outdoor
Feature activation+0.038
enclosure
Token enclosure
Feature activation+2.846
two
Token two
Feature activation+1.299
hours
Token hours
Feature activation+1.597
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+0.000
)
Token)
Feature activation+0.000
remains
Token remains
Feature activation+0.004
with
Token with
Feature activation+0.000
Bor
Token Bor
Feature activation+0.000
ussia
Tokenussia
Feature activation+0.101
Dortmund
Token Dortmund
Feature activation+2.873
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+0.000
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+0.000
Ir
Token Ir
Feature activation+0.000
barely
Token barely
Feature activation+0.000
enough
Token enough
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
open
Token open
Feature activation+3.033
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
divisive
Token divisive
Feature activation+0.000
computer
Token computer
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.412
uncomp
Token uncomp
Feature activation+0.085
rom
Tokenrom
Feature activation+0.000
ised
Tokenised
Feature activation+3.015
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
s
Tokens
Feature activation+0.000
hold
Token hold
Feature activation+0.000
onto
Token onto
Feature activation+0.000
that
Token that
Feature activation+2.770
optimistic
Token optimistic
Feature activation+1.629
interpretation
Token interpretation
Feature activation+3.064
for
Token for
Feature activation+0.926
a
Token a
Feature activation+0.777
minute
Token minute
Feature activation+0.669
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000

INTERVAL 2.271 - 2.725
CONTAINS 0.006%

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
cover
Token cover
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.000
forward
Token forward
Feature activation+2.411
during
Token during
Feature activation+0.000
firing
Token firing
Feature activation+1.236
since
Token since
Feature activation+0.000
it
Token it
Feature activation+0.000
does
Token does
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Google
Token Google
Feature activation+0.000
had
Token had
Feature activation+0.000
continued
Token continued
Feature activation+0.000
these
Token these
Feature activation+0.429
negotiations
Token negotiations
Feature activation+2.720
and
Token and
Feature activation+0.000
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+0.000
paid
Token paid
Feature activation+0.000
up
Token up
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Aunt
Token Aunt
Feature activation+0.160
May
Token May
Feature activation+2.533
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
ev
Token ev
Feature activation+0.000
icted
Tokenicted
Feature activation+0.000
or
Token or
Feature activation+0.000
will
Token will
Feature activation+0.000
involve
Token involve
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
your
Token your
Feature activation+0.000
fire
Token fire
Feature activation+1.187
team
Tokenteam
Feature activation+2.666
personnel
Token personnel
Feature activation+2.331
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
abducted
Token abducted
Feature activation+0.000
and
Token and
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
hang
Token hang
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+1.257
bit
Token bit
Feature activation+2.498
longer
Token longer
Feature activation+0.662
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.000
the
Token the
Feature activation+0.000
source
Token source
Feature activation+0.000

INTERVAL 1.817 - 2.271
CONTAINS 0.010%

saying
Token saying
Feature activation+0.000
he
Token he
Feature activation+0.000
'll
Token'll
Feature activation+0.000
keep
Token keep
Feature activation+0.000
that
Token that
Feature activation+0.000
plant
Token plant
Feature activation+1.976
open
Token open
Feature activation+1.396
,"
Token,"
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
said
Token said
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
wearer
Token wearer
Feature activation+0.000
can
Token can
Feature activation+0.000
comfortably
Token comfortably
Feature activation+0.000
remain
Token remain
Feature activation+0.010
warm
Token warm
Feature activation+1.877
in
Token in
Feature activation+0.644
sub
Token sub
Feature activation+0.000
-
Token-
Feature activation+0.000
zero
Tokenzero
Feature activation+0.249
temperatures
Token temperatures
Feature activation+1.573
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
serving
Token serving
Feature activation+0.000
kept
Token kept
Feature activation+0.000
UN
Token UN
Feature activation+0.000
M
TokenM
Feature activation+2.002
in
Token in
Feature activation+0.337
sets
Token sets
Feature activation+0.335
and
Token and
Feature activation+0.234
Hilbert
Token Hilbert
Feature activation+0.487
said
Token said
Feature activation+0.000
remain
Token remain
Feature activation+0.000
in
Token in
Feature activation+0.401
the
Token the
Feature activation+0.383
European
Token European
Feature activation+0.406
single
Token single
Feature activation+0.000
market
Token market
Feature activation+2.052
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Rem
TokenRem
Feature activation+0.000
aining
Tokenaining
Feature activation+0.000
stay
Token stay
Feature activation+0.000
up
Token up
Feature activation+2.584
-
Token-
Feature activation+1.069
to
Tokento
Feature activation+0.331
-
Token-
Feature activation+0.434
date
Tokendate
Feature activation+1.821
and
Token and
Feature activation+0.210
reflect
Token reflect
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
law
Token law
Feature activation+0.000

INTERVAL 1.363 - 1.817
CONTAINS 0.026%

to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
our
Token our
Feature activation+0.000
allies
Token allies
Feature activation+0.690
with
Token with
Feature activation+0.243
us
Token us
Feature activation+1.595
,
Token,
Feature activation+0.384
especially
Token especially
Feature activation+0.255
our
Token our
Feature activation+0.000
Western
Token Western
Feature activation+0.000
allies
Token allies
Feature activation+0.102
CONT
Token CONT
Feature activation+0.000
ENT
TokenENT
Feature activation+0.000
Help
Token Help
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
Common
Token Common
Feature activation+0.000
Dreams
Token Dreams
Feature activation+1.741
Alive
Token Alive
Feature activation+0.000
Our
Token Our
Feature activation+0.000
progressive
Token progressive
Feature activation+0.000
news
Token news
Feature activation+0.000
model
Token model
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
deck
Token deck
Feature activation+0.530
mostly
Token mostly
Feature activation+0.494
red
Token red
Feature activation+1.487
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
play
Token play
Feature activation+0.000
Triumph
Token Triumph
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
shrink
Token shrink
Feature activation+1.631
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.778
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.106
following
Token following
Feature activation+0.415
their
Token their
Feature activation+0.172
tradition
Token tradition
Feature activation+1.566
of
Token of
Feature activation+0.000
tink
Token tink
Feature activation+0.000
ering
Tokenering
Feature activation+0.496
,
Token,
Feature activation+0.286
driving
Token driving
Feature activation+0.000

INTERVAL 0.908 - 1.363
CONTAINS 0.052%

been
Token been
Feature activation+0.000
held
Token held
Feature activation+0.000
in
Token in
Feature activation+0.213
contempt
Token contempt
Feature activation+1.079
of
Token of
Feature activation+0.000
Congress
Token Congress
Feature activation+1.128
for
Token for
Feature activation+0.000
refusing
Token refusing
Feature activation+0.000
to
Token to
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Token over
Feature activation+0.000
known
Token known
Feature activation+0.000
to
Token to
Feature activation+0.000
stick
Token stick
Feature activation+0.000
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.919
underdog
Token underdog
Feature activation+1.152
sci
Token sci
Feature activation+0.000
-
Token-
Feature activation+0.000
fi
Tokenfi
Feature activation+0.773
series
Token series
Feature activation+1.677
before
Token before
Feature activation+0.000
an
Token an
Feature activation+0.000
energy
Token energy
Feature activation+0.000
shield
Token shield
Feature activation+0.000
which
Token which
Feature activation+0.000
protects
Token protects
Feature activation+0.000
Lester
Token Lester
Feature activation+1.064
from
Token from
Feature activation+0.000
regular
Token regular
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
not
Token not
Feature activation+0.000
afford
Token afford
Feature activation+0.000
to
Token to
Feature activation+0.000
remain
Token remain
Feature activation+0.000
a
Token a
Feature activation+0.487
colony
Token colony
Feature activation+0.945
of
Token of
Feature activation+0.271
Great
Token Great
Feature activation+0.000
Britain
Token Britain
Feature activation+0.961
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
remains
Token remains
Feature activation+0.000
his
Token his
Feature activation+0.936
priority
Token priority
Feature activation+0.199
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000

INTERVAL 0.454 - 0.908
CONTAINS 0.137%

he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
his
Token his
Feature activation+0.000
base
Token base
Feature activation+0.833
skeptical
Token skeptical
Feature activation+0.687
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
reports
Token reports
Feature activation+0.581
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
March
Token March
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
remains
Token remains
Feature activation+0.000
imprisoned
Token imprisoned
Feature activation+0.856
in
Token in
Feature activation+0.159
Iran
Token Iran
Feature activation+1.148
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Hampshire
Token Hampshire
Feature activation+0.000
still
Token still
Feature activation+0.000
maintains
Token maintains
Feature activation+0.074
such
Token such
Feature activation+0.607
harsh
Token harsh
Feature activation+0.048
penalties
Token penalties
Feature activation+0.902
for
Token for
Feature activation+0.070
simple
Token simple
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
possession
Token possession
Feature activation+0.240
âĢ¦
TokenâĢ¦
Feature activation+0.000
that
Token that
Feature activation+0.000
point
Token point
Feature activation+0.000
.
Token.
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
your
Token your
Feature activation+0.000
keys
Token keys
Feature activation+0.533
and
Token and
Feature activation+0.000
coins
Token coins
Feature activation+0.920
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
hand
Token hand
Feature activation+0.283
exist
Token exist
Feature activation+0.000
only
Token only
Feature activation+0.097
to
Token to
Feature activation+0.000
uphold
Token uphold
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.813
neut
Token neut
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ally
Tokenally
Feature activation+0.450
and
Token and
Feature activation+0.456
fairly
Token fairly
Feature activation+0.433

INTERVAL 0.000 - 0.454
CONTAINS 99.764%

endure
Token endure
Feature activation+0.000
the
Token the
Feature activation+0.142
flooding
Token flooding
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
and
Token and
Feature activation+0.000
know
Token know
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
quite
Token quite
Feature activation+0.000
honestly
Token honestly
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
trans
Token trans
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
through
Token through
Feature activation+0.000
international
Token international
Feature activation+0.000
waters
Token waters
Feature activation+0.000
to
Token to
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
's
Token's
Feature activation+0.000
territorial
Token territorial
Feature activation+0.000
waters
Token waters
Feature activation+0.000
.
Token.
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
,
Token,
Feature activation+0.000
29
Token 29
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
Durham
Token Durham
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Morgan
TokenMorgan
Feature activation+0.000
Anne
Token Anne
Feature activation+0.000
Brooks
Token Brooks
Feature activation+0.000
looks
Token looks
Feature activation+0.000
horrible
Token horrible
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
downloaded
Token downloaded
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token .
Feature activation+0.000
og
Tokenog
Feature activation+0.000
v
Tokenv
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
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 H9.10: (feature 16221)

TOP ACTIVATIONS
MAX = 2.938

mi
Tokenmi
Feature activation+0.000
began
Token began
Feature activation+0.000
working
Token working
Feature activation+0.125
for
Token for
Feature activation+0.146
the
Token the
Feature activation+0.145
facility
Token facility
Feature activation+2.938
in
Token in
Feature activation+1.300
December
Token December
Feature activation+0.908
but
Token but
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
first
Token first
Feature activation+0.000
teased
Token teased
Feature activation+0.000
this
Token this
Feature activation+1.310
custom
Token custom
Feature activation+0.803
's
Token's
Feature activation+1.170
abilities
Token abilities
Feature activation+2.903
on
Token on
Feature activation+0.455
Twitter
Token Twitter
Feature activation+1.006
last
Token last
Feature activation+0.776
week
Token week
Feature activation+0.388
,
Token ,
Feature activation+0.332
el
Tokenel
Feature activation+0.000
osi
Tokenosi
Feature activation+0.000
made
Token made
Feature activation+0.000
headlines
Token headlines
Feature activation+0.691
on
Token on
Feature activation+0.909
Tuesday
Token Tuesday
Feature activation+2.769
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
told
Token told
Feature activation+0.000
CNN
Token CNN
Feature activation+0.000
Gingrich
Token Gingrich
Feature activation+0.000
oon
Tokenoon
Feature activation+0.000
.
Token.
Feature activation+0.000
J
Token J
Feature activation+0.000
oon
Tokenoon
Feature activation+0.000
started
Token started
Feature activation+0.000
programming
Token programming
Feature activation+2.575
since
Token since
Feature activation+0.000
2011
Token 2011
Feature activation+0.540
âĢĶ
Token âĢĶ
Feature activation+0.043
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
he
Token he
Feature activation+0.000
learned
Token learned
Feature activation+0.000
of
Token of
Feature activation+0.083
the
Token the
Feature activation+0.302
allegations
Token allegations
Feature activation+2.527
Monday
Token Monday
Feature activation+0.848
,
Token,
Feature activation+0.591
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
adventures
Token adventures
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
dog
Token dog
Feature activation+0.000
Henry
Token Henry
Feature activation+0.000
-
Token -
Feature activation+2.524
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.130
was
Token was
Feature activation+0.000
five
Token five
Feature activation+0.665
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
league
Token league
Feature activation+0.000
debuted
Token debuted
Feature activation+0.000
the
Token the
Feature activation+0.152
Color
Token Color
Feature activation+0.000
Rush
Token Rush
Feature activation+2.512
uniforms
Token uniforms
Feature activation+2.296
last
Token last
Feature activation+0.785
season
Token season
Feature activation+1.063
,
Token,
Feature activation+0.526
and
Token and
Feature activation+0.058
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
learned
Token learned
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.113
video
Token video
Feature activation+2.476
over
Token over
Feature activation+0.419
the
Token the
Feature activation+0.517
weekend
Token weekend
Feature activation+0.789
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
aut
Tokenaut
Feature activation+0.000
ista
Tokenista
Feature activation+0.000
began
Token began
Feature activation+0.000
wrestling
Token wrestling
Feature activation+2.372
in
Token in
Feature activation+0.256
1999
Token 1999
Feature activation+0.646
,
Token,
Feature activation+0.014
and
Token and
Feature activation+0.000
signed
Token signed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Le
TokenLe
Feature activation+0.000
o
Tokeno
Feature activation+0.000
started
Token started
Feature activation+0.000
the
Token the
Feature activation+0.153
book
Token book
Feature activation+2.352
-
Token -
Feature activation+0.352
about
Token about
Feature activation+0.032
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
boy
Token boy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+0.000
ago
Tokenago
Feature activation+0.000
started
Token started
Feature activation+0.000
gl
Token gl
Feature activation+0.000
iding
Tokeniding
Feature activation+2.338
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
15
Token 15
Feature activation+0.000
and
Token and
Feature activation+0.000
resigned
Token resigned
Feature activation+0.176
from
Token from
Feature activation+0.105
the
Token the
Feature activation+0.492
Mirror
Token Mirror
Feature activation+2.292
in
Token in
Feature activation+1.080
2004
Token 2004
Feature activation+2.308
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Ecuador
Token Ecuador
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
first
Token first
Feature activation+0.000
started
Token started
Feature activation+0.000
adopting
Token adopting
Feature activation+0.000
dollars
Token dollars
Feature activation+2.300
inform
Token inform
Feature activation+0.502
ally
Tokenally
Feature activation+1.523
in
Token in
Feature activation+1.144
an
Token an
Feature activation+0.647
effort
Token effort
Feature activation+0.000
league
Token league
Feature activation+0.000
debuted
Token debuted
Feature activation+0.000
the
Token the
Feature activation+0.152
Color
Token Color
Feature activation+0.000
Rush
Token Rush
Feature activation+2.512
uniforms
Token uniforms
Feature activation+2.296
last
Token last
Feature activation+0.785
season
Token season
Feature activation+1.063
,
Token,
Feature activation+0.526
and
Token and
Feature activation+0.058
will
Token will
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
resigned
Token resigned
Feature activation+0.176
from
Token from
Feature activation+0.105
the
Token the
Feature activation+0.492
Mirror
Token Mirror
Feature activation+2.292
in
Token in
Feature activation+1.080
2004
Token 2004
Feature activation+2.308
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
;
Token;
Feature activation+0.000
he
Token he
Feature activation+0.000
retired
Token retired
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.156
university
Token university
Feature activation+2.271
in
Token in
Feature activation+0.146
1992
Token 1992
Feature activation+1.338
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
also
Token also
Feature activation+0.000
got
Token got
Feature activation+0.000
the
Token the
Feature activation+0.079
idea
Token idea
Feature activation+0.905
for
Token for
Feature activation+0.046
the
Token the
Feature activation+0.568
shop
Token shop
Feature activation+2.239
about
Token about
Feature activation+0.431
12
Token 12
Feature activation+0.966
years
Token years
Feature activation+1.016
ago
Token ago
Feature activation+0.230
,
Token,
Feature activation+0.204
Pence
Token Pence
Feature activation+0.000
drew
Token drew
Feature activation+0.000
headlines
Token headlines
Feature activation+0.546
earlier
Token earlier
Feature activation+0.667
this
Token this
Feature activation+0.520
month
Token month
Feature activation+2.237
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
defended
Token defended
Feature activation+0.000
the
Token the
Feature activation+0.000
department
Token department
Feature activation+0.000
health
Token health
Feature activation+0.000
worker
Token worker
Feature activation+0.000
who
Token who
Feature activation+0.000
acquired
Token acquired
Feature activation+0.000
hepatitis
Token hepatitis
Feature activation+1.310
C
Token C
Feature activation+2.221
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
needle
Token needle
Feature activation+0.000
stick
Token stick
Feature activation+0.000
injury
Token injury
Feature activation+0.099
which
Token which
Feature activation+0.000
began
Token began
Feature activation+0.000
appearing
Token appearing
Feature activation+0.353
on
Token on
Feature activation+0.192
subway
Token subway
Feature activation+0.232
cars
Token cars
Feature activation+2.216
on
Token on
Feature activation+0.870
Monday
Token Monday
Feature activation+0.595
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 2.982

said
Token said
Feature activation+0.026
Top resid features:
Oy
Token Oy
Feature activation+0.003
Top resid features:
ek
Tokenek
Feature activation+0.001
Top resid features:
an
Tokenan
Feature activation+0.002
Top resid features:
mi
Tokenmi
Feature activation+0.013
Top resid features:
began
Token began
Feature activation+2.569
Top resid features:
working
Token working
Feature activation+0.535
Top resid features:
for
Token for
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
facility
Token facility
Feature activation+0.028
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
weather
Token weather
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
company
Token company
Feature activation+0.008
Top resid features:
first
Token first
Feature activation+0.711
Top resid features:
teased
Token teased
Feature activation+2.297
Top resid features:
this
Token this
Feature activation+0.081
Top resid features:
custom
Token custom
Feature activation+0.018
Top resid features:
's
Token's
Feature activation+0.081
Top resid features:
abilities
Token abilities
Feature activation+0.037
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
P
TokenP
Feature activation+0.001
Top resid features:
el
Tokenel
Feature activation+0.001
Top resid features:
osi
Tokenosi
Feature activation+0.018
Top resid features:
made
Token made
Feature activation+0.044
Top resid features:
headlines
Token headlines
Feature activation+2.982
Top resid features:
on
Token on
Feature activation+0.117
Top resid features:
Tuesday
Token Tuesday
Feature activation-0.043
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
J
Token J
Feature activation+0.002
Top resid features:
oon
Tokenoon
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
J
Token J
Feature activation+0.005
Top resid features:
oon
Tokenoon
Feature activation+0.006
Top resid features:
started
Token started
Feature activation+2.647
Top resid features:
programming
Token programming
Feature activation+0.247
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
2011
Token 2011
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
ancy
Tokenancy
Feature activation+0.006
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
told
Token told
Feature activation+0.006
Top resid features:
lawmakers
Token lawmakers
Feature activation+0.010
Top resid features:
he
Token he
Feature activation+0.025
Top resid features:
learned
Token learned
Feature activation+2.466
Top resid features:
of
Token of
Feature activation+0.317
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
allegations
Token allegations
Feature activation+0.024
Top resid features:
Monday
Token Monday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Le
TokenLe
Feature activation+0.001
Top resid features:
o
Tokeno
Feature activation+0.008
Top resid features:
started
Token started
Feature activation+2.325
Top resid features:
the
Token the
Feature activation+0.103
Top resid features:
book
Token book
Feature activation+0.332
Top resid features:
-
Token -
Feature activation+0.009
Top resid features:
about
Token about
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
league
Token league
Feature activation+0.012
Top resid features:
debuted
Token debuted
Feature activation+2.316
Top resid features:
the
Token the
Feature activation+0.443
Top resid features:
Color
Token Color
Feature activation+0.028
Top resid features:
Rush
Token Rush
Feature activation+0.055
Top resid features:
uniforms
Token uniforms
Feature activation+0.000
Top resid features:
last
Token last
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:
He
TokenHe
Feature activation+0.006
Top resid features:
said
Token said
Feature activation+0.007
Top resid features:
he
Token he
Feature activation+0.015
Top resid features:
learned
Token learned
Feature activation+2.083
Top resid features:
about
Token about
Feature activation+0.688
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
video
Token video
Feature activation+0.007
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
B
TokenB
Feature activation-0.001
Top resid features:
aut
Tokenaut
Feature activation+0.003
Top resid features:
ista
Tokenista
Feature activation+0.018
Top resid features:
began
Token began
Feature activation+2.586
Top resid features:
wrestling
Token wrestling
Feature activation+0.142
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
1999
Token 1999
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Le
TokenLe
Feature activation+0.003
Top resid features:
o
Tokeno
Feature activation+0.012
Top resid features:
started
Token started
Feature activation+2.287
Top resid features:
the
Token the
Feature activation+0.311
Top resid features:
book
Token book
Feature activation+0.051
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
about
Token about
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:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
J
TokenJ
Feature activation+0.003
Top resid features:
ago
Tokenago
Feature activation+0.016
Top resid features:
started
Token started
Feature activation+2.527
Top resid features:
gl
Token gl
Feature activation+0.031
Top resid features:
iding
Tokeniding
Feature activation+0.104
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
later
Token later
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
He
TokenHe
Feature activation+0.033
Top resid features:
resigned
Token resigned
Feature activation+2.145
Top resid features:
from
Token from
Feature activation+0.330
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
Mirror
Token Mirror
Feature activation+0.028
Top resid features:
in
Token in
Feature activation+0.104
Top resid features:
2004
Token 2004
Feature activation-0.053
Top resid features:
7
Token7
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.010
Top resid features:
Ecuador
Token Ecuador
Feature activation+0.009
Top resid features:
ians
Tokenians
Feature activation+0.009
Top resid features:
first
Token first
Feature activation+0.507
Top resid features:
started
Token started
Feature activation+1.521
Top resid features:
adopting
Token adopting
Feature activation+0.654
Top resid features:
dollars
Token dollars
Feature activation+0.022
Top resid features:
inform
Token inform
Feature activation+0.000
Top resid features:
ally
Tokenally
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
league
Token league
Feature activation+0.013
Top resid features:
debuted
Token debuted
Feature activation+2.212
Top resid features:
the
Token the
Feature activation+0.299
Top resid features:
Color
Token Color
Feature activation+0.010
Top resid features:
Rush
Token Rush
Feature activation+0.102
Top resid features:
uniforms
Token uniforms
Feature activation+0.056
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
later
Token later
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
He
TokenHe
Feature activation+0.008
Top resid features:
resigned
Token resigned
Feature activation+1.667
Top resid features:
from
Token from
Feature activation+0.698
Top resid features:
the
Token the
Feature activation+0.182
Top resid features:
Mirror
Token Mirror
Feature activation+0.022
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2004
Token 2004
Feature activation+0.000
Top resid features:
Fresno
Token Fresno
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
1958
Token 1958
Feature activation-0.050
Top resid features:
;
Token;
Feature activation+0.020
Top resid features:
he
Token he
Feature activation+0.015
Top resid features:
retired
Token retired
Feature activation+2.209
Top resid features:
from
Token from
Feature activation+0.301
Top resid features:
the
Token the
Feature activation+0.110
Top resid features:
university
Token university
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
1992
Token 1992
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.006
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
I
TokenI
Feature activation+0.003
Top resid features:
got
Token got
Feature activation+0.155
Top resid features:
the
Token the
Feature activation+0.131
Top resid features:
idea
Token idea
Feature activation+1.738
Top resid features:
for
Token for
Feature activation+0.462
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
shop
Token shop
Feature activation+0.007
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
12
Token 12
Feature activation+0.000
Top resid features:
Gov
Token Gov
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Mike
Token Mike
Feature activation+0.001
Top resid features:
Pence
Token Pence
Feature activation+0.013
Top resid features:
drew
Token drew
Feature activation+0.084
Top resid features:
headlines
Token headlines
Feature activation+2.549
Top resid features:
earlier
Token earlier
Feature activation+0.002
Top resid features:
this
Token this
Feature activation-0.002
Top resid features:
month
Token month
Feature activation-0.022
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
include
Token include
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
health
Token health
Feature activation+0.001
Top resid features:
worker
Token worker
Feature activation+0.013
Top resid features:
who
Token who
Feature activation+0.027
Top resid features:
acquired
Token acquired
Feature activation+2.323
Top resid features:
hepatitis
Token hepatitis
Feature activation+0.095
Top resid features:
C
Token C
Feature activation+0.107
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
needle
Token needle
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
ads
Token ads
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
which
Token which
Feature activation+0.015
Top resid features:
began
Token began
Feature activation+1.789
Top resid features:
appearing
Token appearing
Feature activation+0.502
Top resid features:
on
Token on
Feature activation+0.182
Top resid features:
subway
Token subway
Feature activation+0.029
Top resid features:
cars
Token cars
Feature activation+0.023
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.03

Head 3: 0.12

Head 4: 0.02

Head 5: 0.05

Head 6: 0.01

Head 7: 0.07

Head 8: 0.02

Head 9: 0.01

Head 10: 0.61

Head 11: 0.02

Positive logits

shortly4.40

yesterday4.07

earlier4.06

recently3.62

last3.56

after3.53

ago3.47

during3.43

late3.40

early3.29

sometime3.27

AFTER3.13

soon3.08

February3.06

prior3.03

December3.01

afterward3.00

September2.98

before2.97

January2.96

Negative logits

stood-2.34

arest-1.85

utations-1.84

]);-1.81

acceptable-1.76

represent-1.73

`.-1.72

%.-1.72

ernal-1.71

maxwell-1.66

okin-1.66

.):-1.65

Reviewer-1.65

=-=-=-=-=-=-=-=--1.61

taboola-1.60

]).-1.60

ito-1.60

"!-1.58

Locations-1.58

keep-1.57

INTERVAL 2.644 - 2.938
CONTAINS 0.000%

mi
Tokenmi
Feature activation+0.000
began
Token began
Feature activation+0.000
working
Token working
Feature activation+0.125
for
Token for
Feature activation+0.146
the
Token the
Feature activation+0.145
facility
Token facility
Feature activation+2.938
in
Token in
Feature activation+1.300
December
Token December
Feature activation+0.908
but
Token but
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
first
Token first
Feature activation+0.000
teased
Token teased
Feature activation+0.000
this
Token this
Feature activation+1.310
custom
Token custom
Feature activation+0.803
's
Token's
Feature activation+1.170
abilities
Token abilities
Feature activation+2.903
on
Token on
Feature activation+0.455
Twitter
Token Twitter
Feature activation+1.006
last
Token last
Feature activation+0.776
week
Token week
Feature activation+0.388
,
Token ,
Feature activation+0.332
el
Tokenel
Feature activation+0.000
osi
Tokenosi
Feature activation+0.000
made
Token made
Feature activation+0.000
headlines
Token headlines
Feature activation+0.691
on
Token on
Feature activation+0.909
Tuesday
Token Tuesday
Feature activation+2.769
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
told
Token told
Feature activation+0.000
CNN
Token CNN
Feature activation+0.000
Gingrich
Token Gingrich
Feature activation+0.000

INTERVAL 2.350 - 2.644
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
aut
Tokenaut
Feature activation+0.000
ista
Tokenista
Feature activation+0.000
began
Token began
Feature activation+0.000
wrestling
Token wrestling
Feature activation+2.372
in
Token in
Feature activation+0.256
1999
Token 1999
Feature activation+0.646
,
Token,
Feature activation+0.014
and
Token and
Feature activation+0.000
signed
Token signed
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
learned
Token learned
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.113
video
Token video
Feature activation+2.476
over
Token over
Feature activation+0.419
the
Token the
Feature activation+0.517
weekend
Token weekend
Feature activation+0.789
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
he
Token he
Feature activation+0.000
learned
Token learned
Feature activation+0.000
of
Token of
Feature activation+0.083
the
Token the
Feature activation+0.302
allegations
Token allegations
Feature activation+2.527
Monday
Token Monday
Feature activation+0.848
,
Token,
Feature activation+0.591
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
adventures
Token adventures
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
dog
Token dog
Feature activation+0.000
Henry
Token Henry
Feature activation+0.000
-
Token -
Feature activation+2.524
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.130
was
Token was
Feature activation+0.000
five
Token five
Feature activation+0.665
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Le
TokenLe
Feature activation+0.000
o
Tokeno
Feature activation+0.000
started
Token started
Feature activation+0.000
the
Token the
Feature activation+0.153
book
Token book
Feature activation+2.352
-
Token -
Feature activation+0.352
about
Token about
Feature activation+0.032
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
boy
Token boy
Feature activation+0.000

INTERVAL 2.056 - 2.350
CONTAINS 0.002%

which
Token which
Feature activation+0.000
began
Token began
Feature activation+0.000
appearing
Token appearing
Feature activation+0.353
on
Token on
Feature activation+0.192
subway
Token subway
Feature activation+0.232
cars
Token cars
Feature activation+2.216
on
Token on
Feature activation+0.870
Monday
Token Monday
Feature activation+0.595
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Center
Token Center
Feature activation+0.113
of
Token of
Feature activation+0.000
Excellence
Token Excellence
Feature activation+1.658
in
Token in
Feature activation+0.518
Fisheries
Token Fisheries
Feature activation+1.918
Education
Token Education
Feature activation+2.136
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.019
Commission
Token Commission
Feature activation+0.461
on
Token on
Feature activation+0.000
Higher
Token Higher
Feature activation+0.000
league
Token league
Feature activation+0.000
debuted
Token debuted
Feature activation+0.000
the
Token the
Feature activation+0.152
Color
Token Color
Feature activation+0.000
Rush
Token Rush
Feature activation+2.512
uniforms
Token uniforms
Feature activation+2.296
last
Token last
Feature activation+0.785
season
Token season
Feature activation+1.063
,
Token,
Feature activation+0.526
and
Token and
Feature activation+0.058
will
Token will
Feature activation+0.000
Ecuador
Token Ecuador
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
first
Token first
Feature activation+0.000
started
Token started
Feature activation+0.000
adopting
Token adopting
Feature activation+0.000
dollars
Token dollars
Feature activation+2.300
inform
Token inform
Feature activation+0.502
ally
Tokenally
Feature activation+1.523
in
Token in
Feature activation+1.144
an
Token an
Feature activation+0.647
effort
Token effort
Feature activation+0.000
Pence
Token Pence
Feature activation+0.000
drew
Token drew
Feature activation+0.000
headlines
Token headlines
Feature activation+0.546
earlier
Token earlier
Feature activation+0.667
this
Token this
Feature activation+0.520
month
Token month
Feature activation+2.237
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
defended
Token defended
Feature activation+0.000
the
Token the
Feature activation+0.000
department
Token department
Feature activation+0.000

INTERVAL 1.763 - 2.056
CONTAINS 0.005%

of
Token of
Feature activation+0.000
wildlife
Token wildlife
Feature activation+0.115
:
Token:
Feature activation+0.112
it
Token it
Feature activation+0.023
was
Token was
Feature activation+0.041
way
Token way
Feature activation+1.779
back
Token back
Feature activation+0.193
in
Token in
Feature activation+0.604
1900
Token 1900
Feature activation+0.411
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Islands
Token Islands
Feature activation+0.000
were
Token were
Feature activation+0.000
taken
Token taken
Feature activation+0.042
briefly
Token briefly
Feature activation+0.178
by
Token by
Feature activation+0.273
Argentina
Token Argentina
Feature activation+1.886
during
Token during
Feature activation+0.249
its
Token its
Feature activation+0.120
1982
Token 1982
Feature activation+0.000
invasion
Token invasion
Feature activation+0.000
which
Token which
Feature activation+0.000
who
Token who
Feature activation+0.000
learned
Token learned
Feature activation+0.000
of
Token of
Feature activation+0.030
his
Token his
Feature activation+0.204
dem
Token dem
Feature activation+0.000
otion
Tokenotion
Feature activation+1.954
to
Token to
Feature activation+0.000
part
Token part
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.769
player
Token player
Feature activation+0.676
ont
Tokenont
Feature activation+0.000
:
Token:
Feature activation+0.000
I
Token I
Feature activation+0.000
became
Token became
Feature activation+0.000
a
Token a
Feature activation+0.085
Christian
Token Christian
Feature activation+1.786
believer
Token believer
Feature activation+1.788
in
Token in
Feature activation+0.848
1989
Token 1989
Feature activation+1.566
,
Token,
Feature activation+0.983
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
began
Token began
Feature activation+0.345
to
Token to
Feature activation+0.000
perk
Token perk
Feature activation+0.496
up
Token up
Feature activation+2.043
around
Token around
Feature activation+0.982
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.070
February
TokenFebruary
Feature activation+0.855
,
Token,
Feature activation+1.014

INTERVAL 1.469 - 1.763
CONTAINS 0.013%

,
Token,
Feature activation+0.000
whose
Token whose
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
Department
Token Department
Feature activation+0.000
charged
Token charged
Feature activation+0.000
Snowden
Token Snowden
Feature activation+1.544
with
Token with
Feature activation+0.118
leaking
Token leaking
Feature activation+0.091
classified
Token classified
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.132
documents
Token documents
Feature activation+0.123
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
to
Token to
Feature activation+0.000
games
Token games
Feature activation+1.622
through
Token through
Feature activation+0.000
fleeting
Token fleeting
Feature activation+0.000
encounters
Token encounters
Feature activation+0.000
with
Token with
Feature activation+0.000
arcade
Token arcade
Feature activation+0.000
Science
Token Science
Feature activation+0.000
team
Token team
Feature activation+0.000
began
Token began
Feature activation+0.000
developing
Token developing
Feature activation+0.361
initial
Token initial
Feature activation+0.000
models
Token models
Feature activation+1.474
in
Token in
Feature activation+1.165
collaboration
Token collaboration
Feature activation+0.000
with
Token with
Feature activation+0.000
Multi
Token Multi
Feature activation+0.000
Care
TokenCare
Feature activation+0.000
state
Token state
Feature activation+1.042
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.382
s
Tokens
Feature activation+0.288
highest
Token highest
Feature activation+0.000
court
Token court
Feature activation+1.625
after
Token after
Feature activation+0.000
admitting
Token admitting
Feature activation+0.000
to
Token to
Feature activation+0.000
sending
Token sending
Feature activation+0.000
approximately
Token approximately
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
retired
Token retired
Feature activation+0.000
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
job
Token job
Feature activation+1.499
to
Token to
Feature activation+0.015
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.000
one
Token one
Feature activation+0.000
son
Token son
Feature activation+0.148

INTERVAL 1.175 - 1.469
CONTAINS 0.028%

doctor
Token doctor
Feature activation+0.544
ate
Tokenate
Feature activation+0.845
in
Token in
Feature activation+0.467
nat
Token nat
Feature activation+0.000
uro
Tokenuro
Feature activation+0.000
pathy
Tokenpathy
Feature activation+1.340
from
Token from
Feature activation+0.000
Clayton
Token Clayton
Feature activation+0.000
College
Token College
Feature activation+0.579
.
Token.
Feature activation+0.000
Clayton
Token Clayton
Feature activation+0.000
shut
Token shut
Feature activation+0.000
off
Token off
Feature activation+0.162
its
Token its
Feature activation+0.000
primary
Token primary
Feature activation+0.043
data
Token data
Feature activation+0.257
stream
Token stream
Feature activation+1.218
prior
Token prior
Feature activation+0.000
to
Token to
Feature activation+0.000
executing
Token executing
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
International
TokenInternational
Feature activation+0.000
divisions
Token divisions
Feature activation+0.000
over
Token over
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
surfaced
Token surfaced
Feature activation+0.346
anew
Token anew
Feature activation+1.192
at
Token at
Feature activation+0.758
a
Token a
Feature activation+0.386
Munich
Token Munich
Feature activation+0.000
conference
Token conference
Feature activation+0.215
where
Token where
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Yas
Token Yas
Feature activation+0.000
Marina
Token Marina
Feature activation+1.118
Circuit
Token Circuit
Feature activation+1.425
in
Token in
Feature activation+0.645
control
Token control
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
com
Tokencom
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
a
Token a
Feature activation+0.618
new
Token new
Feature activation+0.000
structure
Token structure
Feature activation+1.402
in
Token in
Feature activation+1.199
2005
Token 2005
Feature activation+1.016
that
Token that
Feature activation+0.000
meant
Token meant
Feature activation+0.000
competitors
Token competitors
Feature activation+0.000
such
Token such
Feature activation+0.000

INTERVAL 0.881 - 1.175
CONTAINS 0.077%

leaking
Token leaking
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
crashed
Token crashed
Feature activation+0.000
tanker
Token tanker
Feature activation+0.000
,
Token,
Feature activation+0.961
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
caught
Token caught
Feature activation+0.000
fire
Token fire
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
24
Token 24
Feature activation+0.000
,
Token,
Feature activation+0.000
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.250
August
Token August
Feature activation+1.112
2006
Token 2006
Feature activation+1.226
after
Token after
Feature activation+0.000
taking
Token taking
Feature activation+0.000
an
Token an
Feature activation+0.000
overdose
Token overdose
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
saw
Token saw
Feature activation+0.000
this
Token this
Feature activation+0.101
story
Token story
Feature activation+1.011
posted
Token posted
Feature activation+0.259
everywhere
Token everywhere
Feature activation+0.352
on
Token on
Feature activation+0.223
my
Token my
Feature activation+0.000
FB
Token FB
Feature activation+0.128
202
Token 202
Feature activation+0.000
(
Token (
Feature activation+0.000
M
TokenM
Feature activation+0.000
d
Tokend
Feature activation+0.086
.
Token.
Feature activation+0.425
2001
Token 2001
Feature activation+1.116
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
I
Token I
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
form
Token form
Feature activation+0.000
processing
Token processing
Feature activation+0.854
in
Token in
Feature activation+0.967
the
Token the
Feature activation+0.000
Moose
Token Moose
Feature activation+0.000
IRC
Token IRC
Feature activation+0.000
channel
Token channel
Feature activation+0.308
recently
Token recently
Feature activation+0.000

INTERVAL 0.588 - 0.881
CONTAINS 0.200%

his
Token his
Feature activation+0.263
first
Token first
Feature activation+0.407
pro
Token pro
Feature activation+0.000
appearance
Token appearance
Feature activation+0.491
last
Token last
Feature activation+0.450
summer
Token summer
Feature activation+0.700
,
Token,
Feature activation+0.295
but
Token but
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
miles
Token miles
Feature activation+0.000
north
Token north
Feature activation+0.000
of
Token of
Feature activation+0.000
Pret
Token Pret
Feature activation+0.000
oria
Tokenoria
Feature activation+0.000
,
Token,
Feature activation+0.660
after
Token after
Feature activation+0.000
her
Token her
Feature activation+0.000
teenage
Token teenage
Feature activation+0.000
son
Token son
Feature activation+0.000
,
Token,
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
to
Token to
Feature activation+0.000
defend
Token defend
Feature activation+0.062
the
Token the
Feature activation+0.000
Christmas
Token Christmas
Feature activation+0.000
raises
Token raises
Feature activation+0.746
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.058
were
Token were
Feature activation+0.126
announced
Token announced
Feature activation+0.161
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
Austral
TokenAustral
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
voted
Token voted
Feature activation+0.000
no
Token no
Feature activation+0.822
too
Token too
Feature activation+0.862
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Anglic
Token Anglic
Feature activation+0.000
an
Tokenan
Feature activation+0.000
church
Token church
Feature activation+0.000
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
down
Token down
Feature activation+0.093
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.755
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.010
was
Token was
Feature activation+0.000
alerted
Token alerted
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.294 - 0.588
CONTAINS 0.544%

an
Token an
Feature activation+0.000
adversary
Token adversary
Feature activation+0.000
that
Token that
Feature activation+0.000
came
Token came
Feature activation+0.000
at
Token at
Feature activation+0.000
our
Token our
Feature activation+0.395
expense
Token expense
Feature activation+0.194
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
history
Token history
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Wikipedia
TokenWikipedia
Feature activation+0.000
officially
Token officially
Feature activation+0.000
launched
Token launched
Feature activation+0.398
on
Token on
Feature activation+0.565
15
Token 15
Feature activation+0.037
January
Token January
Feature activation+0.151
2001
Token 2001
Feature activation+0.979
,
Token,
Feature activation+0.194
,"
Token,"
Feature activation+0.000
was
Token was
Feature activation+0.000
launched
Token launched
Feature activation+0.000
four
Token four
Feature activation+0.721
months
Token months
Feature activation+0.492
ago
Token ago
Feature activation+0.445
to
Token to
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.386
t
Tokent
Feature activation+0.613
the
Token the
Feature activation+0.229
case
Token case
Feature activation+0.277
in
Token in
Feature activation+0.182
2016
Token 2016
Feature activation+0.000
The
TokenThe
Feature activation+0.000
job
Token job
Feature activation+0.000
was
Token was
Feature activation+0.000
ret
Token ret
Feature activation+0.000
endered
Tokenendered
Feature activation+0.260
in
Token in
Feature activation+0.497
January
Token January
Feature activation+0.494
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.000
soon
Token soon
Feature activation+0.000
after
Token after
Feature activation+0.000

INTERVAL 0.000 - 0.294
CONTAINS 99.130%

My
Token My
Feature activation+0.000
ak
Token ak
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
ceased
Token ceased
Feature activation+0.187
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
finally
Token finally
Feature activation+0.000
got
Token got
Feature activation+0.000
off
Token off
Feature activation+0.000
what
Token what
Feature activation+0.000
places
Token places
Feature activation+0.000
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
places
Token places
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
finding
Token finding
Feature activation+0.000
in
Token in
Feature activation+0.000
aff
Token aff
Feature activation+0.000
ording
Tokenording
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
-
Token-
Feature activation+0.000
of
Tokenof
Feature activation+0.000
-
Token-
Feature activation+0.000
living
Tokenliving
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
om
Tokenom
Feature activation+0.000
ichi
Tokenichi
Feature activation+0.000
Dock
Token Dock
Feature activation+0.000
yard
Tokenyard
Feature activation+0.000
Yard
Token Yard
Feature activation+0.000
number
Token number
Feature activation+0.000
:
Token:
Feature activation+0.000
118
Token 118
Feature activation+0.000
Laun
Token Laun
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
sequence
Token sequence
Feature activation+0.000
or
Token or
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
and
Token and
Feature activation+0.000
retrieve
Token retrieve
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