H1.6 top features

Top feature 0 in H1.6: (feature 12667)

TOP ACTIVATIONS
MAX = 3.110

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.120
not
Token not
Feature activation+0.000
referring
Token referring
Feature activation+3.110
to
Token to
Feature activation+0.080
their
Token their
Feature activation+0.000
slaves
Token slaves
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.085
)
Token )
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Greek
Token Greek
Feature activation+0.000
word
Token word
Feature activation+0.146
meaning
Token meaning
Feature activation+2.824
"
Token "
Feature activation+1.696
character
Tokencharacter
Feature activation+0.016
"
Token"
Feature activation+1.072
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+1.388
this
Token this
Feature activation+0.000
word
Token word
Feature activation+0.684
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+2.813
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
of
Token of
Feature activation+0.000
music
Token music
Feature activation+0.000
el
Tokenel
Feature activation+0.000
k
Tokenk
Feature activation+0.000
"
Token"
Feature activation+0.736
remained
Token remained
Feature activation+0.000
in
Token in
Feature activation+0.000
usage
Token usage
Feature activation+2.738
because
Token because
Feature activation+0.123
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
existence
Token existence
Feature activation+0.000
in
Token in
Feature activation+0.000
The
TokenThe
Feature activation+0.000
word
Token word
Feature activation+0.000
karma
Token karma
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+2.726
in
Token in
Feature activation+0.169
different
Token different
Feature activation+0.197
contexts
Token contexts
Feature activation+0.817
.
Token.
Feature activation+0.000
Y
Token Y
Feature activation+0.011
w
Tokenw
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
zing
Tokenzing
Feature activation+0.000
,"
Token,"
Feature activation+0.000
which
Token which
Feature activation+0.000
refers
Token refers
Feature activation+2.693
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
common
Token common
Feature activation+0.000
form
Token form
Feature activation+0.000
of
Token of
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
reference
Token reference
Feature activation+1.366
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
meaning
Token meaning
Feature activation+2.518
became
Token became
Feature activation+0.000
rather
Token rather
Feature activation+0.000
vague
Token vague
Feature activation+0.214
to
Token to
Feature activation+0.000
most
Token most
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.291
61
Token 61
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.150
usage
Token usage
Feature activation+2.433
as
Token as
Feature activation+0.384
a
Token a
Feature activation+0.000
trans
Token trans
Feature activation+0.175
itive
Tokenitive
Feature activation+0.185
verb
Token verb
Feature activation+1.190
most
Token most
Feature activation+0.000
general
Token general
Feature activation+0.061
sense
Token sense
Feature activation+0.380
,
Token,
Feature activation+0.000
karma
Token karma
Feature activation+0.000
refers
Token refers
Feature activation+2.411
to
Token to
Feature activation+0.000
any
Token any
Feature activation+0.000
action
Token action
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
What
Token What
Feature activation+0.000
transition
Token transition
Feature activation+0.000
phrases
Token phrases
Feature activation+0.000
did
Token did
Feature activation+0.000
they
Token they
Feature activation+0.000
use
Token use
Feature activation+2.326
?
Token?
Feature activation+0.000
Any
Token Any
Feature activation+0.000
sentence
Token sentence
Feature activation+0.009
fragments
Token fragments
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token"
Feature activation+1.072
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+2.106
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+2.320
the
Token the
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
or
Token or
Feature activation+0.000
ideals
Token ideals
Feature activation+0.000
loses
Token loses
Feature activation+0.068
all
Token all
Feature activation+0.000
meaning
Token meaning
Feature activation+2.069
in
Token in
Feature activation+0.085
the
Token the
Feature activation+0.053
context
Token context
Feature activation+2.213
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
did
Token did
Feature activation+0.013
when
Token when
Feature activation+0.000
G
TokenG
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Cont
Token Cont
Feature activation+0.000
roversial
Tokenroversial
Feature activation+0.000
words
Token words
Feature activation+0.000
spoken
Token spoken
Feature activation+2.192
by
Token by
Feature activation+0.000
kids
Token kids
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
school
Token school
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
word
Token word
Feature activation+0.236
's
Token's
Feature activation+0.000
use
Token use
Feature activation+2.167
in
Token in
Feature activation+0.000
rhetoric
Token rhetoric
Feature activation+0.000
is
Token is
Feature activation+0.000
closely
Token closely
Feature activation+0.011
based
Token based
Feature activation+0.000
add
Tokenadd
Feature activation+0.000
ow
Tokenow
Feature activation+0.000
'
Token'
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
context
Token context
Feature activation+2.159
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Madd
Token Madd
Feature activation+0.000
reserved
Token reserved
Feature activation+0.000
word
Token word
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+2.153
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000
argument
Token argument
Feature activation+0.000
name
Token name
Feature activation+0.000
sort
Token sort
Feature activation+0.161
them
Token them
Feature activation+0.040
by
Token by
Feature activation+0.000
frequency
Token frequency
Feature activation+0.702
of
Token of
Feature activation+0.000
usage
Token usage
Feature activation+2.148
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
take
Token take
Feature activation+0.055
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
the
Token the
Feature activation+0.000
words
Token words
Feature activation+0.000
and
Token and
Feature activation+0.000
phrases
Token phrases
Feature activation+0.000
I
Token I
Feature activation+0.000
use
Token use
Feature activation+2.123
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
casual
Token casual
Feature activation+0.000
"
Token "
Feature activation+1.696
character
Tokencharacter
Feature activation+0.016
"
Token"
Feature activation+1.072
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+2.106
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+2.320
the
Token the
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
completely
Token completely
Feature activation+0.024
inappropriate
Token inappropriate
Feature activation+0.322
and
Token and
Feature activation+0.000
loses
Token loses
Feature activation+0.068
all
Token all
Feature activation+0.000
meaning
Token meaning
Feature activation+2.069
in
Token in
Feature activation+0.085
the
Token the
Feature activation+0.053
context
Token context
Feature activation+2.213
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000

Top DFA by src position
MAX = 3.602

.
Token.
Feature activation-0.004
Top resid features:
When
Token When
Feature activation+0.006
Top resid features:
they
Token they
Feature activation+0.006
Top resid features:
used
Token used
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
phrase
Token phrase
Feature activation+3.543
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
âĢ
Token âĢ
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation+0.016
Top resid features:
all
Tokenall
Feature activation+0.006
Top resid features:
men
Token men
Feature activation+0.037
Top resid features:
:
Token:
Feature activation+0.048
Top resid features:
)
Token )
Feature activation+0.026
Top resid features:
is
Token is
Feature activation+0.068
Top resid features:
a
Token a
Feature activation+0.059
Top resid features:
Greek
Token Greek
Feature activation+0.127
Top resid features:
word
Token word
Feature activation+3.602
Top resid features:
meaning
Token meaning
Feature activation+0.157
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
character
Tokencharacter
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.024
Top resid features:
Greeks
Token Greeks
Feature activation+0.065
Top resid features:
also
Token also
Feature activation+0.005
Top resid features:
used
Token used
Feature activation+0.051
Top resid features:
this
Token this
Feature activation+0.045
Top resid features:
word
Token word
Feature activation+1.844
Top resid features:
to
Token to
Feature activation+0.131
Top resid features:
refer
Token refer
Feature activation+0.070
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
old
Token old
Feature activation+0.009
Top resid features:
.[
Token.[
Feature activation+0.050
Top resid features:
7
Token7
Feature activation+0.009
Top resid features:
]
Token]
Feature activation-0.021
Top resid features:
The
Token The
Feature activation+0.021
Top resid features:
word
Token word
Feature activation+3.506
Top resid features:
"
Token "
Feature activation+0.065
Top resid features:
el
Tokenel
Feature activation+0.005
Top resid features:
k
Tokenk
Feature activation+0.007
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
remained
Token remained
Feature activation+0.048
Top resid features:
ata
Tokenata
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
The
TokenThe
Feature activation+0.016
Top resid features:
word
Token word
Feature activation+3.294
Top resid features:
karma
Token karma
Feature activation+0.078
Top resid features:
is
Token is
Feature activation+0.134
Top resid features:
also
Token also
Feature activation+0.053
Top resid features:
used
Token used
Feature activation+0.090
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
n
Tokenn
Feature activation-0.013
Top resid features:
zer
Tokenzer
Feature activation+0.011
Top resid features:
,"
Token,"
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
German
Token German
Feature activation+0.027
Top resid features:
word
Token word
Feature activation+3.492
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
"
Token "
Feature activation+0.050
Top resid features:
w
Tokenw
Feature activation-0.013
Top resid features:
alt
Tokenalt
Feature activation+0.019
Top resid features:
zing
Tokenzing
Feature activation+0.062
Top resid features:
old
Token old
Feature activation+0.002
Top resid features:
.[
Token.[
Feature activation+0.005
Top resid features:
7
Token7
Feature activation-0.002
Top resid features:
]
Token]
Feature activation-0.006
Top resid features:
The
Token The
Feature activation+0.008
Top resid features:
word
Token word
Feature activation+2.866
Top resid features:
"
Token "
Feature activation+0.022
Top resid features:
el
Tokenel
Feature activation-0.001
Top resid features:
k
Tokenk
Feature activation-0.005
Top resid features:
"
Token"
Feature activation+0.007
Top resid features:
remained
Token remained
Feature activation+0.008
Top resid features:
arrest
Token arrest
Feature activation-0.026
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
word
Token word
Feature activation+1.769
Top resid features:
âĢ
Token âĢ
Feature activation+0.007
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
take
Tokentake
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.011
Top resid features:
ata
Tokenata
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
word
Token word
Feature activation+3.207
Top resid features:
karma
Token karma
Feature activation+0.010
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
also
Token also
Feature activation-0.005
Top resid features:
used
Token used
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
read
Token read
Feature activation+0.070
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
What
Token What
Feature activation+0.025
Top resid features:
transition
Token transition
Feature activation+0.046
Top resid features:
phrases
Token phrases
Feature activation+1.899
Top resid features:
did
Token did
Feature activation+0.100
Top resid features:
they
Token they
Feature activation+0.079
Top resid features:
use
Token use
Feature activation+0.035
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Any
Token Any
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.014
Top resid features:
)
Token )
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
Greek
Token Greek
Feature activation+0.089
Top resid features:
word
Token word
Feature activation+2.891
Top resid features:
meaning
Token meaning
Feature activation+0.153
Top resid features:
"
Token "
Feature activation+0.075
Top resid features:
character
Tokencharacter
Feature activation+0.085
Top resid features:
"
Token"
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.051
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
after
Token after
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
while
Token while
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
word
Token word
Feature activation+2.111
Top resid features:
becomes
Token becomes
Feature activation+0.022
Top resid features:
completely
Token completely
Feature activation+0.029
Top resid features:
inappropriate
Token inappropriate
Feature activation+0.083
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
loses
Token loses
Feature activation+0.027
Top resid features:
BUR
TokenBUR
Feature activation+0.015
Top resid features:
G
TokenG
Feature activation+0.009
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.043
Top resid features:
Cont
Token Cont
Feature activation+0.030
Top resid features:
roversial
Tokenroversial
Feature activation+0.060
Top resid features:
words
Token words
Feature activation+3.109
Top resid features:
spoken
Token spoken
Feature activation-0.108
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
kids
Token kids
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
compelling
Token compelling
Feature activation+0.015
Top resid features:
way
Token way
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
word
Token word
Feature activation+1.426
Top resid features:
's
Token's
Feature activation+0.112
Top resid features:
use
Token use
Feature activation+0.026
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
rhetoric
Token rhetoric
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
tem
Token tem
Feature activation+0.012
Top resid features:
erity
Tokenerity
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
type
Token type
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
word
Token word
Feature activation+2.746
Top resid features:
'
Token '
Feature activation+0.028
Top resid features:
M
TokenM
Feature activation+0.043
Top resid features:
add
Tokenadd
Feature activation+0.027
Top resid features:
ow
Tokenow
Feature activation+0.014
Top resid features:
'
Token'
Feature activation-0.023
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.038
Top resid features:
t
Tokent
Feature activation-0.019
Top resid features:
a
Token a
Feature activation+0.039
Top resid features:
reserved
Token reserved
Feature activation+0.044
Top resid features:
word
Token word
Feature activation+2.875
Top resid features:
it
Token it
Feature activation+0.062
Top resid features:
may
Token may
Feature activation+0.090
Top resid features:
be
Token be
Feature activation+0.123
Top resid features:
used
Token used
Feature activation+0.192
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Focus
TokenFocus
Feature activation-0.010
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
most
Token most
Feature activation+0.006
Top resid features:
common
Token common
Feature activation+0.010
Top resid features:
words
Token words
Feature activation+0.853
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
D
TokenD
Feature activation-0.007
Top resid features:
iction
Tokeniction
Feature activation+0.014
Top resid features:
aries
Tokenaries
Feature activation+0.043
Top resid features:
world
Token world
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
sometimes
Token sometimes
Feature activation+0.042
Top resid features:
affect
Token affect
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
words
Token words
Feature activation+1.567
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
phrases
Token phrases
Feature activation+1.329
Top resid features:
I
Token I
Feature activation+0.092
Top resid features:
use
Token use
Feature activation+0.007
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.020
Top resid features:
)
Token )
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
Greek
Token Greek
Feature activation+0.085
Top resid features:
word
Token word
Feature activation+2.642
Top resid features:
meaning
Token meaning
Feature activation+0.199
Top resid features:
"
Token "
Feature activation+0.082
Top resid features:
character
Tokencharacter
Feature activation+0.068
Top resid features:
"
Token"
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.074
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
after
Token after
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
while
Token while
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
word
Token word
Feature activation+1.390
Top resid features:
becomes
Token becomes
Feature activation+0.032
Top resid features:
completely
Token completely
Feature activation+0.040
Top resid features:
inappropriate
Token inappropriate
Feature activation+0.104
Top resid features:
and
Token and
Feature activation+0.037
Top resid features:
loses
Token loses
Feature activation+0.078
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.04

Head 3: 0.01

Head 4: 0.04

Head 5: 0.08

Head 6: 0.56

Head 7: 0.05

Head 8: 0.02

Head 9: 0.02

Head 10: 0.03

Head 11: 0.08

Positive logits

uttered2.35

phrase2.22

abbre2.18

acronym2.14

phrases2.11

pronounce2.09

Liter1.99

utter1.96

Twain1.94

unciation1.90

م1.88

abbrevi1.88

stereotypes1.87

oons1.85

tymology1.84

Latin1.83

English1.83

classics1.82

204391.81

Adult1.77

Negative logits

ascular-2.07

pending-2.00

indemn-1.84

payroll-1.81

feasibility-1.77

servicing-1.72

Frey-1.69

staffing-1.69

jriwal-1.69

etheus-1.69

compensated-1.69

perimeter-1.69

compensation-1.68

pri-1.67

pipeline-1.67

cleanup-1.65

planned-1.64

managing-1.64

shutdown-1.63

confidential-1.63

INTERVAL 2.799 - 3.110
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.120
not
Token not
Feature activation+0.000
referring
Token referring
Feature activation+3.110
to
Token to
Feature activation+0.080
their
Token their
Feature activation+0.000
slaves
Token slaves
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.085
)
Token )
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Greek
Token Greek
Feature activation+0.000
word
Token word
Feature activation+0.146
meaning
Token meaning
Feature activation+2.824
"
Token "
Feature activation+1.696
character
Tokencharacter
Feature activation+0.016
"
Token"
Feature activation+1.072
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+1.388
this
Token this
Feature activation+0.000
word
Token word
Feature activation+0.684
to
Token to
Feature activation+0.000
refer
Token refer
Feature activation+2.813
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
of
Token of
Feature activation+0.000
music
Token music
Feature activation+0.000

INTERVAL 2.488 - 2.799
CONTAINS 0.000%

el
Tokenel
Feature activation+0.000
k
Tokenk
Feature activation+0.000
"
Token"
Feature activation+0.736
remained
Token remained
Feature activation+0.000
in
Token in
Feature activation+0.000
usage
Token usage
Feature activation+2.738
because
Token because
Feature activation+0.123
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
existence
Token existence
Feature activation+0.000
in
Token in
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
reference
Token reference
Feature activation+1.366
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
meaning
Token meaning
Feature activation+2.518
became
Token became
Feature activation+0.000
rather
Token rather
Feature activation+0.000
vague
Token vague
Feature activation+0.214
to
Token to
Feature activation+0.000
most
Token most
Feature activation+0.000
w
Tokenw
Feature activation+0.000
alt
Tokenalt
Feature activation+0.000
zing
Tokenzing
Feature activation+0.000
,"
Token,"
Feature activation+0.000
which
Token which
Feature activation+0.000
refers
Token refers
Feature activation+2.693
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
common
Token common
Feature activation+0.000
form
Token form
Feature activation+0.000
of
Token of
Feature activation+0.000
The
TokenThe
Feature activation+0.000
word
Token word
Feature activation+0.000
karma
Token karma
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+2.726
in
Token in
Feature activation+0.169
different
Token different
Feature activation+0.197
contexts
Token contexts
Feature activation+0.817
.
Token.
Feature activation+0.000
Y
Token Y
Feature activation+0.011

INTERVAL 2.177 - 2.488
CONTAINS 0.001%

"
Token"
Feature activation+1.072
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+2.106
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+2.320
the
Token the
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
or
Token or
Feature activation+0.000
ideals
Token ideals
Feature activation+0.000
loses
Token loses
Feature activation+0.068
all
Token all
Feature activation+0.000
meaning
Token meaning
Feature activation+2.069
in
Token in
Feature activation+0.085
the
Token the
Feature activation+0.053
context
Token context
Feature activation+2.213
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
did
Token did
Feature activation+0.013
when
Token when
Feature activation+0.000
most
Token most
Feature activation+0.000
general
Token general
Feature activation+0.061
sense
Token sense
Feature activation+0.380
,
Token,
Feature activation+0.000
karma
Token karma
Feature activation+0.000
refers
Token refers
Feature activation+2.411
to
Token to
Feature activation+0.000
any
Token any
Feature activation+0.000
action
Token action
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
G
TokenG
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Cont
Token Cont
Feature activation+0.000
roversial
Tokenroversial
Feature activation+0.000
words
Token words
Feature activation+0.000
spoken
Token spoken
Feature activation+2.192
by
Token by
Feature activation+0.000
kids
Token kids
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
school
Token school
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.291
61
Token 61
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.150
usage
Token usage
Feature activation+2.433
as
Token as
Feature activation+0.384
a
Token a
Feature activation+0.000
trans
Token trans
Feature activation+0.175
itive
Tokenitive
Feature activation+0.185
verb
Token verb
Feature activation+1.190

INTERVAL 1.866 - 2.177
CONTAINS 0.002%

morals
Token morals
Feature activation+0.000
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
]
Token]
Feature activation+0.000
Early
Token Early
Feature activation+0.000
Greek
Token Greek
Feature activation+1.916
stories
Token stories
Feature activation+0.000
of
Token of
Feature activation+0.000
Or
Token Or
Feature activation+0.000
pheus
Tokenpheus
Feature activation+0.000
exhibit
Token exhibit
Feature activation+0.000
ill
Token ill
Feature activation+0.000
-
Token-
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
phrases
Token phrases
Feature activation+0.057
referred
Token referred
Feature activation+2.054
to
Token to
Feature activation+0.000
Keystone
Token Keystone
Feature activation+0.000
XL
Token XL
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
Jim
Token Jim
Feature activation+0.000
Corn
Token Corn
Feature activation+0.000
ette
Tokenette
Feature activation+0.000
once
Token once
Feature activation+0.000
phr
Token phr
Feature activation+0.000
ased
Tokenased
Feature activation+2.021
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
where
Tokenwhere
Feature activation+0.000
sort
Token sort
Feature activation+0.161
them
Token them
Feature activation+0.040
by
Token by
Feature activation+0.000
frequency
Token frequency
Feature activation+0.702
of
Token of
Feature activation+0.000
usage
Token usage
Feature activation+2.148
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
take
Token take
Feature activation+0.055
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
reserved
Token reserved
Feature activation+0.000
word
Token word
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+2.153
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000
argument
Token argument
Feature activation+0.000
name
Token name
Feature activation+0.000

INTERVAL 1.555 - 1.866
CONTAINS 0.002%

atching
Tokenatching
Feature activation+0.000
a
Token a
Feature activation+0.000
plan
Token plan
Feature activation+0.000
to
Token to
Feature activation+0.000
egg
Token egg
Feature activation+0.000
mean
Token mean
Feature activation+1.654
old
Token old
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Chapter
TokenChapter
Feature activation+0.000
Text
Token Text
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
an
Token an
Feature activation+0.000
Irish
Token Irish
Feature activation+0.312
noun
Token noun
Feature activation+0.243
and
Token and
Feature activation+0.000
verb
Token verb
Feature activation+0.524
used
Token used
Feature activation+1.693
in
Token in
Feature activation+0.000
H
Token H
Feature activation+0.078
iber
Tokeniber
Feature activation+0.000
no
Tokenno
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Token a
Feature activation+0.000
System
Token System
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
being
Token being
Feature activation+0.000
used
Token used
Feature activation+1.567
here
Token here
Feature activation+0.158
on
Token on
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
but
Token but
Feature activation+0.000
on
Token on
Feature activation+0.000
what
Token what
Feature activation+0.000
happened
Token happened
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
He
Token He
Feature activation+0.000
means
Token means
Feature activation+1.657
EX
Token EX
Feature activation+0.000
ACT
TokenACT
Feature activation+0.000
LY
TokenLY
Feature activation+0.000
that
Token that
Feature activation+0.029
)?
Token)?
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Greek
Token Greek
Feature activation+0.000
word
Token word
Feature activation+0.146
meaning
Token meaning
Feature activation+2.824
"
Token "
Feature activation+1.696
character
Tokencharacter
Feature activation+0.016
"
Token"
Feature activation+1.072
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+2.106

INTERVAL 1.244 - 1.555
CONTAINS 0.002%

speakers
Token speakers
Feature activation+1.210
of
Token of
Feature activation+0.000
English
Token English
Feature activation+0.746
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
used
Token used
Feature activation+1.476
"
Token "
Feature activation+0.574
el
Tokenel
Feature activation+0.000
k
Tokenk
Feature activation+0.000
"
Token"
Feature activation+0.338
to
Token to
Feature activation+0.000
every
Token every
Feature activation+0.000
single
Token single
Feature activation+0.000
sentence
Token sentence
Feature activation+0.097
where
Token where
Feature activation+0.000
I
Token I
Feature activation+0.000
use
Token use
Feature activation+1.388
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
could
Token could
Feature activation+0.000
get
Token get
Feature activation+0.000
away
Token away
Feature activation+0.000
with
Token with
Feature activation+0.000
referring
Token referring
Feature activation+1.532
to
Token to
Feature activation+0.000
today
Token today
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
know
Token know
Feature activation+0.623
to
Token to
Feature activation+0.000
whom
Token whom
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
referring
Token referring
Feature activation+1.248
.
Token.
Feature activation+0.000
S
Token S
Feature activation+0.000
ibling
Tokenibling
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.000
sampling
Token sampling
Feature activation+0.000
the
Token the
Feature activation+0.000
syll
Token syll
Feature activation+0.177
able
Tokenable
Feature activation+1.403
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
oh
Tokenoh
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 0.933 - 1.244
CONTAINS 0.004%

minister
Token minister
Feature activation+0.000
who
Token who
Feature activation+0.000
"
Token "
Feature activation+0.518
opened
Tokenopened
Feature activation+0.000
up
Token up
Feature activation+0.000
"
Token"
Feature activation+1.018
the
Token the
Feature activation+0.000
Australian
Token Australian
Feature activation+0.000
economy
Token economy
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
person
Token person
Feature activation+0.000
's
Token's
Feature activation+0.000
command
Token command
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
spoken
Token spoken
Feature activation+1.102
word
Token word
Feature activation+0.847
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
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
such
Token such
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.449
in
Token in
Feature activation+0.000
English
Token English
Feature activation+1.004
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.536
Fog
Token Fog
Feature activation+0.000
el
Tokenel
Feature activation+0.000
says
Token says
Feature activation+0.368
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
state
Token state
Feature activation+1.029
the
Token the
Feature activation+0.000
intention
Token intention
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
paragraph
Token paragraph
Feature activation+0.000
this
Token this
Feature activation+0.000
form
Token form
Feature activation+0.154
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
call
Token call
Feature activation+0.950
them
Token them
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
sis
Tokensis
Feature activation+0.000

INTERVAL 0.622 - 0.933
CONTAINS 0.005%

"
Token "
Feature activation+0.844
net
Tokennet
Feature activation+0.023
-
Token-
Feature activation+0.046
woman
Tokenwoman
Feature activation+0.000
"
Token"
Feature activation+0.504
encompasses
Token encompasses
Feature activation+0.820
the
Token the
Feature activation+0.000
figur
Token figur
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
in
Token in
Feature activation+0.000
H
Token H
Feature activation+0.078
iber
Tokeniber
Feature activation+0.000
no
Tokenno
Feature activation+0.000
-
Token-
Feature activation+0.000
English
TokenEnglish
Feature activation+0.657
;
Token;
Feature activation+0.000
it
Token it
Feature activation+0.104
means
Token means
Feature activation+1.954
empty
Token empty
Feature activation+0.372
fl
Token fl
Feature activation+0.070
c
Token c
Feature activation+0.189
ihu
Tokenihu
Feature activation+0.000
atl
Tokenatl
Feature activation+0.000
(
Token (
Feature activation+0.172
meaning
Tokenmeaning
Feature activation+1.423
"
Token "
Feature activation+0.907
woman
Tokenwoman
Feature activation+0.000
")
Token")
Feature activation+0.281
and
Token and
Feature activation+0.000
mat
Token mat
Feature activation+0.000
lat
Tokenlat
Feature activation+0.000
with
Token with
Feature activation+0.000
scores
Token scores
Feature activation+0.000
of
Token of
Feature activation+0.000
unlock
Token unlock
Feature activation+0.000
able
Tokenable
Feature activation+0.000
entries
Token entries
Feature activation+0.743
contains
Token contains
Feature activation+0.000
an
Token an
Feature activation+0.000
explanation
Token explanation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
My
Token My
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
also
Token also
Feature activation+0.000
respond
Token respond
Feature activation+0.397
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.912
Where
TokenWhere
Feature activation+0.000
's
Token's
Feature activation+0.000
Jo
Token Jo
Feature activation+0.000
annie
Tokenannie
Feature activation+0.000
?"
Token?"
Feature activation+0.000

INTERVAL 0.311 - 0.622
CONTAINS 0.014%

trying
Token trying
Feature activation+0.449
to
Token to
Feature activation+0.000
figure
Token figure
Feature activation+0.394
out
Token out
Feature activation+0.000
which
Token which
Feature activation+0.163
words
Token words
Feature activation+0.463
are
Token are
Feature activation+0.211
the
Token the
Feature activation+0.067
important
Token important
Feature activation+0.197
ones
Token ones
Feature activation+0.000
.
Token.
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Spanish
Token Spanish
Feature activation+0.000
word
Token word
Feature activation+0.380
for
Token for
Feature activation+0.000
"
Token "
Feature activation+0.419
peace
Tokenpeace
Feature activation+0.000
"
Token"
Feature activation+0.795
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
demonstration
Token demonstration
Feature activation+0.000
is
Token is
Feature activation+0.000
ambiguous
Token ambiguous
Feature activation+0.539
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.000
said
Token said
Feature activation+0.414
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000
80
Token 80
Feature activation+0.000
different
Token different
Feature activation+0.000
words
Token words
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
define
Token define
Feature activation+0.368
Lucky
Token Lucky
Feature activation+0.000
Peach
Token Peach
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
-
Token-
Feature activation+0.000
used
Tokenused
Feature activation+0.000
character
Token character
Feature activation+0.389
Ã
Token Ã
Feature activation+0.000
¹
Token¹
Feature activation+0.000
has
Token has
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.000 - 0.311
CONTAINS 99.971%

.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
more
Token more
Feature activation+0.000
from
Token from
Feature activation+0.000
The
Token The
Feature activation+0.000
Nation
Token Nation
Feature activation+0.000
,
Token,
Feature activation+0.000
check
Token check
Feature activation+0.000
out
Token out
Feature activation+0.000
our
Token our
Feature activation+0.000
latest
Token latest
Feature activation+0.000
unique
Token unique
Feature activation+0.000
space
Token space
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
explains
Token explains
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
we
Tokenwe
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
release
Token release
Feature activation+0.000
of
Token of
Feature activation+0.000
No
Token No
Feature activation+0.000
Man
Token Man
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Sky
Token Sky
Feature activation+0.000
T
TokenT
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
militant
Token militant
Feature activation+0.000
group
Token group
Feature activation+0.000
India
Token India
Feature activation+0.000
believes
Token believes
Feature activation+0.000
is
Token is
Feature activation+0.000
responsible
Token responsible
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Cald
Token Cald
Feature activation+0.000
e
Tokene
Feature activation+0.000
ira
Tokenira
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
climate
Token climate
Feature activation+0.000
scientist
Token scientist
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Carnegie
Token Carnegie
Feature activation+0.000
Institution
Token Institution
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 H1.6: (feature 790)

TOP ACTIVATIONS
MAX = 3.404

Maurit
Token Maurit
Feature activation+0.000
ius
Tokenius
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
wrote
Token wrote
Feature activation+3.404
the
Token the
Feature activation+0.000
employee
Token employee
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
warns
Token warns
Feature activation+0.000
it
Token it
Feature activation+0.000
from
Token from
Feature activation+1.109
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
recipients
Token recipients
Feature activation+3.359
.
Token.
Feature activation+0.000
Written
Token Written
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
at
Token at
Feature activation+0.304
d
Token d
Feature activation+0.000
s
Tokens
Feature activation+0.428
ak
Tokenak
Feature activation+0.000
amoto
Tokenamoto
Feature activation+0.000
@
Token@
Feature activation+3.346
dp
Tokendp
Feature activation+0.000
w
Tokenw
Feature activation+0.000
.
Token.
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
An
Token An
Feature activation+0.000
unidentified
Token unidentified
Feature activation+0.000
student
Token student
Feature activation+0.000
sent
Token sent
Feature activation+2.933
an
Token an
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
to
Token to
Feature activation+0.795
s
Tokens
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
private
Token private
Feature activation+0.000
emails
Token emails
Feature activation+0.000
sent
Token sent
Feature activation+2.813
and
Token and
Feature activation+0.000
received
Token received
Feature activation+2.072
between
Token between
Feature activation+0.116
2009
Token 2009
Feature activation+0.000
and
Token and
Feature activation+0.000
emails
Token emails
Feature activation+0.918
are
Token are
Feature activation+0.000
processed
Token processed
Feature activation+1.348
by
Token by
Feature activation+0.202
the
Token the
Feature activation+0.051
recipient
Token recipient
Feature activation+2.715
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.531
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+0.326
at
Token at
Feature activation+0.924
j
Token j
Feature activation+0.000
dam
Tokendam
Feature activation+0.000
u
Tokenu
Feature activation+0.000
2
Token2
Feature activation+0.000
@
Token@
Feature activation+2.698
yahoo
Tokenyahoo
Feature activation+0.000
.
Token.
Feature activation+0.543
com
Tokencom
Feature activation+0.165
.
Token.
Feature activation+0.533
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
be
Token be
Feature activation+0.000
an
Token an
Feature activation+0.000
expert
Token expert
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
subject
Token subject
Feature activation+2.670
who
Token who
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
tem
Token tem
Feature activation+0.000
to
Token to
Feature activation+0.157
:
Token:
Feature activation+0.000
mm
Token mm
Feature activation+0.000
wr
Tokenwr
Feature activation+0.000
q
Tokenq
Feature activation+0.000
@
Token@
Feature activation+2.647
cd
Tokencd
Feature activation+0.000
c
Tokenc
Feature activation+0.000
.
Token.
Feature activation+0.000
gov
Tokengov
Feature activation+0.000
.
Token.
Feature activation+0.000
idea
Token idea
Feature activation+0.000
what
Token what
Feature activation+0.000
message
Token message
Feature activation+0.994
he
Token he
Feature activation+0.000
should
Token should
Feature activation+0.000
send
Token send
Feature activation+2.440
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
:
Token:
Feature activation+0.000
mc
Token mc
Feature activation+0.024
aban
Tokenaban
Feature activation+0.000
at
Tokenat
Feature activation+0.055
uan
Tokenuan
Feature activation+0.000
@
Token@
Feature activation+2.211
sf
Tokensf
Feature activation+0.000
chron
Tokenchron
Feature activation+0.000
icle
Tokenicle
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
sender
Token sender
Feature activation+2.208
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.598
to
Token to
Feature activation+0.215
a
Token a
Feature activation+0.000
address
Token address
Feature activation+0.000
below
Token below
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
'll
Token'll
Feature activation+0.000
send
Token send
Feature activation+2.202
you
Token you
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
coupon
Token coupon
Feature activation+0.000
of
Token of
Feature activation+0.000
private
Token private
Feature activation+0.000
emails
Token emails
Feature activation+0.000
sent
Token sent
Feature activation+2.813
and
Token and
Feature activation+0.000
received
Token received
Feature activation+2.072
between
Token between
Feature activation+0.116
2009
Token 2009
Feature activation+0.000
and
Token and
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
was
Token was
Feature activation+0.000
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+0.000
recipient
Token recipient
Feature activation+2.048
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
highest
Token highest
Feature activation+0.000
court
Token court
Feature activation+0.000
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+2.022
approximately
Token approximately
Feature activation+0.000
18
Token 18
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
in
Tokenin
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+1.939
line
Token line
Feature activation+0.000
of
Token of
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.012
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Des
Token Des
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
wrote
Token wrote
Feature activation+1.911
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
alert
Token alert
Feature activation+0.842
ing
Tokening
Feature activation+0.467
The
Token The
Feature activation+0.000
following
Token following
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
from
Token from
Feature activation+1.905
Terry
Token Terry
Feature activation+0.054
Kramer
Token Kramer
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
be
Token be
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
recipient
Token recipient
Feature activation+1.870
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.165
assistant
Token assistant
Feature activation+0.000
opens
Token opens
Feature activation+0.174

Top DFA by src position
MAX = 4.751

.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
In
TokenIn
Feature activation+0.007
Top resid features:
an
Token an
Feature activation+0.027
Top resid features:
email
Token email
Feature activation+2.828
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
February
Token February
Feature activation+0.011
Top resid features:
2010
Token 2010
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Heritage
Token Heritage
Feature activation-0.001
Top resid features:
ell
Tokenell
Feature activation+0.039
Top resid features:
man
Tokenman
Feature activation+0.023
Top resid features:
reprodu
Token reprodu
Feature activation+0.044
Top resid features:
ces
Tokences
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
email
Token email
Feature activation+4.751
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
Ang
Token Ang
Feature activation+0.029
Top resid features:
ler
Tokenler
Feature activation+0.041
Top resid features:
.
Token.
Feature activation-0.090
Top resid features:
He
Token He
Feature activation+0.007
Top resid features:
be
Token be
Feature activation+0.007
Top resid features:
submitted
Token submitted
Feature activation+0.030
Top resid features:
via
Token via
Feature activation+0.035
Top resid features:
e
Token e
Feature activation+0.129
Top resid features:
-
Token-
Feature activation+0.040
Top resid features:
mail
Tokenmail
Feature activation+4.202
Top resid features:
at
Token at
Feature activation+0.027
Top resid features:
d
Token d
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.029
Top resid features:
ak
Tokenak
Feature activation+0.026
Top resid features:
amoto
Tokenamoto
Feature activation-0.008
Top resid features:
wrote
Token wrote
Feature activation+0.070
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
e
Token e
Feature activation+0.033
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
mail
Tokenmail
Feature activation+3.973
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
âĢ
Token âĢ
Feature activation+0.006
Top resid features:
ľ
Tokenľ
Feature activation+0.014
Top resid features:
In
TokenIn
Feature activation+0.005
Top resid features:
other
Token other
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation+0.030
Top resid features:
s
Tokens
Feature activation+0.019
Top resid features:
thousands
Token thousands
Feature activation+0.098
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
private
Token private
Feature activation+0.020
Top resid features:
emails
Token emails
Feature activation+4.509
Top resid features:
sent
Token sent
Feature activation-0.636
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
received
Token received
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
who
Token who
Feature activation-0.004
Top resid features:
use
Token use
Feature activation+0.011
Top resid features:
web
Token web
Feature activation+0.044
Top resid features:
-
Token-
Feature activation-0.010
Top resid features:
based
Tokenbased
Feature activation+0.014
Top resid features:
email
Token email
Feature activation+1.283
Top resid features:
today
Token today
Feature activation+0.015
Top resid features:
cannot
Token cannot
Feature activation+0.002
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
surprised
Token surprised
Feature activation+0.032
Top resid features:
if
Token if
Feature activation-0.012
Top resid features:
Alliance
Token Alliance
Feature activation+0.018
Top resid features:
for
Token for
Feature activation-0.006
Top resid features:
Just
Token Just
Feature activation+0.026
Top resid features:
Immigration
Token Immigration
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Email
Token Email
Feature activation+3.723
Top resid features:
him
Token him
Feature activation+0.029
Top resid features:
at
Token at
Feature activation+0.031
Top resid features:
j
Token j
Feature activation+0.029
Top resid features:
dam
Tokendam
Feature activation+0.072
Top resid features:
u
Tokenu
Feature activation+0.022
Top resid features:
ack
Tokenack
Feature activation+0.010
Top resid features:
Center
Token Center
Feature activation+0.019
Top resid features:
is
Token is
Feature activation+0.023
Top resid features:
demanding
Token demanding
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
emails
Token emails
Feature activation+4.168
Top resid features:
of
Token of
Feature activation-0.019
Top resid features:
anybody
Token anybody
Feature activation+0.011
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.016
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
please
Token please
Feature activation-0.012
Top resid features:
send
Token send
Feature activation+0.108
Top resid features:
e
Token e
Feature activation+0.144
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
mail
Tokenmail
Feature activation+4.015
Top resid features:
to
Token to
Feature activation-0.022
Top resid features:
:
Token:
Feature activation-0.038
Top resid features:
mm
Token mm
Feature activation-0.005
Top resid features:
wr
Tokenwr
Feature activation-0.089
Top resid features:
q
Tokenq
Feature activation+0.062
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
And
Token And
Feature activation+0.003
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
12
Token 12
Feature activation+0.021
Top resid features:
AM
Token AM
Feature activation+0.003
Top resid features:
email
Token email
Feature activation+3.428
Top resid features:
revealed
Token revealed
Feature activation+0.025
Top resid features:
that
Token that
Feature activation-0.011
Top resid features:
he
Token he
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.028
Top resid features:
Francisco
Token Francisco
Feature activation+0.004
Top resid features:
Chronicle
Token Chronicle
Feature activation+0.018
Top resid features:
staff
Token staff
Feature activation+0.028
Top resid features:
writer
Token writer
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Email
Token Email
Feature activation+3.335
Top resid features:
:
Token:
Feature activation+0.016
Top resid features:
mc
Token mc
Feature activation+0.020
Top resid features:
aban
Tokenaban
Feature activation+0.100
Top resid features:
at
Tokenat
Feature activation+0.048
Top resid features:
uan
Tokenuan
Feature activation-0.004
Top resid features:
people
Token people
Feature activation-0.001
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
care
Token care
Feature activation-0.005
Top resid features:
about
Token about
Feature activation+0.015
Top resid features:
their
Token their
Feature activation+0.012
Top resid features:
email
Token email
Feature activation+2.430
Top resid features:
correspond
Token correspond
Feature activation+0.039
Top resid features:
ents
Tokenents
Feature activation+0.027
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.028
Top resid features:
privacy
Token privacy
Feature activation+0.008
Top resid features:
WordPress
Token WordPress
Feature activation-0.007
Top resid features:
theme
Token theme
Feature activation-0.024
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
Add
Token Add
Feature activation+0.085
Top resid features:
your
Token your
Feature activation+0.048
Top resid features:
email
Token email
Feature activation+3.198
Top resid features:
address
Token address
Feature activation+0.145
Top resid features:
below
Token below
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
I
Token I
Feature activation+0.049
Top resid features:
'll
Token'll
Feature activation+0.076
Top resid features:
Ļ
TokenĻ
Feature activation+0.032
Top resid features:
s
Tokens
Feature activation+0.025
Top resid features:
thousands
Token thousands
Feature activation+0.070
Top resid features:
of
Token of
Feature activation-0.017
Top resid features:
private
Token private
Feature activation+0.022
Top resid features:
emails
Token emails
Feature activation+2.739
Top resid features:
sent
Token sent
Feature activation+0.374
Top resid features:
and
Token and
Feature activation+0.093
Top resid features:
received
Token received
Feature activation-0.387
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
received
Token received
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
following
Token following
Feature activation+0.006
Top resid features:
e
Token e
Feature activation+0.069
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
mail
Tokenmail
Feature activation+2.857
Top resid features:
message
Token message
Feature activation+0.139
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Notice
TokenNotice
Feature activation+0.012
Top resid features:
exchange
Token exchange
Feature activation+0.040
Top resid features:
sexually
Token sexually
Feature activation-0.035
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
racially
Token racially
Feature activation+0.006
Top resid features:
offensive
Token offensive
Feature activation+0.012
Top resid features:
emails
Token emails
Feature activation+3.544
Top resid features:
with
Token with
Feature activation+0.019
Top resid features:
his
Token his
Feature activation+0.044
Top resid features:
peers
Token peers
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
please
Token please
Feature activation-0.008
Top resid features:
send
Token send
Feature activation+0.062
Top resid features:
e
Token e
Feature activation+0.040
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
mail
Tokenmail
Feature activation+2.605
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
mm
Token mm
Feature activation+0.025
Top resid features:
wr
Tokenwr
Feature activation-0.012
Top resid features:
q
Tokenq
Feature activation+0.026
Top resid features:
In
TokenIn
Feature activation+0.008
Top resid features:
one
Token one
Feature activation+0.015
Top resid features:
instance
Token instance
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
emails
Token emails
Feature activation+2.953
Top resid features:
show
Token show
Feature activation+0.024
Top resid features:
Amit
Token Amit
Feature activation-0.022
Top resid features:
ab
Tokenab
Feature activation+0.006
Top resid features:
h
Tokenh
Feature activation+0.010
Top resid features:
Des
Token Des
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
The
Token The
Feature activation+0.029
Top resid features:
following
Token following
Feature activation+0.050
Top resid features:
is
Token is
Feature activation+0.089
Top resid features:
an
Token an
Feature activation+0.073
Top resid features:
email
Token email
Feature activation+2.792
Top resid features:
from
Token from
Feature activation-0.011
Top resid features:
Terry
Token Terry
Feature activation+0.000
Top resid features:
Kramer
Token Kramer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.001
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
care
Token care
Feature activation+0.003
Top resid features:
about
Token about
Feature activation+0.015
Top resid features:
their
Token their
Feature activation+0.009
Top resid features:
email
Token email
Feature activation+1.467
Top resid features:
correspond
Token correspond
Feature activation+0.028
Top resid features:
ents
Tokenents
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.018
Top resid features:
privacy
Token privacy
Feature activation+0.017
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.03

Head 3: 0.01

Head 4: 0.04

Head 5: 0.08

Head 6: 0.55

Head 7: 0.05

Head 8: 0.02

Head 9: 0.02

Head 10: 0.03

Head 11: 0.08

Positive logits

inbox2.56

Emails2.46

replies2.29

CLASSIFIED2.28

reply2.26

emails2.26

invitations2.24

mail2.20

Subscribe2.18

correspondence2.16

encrypted2.13

fax2.13

forwarded2.12

email2.10

Email2.05

Mail2.04

subscriptions2.00

answ2.00

UNCLASSIFIED1.95

notifications1.94

Negative logits

Rally-1.87

rally-1.85

Kru-1.80

torch-1.79

uay-1.73

sto-1.70

tanks-1.69

measure-1.69

choke-1.68

displacement-1.67

Pit-1.65

Pike-1.63

run-1.62

unequal-1.61

oppressed-1.60

rac-1.59

bulldo-1.58

deform-1.56

BIP-1.56

tank-1.56

INTERVAL 3.064 - 3.404
CONTAINS 0.000%

Maurit
Token Maurit
Feature activation+0.000
ius
Tokenius
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
wrote
Token wrote
Feature activation+3.404
the
Token the
Feature activation+0.000
employee
Token employee
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
warns
Token warns
Feature activation+0.000
it
Token it
Feature activation+0.000
from
Token from
Feature activation+1.109
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
recipients
Token recipients
Feature activation+3.359
.
Token.
Feature activation+0.000
Written
Token Written
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
at
Token at
Feature activation+0.304
d
Token d
Feature activation+0.000
s
Tokens
Feature activation+0.428
ak
Tokenak
Feature activation+0.000
amoto
Tokenamoto
Feature activation+0.000
@
Token@
Feature activation+3.346
dp
Tokendp
Feature activation+0.000
w
Tokenw
Feature activation+0.000
.
Token.
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ac
Tokenac
Feature activation+0.000

INTERVAL 2.723 - 3.064
CONTAINS 0.000%

s
Tokens
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
private
Token private
Feature activation+0.000
emails
Token emails
Feature activation+0.000
sent
Token sent
Feature activation+2.813
and
Token and
Feature activation+0.000
received
Token received
Feature activation+2.072
between
Token between
Feature activation+0.116
2009
Token 2009
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
An
Token An
Feature activation+0.000
unidentified
Token unidentified
Feature activation+0.000
student
Token student
Feature activation+0.000
sent
Token sent
Feature activation+2.933
an
Token an
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
to
Token to
Feature activation+0.795

INTERVAL 2.383 - 2.723
CONTAINS 0.001%

idea
Token idea
Feature activation+0.000
what
Token what
Feature activation+0.000
message
Token message
Feature activation+0.994
he
Token he
Feature activation+0.000
should
Token should
Feature activation+0.000
send
Token send
Feature activation+2.440
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
to
Token to
Feature activation+0.157
:
Token:
Feature activation+0.000
mm
Token mm
Feature activation+0.000
wr
Tokenwr
Feature activation+0.000
q
Tokenq
Feature activation+0.000
@
Token@
Feature activation+2.647
cd
Tokencd
Feature activation+0.000
c
Tokenc
Feature activation+0.000
.
Token.
Feature activation+0.000
gov
Tokengov
Feature activation+0.000
.
Token.
Feature activation+0.000
emails
Token emails
Feature activation+0.918
are
Token are
Feature activation+0.000
processed
Token processed
Feature activation+1.348
by
Token by
Feature activation+0.202
the
Token the
Feature activation+0.051
recipient
Token recipient
Feature activation+2.715
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.531
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+0.326
be
Token be
Feature activation+0.000
an
Token an
Feature activation+0.000
expert
Token expert
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
subject
Token subject
Feature activation+2.670
who
Token who
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
tem
Token tem
Feature activation+0.000
at
Token at
Feature activation+0.924
j
Token j
Feature activation+0.000
dam
Tokendam
Feature activation+0.000
u
Tokenu
Feature activation+0.000
2
Token2
Feature activation+0.000
@
Token@
Feature activation+2.698
yahoo
Tokenyahoo
Feature activation+0.000
.
Token.
Feature activation+0.543
com
Tokencom
Feature activation+0.165
.
Token.
Feature activation+0.533
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000

INTERVAL 2.043 - 2.383
CONTAINS 0.001%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
sender
Token sender
Feature activation+2.208
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.598
to
Token to
Feature activation+0.215
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
private
Token private
Feature activation+0.000
emails
Token emails
Feature activation+0.000
sent
Token sent
Feature activation+2.813
and
Token and
Feature activation+0.000
received
Token received
Feature activation+2.072
between
Token between
Feature activation+0.116
2009
Token 2009
Feature activation+0.000
and
Token and
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
was
Token was
Feature activation+0.000
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+0.000
recipient
Token recipient
Feature activation+2.048
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
address
Token address
Feature activation+0.000
below
Token below
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
'll
Token'll
Feature activation+0.000
send
Token send
Feature activation+2.202
you
Token you
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
coupon
Token coupon
Feature activation+0.000
:
Token:
Feature activation+0.000
mc
Token mc
Feature activation+0.024
aban
Tokenaban
Feature activation+0.000
at
Tokenat
Feature activation+0.055
uan
Tokenuan
Feature activation+0.000
@
Token@
Feature activation+2.211
sf
Tokensf
Feature activation+0.000
chron
Tokenchron
Feature activation+0.000
icle
Tokenicle
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000

INTERVAL 1.702 - 2.043
CONTAINS 0.001%

cannot
Token cannot
Feature activation+0.000
be
Token be
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
recipient
Token recipient
Feature activation+1.870
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.165
assistant
Token assistant
Feature activation+0.000
opens
Token opens
Feature activation+0.174
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Car
Token Car
Feature activation+0.000
on
Tokenon
Feature activation+0.000
wrote
Token wrote
Feature activation+1.718
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
,
Token,
Feature activation+0.000
deserve
Token deserve
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
writes
Token writes
Feature activation+1.850
the
Token the
Feature activation+0.000
76
Token 76
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
The
Token The
Feature activation+0.000
following
Token following
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
from
Token from
Feature activation+1.905
Terry
Token Terry
Feature activation+0.054
Kramer
Token Kramer
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+1.939
line
Token line
Feature activation+0.000
of
Token of
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.012

INTERVAL 1.362 - 1.702
CONTAINS 0.001%

]
Token]
Feature activation+0.000
in
Token in
Feature activation+0.110
the
Token the
Feature activation+0.054
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.101
delivery
Token delivery
Feature activation+1.548
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.169
receive
Token receive
Feature activation+1.689
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.331
date
Token date
Feature activation+0.000
financial
Token financial
Feature activation+0.000
information
Token information
Feature activation+0.000
of
Token of
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
400
Token 400
Feature activation+0.000
messages
Token messages
Feature activation+0.615
recently
Token recently
Feature activation+0.000
released
Token released
Feature activation+1.476
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+0.854
Department
Token Department
Feature activation+0.581
after
Token after
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+1.518
Public
Token Public
Feature activation+0.000
Knowledge
Token Knowledge
Feature activation+0.000
and
Token and
Feature activation+0.000
Bent
Token Bent
Feature activation+0.000
on
Tokenon
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
emails
Token emails
Feature activation+0.000
the
Token the
Feature activation+0.000
woman
Token woman
Feature activation+0.000
wrote
Token wrote
Feature activation+1.464
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
San
Token San
Feature activation+0.000
Marcos
Token Marcos
Feature activation+0.000
Police
Token Police
Feature activation+0.000

INTERVAL 1.021 - 1.362
CONTAINS 0.002%

ľ
Tokenľ
Feature activation+0.000
conf
Tokenconf
Feature activation+0.000
idential
Tokenidential
Feature activation+0.046
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
classified
Token classified
Feature activation+1.217
information
Token information
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
got
Token got
Feature activation+0.000
it
Token it
Feature activation+0.000
from
Token from
Feature activation+1.109
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
recipients
Token recipients
Feature activation+3.359
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
invalid
Token invalid
Feature activation+0.000
Fill
Token Fill
Feature activation+0.167
out
Token out
Feature activation+0.000
this
Token this
Feature activation+0.000
field
Token field
Feature activation+1.066
Email
Token Email
Feature activation+0.000
address
Token address
Feature activation+0.265
is
Token is
Feature activation+0.000
invalid
Token invalid
Feature activation+0.000
You
Token You
Feature activation+0.408
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
message
Token message
Feature activation+1.273
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Notice
TokenNotice
Feature activation+0.000
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
approved
Token approved
Feature activation+0.019
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+1.180
Department
Token Department
Feature activation+0.375
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
legal
Token legal
Feature activation+0.000

INTERVAL 0.681 - 1.021
CONTAINS 0.004%

our
Token our
Feature activation+0.000
email
Token email
Feature activation+0.000
your
Token your
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
ories
Tokenories
Feature activation+0.000
@
Token@
Feature activation+0.725
f
Tokenf
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
ories
Tokenories
Feature activation+0.000
podcast
Tokenpodcast
Feature activation+0.000
:
Token:
Feature activation+0.000
ric
Token ric
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
yr
Tokenyr
Feature activation+0.000
l
Tokenl
Feature activation+0.000
@
Token@
Feature activation+0.979
mont
Tokenmont
Feature activation+0.000
gomery
Tokengomery
Feature activation+0.000
count
Tokencount
Feature activation+0.000
y
Tokeny
Feature activation+0.000
va
Tokenva
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
email
Token email
Feature activation+0.000
system
Token system
Feature activation+0.748
and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
impact
Token impact
Feature activation+0.033
on
Token on
Feature activation+0.356
the
Token the
Feature activation+0.000
Email
Token Email
Feature activation+0.000
address
Token address
Feature activation+0.249
:
Token:
Feature activation+0.000
Leave
Token Leave
Feature activation+0.000
this
Token this
Feature activation+0.000
field
Token field
Feature activation+0.804
empty
Token empty
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.272
're
Token're
Feature activation+0.000
human
Token human
Feature activation+0.000
mass
Token mass
Feature activation+0.000
email
Token email
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.675
usually
Token usually
Feature activation+0.000
delete
Token delete
Feature activation+1.012
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Typically
Token Typically
Feature activation+0.000
without
Token without
Feature activation+0.000
reading
Token reading
Feature activation+0.000

INTERVAL 0.340 - 0.681
CONTAINS 0.013%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
*****
Token*****
Feature activation+0.000
We
TokenWe
Feature activation+0.000
've
Token've
Feature activation+0.000
reached
Token reached
Feature activation+0.362
our
Token our
Feature activation+0.000
final
Token final
Feature activation+0.000
goal
Token goal
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
both
Token both
Feature activation+0.000
because
Token because
Feature activation+0.067
we
Token we
Feature activation+0.513
urgently
Token urgently
Feature activation+0.177
need
Token need
Feature activation+0.035
to
Token to
Feature activation+0.520
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
dom
Tokendom
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
by
Token by
Feature activation+0.202
the
Token the
Feature activation+0.051
recipient
Token recipient
Feature activation+2.715
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.531
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+0.326
provider
Token provider
Feature activation+0.000
]
Token]
Feature activation+0.000
in
Token in
Feature activation+0.110
his
Token his
Feature activation+0.000
friend
Token friend
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
remain
Token remain
Feature activation+0.000
anonymous
Token anonymous
Feature activation+0.456
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Te
TokenTe
Feature activation+0.000
aching
Tokenaching
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
batch
Token batch
Feature activation+0.450
of
Token of
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
400
Token 400
Feature activation+0.000
messages
Token messages
Feature activation+0.615
recently
Token recently
Feature activation+0.000

INTERVAL 0.000 - 0.340
CONTAINS 99.977%

kid
Token kid
Feature activation+0.000
.
Token.
Feature activation+0.000
Ye
Token Ye
Feature activation+0.000
a
Tokena
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
gave
Token gave
Feature activation+0.000
my
Token my
Feature activation+0.000
kid
Token kid
Feature activation+0.000
formula
Token formula
Feature activation+0.000
and
Token and
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
any
Token any
Feature activation+0.000
dist
Token dist
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
eful
Tokeneful
Feature activation+0.000
term
Token term
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
back
Tokenback
Feature activation+0.000
this
Token this
Feature activation+0.000
issue
Token issue
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
alarmed
Token alarmed
Feature activation+0.000
that
Token that
Feature activation+0.000
supposedly
Token supposedly
Feature activation+0.000
new
Token new
Feature activation+0.000
information
Token information
Feature activation+0.000
continues
Token continues
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
applies
Token applies
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
region
Token region
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
all
Token all
Feature activation+0.000
states
Token states
Feature activation+0.000
described
Token described
Feature activation+0.000
more
Token more
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
rapid
Token rapid
Feature activation+0.000
-
Token-
Feature activation+0.000
response
Tokenresponse
Feature activation+0.000
effect
Token effect
Feature activation+0.000
:
Token:
Feature activation+0.000
If
Token If
Feature activation+0.000
a
Token a
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 H1.6: (feature 5425)

TOP ACTIVATIONS
MAX = 3.322

no
Token no
Feature activation+0.000
further
Token further
Feature activation+0.000
deterioration
Token deterioration
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
sight
Token sight
Feature activation+3.322
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
tensions
Token tensions
Feature activation+0.000
have
Token have
Feature activation+0.000
course
Token course
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.000
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.338
eye
Token eye
Feature activation+3.008
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
military
Token military
Feature activation+0.000
coup
Token coup
Feature activation+0.000
ousted
Token ousted
Feature activation+0.000
left
Token left
Feature activation+0.000
almost
Token almost
Feature activation+0.000
blind
Token blind
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
eye
Token eye
Feature activation+2.764
and
Token and
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.453
to
Token to
Feature activation+0.000
going
Token going
Feature activation+0.000
blind
Token blind
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
eye
Token eye
Feature activation+2.654
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
regular
Token regular
Feature activation+0.000
check
Token check
Feature activation+0.000
is
Token is
Feature activation+0.000
completely
Token completely
Feature activation+0.000
turning
Token turning
Feature activation+0.000
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.000
eye
Token eye
Feature activation+2.141
to
Token to
Feature activation+0.000
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
visually
Token visually
Feature activation+1.976
impaired
Token impaired
Feature activation+1.172
person
Token person
Feature activation+0.168
to
Token to
Feature activation+0.000
head
Token head
Feature activation+1.025
the
Token the
Feature activation+0.000
fat
Token fat
Feature activation+0.000
.
Token.
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
vision
Token vision
Feature activation+1.728
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
o
Token o
Feature activation+0.000
phthal
Tokenphthal
Feature activation+0.270
m
Tokenm
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
visually
Token visually
Feature activation+1.976
impaired
Token impaired
Feature activation+1.172
person
Token person
Feature activation+0.168
to
Token to
Feature activation+0.000
head
Token head
Feature activation+1.025
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+1.136
players
Token players
Feature activation+0.000
taking
Token taking
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
we
Token we
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
dece
Token dece
Feature activation+0.000
iving
Tokeniving
Feature activation+1.066
ourselves
Token ourselves
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+1.058
clubs
Token clubs
Feature activation+0.000
developed
Token developed
Feature activation+0.000
analytics
Token analytics
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
visually
Token visually
Feature activation+1.976
impaired
Token impaired
Feature activation+1.172
person
Token person
Feature activation+0.168
to
Token to
Feature activation+0.000
head
Token head
Feature activation+1.025
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
than
Token than
Feature activation+0.000
taking
Token taking
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+0.908
Wall
Token Wall
Feature activation+0.000
Street
Token Street
Feature activation+0.000
firms
Token firms
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.000
they
Token they
Feature activation+0.000
encounter
Token encounter
Feature activation+0.000
two
Token two
Feature activation+0.000
blind
Token blind
Feature activation+0.000
fold
Tokenfold
Feature activation+0.756
ed
Tokened
Feature activation+0.897
women
Token women
Feature activation+0.196
preparing
Token preparing
Feature activation+0.000
to
Token to
Feature activation+0.032
be
Token be
Feature activation+0.192
padd
Token padd
Feature activation+0.000
royalties
Token royalties
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
ab
Token ab
Feature activation+0.000
rid
Tokenrid
Feature activation+0.000
ged
Tokenged
Feature activation+0.885
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000
Dream
TokenDream
Feature activation+0.000
s
Tokens
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
completely
Token completely
Feature activation+0.000
colour
Token colour
Feature activation+0.000
-
Token-
Feature activation+0.000
blind
Tokenblind
Feature activation+0.835
.
Token.
Feature activation+0.358
Ċ
TokenĊ
Feature activation+0.052
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
day
Token day
Feature activation+0.000
casually
Token casually
Feature activation+0.000
dropped
Token dropped
Feature activation+0.000
his
Token his
Feature activation+0.000
ab
Token ab
Feature activation+0.000
rid
Tokenrid
Feature activation+0.000
ged
Tokenged
Feature activation+0.783
rendition
Token rendition
Feature activation+0.000
of
Token of
Feature activation+0.000
Nikol
Token Nikol
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
G
Token G
Feature activation+0.000
also
Token also
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
face
Token face
Feature activation+0.220
discrimination
Token discrimination
Feature activation+0.000
when
Token when
Feature activation+0.000
looking
Token looking
Feature activation+0.781
for
Token for
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
or
Token or
Feature activation+0.000
places
Token places
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
encounter
Token encounter
Feature activation+0.000
two
Token two
Feature activation+0.000
blind
Token blind
Feature activation+0.000
fold
Tokenfold
Feature activation+0.756
ed
Tokened
Feature activation+0.897
women
Token women
Feature activation+0.196
preparing
Token preparing
Feature activation+0.000
to
Token to
Feature activation+0.032
be
Token be
Feature activation+0.192
separating
Token separating
Feature activation+0.000
the
Token the
Feature activation+0.000
chamber
Token chamber
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
viewing
Token viewing
Feature activation+0.654
room
Token room
Feature activation+0.000
were
Token were
Feature activation+0.000
lowered
Token lowered
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

Top DFA by src position
MAX = 4.973

had
Token had
Feature activation-0.014
Top resid features:
come
Token come
Feature activation+0.007
Top resid features:
close
Token close
Feature activation+0.015
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
going
Token going
Feature activation-0.000
Top resid features:
blind
Token blind
Feature activation+4.973
Top resid features:
in
Token in
Feature activation-0.015
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
other
Token other
Feature activation+0.001
Top resid features:
eye
Token eye
Feature activation-0.029
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
reverse
Token reverse
Feature activation+0.095
Top resid features:
course
Token course
Feature activation-0.035
Top resid features:
and
Token and
Feature activation-0.126
Top resid features:
turn
Token turn
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.149
Top resid features:
blind
Token blind
Feature activation+4.522
Top resid features:
eye
Token eye
Feature activation+0.213
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
military
Token military
Feature activation+0.000
Top resid features:
coup
Token coup
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.741
Top resid features:
was
Token was
Feature activation-0.113
Top resid features:
left
Token left
Feature activation-0.047
Top resid features:
almost
Token almost
Feature activation-0.075
Top resid features:
blind
Token blind
Feature activation+4.307
Top resid features:
in
Token in
Feature activation-0.045
Top resid features:
one
Token one
Feature activation-0.027
Top resid features:
eye
Token eye
Feature activation+0.172
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
had
Token had
Feature activation-0.036
Top resid features:
come
Token come
Feature activation-0.005
Top resid features:
close
Token close
Feature activation+0.062
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
going
Token going
Feature activation-0.033
Top resid features:
blind
Token blind
Feature activation+4.056
Top resid features:
in
Token in
Feature activation-0.033
Top resid features:
the
Token the
Feature activation-0.082
Top resid features:
other
Token other
Feature activation+0.015
Top resid features:
eye
Token eye
Feature activation+0.075
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
media
Token media
Feature activation-0.017
Top resid features:
is
Token is
Feature activation-0.063
Top resid features:
completely
Token completely
Feature activation+0.008
Top resid features:
turning
Token turning
Feature activation+0.030
Top resid features:
a
Token a
Feature activation-0.145
Top resid features:
blind
Token blind
Feature activation+3.717
Top resid features:
eye
Token eye
Feature activation+0.251
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
1998
Token 1998
Feature activation+0.008
Top resid features:
by
Token by
Feature activation-0.005
Top resid features:
becoming
Token becoming
Feature activation+0.007
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
first
Token first
Feature activation-0.001
Top resid features:
blind
Token blind
Feature activation+2.855
Top resid features:
person
Token person
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
appointed
Token appointed
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.739
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
leads
Token leads
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
permanent
Token permanent
Feature activation+0.016
Top resid features:
blindness
Token blindness
Feature activation+3.482
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Que
TokenQue
Feature activation+0.006
Top resid features:
iro
Tokeniro
Feature activation+0.007
Top resid features:
1998
Token 1998
Feature activation+0.008
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
becoming
Token becoming
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
first
Token first
Feature activation-0.001
Top resid features:
blind
Token blind
Feature activation+1.600
Top resid features:
person
Token person
Feature activation-0.012
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
appointed
Token appointed
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
environment
Token environment
Feature activation+0.019
Top resid features:
,
Token,
Feature activation-0.154
Top resid features:
with
Token with
Feature activation-0.011
Top resid features:
deep
Token deep
Feature activation+0.066
Top resid features:
-
Token-
Feature activation-0.031
Top resid features:
pocket
Tokenpocket
Feature activation+2.593
Top resid features:
ed
Tokened
Feature activation-0.013
Top resid features:
players
Token players
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
advantage
Token advantage
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.058
Top resid features:
we
Token we
Feature activation-0.002
Top resid features:
aren
Token aren
Feature activation-0.130
Top resid features:
't
Token't
Feature activation+0.042
Top resid features:
just
Token just
Feature activation-0.016
Top resid features:
dece
Token dece
Feature activation+2.419
Top resid features:
iving
Tokeniving
Feature activation+0.231
Top resid features:
ourselves
Token ourselves
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
,
Token,
Feature activation-0.050
Top resid features:
as
Token as
Feature activation-0.013
Top resid features:
deep
Token deep
Feature activation+0.166
Top resid features:
-
Token-
Feature activation+0.023
Top resid features:
pocket
Tokenpocket
Feature activation+2.464
Top resid features:
ed
Tokened
Feature activation+0.004
Top resid features:
clubs
Token clubs
Feature activation+0.000
Top resid features:
developed
Token developed
Feature activation+0.000
Top resid features:
analytics
Token analytics
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
1998
Token 1998
Feature activation+0.007
Top resid features:
by
Token by
Feature activation-0.006
Top resid features:
becoming
Token becoming
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
first
Token first
Feature activation-0.003
Top resid features:
blind
Token blind
Feature activation+2.036
Top resid features:
person
Token person
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
be
Token be
Feature activation+0.007
Top resid features:
appointed
Token appointed
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
costly
Token costly
Feature activation-0.026
Top resid features:
than
Token than
Feature activation-0.067
Top resid features:
taking
Token taking
Feature activation+0.001
Top resid features:
deep
Token deep
Feature activation+0.058
Top resid features:
-
Token-
Feature activation-0.056
Top resid features:
pocket
Tokenpocket
Feature activation+2.582
Top resid features:
ed
Tokened
Feature activation-0.015
Top resid features:
Wall
Token Wall
Feature activation+0.000
Top resid features:
Street
Token Street
Feature activation+0.000
Top resid features:
firms
Token firms
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.080
Top resid features:
,
Token,
Feature activation-0.037
Top resid features:
they
Token they
Feature activation+0.072
Top resid features:
encounter
Token encounter
Feature activation+0.125
Top resid features:
two
Token two
Feature activation-0.016
Top resid features:
blind
Token blind
Feature activation+1.063
Top resid features:
fold
Tokenfold
Feature activation+0.963
Top resid features:
ed
Tokened
Feature activation+0.095
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
preparing
Token preparing
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
royalties
Token royalties
Feature activation-0.045
Top resid features:
for
Token for
Feature activation-0.004
Top resid features:
an
Token an
Feature activation-0.134
Top resid features:
ab
Token ab
Feature activation+0.013
Top resid features:
rid
Tokenrid
Feature activation+2.838
Top resid features:
ged
Tokenged
Feature activation-0.058
Top resid features:
version
Token version
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Dream
TokenDream
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.010
Top resid features:
not
Token not
Feature activation+0.057
Top resid features:
completely
Token completely
Feature activation+0.056
Top resid features:
colour
Token colour
Feature activation+0.267
Top resid features:
-
Token-
Feature activation+0.012
Top resid features:
blind
Tokenblind
Feature activation+1.698
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:
In
TokenIn
Feature activation+0.000
Top resid features:
day
Token day
Feature activation+0.000
Top resid features:
he
Token he
Feature activation-0.037
Top resid features:
casually
Token casually
Feature activation+0.004
Top resid features:
dropped
Token dropped
Feature activation+0.028
Top resid features:
his
Token his
Feature activation-0.079
Top resid features:
ab
Token ab
Feature activation-0.017
Top resid features:
rid
Tokenrid
Feature activation+2.687
Top resid features:
ged
Tokenged
Feature activation+0.011
Top resid features:
rendition
Token rendition
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Nikol
Token Nikol
Feature activation+0.000
Top resid features:
ai
Tokenai
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.045
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
completely
Token completely
Feature activation+0.019
Top resid features:
colour
Token colour
Feature activation+0.036
Top resid features:
-
Token-
Feature activation+0.019
Top resid features:
blind
Tokenblind
Feature activation+1.643
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
In
TokenIn
Feature activation-0.006
Top resid features:
day
Token day
Feature activation-0.002
Top resid features:
way
Token way
Feature activation+0.091
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
they
Token they
Feature activation+0.098
Top resid features:
encounter
Token encounter
Feature activation+0.133
Top resid features:
two
Token two
Feature activation-0.004
Top resid features:
blind
Token blind
Feature activation+1.592
Top resid features:
fold
Tokenfold
Feature activation+0.014
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
preparing
Token preparing
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
being
Token being
Feature activation-0.002
Top resid features:
declared
Token declared
Feature activation+0.041
Top resid features:
dead
Token dead
Feature activation+0.008
Top resid features:
,
Token,
Feature activation-0.076
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
blind
Token blind
Feature activation+1.429
Top resid features:
s
Tokens
Feature activation+0.039
Top resid features:
separating
Token separating
Feature activation+0.041
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
chamber
Token chamber
Feature activation-0.018
Top resid features:
from
Token from
Feature activation+0.056
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.04

Head 3: 0.02

Head 4: 0.04

Head 5: 0.05

Head 6: 0.54

Head 7: 0.05

Head 8: 0.03

Head 9: 0.03

Head 10: 0.03

Head 11: 0.06

Positive logits

ensical2.08

Paraly2.06

dart2.00

monkey1.90

monkeys1.88

blinded1.86

bunny1.86

clown1.81

juggling1.76

naïve1.72

Stamford1.70

dodged1.68

Blazers1.65

broom1.63

vaccine1.63

paralyzed1.61

impartial1.59

ears1.58

owl1.58

sled1.58

Negative logits

ZI-1.87

minster-1.87

amura-1.81

auri-1.74

arez-1.74

jen-1.73

Reloaded-1.72

nants-1.72

dat-1.70

ieri-1.68

custom-1.68

tera-1.67

JO-1.63

Ger-1.62

itant-1.61

Quote-1.61

installs-1.61

xit-1.59

aeda-1.58

nikov-1.57

INTERVAL 2.990 - 3.322
CONTAINS 0.000%

course
Token course
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.000
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.338
eye
Token eye
Feature activation+3.008
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
military
Token military
Feature activation+0.000
coup
Token coup
Feature activation+0.000
ousted
Token ousted
Feature activation+0.000
no
Token no
Feature activation+0.000
further
Token further
Feature activation+0.000
deterioration
Token deterioration
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
sight
Token sight
Feature activation+3.322
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
tensions
Token tensions
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 2.658 - 2.990
CONTAINS 0.000%

left
Token left
Feature activation+0.000
almost
Token almost
Feature activation+0.000
blind
Token blind
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
eye
Token eye
Feature activation+2.764
and
Token and
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.453
to
Token to
Feature activation+0.000

INTERVAL 2.326 - 2.658
CONTAINS 0.000%

going
Token going
Feature activation+0.000
blind
Token blind
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
eye
Token eye
Feature activation+2.654
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
regular
Token regular
Feature activation+0.000
check
Token check
Feature activation+0.000

INTERVAL 1.993 - 2.326
CONTAINS 0.000%

is
Token is
Feature activation+0.000
completely
Token completely
Feature activation+0.000
turning
Token turning
Feature activation+0.000
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.000
eye
Token eye
Feature activation+2.141
to
Token to
Feature activation+0.000
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.661 - 1.993
CONTAINS 0.000%

fat
Token fat
Feature activation+0.000
.
Token.
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
vision
Token vision
Feature activation+1.728
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
o
Token o
Feature activation+0.000
phthal
Tokenphthal
Feature activation+0.270
m
Tokenm
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
visually
Token visually
Feature activation+1.976
impaired
Token impaired
Feature activation+1.172
person
Token person
Feature activation+0.168
to
Token to
Feature activation+0.000
head
Token head
Feature activation+1.025
the
Token the
Feature activation+0.000

INTERVAL 1.329 - 1.661
CONTAINS 0.000%

INTERVAL 0.997 - 1.329
CONTAINS 0.001%

,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+1.136
players
Token players
Feature activation+0.000
taking
Token taking
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
we
Token we
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
dece
Token dece
Feature activation+0.000
iving
Tokeniving
Feature activation+1.066
ourselves
Token ourselves
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
visually
Token visually
Feature activation+1.976
impaired
Token impaired
Feature activation+1.172
person
Token person
Feature activation+0.168
to
Token to
Feature activation+0.000
head
Token head
Feature activation+1.025
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
visually
Token visually
Feature activation+1.976
impaired
Token impaired
Feature activation+1.172
person
Token person
Feature activation+0.168
to
Token to
Feature activation+0.000
head
Token head
Feature activation+1.025
the
Token the
Feature activation+0.000
Senate
Token Senate
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
as
Token as
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+1.058
clubs
Token clubs
Feature activation+0.000
developed
Token developed
Feature activation+0.000
analytics
Token analytics
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 0.664 - 0.997
CONTAINS 0.001%

are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
completely
Token completely
Feature activation+0.000
colour
Token colour
Feature activation+0.000
-
Token-
Feature activation+0.000
blind
Tokenblind
Feature activation+0.835
.
Token.
Feature activation+0.358
Ċ
TokenĊ
Feature activation+0.052
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
day
Token day
Feature activation+0.000
also
Token also
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
face
Token face
Feature activation+0.220
discrimination
Token discrimination
Feature activation+0.000
when
Token when
Feature activation+0.000
looking
Token looking
Feature activation+0.781
for
Token for
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
or
Token or
Feature activation+0.000
places
Token places
Feature activation+0.000
to
Token to
Feature activation+0.000
royalties
Token royalties
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
ab
Token ab
Feature activation+0.000
rid
Tokenrid
Feature activation+0.000
ged
Tokenged
Feature activation+0.885
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000
Dream
TokenDream
Feature activation+0.000
s
Tokens
Feature activation+0.000
casually
Token casually
Feature activation+0.000
dropped
Token dropped
Feature activation+0.000
his
Token his
Feature activation+0.000
ab
Token ab
Feature activation+0.000
rid
Tokenrid
Feature activation+0.000
ged
Tokenged
Feature activation+0.783
rendition
Token rendition
Feature activation+0.000
of
Token of
Feature activation+0.000
Nikol
Token Nikol
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
G
Token G
Feature activation+0.000
than
Token than
Feature activation+0.000
taking
Token taking
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+0.908
Wall
Token Wall
Feature activation+0.000
Street
Token Street
Feature activation+0.000
firms
Token firms
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.000

INTERVAL 0.332 - 0.664
CONTAINS 0.001%

some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
deaf
Token deaf
Feature activation+0.000
and
Token and
Feature activation+0.000
hearing
Token hearing
Feature activation+0.357
-
Token-
Feature activation+0.000
im
Tokenim
Feature activation+0.000
pa
Tokenpa
Feature activation+0.000
ired
Tokenired
Feature activation+0.000
fans
Token fans
Feature activation+0.000
not
Token not
Feature activation+0.000
completely
Token completely
Feature activation+0.000
colour
Token colour
Feature activation+0.000
-
Token-
Feature activation+0.000
blind
Tokenblind
Feature activation+0.835
.
Token.
Feature activation+0.358
Ċ
TokenĊ
Feature activation+0.052
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
day
Token day
Feature activation+0.000
-
Token-
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
allegedly
Token allegedly
Feature activation+0.000
dece
Token dece
Feature activation+0.000
iving
Tokeniving
Feature activation+0.462
consumers
Token consumers
Feature activation+0.000
into
Token into
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
the
Token the
Feature activation+0.000
beverage
Token beverage
Feature activation+0.000
by
Token by
Feature activation+0.000
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+0.018
person
Token person
Feature activation+0.386
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
act
Token act
Feature activation+0.000
of
Token of
Feature activation+0.000
sacrifice
Token sacrifice
Feature activation+0.000
/
Token/
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
ering
Tokenering
Feature activation+0.399
/
Token/
Feature activation+0.000
w
Tokenw
Feature activation+0.000
orship
Tokenorship
Feature activation+0.000
ing
Tokening
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.332
CONTAINS 99.997%

is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
Ricky
Token Ricky
Feature activation+0.000
,
Token,
Feature activation+0.000
Julian
Token Julian
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Bub
Token Bub
Feature activation+0.000
bles
Tokenbles
Feature activation+0.000
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
They
TokenThey
Feature activation+0.000
killed
Token killed
Feature activation+0.000
him
Token him
Feature activation+0.000
by
Token by
Feature activation+0.000
punching
Token punching
Feature activation+0.000
and
Token and
Feature activation+0.000
kicking
Token kicking
Feature activation+0.000
him
Token him
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Many
TokenMany
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
,
Token,
Feature activation+0.000
Web
Token Web
Feature activation+0.000
design
Token design
Feature activation+0.000
or
Token or
Feature activation+0.000
information
Token information
Feature activation+0.000
technology
Token technology
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
and
Token and
Feature activation+0.000
cast
Token cast
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
community
Token community
Feature activation+0.000
's
Token's
Feature activation+0.000
conclusion
Token conclusion
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
indicates
Token indicates
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
some
Token some
Feature activation+0.000
basis
Token basis
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 3 in H1.6: (feature 8927)

TOP ACTIVATIONS
MAX = 3.273

-
Token-
Feature activation+0.000
different
Tokendifferent
Feature activation+0.330
couples
Token couples
Feature activation+0.568
where
Token where
Feature activation+0.000
one
Token one
Feature activation+2.374
partner
Token partner
Feature activation+3.273
was
Token was
Feature activation+0.000
HIV
Token HIV
Feature activation+0.000
positive
Token positive
Feature activation+0.000
and
Token and
Feature activation+0.000
undet
Token undet
Feature activation+0.000
That
TokenThat
Feature activation+0.000
ensures
Token ensures
Feature activation+0.000
that
Token that
Feature activation+0.000
marriages
Token marriages
Feature activation+0.651
are
Token are
Feature activation+0.000
performed
Token performed
Feature activation+3.045
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.000
fashion
Token fashion
Feature activation+0.000
."
Token."
Feature activation+0.000
able
Tokenable
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.985
partner
Token partner
Feature activation+2.983
was
Token was
Feature activation+0.000
HIV
Token HIV
Feature activation+0.000
negative
Token negative
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.965
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
couples
Token couples
Feature activation+1.456
who
Token who
Feature activation+0.460
get
Token get
Feature activation+0.270
together
Token together
Feature activation+2.900
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.074
of
Token of
Feature activation+0.000
movies
Token movies
Feature activation+0.000
les
Tokenles
Feature activation+0.000
ial
Tokenial
Feature activation+0.000
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
couple
Token couple
Feature activation+2.860
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
consent
Token consent
Feature activation+0.690
binds
Token binds
Feature activation+0.467
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
life
Token life
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.846
to
Token to
Feature activation+0.000
God
Token God
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
Cardinal
Token Cardinal
Feature activation+0.000
Gay
TokenGay
Feature activation+0.000
couples
Token couples
Feature activation+0.602
who
Token who
Feature activation+0.280
want
Token want
Feature activation+1.068
to
Token to
Feature activation+0.000
wed
Token wed
Feature activation+2.777
"
Token "
Feature activation+0.230
would
Tokenwould
Feature activation+0.329
suffer
Token suffer
Feature activation+0.562
many
Token many
Feature activation+0.368
hardships
Token hardships
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
app
Token app
Feature activation+0.000
ortion
Tokenortion
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.732
's
Token's
Feature activation+0.014
approximately
Token approximately
Feature activation+0.000
$
Token $
Feature activation+0.141
500
Token500
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Church
Token Church
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.682
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+1.264
seek
Token seek
Feature activation+0.279
to
Token to
Feature activation+0.000
enter
Token enter
Feature activation+0.000
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
logical
Token logical
Feature activation+0.000
union
Token union
Feature activation+2.625
with
Token with
Feature activation+0.648
porn
Token porn
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
a
Token a
Feature activation+0.000
another
Token another
Feature activation+0.516
through
Token through
Feature activation+0.000
Christ
Token Christ
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
couple
Token couple
Feature activation+2.563
becomes
Token becomes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
sacrament
Token sacrament
Feature activation+0.000
of
Token of
Feature activation+0.000
?
Token?
Feature activation+0.000
Surely
Token Surely
Feature activation+0.000
they
Token they
Feature activation+1.193
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
together
Token together
Feature activation+2.548
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
fulness
Tokenfulness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nu
Token nu
Feature activation+2.518
pt
Tokenpt
Feature activation+0.000
ial
Tokenial
Feature activation+0.000
mystery
Token mystery
Feature activation+0.000
solely
Token solely
Feature activation+0.028
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.074
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+2.440
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
foreseeable
Token foreseeable
Feature activation+0.000
future
Token future
Feature activation+0.000
,
Token,
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
fulness
Tokenfulness
Feature activation+0.000
granted
Token granted
Feature activation+0.234
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.391
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
o
Tokeno
Feature activation+0.000
-
Token-
Feature activation+0.000
different
Tokendifferent
Feature activation+0.330
couples
Token couples
Feature activation+0.568
where
Token where
Feature activation+0.000
one
Token one
Feature activation+2.374
partner
Token partner
Feature activation+3.273
was
Token was
Feature activation+0.000
HIV
Token HIV
Feature activation+0.000
positive
Token positive
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
their
Token their
Feature activation+1.533
characters
Token characters
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
together
Token together
Feature activation+2.368
forever
Token forever
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.325
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.023
task
Token task
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
equally
Token equally
Feature activation+0.000
shared
Token shared
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
parties
Token parties
Feature activation+2.280
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
an
Token an
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
offence
Token offence
Feature activation+0.000
where
Token where
Feature activation+0.000
unmarried
Token unmarried
Feature activation+0.768
men
Token men
Feature activation+1.898
and
Token and
Feature activation+0.000
women
Token women
Feature activation+1.294
are
Token are
Feature activation+0.000
found
Token found
Feature activation+0.095
together
Token together
Feature activation+0.938

Top DFA by src position
MAX = 4.084

PART
Token PART
Feature activation+0.001
Top resid features:
NER
TokenNER
Feature activation-0.022
Top resid features:
started
Token started
Feature activation-0.020
Top resid features:
enroll
Token enroll
Feature activation-0.038
Top resid features:
ing
Tokening
Feature activation-0.020
Top resid features:
couples
Token couples
Feature activation+3.148
Top resid features:
.
Token.
Feature activation-0.047
Top resid features:
They
Token They
Feature activation-0.014
Top resid features:
were
Token were
Feature activation-0.028
Top resid features:
looking
Token looking
Feature activation-0.024
Top resid features:
for
Token for
Feature activation-0.035
Top resid features:
.
Token.
Feature activation-0.040
Top resid features:
"
Token "
Feature activation-0.007
Top resid features:
That
TokenThat
Feature activation-0.026
Top resid features:
ensures
Token ensures
Feature activation-0.091
Top resid features:
that
Token that
Feature activation-0.084
Top resid features:
marriages
Token marriages
Feature activation+4.084
Top resid features:
are
Token are
Feature activation-0.075
Top resid features:
performed
Token performed
Feature activation-0.037
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
blind
Token blind
Feature activation+0.000
Top resid features:
PART
Token PART
Feature activation+0.003
Top resid features:
NER
TokenNER
Feature activation-0.005
Top resid features:
started
Token started
Feature activation-0.006
Top resid features:
enroll
Token enroll
Feature activation-0.028
Top resid features:
ing
Tokening
Feature activation-0.000
Top resid features:
couples
Token couples
Feature activation+2.978
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
were
Token were
Feature activation-0.006
Top resid features:
looking
Token looking
Feature activation-0.013
Top resid features:
for
Token for
Feature activation-0.010
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.007
Top resid features:
M
TokenM
Feature activation+0.015
Top resid features:
ovies
Tokenovies
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
which
Token which
Feature activation+0.006
Top resid features:
couples
Token couples
Feature activation+2.004
Top resid features:
overcome
Token overcome
Feature activation+0.013
Top resid features:
various
Token various
Feature activation-0.002
Top resid features:
misunderstand
Token misunderstand
Feature activation+0.028
Top resid features:
ings
Tokenings
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
thinking
Token thinking
Feature activation+0.001
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
sacrament
Token sacrament
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
marriage
Token marriage
Feature activation+2.502
Top resid features:
while
Token while
Feature activation+0.001
Top resid features:
teaching
Token teaching
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
course
Token course
Feature activation-0.014
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
fundamental
Token fundamental
Feature activation+0.039
Top resid features:
end
Token end
Feature activation+0.016
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
marriage
Token marriage
Feature activation+3.759
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
not
Token not
Feature activation-0.003
Top resid features:
reproduction
Token reproduction
Feature activation+0.035
Top resid features:
at
Token at
Feature activation-0.016
Top resid features:
all
Token all
Feature activation-0.003
Top resid features:
issued
Token issued
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation-0.035
Top resid features:
Ċ
TokenĊ
Feature activation-0.046
Top resid features:
Gay
TokenGay
Feature activation+0.126
Top resid features:
couples
Token couples
Feature activation+3.459
Top resid features:
who
Token who
Feature activation-0.095
Top resid features:
want
Token want
Feature activation-0.031
Top resid features:
to
Token to
Feature activation-0.066
Top resid features:
wed
Token wed
Feature activation+0.254
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
malicious
Token malicious
Feature activation-0.009
Top resid features:
attempt
Token attempt
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
prevent
Token prevent
Feature activation-0.008
Top resid features:
his
Token his
Feature activation-0.004
Top resid features:
wife
Token wife
Feature activation+1.169
Top resid features:
from
Token from
Feature activation-0.019
Top resid features:
recovering
Token recovering
Feature activation-0.031
Top resid features:
marital
Token marital
Feature activation+1.130
Top resid features:
assets
Token assets
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.065
Top resid features:
:
Token:
Feature activation-0.007
Top resid features:
A
Token A
Feature activation+0.006
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
ology
Tokenology
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Marriage
Token Marriage
Feature activation+1.657
Top resid features:
and
Token and
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Family
Token Family
Feature activation+0.009
Top resid features:
for
Token for
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.216
Top resid features:
an
Token an
Feature activation+0.056
Top resid features:
unlikely
Token unlikely
Feature activation-0.010
Top resid features:
marriage
Token marriage
Feature activation+3.571
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
early
Token early
Feature activation+0.002
Top resid features:
American
Token American
Feature activation+0.029
Top resid features:
history
Token history
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.033
Top resid features:
thinking
Token thinking
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
sacrament
Token sacrament
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
marriage
Token marriage
Feature activation+2.204
Top resid features:
while
Token while
Feature activation+0.003
Top resid features:
teaching
Token teaching
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
course
Token course
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.009
Top resid features:
M
TokenM
Feature activation+0.008
Top resid features:
ovies
Tokenovies
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
which
Token which
Feature activation+0.006
Top resid features:
couples
Token couples
Feature activation+1.757
Top resid features:
overcome
Token overcome
Feature activation+0.011
Top resid features:
various
Token various
Feature activation-0.002
Top resid features:
misunderstand
Token misunderstand
Feature activation+0.015
Top resid features:
ings
Tokenings
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
fulness
Tokenfulness
Feature activation-0.008
Top resid features:
within
Token within
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
sacrament
Token sacrament
Feature activation+0.028
Top resid features:
of
Token of
Feature activation-0.013
Top resid features:
marriage
Token marriage
Feature activation+3.034
Top resid features:
to
Token to
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
act
Token act
Feature activation+0.013
Top resid features:
of
Token of
Feature activation-0.013
Top resid features:
pro
Token pro
Feature activation-0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
Top resid features:
M
TokenM
Feature activation+0.013
Top resid features:
ovies
Tokenovies
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
which
Token which
Feature activation+0.007
Top resid features:
couples
Token couples
Feature activation+1.774
Top resid features:
overcome
Token overcome
Feature activation+0.013
Top resid features:
various
Token various
Feature activation-0.002
Top resid features:
misunderstand
Token misunderstand
Feature activation+0.023
Top resid features:
ings
Tokenings
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
A
Token A
Feature activation+0.003
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
ology
Tokenology
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Marriage
Token Marriage
Feature activation+1.281
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
Family
Token Family
Feature activation+0.006
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
PART
Token PART
Feature activation+0.003
Top resid features:
NER
TokenNER
Feature activation-0.017
Top resid features:
started
Token started
Feature activation-0.016
Top resid features:
enroll
Token enroll
Feature activation-0.029
Top resid features:
ing
Tokening
Feature activation-0.014
Top resid features:
couples
Token couples
Feature activation+2.242
Top resid features:
.
Token.
Feature activation-0.048
Top resid features:
They
Token They
Feature activation-0.014
Top resid features:
were
Token were
Feature activation-0.027
Top resid features:
looking
Token looking
Feature activation-0.034
Top resid features:
for
Token for
Feature activation-0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
Top resid features:
M
TokenM
Feature activation+0.020
Top resid features:
ovies
Tokenovies
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
which
Token which
Feature activation+0.005
Top resid features:
couples
Token couples
Feature activation+3.268
Top resid features:
overcome
Token overcome
Feature activation+0.017
Top resid features:
various
Token various
Feature activation-0.004
Top resid features:
misunderstand
Token misunderstand
Feature activation+0.042
Top resid features:
ings
Tokenings
Feature activation+0.016
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
that
Token that
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
fundamental
Token fundamental
Feature activation+0.013
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
marriage
Token marriage
Feature activation+1.125
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
not
Token not
Feature activation-0.008
Top resid features:
reproduction
Token reproduction
Feature activation+0.025
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
all
Token all
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
commencement
Token commencement
Feature activation-0.017
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
divorce
Token divorce
Feature activation+1.052
Top resid features:
action
Token action
Feature activation+0.008
Top resid features:
constitute
Token constitute
Feature activation-0.010
Top resid features:
marital
Token marital
Feature activation+0.522
Top resid features:
debt
Token debt
Feature activation+0.007
Top resid features:
which
Token which
Feature activation-0.015
Top resid features:
,
Token,
Feature activation-0.035
Top resid features:
an
Token an
Feature activation+0.008
Top resid features:
Islamic
Token Islamic
Feature activation-0.011
Top resid features:
offence
Token offence
Feature activation-0.014
Top resid features:
where
Token where
Feature activation-0.034
Top resid features:
unmarried
Token unmarried
Feature activation+1.355
Top resid features:
men
Token men
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.02

Head 3: 0.02

Head 4: 0.04

Head 5: 0.09

Head 6: 0.54

Head 7: 0.06

Head 8: 0.03

Head 9: 0.03

Head 10: 0.02

Head 11: 0.07

Positive logits

twins2.41

arenthood2.39

marriage2.36

divor2.24

Marriage2.19

equality2.17

marriage2.11

couples2.10

spouses2.08

spouse2.03

compan1.99

Loving1.97

divorce1.96

fiance1.93

marry1.93

wife1.92

Counsel1.91

solicitor1.91

marriages1.85

Family1.84

Negative logits

meteor-2.22

-2.06

nit-2.03

ompl-1.90

patrolling-1.86

Beam-1.82

monary-1.81

velength-1.78

actionGroup-1.76

Nare-1.73

iencies-1.73

ion-1.73

looting-1.72

scaven-1.71

Cavern-1.70

pellets-1.70

bunker-1.69

KN-1.68

projectile-1.66

replay-1.66

INTERVAL 2.946 - 3.273
CONTAINS 0.000%

-
Token-
Feature activation+0.000
different
Tokendifferent
Feature activation+0.330
couples
Token couples
Feature activation+0.568
where
Token where
Feature activation+0.000
one
Token one
Feature activation+2.374
partner
Token partner
Feature activation+3.273
was
Token was
Feature activation+0.000
HIV
Token HIV
Feature activation+0.000
positive
Token positive
Feature activation+0.000
and
Token and
Feature activation+0.000
undet
Token undet
Feature activation+0.000
able
Tokenable
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.985
partner
Token partner
Feature activation+2.983
was
Token was
Feature activation+0.000
HIV
Token HIV
Feature activation+0.000
negative
Token negative
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.965
That
TokenThat
Feature activation+0.000
ensures
Token ensures
Feature activation+0.000
that
Token that
Feature activation+0.000
marriages
Token marriages
Feature activation+0.651
are
Token are
Feature activation+0.000
performed
Token performed
Feature activation+3.045
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.000
fashion
Token fashion
Feature activation+0.000
."
Token."
Feature activation+0.000

INTERVAL 2.619 - 2.946
CONTAINS 0.001%

enter
Token enter
Feature activation+0.000
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
logical
Token logical
Feature activation+0.000
union
Token union
Feature activation+2.625
with
Token with
Feature activation+0.648
porn
Token porn
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
a
Token a
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
couples
Token couples
Feature activation+1.456
who
Token who
Feature activation+0.460
get
Token get
Feature activation+0.270
together
Token together
Feature activation+2.900
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.074
of
Token of
Feature activation+0.000
movies
Token movies
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Church
Token Church
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.682
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+1.264
seek
Token seek
Feature activation+0.279
to
Token to
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
app
Token app
Feature activation+0.000
ortion
Tokenortion
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.732
's
Token's
Feature activation+0.014
approximately
Token approximately
Feature activation+0.000
$
Token $
Feature activation+0.141
500
Token500
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
life
Token life
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.846
to
Token to
Feature activation+0.000
God
Token God
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
Cardinal
Token Cardinal
Feature activation+0.000

INTERVAL 2.291 - 2.619
CONTAINS 0.001%

that
Token that
Feature activation+0.000
their
Token their
Feature activation+1.533
characters
Token characters
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
together
Token together
Feature activation+2.368
forever
Token forever
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+2.325
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.023
task
Token task
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
fulness
Tokenfulness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nu
Token nu
Feature activation+2.518
pt
Tokenpt
Feature activation+0.000
ial
Tokenial
Feature activation+0.000
mystery
Token mystery
Feature activation+0.000
solely
Token solely
Feature activation+0.028
in
Token in
Feature activation+0.000
?
Token?
Feature activation+0.000
Surely
Token Surely
Feature activation+0.000
they
Token they
Feature activation+1.193
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
together
Token together
Feature activation+2.548
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
another
Token another
Feature activation+0.516
through
Token through
Feature activation+0.000
Christ
Token Christ
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
couple
Token couple
Feature activation+2.563
becomes
Token becomes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
sacrament
Token sacrament
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.964 - 2.291
CONTAINS 0.000%

be
Token be
Feature activation+0.000
equally
Token equally
Feature activation+0.000
shared
Token shared
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
parties
Token parties
Feature activation+2.280
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000

INTERVAL 1.637 - 1.964
CONTAINS 0.002%

Researchers
Token Researchers
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
couples
Token couples
Feature activation+0.961
âĢĶ
TokenâĢĶ
Feature activation+0.000
both
Tokenboth
Feature activation+1.646
men
Token men
Feature activation+1.605
and
Token and
Feature activation+0.021
women
Token women
Feature activation+0.950
!
Token!
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
mother
Token mother
Feature activation+0.000
passed
Token passed
Feature activation+0.000
away
Token away
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
couple
Token couple
Feature activation+1.726
's
Token's
Feature activation+0.000
net
Token net
Feature activation+0.000
worth
Token worth
Feature activation+0.000
skyrocket
Token skyrocket
Feature activation+0.000
ed
Tokened
Feature activation+0.000
only
Token only
Feature activation+0.000
route
Token route
Feature activation+0.000
to
Token to
Feature activation+0.000
having
Token having
Feature activation+1.210
a
Token a
Feature activation+0.108
baby
Token baby
Feature activation+1.821
is
Token is
Feature activation+0.000
international
Token international
Feature activation+0.000
surrog
Token surrog
Feature activation+1.342
acy
Tokenacy
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
relationships
Token relationships
Feature activation+1.836
beginning
Token beginning
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Token for
Feature activation+0.000
straight
Token straight
Feature activation+0.799
couples
Token couples
Feature activation+1.104
,
Token,
Feature activation+0.000
whose
Token whose
Feature activation+0.000
marriages
Token marriages
Feature activation+1.831
are
Token are
Feature activation+0.000
protected
Token protected
Feature activation+0.000
by
Token by
Feature activation+0.000
laws
Token laws
Feature activation+0.000
dict
Token dict
Feature activation+0.000

INTERVAL 1.309 - 1.637
CONTAINS 0.003%

it
Token it
Feature activation+0.000
."
Token."
Feature activation+0.000
He
Token He
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
partner
Token partner
Feature activation+1.361
regard
Token regard
Feature activation+0.176
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.158
law
Token law
Feature activation+0.000
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
divorce
Token divorce
Feature activation+1.350
action
Token action
Feature activation+0.000
constitute
Token constitute
Feature activation+0.000
marital
Token marital
Feature activation+1.592
debt
Token debt
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+0.000
under
Token under
Feature activation+0.000
normal
Token normal
Feature activation+0.000
first
Token first
Feature activation+0.000
European
Token European
Feature activation+0.000
women
Token women
Feature activation+0.327
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
vows
Token vows
Feature activation+1.589
as
Token as
Feature activation+0.000
Tibetan
Token Tibetan
Feature activation+0.000
Buddhist
Token Buddhist
Feature activation+0.000
nun
Token nun
Feature activation+0.000
.
Token.
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
:
Token:
Feature activation+0.000
assuming
Token assuming
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
couples
Token couples
Feature activation+1.456
who
Token who
Feature activation+0.460
get
Token get
Feature activation+0.270
together
Token together
Feature activation+2.900
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
get
Token get
Feature activation+0.077
a
Token a
Feature activation+0.056
domestic
Token domestic
Feature activation+1.424
partnership
Token partnership
Feature activation+0.478
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.982 - 1.309
CONTAINS 0.004%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
relieved
Token relieved
Feature activation+0.200
she
Token she
Feature activation+0.545
broke
Token broke
Feature activation+1.064
up
Token up
Feature activation+0.000
with
Token with
Feature activation+0.085
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
already
Token already
Feature activation+0.000
allow
Token allow
Feature activation+0.000
gay
Token gay
Feature activation+0.557
couples
Token couples
Feature activation+0.782
to
Token to
Feature activation+0.000
marry
Token marry
Feature activation+1.267
.
Token.
Feature activation+0.000
New
Token New
Feature activation+0.000
Jersey
Token Jersey
Feature activation+0.000
offers
Token offers
Feature activation+0.540
gay
Token gay
Feature activation+0.327
wedding
Token wedding
Feature activation+0.000
dress
Token dress
Feature activation+0.408
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.000
even
Token even
Feature activation+0.000
proposed
Token proposed
Feature activation+1.241
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
one
Token one
Feature activation+0.049
you
Token you
Feature activation+0.000
Pin
Token Pin
Feature activation+0.000
ology
Tokenology
Feature activation+0.000
of
Token of
Feature activation+0.000
Marriage
Token Marriage
Feature activation+0.208
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Family
Token Family
Feature activation+1.058
for
Token for
Feature activation+0.173
the
Token the
Feature activation+0.046
New
Token New
Feature activation+0.000
Evangel
Token Evangel
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
.
Token.
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
for
Token for
Feature activation+0.000
straight
Token straight
Feature activation+0.799
couples
Token couples
Feature activation+1.104
,
Token,
Feature activation+0.000
whose
Token whose
Feature activation+0.000
marriages
Token marriages
Feature activation+1.831
are
Token are
Feature activation+0.000
protected
Token protected
Feature activation+0.000

INTERVAL 0.655 - 0.982
CONTAINS 0.008%

man
Token man
Feature activation+0.865
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.236
a
Token a
Feature activation+0.000
fraught
Token fraught
Feature activation+0.000
affair
Token affair
Feature activation+0.692
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
crush
Token crush
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
how
Token how
Feature activation+0.000
her
Token her
Feature activation+0.000
husband
Token husband
Feature activation+0.000
cheated
Token cheated
Feature activation+0.786
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.214
because
Token because
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.095
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
more
Token more
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
breakup
Token breakup
Feature activation+0.961
.
Token.
Feature activation+0.000
Truth
Token Truth
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
similar
Token similar
Feature activation+0.000
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.704
action
Token action
Feature activation+0.188
role
Token role
Feature activation+0.000
play
Token play
Feature activation+0.000
--
Token --
Feature activation+0.000
it
Token it
Feature activation+0.000
you
Token you
Feature activation+0.000
how
Token how
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+0.000
their
Token their
Feature activation+0.390
divorce
Token divorce
Feature activation+0.823
his
Token his
Feature activation+0.224
painful
Token painful
Feature activation+0.301
words
Token words
Feature activation+0.000
led
Token led
Feature activation+0.000
her
Token her
Feature activation+0.182

INTERVAL 0.327 - 0.655
CONTAINS 0.021%

or
Token or
Feature activation+0.000
may
Token may
Feature activation+0.000
not
Token not
Feature activation+0.000
make
Token make
Feature activation+0.021
the
Token the
Feature activation+0.000
contract
Token contract
Feature activation+0.378
or
Token or
Feature activation+0.000
imposing
Token imposing
Feature activation+0.040
any
Token any
Feature activation+0.000
prior
Token prior
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
's
Token's
Feature activation+0.000
income
Token income
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.379
can
Token can
Feature activation+0.000
afford
Token afford
Feature activation+0.412
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
another
Token another
Feature activation+0.064
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.379
can
Token can
Feature activation+0.000
afford
Token afford
Feature activation+0.412
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
another
Token another
Feature activation+0.064
wife
Token wife
Feature activation+0.393
and
Token and
Feature activation+0.000
family
Token family
Feature activation+0.879
knew
Token knew
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
love
Token love
Feature activation+0.554
with
Token with
Feature activation+0.174
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
but
Token but
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Because
TokenBecause
Feature activation+0.000
they
Token they
Feature activation+0.817
belong
Token belong
Feature activation+0.503
to
Token to
Feature activation+0.000
Christ
Token Christ
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.327
CONTAINS 99.961%

centres
Token centres
Feature activation+0.000
which
Token which
Feature activation+0.000
usually
Token usually
Feature activation+0.000
feature
Token feature
Feature activation+0.000
Wal
Token Wal
Feature activation+0.000
-
Token-
Feature activation+0.000
Mart
TokenMart
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
anchor
Token anchor
Feature activation+0.000
tenant
Token tenant
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
personality
Token personality
Feature activation+0.000
,
Token,
Feature activation+0.000
playing
Token playing
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
chip
Token chip
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
shoulder
Token shoulder
Feature activation+0.000
Unt
Token Unt
Feature activation+0.000
old
Tokenold
Feature activation+0.000
Stories
Token Stories
Feature activation+0.000
and
Token and
Feature activation+0.000
L
Token L
Feature activation+0.000
argo
Tokenargo
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Unt
Token Unt
Feature activation+0.000
old
Tokenold
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.000
au
Tokenau
Feature activation+0.000
ffen
Tokenffen
Feature activation+0.000
bach
Tokenbach
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
invited
Token invited
Feature activation+0.000
to
Token to
Feature activation+0.000
Super
Token Super
Feature activation+0.000
visors
Tokenvisors
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Rachel
TokenRachel
Feature activation+0.000
Swan
Token Swan
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H1.6: (feature 6571)

TOP ACTIVATIONS
MAX = 2.619

district
Token district
Feature activation+0.000
and
Token and
Feature activation+0.000
offered
Token offered
Feature activation+0.000
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
between
Token between
Feature activation+2.619
starvation
Token starvation
Feature activation+0.000
and
Token and
Feature activation+0.000
surrender
Token surrender
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.241
',
Token',
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
or
Token or
Feature activation+2.399
they
Token they
Feature activation+0.000
won
Token won
Feature activation+0.702
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
voting
Token voting
Feature activation+0.000
over
Token over
Feature activation+0.408
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+2.215
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.109
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
ancient
Token ancient
Feature activation+0.000
woodland
Token woodland
Feature activation+0.000
clearing
Token clearing
Feature activation+0.000
or
Token or
Feature activation+2.187
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.135
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
made
Token made
Feature activation+2.184
for
Token for
Feature activation+0.028
reasons
Token reasons
Feature activation+0.000
of
Token of
Feature activation+0.000
cost
Token cost
Feature activation+0.000
.
Token.
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
or
Token or
Feature activation+2.149
a
Token a
Feature activation+0.000
circus
Token circus
Feature activation+0.000
clown
Token clown
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
choice
Token choice
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
personally
Token personally
Feature activation+0.000
never
Token never
Feature activation+0.000
make
Token make
Feature activation+2.043
âĢĵ
Token âĢĵ
Feature activation+0.000
I
Token I
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
I
Token I
Feature activation+0.018
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ever
Token ever
Feature activation+0.000
made
Token made
Feature activation+1.979
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
all
Token all
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
or
Token or
Feature activation+1.946
die
Token die
Feature activation+0.000
.
Token.
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
-
Token-
Feature activation+0.000
El
TokenEl
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
lifestyle
Token lifestyle
Feature activation+0.000
choices
Token choices
Feature activation+0.034
they
Token they
Feature activation+0.000
make
Token make
Feature activation+1.941
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
.
Token.
Feature activation+0.000
Given
Token Given
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
between
Token between
Feature activation+1.833
Cruz
Token Cruz
Feature activation+0.000
and
Token and
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
map
Token map
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+1.807
guild
Token guild
Feature activation+0.000
survival
Token survival
Feature activation+0.000
arena
Token arena
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.719
the
Token the
Feature activation+0.000
Communists
Token Communists
Feature activation+0.000
would
Token would
Feature activation+0.000
win
Token win
Feature activation+0.277
.
Token.
Feature activation+0.000
could
Token could
Feature activation+0.000
choose
Token choose
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
tablets
Token tablets
Feature activation+0.000
or
Token or
Feature activation+1.479
use
Token use
Feature activation+0.000
fluoride
Token fluoride
Feature activation+0.000
in
Token in
Feature activation+0.000
another
Token another
Feature activation+0.000
form
Token form
Feature activation+0.000
design
Token design
Feature activation+0.000
choices
Token choices
Feature activation+0.195
regarding
Token regarding
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
-
Token-
Feature activation+0.000
Based
TokenBased
Feature activation+1.425
combat
Token combat
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
will
Token will
Feature activation+0.066
be
Token be
Feature activation+0.000
MD
TokenMD
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
would
Token would
Feature activation+0.109
you
Token you
Feature activation+0.000
pick
Token pick
Feature activation+1.415
?
Token?
Feature activation+0.000
More
Token More
Feature activation+0.000
than
Token than
Feature activation+0.000
likely
Token likely
Feature activation+0.000
,
Token,
Feature activation+0.000
finish
Token finish
Feature activation+0.000
(
Token (
Feature activation+0.000
choice
Tokenchoice
Feature activation+0.127
of
Token of
Feature activation+0.000
black
Token black
Feature activation+0.000
or
Token or
Feature activation+1.387
white
Token white
Feature activation+0.000
).
Token).
Feature activation+0.000
An
Token An
Feature activation+0.000
elastic
Token elastic
Feature activation+0.000
band
Token band
Feature activation+0.000
rodent
Token rodent
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
mar
Token mar
Feature activation+0.000
a
Tokena
Feature activation+0.000
or
Token or
Feature activation+1.382
Pat
Token Pat
Feature activation+0.000
agon
Tokenagon
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
c
Token c
Feature activation+0.000
avy
Tokenavy
Feature activation+0.000
whether
Token whether
Feature activation+0.000
their
Token their
Feature activation+0.000
answers
Token answers
Feature activation+0.000
were
Token were
Feature activation+0.000
correct
Token correct
Feature activation+0.000
or
Token or
Feature activation+1.356
incorrect
Token incorrect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Professor
TokenProfessor
Feature activation+0.000
than
Token than
Feature activation+0.000
likely
Token likely
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
would
Token would
Feature activation+0.110
pick
Token pick
Feature activation+1.337
the
Token the
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
most
Token most
Feature activation+0.179
prepared
Token prepared
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 3.792

rebel
Token rebel
Feature activation+0.028
Top resid features:
district
Token district
Feature activation+0.041
Top resid features:
and
Token and
Feature activation-0.037
Top resid features:
offered
Token offered
Feature activation-0.112
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
choice
Token choice
Feature activation+3.792
Top resid features:
between
Token between
Feature activation-0.015
Top resid features:
starvation
Token starvation
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
surrender
Token surrender
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
that
Tokenthat
Feature activation+0.006
Top resid features:
',
Token',
Feature activation-0.108
Top resid features:
they
Token they
Feature activation+0.019
Top resid features:
have
Token have
Feature activation+0.013
Top resid features:
no
Token no
Feature activation+0.171
Top resid features:
choice
Token choice
Feature activation+3.467
Top resid features:
or
Token or
Feature activation+0.036
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
won
Token won
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.041
Top resid features:
exposes
Token exposes
Feature activation+0.013
Top resid features:
their
Token their
Feature activation+0.087
Top resid features:
choices
Token choices
Feature activation+2.865
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
people
Token people
Feature activation+0.031
Top resid features:
who
Token who
Feature activation+0.038
Top resid features:
may
Token may
Feature activation+0.038
Top resid features:
have
Token have
Feature activation+0.053
Top resid features:
tend
Token tend
Feature activation+0.037
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
activities
Token activities
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
choice
Token choice
Feature activation+3.356
Top resid features:
.
Token.
Feature activation-0.066
Top resid features:
Throw
Token Throw
Feature activation+0.051
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
an
Token an
Feature activation+0.036
Top resid features:
ancient
Token ancient
Feature activation+0.035
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.085
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
The
TokenThe
Feature activation+0.137
Top resid features:
choice
Token choice
Feature activation+3.354
Top resid features:
has
Token has
Feature activation+0.073
Top resid features:
been
Token been
Feature activation+0.056
Top resid features:
made
Token made
Feature activation+0.028
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
reasons
Token reasons
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.027
Top resid features:
moment
Token moment
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.008
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
choice
Token choice
Feature activation+3.044
Top resid features:
about
Token about
Feature activation-0.000
Top resid features:
who
Token who
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.014
Top resid features:
am
Token am
Feature activation+0.005
Top resid features:
becoming
Token becoming
Feature activation+0.027
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
six
Token six
Feature activation+0.014
Top resid features:
months
Token months
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
choice
Token choice
Feature activation+3.139
Top resid features:
I
Token I
Feature activation+0.017
Top resid features:
would
Token would
Feature activation+0.003
Top resid features:
personally
Token personally
Feature activation+0.043
Top resid features:
never
Token never
Feature activation+0.071
Top resid features:
make
Token make
Feature activation-0.046
Top resid features:
beginning
Token beginning
Feature activation+0.020
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
re
Token re
Feature activation+0.023
Top resid features:
thinking
Tokenthinking
Feature activation+0.052
Top resid features:
every
Token every
Feature activation+0.035
Top resid features:
choice
Token choice
Feature activation+2.928
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.060
Top resid features:
Ļ
TokenĻ
Feature activation+0.023
Top resid features:
ve
Tokenve
Feature activation+0.083
Top resid features:
ever
Token ever
Feature activation+0.011
Top resid features:
D
Token D
Feature activation+0.008
Top resid features:
ax
Tokenax
Feature activation+0.030
Top resid features:
am
Tokenam
Feature activation+0.013
Top resid features:
ites
Tokenites
Feature activation+0.022
Top resid features:
no
Token no
Feature activation+0.124
Top resid features:
choice
Token choice
Feature activation+2.740
Top resid features:
but
Token but
Feature activation-0.026
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
leave
Token leave
Feature activation+0.036
Top resid features:
or
Token or
Feature activation+0.060
Top resid features:
die
Token die
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
but
Token but
Feature activation+0.041
Top resid features:
by
Token by
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.105
Top resid features:
lifestyle
Token lifestyle
Feature activation+0.254
Top resid features:
choices
Token choices
Feature activation+2.749
Top resid features:
they
Token they
Feature activation+0.172
Top resid features:
make
Token make
Feature activation-0.170
Top resid features:
.[
Token.[
Feature activation+0.000
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Ted
Token Ted
Feature activation+0.061
Top resid features:
Cruz
Token Cruz
Feature activation+0.090
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
Given
Token Given
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.122
Top resid features:
choice
Token choice
Feature activation+2.950
Top resid features:
between
Token between
Feature activation+0.034
Top resid features:
Cruz
Token Cruz
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Players
TokenPlayers
Feature activation+0.056
Top resid features:
can
Token can
Feature activation+0.274
Top resid features:
now
Token now
Feature activation+0.006
Top resid features:
choose
Token choose
Feature activation+2.519
Top resid features:
which
Token which
Feature activation-0.010
Top resid features:
map
Token map
Feature activation+0.032
Top resid features:
to
Token to
Feature activation-0.026
Top resid features:
start
Token start
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.070
Top resid features:
traditions
Token traditions
Feature activation+0.010
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.004
Top resid features:
had
Token had
Feature activation+0.001
Top resid features:
no
Token no
Feature activation+0.136
Top resid features:
choice
Token choice
Feature activation+2.374
Top resid features:
but
Token but
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
go
Token go
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
He
TokenHe
Feature activation+0.012
Top resid features:
said
Token said
Feature activation-0.049
Top resid features:
people
Token people
Feature activation+0.037
Top resid features:
could
Token could
Feature activation+0.178
Top resid features:
choose
Token choose
Feature activation+2.249
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
take
Token take
Feature activation+0.008
Top resid features:
tablets
Token tablets
Feature activation+0.115
Top resid features:
or
Token or
Feature activation+0.128
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.029
Top resid features:
common
Token common
Feature activation+0.047
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
interesting
Token interesting
Feature activation+0.042
Top resid features:
design
Token design
Feature activation+0.119
Top resid features:
choices
Token choices
Feature activation+1.880
Top resid features:
regarding
Token regarding
Feature activation-0.024
Top resid features:
Turn
Token Turn
Feature activation+0.228
Top resid features:
-
Token-
Feature activation-0.170
Top resid features:
Based
TokenBased
Feature activation-0.059
Top resid features:
combat
Token combat
Feature activation+0.000
Top resid features:
came
Token came
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
?
Token?
Feature activation+0.015
Top resid features:
If
Token If
Feature activation+0.010
Top resid features:
your
Token your
Feature activation+0.021
Top resid features:
options
Token options
Feature activation+2.396
Top resid features:
were
Token were
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
Harvard
Token Harvard
Feature activation-0.002
Top resid features:
graduate
Token graduate
Feature activation+0.004
Top resid features:
who
Token who
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
faux
Token faux
Feature activation+0.013
Top resid features:
leather
Token leather
Feature activation+0.047
Top resid features:
finish
Token finish
Feature activation+0.017
Top resid features:
(
Token (
Feature activation-0.046
Top resid features:
choice
Tokenchoice
Feature activation+2.095
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
black
Token black
Feature activation+0.100
Top resid features:
or
Token or
Feature activation+0.011
Top resid features:
white
Token white
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
o
Tokeno
Feature activation+0.002
Top resid features:
name
Token name
Feature activation+0.005
Top resid features:
stamp
Token stamp
Feature activation-0.004
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.005
Top resid features:
choice
Token choice
Feature activation+2.039
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
unusual
Token unusual
Feature activation+0.007
Top resid features:
animal
Token animal
Feature activation-0.001
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
subjects
Token subjects
Feature activation-0.015
Top resid features:
tried
Token tried
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
make
Token make
Feature activation+0.020
Top resid features:
their
Token their
Feature activation+0.029
Top resid features:
choice
Token choice
Feature activation+1.910
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
immediately
Token immediately
Feature activation-0.016
Top resid features:
after
Token after
Feature activation-0.018
Top resid features:
feedback
Token feedback
Feature activation+0.078
Top resid features:
came
Token came
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
?
Token?
Feature activation+0.013
Top resid features:
If
Token If
Feature activation+0.008
Top resid features:
your
Token your
Feature activation+0.019
Top resid features:
options
Token options
Feature activation+2.125
Top resid features:
were
Token were
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
Harvard
Token Harvard
Feature activation-0.003
Top resid features:
graduate
Token graduate
Feature activation-0.000
Top resid features:
who
Token who
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.04

Head 3: 0.02

Head 4: 0.04

Head 5: 0.05

Head 6: 0.54

Head 7: 0.05

Head 8: 0.02

Head 9: 0.02

Head 10: 0.03

Head 11: 0.06

Positive logits

choices3.04

choice2.73

selections2.44

options2.44

selection2.31

CHO2.24

option2.17

Choice2.17

alternatives2.15

chose2.10

preferences2.09

choosing2.02

utilitarian2.00

choice1.96

Option1.96

customization1.95

convenience1.94

simplicity1.93

pairing1.93

selecting1.91

Negative logits

bad-2.02

monton-2.01

forestation-1.97

dig-1.92

worm-1.90

trace-1.86

auri-1.86

dro-1.80

recorded-1.78

awar-1.76

adal-1.76

ujah-1.75

anus-1.75

oen-1.74

wave-1.73

surface-1.73

deep-1.72

ongo-1.72

gur-1.71

heres-1.71

INTERVAL 2.357 - 2.619
CONTAINS 0.000%

district
Token district
Feature activation+0.000
and
Token and
Feature activation+0.000
offered
Token offered
Feature activation+0.000
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
between
Token between
Feature activation+2.619
starvation
Token starvation
Feature activation+0.000
and
Token and
Feature activation+0.000
surrender
Token surrender
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.241
',
Token',
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
or
Token or
Feature activation+2.399
they
Token they
Feature activation+0.000
won
Token won
Feature activation+0.702
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000

INTERVAL 2.095 - 2.357
CONTAINS 0.000%

want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
or
Token or
Feature activation+2.149
a
Token a
Feature activation+0.000
circus
Token circus
Feature activation+0.000
clown
Token clown
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
voting
Token voting
Feature activation+0.000
over
Token over
Feature activation+0.408
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+2.215
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.109
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
ancient
Token ancient
Feature activation+0.000
woodland
Token woodland
Feature activation+0.000
clearing
Token clearing
Feature activation+0.000
or
Token or
Feature activation+2.187
state
Token state
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.135
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
made
Token made
Feature activation+2.184
for
Token for
Feature activation+0.028
reasons
Token reasons
Feature activation+0.000
of
Token of
Feature activation+0.000
cost
Token cost
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.833 - 2.095
CONTAINS 0.000%

choice
Token choice
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
personally
Token personally
Feature activation+0.000
never
Token never
Feature activation+0.000
make
Token make
Feature activation+2.043
âĢĵ
Token âĢĵ
Feature activation+0.000
I
Token I
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
lifestyle
Token lifestyle
Feature activation+0.000
choices
Token choices
Feature activation+0.034
they
Token they
Feature activation+0.000
make
Token make
Feature activation+1.941
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
Token I
Feature activation+0.018
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ever
Token ever
Feature activation+0.000
made
Token made
Feature activation+1.979
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
all
Token all
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
or
Token or
Feature activation+1.946
die
Token die
Feature activation+0.000
.
Token.
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
-
Token-
Feature activation+0.000
El
TokenEl
Feature activation+0.000

INTERVAL 1.571 - 1.833
CONTAINS 0.000%

Cruz
Token Cruz
Feature activation+0.000
.
Token.
Feature activation+0.000
Given
Token Given
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
between
Token between
Feature activation+1.833
Cruz
Token Cruz
Feature activation+0.000
and
Token and
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
map
Token map
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+1.807
guild
Token guild
Feature activation+0.000
survival
Token survival
Feature activation+0.000
arena
Token arena
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.719
the
Token the
Feature activation+0.000
Communists
Token Communists
Feature activation+0.000
would
Token would
Feature activation+0.000
win
Token win
Feature activation+0.277
.
Token.
Feature activation+0.000

INTERVAL 1.309 - 1.571
CONTAINS 0.001%

could
Token could
Feature activation+0.000
choose
Token choose
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
tablets
Token tablets
Feature activation+0.000
or
Token or
Feature activation+1.479
use
Token use
Feature activation+0.000
fluoride
Token fluoride
Feature activation+0.000
in
Token in
Feature activation+0.000
another
Token another
Feature activation+0.000
form
Token form
Feature activation+0.000
finish
Token finish
Feature activation+0.000
(
Token (
Feature activation+0.000
choice
Tokenchoice
Feature activation+0.127
of
Token of
Feature activation+0.000
black
Token black
Feature activation+0.000
or
Token or
Feature activation+1.387
white
Token white
Feature activation+0.000
).
Token).
Feature activation+0.000
An
Token An
Feature activation+0.000
elastic
Token elastic
Feature activation+0.000
band
Token band
Feature activation+0.000
rodent
Token rodent
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
mar
Token mar
Feature activation+0.000
a
Tokena
Feature activation+0.000
or
Token or
Feature activation+1.382
Pat
Token Pat
Feature activation+0.000
agon
Tokenagon
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
c
Token c
Feature activation+0.000
avy
Tokenavy
Feature activation+0.000
than
Token than
Feature activation+0.000
likely
Token likely
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
would
Token would
Feature activation+0.110
pick
Token pick
Feature activation+1.337
the
Token the
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
most
Token most
Feature activation+0.179
prepared
Token prepared
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
their
Token their
Feature activation+0.000
answers
Token answers
Feature activation+0.000
were
Token were
Feature activation+0.000
correct
Token correct
Feature activation+0.000
or
Token or
Feature activation+1.356
incorrect
Token incorrect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Professor
TokenProfessor
Feature activation+0.000

INTERVAL 1.048 - 1.309
CONTAINS 0.000%

when
Token when
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
other
Token other
Feature activation+0.000
choice
Token choice
Feature activation+1.049
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
necessarily
Token necessarily
Feature activation+0.000
between
Token between
Feature activation+2.619
starvation
Token starvation
Feature activation+0.000
and
Token and
Feature activation+0.000
surrender
Token surrender
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.241
a
Token a
Feature activation+0.000
halt
Token halt
Feature activation+0.000
to
Token to
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.786 - 1.048
CONTAINS 0.001%

.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
chose
Token chose
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
State
Token State
Feature activation+0.000
based
Token based
Feature activation+1.040
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+0.000
acity
Tokenacity
Feature activation+0.000
to
Token to
Feature activation+0.000
50
Token 50
Feature activation+0.000
%
Token%
Feature activation+0.000
and
Token and
Feature activation+0.000
choose
Token choose
Feature activation+0.793
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
edged
Tokenedged
Feature activation+0.000
brush
Token brush
Feature activation+0.000
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Cho
TokenCho
Feature activation+0.000
osing
Tokenosing
Feature activation+0.838
wisely
Token wisely
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
,
Token,
Feature activation+0.000
invited
Token invited
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
take
Token take
Feature activation+0.000
out
Token out
Feature activation+0.000
their
Token their
Feature activation+0.000
turrets
Token turrets
Feature activation+0.000
or
Token or
Feature activation+0.975
target
Token target
Feature activation+0.000
weak
Token weak
Feature activation+0.000
-
Token-
Feature activation+0.000
points
Tokenpoints
Feature activation+0.000
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
between
Token between
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
5
Token 5
Feature activation+0.000
or
Token or
Feature activation+0.849
10
Token 10
Feature activation+0.000
videos
Token videos
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
type
Token type
Feature activation+0.000

INTERVAL 0.524 - 0.786
CONTAINS 0.003%

the
Token the
Feature activation+0.000
forefront
Token forefront
Feature activation+0.000
of
Token of
Feature activation+0.000
medicine
Token medicine
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.582
someone
Token someone
Feature activation+0.000
âĢĭ
TokenâĢĭ
Feature activation+0.000
who
Token who
Feature activation+0.000
took
Token took
Feature activation+0.000
some
Token some
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
or
Token or
Feature activation+2.399
they
Token they
Feature activation+0.000
won
Token won
Feature activation+0.702
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
ate
Tokenate
Feature activation+0.297
sources
Token sources
Feature activation+0.000
of
Token of
Feature activation+0.000
funding
Token funding
Feature activation+0.000
"
Token"
Feature activation+0.000
or
Token or
Feature activation+0.733
the
Token the
Feature activation+0.000
status
Token status
Feature activation+0.000
quo
Token quo
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
that
Token that
Feature activation+0.000
Kelly
Token Kelly
Feature activation+0.000
cove
Token cove
Feature activation+0.000
ts
Tokents
Feature activation+0.534
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
offense
Token offense
Feature activation+0.000
,
Token,
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
they
Token they
Feature activation+0.000
choose
Token choose
Feature activation+0.214
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
from
Token from
Feature activation+0.552
Tra
Token Tra
Feature activation+0.000
verse
Tokenverse
Feature activation+0.000
City
Token City
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.262 - 0.524
CONTAINS 0.008%

=
Token=
Feature activation+0.000
1
Token1
Feature activation+0.000
;
Token;
Feature activation+0.000
Select
Token Select
Feature activation+0.000
*
Token *
Feature activation+0.000
from
Token from
Feature activation+0.480
users
Token users
Feature activation+0.000
;
Token ;
Feature activation+0.000
--
Token --
Feature activation+0.000
"
Token"
Feature activation+0.000
if
Token if
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
discriminate
Token discriminate
Feature activation+0.000
based
Token based
Feature activation+0.359
on
Token on
Feature activation+0.000
age
Token age
Feature activation+0.000
.
Token.
Feature activation+0.000
McMahon
Token McMahon
Feature activation+0.000
may
Token may
Feature activation+0.000
,
Token,
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
can
Token can
Feature activation+0.000
chose
Token chose
Feature activation+0.000
his
Token his
Feature activation+0.000
or
Token or
Feature activation+0.341
her
Token her
Feature activation+0.000
partner
Token partner
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
he
Token he
Feature activation+0.000
LSU
Token LSU
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+0.403
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.521
case
Token case
Feature activation+0.000
scenario
Token scenario
Feature activation+0.000
,
Token,
Feature activation+0.000
trade
Token trade
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
opt
Tokenopt
Feature activation+0.000
imal
Tokenimal
Feature activation+0.343
control
Token control
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
speeches
Token speeches
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 0.262
CONTAINS 99.986%

used
Token used
Feature activation+0.000
by
Token by
Feature activation+0.000
custom
Token custom
Feature activation+0.000
wra
Token wra
Feature activation+0.000
ppers
Tokenppers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Latest
TokenLatest
Feature activation+0.000
version
Token version
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
deserve
Token deserve
Feature activation+0.000
,
Token,
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
African
Token African
Feature activation+0.000
American
Token American
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
(
Token (
Feature activation+0.000
58
Token58
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
told
Token told
Feature activation+0.000
ABC
Token ABC
Feature activation+0.000
News
Token News
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Jonathan
Token Jonathan
Feature activation+0.000
Karl
Token Karl
Feature activation+0.000
blade
Token blade
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
just
Token just
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
stra
Token stra
Feature activation+0.000
ighter
Tokenighter
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
phone
Token phone
Feature activation+0.000
without
Token without
Feature activation+0.000
having
Token having
Feature activation+0.000
to
Token to
Feature activation+0.000
remove
Token remove
Feature activation+0.000
your
Token your
Feature activation+0.000
hands
Token hands
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
throttle
Token throttle
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 H1.6: (feature 14559)

TOP ACTIVATIONS
MAX = 4.101

,
Token,
Feature activation+0.000
California
Token California
Feature activation+0.391
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
each
Token each
Feature activation+0.000
camp
Token camp
Feature activation+4.101
on
Token on
Feature activation+0.314
the
Token the
Feature activation+0.000
map
Token map
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
has
Token has
Feature activation+0.000
visited
Token visited
Feature activation+1.445
a
Token a
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
camp
Token camp
Feature activation+3.700
in
Token in
Feature activation+0.350
Iraq
Token Iraq
Feature activation+2.635
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
also
Token also
Feature activation+0.000
for
Token for
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
tour
Token tour
Feature activation+0.000
refugee
Token refugee
Feature activation+0.045
camps
Token camps
Feature activation+3.601
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.148
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+3.256
refugees
Token refugees
Feature activation+0.000
arriving
Token arriving
Feature activation+3.052
in
Token in
Feature activation+0.023
Canada
Token Canada
Feature activation+0.684
as
Token as
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+3.256
refugees
Token refugees
Feature activation+0.000
arriving
Token arriving
Feature activation+3.052
in
Token in
Feature activation+0.023
Canada
Token Canada
Feature activation+0.684
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
drop
Token drop
Feature activation+0.000
in
Token in
Feature activation+0.000
refugees
Token refugees
Feature activation+0.016
arriving
Token arriving
Feature activation+2.986
in
Token in
Feature activation+0.000
Hungary
Token Hungary
Feature activation+1.036
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.472
400
Token 400
Feature activation+0.000
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+2.943
"
Token "
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
were
Token were
Feature activation+0.000
afraid
Token afraid
Feature activation+0.000
that
Token that
Feature activation+0.000
guidance
Token guidance
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.551
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+2.768
a
Token a
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.321
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
to
Token to
Feature activation+0.000
refugee
Token refugee
Feature activation+0.138
centres
Token centres
Feature activation+2.673
in
Token in
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.522
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+2.426
the
Token the
Feature activation+0.000
f
Token f
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
of
Token of
Feature activation+0.000
families
Token families
Feature activation+2.006
fleeing
Token fleeing
Feature activation+2.668
persecution
Token persecution
Feature activation+0.317
from
Token from
Feature activation+0.867
its
Token its
Feature activation+0.298
northern
Token northern
Feature activation+0.351
neighbour
Token neighbour
Feature activation+0.292
visited
Token visited
Feature activation+1.445
a
Token a
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
camp
Token camp
Feature activation+3.700
in
Token in
Feature activation+0.350
Iraq
Token Iraq
Feature activation+2.635
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
also
Token also
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
t
Tokent
Feature activation+0.000
outed
Tokenouted
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+2.466
ettle
Tokenettle
Feature activation+2.582
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
(
Token (
Feature activation+0.000
formerly
Tokenformerly
Feature activation+0.000
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
outed
Tokenouted
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+2.466
ettle
Tokenettle
Feature activation+2.582
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
(
Token (
Feature activation+0.000
centres
Token centres
Feature activation+2.673
in
Token in
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.522
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+2.426
a
Token a
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.144
repeat
Token repeat
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.144
Year
Token Year
Feature activation+0.000
attacks
Token attacks
Feature activation+2.382
in
Token in
Feature activation+0.000
Cologne
Token Cologne
Feature activation+0.000
(
Token(
Feature activation+0.000
pictured
Tokenpictured
Feature activation+0.000
)
Token)
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
also
Token also
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
national
Token national
Feature activation+2.345
spokeswoman
Token spokeswoman
Feature activation+0.000
for
Token for
Feature activation+0.345
a
Token a
Feature activation+0.029
left
Token left
Feature activation+0.719
-
Token-
Feature activation+0.000
other
Token other
Feature activation+0.000
privately
Token privately
Feature activation+0.000
sponsored
Token sponsored
Feature activation+0.000
refugees
Token refugees
Feature activation+0.000
and
Token and
Feature activation+0.000
asylum
Token asylum
Feature activation+2.223
-
Token-
Feature activation+0.000
seekers
Tokenseekers
Feature activation+0.292
in
Token in
Feature activation+0.015
limbo
Token limbo
Feature activation+1.302
get
Token get
Feature activation+0.443
enough
Token enough
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
those
Token those
Feature activation+0.000
arriving
Token arriving
Feature activation+2.206
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+0.570
illegally
Token illegally
Feature activation+1.155
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
G
TokenG
Feature activation+0.000
bag
Tokenbag
Feature activation+0.000
bo
Tokenbo
Feature activation+0.000
refused
Token refused
Feature activation+0.081
to
Token to
Feature activation+0.000
accept
Token accept
Feature activation+2.080
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
World
TokenWorld
Feature activation+0.659
Refugee
Token Refugee
Feature activation+0.555
Day
Token Day
Feature activation+0.133
,
Token,
Feature activation+0.000
recognized
Token recognized
Feature activation+2.049
each
Token each
Feature activation+0.000
year
Token year
Feature activation+0.391
on
Token on
Feature activation+0.009
June
Token June
Feature activation+0.000
20
Token 20
Feature activation+0.000

Top DFA by src position
MAX = 5.056

,
Token,
Feature activation-0.014
Top resid features:
houses
Token houses
Feature activation+0.002
Top resid features:
138
Token 138
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
102
Token102
Feature activation-0.020
Top resid features:
refugees
Token refugees
Feature activation+5.056
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
which
Token which
Feature activation-0.017
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
equivalent
Token equivalent
Feature activation+0.036
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
In
Token In
Feature activation-0.009
Top resid features:
her
Token her
Feature activation+0.002
Top resid features:
work
Token work
Feature activation-0.019
Top resid features:
as
Token as
Feature activation-0.015
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
refugee
Token refugee
Feature activation+3.152
Top resid features:
activist
Token activist
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.109
Top resid features:
Gö
Token Gö
Feature activation-0.057
Top resid features:
ren
Tokenren
Feature activation-0.004
Top resid features:
has
Token has
Feature activation-0.136
Top resid features:
program
Token program
Feature activation-0.009
Top resid features:
for
Token for
Feature activation-0.074
Top resid features:
him
Token him
Feature activation-0.023
Top resid features:
to
Token to
Feature activation-0.094
Top resid features:
tour
Token tour
Feature activation+0.066
Top resid features:
refugee
Token refugee
Feature activation+4.828
Top resid features:
camps
Token camps
Feature activation+0.176
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:
The
TokenThe
Feature activation+0.000
Top resid features:
special
Token special
Feature activation-0.002
Top resid features:
provision
Token provision
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
ensure
Token ensure
Feature activation+0.008
Top resid features:
Syrian
Token Syrian
Feature activation+0.025
Top resid features:
refugees
Token refugees
Feature activation+3.127
Top resid features:
get
Token get
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
full
Token full
Feature activation-0.001
Top resid features:
slate
Token slate
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
to
Token to
Feature activation-0.060
Top resid features:
all
Token all
Feature activation-0.071
Top resid features:
of
Token of
Feature activation-0.025
Top resid features:
the
Token the
Feature activation-0.072
Top resid features:
Syrian
Token Syrian
Feature activation-0.047
Top resid features:
refugees
Token refugees
Feature activation+1.654
Top resid features:
arriving
Token arriving
Feature activation+0.199
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Canada
Token Canada
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
treatment
Token treatment
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.007
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
deter
Token deter
Feature activation+0.001
Top resid features:
refugees
Token refugees
Feature activation+2.005
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Hung
TokenHung
Feature activation-0.012
Top resid features:
ary
Tokenary
Feature activation-0.007
Top resid features:
pro
Token pro
Feature activation-0.001
Top resid features:
-
Token-
Feature activation-0.012
Top resid features:
G
TokenG
Feature activation-0.003
Top resid features:
bag
Tokenbag
Feature activation+0.001
Top resid features:
bo
Tokenbo
Feature activation+0.007
Top resid features:
refugees
Token refugees
Feature activation+4.084
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
experts
Token experts
Feature activation-0.002
Top resid features:
ures
Tokenures
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
distributed
Token distributed
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
refugee
Token refugee
Feature activation+3.647
Top resid features:
centres
Token centres
Feature activation+0.007
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
Belgium
Token Belgium
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
ures
Tokenures
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.079
Top resid features:
be
Token be
Feature activation-0.094
Top resid features:
distributed
Token distributed
Feature activation-0.078
Top resid features:
to
Token to
Feature activation-0.159
Top resid features:
refugee
Token refugee
Feature activation+4.254
Top resid features:
centres
Token centres
Feature activation+0.139
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Belgium
Token Belgium
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.028
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.018
Top resid features:
says
Token says
Feature activation+0.014
Top resid features:
admitting
Token admitting
Feature activation+0.009
Top resid features:
Syrian
Token Syrian
Feature activation+0.035
Top resid features:
refugees
Token refugees
Feature activation+3.474
Top resid features:
will
Token will
Feature activation+0.022
Top resid features:
allow
Token allow
Feature activation+0.013
Top resid features:
terrorists
Token terrorists
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
In
Token In
Feature activation+0.008
Top resid features:
her
Token her
Feature activation+0.024
Top resid features:
work
Token work
Feature activation-0.009
Top resid features:
as
Token as
Feature activation-0.008
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
refugee
Token refugee
Feature activation+2.459
Top resid features:
activist
Token activist
Feature activation+0.004
Top resid features:
,
Token,
Feature activation-0.055
Top resid features:
Gö
Token Gö
Feature activation-0.053
Top resid features:
ren
Tokenren
Feature activation-0.008
Top resid features:
has
Token has
Feature activation-0.043
Top resid features:
plan
Token plan
Feature activation-0.023
Top resid features:
el
Tokenel
Feature activation+0.089
Top resid features:
oad
Tokenoad
Feature activation-0.023
Top resid features:
of
Token of
Feature activation-0.023
Top resid features:
Syrian
Token Syrian
Feature activation+0.014
Top resid features:
refugees
Token refugees
Feature activation+3.730
Top resid features:
Thursday
Token Thursday
Feature activation-0.017
Top resid features:
evening
Token evening
Feature activation-0.018
Top resid features:
as
Token as
Feature activation-0.007
Top resid features:
part
Token part
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.025
Top resid features:
plan
Token plan
Feature activation-0.021
Top resid features:
el
Tokenel
Feature activation+0.037
Top resid features:
oad
Tokenoad
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.021
Top resid features:
Syrian
Token Syrian
Feature activation+0.136
Top resid features:
refugees
Token refugees
Feature activation+3.520
Top resid features:
Thursday
Token Thursday
Feature activation-0.021
Top resid features:
evening
Token evening
Feature activation-0.022
Top resid features:
as
Token as
Feature activation-0.006
Top resid features:
part
Token part
Feature activation-0.009
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
ures
Tokenures
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
be
Token be
Feature activation-0.007
Top resid features:
distributed
Token distributed
Feature activation+0.019
Top resid features:
to
Token to
Feature activation-0.040
Top resid features:
refugee
Token refugee
Feature activation+3.742
Top resid features:
centres
Token centres
Feature activation-0.012
Top resid features:
in
Token in
Feature activation-0.023
Top resid features:
Belgium
Token Belgium
Feature activation-0.013
Top resid features:
,
Token,
Feature activation-0.187
Top resid features:
to
Token to
Feature activation-0.121
Top resid features:
ures
Tokenures
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.019
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
distributed
Token distributed
Feature activation-0.009
Top resid features:
to
Token to
Feature activation-0.028
Top resid features:
refugee
Token refugee
Feature activation+3.673
Top resid features:
centres
Token centres
Feature activation-0.010
Top resid features:
in
Token in
Feature activation-0.025
Top resid features:
Belgium
Token Belgium
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.085
Top resid features:
to
Token to
Feature activation-0.045
Top resid features:
In
Token In
Feature activation+0.007
Top resid features:
her
Token her
Feature activation+0.004
Top resid features:
work
Token work
Feature activation-0.012
Top resid features:
as
Token as
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.022
Top resid features:
refugee
Token refugee
Feature activation+2.135
Top resid features:
activist
Token activist
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
Gö
Token Gö
Feature activation-0.035
Top resid features:
ren
Tokenren
Feature activation-0.005
Top resid features:
has
Token has
Feature activation+0.031
Top resid features:
special
Token special
Feature activation-0.001
Top resid features:
provision
Token provision
Feature activation+0.009
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
ensure
Token ensure
Feature activation-0.006
Top resid features:
Syrian
Token Syrian
Feature activation+0.015
Top resid features:
refugees
Token refugees
Feature activation+2.368
Top resid features:
get
Token get
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
full
Token full
Feature activation+0.001
Top resid features:
slate
Token slate
Feature activation+0.012
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
cannot
Token cannot
Feature activation+0.005
Top resid features:
strip
Token strip
Feature activation-0.001
Top resid features:
them
Token them
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
their
Token their
Feature activation+0.006
Top resid features:
refugee
Token refugee
Feature activation+3.165
Top resid features:
status
Token status
Feature activation+0.023
Top resid features:
because
Token because
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
many
Token many
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
pro
Token pro
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.007
Top resid features:
G
TokenG
Feature activation-0.001
Top resid features:
bag
Tokenbag
Feature activation-0.003
Top resid features:
bo
Tokenbo
Feature activation+0.005
Top resid features:
refugees
Token refugees
Feature activation+3.039
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
experts
Token experts
Feature activation-0.002
Top resid features:
size
Token size
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.048
Top resid features:
Ċ
TokenĊ
Feature activation-0.048
Top resid features:
Ċ
TokenĊ
Feature activation-0.052
Top resid features:
World
TokenWorld
Feature activation+0.054
Top resid features:
Refugee
Token Refugee
Feature activation+1.768
Top resid features:
Day
Token Day
Feature activation-0.083
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
recognized
Token recognized
Feature activation+0.188
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.03

Head 3: 0.02

Head 4: 0.04

Head 5: 0.10

Head 6: 0.54

Head 7: 0.06

Head 8: 0.03

Head 9: 0.03

Head 10: 0.03

Head 11: 0.06

Positive logits

Refugees2.74

refugees2.66

refugee2.54

resettlement2.52

Refugee2.43

UNHCR2.39

Shelter2.14

fleeing2.09

aboard2.07

igrants2.06

convoy2.05

seekers2.04

Kurds2.02

Syrians2.00

boarding2.00

idi1.95

migrants1.92

shelters1.92

Kurd1.91

merga1.90

Negative logits

antioxid-2.62

lapt-2.08

cryptoc-2.07

resemb-2.07

similarities-2.03

ATURE-1.99

ELD-1.92

MET-1.90

patents-1.89

antitrust-1.87

exponent-1.83

Trend-1.81

baugh-1.75

patented-1.74

edly-1.73

TABLE-1.71

XT-1.70

virtues-1.69

RAL-1.68

sonian-1.68

INTERVAL 3.691 - 4.101
CONTAINS 0.000%

ren
Tokenren
Feature activation+0.000
has
Token has
Feature activation+0.000
visited
Token visited
Feature activation+1.445
a
Token a
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
camp
Token camp
Feature activation+3.700
in
Token in
Feature activation+0.350
Iraq
Token Iraq
Feature activation+2.635
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
also
Token also
Feature activation+0.000
,
Token,
Feature activation+0.000
California
Token California
Feature activation+0.391
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
each
Token each
Feature activation+0.000
camp
Token camp
Feature activation+4.101
on
Token on
Feature activation+0.314
the
Token the
Feature activation+0.000
map
Token map
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 3.281 - 3.691
CONTAINS 0.000%

for
Token for
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
tour
Token tour
Feature activation+0.000
refugee
Token refugee
Feature activation+0.045
camps
Token camps
Feature activation+3.601
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.148

INTERVAL 2.871 - 3.281
CONTAINS 0.000%

who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+2.943
"
Token "
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
were
Token were
Feature activation+0.000
afraid
Token afraid
Feature activation+0.000
that
Token that
Feature activation+0.000
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+3.256
refugees
Token refugees
Feature activation+0.000
arriving
Token arriving
Feature activation+3.052
in
Token in
Feature activation+0.023
Canada
Token Canada
Feature activation+0.684
as
Token as
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+3.256
refugees
Token refugees
Feature activation+0.000
arriving
Token arriving
Feature activation+3.052
in
Token in
Feature activation+0.023
Canada
Token Canada
Feature activation+0.684
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
drop
Token drop
Feature activation+0.000
in
Token in
Feature activation+0.000
refugees
Token refugees
Feature activation+0.016
arriving
Token arriving
Feature activation+2.986
in
Token in
Feature activation+0.000
Hungary
Token Hungary
Feature activation+1.036
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.472
400
Token 400
Feature activation+0.000

INTERVAL 2.461 - 2.871
CONTAINS 0.001%

t
Tokent
Feature activation+0.000
outed
Tokenouted
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+2.466
ettle
Tokenettle
Feature activation+2.582
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
(
Token (
Feature activation+0.000
formerly
Tokenformerly
Feature activation+0.000
visited
Token visited
Feature activation+1.445
a
Token a
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
camp
Token camp
Feature activation+3.700
in
Token in
Feature activation+0.350
Iraq
Token Iraq
Feature activation+2.635
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
also
Token also
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
to
Token to
Feature activation+0.000
refugee
Token refugee
Feature activation+0.138
centres
Token centres
Feature activation+2.673
in
Token in
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.522
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+2.426
the
Token the
Feature activation+0.000
f
Token f
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
of
Token of
Feature activation+0.000
families
Token families
Feature activation+2.006
fleeing
Token fleeing
Feature activation+2.668
persecution
Token persecution
Feature activation+0.317
from
Token from
Feature activation+0.867
its
Token its
Feature activation+0.298
northern
Token northern
Feature activation+0.351
neighbour
Token neighbour
Feature activation+0.292
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
outed
Tokenouted
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+2.466
ettle
Tokenettle
Feature activation+2.582
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 2.050 - 2.461
CONTAINS 0.001%

G
TokenG
Feature activation+0.000
bag
Tokenbag
Feature activation+0.000
bo
Tokenbo
Feature activation+0.000
refused
Token refused
Feature activation+0.081
to
Token to
Feature activation+0.000
accept
Token accept
Feature activation+2.080
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
other
Token other
Feature activation+0.000
privately
Token privately
Feature activation+0.000
sponsored
Token sponsored
Feature activation+0.000
refugees
Token refugees
Feature activation+0.000
and
Token and
Feature activation+0.000
asylum
Token asylum
Feature activation+2.223
-
Token-
Feature activation+0.000
seekers
Tokenseekers
Feature activation+0.292
in
Token in
Feature activation+0.015
limbo
Token limbo
Feature activation+1.302
get
Token get
Feature activation+0.443
enough
Token enough
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
those
Token those
Feature activation+0.000
arriving
Token arriving
Feature activation+2.206
in
Token in
Feature activation+0.000
Australia
Token Australia
Feature activation+0.570
illegally
Token illegally
Feature activation+1.155
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.144
Year
Token Year
Feature activation+0.000
attacks
Token attacks
Feature activation+2.382
in
Token in
Feature activation+0.000
Cologne
Token Cologne
Feature activation+0.000
(
Token(
Feature activation+0.000
pictured
Tokenpictured
Feature activation+0.000
)
Token)
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
also
Token also
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
national
Token national
Feature activation+2.345
spokeswoman
Token spokeswoman
Feature activation+0.000
for
Token for
Feature activation+0.345
a
Token a
Feature activation+0.029
left
Token left
Feature activation+0.719
-
Token-
Feature activation+0.000

INTERVAL 1.640 - 2.050
CONTAINS 0.001%

repeat
Token repeat
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.321
Year
Token Year
Feature activation+0.000
attacks
Token attacks
Feature activation+1.809
on
Token on
Feature activation+0.000
women
Token women
Feature activation+0.000
in
Token in
Feature activation+0.000
Cologne
Token Cologne
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
wants
Token wants
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
who
Token who
Feature activation+0.000
evac
Token evac
Feature activation+0.000
uates
Tokenuates
Feature activation+2.001
to
Token to
Feature activation+0.000
register
Token register
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
f
Token f
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
of
Token of
Feature activation+0.000
families
Token families
Feature activation+2.006
fleeing
Token fleeing
Feature activation+2.668
persecution
Token persecution
Feature activation+0.317
from
Token from
Feature activation+0.867
its
Token its
Feature activation+0.298
northern
Token northern
Feature activation+0.351
specialists
Token specialists
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
clinics
Token clinics
Feature activation+0.000
provide
Token provide
Feature activation+0.000
families
Token families
Feature activation+2.010
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
initial
Token initial
Feature activation+0.000
eye
Token eye
Feature activation+0.000
exam
Token exam
Feature activation+0.000
strip
Token strip
Feature activation+0.000
them
Token them
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
status
Token status
Feature activation+1.956
because
Token because
Feature activation+0.000
for
Token for
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.022

INTERVAL 1.230 - 1.640
CONTAINS 0.002%

academic
Token academic
Feature activation+0.000
delegation
Token delegation
Feature activation+0.000
,
Token,
Feature activation+0.000
coordinated
Token coordinated
Feature activation+0.020
his
Token his
Feature activation+0.000
entry
Token entry
Feature activation+1.551
to
Token to
Feature activation+0.053
Gaza
Token Gaza
Feature activation+0.083
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
Raf
Token Raf
Feature activation+0.000
",
Token",
Feature activation+0.000
in
Token in
Feature activation+0.000
1941
Token 1941
Feature activation+0.000
,
Token,
Feature activation+0.000
evac
Token evac
Feature activation+0.000
uating
Tokenuating
Feature activation+1.490
mainly
Token mainly
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
from
Token from
Feature activation+0.000
activist
Token activist
Feature activation+0.000
,
Token,
Feature activation+0.000
Gö
Token Gö
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
has
Token has
Feature activation+0.000
visited
Token visited
Feature activation+1.445
a
Token a
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
camp
Token camp
Feature activation+3.700
in
Token in
Feature activation+0.350
Iraq
Token Iraq
Feature activation+2.635
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
help
Token help
Feature activation+0.000
with
Token with
Feature activation+0.000
evac
Token evac
Feature activation+0.000
uations
Tokenuations
Feature activation+1.520
and
Token and
Feature activation+0.000
relief
Token relief
Feature activation+0.249
distribution
Token distribution
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
refugees
Token refugees
Feature activation+0.000
into
Token into
Feature activation+1.335
Syria
Token Syria
Feature activation+1.513
has
Token has
Feature activation+0.000
encouraged
Token encouraged
Feature activation+0.037
foreign
Token foreign
Feature activation+1.433
evangel
Token evangel
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
,
Token,
Feature activation+0.000
mainly
Token mainly
Feature activation+0.000
Americans
Token Americans
Feature activation+0.198

INTERVAL 0.820 - 1.230
CONTAINS 0.002%

"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000
really
Token really
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.935
a
Token a
Feature activation+0.000
legacy
Token legacy
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
peace
Token peace
Feature activation+0.000
people
Token people
Feature activation+0.439
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
entered
Token entered
Feature activation+0.859
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.135
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Germany
Token Germany
Feature activation+0.044
The
TokenThe
Feature activation+0.000
Government
Token Government
Feature activation+0.534
is
Token is
Feature activation+0.000
committed
Token committed
Feature activation+0.000
to
Token to
Feature activation+0.000
restoring
Token restoring
Feature activation+0.877
the
Token the
Feature activation+0.000
Inter
Token Inter
Feature activation+0.000
im
Tokenim
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Health
Token Health
Feature activation+0.000
says
Token says
Feature activation+0.000
admitting
Token admitting
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
refugees
Token refugees
Feature activation+0.000
will
Token will
Feature activation+0.000
allow
Token allow
Feature activation+1.070
terrorists
Token terrorists
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
refused
Token refused
Feature activation+0.287
to
Token to
Feature activation+0.000
divul
Token divul
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
the
Token the
Feature activation+0.000
ethnic
Token ethnic
Feature activation+0.843
identity
Token identity
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
attackers
Token attackers
Feature activation+0.000
because
Token because
Feature activation+0.000

INTERVAL 0.410 - 0.820
CONTAINS 0.007%

distributed
Token distributed
Feature activation+0.000
to
Token to
Feature activation+0.000
refugee
Token refugee
Feature activation+0.138
centres
Token centres
Feature activation+2.673
in
Token in
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.522
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+2.426
a
Token a
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
June
Token June
Feature activation+0.000
20
Token 20
Feature activation+0.000
,
Token,
Feature activation+0.000
honors
Token honors
Feature activation+0.528
the
Token the
Feature activation+0.000
millions
Token millions
Feature activation+0.772
of
Token of
Feature activation+0.000
displaced
Token displaced
Feature activation+0.559
men
Token men
Feature activation+0.635
,
Token,
Feature activation+0.000
women
Token women
Feature activation+0.689
a
Token a
Feature activation+0.000
vigilante
Token vigilante
Feature activation+0.000
group
Token group
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
French
Token French
Feature activation+0.702
port
Token port
Feature activation+0.804
town
Token town
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.137
have
Token have
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
guidance
Token guidance
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.551
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+2.768
a
Token a
Feature activation+0.000
repeat
Token repeat
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
national
Token national
Feature activation+2.345
spokeswoman
Token spokeswoman
Feature activation+0.000
for
Token for
Feature activation+0.345
a
Token a
Feature activation+0.029
left
Token left
Feature activation+0.719
-
Token-
Feature activation+0.000
wing
Tokenwing
Feature activation+0.000
political
Token political
Feature activation+0.000
group
Token group
Feature activation+0.000
called
Token called
Feature activation+0.160

INTERVAL 0.000 - 0.410
CONTAINS 99.987%

ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
time
Token time
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
sometimes
Tokensometimes
Feature activation+0.000
you
Token you
Feature activation+0.000
just
Token just
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.000
things
Token things
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
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
merely
Token merely
Feature activation+0.000
a
Token a
Feature activation+0.000
children
Token children
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
are
Token are
Feature activation+0.000
living
Token living
Feature activation+0.000
near
Token near
Feature activation+0.000
the
Token the
Feature activation+0.000
poverty
Token poverty
Feature activation+0.000
line
Token line
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
You
TokenYou
Feature activation+0.000
're
Token're
Feature activation+0.000
sure
Token sure
Feature activation+0.000
?"
Token?"
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
asked
Token asked
Feature activation+0.000
.
Token.
Feature activation+0.000
Pyrrha
Token Pyrrha
Feature activation+0.000
nodded
Token nodded
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 H1.6: (feature 19420)

TOP ACTIVATIONS
MAX = 4.668

cast
Token cast
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
gender
Token gender
Feature activation+0.506
as
Token as
Feature activation+0.080
woman
Token woman
Feature activation+4.668
.
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
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
boy
Token boy
Feature activation+3.265
and
Token and
Feature activation+0.000
girl
Token girl
Feature activation+3.506
sections
Token sections
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
two
Token two
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
-
Token-
Feature activation+0.000
2016
Token2016
Feature activation+0.000
to
Token to
Feature activation+0.000
test
Token test
Feature activation+0.000
whether
Token whether
Feature activation+0.000
women
Token women
Feature activation+3.371
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
to
Token to
Feature activation+0.000
grades
Token grades
Feature activation+0.000
of
Token of
Feature activation+0.000
pages
Token pages
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
boy
Token boy
Feature activation+3.265
and
Token and
Feature activation+0.000
girl
Token girl
Feature activation+3.506
sections
Token sections
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
People
Token People
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
care
Token care
Feature activation+0.039
what
Token what
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+3.252
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
had
Token had
Feature activation+0.016
given
Token given
Feature activation+0.480
birth
Token birth
Feature activation+0.218
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.042
girl
Token girl
Feature activation+3.208
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
Morrow
Token Morrow
Feature activation+0.000
they
Token they
Feature activation+0.000
hate
Token hate
Feature activation+0.000
it
Token it
Feature activation+0.000
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.041
woman
Token woman
Feature activation+3.134
gets
Token gets
Feature activation+0.000
hurt
Token hurt
Feature activation+0.000
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+2.121
âĢĶ
TokenâĢĶ
Feature activation+0.000
more
Token more
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
to
Token to
Feature activation+0.000
grades
Token grades
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.039
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
female
Token female
Feature activation+2.847
and
Token and
Feature activation+0.000
male
Token male
Feature activation+2.482
em
Token em
Feature activation+0.000
oj
Tokenoj
Feature activation+0.000
is
Tokenis
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
female
Token female
Feature activation+2.771
character
Token character
Feature activation+0.000
in
Token in
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+2.746
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
gender
Token gender
Feature activation+0.339
gap
Token gap
Feature activation+0.388
in
Token in
Feature activation+0.000
tech
Token tech
Feature activation+0.000
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+2.738
simply
Token simply
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
of
Token of
Feature activation+0.000
gender
Token gender
Feature activation+0.000
equality
Token equality
Feature activation+0.000
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.000
men
Token men
Feature activation+2.704
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
That
TokenThat
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.582
)
Token)
Feature activation+0.000
Female
Token Female
Feature activation+2.691
Sequence
Token Sequence
Feature activation+0.000
Male
Token Male
Feature activation+2.218
Sequence
Token Sequence
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
for
Token for
Feature activation+0.000
men
Token men
Feature activation+2.689
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
just
Token just
Feature activation+0.000
not
Token not
Feature activation+0.000
solely
Token solely
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
for
Token for
Feature activation+0.000
women
Token women
Feature activation+2.679
.
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
hed
Tokenhed
Feature activation+0.000
between
Token between
Feature activation+0.000
two
Token two
Feature activation+0.000
more
Token more
Feature activation+0.000
gender
Token gender
Feature activation+0.000
neutral
Token neutral
Feature activation+2.623
sets
Token sets
Feature activation+0.000
of
Token of
Feature activation+0.000
pages
Token pages
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
male
Token male
Feature activation+2.614
character
Token character
Feature activation+0.000
,
Token,
Feature activation+0.000
simple
Token simple
Feature activation+0.000
as
Token as
Feature activation+0.000
that
Token that
Feature activation+0.000
advocacy
Token advocacy
Feature activation+0.000
needed
Token needed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
sex
Token sex
Feature activation+2.591
discrimination
Token discrimination
Feature activation+0.000
commissioner
Token commissioner
Feature activation+0.000
says
Token says
Feature activation+0.000
men
Token men
Feature activation+2.228
have
Token have
Feature activation+0.000
identity
Token identity
Feature activation+2.263
as
Token as
Feature activation+0.723
the
Token the
Feature activation+0.000
student
Token student
Feature activation+0.000
's
Token's
Feature activation+0.000
sex
Token sex
Feature activation+2.583
for
Token for
Feature activation+0.000
purposes
Token purposes
Feature activation+0.000
of
Token of
Feature activation+0.000
Title
Token Title
Feature activation+0.000
IX
Token IX
Feature activation+0.000

Top DFA by src position
MAX = 6.284

have
Token have
Feature activation-0.016
Top resid features:
been
Token been
Feature activation-0.004
Top resid features:
cast
Token cast
Feature activation+0.011
Top resid features:
on
Token on
Feature activation-0.029
Top resid features:
her
Token her
Feature activation+0.040
Top resid features:
gender
Token gender
Feature activation+6.284
Top resid features:
as
Token as
Feature activation+0.086
Top resid features:
woman
Token woman
Feature activation+0.060
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
wic
Tokenwic
Feature activation+0.039
Top resid features:
hed
Tokenhed
Feature activation-0.006
Top resid features:
between
Token between
Feature activation-0.003
Top resid features:
two
Token two
Feature activation+0.015
Top resid features:
more
Token more
Feature activation+0.003
Top resid features:
gender
Token gender
Feature activation+5.243
Top resid features:
neutral
Token neutral
Feature activation+0.048
Top resid features:
sets
Token sets
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
pages
Token pages
Feature activation-0.001
Top resid features:
are
Token are
Feature activation+0.016
Top resid features:
major
Token major
Feature activation-0.013
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
related
Tokenrelated
Feature activation+0.001
Top resid features:
classes
Token classes
Feature activation+0.026
Top resid features:
explains
Token explains
Feature activation+0.002
Top resid features:
gender
Token gender
Feature activation+4.452
Top resid features:
differences
Token differences
Feature activation+0.194
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
final
Token final
Feature activation+0.011
Top resid features:
majors
Token majors
Feature activation-0.008
Top resid features:
wic
Tokenwic
Feature activation+0.042
Top resid features:
hed
Tokenhed
Feature activation-0.010
Top resid features:
between
Token between
Feature activation-0.005
Top resid features:
two
Token two
Feature activation+0.015
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
gender
Token gender
Feature activation+4.671
Top resid features:
neutral
Token neutral
Feature activation+0.053
Top resid features:
sets
Token sets
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
pages
Token pages
Feature activation-0.002
Top resid features:
are
Token are
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.013
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
talk
Token talk
Feature activation-0.008
Top resid features:
about
Token about
Feature activation+0.003
Top resid features:
gender
Token gender
Feature activation+4.343
Top resid features:
.
Token.
Feature activation-0.070
Top resid features:
People
Token People
Feature activation+0.052
Top resid features:
rarely
Token rarely
Feature activation+0.056
Top resid features:
care
Token care
Feature activation+0.047
Top resid features:
what
Token what
Feature activation+0.041
Top resid features:
daughter
Token daughter
Feature activation+0.016
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
emerging
Token emerging
Feature activation+0.025
Top resid features:
gender
Token gender
Feature activation+4.339
Top resid features:
identity
Token identity
Feature activation+0.105
Top resid features:
since
Token since
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
child
Token child
Feature activation-0.013
Top resid features:
started
Token started
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.014
Top resid features:
time
Token time
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
talk
Token talk
Feature activation-0.003
Top resid features:
about
Token about
Feature activation+0.015
Top resid features:
gender
Token gender
Feature activation+4.151
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
People
Token People
Feature activation+0.031
Top resid features:
rarely
Token rarely
Feature activation+0.022
Top resid features:
care
Token care
Feature activation+0.031
Top resid features:
what
Token what
Feature activation+0.019
Top resid features:
major
Token major
Feature activation-0.012
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
related
Tokenrelated
Feature activation+0.001
Top resid features:
classes
Token classes
Feature activation+0.012
Top resid features:
explains
Token explains
Feature activation+0.006
Top resid features:
gender
Token gender
Feature activation+4.135
Top resid features:
differences
Token differences
Feature activation+0.076
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
final
Token final
Feature activation+0.007
Top resid features:
majors
Token majors
Feature activation+0.002
Top resid features:
iOS
Token iOS
Feature activation-0.053
Top resid features:
10
Token 10
Feature activation-0.028
Top resid features:
:
Token:
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation-0.029
Top resid features:
Ċ
TokenĊ
Feature activation-0.035
Top resid features:
Gender
TokenGender
Feature activation+4.570
Top resid features:
Neutral
Token Neutral
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation-0.066
Top resid features:
Ċ
TokenĊ
Feature activation-0.074
Top resid features:
The
TokenThe
Feature activation-0.020
Top resid features:
way
Token way
Feature activation-0.051
Top resid features:
protagonist
Token protagonist
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
gender
Token gender
Feature activation+4.310
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
Remember
Token Remember
Feature activation+0.001
Top resid features:
Me
Token Me
Feature activation-0.000
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
main
Token main
Feature activation-0.003
Top resid features:
protagonist
Token protagonist
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
gender
Token gender
Feature activation+3.082
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Remember
Token Remember
Feature activation+0.002
Top resid features:
Me
Token Me
Feature activation-0.000
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
main
Token main
Feature activation-0.000
Top resid features:
ve
Tokenve
Feature activation-0.002
Top resid features:
all
Token all
Feature activation-0.000
Top resid features:
heard
Token heard
Feature activation-0.019
Top resid features:
about
Token about
Feature activation+0.029
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
gender
Token gender
Feature activation+3.829
Top resid features:
gap
Token gap
Feature activation+0.371
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
tech
Token tech
Feature activation+0.039
Top resid features:
.
Token.
Feature activation-0.107
Top resid features:
Women
Token Women
Feature activation+0.255
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.064
Top resid features:
taking
Token taking
Feature activation-0.041
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
message
Token message
Feature activation-0.048
Top resid features:
of
Token of
Feature activation-0.032
Top resid features:
gender
Token gender
Feature activation+4.140
Top resid features:
equality
Token equality
Feature activation+0.328
Top resid features:
to
Token to
Feature activation-0.083
Top resid features:
other
Token other
Feature activation-0.024
Top resid features:
men
Token men
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
iOS
Token iOS
Feature activation-0.019
Top resid features:
10
Token 10
Feature activation-0.005
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Gender
TokenGender
Feature activation+2.837
Top resid features:
Neutral
Token Neutral
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
way
Token way
Feature activation-0.001
Top resid features:
ve
Tokenve
Feature activation+0.002
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
heard
Token heard
Feature activation-0.001
Top resid features:
about
Token about
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
gender
Token gender
Feature activation+3.975
Top resid features:
gap
Token gap
Feature activation+0.272
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
tech
Token tech
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
Women
Token Women
Feature activation+0.075
Top resid features:
ve
Tokenve
Feature activation+0.001
Top resid features:
all
Token all
Feature activation+0.002
Top resid features:
heard
Token heard
Feature activation+0.001
Top resid features:
about
Token about
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
gender
Token gender
Feature activation+3.808
Top resid features:
gap
Token gap
Feature activation+0.339
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
tech
Token tech
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Women
Token Women
Feature activation+0.073
Top resid features:
wic
Tokenwic
Feature activation+0.054
Top resid features:
hed
Tokenhed
Feature activation-0.022
Top resid features:
between
Token between
Feature activation-0.004
Top resid features:
two
Token two
Feature activation+0.036
Top resid features:
more
Token more
Feature activation+0.087
Top resid features:
gender
Token gender
Feature activation+4.200
Top resid features:
neutral
Token neutral
Feature activation-0.035
Top resid features:
sets
Token sets
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
pages
Token pages
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
protagonist
Token protagonist
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
gender
Token gender
Feature activation+4.504
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
Remember
Token Remember
Feature activation+0.001
Top resid features:
Me
Token Me
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
main
Token main
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.069
Top resid features:
taking
Token taking
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
message
Token message
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
gender
Token gender
Feature activation+3.326
Top resid features:
equality
Token equality
Feature activation+0.761
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
other
Token other
Feature activation+0.002
Top resid features:
men
Token men
Feature activation+0.128
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
t
Tokent
Feature activation-0.005
Top resid features:
reat
Tokenreat
Feature activation+0.018
Top resid features:
a
Token a
Feature activation-0.018
Top resid features:
student
Token student
Feature activation-0.002
Top resid features:
's
Token's
Feature activation+0.015
Top resid features:
gender
Token gender
Feature activation+3.214
Top resid features:
identity
Token identity
Feature activation+0.671
Top resid features:
as
Token as
Feature activation+0.016
Top resid features:
the
Token the
Feature activation-0.035
Top resid features:
student
Token student
Feature activation-0.018
Top resid features:
's
Token's
Feature activation+0.036
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.03

Head 3: 0.02

Head 4: 0.04

Head 5: 0.11

Head 6: 0.53

Head 7: 0.05

Head 8: 0.02

Head 9: 0.03

Head 10: 0.03

Head 11: 0.07

Positive logits

Gender2.59

pronouns2.49

gender2.49

genders2.46

endered2.44

stereotypes2.22

Caucasian2.18

stereotypical2.13

Females2.11

Transgender2.09

hijab2.08

gender2.07

Caucas2.06

Diversity2.06

stereotyp2.04

sexes2.03

Differences2.02

Discrimination2.01

equality2.00

gyn1.97

Negative logits

pled-1.94

ambush-1.88

hope-1.87

prosecuting-1.80

bombardment-1.80

deterrence-1.77

ofi-1.76

propell-1.76

detonated-1.75

gunfire-1.73

deliver-1.72

salv-1.70

delivered-1.70

hooting-1.67

stockp-1.66

delivering-1.66

sprayed-1.66

delivery-1.65

prosecut-1.65

advance-1.64

INTERVAL 4.201 - 4.668
CONTAINS 0.000%

cast
Token cast
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
gender
Token gender
Feature activation+0.506
as
Token as
Feature activation+0.080
woman
Token woman
Feature activation+4.668
.
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

INTERVAL 3.735 - 4.201
CONTAINS 0.000%

INTERVAL 3.268 - 3.735
CONTAINS 0.000%

-
Token-
Feature activation+0.000
2016
Token2016
Feature activation+0.000
to
Token to
Feature activation+0.000
test
Token test
Feature activation+0.000
whether
Token whether
Feature activation+0.000
women
Token women
Feature activation+3.371
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
to
Token to
Feature activation+0.000
grades
Token grades
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
boy
Token boy
Feature activation+3.265
and
Token and
Feature activation+0.000
girl
Token girl
Feature activation+3.506
sections
Token sections
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
two
Token two
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000

INTERVAL 2.801 - 3.268
CONTAINS 0.001%

they
Token they
Feature activation+0.000
hate
Token hate
Feature activation+0.000
it
Token it
Feature activation+0.000
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.041
woman
Token woman
Feature activation+3.134
gets
Token gets
Feature activation+0.000
hurt
Token hurt
Feature activation+0.000
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+2.121
âĢĶ
TokenâĢĶ
Feature activation+0.000
People
Token People
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
care
Token care
Feature activation+0.039
what
Token what
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+3.252
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
female
Token female
Feature activation+2.847
and
Token and
Feature activation+0.000
male
Token male
Feature activation+2.482
em
Token em
Feature activation+0.000
oj
Tokenoj
Feature activation+0.000
is
Tokenis
Feature activation+0.000
more
Token more
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
to
Token to
Feature activation+0.000
grades
Token grades
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.039
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
of
Token of
Feature activation+0.000
pages
Token pages
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
boy
Token boy
Feature activation+3.265
and
Token and
Feature activation+0.000
girl
Token girl
Feature activation+3.506
sections
Token sections
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000

INTERVAL 2.334 - 2.801
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
gender
Token gender
Feature activation+0.000
-
Token-
Feature activation+0.000
neutral
Tokenneutral
Feature activation+2.432
bathrooms
Token bathrooms
Feature activation+0.223
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
allow
Token allow
Feature activation+0.000
students
Token students
Feature activation+0.000
advocacy
Token advocacy
Feature activation+0.000
needed
Token needed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
sex
Token sex
Feature activation+2.591
discrimination
Token discrimination
Feature activation+0.000
commissioner
Token commissioner
Feature activation+0.000
says
Token says
Feature activation+0.000
men
Token men
Feature activation+2.228
have
Token have
Feature activation+0.000
gender
Token gender
Feature activation+0.339
gap
Token gap
Feature activation+0.388
in
Token in
Feature activation+0.000
tech
Token tech
Feature activation+0.000
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+2.738
simply
Token simply
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
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+2.746
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.582
)
Token)
Feature activation+0.000
Female
Token Female
Feature activation+2.691
Sequence
Token Sequence
Feature activation+0.000
Male
Token Male
Feature activation+2.218
Sequence
Token Sequence
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.867 - 2.334
CONTAINS 0.001%

,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
37
Token 37
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
women
Token women
Feature activation+1.986
citing
Token citing
Feature activation+0.000
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
year
Token year
Feature activation+0.000
was
Token was
Feature activation+0.000
we
Token we
Feature activation+0.000
had
Token had
Feature activation+0.000
more
Token more
Feature activation+0.000
men
Token men
Feature activation+1.997
getting
Token getting
Feature activation+0.000
on
Token on
Feature activation+0.000
board
Token board
Feature activation+0.000
,
Token,
Feature activation+0.000
stepping
Token stepping
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
of
Token of
Feature activation+0.000
gender
Token gender
Feature activation+0.114
transition
Token transition
Feature activation+2.308
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
either
Token either
Feature activation+0.000
gender
Token gender
Feature activation+0.000
or
Token or
Feature activation+0.000
were
Token were
Feature activation+0.000
in
Token in
Feature activation+0.000
transition
Token transition
Feature activation+2.235
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
MON
TokenMON
Feature activation+0.000
T
TokenT
Feature activation+0.000
RE
TokenRE
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
harm
Token harm
Feature activation+0.000
or
Token or
Feature activation+0.000
suffering
Token suffering
Feature activation+0.000
to
Token to
Feature activation+0.000
women
Token women
Feature activation+1.961
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
threats
Token threats
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000

INTERVAL 1.400 - 1.867
CONTAINS 0.001%

,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+1.726
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
just
Token just
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+0.000
riding
Token riding
Feature activation+0.000
for
Token for
Feature activation+0.000
women
Token women
Feature activation+1.771
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
men
Token men
Feature activation+2.309
make
Token make
Feature activation+0.000
riding
Token riding
Feature activation+0.000
more
Token more
Feature activation+0.000
appealing
Token appealing
Feature activation+0.000
to
Token to
Feature activation+0.000
women
Token women
Feature activation+1.843
by
Token by
Feature activation+0.000
adding
Token adding
Feature activation+0.000
off
Token off
Feature activation+0.000
-
Token-
Feature activation+0.000
road
Tokenroad
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
second
Token second
Feature activation+0.000
topic
Token topic
Feature activation+0.000
was
Token was
Feature activation+0.000
sex
Token sex
Feature activation+1.668
education
Token education
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.019
kind
Token kind
Feature activation+0.053
is
Token is
Feature activation+0.040
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
emerging
Token emerging
Feature activation+0.000
gender
Token gender
Feature activation+0.541
identity
Token identity
Feature activation+1.840
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
child
Token child
Feature activation+0.449
started
Token started
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.934 - 1.400
CONTAINS 0.002%

on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.996
might
Token might
Feature activation+0.000
dance
Token dance
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
DC
Token DC
Feature activation+0.000
trans
Token trans
Feature activation+1.226
woman
Token woman
Feature activation+1.160
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
murdered
Token murdered
Feature activation+0.000
in
Token in
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
better
Token better
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
than
Token than
Feature activation+0.000
women
Token women
Feature activation+0.947
.
Token.
Feature activation+0.000
Short
Token Short
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
won
Token won
Feature activation+0.000
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Gender
TokenGender
Feature activation+0.250
Neutral
Token Neutral
Feature activation+1.058
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
male
Token male
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
men
Token men
Feature activation+1.185
make
Token make
Feature activation+0.000
forceful
Token forceful
Feature activation+0.000
gestures
Token gestures
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 0.467 - 0.934
CONTAINS 0.006%

a
Token a
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
chromosomes
Token chromosomes
Feature activation+0.494
,
Token,
Feature activation+0.000
DNA
Token DNA
Feature activation+0.379
and
Token and
Feature activation+0.000
memes
Token memes
Feature activation+0.000
.
Token.
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
cast
Token cast
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
gender
Token gender
Feature activation+0.506
as
Token as
Feature activation+0.080
woman
Token woman
Feature activation+4.668
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
result
Token result
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
physical
Token physical
Feature activation+0.000
,
Token,
Feature activation+0.000
sexual
Token sexual
Feature activation+0.730
or
Token or
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
harm
Token harm
Feature activation+0.000
or
Token or
Feature activation+0.000
suffering
Token suffering
Feature activation+0.000
-
Token-
Feature activation+0.000
public
Tokenpublic
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
/
Token/
Feature activation+0.000
trans
Tokentrans
Feature activation+0.000
gender
Tokengender
Feature activation+0.891
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.170
-
Token-
Feature activation+0.000
plan
Tokenplan
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
that
Token that
Feature activation+0.000
bans
Token bans
Feature activation+0.000
women
Token women
Feature activation+0.525
from
Token from
Feature activation+0.000
driving
Token driving
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.000 - 0.467
CONTAINS 99.987%

first
Token first
Feature activation+0.000
sit
Token sit
Feature activation+0.000
down
Token down
Feature activation+0.000
with
Token with
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Introdu
TokenIntrodu
Feature activation+0.000
cing
Tokencing
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
economic
Token economic
Feature activation+0.000
commentary
Token commentary
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
papers
Token papers
Feature activation+0.000
is
Token is
Feature activation+0.000
focused
Token focused
Feature activation+0.000
the
Token the
Feature activation+0.000
F
Token F
Feature activation+0.000
35
Token35
Feature activation+0.000
?
Token?
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
my
Token my
Feature activation+0.000
favorite
Token favorite
Feature activation+0.000
one
Token one
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
inquest
Token inquest
Feature activation+0.000
heard
Token heard
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lou
TokenLou
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
and
Token and
Feature activation+0.000
rye
Token rye
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
other
Token other
Feature activation+0.000
foods
Token foods
Feature activation+0.000
including
Token including
Feature activation+0.000
apples
Token apples
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H1.6: (feature 23126)

TOP ACTIVATIONS
MAX = 3.415

I
Token I
Feature activation+0.000
MAX
TokenMAX
Feature activation+1.799
and
Token and
Feature activation+0.000
certain
Token certain
Feature activation+0.000
Large
Token Large
Feature activation+0.000
Format
Token Format
Feature activation+3.415
theaters
Token theaters
Feature activation+0.576
and
Token and
Feature activation+0.000
opened
Token opened
Feature activation+0.895
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
x
Tokenx
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
early
Token early
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.000
screening
Token screening
Feature activation+3.303
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.000
June
Token June
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
forget
Token forget
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+3.300
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.500
lessons
Token lessons
Feature activation+0.000
(
Token (
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token '
Feature activation+0.000
As
TokenAs
Feature activation+0.002
anyone
Token anyone
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
seen
Token seen
Feature activation+3.179
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.000
can
Token can
Feature activation+0.000
attest
Token attest
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
le
Tokenle
Feature activation+0.000
of
Token of
Feature activation+0.000
Dogs
Token Dogs
Feature activation+0.000
premie
Token premie
Feature activation+2.971
res
Tokenres
Feature activation+0.921
in
Token in
Feature activation+0.000
theat
Token theat
Feature activation+0.769
res
Tokenres
Feature activation+1.007
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
Other
Token Other
Feature activation+0.000
Home
Token Home
Feature activation+0.000
begins
Token begins
Feature activation+0.238
screening
Token screening
Feature activation+2.822
in
Token in
Feature activation+0.168
China
Token China
Feature activation+0.000
on
Token on
Feature activation+0.000
August
Token August
Feature activation+0.000
11
Token 11
Feature activation+0.108
Film
Token Film
Feature activation+0.000
1937
Token 1937
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Shot
TokenShot
Feature activation+2.821
list
Tokenlist
Feature activation+0.000
:
Token:
Feature activation+0.000
Credits
Token Credits
Feature activation+0.516
(
Token (
Feature activation+0.000
0
Token0
Feature activation+0.000
technical
Token technical
Feature activation+0.000
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
film
Token film
Feature activation+0.010
-
Token-
Feature activation+0.000
making
Tokenmaking
Feature activation+2.762
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
this
Token this
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
seen
Token seen
Feature activation+2.617
it
Token it
Feature activation+0.091
,
Token,
Feature activation+0.000
read
Token read
Feature activation+0.000
no
Token no
Feature activation+0.000
further
Token further
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.616
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.654
was
Token was
Feature activation+0.207
shot
Token shot
Feature activation+2.588
at
Token at
Feature activation+0.000
Lake
Token Lake
Feature activation+0.000
A
Token A
Feature activation+0.000
ft
Tokenft
Feature activation+0.086
on
Tokenon
Feature activation+0.000
in
Token in
Feature activation+0.000
Egypt
Token Egypt
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
are
Token are
Feature activation+0.000
shown
Token shown
Feature activation+2.577
all
Token all
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+0.000
-
Token-
Feature activation+0.000
watch
Tokenwatch
Feature activation+2.350
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
20
Token 20
Feature activation+0.000
minutes
Token minutes
Feature activation+2.514
leading
Token leading
Feature activation+0.988
into
Token into
Feature activation+0.000
his
Token his
Feature activation+0.000
unt
Token unt
Feature activation+0.019
ime
Tokenime
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
business
Token business
Feature activation+0.386
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
casting
Token casting
Feature activation+2.495
white
Token white
Feature activation+0.000
men
Token men
Feature activation+0.000
will
Token will
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
to
Token to
Feature activation+0.000
called
Token called
Feature activation+0.000
One
Token One
Feature activation+0.000
Last
Token Last
Feature activation+0.000
Shot
Token Shot
Feature activation+1.894
was
Token was
Feature activation+0.000
shot
Token shot
Feature activation+2.485
in
Token in
Feature activation+0.000
black
Token black
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+0.000
-
Token-
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
rest
Tokenrest
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
limited
Token limited
Feature activation+0.000
release
Token release
Feature activation+2.448
in
Token in
Feature activation+0.000
I
Token I
Feature activation+0.000
MAX
TokenMAX
Feature activation+1.799
and
Token and
Feature activation+0.000
certain
Token certain
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
General
Token General
Feature activation+0.000
-
Token-
Feature activation+0.000
Direct
TokenDirect
Feature activation+2.446
orate
Tokenorate
Feature activation+0.000
for
Token for
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
says
Token says
Feature activation+0.000
an
Token an
Feature activation+0.000
With
TokenWith
Feature activation+0.000
the
Token the
Feature activation+0.000
exception
Token exception
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
cast
Token cast
Feature activation+2.438
party
Token party
Feature activation+0.000
screening
Token screening
Feature activation+2.431
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.801
(
Token (
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
16
Token16
Feature activation+0.000
)
Token)
Feature activation+0.000
shot
Token shot
Feature activation+2.435
of
Token of
Feature activation+0.000
models
Token models
Feature activation+0.000
of
Token of
Feature activation+0.000
London
Token London
Feature activation+0.000
Transport
Token Transport
Feature activation+0.000
exception
Token exception
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
cast
Token cast
Feature activation+2.438
party
Token party
Feature activation+0.000
screening
Token screening
Feature activation+2.431
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.801
sat
Token sat
Feature activation+0.067
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.000
and
Token and
Feature activation+0.000
re
Token re
Feature activation+0.689
-
Token-
Feature activation+0.000
watch
Tokenwatch
Feature activation+2.350
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
20
Token 20
Feature activation+0.000
minutes
Token minutes
Feature activation+2.514
leading
Token leading
Feature activation+0.988

Top DFA by src position
MAX = 4.281

great
Token great
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
an
Token an
Feature activation+0.012
Top resid features:
adult
Token adult
Feature activation+0.001
Top resid features:
oriented
Token oriented
Feature activation+0.007
Top resid features:
film
Token film
Feature activation+4.281
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
In
Token In
Feature activation+0.002
Top resid features:
comparison
Token comparison
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
Gone
Token Gone
Feature activation-0.002
Top resid features:
out
Token out
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
make
Token make
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
new
Token new
Feature activation-0.004
Top resid features:
film
Token film
Feature activation+3.942
Top resid features:
based
Token based
Feature activation+0.011
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
Jane
Token Jane
Feature activation-0.020
Top resid features:
Aust
Token Aust
Feature activation-0.037
Top resid features:
en
Tokenen
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Screen
TokenScreen
Feature activation+0.057
Top resid features:
cap
Tokencap
Feature activation+0.011
Top resid features:
from
Token from
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
movie
Token movie
Feature activation+4.216
Top resid features:
"
Token "
Feature activation+0.007
Top resid features:
Y
TokenY
Feature activation+0.005
Top resid features:
ours
Tokenours
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Mine
Token Mine
Feature activation-0.003
Top resid features:
.'
Token.'
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
But
TokenBut
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
film
Token film
Feature activation+3.952
Top resid features:
's
Token's
Feature activation-0.002
Top resid features:
studio
Token studio
Feature activation+0.047
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
Fox
Token Fox
Feature activation+0.024
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.007
Top resid features:
stop
Token stop
Feature activation-0.003
Top resid features:
motion
Token motion
Feature activation+0.022
Top resid features:
film
Token film
Feature activation+3.916
Top resid features:
will
Token will
Feature activation+0.001
Top resid features:
star
Token star
Feature activation+0.105
Top resid features:
Bill
Token Bill
Feature activation-0.000
Top resid features:
Murray
Token Murray
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
China
Token China
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
film
Token film
Feature activation+1.628
Top resid features:
shows
Token shows
Feature activation+0.019
Top resid features:
us
Token us
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
he
Token he
Feature activation+0.006
Top resid features:
knows
Token knows
Feature activation-0.002
Top resid features:
An
TokenAn
Feature activation-0.009
Top resid features:
amateur
Token amateur
Feature activation+0.010
Top resid features:
prize
Token prize
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
winning
Tokenwinning
Feature activation+0.001
Top resid features:
film
Token film
Feature activation+2.240
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
1937
Token 1937
Feature activation+0.014
Top resid features:
].
Token].
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
in
Token in
Feature activation-0.009
Top resid features:
advance
Token advance
Feature activation+0.023
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
The
Token The
Feature activation-0.009
Top resid features:
Rogue
Token Rogue
Feature activation-0.011
Top resid features:
Film
Token Film
Feature activation+2.122
Top resid features:
School
Token School
Feature activation-0.012
Top resid features:
will
Token will
Feature activation-0.033
Top resid features:
not
Token not
Feature activation-0.006
Top resid features:
teach
Token teach
Feature activation-0.032
Top resid features:
anything
Token anything
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
because
Token because
Feature activation+0.002
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
feel
Token feel
Feature activation-0.004
Top resid features:
this
Token this
Feature activation+0.022
Top resid features:
film
Token film
Feature activation+2.386
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
difficult
Token difficult
Feature activation-0.010
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
dissect
Token dissect
Feature activation+0.025
Top resid features:
without
Token without
Feature activation-0.001
Top resid features:
8
Token8
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
000
Token000
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
The
Token The
Feature activation+0.018
Top resid features:
movie
Token movie
Feature activation+1.901
Top resid features:
's
Token's
Feature activation+0.018
Top resid features:
cast
Token cast
Feature activation+0.040
Top resid features:
and
Token and
Feature activation-0.014
Top resid features:
crew
Token crew
Feature activation-0.003
Top resid features:
members
Token members
Feature activation-0.021
Top resid features:
due
Token due
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.032
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
massive
Token massive
Feature activation-0.014
Top resid features:
movie
Token movie
Feature activation+3.789
Top resid features:
industry
Token industry
Feature activation-0.011
Top resid features:
in
Token in
Feature activation-0.048
Top resid features:
Egypt
Token Egypt
Feature activation-0.040
Top resid features:
,
Token,
Feature activation-0.087
Top resid features:
which
Token which
Feature activation-0.024
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
particular
Token particular
Feature activation+0.004
Top resid features:
point
Token point
Feature activation+0.009
Top resid features:
in
Token in
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
film
Token film
Feature activation+2.055
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
So
Token So
Feature activation-0.030
Top resid features:
you
Token you
Feature activation-0.023
Top resid features:
re
Token re
Feature activation+0.012
Top resid features:
wind
Tokenwind
Feature activation-0.034
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
hear
Token hear
Feature activation-0.026
Top resid features:
about
Token about
Feature activation-0.013
Top resid features:
how
Token how
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
film
Token film
Feature activation+3.311
Top resid features:
industry
Token industry
Feature activation+0.105
Top resid features:
is
Token is
Feature activation-0.043
Top resid features:
a
Token a
Feature activation-0.014
Top resid features:
business
Token business
Feature activation+0.027
Top resid features:
and
Token and
Feature activation-0.094
Top resid features:
trailer
Token trailer
Feature activation-0.010
Top resid features:
park
Token park
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
The
Token The
Feature activation-0.013
Top resid features:
original
Token original
Feature activation-0.024
Top resid features:
film
Token film
Feature activation+3.145
Top resid features:
,
Token,
Feature activation-0.064
Top resid features:
called
Token called
Feature activation-0.084
Top resid features:
One
Token One
Feature activation-0.038
Top resid features:
Last
Token Last
Feature activation-0.018
Top resid features:
Shot
Token Shot
Feature activation+0.155
Top resid features:
great
Token great
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
an
Token an
Feature activation+0.013
Top resid features:
adult
Token adult
Feature activation+0.001
Top resid features:
oriented
Token oriented
Feature activation+0.001
Top resid features:
film
Token film
Feature activation+3.315
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
In
Token In
Feature activation+0.001
Top resid features:
comparison
Token comparison
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Gone
Token Gone
Feature activation+0.023
Top resid features:
during
Token during
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
shooting
Token shooting
Feature activation+0.098
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
film
Token film
Feature activation+2.709
Top resid features:
by
Token by
Feature activation-0.012
Top resid features:
director
Token director
Feature activation+0.299
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
former
Token former
Feature activation-0.010
Top resid features:
Mont
Token Mont
Feature activation-0.001
Top resid features:
98
Token98
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
help
Token help
Feature activation+0.008
Top resid features:
fund
Token fund
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
film
Token film
Feature activation+1.600
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
It
Token It
Feature activation+0.005
Top resid features:
was
Token was
Feature activation-0.006
Top resid features:
shot
Token shot
Feature activation+0.054
Top resid features:
at
Token at
Feature activation+0.005
Top resid features:
An
TokenAn
Feature activation+0.001
Top resid features:
amateur
Token amateur
Feature activation-0.001
Top resid features:
prize
Token prize
Feature activation-0.005
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
winning
Tokenwinning
Feature activation+0.004
Top resid features:
film
Token film
Feature activation+2.048
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
1937
Token 1937
Feature activation+0.020
Top resid features:
].
Token].
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
8
Token8
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
000
Token000
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.005
Top resid features:
movie
Token movie
Feature activation+1.652
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
cast
Token cast
Feature activation+0.155
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
crew
Token crew
Feature activation+0.013
Top resid features:
members
Token members
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
particular
Token particular
Feature activation+0.002
Top resid features:
point
Token point
Feature activation+0.012
Top resid features:
in
Token in
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
film
Token film
Feature activation+1.262
Top resid features:
.
Token.
Feature activation-0.046
Top resid features:
So
Token So
Feature activation-0.040
Top resid features:
you
Token you
Feature activation-0.031
Top resid features:
re
Token re
Feature activation+0.052
Top resid features:
wind
Tokenwind
Feature activation-0.047
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.01

Head 4: 0.03

Head 5: 0.10

Head 6: 0.53

Head 7: 0.06

Head 8: 0.02

Head 9: 0.02

Head 10: 0.03

Head 11: 0.09

Positive logits

��2.44

writer2.33

writers2.22

excerpts2.16

films2.13

isodes1.99

convol1.97

netflix1.92

nudity1.90

itone1.90

portray1.90

actresses1.89

Films1.86

ovies1.84

paperback1.81

narration1.81

portraying1.79

1.79

obook1.79

NIGHT1.78

Negative logits

leve-1.75

neighbor-1.75

Wealth-1.72

traded-1.71

laus-1.71

ndra-1.69

routed-1.69

Slack-1.68

neau-1.67

Rails-1.67

GP-1.65

votes-1.64

mone-1.61

osi-1.61

parked-1.57

uninsured-1.57

drilled-1.56

defensive-1.55

Hockey-1.55

nard-1.54

INTERVAL 3.074 - 3.415
CONTAINS 0.000%

I
Token I
Feature activation+0.000
MAX
TokenMAX
Feature activation+1.799
and
Token and
Feature activation+0.000
certain
Token certain
Feature activation+0.000
Large
Token Large
Feature activation+0.000
Format
Token Format
Feature activation+3.415
theaters
Token theaters
Feature activation+0.576
and
Token and
Feature activation+0.000
opened
Token opened
Feature activation+0.895
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
x
Tokenx
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
early
Token early
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.000
screening
Token screening
Feature activation+3.303
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.000
June
Token June
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token '
Feature activation+0.000
As
TokenAs
Feature activation+0.002
anyone
Token anyone
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
seen
Token seen
Feature activation+3.179
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.000
can
Token can
Feature activation+0.000
attest
Token attest
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
forget
Token forget
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+3.300
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.500
lessons
Token lessons
Feature activation+0.000
(
Token (
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.732 - 3.074
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
le
Tokenle
Feature activation+0.000
of
Token of
Feature activation+0.000
Dogs
Token Dogs
Feature activation+0.000
premie
Token premie
Feature activation+2.971
res
Tokenres
Feature activation+0.921
in
Token in
Feature activation+0.000
theat
Token theat
Feature activation+0.769
res
Tokenres
Feature activation+1.007
on
Token on
Feature activation+0.000
technical
Token technical
Feature activation+0.000
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
film
Token film
Feature activation+0.010
-
Token-
Feature activation+0.000
making
Tokenmaking
Feature activation+2.762
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
this
Token this
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
Other
Token Other
Feature activation+0.000
Home
Token Home
Feature activation+0.000
begins
Token begins
Feature activation+0.238
screening
Token screening
Feature activation+2.822
in
Token in
Feature activation+0.168
China
Token China
Feature activation+0.000
on
Token on
Feature activation+0.000
August
Token August
Feature activation+0.000
11
Token 11
Feature activation+0.108
Film
Token Film
Feature activation+0.000
1937
Token 1937
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Shot
TokenShot
Feature activation+2.821
list
Tokenlist
Feature activation+0.000
:
Token:
Feature activation+0.000
Credits
Token Credits
Feature activation+0.516
(
Token (
Feature activation+0.000
0
Token0
Feature activation+0.000

INTERVAL 2.391 - 2.732
CONTAINS 0.001%

With
TokenWith
Feature activation+0.000
the
Token the
Feature activation+0.000
exception
Token exception
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
cast
Token cast
Feature activation+2.438
party
Token party
Feature activation+0.000
screening
Token screening
Feature activation+2.431
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.801
-
Token-
Feature activation+0.000
watch
Tokenwatch
Feature activation+2.350
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
20
Token 20
Feature activation+0.000
minutes
Token minutes
Feature activation+2.514
leading
Token leading
Feature activation+0.988
into
Token into
Feature activation+0.000
his
Token his
Feature activation+0.000
unt
Token unt
Feature activation+0.019
ime
Tokenime
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
business
Token business
Feature activation+0.386
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
casting
Token casting
Feature activation+2.495
white
Token white
Feature activation+0.000
men
Token men
Feature activation+0.000
will
Token will
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
General
Token General
Feature activation+0.000
-
Token-
Feature activation+0.000
Direct
TokenDirect
Feature activation+2.446
orate
Tokenorate
Feature activation+0.000
for
Token for
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
says
Token says
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.616
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.654
was
Token was
Feature activation+0.207
shot
Token shot
Feature activation+2.588
at
Token at
Feature activation+0.000
Lake
Token Lake
Feature activation+0.000
A
Token A
Feature activation+0.000
ft
Tokenft
Feature activation+0.086
on
Tokenon
Feature activation+0.000

INTERVAL 2.049 - 2.391
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.280
very
Token very
Feature activation+0.000
first
Token first
Feature activation+0.049
scene
Token scene
Feature activation+2.281
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
H
Token H
Feature activation+0.000
ux
Tokenux
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
very
Token very
Feature activation+0.000
frustrating
Token frustrating
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
we
Token we
Feature activation+0.000
saw
Token saw
Feature activation+2.336
this
Token this
Feature activation+0.000
script
Token script
Feature activation+1.280
come
Token come
Feature activation+0.000
through
Token through
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
exhilar
Token exhilar
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
shot
Token shot
Feature activation+2.225
at
Token at
Feature activation+0.000
unsuccessfully
Token unsuccessfully
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
athletic
Token athletic
Feature activation+0.000
and
Token and
Feature activation+0.000
food
Token food
Feature activation+0.000
additives
Token additives
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
which
Token which
Feature activation+0.000
viewers
Token viewers
Feature activation+2.100
are
Token are
Feature activation+0.000
told
Token told
Feature activation+0.223
,
Token,
Feature activation+0.000
via
Token via
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
Trinity
Token Trinity
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
directors
Token directors
Feature activation+2.330
and
Token and
Feature activation+0.000
stars
Token stars
Feature activation+0.750
are
Token are
Feature activation+0.000
worshipped
Token worshipped
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.708 - 2.049
CONTAINS 0.003%

asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+0.000
whom
Token whom
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
cast
Token cast
Feature activation+1.910
if
Token if
Feature activation+0.000
she
Token she
Feature activation+0.000
denies
Token denies
Feature activation+0.000
,
Token,
Feature activation+0.000
Rav
Token Rav
Feature activation+0.000
.
Token.
Feature activation+0.000
Story
Token Story
Feature activation+0.418
board
Tokenboard
Feature activation+0.000
Compos
Token Compos
Feature activation+0.312
er
Tokener
Feature activation+0.000
HD
Token HD
Feature activation+2.041
also
Token also
Feature activation+0.000
lets
Token lets
Feature activation+0.000
you
Token you
Feature activation+0.000
add
Token add
Feature activation+0.000
camera
Token camera
Feature activation+0.944
It
Token It
Feature activation+0.185
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
worth
Token worth
Feature activation+0.000
watching
Token watching
Feature activation+1.777
7
Token 7
Feature activation+0.000
/
Token/
Feature activation+0.000
10
Token10
Feature activation+0.000
.
Token.
Feature activation+0.000
Actually
Token Actually
Feature activation+0.000
previously
Token previously
Feature activation+0.222
anticipated
Token anticipated
Feature activation+0.012
.
Token.
Feature activation+0.000
Maver
Token Maver
Feature activation+1.384
ick
Tokenick
Feature activation+0.000
directors
Token directors
Feature activation+1.951
both
Token both
Feature activation+0.000
great
Token great
Feature activation+0.000
(
Token (
Feature activation+0.000
John
TokenJohn
Feature activation+0.000
Woo
Token Woo
Feature activation+0.000
,
Token,
Feature activation+0.000
utterly
Token utterly
Feature activation+0.000
lost
Token lost
Feature activation+0.000
by
Token by
Feature activation+0.000
what
Token what
Feature activation+0.000
director
Token director
Feature activation+1.916
Richard
Token Richard
Feature activation+0.000
Kelly
Token Kelly
Feature activation+0.000
was
Token was
Feature activation+0.000
going
Token going
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 1.366 - 1.708
CONTAINS 0.005%

morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
film
Token film
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+1.533
on
Token on
Feature activation+0.000
March
Token March
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
year
Token year
Feature activation+0.000
local
Token local
Feature activation+0.626
Feature
Token Feature
Feature activation+1.446
production
Token production
Feature activation+2.133
hit
Token hit
Feature activation+0.000
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
-
Token-
Feature activation+0.000
("
Token ("
Feature activation+0.000
Lost
TokenLost
Feature activation+0.000
")
Token")
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
director
Token director
Feature activation+1.608
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+0.504
movie
Token movie
Feature activation+0.322
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
ad
Token ad
Feature activation+0.442
heres
Tokenheres
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Director
Token Director
Feature activation+1.483
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
original
Token original
Feature activation+0.440
vision
Token vision
Feature activation+0.717
near
Token near
Feature activation+0.000
the
Token the
Feature activation+0.000
enormous
Token enormous
Feature activation+0.000
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
screen
Tokenscreen
Feature activation+1.556
average
Token average
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
blockbuster
Token blockbuster
Feature activation+0.549
new
Token new
Feature activation+0.000

INTERVAL 1.025 - 1.366
CONTAINS 0.007%

to
Token to
Feature activation+0.000
ever
Token ever
Feature activation+0.000
work
Token work
Feature activation+0.442
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
medium
Token medium
Feature activation+1.274
,
Token,
Feature activation+0.000
Hay
Token Hay
Feature activation+0.219
ao
Tokenao
Feature activation+0.000
Miy
Token Miy
Feature activation+0.000
azaki
Tokenazaki
Feature activation+0.426
tear
Token tear
Feature activation+0.088
j
Tokenj
Feature activation+0.000
erker
Tokenerker
Feature activation+0.392
!
Token!
Feature activation+0.000
Cha
Token Cha
Feature activation+0.000
plin
Tokenplin
Feature activation+1.247
is
Token is
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
w
Tokenw
Feature activation+0.000
illing
Tokenilling
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
other
Token other
Feature activation+0.000
directing
Token directing
Feature activation+1.098
projects
Token projects
Feature activation+1.494
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
:
Token:
Feature activation+0.000
Age
Token Age
Feature activation+0.000
of
Token of
Feature activation+0.000
Ultron
Token Ultron
Feature activation+0.000
cast
Token cast
Feature activation+1.061
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
film
Token film
Feature activation+0.296
website
Token website
Feature activation+0.000
IM
Token IM
Feature activation+0.000
whether
Token whether
Feature activation+0.000
to
Token to
Feature activation+0.000
dance
Token dance
Feature activation+0.000
or
Token or
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+1.060
.
Token.
Feature activation+0.000
Having
Token Having
Feature activation+0.000
that
Token that
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.683 - 1.025
CONTAINS 0.017%

Eden
Token Eden
Feature activation+0.000
,
Token,
Feature activation+0.000
Memory
Token Memory
Feature activation+0.000
,
Token,
Feature activation+0.000
&
Token &
Feature activation+0.000
Fil
Token Fil
Feature activation+0.940
ia
Tokenia
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
son
Token son
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
feature
Token feature
Feature activation+0.832
film
Token film
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
Although
TokenAlthough
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.134
had
Token had
Feature activation+0.000
mixed
Token mixed
Feature activation+1.001
reviews
Token reviews
Feature activation+0.809
,
Token,
Feature activation+0.000
Pop
Token Pop
Feature activation+0.000
eye
Tokeneye
Feature activation+0.000
Village
Token Village
Feature activation+0.000
remains
Token remains
Feature activation+0.000
Crit
Token Crit
Feature activation+0.556
erion
Tokenerion
Feature activation+0.222
Collection
Token Collection
Feature activation+0.887
Blu
Token Blu
Feature activation+0.247
-
Token-
Feature activation+0.000
ray
Tokenray
Feature activation+0.983
release
Token release
Feature activation+0.632
of
Token of
Feature activation+0.000
Godzilla
Token Godzilla
Feature activation+0.000
features
Token features
Feature activation+0.743
a
Token a
Feature activation+0.000
make
Token make
Feature activation+0.000
their
Token their
Feature activation+0.000
North
Token North
Feature activation+0.000
American
Token American
Feature activation+0.000
premie
Token premie
Feature activation+0.000
res
Tokenres
Feature activation+0.987
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
8
Token 8
Feature activation+0.000
Series
Token Series
Feature activation+0.000

INTERVAL 0.342 - 0.683
CONTAINS 0.033%

book
Token book
Feature activation+0.000
editor
Token editor
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
the
Token the
Feature activation+0.000
section
Token section
Feature activation+0.510
dropped
Token dropped
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
read
Token read
Feature activation+0.054
most
Token most
Feature activation+0.000
unique
Token unique
Feature activation+0.000
packaging
Token packaging
Feature activation+0.243
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
collection
Token collection
Feature activation+0.386
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
dig
Token dig
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
writer
Token writer
Feature activation+0.000
Ald
Token Ald
Feature activation+0.354
ous
Tokenous
Feature activation+0.000
H
Token H
Feature activation+0.000
ux
Tokenux
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
,
Token,
Feature activation+0.000
Code
Token Code
Feature activation+0.000
made
Token made
Feature activation+0.816
it
Token it
Feature activation+0.000
harder
Token harder
Feature activation+0.000
to
Token to
Feature activation+0.000
convey
Token convey
Feature activation+0.356
sex
Token sex
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
film
Token film
Feature activation+1.085
no
Token no
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
get
Token get
Feature activation+0.000
published
Token published
Feature activation+0.548
until
Token until
Feature activation+0.000
1967
Token 1967
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.000 - 0.342
CONTAINS 99.931%

machine
Token machine
Feature activation+0.000
is
Token is
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
any
Token any
Feature activation+0.000
human
Token human
Feature activation+0.000
should
Token should
Feature activation+0.000
aspire
Token aspire
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
the
Token the
Feature activation+0.000
dam
Token dam
Feature activation+0.000
's
Token's
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
bust
Token bust
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Gut
Token Gut
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ér
Tokenér
Feature activation+0.000
rez
Tokenrez
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
shut
Token shut
Feature activation+0.000
Gabriel
Token Gabriel
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
zes
Tokenzes
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
motivate
Token motivate
Feature activation+0.000
people
Token people
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
physics
Token physics
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
rush
Token rush
Feature activation+0.000
experts
Token experts
Feature activation+0.000
valuable
Token valuable
Feature activation+0.000
information
Token information
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
dolphins
Token dolphins
Feature activation+0.000
and
Token and
Feature activation+0.000
Bel
Token Bel
Feature activation+0.000
uga
Tokenuga
Feature activation+0.000
whales
Token whales
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 H1.6: (feature 20433)

TOP ACTIVATIONS
MAX = 3.620

rules
Token rules
Feature activation+0.495
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
after
Token after
Feature activation+0.000
her
Token her
Feature activation+0.000
arrival
Token arrival
Feature activation+3.620
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+1.652
States
Token States
Feature activation+1.666
,
Token,
Feature activation+0.000
sensible
Token sensible
Feature activation+0.000
positions
Token positions
Feature activation+0.000
on
Token on
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+3.316
guns
Token guns
Feature activation+0.000
,
Token,
Feature activation+0.000
abortion
Token abortion
Feature activation+0.000
rights
Token rights
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
green
Token green
Feature activation+2.024
card
Token card
Feature activation+0.429
because
Token because
Feature activation+0.000
he
Token he
Feature activation+0.000
arrived
Token arrived
Feature activation+3.193
before
Token before
Feature activation+0.000
1972
Token 1972
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
added
Token added
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
A
TokenA
Feature activation+0.000
hundred
Token hundred
Feature activation+0.000
illeg
Token illeg
Feature activation+2.784
als
Tokenals
Feature activation+0.801
all
Token all
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
for
Token for
Feature activation+0.000
re
Token re
Feature activation+1.238
entry
Tokenentry
Feature activation+2.022
into
Token into
Feature activation+1.225
another
Token another
Feature activation+0.000
country
Token country
Feature activation+2.718
after
Token after
Feature activation+0.000
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.198
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
joined
Token joined
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
native
Token native
Feature activation+2.686
Brazil
Token Brazil
Feature activation+0.281
ians
Tokenians
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.376
foreign
Token foreign
Feature activation+1.638
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.084
residents
Token residents
Feature activation+0.397
living
Token living
Feature activation+0.462
illegally
Token illegally
Feature activation+2.678
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.090
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+2.551
Stats
Token Stats
Feature activation+0.000
before
Token before
Feature activation+0.000
receiving
Token receiving
Feature activation+0.923
taxpayer
Token taxpayer
Feature activation+0.000
-
Token-
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
poll
Token poll
Feature activation+0.000
respondents
Token respondents
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
illegal
Token illegal
Feature activation+2.428
immigrants
Token immigrants
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
American
Token American
Feature activation+0.803
-
Token-
Feature activation+0.000
indictment
Token indictment
Feature activation+0.000
count
Token count
Feature activation+0.000
alleges
Token alleges
Feature activation+0.000
You
Token You
Feature activation+0.000
n
Tokenn
Feature activation+0.000
illegally
Token illegally
Feature activation+2.401
tam
Token tam
Feature activation+0.000
pered
Tokenpered
Feature activation+0.000
with
Token with
Feature activation+0.000
witness
Token witness
Feature activation+0.000
testimony
Token testimony
Feature activation+0.000
workers
Token workers
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.281
illegal
Token illegal
Feature activation+2.363
âĢĶ
Token âĢĶ
Feature activation+0.000
willing
Token willing
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.312
year
Token year
Feature activation+0.000
as
Token as
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+2.009
entered
Token entered
Feature activation+2.349
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.973
than
Token than
Feature activation+0.000
left
Token left
Feature activation+0.792
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.004
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.989
illegally
Token illegally
Feature activation+2.333
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
often
Token often
Feature activation+0.000
only
Token only
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
frequent
Token frequent
Feature activation+0.000
country
Token country
Feature activation+1.298
of
Token of
Feature activation+0.000
origin
Token origin
Feature activation+2.321
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
immigration
Token immigration
Feature activation+0.171
status
Token status
Feature activation+1.714
of
Token of
Feature activation+0.000
County
Token County
Feature activation+0.000
Wine
Token Wine
Feature activation+0.000
Country
Token Country
Feature activation+0.335
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
illegal
Token illegal
Feature activation+2.284
alien
Token alien
Feature activation+0.241
from
Token from
Feature activation+1.022
Mexico
Token Mexico
Feature activation+1.557
who
Token who
Feature activation+0.211
has
Token has
Feature activation+0.105
be
Token be
Feature activation+0.000
natural
Token natural
Feature activation+1.332
ized
Tokenized
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+2.253
year
Token year
Feature activation+0.034
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
country
Token country
Feature activation+0.000
bo
Token bo
Feature activation+0.000
omed
Tokenomed
Feature activation+0.000
,
Token,
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.000
arrived
Token arrived
Feature activation+2.244
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
millions
Token millions
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+1.652
States
Token States
Feature activation+1.666
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
returned
Token returned
Feature activation+2.212
home
Token home
Feature activation+0.433
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
every
Tokenevery
Feature activation+0.000
few
Token few
Feature activation+0.000
immigrant
Token immigrant
Feature activation+0.562
who
Token who
Feature activation+0.009
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
accepted
Token accepted
Feature activation+2.167
for
Token for
Feature activation+0.000
re
Token re
Feature activation+1.238
entry
Tokenentry
Feature activation+2.022
into
Token into
Feature activation+1.225
another
Token another
Feature activation+0.000
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.000
baby
Token baby
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
illegal
Token illegal
Feature activation+2.165
immigrant
Token immigrant
Feature activation+0.000
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+1.981

Top DFA by src position
MAX = 4.835

has
Token has
Feature activation-0.000
Top resid features:
said
Token said
Feature activation+0.028
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
she
Token she
Feature activation+0.028
Top resid features:
followed
Token followed
Feature activation-0.005
Top resid features:
immigration
Token immigration
Feature activation+4.835
Top resid features:
rules
Token rules
Feature activation+0.033
Top resid features:
and
Token and
Feature activation-0.071
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
after
Token after
Feature activation+0.136
Top resid features:
her
Token her
Feature activation+0.122
Top resid features:
also
Token also
Feature activation+0.018
Top resid features:
taken
Token taken
Feature activation+0.066
Top resid features:
sensible
Token sensible
Feature activation+0.078
Top resid features:
positions
Token positions
Feature activation+0.040
Top resid features:
on
Token on
Feature activation+0.013
Top resid features:
immigration
Token immigration
Feature activation+4.740
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
illegal
Token illegal
Feature activation-0.136
Top resid features:
guns
Token guns
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
abortion
Token abortion
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
On
TokenOn
Feature activation+0.003
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
immigration
Token immigration
Feature activation+4.349
Top resid features:
Judge
Token Judge
Feature activation+0.016
Top resid features:
Leonard
Token Leonard
Feature activation+0.010
Top resid features:
I
Token I
Feature activation+0.011
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Shapiro
Token Shapiro
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
tunnel
Token tunnel
Feature activation-0.006
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
illegal
Token illegal
Feature activation+0.053
Top resid features:
immigrants
Token immigrants
Feature activation+3.969
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
progress
Token progress
Feature activation+0.001
Top resid features:
!'
Token!'
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
interpreted
Token interpreted
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
mean
Token mean
Feature activation+0.037
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
an
Token an
Feature activation+0.016
Top resid features:
immigrant
Token immigrant
Feature activation+2.939
Top resid features:
who
Token who
Feature activation+0.010
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
not
Token not
Feature activation+0.016
Top resid features:
been
Token been
Feature activation+0.005
Top resid features:
accepted
Token accepted
Feature activation+0.038
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.333
Top resid features:
massive
Token massive
Feature activation+0.022
Top resid features:
wave
Token wave
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
immigrants
Token immigrants
Feature activation+1.994
Top resid features:
combined
Token combined
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
growth
Token growth
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
S
TokenS
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Congress
Token Congress
Feature activation-0.010
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
pass
Token pass
Feature activation+0.033
Top resid features:
immigration
Token immigration
Feature activation+4.059
Top resid features:
reform
Token reform
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
particularly
Token particularly
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
adoption
Token adoption
Feature activation+0.043
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
83
Token 83
Feature activation+0.010
Top resid features:
percent
Token percent
Feature activation+0.057
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
participants
Token participants
Feature activation+0.008
Top resid features:
immigrants
Token immigrants
Feature activation+2.029
Top resid features:
should
Token should
Feature activation+0.026
Top resid features:
be
Token be
Feature activation+0.031
Top resid features:
mandated
Token mandated
Feature activation-0.017
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
prove
Token prove
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
51
Token 51
Feature activation+0.022
Top resid features:
percent
Token percent
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
immigration
Token immigration
Feature activation+1.856
Top resid features:
poll
Token poll
Feature activation-0.041
Top resid features:
respondents
Token respondents
Feature activation+0.024
Top resid features:
said
Token said
Feature activation+0.047
Top resid features:
that
Token that
Feature activation+0.020
Top resid features:
illegal
Token illegal
Feature activation-0.193
Top resid features:
You
Token You
Feature activation+0.009
Top resid features:
n
Tokenn
Feature activation+0.012
Top resid features:
violated
Token violated
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
federal
Token federal
Feature activation+0.016
Top resid features:
immigration
Token immigration
Feature activation+3.186
Top resid features:
law
Token law
Feature activation+0.022
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
prohibits
Token prohibits
Feature activation-0.007
Top resid features:
bringing
Token bringing
Feature activation+0.026
Top resid features:
illegal
Token illegal
Feature activation-0.006
Top resid features:
have
Token have
Feature activation+0.024
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
large
Token large
Feature activation+0.039
Top resid features:
population
Token population
Feature activation+0.055
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
immigrant
Token immigrant
Feature activation+3.543
Top resid features:
workers
Token workers
Feature activation+0.042
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.089
Top resid features:
many
Token many
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
them
Token them
Feature activation+0.080
Top resid features:
14
Token 14
Feature activation+0.016
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
000
Token000
Feature activation+0.012
Top resid features:
fall
Token fall
Feature activation-0.011
Top resid features:
in
Token in
Feature activation-0.010
Top resid features:
immigration
Token immigration
Feature activation+2.564
Top resid features:
during
Token during
Feature activation+0.013
Top resid features:
this
Token this
Feature activation+0.022
Top resid features:
period
Token period
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
As
Token As
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
practice
Token practice
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
protect
Token protect
Feature activation+0.008
Top resid features:
illegal
Token illegal
Feature activation-0.017
Top resid features:
immigrants
Token immigrants
Feature activation+2.429
Top resid features:
convicted
Token convicted
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
crimes
Token crimes
Feature activation-0.020
Top resid features:
from
Token from
Feature activation+0.018
Top resid features:
being
Token being
Feature activation+0.009
Top resid features:
Nearly
TokenNearly
Feature activation+0.014
Top resid features:
70
Token 70
Feature activation-0.002
Top resid features:
percent
Token percent
Feature activation+0.025
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
immigrants
Token immigrants
Feature activation+3.269
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
list
Token list
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.016
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.019
Top resid features:
U
Token U
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
S
TokenS
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Immigration
Token Immigration
Feature activation+3.283
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
Customs
Token Customs
Feature activation+0.134
Top resid features:
Enforcement
Token Enforcement
Feature activation+0.038
Top resid features:
(
Token (
Feature activation-0.002
Top resid features:
ICE
TokenICE
Feature activation+0.034
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
7
Token7
Feature activation+0.014
Top resid features:
million
Token million
Feature activation+0.038
Top resid features:
estimated
Token estimated
Feature activation+0.032
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
immigrants
Token immigrants
Feature activation+3.519
Top resid features:
eligible
Token eligible
Feature activation+0.002
Top resid features:
today
Token today
Feature activation+0.025
Top resid features:
for
Token for
Feature activation+0.018
Top resid features:
eventual
Token eventual
Feature activation-0.004
Top resid features:
natural
Token natural
Feature activation-0.003
Top resid features:
The
Token The
Feature activation+0.045
Top resid features:
country
Token country
Feature activation+0.050
Top resid features:
bo
Token bo
Feature activation+0.032
Top resid features:
omed
Tokenomed
Feature activation+0.079
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
immigrants
Token immigrants
Feature activation+3.566
Top resid features:
arrived
Token arrived
Feature activation+0.022
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
millions
Token millions
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.005
Top resid features:
said
Token said
Feature activation+0.032
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
she
Token she
Feature activation+0.027
Top resid features:
followed
Token followed
Feature activation+0.002
Top resid features:
immigration
Token immigration
Feature activation+3.190
Top resid features:
rules
Token rules
Feature activation+0.010
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
after
Token after
Feature activation+0.047
Top resid features:
her
Token her
Feature activation+0.039
Top resid features:
interpreted
Token interpreted
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
mean
Token mean
Feature activation+0.047
Top resid features:
that
Token that
Feature activation-0.011
Top resid features:
an
Token an
Feature activation+0.044
Top resid features:
immigrant
Token immigrant
Feature activation+2.233
Top resid features:
who
Token who
Feature activation-0.026
Top resid features:
has
Token has
Feature activation+0.022
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.025
Top resid features:
accepted
Token accepted
Feature activation+0.146
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.330
Top resid features:
same
Token same
Feature activation+0.005
Top resid features:
illegal
Token illegal
Feature activation-0.002
Top resid features:
immigration
Token immigration
Feature activation+2.489
Top resid features:
poll
Token poll
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
total
Token total
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.03

Head 3: 0.02

Head 4: 0.03

Head 5: 0.11

Head 6: 0.53

Head 7: 0.07

Head 8: 0.03

Head 9: 0.03

Head 10: 0.02

Head 11: 0.06

Positive logits

DACA2.21

Refugee2.20

refugee2.16

Refugees2.16

deport2.09

immigrant2.09

refugees2.04

born2.04

visa2.01

arrivals2.00

deported2.00

visas2.00

abouts1.97

immigrant1.92

ocumented1.91

boarding1.87

igrants1.87

Afghans1.86

Detention1.84

Census1.83

Negative logits

HY-2.14

insula-2.01

RAL-1.99

quickShipAvailable-1.97

velength-1.94

sonian-1.89

-1.87

magnification-1.86

IPM-1.85

outube-1.84

iron-1.84

roth-1.80

ELD-1.80

exerted-1.77

Zen-1.76

MET-1.75

Nich-1.71

elight-1.70

ury-1.70

antioxid-1.70

INTERVAL 3.258 - 3.620
CONTAINS 0.000%

sensible
Token sensible
Feature activation+0.000
positions
Token positions
Feature activation+0.000
on
Token on
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+3.316
guns
Token guns
Feature activation+0.000
,
Token,
Feature activation+0.000
abortion
Token abortion
Feature activation+0.000
rights
Token rights
Feature activation+0.000
and
Token and
Feature activation+0.000
rules
Token rules
Feature activation+0.495
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
after
Token after
Feature activation+0.000
her
Token her
Feature activation+0.000
arrival
Token arrival
Feature activation+3.620
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+1.652
States
Token States
Feature activation+1.666
,
Token,
Feature activation+0.000

INTERVAL 2.896 - 3.258
CONTAINS 0.000%

a
Token a
Feature activation+0.000
green
Token green
Feature activation+2.024
card
Token card
Feature activation+0.429
because
Token because
Feature activation+0.000
he
Token he
Feature activation+0.000
arrived
Token arrived
Feature activation+3.193
before
Token before
Feature activation+0.000
1972
Token 1972
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.534 - 2.896
CONTAINS 0.001%

and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
joined
Token joined
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
native
Token native
Feature activation+2.686
Brazil
Token Brazil
Feature activation+0.281
ians
Tokenians
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.376
for
Token for
Feature activation+0.000
re
Token re
Feature activation+1.238
entry
Tokenentry
Feature activation+2.022
into
Token into
Feature activation+1.225
another
Token another
Feature activation+0.000
country
Token country
Feature activation+2.718
after
Token after
Feature activation+0.000
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.198
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
added
Token added
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
A
TokenA
Feature activation+0.000
hundred
Token hundred
Feature activation+0.000
illeg
Token illeg
Feature activation+2.784
als
Tokenals
Feature activation+0.801
all
Token all
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+2.551
Stats
Token Stats
Feature activation+0.000
before
Token before
Feature activation+0.000
receiving
Token receiving
Feature activation+0.923
taxpayer
Token taxpayer
Feature activation+0.000
-
Token-
Feature activation+0.000
foreign
Token foreign
Feature activation+1.638
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.084
residents
Token residents
Feature activation+0.397
living
Token living
Feature activation+0.462
illegally
Token illegally
Feature activation+2.678
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.090
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.172 - 2.534
CONTAINS 0.001%

County
Token County
Feature activation+0.000
Wine
Token Wine
Feature activation+0.000
Country
Token Country
Feature activation+0.335
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
illegal
Token illegal
Feature activation+2.284
alien
Token alien
Feature activation+0.241
from
Token from
Feature activation+1.022
Mexico
Token Mexico
Feature activation+1.557
who
Token who
Feature activation+0.211
has
Token has
Feature activation+0.105
immigration
Token immigration
Feature activation+0.000
poll
Token poll
Feature activation+0.000
respondents
Token respondents
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
illegal
Token illegal
Feature activation+2.428
immigrants
Token immigrants
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
American
Token American
Feature activation+0.803
-
Token-
Feature activation+0.000
country
Token country
Feature activation+0.000
bo
Token bo
Feature activation+0.000
omed
Tokenomed
Feature activation+0.000
,
Token,
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.000
arrived
Token arrived
Feature activation+2.244
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
millions
Token millions
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
workers
Token workers
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.281
illegal
Token illegal
Feature activation+2.363
âĢĶ
Token âĢĶ
Feature activation+0.000
willing
Token willing
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
frequent
Token frequent
Feature activation+0.000
country
Token country
Feature activation+1.298
of
Token of
Feature activation+0.000
origin
Token origin
Feature activation+2.321
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
immigration
Token immigration
Feature activation+0.171
status
Token status
Feature activation+1.714
of
Token of
Feature activation+0.000

INTERVAL 1.810 - 2.172
CONTAINS 0.002%

immigrant
Token immigrant
Feature activation+0.562
who
Token who
Feature activation+0.009
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
accepted
Token accepted
Feature activation+2.167
for
Token for
Feature activation+0.000
re
Token re
Feature activation+1.238
entry
Tokenentry
Feature activation+2.022
into
Token into
Feature activation+1.225
another
Token another
Feature activation+0.000
the
Token the
Feature activation+0.000
permanent
Token permanent
Feature activation+1.286
part
Token part
Feature activation+0.000
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+2.002
first
Token first
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.312
year
Token year
Feature activation+0.000
as
Token as
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+2.009
entered
Token entered
Feature activation+2.349
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.973
than
Token than
Feature activation+0.000
left
Token left
Feature activation+0.792
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Who
TokenWho
Feature activation+0.183
is
Token is
Feature activation+0.000
staying
Token staying
Feature activation+1.988
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
long
Token long
Feature activation+0.000
border
Token border
Feature activation+0.615
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
allowed
Token allowed
Feature activation+0.581
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+1.953
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Critics
TokenCritics
Feature activation+0.000
say
Token say
Feature activation+0.000

INTERVAL 1.448 - 1.810
CONTAINS 0.003%

her
Token her
Feature activation+0.000
arrival
Token arrival
Feature activation+3.620
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+1.652
States
Token States
Feature activation+1.666
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
returned
Token returned
Feature activation+2.212
home
Token home
Feature activation+0.433
âĢ
Token âĢ
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
prohibits
Token prohibits
Feature activation+0.006
bringing
Token bringing
Feature activation+1.988
illegal
Token illegal
Feature activation+1.746
aliens
Token aliens
Feature activation+0.000
into
Token into
Feature activation+1.404
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.769
States
Token States
Feature activation+0.445
Ley
Token Ley
Feature activation+0.000
,
Token,
Feature activation+0.000
holder
Token holder
Feature activation+0.470
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Canada
Token Canada
Feature activation+1.534
Research
Token Research
Feature activation+0.000
Chair
Token Chair
Feature activation+0.000
in
Token in
Feature activation+0.000
Ge
Token Ge
Feature activation+0.000
ography
Tokenography
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
deeper
Token deeper
Feature activation+0.000
attachment
Token attachment
Feature activation+0.000
to
Token to
Feature activation+0.000
Canada
Token Canada
Feature activation+1.463
and
Token and
Feature activation+0.000
feels
Token feels
Feature activation+0.000
a
Token a
Feature activation+0.000
stronger
Token stronger
Feature activation+0.000
sense
Token sense
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
illegal
Token illegal
Feature activation+2.284
alien
Token alien
Feature activation+0.241
from
Token from
Feature activation+1.022
Mexico
Token Mexico
Feature activation+1.557
who
Token who
Feature activation+0.211
has
Token has
Feature activation+0.105
been
Token been
Feature activation+0.000
twice
Token twice
Feature activation+0.000
returned
Token returned
Feature activation+1.436

INTERVAL 1.086 - 1.448
CONTAINS 0.005%

trusting
Token trusting
Feature activation+0.000
or
Token or
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
permanent
Token permanent
Feature activation+1.286
part
Token part
Feature activation+0.000
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+2.002
first
Token first
Feature activation+0.000
U
TokenU
Feature activation+0.261
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.172
.
Token.
Feature activation+0.000
immigration
Token immigration
Feature activation+0.145
officials
Token officials
Feature activation+1.431
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
crisis
Token crisis
Feature activation+0.799
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.040
were
Token were
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.138
from
Token from
Feature activation+1.135
Germany
Token Germany
Feature activation+0.076
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.007
residents
Token residents
Feature activation+0.397
living
Token living
Feature activation+0.462
illegally
Token illegally
Feature activation+2.678
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.090
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
bipartisan
Token bipartisan
Feature activation+0.000
program
Token program
Feature activation+0.508
,
Token,
Feature activation+0.000
commonly
Token commonly
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
Dream
Token Dream
Feature activation+1.300
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000
legal
Token legal
Feature activation+1.336
status
Token status
Feature activation+1.418

INTERVAL 0.724 - 1.086
CONTAINS 0.006%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
family
Token family
Feature activation+0.353
is
Token is
Feature activation+0.000
from
Token from
Feature activation+0.976
Sri
Token Sri
Feature activation+1.598
Lanka
Token Lanka
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
parents
Token parents
Feature activation+0.000
basic
Token basic
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
principles
Token principles
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.869
States
Token States
Feature activation+0.520
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
also
Token also
Feature activation+0.000
reveals
Token reveals
Feature activation+0.000
people
Token people
Feature activation+2.009
entered
Token entered
Feature activation+2.349
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.973
than
Token than
Feature activation+0.000
left
Token left
Feature activation+0.792
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Who
TokenWho
Feature activation+0.183
them
Token them
Feature activation+0.110
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
released
Token released
Feature activation+0.842
from
Token from
Feature activation+0.822
custody
Token custody
Feature activation+0.018
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
case
Token case
Feature activation+0.278
legislative
Token legislative
Feature activation+0.000
solution
Token solution
Feature activation+0.000
before
Token before
Feature activation+0.000
ordering
Token ordering
Feature activation+0.000
deport
Token deport
Feature activation+0.000
ations
Tokenations
Feature activation+0.750
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.362 - 0.724
CONTAINS 0.014%

11
Token 11
Feature activation+0.000
million
Token million
Feature activation+0.720
foreign
Token foreign
Feature activation+1.638
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.084
residents
Token residents
Feature activation+0.397
living
Token living
Feature activation+0.462
illegally
Token illegally
Feature activation+2.678
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.090
nationality
Token nationality
Feature activation+0.236
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+1.237
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.432
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
141
Token141
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.713
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Natural
Token Natural
Feature activation+0.667
ization
Tokenization
Feature activation+0.000
process
Token process
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
exempt
Token exempt
Feature activation+0.000
other
Token other
Feature activation+0.000
big
Token big
Feature activation+0.000
consumer
Token consumer
Feature activation+0.000
countries
Token countries
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.607
their
Token their
Feature activation+0.069
share
Token share
Feature activation+0.000
of
Token of
Feature activation+0.000
responsibility
Token responsibility
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.149
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
program
Token program
Feature activation+0.508
,
Token,
Feature activation+0.000
commonly
Token commonly
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
Dream
Token Dream
Feature activation+1.300

INTERVAL 0.000 - 0.362
CONTAINS 99.970%

ensuring
Token ensuring
Feature activation+0.000
no
Token no
Feature activation+0.000
l
Token l
Feature activation+0.000
umps
Tokenumps
Feature activation+0.000
.
Token.
Feature activation+0.000
Finally
Token Finally
Feature activation+0.000
,
Token,
Feature activation+0.000
stir
Token stir
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+0.000
Party
Token Party
Feature activation+0.000
with
Token with
Feature activation+0.000
respect
Token respect
Feature activation+0.000
to
Token to
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
and
Token and
Feature activation+0.000
military
Token military
Feature activation+0.000
voters
Token voters
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
McCain
Token McCain
Feature activation+0.000
the
Token the
Feature activation+0.000
rhetorical
Token rhetorical
Feature activation+0.000
escalation
Token escalation
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
Spicer
Token Spicer
Feature activation+0.000
himself
Token himself
Feature activation+0.000
.
Token.
Feature activation+0.000
together
Token together
Feature activation+0.000
to
Token to
Feature activation+0.000
talk
Token talk
Feature activation+0.000
again
Token again
Feature activation+0.000
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
did
Token did
Feature activation+0.000
Stat
Token Stat
Feature activation+0.000
eman
Tokeneman
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
say
Token say
Feature activation+0.000
baby
Token baby
Feature activation+0.000
is
Token is
Feature activation+0.000
international
Token international
Feature activation+0.000
surrog
Token surrog
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
rapid
Token rapid
Feature activation+0.000
rise
Token rise
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H1.6: (feature 8008)

TOP ACTIVATIONS
MAX = 2.844

The
TokenThe
Feature activation+0.000
planned
Token planned
Feature activation+0.000
changes
Token changes
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+2.844
in
Token in
Feature activation+0.035
consultation
Token consultation
Feature activation+0.000
with
Token with
Feature activation+0.000
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.000
suspended
Token suspended
Feature activation+0.000
until
Token until
Feature activation+0.000
changes
Token changes
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+2.521
to
Token to
Feature activation+0.462
restore
Token restore
Feature activation+0.195
every
Token every
Feature activation+0.016
voter
Token voter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defendant
Token defendant
Feature activation+0.000
changed
Token changed
Feature activation+0.000
his
Token his
Feature activation+0.000
original
Token original
Feature activation+2.513
statement
Token statement
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
picked
Token picked
Feature activation+0.000
changes
Token changes
Feature activation+0.388
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
components
Token components
Feature activation+0.000
now
Token now
Feature activation+2.495
compile
Token compile
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
in
Token in
Feature activation+0.040
Linux
Token Linux
Feature activation+0.000
allowing
Token allowing
Feature activation+0.055
mind
Token mind
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
code
Token code
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+2.306
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
's
Token's
Feature activation+0.000
Plan
Token Plan
Feature activation+0.000
(
Token (
Feature activation+0.000
ST
TokenST
Feature activation+0.000
P
TokenP
Feature activation+0.000
)
Token)
Feature activation+0.000
made
Token made
Feature activation+2.235
a
Token a
Feature activation+0.000
clear
Token clear
Feature activation+0.067
commitment
Token commitment
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
pload
Tokenpload
Feature activation+0.000
shutdown
Token shutdown
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+2.158
the
Token the
Feature activation+0.000
tables
Token tables
Feature activation+0.000
have
Token have
Feature activation+0.000
turned
Token turned
Feature activation+0.000
.
Token.
Feature activation+0.000
it
Token it
Feature activation+0.000
:
Token:
Feature activation+0.000
such
Token such
Feature activation+0.000
changes
Token changes
Feature activation+0.000
are
Token are
Feature activation+0.000
made
Token made
Feature activation+2.104
nightly
Token nightly
Feature activation+0.000
by
Token by
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
not
Token not
Feature activation+0.000
saying
Token saying
Feature activation+0.000
these
Token these
Feature activation+0.000
adjustments
Token adjustments
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+1.971
the
Token the
Feature activation+0.000
puck
Token puck
Feature activation+0.000
go
Token go
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
German
Token German
Feature activation+0.000
government
Token government
Feature activation+0.000
now
Token now
Feature activation+1.956
believes
Token believes
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
eurozone
Token eurozone
Feature activation+0.000
is
Token is
Feature activation+0.000
Regulations
Token Regulations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+1.948
rules
Token rules
Feature activation+0.000
are
Token are
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
t
Tokent
Feature activation+0.000
changed
Token changed
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
for
Token for
Feature activation+0.000
now
Token now
Feature activation+1.906
,
Token,
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.000
War
Token War
Feature activation+0.000
the
Token the
Feature activation+0.000
changes
Token changes
Feature activation+0.000
approved
Token approved
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+1.898
rules
Token rules
Feature activation+0.000
have
Token have
Feature activation+0.000
now
Token now
Feature activation+1.503
been
Token been
Feature activation+0.504
declared
Token declared
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+1.893
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
push
Token push
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
changes
Token changes
Feature activation+0.000
do
Token do
Feature activation+0.000
make
Token make
Feature activation+1.888
it
Token it
Feature activation+0.000
an
Token an
Feature activation+0.000
ent
Token ent
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
changes
Token changes
Feature activation+0.000
do
Token do
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+1.872
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
push
Token push
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.196
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
TokenNew
Feature activation+1.867
Area
Token Area
Feature activation+0.000
-
Token -
Feature activation+0.000
Ruins
Token Ruins
Feature activation+0.000
of
Token of
Feature activation+0.000
S
Token S
Feature activation+0.000
App
Token App
Feature activation+0.000
Gallery
Token Gallery
Feature activation+0.000
is
Token is
Feature activation+0.000
gone
Token gone
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+1.806
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
is
Token is
Feature activation+0.000
public
Token public
Feature activation+0.000
API
Token API
Feature activation+0.000
the
Token the
Feature activation+0.000
Canucks
Token Canucks
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
now
Token now
Feature activation+1.786
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
putting
Token putting
Feature activation+0.066
their
Token their
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
from
Token from
Feature activation+0.492
now
Token now
Feature activation+1.767
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+1.190
kind
Token kind
Feature activation+0.000

Top DFA by src position
MAX = 3.483

.
Token.
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
The
TokenThe
Feature activation-0.013
Top resid features:
planned
Token planned
Feature activation+0.004
Top resid features:
changes
Token changes
Feature activation+3.266
Top resid features:
will
Token will
Feature activation-0.070
Top resid features:
be
Token be
Feature activation+0.210
Top resid features:
made
Token made
Feature activation-0.131
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
consultation
Token consultation
Feature activation+0.000
Top resid features:
law
Token law
Feature activation+0.014
Top resid features:
must
Token must
Feature activation-0.007
Top resid features:
be
Token be
Feature activation+0.036
Top resid features:
suspended
Token suspended
Feature activation-0.001
Top resid features:
until
Token until
Feature activation-0.001
Top resid features:
changes
Token changes
Feature activation+2.984
Top resid features:
can
Token can
Feature activation-0.032
Top resid features:
be
Token be
Feature activation+0.143
Top resid features:
made
Token made
Feature activation-0.074
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
restore
Token restore
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation-0.028
Top resid features:
defendant
Token defendant
Feature activation-0.116
Top resid features:
changed
Token changed
Feature activation+3.483
Top resid features:
his
Token his
Feature activation+0.233
Top resid features:
original
Token original
Feature activation-0.290
Top resid features:
statement
Token statement
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
f
Tokenf
Feature activation-0.003
Top resid features:
ov
Tokenov
Feature activation-0.003
Top resid features:
70
Token 70
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Changes
TokenChanges
Feature activation+1.894
Top resid features:
are
Token are
Feature activation+0.037
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
follows
Token follows
Feature activation+0.045
Top resid features:
:
Token:
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.013
Top resid features:
and
Token and
Feature activation-0.022
Top resid features:
although
Token although
Feature activation-0.011
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
later
Token later
Feature activation+0.015
Top resid features:
changed
Token changed
Feature activation+2.718
Top resid features:
its
Token its
Feature activation+0.023
Top resid features:
mind
Token mind
Feature activation+0.022
Top resid features:
,
Token,
Feature activation-0.046
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
code
Token code
Feature activation+0.031
Top resid features:
ching
Tokenching
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
proposals
Token proposals
Feature activation+0.030
Top resid features:
for
Token for
Feature activation+0.015
Top resid features:
changes
Token changes
Feature activation+2.405
Top resid features:
at
Token at
Feature activation+0.012
Top resid features:
Ch
Token Ch
Feature activation+0.012
Top resid features:
aring
Tokenaring
Feature activation+0.004
Top resid features:
Cross
Token Cross
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
cyber
Token cyber
Feature activation+0.024
Top resid features:
lock
Tokenlock
Feature activation+0.000
Top resid features:
er
Tokener
Feature activation-0.009
Top resid features:
business
Token business
Feature activation-0.017
Top resid features:
changed
Token changed
Feature activation+2.726
Top resid features:
dramatically
Token dramatically
Feature activation+0.011
Top resid features:
following
Token following
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
Meg
Token Meg
Feature activation-0.010
Top resid features:
au
Tokenau
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.020
Top resid features:
carry
Token carry
Feature activation+0.019
Top resid features:
it
Token it
Feature activation+0.021
Top resid features:
:
Token:
Feature activation-0.078
Top resid features:
such
Token such
Feature activation-0.008
Top resid features:
changes
Token changes
Feature activation+2.867
Top resid features:
are
Token are
Feature activation+0.118
Top resid features:
made
Token made
Feature activation-0.152
Top resid features:
nightly
Token nightly
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
everyone
Token everyone
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
m
Tokenm
Feature activation-0.004
Top resid features:
not
Token not
Feature activation+0.012
Top resid features:
saying
Token saying
Feature activation+0.067
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
adjustments
Token adjustments
Feature activation+2.504
Top resid features:
will
Token will
Feature activation+0.075
Top resid features:
make
Token make
Feature activation-0.340
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
puck
Token puck
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.006
Top resid features:
second
Token second
Feature activation-0.015
Top resid features:
factor
Token factor
Feature activation+0.008
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
changed
Token changed
Feature activation+2.536
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
German
Token German
Feature activation+0.012
Top resid features:
government
Token government
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
With
TokenWith
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
changes
Token changes
Feature activation+1.077
Top resid features:
approved
Token approved
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
new
Token new
Feature activation-0.007
Top resid features:
rules
Token rules
Feature activation+0.049
Top resid features:
dates
Token dates
Feature activation-0.018
Top resid features:
haven
Token haven
Feature activation-0.020
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
t
Tokent
Feature activation-0.008
Top resid features:
changed
Token changed
Feature activation+2.150
Top resid features:
,
Token,
Feature activation-0.045
Top resid features:
so
Token so
Feature activation+0.104
Top resid features:
for
Token for
Feature activation+0.094
Top resid features:
now
Token now
Feature activation-0.157
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
With
TokenWith
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
changes
Token changes
Feature activation+1.597
Top resid features:
approved
Token approved
Feature activation-0.024
Top resid features:
,
Token,
Feature activation-0.076
Top resid features:
the
Token the
Feature activation+0.123
Top resid features:
new
Token new
Feature activation-0.135
Top resid features:
rules
Token rules
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
their
Token their
Feature activation+0.029
Top resid features:
attitudes
Token attitudes
Feature activation+0.018
Top resid features:
also
Token also
Feature activation-0.015
Top resid features:
having
Token having
Feature activation+0.013
Top resid features:
changed
Token changed
Feature activation+2.513
Top resid features:
for
Token for
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
worse
Token worse
Feature activation+0.027
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
prett
Token prett
Feature activation+0.020
Top resid features:
ier
Tokenier
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
and
Token and
Feature activation-0.029
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
changes
Token changes
Feature activation+2.596
Top resid features:
do
Token do
Feature activation+0.057
Top resid features:
make
Token make
Feature activation-0.277
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ent
Token ent
Feature activation+0.000
Top resid features:
Senator
TokenSenator
Feature activation-0.077
Top resid features:
Mad
Token Mad
Feature activation+0.004
Top resid features:
igan
Tokenigan
Feature activation-0.058
Top resid features:
says
Token says
Feature activation-0.004
Top resid features:
while
Token while
Feature activation-0.012
Top resid features:
changes
Token changes
Feature activation+2.571
Top resid features:
do
Token do
Feature activation+0.015
Top resid features:
need
Token need
Feature activation+0.015
Top resid features:
to
Token to
Feature activation-0.073
Top resid features:
be
Token be
Feature activation+0.198
Top resid features:
made
Token made
Feature activation+0.031
Top resid features:
up
Tokenup
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
most
Token most
Feature activation+0.004
Top resid features:
awesome
Token awesome
Feature activation-0.018
Top resid features:
changes
Token changes
Feature activation+1.753
Top resid features:
coming
Token coming
Feature activation+0.011
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
Patch
Token Patch
Feature activation+0.013
Top resid features:
2
Token 2
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
Unfortunately
Token Unfortunately
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.031
Top resid features:
times
Token times
Feature activation+0.040
Top resid features:
have
Token have
Feature activation+0.013
Top resid features:
changed
Token changed
Feature activation+2.217
Top resid features:
since
Token since
Feature activation+0.026
Top resid features:
2009
Token 2009
Feature activation+0.004
Top resid features:
--
Token --
Feature activation-0.034
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
old
Token old
Feature activation+0.102
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
18
Token18
Feature activation-0.012
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Change
TokenChange
Feature activation+2.326
Top resid features:
may
Token may
Feature activation+0.005
Top resid features:
be
Token be
Feature activation+0.057
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
foot
Tokenfoot
Feature activation-0.008
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
however
Token however
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
Google
Token Google
Feature activation-0.007
Top resid features:
has
Token has
Feature activation-0.007
Top resid features:
changed
Token changed
Feature activation+2.230
Top resid features:
plenty
Token plenty
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
increasingly
Token increasingly
Feature activation+0.026
Top resid features:
profound
Token profound
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.04

Head 3: 0.02

Head 4: 0.05

Head 5: 0.06

Head 6: 0.52

Head 7: 0.06

Head 8: 0.03

Head 9: 0.03

Head 10: 0.03

Head 11: 0.07

Positive logits

Changes2.40

changes2.09

redesign2.08

drastically1.98

reverted1.98

Differences1.88

changes1.87

radically1.86

Balance1.86

revert1.84

��1.84

merged1.78

Changes1.78

Kitt1.77

leveled1.74

decre1.71

modified1.71

outdated1.71

redesigned1.71

��1.70

Negative logits

cade-2.14

pd-2.07

olicited-1.85

tu-1.75

ideo-1.71

venture-1.70

lehem-1.70

liga-1.68

venture-1.68

cam-1.67

afer-1.67

ecd-1.65

aleb-1.64

defense-1.64

entious-1.63

lov-1.62

anamo-1.61

Fre-1.61

ofi-1.61

abl-1.60

INTERVAL 2.560 - 2.844
CONTAINS 0.000%

The
TokenThe
Feature activation+0.000
planned
Token planned
Feature activation+0.000
changes
Token changes
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+2.844
in
Token in
Feature activation+0.035
consultation
Token consultation
Feature activation+0.000
with
Token with
Feature activation+0.000
staff
Token staff
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.275 - 2.560
CONTAINS 0.000%

mind
Token mind
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
code
Token code
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+2.306
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
's
Token's
Feature activation+0.000
changes
Token changes
Feature activation+0.388
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
components
Token components
Feature activation+0.000
now
Token now
Feature activation+2.495
compile
Token compile
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
in
Token in
Feature activation+0.040
Linux
Token Linux
Feature activation+0.000
allowing
Token allowing
Feature activation+0.055
suspended
Token suspended
Feature activation+0.000
until
Token until
Feature activation+0.000
changes
Token changes
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+2.521
to
Token to
Feature activation+0.462
restore
Token restore
Feature activation+0.195
every
Token every
Feature activation+0.016
voter
Token voter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defendant
Token defendant
Feature activation+0.000
changed
Token changed
Feature activation+0.000
his
Token his
Feature activation+0.000
original
Token original
Feature activation+2.513
statement
Token statement
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
picked
Token picked
Feature activation+0.000

INTERVAL 1.991 - 2.275
CONTAINS 0.000%

it
Token it
Feature activation+0.000
:
Token:
Feature activation+0.000
such
Token such
Feature activation+0.000
changes
Token changes
Feature activation+0.000
are
Token are
Feature activation+0.000
made
Token made
Feature activation+2.104
nightly
Token nightly
Feature activation+0.000
by
Token by
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
Plan
Token Plan
Feature activation+0.000
(
Token (
Feature activation+0.000
ST
TokenST
Feature activation+0.000
P
TokenP
Feature activation+0.000
)
Token)
Feature activation+0.000
made
Token made
Feature activation+2.235
a
Token a
Feature activation+0.000
clear
Token clear
Feature activation+0.067
commitment
Token commitment
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
pload
Tokenpload
Feature activation+0.000
shutdown
Token shutdown
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+2.158
the
Token the
Feature activation+0.000
tables
Token tables
Feature activation+0.000
have
Token have
Feature activation+0.000
turned
Token turned
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.706 - 1.991
CONTAINS 0.002%

post
Token post
Feature activation+0.000
indicates
Token indicates
Feature activation+0.000
the
Token the
Feature activation+0.000
API
Token API
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+1.728
focused
Token focused
Feature activation+0.000
on
Token on
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
Netflix
Token Netflix
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
changes
Token changes
Feature activation+0.000
approved
Token approved
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+1.898
rules
Token rules
Feature activation+0.000
have
Token have
Feature activation+0.000
now
Token now
Feature activation+1.503
been
Token been
Feature activation+0.504
declared
Token declared
Feature activation+0.000
not
Token not
Feature activation+0.000
saying
Token saying
Feature activation+0.000
these
Token these
Feature activation+0.000
adjustments
Token adjustments
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+1.971
the
Token the
Feature activation+0.000
puck
Token puck
Feature activation+0.000
go
Token go
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
F
Token F
Feature activation+0.000
OV
TokenOV
Feature activation+0.000
setting
Token setting
Feature activation+0.000
to
Token to
Feature activation+0.228
the
Token the
Feature activation+0.000
new
Token new
Feature activation+1.719
default
Token default
Feature activation+0.000
value
Token value
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
game
Token game
Feature activation+0.000
App
Token App
Feature activation+0.000
Gallery
Token Gallery
Feature activation+0.000
is
Token is
Feature activation+0.000
gone
Token gone
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+1.806
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
is
Token is
Feature activation+0.000
public
Token public
Feature activation+0.000
API
Token API
Feature activation+0.000

INTERVAL 1.422 - 1.706
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000
changes
Token changes
Feature activation+0.000
and
Token and
Feature activation+0.000
new
Token new
Feature activation+1.646
APIs
Token APIs
Feature activation+0.000
for
Token for
Feature activation+0.000
web
Token web
Feature activation+0.000
developers
Token developers
Feature activation+0.000
can
Token can
Feature activation+0.000
of
Token of
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000
previously
Token previously
Feature activation+1.437
sought
Token sought
Feature activation+0.000
reform
Token reform
Feature activation+0.000
through
Token through
Feature activation+0.000
peaceful
Token peaceful
Feature activation+0.000
means
Token means
Feature activation+0.000
hoped
Token hoped
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
court
Token court
Feature activation+0.000
would
Token would
Feature activation+0.000
now
Token now
Feature activation+1.493
settle
Token settle
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
promptly
Token promptly
Feature activation+0.000
.
Token.
Feature activation+0.000
national
Token national
Feature activation+0.000
prescribing
Token prescribing
Feature activation+0.000
trends
Token trends
Feature activation+0.000
have
Token have
Feature activation+0.000
changed
Token changed
Feature activation+0.000
since
Token since
Feature activation+1.691
2010
Token 2010
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
any
Token any
Feature activation+0.000
drug
Token drug
Feature activation+0.000
changed
Token changed
Feature activation+0.000
.
Token.
Feature activation+0.000
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+1.558
religion
Token religion
Feature activation+0.000
with
Token with
Feature activation+0.000
sex
Token sex
Feature activation+0.000
,
Token,
Feature activation+0.000
violence
Token violence
Feature activation+0.000

INTERVAL 1.138 - 1.422
CONTAINS 0.002%

the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+1.196
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
20
Token 20
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.492
now
Token now
Feature activation+1.767
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+1.190
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
search
Token search
Feature activation+0.000
engine
Token engine
Feature activation+0.000
.
Token.
Feature activation+0.000
levels
Token levels
Feature activation+0.000
in
Token in
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
new
Token new
Feature activation+1.298
taxes
Token taxes
Feature activation+0.000
for
Token for
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
income
Tokenincome
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+1.139
study
Token study
Feature activation+0.000
called
Token called
Feature activation+0.000
PART
Token PART
Feature activation+0.000
NER
TokenNER
Feature activation+0.000
started
Token started
Feature activation+0.000
forward
Token forward
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
S
Token S
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
now
Token now
Feature activation+1.390
cement
Token cement
Feature activation+0.000
ed
Tokened
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000

INTERVAL 0.853 - 1.138
CONTAINS 0.004%

there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.313
too
Token too
Feature activation+0.000
many
Token many
Feature activation+0.000
new
Token new
Feature activation+1.050
buildings
Token buildings
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
now
Token now
Feature activation+1.458
,
Token,
Feature activation+0.000
sour
Token sour
Feature activation+0.000
beers
Token beers
Feature activation+0.000
may
Token may
Feature activation+0.000
still
Token still
Feature activation+1.136
be
Token be
Feature activation+0.000
just
Token just
Feature activation+0.000
slightly
Token slightly
Feature activation+0.087
unpopular
Token unpopular
Feature activation+0.000
enough
Token enough
Feature activation+0.000
Brock
Token Brock
Feature activation+0.000
Les
Token Les
Feature activation+0.000
nar
Tokennar
Feature activation+0.000
vs
Token vs
Feature activation+0.000
.
Token.
Feature activation+0.000
new
Token new
Feature activation+1.123
WWE
Token WWE
Feature activation+0.000
Champion
Token Champion
Feature activation+0.000
AJ
Token AJ
Feature activation+0.000
Styles
Token Styles
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
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
become
Token become
Feature activation+0.933
common
Token common
Feature activation+0.038
to
Token to
Feature activation+0.266
find
Token find
Feature activation+0.000
sour
Token sour
Feature activation+0.000
beers
Token beers
Feature activation+0.000
legendary
Token legendary
Feature activation+0.000
lightweight
Token lightweight
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+0.992
head
Token head
Feature activation+0.000
band
Tokenband
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000

INTERVAL 0.569 - 0.853
CONTAINS 0.007%

recognizable
Token recognizable
Feature activation+0.000
form
Token form
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.826
art
Token art
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
and
Token and
Feature activation+0.000
job
Token job
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.000
and
Token and
Feature activation+0.000
build
Token build
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.724
party
Token party
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Nothing
TokenNothing
Feature activation+0.000
will
Token will
Feature activation+0.000
different
Token different
Feature activation+0.033
populations
Token populations
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
now
Token now
Feature activation+0.728
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
different
Token different
Feature activation+0.135
jaw
Token jaw
Feature activation+0.000
the
Token the
Feature activation+0.000
clinical
Token clinical
Feature activation+0.000
literature
Token literature
Feature activation+0.000
,
Token,
Feature activation+0.000
our
Token our
Feature activation+0.000
previous
Token previous
Feature activation+0.759
work
Token work
Feature activation+0.000
(
Token (
Feature activation+0.000
Mont
TokenMont
Feature activation+0.000
al
Tokenal
Feature activation+0.000
vo
Tokenvo
Feature activation+0.000
to
Token to
Feature activation+0.000
next
Token next
Feature activation+0.000
map
Token map
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
still
Token still
Feature activation+0.705
taking
Token taking
Feature activation+0.000
affect
Token affect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.284 - 0.569
CONTAINS 0.017%

improve
Token improve
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.118
change
Token change
Feature activation+0.404
;
Token;
Feature activation+0.000
to
Token to
Feature activation+0.393
be
Token be
Feature activation+0.019
perfect
Token perfect
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.360
change
Token change
Feature activation+0.456
advent
Token advent
Feature activation+0.000
of
Token of
Feature activation+0.000
reverse
Token reverse
Feature activation+0.000
vending
Token vending
Feature activation+0.000
machines
Token machines
Feature activation+0.000
making
Token making
Feature activation+0.452
deposit
Token deposit
Feature activation+0.000
refunds
Token refunds
Feature activation+0.000
simpler
Token simpler
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.110
should
Token should
Feature activation+0.000
stand
Token stand
Feature activation+0.000
out
Token out
Feature activation+0.000
almost
Token almost
Feature activation+0.014
immediately
Token immediately
Feature activation+0.059
after
Token after
Feature activation+0.387
starting
Token starting
Feature activation+0.036
up
Token up
Feature activation+0.000
YouTube
Token YouTube
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
examples
Token examples
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
current
Token current
Feature activation+0.951
evolution
Token evolution
Feature activation+0.000
began
Token began
Feature activation+0.321
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
longer
Token longer
Feature activation+0.297
ago
Token ago
Feature activation+0.109
than
Token than
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
awesome
Token awesome
Feature activation+0.000
changes
Token changes
Feature activation+0.000
coming
Token coming
Feature activation+0.458
with
Token with
Feature activation+0.000
Patch
Token Patch
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000

INTERVAL 0.000 - 0.284
CONTAINS 99.967%

build
Token build
Feature activation+0.000
us
Token us
Feature activation+0.000
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
safer
Token safer
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
you
Token you
Feature activation+0.000
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
P
Token P
Feature activation+0.000
AM
TokenAM
Feature activation+0.000
sequence
Token sequence
Feature activation+0.000
(
Token (
Feature activation+0.000
Fig
TokenFig
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
).
Token ).
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
anything
Token anything
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
Navy
Token Navy
Feature activation+0.000
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
about
Token about
Feature activation+0.000
its
Token its
Feature activation+0.000
has
Token has
Feature activation+0.000
operated
Token operated
Feature activation+0.000
since
Token since
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
lead
Token lead
Feature activation+0.000
Ju
Token Ju
Feature activation+0.000
ha
Tokenha
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