H6.11 top features

Top feature 0 in H6.11: (feature 8483)

TOP ACTIVATIONS
MAX = 3.115

ures
Tokenures
Feature activation+0.000
in
Token in
Feature activation+0.000
Malfoy
Token Malfoy
Feature activation+0.874
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.115
house
Token house
Feature activation+0.743
.
Token.
Feature activation+0.000
Re
Token Re
Feature activation+0.000
iter
Tokeniter
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
leading
Tokenleading
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.078
I
Token I
Feature activation+1.121
gar
Tokengar
Feature activation+1.424
ashi
Tokenashi
Feature activation+2.446
's
Token's
Feature activation+1.544
case
Token case
Feature activation+0.366
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
death
Token death
Feature activation+0.000
.
Token.
Feature activation+0.000
instead
Token instead
Feature activation+0.000
,
Token,
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
in
Token in
Feature activation+0.000
some
Token some
Feature activation+2.204
way
Token way
Feature activation+0.923
to
Token to
Feature activation+0.000
contribute
Token contribute
Feature activation+0.000
to
Token to
Feature activation+0.000
more
Token more
Feature activation+0.000
what
Token what
Feature activation+0.000
activities
Token activities
Feature activation+0.000
will
Token will
Feature activation+0.000
occur
Token occur
Feature activation+0.000
in
Token in
Feature activation+0.000
what
Token what
Feature activation+2.059
order
Token order
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
can
Token can
Feature activation+0.000
also
Token also
Feature activation+0.000
an
Token an
Feature activation+0.000
exclusive
Token exclusive
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
if
Token if
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+2.032
case
Token case
Feature activation+0.040
,
Token,
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
state
Token state
Feature activation+0.000
But
Token But
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
in
Token in
Feature activation+0.000
Joe
Token Joe
Feature activation+1.086
Man
Token Man
Feature activation+0.017
chin
Tokenchin
Feature activation+2.031
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.624
world
Token world
Feature activation+0.921
today
Token today
Feature activation+0.155
Elliot
Token Elliot
Feature activation+0.000
te
Tokente
Feature activation+0.000
Friedman
Token Friedman
Feature activation+0.459
âĢ
TokenâĢ
Feature activation+0.088
Ļ
TokenĻ
Feature activation+0.292
s
Tokens
Feature activation+1.990
30
Token 30
Feature activation+0.000
Thoughts
Token Thoughts
Feature activation+0.000
article
Token article
Feature activation+1.136
today
Token today
Feature activation+0.221
he
Token he
Feature activation+0.200
]
Token]
Feature activation+0.000
first
Token first
Feature activation+0.000
called
Token called
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
maths
Token maths
Feature activation+1.982
class
Token class
Feature activation+0.892
,"
Token,"
Feature activation+0.000
Ver
Token Ver
Feature activation+0.000
h
Tokenh
Feature activation+0.000
agen
Tokenagen
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Miller
Token Miller
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.094
Ļ
TokenĻ
Feature activation+0.090
s
Tokens
Feature activation+1.964
defense
Token defense
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
leading
Token leading
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
spur
Token spur
Feature activation+0.891
ge
Tokenge
Feature activation+1.954
family
Token family
Feature activation+0.850
(
Token (
Feature activation+0.000
E
TokenE
Feature activation+0.000
uph
Tokenuph
Feature activation+0.000
or
Tokenor
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Snowden
Token Snowden
Feature activation+1.037
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.240
s
Tokens
Feature activation+1.952
case
Token case
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
obstacle
Token obstacle
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.067
exact
Token exact
Feature activation+1.448
same
Token same
Feature activation+1.948
way
Token way
Feature activation+0.063
,
Token,
Feature activation+0.000
250
Token 250
Feature activation+0.000
times
Token times
Feature activation+0.000
.
Token.
Feature activation+0.000
rupt
Tokenrupt
Feature activation+0.000
Begin
Token Begin
Feature activation+0.000
nings
Tokennings
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+1.938
Hit
Token Hit
Feature activation+0.000
chens
Tokenchens
Feature activation+0.000
discusses
Token discusses
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
fascinating
Token fascinating
Feature activation+0.000
storyline
Token storyline
Feature activation+0.000
in
Token in
Feature activation+0.000
amazing
Token amazing
Feature activation+1.923
animation
Token animation
Feature activation+0.114
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
game
Token game
Feature activation+0.000
by
Token by
Feature activation+0.000
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+1.719
space
Token space
Feature activation+1.885
they
Token they
Feature activation+0.055
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.174
supposed
Token supposed
Feature activation+0.003
the
Token the
Feature activation+0.387
Avengers
Token Avengers
Feature activation+1.119
:
Token:
Feature activation+0.000
Age
Token Age
Feature activation+0.000
of
Token of
Feature activation+0.000
Ultron
Token Ultron
Feature activation+1.834
cast
Token cast
Feature activation+1.456
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
film
Token film
Feature activation+0.000
website
Token website
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
GE
Token GE
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.764
s
Tokens
Feature activation+1.778
case
Token case
Feature activation+0.000
,
Token,
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.020
Our
Token Our
Feature activation+0.000
Lady
Token Lady
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.752
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
D
TokenD
Feature activation+0.000
ign
Tokenign
Feature activation+0.000
actually
Token actually
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
Naked
Token Naked
Feature activation+0.133
Lunch
Token Lunch
Feature activation+1.751
,
Token,
Feature activation+0.565
"
Token "
Feature activation+0.000
Ste
TokenSte
Feature activation+0.000
e
Tokene
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
property
Token property
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.161
content
Token content
Feature activation+1.747
of
Token of
Feature activation+0.325
an
Token an
Feature activation+0.269
email
Token email
Feature activation+0.325
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000

Top DFA by src position
MAX = 3.740

female
Token female
Feature activation-0.002
Top resid features:
teacher
Token teacher
Feature activation-0.000
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
tort
Token tort
Feature activation+0.005
Top resid features:
ures
Tokenures
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+3.740
Top resid features:
Malfoy
Token Malfoy
Feature activation-0.072
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation-0.018
Top resid features:
house
Token house
Feature activation+0.000
Top resid features:
gar
Tokengar
Feature activation-0.003
Top resid features:
ashi
Tokenashi
Feature activation-0.002
Top resid features:
(
Token (
Feature activation+0.027
Top resid features:
leading
Tokenleading
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
in
Token in
Feature activation+2.999
Top resid features:
I
Token I
Feature activation-0.014
Top resid features:
gar
Tokengar
Feature activation+0.008
Top resid features:
ashi
Tokenashi
Feature activation-0.015
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation-0.025
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
instead
Token instead
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
hoping
Token hoping
Feature activation+0.039
Top resid features:
in
Token in
Feature activation+2.801
Top resid features:
some
Token some
Feature activation+0.011
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
contribute
Token contribute
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.010
Top resid features:
what
Token what
Feature activation+0.011
Top resid features:
activities
Token activities
Feature activation+0.022
Top resid features:
will
Token will
Feature activation+0.008
Top resid features:
occur
Token occur
Feature activation+0.081
Top resid features:
in
Token in
Feature activation+2.446
Top resid features:
what
Token what
Feature activation+0.019
Top resid features:
order
Token order
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
an
Token an
Feature activation+0.009
Top resid features:
exclusive
Token exclusive
Feature activation+0.001
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.004
Top resid features:
if
Token if
Feature activation-0.074
Top resid features:
in
Token in
Feature activation+2.519
Top resid features:
their
Token their
Feature activation+0.113
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Islamic
Token Islamic
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
Man
Token Man
Feature activation-0.006
Top resid features:
chin
Tokenchin
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
But
Token But
Feature activation-0.023
Top resid features:
perhaps
Token perhaps
Feature activation-0.019
Top resid features:
in
Token in
Feature activation+2.904
Top resid features:
Joe
Token Joe
Feature activation-0.132
Top resid features:
Man
Token Man
Feature activation-0.035
Top resid features:
chin
Tokenchin
Feature activation-0.034
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
11
Token11
Feature activation+0.001
Top resid features:
th
Tokenth
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.001
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+2.756
Top resid features:
Elliot
Token Elliot
Feature activation-0.012
Top resid features:
te
Tokente
Feature activation+0.002
Top resid features:
Friedman
Token Friedman
Feature activation-0.074
Top resid features:
âĢ
TokenâĢ
Feature activation-0.047
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
o
Tokeno
Feature activation-0.001
Top resid features:
]
Token]
Feature activation-0.002
Top resid features:
first
Token first
Feature activation-0.004
Top resid features:
called
Token called
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
in
Token in
Feature activation+2.594
Top resid features:
maths
Token maths
Feature activation-0.073
Top resid features:
class
Token class
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
Ver
Token Ver
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.010
Top resid features:
gone
Token gone
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
In
TokenIn
Feature activation+2.731
Top resid features:
Miller
Token Miller
Feature activation-0.109
Top resid features:
âĢ
TokenâĢ
Feature activation-0.013
Top resid features:
Ļ
TokenĻ
Feature activation-0.020
Top resid features:
s
Tokens
Feature activation-0.024
Top resid features:
defense
Token defense
Feature activation+0.000
Top resid features:
commonly
Token commonly
Feature activation-0.011
Top resid features:
called
Token called
Feature activation-0.015
Top resid features:
spur
Token spur
Feature activation-0.024
Top resid features:
ge
Tokenge
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
in
Token in
Feature activation+2.374
Top resid features:
the
Token the
Feature activation+0.375
Top resid features:
spur
Token spur
Feature activation-0.271
Top resid features:
ge
Tokenge
Feature activation-0.024
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
in
Tokenin
Feature activation+0.017
Top resid features:
consistently
Token consistently
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
In
TokenIn
Feature activation+3.052
Top resid features:
Snowden
Token Snowden
Feature activation-0.327
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation-0.022
Top resid features:
s
Tokens
Feature activation-0.094
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
exact
Token exact
Feature activation+0.015
Top resid features:
same
Token same
Feature activation+0.019
Top resid features:
obstacle
Token obstacle
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
in
Token in
Feature activation+2.368
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
exact
Token exact
Feature activation+0.017
Top resid features:
same
Token same
Feature activation+0.066
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ually
Tokenually
Feature activation-0.000
Top resid features:
immoral
Token immoral
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
In
TokenIn
Feature activation+2.746
Top resid features:
chapter
Token chapter
Feature activation-0.051
Top resid features:
eleven
Token eleven
Feature activation-0.031
Top resid features:
,
Token,
Feature activation-0.098
Top resid features:
âĢ
Token âĢ
Feature activation-0.020
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
effects
Token effects
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
fascinating
Token fascinating
Feature activation+0.010
Top resid features:
storyline
Token storyline
Feature activation+0.055
Top resid features:
in
Token in
Feature activation+2.422
Top resid features:
amazing
Token amazing
Feature activation-0.002
Top resid features:
animation
Token animation
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
game
Token game
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
constantly
Token constantly
Feature activation+0.002
Top resid features:
figure
Token figure
Feature activation-0.000
Top resid features:
out
Token out
Feature activation-0.001
Top resid features:
where
Token where
Feature activation+0.021
Top resid features:
in
Token in
Feature activation+2.544
Top resid features:
that
Token that
Feature activation-0.114
Top resid features:
space
Token space
Feature activation+0.016
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
stars
Token stars
Feature activation+0.004
Top resid features:
said
Token said
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
be
Token be
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+1.841
Top resid features:
the
Token the
Feature activation+0.636
Top resid features:
Avengers
Token Avengers
Feature activation-0.088
Top resid features:
:
Token:
Feature activation-0.038
Top resid features:
Age
Token Age
Feature activation-0.009
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
Omaha
Token Omaha
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
In
TokenIn
Feature activation+2.445
Top resid features:
GE
Token GE
Feature activation-0.130
Top resid features:
âĢ
TokenâĢ
Feature activation-0.019
Top resid features:
Ļ
TokenĻ
Feature activation-0.009
Top resid features:
s
Tokens
Feature activation-0.014
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
bulletin
Token bulletin
Feature activation+0.000
Top resid features:
items
Token items
Feature activation+0.012
Top resid features:
like
Token like
Feature activation+0.023
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
one
Token one
Feature activation-0.011
Top resid features:
in
Token in
Feature activation+2.271
Top resid features:
Our
Token Our
Feature activation-0.001
Top resid features:
Lady
Token Lady
Feature activation+0.067
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation-0.033
Top resid features:
but
Token but
Feature activation+0.005
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
actually
Token actually
Feature activation+0.001
Top resid features:
understanding
Token understanding
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
In
Token In
Feature activation+2.431
Top resid features:
Naked
Token Naked
Feature activation-0.047
Top resid features:
Lunch
Token Lunch
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Ste
TokenSte
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.008
Top resid features:
there
Token there
Feature activation-0.003
Top resid features:
should
Token should
Feature activation-0.037
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
property
Token property
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+2.228
Top resid features:
the
Token the
Feature activation+0.072
Top resid features:
content
Token content
Feature activation+0.036
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
email
Token email
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.03

Head 2: 0.02

Head 3: 0.02

Head 4: 0.03

Head 5: 0.05

Head 6: 0.03

Head 7: 0.04

Head 8: 0.08

Head 9: 0.02

Head 10: 0.01

Head 11: 0.56

Positive logits

guise2.45

increments2.06

vein2.01

corridors1.85

contexts1.79

woods1.77

arenas1.77

manner1.74

realm1.73

halls1.71

context1.69

circles1.66

realms1.65

courtroom1.64

disguise1.63

fashion1.62

mode1.62

areas1.59

confines1.59

precincts1.58

Negative logits

orsi-1.48

ourge-1.40

pletion-1.36

SpaceEngineers-1.33

rike-1.31

ient-1.30

itans-1.29

successful-1.29

omaly-1.28

rification-1.25

antz-1.25

apego-1.24

itiveness-1.22

orem-1.21

Thing-1.20

apter-1.19

))))-1.19

vantage-1.19

piring-1.19

oulder-1.19

INTERVAL 2.803 - 3.115
CONTAINS 0.000%

ures
Tokenures
Feature activation+0.000
in
Token in
Feature activation+0.000
Malfoy
Token Malfoy
Feature activation+0.874
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.115
house
Token house
Feature activation+0.743
.
Token.
Feature activation+0.000
Re
Token Re
Feature activation+0.000
iter
Tokeniter
Feature activation+0.000
ating
Tokenating
Feature activation+0.000

INTERVAL 2.492 - 2.803
CONTAINS 0.000%

INTERVAL 2.180 - 2.492
CONTAINS 0.000%

.
Token.
Feature activation+0.000
instead
Token instead
Feature activation+0.000
,
Token,
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
in
Token in
Feature activation+0.000
some
Token some
Feature activation+2.204
way
Token way
Feature activation+0.923
to
Token to
Feature activation+0.000
contribute
Token contribute
Feature activation+0.000
to
Token to
Feature activation+0.000
more
Token more
Feature activation+0.000
leading
Tokenleading
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.078
I
Token I
Feature activation+1.121
gar
Tokengar
Feature activation+1.424
ashi
Tokenashi
Feature activation+2.446
's
Token's
Feature activation+1.544
case
Token case
Feature activation+0.366
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
death
Token death
Feature activation+0.000

INTERVAL 1.869 - 2.180
CONTAINS 0.001%

figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+1.719
space
Token space
Feature activation+1.885
they
Token they
Feature activation+0.055
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.174
supposed
Token supposed
Feature activation+0.003
rupt
Tokenrupt
Feature activation+0.000
Begin
Token Begin
Feature activation+0.000
nings
Tokennings
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+1.938
Hit
Token Hit
Feature activation+0.000
chens
Tokenchens
Feature activation+0.000
discusses
Token discusses
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
fascinating
Token fascinating
Feature activation+0.000
storyline
Token storyline
Feature activation+0.000
in
Token in
Feature activation+0.000
amazing
Token amazing
Feature activation+1.923
animation
Token animation
Feature activation+0.114
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
game
Token game
Feature activation+0.000
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
exclusive
Token exclusive
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
if
Token if
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+2.032
case
Token case
Feature activation+0.040
,
Token,
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
state
Token state
Feature activation+0.000
what
Token what
Feature activation+0.000
activities
Token activities
Feature activation+0.000
will
Token will
Feature activation+0.000
occur
Token occur
Feature activation+0.000
in
Token in
Feature activation+0.000
what
Token what
Feature activation+2.059
order
Token order
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
can
Token can
Feature activation+0.000
also
Token also
Feature activation+0.000

INTERVAL 1.557 - 1.869
CONTAINS 0.003%

actually
Token actually
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
Naked
Token Naked
Feature activation+0.133
Lunch
Token Lunch
Feature activation+1.751
,
Token,
Feature activation+0.565
"
Token "
Feature activation+0.000
Ste
TokenSte
Feature activation+0.000
e
Tokene
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
lists
Tokenlists
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.504
wide
Token wide
Feature activation+0.445
variety
Token variety
Feature activation+1.018
of
Token of
Feature activation+1.736
themes
Token themes
Feature activation+0.298
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
Store
Token Store
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Then
TokenThen
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
Walker
Token Walker
Feature activation+1.627
's
Token's
Feature activation+0.847
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+0.000
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
the
Token the
Feature activation+0.000
labor
Token labor
Feature activation+0.000
force
Token force
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
many
Token many
Feature activation+1.658
cases
Token cases
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
property
Token property
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.161
content
Token content
Feature activation+1.747
of
Token of
Feature activation+0.325
an
Token an
Feature activation+0.269
email
Token email
Feature activation+0.325
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000

INTERVAL 1.246 - 1.557
CONTAINS 0.008%

days
Token days
Feature activation+0.000
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
summer
Token summer
Feature activation+1.364
and
Token and
Feature activation+0.000
winter
Token winter
Feature activation+1.314
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
my
Token my
Feature activation+0.000
arts
Tokenarts
Feature activation+0.000
,
Token,
Feature activation+0.026
Urban
TokenUrban
Feature activation+0.000
Shadows
Token Shadows
Feature activation+0.000
,
Token,
Feature activation+0.329
and
Token and
Feature activation+1.525
more
Token more
Feature activation+0.570
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
promised
Token promised
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.196
ways
Token ways
Feature activation+1.324
of
Token of
Feature activation+0.535
benefits
Token benefits
Feature activation+0.168
for
Token for
Feature activation+0.000
Medicare
Token Medicare
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
d
Tokend
Feature activation+0.000
oled
Tokenoled
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.064
166
Token 166
Feature activation+1.263
payments
Token payments
Feature activation+0.544
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Avengers
Token Avengers
Feature activation+1.119
:
Token:
Feature activation+0.000
Age
Token Age
Feature activation+0.000
of
Token of
Feature activation+0.000
Ultron
Token Ultron
Feature activation+1.834
cast
Token cast
Feature activation+1.456
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
film
Token film
Feature activation+0.000
website
Token website
Feature activation+0.000
IM
Token IM
Feature activation+0.000

INTERVAL 0.934 - 1.246
CONTAINS 0.025%

,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
is
Token is
Feature activation+0.000
clear
Token clear
Feature activation+0.000
in
Token in
Feature activation+0.000
saying
Token saying
Feature activation+1.218
that
Token that
Feature activation+0.016
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
's
Token's
Feature activation+0.000
Plays
Token Plays
Feature activation+0.000
et
Tokenet
Feature activation+0.000
Is
Token Is
Feature activation+0.000
in
Token in
Feature activation+0.000
Her
Token Her
Feature activation+0.976
Own
Token Own
Feature activation+0.498
Back
Token Back
Feature activation+0.224
yard
Tokenyard
Feature activation+0.128
,
Token,
Feature activation+0.221
City
Token City
Feature activation+0.000
who
Token who
Feature activation+0.000
the
Token the
Feature activation+0.000
responsible
Token responsible
Feature activation+0.000
adults
Token adults
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.224
family
Token family
Feature activation+0.061
are
Token are
Feature activation+0.000
because
Token because
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.001
session
Token session
Feature activation+0.375
for
Token for
Feature activation+0.000
BBC
Token BBC
Feature activation+0.006
Introdu
Token Introdu
Feature activation+0.038
cing
Tokencing
Feature activation+1.043
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
John
Token John
Feature activation+0.000
D
Token D
Feature activation+0.000
.
Token.
Feature activation+0.000
Rate
Token Rate
Feature activation+0.000
l
Tokenl
Feature activation+0.000
iff
Tokeniff
Feature activation+1.243
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.938
The
Token The
Feature activation+0.000
History
Token History
Feature activation+0.000

INTERVAL 0.623 - 0.934
CONTAINS 0.077%

"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
bold
Token bold
Feature activation+0.000
move
Token move
Feature activation+0.000
in
Token in
Feature activation+0.004
exploring
Token exploring
Feature activation+0.834
new
Token new
Feature activation+0.000
depths
Token depths
Feature activation+0.000
of
Token of
Feature activation+0.000
sheer
Token sheer
Feature activation+0.072
worth
Token worth
Feature activation+0.000
by
Token by
Feature activation+0.000
N
Token N
Feature activation+0.000
IA
TokenIA
Feature activation+0.000
and
Token and
Feature activation+0.000
Kerala
Token Kerala
Feature activation+0.000
police
Token police
Feature activation+0.776
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
is
Token is
Feature activation+0.000
asking
Token asking
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.822
good
Token good
Feature activation+0.599
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.304
own
Token own
Feature activation+1.534
words
Token words
Feature activation+0.637
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
reason
Token reason
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
Revolution
Token Revolution
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
Russell
Token Russell
Feature activation+0.555
's
Token's
Feature activation+0.669
parents
Token parents
Feature activation+0.671
'
Token'
Feature activation+0.675
basement
Token basement
Feature activation+0.134
when
Token when
Feature activation+0.000
Hear
Token Hear
Feature activation+0.000
n
Tokenn
Feature activation+0.000

INTERVAL 0.311 - 0.623
CONTAINS 0.238%

ura
Tokenura
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Nir
Token Nir
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
ta
Tokenta
Feature activation+0.481
[
Token [
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
mology
Tokenmology
Feature activation+0.000
treat
Token treat
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
er
Tokener
Feature activation+0.000
growing
Token growing
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
pure
Token pure
Feature activation+0.313
black
Token black
Feature activation+0.090
cat
Token cat
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.090
more
Token more
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
in
Token in
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.380
than
Token than
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.142
other
Token other
Feature activation+0.346
U
Token U
Feature activation+0.000
been
Token been
Feature activation+0.000
paid
Token paid
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.512
than
Token than
Feature activation+0.000
three
Token three
Feature activation+0.347
years
Token years
Feature activation+0.056
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
frozen
Token frozen
Feature activation+0.000
package
Token package
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.334
hand
Token hand
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.000 - 0.311
CONTAINS 99.647%

Car
TokenCar
Feature activation+0.000
category
Token category
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
original
Token original
Feature activation+0.000
goal
Token goal
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
warming
Token warming
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
sh
Token sh
Feature activation+0.000
akedown
Tokenakedown
Feature activation+0.000
of
Token of
Feature activation+0.000
historic
Token historic
Feature activation+0.000
proportions
Token proportions
Feature activation+0.000
.
Token.
Feature activation+0.000
Rather
Token Rather
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
lesbians
Token lesbians
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
priests
Token priests
Feature activation+0.000
and
Token and
Feature activation+0.000
nine
Token nine
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+0.000
electing
Token electing
Feature activation+0.000
refer
Token refer
Feature activation+0.000
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
inf
Token inf
Feature activation+0.000
lection
Tokenlection
Feature activation+0.000
point
Token point
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
authors
Token authors
Feature activation+0.000
'
Token'
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
some
Token some
Feature activation+0.000
today
Token today
Feature activation+0.000
would
Token would
Feature activation+0.000
call
Token call
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 1 in H6.11: (feature 14364)

TOP ACTIVATIONS
MAX = 2.615

âĢĶ
Token âĢĶ
Feature activation+0.000
not
Token not
Feature activation+0.000
mirror
Token mirror
Feature activation+0.573
images
Token images
Feature activation+1.140
,
Token,
Feature activation+0.911
as
Token as
Feature activation+2.615
a
Token a
Feature activation+0.912
display
Token display
Feature activation+0.000
that
Token that
Feature activation+0.000
emitted
Token emitted
Feature activation+0.000
light
Token light
Feature activation+0.009
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
it
Token it
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
name
Token name
Feature activation+2.013
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
screamed
Token screamed
Feature activation+0.000
and
Token and
Feature activation+0.000
resisted
Token resisted
Feature activation+0.000
States
Token States
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
neither
Token neither
Feature activation+0.000
Baghdad
Token Baghdad
Feature activation+1.952
nor
Token nor
Feature activation+0.000
Washington
Token Washington
Feature activation+0.670
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
as
Token as
Feature activation+1.618
many
Token many
Feature activation+0.000
b
Token b
Feature activation+0.000
erg
Tokenerg
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+1.903
San
Token San
Feature activation+0.000
Rafael
Token Rafael
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
run
Token run
Feature activation+0.292
over
Token over
Feature activation+1.779
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
year
Token year
Feature activation+0.000
)
Token)
Feature activation+0.014
or
Token or
Feature activation+0.127
cal
Token cal
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
as
Token as
Feature activation+1.618
many
Token many
Feature activation+0.000
b
Token b
Feature activation+0.000
erg
Tokenerg
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+1.903
ure
Tokenure
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.110
,
Token,
Feature activation+1.616
but
Token but
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
permanently
Token permanently
Feature activation+0.254
displayed
Token displayed
Feature activation+0.529
in
Token in
Feature activation+1.558
Latin
Token Latin
Feature activation+0.197
America
Token America
Feature activation+1.088
in
Token in
Feature activation+1.581
the
Token the
Feature activation+1.047
past
Token past
Feature activation+0.274
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
museum
Token museum
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.599
permanently
Token permanently
Feature activation+0.254
displayed
Token displayed
Feature activation+0.529
in
Token in
Feature activation+1.558
Latin
Token Latin
Feature activation+0.197
America
Token America
Feature activation+1.088
in
Token in
Feature activation+1.581
the
Token the
Feature activation+1.047
past
Token past
Feature activation+0.274
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.815
nationally
Token nationally
Feature activation+0.000
representative
Token representative
Feature activation+0.520
sample
Token sample
Feature activation+1.527
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
results
Token results
Feature activation+0.000
provide
Token provide
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
turned
Token turned
Feature activation+0.000
himself
Token himself
Feature activation+0.000
in
Token in
Feature activation+1.517
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
she
Token she
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
related
Token related
Feature activation+1.511
to
Token to
Feature activation+0.564
.
Token.
Feature activation+0.000
Is
Token Is
Feature activation+0.000
it
Token it
Feature activation+0.000
acceptable
Token acceptable
Feature activation+0.000
other
Token other
Feature activation+0.000
hand
Token hand
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
demolished
Token demolished
Feature activation+1.492
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
hundred
Token hundred
Feature activation+0.000
the
Token the
Feature activation+0.000
plastics
Token plastics
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
seen
Token seen
Feature activation+1.478
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
truly
Token truly
Feature activation+0.000
worrisome
Token worrisome
Feature activation+0.000
.
Token.
Feature activation+0.000
same
Token same
Feature activation+0.000
services
Token services
Feature activation+0.000
but
Token but
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
perform
Token perform
Feature activation+1.448
abortions
Token abortions
Feature activation+1.241
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
over
Token over
Feature activation+0.000
half
Token half
Feature activation+0.000
Markus
Token Markus
Feature activation+0.000
W
Token W
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
z
Tokenz
Feature activation+0.000
och
Tokenoch
Feature activation+0.000
,
Token,
Feature activation+1.407
industrial
Token industrial
Feature activation+0.000
design
Token design
Feature activation+0.000
director
Token director
Feature activation+0.000
at
Token at
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
with
Token with
Feature activation+0.000
potential
Token potential
Feature activation+0.000
pitfalls
Token pitfalls
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+1.388
least
Token least
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.312
story
Token story
Feature activation+1.369
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
fe
Token fe
Feature activation+0.000
int
Tokenint
Feature activation+0.000
of
Token of
Feature activation+0.000
guys
Token guys
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
teamed
Token teamed
Feature activation+1.156
a
Token a
Feature activation+1.361
lot
Token lot
Feature activation+0.757
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
prices
Token prices
Feature activation+0.000
in
Token in
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
risen
Token risen
Feature activation+1.350
in
Token in
Feature activation+1.140
past
Token past
Feature activation+0.109
decades
Token decades
Feature activation+0.708
,
Token,
Feature activation+0.193
as
Token as
Feature activation+0.850

Top DFA by src position
MAX = 3.311

viewers
Token viewers
Feature activation-0.004
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
both
Token both
Feature activation+0.003
Top resid features:
sides
Token sides
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.001
Top resid features:
not
Token not
Feature activation+3.311
Top resid features:
mirror
Token mirror
Feature activation-0.000
Top resid features:
images
Token images
Feature activation-0.018
Top resid features:
,
Token,
Feature activation-0.137
Top resid features:
as
Token as
Feature activation-0.055
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
victim
Token victim
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
whom
Token whom
Feature activation-0.033
Top resid features:
it
Token it
Feature activation-0.020
Top resid features:
did
Token did
Feature activation+0.042
Top resid features:
not
Token not
Feature activation+2.241
Top resid features:
name
Token name
Feature activation+0.291
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
screamed
Token screamed
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
United
Token United
Feature activation+0.007
Top resid features:
States
Token States
Feature activation-0.005
Top resid features:
wanted
Token wanted
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
when
Token when
Feature activation-0.015
Top resid features:
neither
Token neither
Feature activation+2.569
Top resid features:
Baghdad
Token Baghdad
Feature activation-0.053
Top resid features:
nor
Token nor
Feature activation+0.000
Top resid features:
Washington
Token Washington
Feature activation+0.000
Top resid features:
wanted
Token wanted
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
San
TokenSan
Feature activation+0.003
Top resid features:
Quint
Token Quint
Feature activation-0.000
Top resid features:
ÃŃn
TokenÃŃn
Feature activation+0.001
Top resid features:
does
Token does
Feature activation+0.053
Top resid features:
not
Token not
Feature activation+2.344
Top resid features:
flow
Token flow
Feature activation+0.019
Top resid features:
as
Token as
Feature activation+0.004
Top resid features:
fast
Token fast
Feature activation-0.013
Top resid features:
(
Token (
Feature activation+0.027
Top resid features:
1
Token1
Feature activation+0.007
Top resid features:
In
Token In
Feature activation-0.007
Top resid features:
fact
Token fact
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
he
Token he
Feature activation+0.016
Top resid features:
was
Token was
Feature activation+0.036
Top resid features:
not
Token not
Feature activation+2.222
Top resid features:
run
Token run
Feature activation-0.058
Top resid features:
over
Token over
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
San
TokenSan
Feature activation+0.006
Top resid features:
Quint
Token Quint
Feature activation-0.000
Top resid features:
ÃŃn
TokenÃŃn
Feature activation+0.002
Top resid features:
does
Token does
Feature activation+0.043
Top resid features:
not
Token not
Feature activation+2.162
Top resid features:
flow
Token flow
Feature activation+0.055
Top resid features:
as
Token as
Feature activation-0.013
Top resid features:
fast
Token fast
Feature activation-0.049
Top resid features:
(
Token (
Feature activation-0.007
Top resid features:
1
Token1
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
new
Token new
Feature activation+0.002
Top resid features:
discoveries
Token discoveries
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.039
Top resid features:
not
Token not
Feature activation+2.132
Top resid features:
âĢ
Token âĢ
Feature activation-0.030
Top resid features:
ĺ
Tokenĺ
Feature activation+0.011
Top resid features:
E
TokenE
Feature activation+0.003
Top resid features:
ure
Tokenure
Feature activation+0.021
Top resid features:
ka
Tokenka
Feature activation+0.036
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
European
Token European
Feature activation+0.010
Top resid features:
art
Token art
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.015
Top resid features:
have
Token have
Feature activation+0.047
Top resid features:
not
Token not
Feature activation+1.667
Top resid features:
been
Token been
Feature activation+0.148
Top resid features:
permanently
Token permanently
Feature activation-0.009
Top resid features:
displayed
Token displayed
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.020
Top resid features:
Latin
Token Latin
Feature activation+0.006
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
European
Token European
Feature activation+0.028
Top resid features:
art
Token art
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
have
Token have
Feature activation+0.025
Top resid features:
not
Token not
Feature activation+1.710
Top resid features:
been
Token been
Feature activation+0.163
Top resid features:
permanently
Token permanently
Feature activation-0.019
Top resid features:
displayed
Token displayed
Feature activation+0.034
Top resid features:
in
Token in
Feature activation+0.058
Top resid features:
Latin
Token Latin
Feature activation+0.000
Top resid features:
email
Token email
Feature activation+0.007
Top resid features:
list
Token list
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
which
Token which
Feature activation-0.016
Top resid features:
is
Token is
Feature activation+0.044
Top resid features:
not
Token not
Feature activation+1.611
Top resid features:
a
Token a
Feature activation+0.517
Top resid features:
nationally
Token nationally
Feature activation-0.031
Top resid features:
representative
Token representative
Feature activation-0.052
Top resid features:
sample
Token sample
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
Illinois
Token Illinois
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
has
Token has
Feature activation+0.023
Top resid features:
not
Token not
Feature activation+2.134
Top resid features:
turned
Token turned
Feature activation-0.118
Top resid features:
himself
Token himself
Feature activation+0.005
Top resid features:
in
Token in
Feature activation-0.021
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.021
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
man
Token man
Feature activation-0.003
Top resid features:
she
Token she
Feature activation+0.078
Top resid features:
wasn
Token wasn
Feature activation+0.221
Top resid features:
't
Token't
Feature activation+1.559
Top resid features:
related
Token related
Feature activation+0.084
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Is
Token Is
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
other
Token other
Feature activation+0.011
Top resid features:
hand
Token hand
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
were
Token were
Feature activation+0.033
Top resid features:
not
Token not
Feature activation+1.809
Top resid features:
demolished
Token demolished
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Only
Token Only
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
plastics
Token plastics
Feature activation+0.019
Top resid features:
that
Token that
Feature activation-0.042
Top resid features:
are
Token are
Feature activation+0.038
Top resid features:
not
Token not
Feature activation+1.923
Top resid features:
seen
Token seen
Feature activation+0.077
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
truly
Token truly
Feature activation+0.000
Top resid features:
worrisome
Token worrisome
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.072
Top resid features:
same
Token same
Feature activation-0.044
Top resid features:
services
Token services
Feature activation+0.017
Top resid features:
but
Token but
Feature activation+0.031
Top resid features:
do
Token do
Feature activation+0.109
Top resid features:
not
Token not
Feature activation+1.855
Top resid features:
perform
Token perform
Feature activation+0.123
Top resid features:
abortions
Token abortions
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Just
Token Just
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.042
Top resid features:
Not
Token Not
Feature activation+2.127
Top resid features:
Markus
Token Markus
Feature activation+0.021
Top resid features:
W
Token W
Feature activation-0.055
Top resid features:
ier
Tokenier
Feature activation-0.015
Top resid features:
z
Tokenz
Feature activation-0.002
Top resid features:
och
Tokenoch
Feature activation-0.034
Top resid features:
fraught
Token fraught
Feature activation-0.024
Top resid features:
with
Token with
Feature activation-0.007
Top resid features:
potential
Token potential
Feature activation-0.018
Top resid features:
pitfalls
Token pitfalls
Feature activation-0.047
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
not
Token not
Feature activation+1.948
Top resid features:
the
Token the
Feature activation+0.112
Top resid features:
least
Token least
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
trial
Token trial
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
This
Token This
Feature activation-0.016
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
not
Token not
Feature activation+1.889
Top resid features:
a
Token a
Feature activation+0.119
Top resid features:
story
Token story
Feature activation-0.019
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fe
Token fe
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
two
Token two
Feature activation+0.007
Top resid features:
guys
Token guys
Feature activation+0.016
Top resid features:
who
Token who
Feature activation+0.014
Top resid features:
have
Token have
Feature activation+0.050
Top resid features:
not
Token not
Feature activation+1.503
Top resid features:
teamed
Token teamed
Feature activation+0.258
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
housing
Token housing
Feature activation+0.004
Top resid features:
prices
Token prices
Feature activation+0.074
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
Japan
Token Japan
Feature activation+0.061
Top resid features:
have
Token have
Feature activation+0.067
Top resid features:
not
Token not
Feature activation+1.708
Top resid features:
risen
Token risen
Feature activation+0.037
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.000
Top resid features:
decades
Token decades
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.03

Head 2: 0.02

Head 3: 0.04

Head 4: 0.03

Head 5: 0.06

Head 6: 0.04

Head 7: 0.07

Head 8: 0.07

Head 9: 0.01

Head 10: 0.01

Head 11: 0.54

Positive logits

anymore4.48

nor4.48

yet3.13

necessarily2.98

anything2.96

yet2.88

any2.54

slightest2.49

nor2.32

necess2.30

whatsoever2.27

specifics2.22

anybody2.16

anywhere2.16

altogether2.12

anyone2.10

EVER2.09

unless2.08

:(2.07

Nor2.04

Negative logits

DragonMagazine-1.69

Travels-1.49

assorted-1.46

leted-1.39

raq-1.39

DRAGON-1.35

auri-1.35

ior-1.34

Minority-1.33

BET-1.33

Consider-1.32

anian-1.31

zi-1.30

WIND-1.30

IONS-1.30

TRANS-1.29

Slowly-1.29

FontSize-1.28

Congratulations-1.28

Networks-1.28

INTERVAL 2.354 - 2.615
CONTAINS 0.000%

âĢĶ
Token âĢĶ
Feature activation+0.000
not
Token not
Feature activation+0.000
mirror
Token mirror
Feature activation+0.573
images
Token images
Feature activation+1.140
,
Token,
Feature activation+0.911
as
Token as
Feature activation+2.615
a
Token a
Feature activation+0.912
display
Token display
Feature activation+0.000
that
Token that
Feature activation+0.000
emitted
Token emitted
Feature activation+0.000
light
Token light
Feature activation+0.009

INTERVAL 2.092 - 2.354
CONTAINS 0.000%

INTERVAL 1.831 - 2.092
CONTAINS 0.000%

States
Token States
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
neither
Token neither
Feature activation+0.000
Baghdad
Token Baghdad
Feature activation+1.952
nor
Token nor
Feature activation+0.000
Washington
Token Washington
Feature activation+0.670
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
it
Token it
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
name
Token name
Feature activation+2.013
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
screamed
Token screamed
Feature activation+0.000
and
Token and
Feature activation+0.000
resisted
Token resisted
Feature activation+0.000
as
Token as
Feature activation+1.618
many
Token many
Feature activation+0.000
b
Token b
Feature activation+0.000
erg
Tokenerg
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+1.903
San
Token San
Feature activation+0.000
Rafael
Token Rafael
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 1.569 - 1.831
CONTAINS 0.000%

ure
Tokenure
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.110
,
Token,
Feature activation+1.616
but
Token but
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
run
Token run
Feature activation+0.292
over
Token over
Feature activation+1.779
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
permanently
Token permanently
Feature activation+0.254
displayed
Token displayed
Feature activation+0.529
in
Token in
Feature activation+1.558
Latin
Token Latin
Feature activation+0.197
America
Token America
Feature activation+1.088
in
Token in
Feature activation+1.581
the
Token the
Feature activation+1.047
past
Token past
Feature activation+0.274
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
museum
Token museum
Feature activation+0.000
year
Token year
Feature activation+0.000
)
Token)
Feature activation+0.014
or
Token or
Feature activation+0.127
cal
Token cal
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
as
Token as
Feature activation+1.618
many
Token many
Feature activation+0.000
b
Token b
Feature activation+0.000
erg
Tokenerg
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+1.903

INTERVAL 1.308 - 1.569
CONTAINS 0.002%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
any
Token any
Feature activation+0.000
strength
Token strength
Feature activation+0.000
not
Token not
Feature activation+0.000
applied
Token applied
Feature activation+1.342
is
Token is
Feature activation+0.000
saved
Token saved
Feature activation+0.000
as
Token as
Feature activation+0.000
extra
Token extra
Feature activation+0.000
fat
Token fat
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.312
story
Token story
Feature activation+1.369
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
fe
Token fe
Feature activation+0.000
int
Tokenint
Feature activation+0.000
of
Token of
Feature activation+0.000
with
Token with
Feature activation+0.000
potential
Token potential
Feature activation+0.000
pitfalls
Token pitfalls
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+1.388
least
Token least
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.599
permanently
Token permanently
Feature activation+0.254
displayed
Token displayed
Feature activation+0.529
in
Token in
Feature activation+1.558
Latin
Token Latin
Feature activation+0.197
America
Token America
Feature activation+1.088
in
Token in
Feature activation+1.581
the
Token the
Feature activation+1.047
past
Token past
Feature activation+0.274
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
turned
Token turned
Feature activation+0.000
himself
Token himself
Feature activation+0.000
in
Token in
Feature activation+1.517
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 1.046 - 1.308
CONTAINS 0.008%

thankful
Token thankful
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
not
Tokennot
Feature activation+0.000
his
Token his
Feature activation+1.101
predecessor
Token predecessor
Feature activation+0.939
âĢĶ
TokenâĢĶ
Feature activation+0.000
is
Tokenis
Feature activation+0.000
in
Token in
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
not
Token not
Feature activation+0.000
affected
Token affected
Feature activation+0.035
Mac
Token Mac
Feature activation+0.000
sales
Token sales
Feature activation+1.067
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
via
Tokenvia
Feature activation+0.000
world
Token world
Feature activation+0.000
-
Token -
Feature activation+0.000
not
Token not
Feature activation+0.000
that
Token that
Feature activation+0.380
M
Token M
Feature activation+0.000
ondo
Tokenondo
Feature activation+1.207
can
Token can
Feature activation+0.646
hear
Token hear
Feature activation+0.000
anything
Token anything
Feature activation+0.109
the
Token the
Feature activation+0.287
old
Token old
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
powers
Token powers
Feature activation+0.000
not
Token not
Feature activation+0.000
delegated
Token delegated
Feature activation+1.071
to
Token to
Feature activation+0.963
the
Token the
Feature activation+0.647
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.485
by
Token by
Feature activation+0.503
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
might
Token might
Feature activation+0.000
not
Token not
Feature activation+0.037
have
Token have
Feature activation+0.494
been
Token been
Feature activation+1.092
the
Token the
Feature activation+1.134
best
Token best
Feature activation+0.162
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000

INTERVAL 0.785 - 1.046
CONTAINS 0.022%

Nation
Token Nation
Feature activation+0.000
)
Token)
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
take
Token take
Feature activation+0.070
place
Token place
Feature activation+0.998
or
Token or
Feature activation+0.000
took
Token took
Feature activation+0.000
place
Token place
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.199
spills
Token spills
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.007
cleaned
Token cleaned
Feature activation+1.146
up
Token up
Feature activation+0.794
.
Token.
Feature activation+0.000
Gar
Token Gar
Feature activation+0.000
bage
Tokenbage
Feature activation+0.000
cans
Token cans
Feature activation+0.000
that
Token that
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
led
Token led
Feature activation+0.136
by
Token by
Feature activation+0.960
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.,
Token.,
Feature activation+0.000
and
Token and
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
collect
Token collect
Feature activation+0.625
sales
Token sales
Feature activation+0.353
taxes
Token taxes
Feature activation+0.916
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
measure
Token measure
Feature activation+0.000
would
Token would
Feature activation+0.000
allow
Token allow
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
asked
Token asked
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.365
be
Token be
Feature activation+0.824
identified
Token identified
Feature activation+0.770
because
Token because
Feature activation+0.067
the
Token the
Feature activation+0.000
talks
Token talks
Feature activation+0.000
are
Token are
Feature activation+0.123

INTERVAL 0.523 - 0.785
CONTAINS 0.065%

regional
Token regional
Feature activation+0.063
government
Token government
Feature activation+1.186
nor
Token nor
Feature activation+0.000
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
government
Token government
Feature activation+0.590
in
Token in
Feature activation+0.000
Madrid
Token Madrid
Feature activation+0.655
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
willing
Token willing
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.190
accepted
Token accepted
Feature activation+0.424
for
Token for
Feature activation+0.195
re
Token re
Feature activation+0.000
entry
Tokenentry
Feature activation+0.524
into
Token into
Feature activation+0.000
another
Token another
Feature activation+0.000
country
Token country
Feature activation+0.630
after
Token after
Feature activation+0.099
six
Token six
Feature activation+0.000
Android
Token Android
Feature activation+0.201
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.096
Dungeon
Token Dungeon
Feature activation+0.000
,
Token,
Feature activation+0.607
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
industry
Token industry
Feature activation+0.000
adaptation
Token adaptation
Feature activation+0.040
of
Token of
Feature activation+0.000
Tolkien
Token Tolkien
Feature activation+0.000
's
Token's
Feature activation+0.000
text
Token text
Feature activation+0.000
,
Token,
Feature activation+0.743
or
Token or
Feature activation+0.337
even
Token even
Feature activation+0.000
one
Token one
Feature activation+0.000
that
Token that
Feature activation+0.000
rivals
Token rivals
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
Jordan
Token Jordan
Feature activation+0.321
Lynch
Token Lynch
Feature activation+0.738
or
Token or
Feature activation+0.935
Chandler
Token Chandler
Feature activation+0.000
H
Token H
Feature activation+0.000
arn
Tokenarn
Feature activation+0.000
ish
Tokenish
Feature activation+0.301

INTERVAL 0.262 - 0.523
CONTAINS 0.179%

doesn
Tokendoesn
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
any
Token any
Feature activation+0.293
sh
Token sh
Feature activation+0.000
adier
Tokenadier
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+0.000
?).
Token?).
Feature activation+0.000
egg
Token egg
Feature activation+0.000
begins
Token begins
Feature activation+0.000
to
Token to
Feature activation+0.000
divide
Token divide
Feature activation+0.000
without
Token without
Feature activation+0.000
being
Token being
Feature activation+0.369
fertil
Token fertil
Feature activation+0.051
ised
Tokenised
Feature activation+0.219
.
Token.
Feature activation+0.000
Common
Token Common
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.000
he
Token he
Feature activation+0.238
himself
Token himself
Feature activation+0.250
can
Token can
Feature activation+0.425
defend
Token defend
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
that
Token that
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
for
Token for
Feature activation+0.000
Mrs
Token Mrs
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
to
Token to
Feature activation+0.328
claim
Token claim
Feature activation+0.000
victory
Token victory
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
based
Token based
Feature activation+0.000
to
Token to
Feature activation+0.000
intimidate
Token intimidate
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
actually
Token actually
Feature activation+0.000
to
Token to
Feature activation+0.303
compliment
Token compliment
Feature activation+0.051
.*
Token.*
Feature activation+0.000
This
Token This
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.000 - 0.262
CONTAINS 99.723%

the
Token the
Feature activation+0.000
child
Token child
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
child
Token child
Feature activation+0.000
seat
Token seat
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
riding
Token riding
Feature activation+0.000
effort
Token effort
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
clear
Tokenclear
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
external
Token external
Feature activation+0.000
threats
Token threats
Feature activation+0.000
that
Token that
Feature activation+0.000
previously
Token previously
Feature activation+0.000
had
Token had
Feature activation+0.000
not
Token not
Feature activation+0.000
employed
Token employed
Feature activation+0.000
Aw
Token Aw
Feature activation+0.000
an
Tokenan
Feature activation+0.000
and
Token and
Feature activation+0.000
four
Token four
Feature activation+0.000
family
Token family
Feature activation+0.000
members
Token members
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.000
as
Token as
Feature activation+0.000
IT
Token IT
Feature activation+0.000
section
Token section
Feature activation+0.000
of
Token of
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
,
Token,
Feature activation+0.000
Pennsylvania
Token Pennsylvania
Feature activation+0.000
.
Token.
Feature activation+0.000
Central
Token Central
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
-
Token-
Feature activation+0.000
fa
Token fa
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
and
Token and
Feature activation+0.000
exterior
Token exterior
Feature activation+0.000
plaza
Token plaza
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000
above
Token above
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H6.11: (feature 1925)

TOP ACTIVATIONS
MAX = 5.455

aph
Tokenaph
Feature activation+0.000
ones
Tokenones
Feature activation+1.632
,
Token,
Feature activation+0.464
and
Token and
Feature activation+1.399
drums
Token drums
Feature activation+3.387
at
Token at
Feature activation+5.455
home
Token home
Feature activation+1.636
in
Token in
Feature activation+2.342
Kingston
Token Kingston
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
worse
Token worse
Feature activation+0.000
dodge
Token dodge
Feature activation+0.000
if
Token if
Feature activation+0.000
she
Token she
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+4.895
out
Token out
Feature activation+1.100
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
note
Token note
Feature activation+0.000
Koreans
Token Koreans
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
their
Token their
Feature activation+2.731
fate
Token fate
Feature activation+4.800
to
Token to
Feature activation+3.518
the
Token the
Feature activation+0.862
hated
Token hated
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
when
Token when
Feature activation+0.617
's
Token's
Feature activation+0.000
important
Token important
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+4.583
that
Token that
Feature activation+1.164
way
Token way
Feature activation+2.243
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
else
Token else
Feature activation+0.000
are
Token are
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
in
Token in
Feature activation+3.687
their
Token their
Feature activation+4.566
space
Token space
Feature activation+0.280
âĢĶ
Token âĢĶ
Feature activation+0.460
earnest
Token earnest
Feature activation+0.000
,
Token,
Feature activation+0.000
occasionally
Token occasionally
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
best
Token best
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+4.533
be
Token be
Feature activation+2.063
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
style
Token style
Feature activation+0.000
--
Token --
Feature activation+0.000
violated
Token violated
Feature activation+0.000
"
Token "
Feature activation+0.000
leave
Tokenleave
Feature activation+0.000
no
Token no
Feature activation+4.530
trace
Token trace
Feature activation+0.088
"
Token"
Feature activation+0.000
principles
Token principles
Feature activation+0.000
with
Token with
Feature activation+0.000
one
Token one
Feature activation+0.000
're
Token're
Feature activation+0.000
not
Token not
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
stuff
Token stuff
Feature activation+4.475
around
Token around
Feature activation+1.716
when
Token when
Feature activation+0.815
they
Token they
Feature activation+0.339
film
Token film
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.839
fl
Token fl
Feature activation+0.836
utes
Tokenutes
Feature activation+4.456
,
Token,
Feature activation+3.311
clar
Token clar
Feature activation+0.000
in
Tokenin
Feature activation+0.000
ets
Tokenets
Feature activation+2.277
,
Token,
Feature activation+2.815
entered
Token entered
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
than
Token than
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+4.428
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Who
TokenWho
Feature activation+0.000
is
Token is
Feature activation+0.000
nor
Token nor
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+4.276
there
Token there
Feature activation+2.913
,
Token,
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
broke
Token broke
Feature activation+0.000
down
Token down
Feature activation+0.000
week
Token week
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.018
him
Token him
Feature activation+4.275
with
Token with
Feature activation+2.753
my
Token my
Feature activation+1.009
in
Token in
Feature activation+0.000
-
Token-
Feature activation+0.000
laws
Tokenlaws
Feature activation+0.510
shake
Token shake
Feature activation+0.000
her
Token her
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.263
her
Token her
Feature activation+4.226
hearts
Token hearts
Feature activation+1.493
ick
Tokenick
Feature activation+1.871
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
were
Token were
Feature activation+0.000
still
Token still
Feature activation+0.000
together
Token together
Feature activation+0.000
and
Token and
Feature activation+0.000
leaving
Token leaving
Feature activation+0.559
her
Token her
Feature activation+4.179
in
Token in
Feature activation+2.676
relationship
Token relationship
Feature activation+0.545
limbo
Token limbo
Feature activation+0.005
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
issue
Token issue
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
leave
Token leave
Feature activation+0.000
residents
Token residents
Feature activation+4.165
"
Token "
Feature activation+4.167
in
Tokenin
Feature activation+3.676
the
Token the
Feature activation+3.677
l
Token l
Feature activation+0.095
urch
Tokenurch
Feature activation+0.439
".
Token".
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
leave
Token leave
Feature activation+0.000
residents
Token residents
Feature activation+4.165
"
Token "
Feature activation+4.167
in
Tokenin
Feature activation+3.676
the
Token the
Feature activation+3.677
l
Token l
Feature activation+0.095
urch
Tokenurch
Feature activation+0.439
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
leave
Token leave
Feature activation+0.242
it
Token it
Feature activation+4.083
at
Token at
Feature activation+4.103
that
Token that
Feature activation+2.139
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
yet
Token yet
Feature activation+0.000
that
Token that
Feature activation+0.000
outlines
Token outlines
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.000
them
Token them
Feature activation+4.097
on
Token on
Feature activation+2.499
for
Token for
Feature activation+1.572
about
Token about
Feature activation+0.052
five
Token five
Feature activation+0.000
minutes
Token minutes
Feature activation+0.129
then
Token then
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.208
sh
Token sh
Feature activation+0.080
aker
Tokenaker
Feature activation+3.770
in
Token in
Feature activation+4.097
the
Token the
Feature activation+3.005
freezer
Token freezer
Feature activation+0.623
to
Token to
Feature activation+0.229
chill
Token chill
Feature activation+0.000
while
Token while
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
leave
Token leave
Feature activation+0.242
it
Token it
Feature activation+4.083
at
Token at
Feature activation+4.103
that
Token that
Feature activation+2.139
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
yet
Token yet
Feature activation+0.000

Top DFA by src position
MAX = 6.073

's
Token's
Feature activation-0.000
Top resid features:
request
Token request
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
will
Token will
Feature activation-0.002
Top resid features:
leave
Token leave
Feature activation+6.073
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
fl
Token fl
Feature activation-0.001
Top resid features:
utes
Tokenutes
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
clar
Token clar
Feature activation+0.008
Top resid features:
even
Token even
Feature activation-0.005
Top resid features:
worse
Token worse
Feature activation+0.015
Top resid features:
dodge
Token dodge
Feature activation-0.018
Top resid features:
if
Token if
Feature activation+0.046
Top resid features:
she
Token she
Feature activation+0.033
Top resid features:
left
Token left
Feature activation+5.421
Top resid features:
it
Token it
Feature activation+0.177
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.004
Top resid features:
North
Token North
Feature activation-0.015
Top resid features:
Koreans
Token Koreans
Feature activation-0.038
Top resid features:
want
Token want
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
leave
Token leave
Feature activation+5.592
Top resid features:
their
Token their
Feature activation+0.044
Top resid features:
fate
Token fate
Feature activation+0.104
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
hated
Token hated
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.010
Top resid features:
's
Token's
Feature activation-0.002
Top resid features:
important
Token important
Feature activation-0.053
Top resid features:
that
Token that
Feature activation-0.026
Top resid features:
you
Token you
Feature activation-0.025
Top resid features:
leave
Token leave
Feature activation+5.489
Top resid features:
them
Token them
Feature activation+0.191
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
Burns
Token Burns
Feature activation-0.000
Top resid features:
projects
Token projects
Feature activation-0.003
Top resid features:
are
Token are
Feature activation+0.016
Top resid features:
easy
Token easy
Feature activation+0.096
Top resid features:
to
Token to
Feature activation-0.053
Top resid features:
leave
Token leave
Feature activation+5.228
Top resid features:
in
Token in
Feature activation+0.116
Top resid features:
their
Token their
Feature activation+0.112
Top resid features:
space
Token space
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
earnest
Token earnest
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
always
Token always
Feature activation+0.002
Top resid features:
best
Token best
Feature activation-0.029
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
leave
Token leave
Feature activation+5.321
Top resid features:
them
Token them
Feature activation+0.206
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
However
Token However
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
impact
Tokenimpact
Feature activation+0.005
Top resid features:
style
Token style
Feature activation+0.005
Top resid features:
--
Token --
Feature activation+0.008
Top resid features:
violated
Token violated
Feature activation+0.030
Top resid features:
"
Token "
Feature activation+0.050
Top resid features:
leave
Tokenleave
Feature activation+5.208
Top resid features:
no
Token no
Feature activation+0.067
Top resid features:
trace
Token trace
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
principles
Token principles
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
They
TokenThey
Feature activation+0.013
Top resid features:
're
Token're
Feature activation-0.001
Top resid features:
not
Token not
Feature activation-0.001
Top resid features:
supposed
Token supposed
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.021
Top resid features:
leave
Token leave
Feature activation+5.303
Top resid features:
stuff
Token stuff
Feature activation-0.008
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
film
Token film
Feature activation+0.000
Top resid features:
's
Token's
Feature activation-0.004
Top resid features:
request
Token request
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
they
Token they
Feature activation+0.013
Top resid features:
will
Token will
Feature activation+0.017
Top resid features:
leave
Token leave
Feature activation+5.131
Top resid features:
the
Token the
Feature activation+0.178
Top resid features:
fl
Token fl
Feature activation-0.134
Top resid features:
utes
Tokenutes
Feature activation+0.061
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
clar
Token clar
Feature activation+0.000
Top resid features:
people
Token people
Feature activation-0.043
Top resid features:
entered
Token entered
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
country
Token country
Feature activation+0.020
Top resid features:
than
Token than
Feature activation+0.076
Top resid features:
left
Token left
Feature activation+5.218
Top resid features:
it
Token it
Feature activation+0.112
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:
Who
TokenWho
Feature activation+0.000
Top resid features:
Baghdad
Token Baghdad
Feature activation-0.026
Top resid features:
nor
Token nor
Feature activation-0.058
Top resid features:
Washington
Token Washington
Feature activation-0.001
Top resid features:
wanted
Token wanted
Feature activation-0.129
Top resid features:
to
Token to
Feature activation-0.070
Top resid features:
leave
Token leave
Feature activation+5.449
Top resid features:
them
Token them
Feature activation+0.133
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
negotiations
Token negotiations
Feature activation+0.000
Top resid features:
broke
Token broke
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
week
Token week
Feature activation-0.010
Top resid features:
old
Token old
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
I
Token I
Feature activation+0.061
Top resid features:
left
Token left
Feature activation+4.887
Top resid features:
him
Token him
Feature activation+0.134
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.025
Top resid features:
shake
Token shake
Feature activation+0.078
Top resid features:
her
Token her
Feature activation+0.083
Top resid features:
off
Token off
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
leaving
Token leaving
Feature activation+4.619
Top resid features:
her
Token her
Feature activation+0.050
Top resid features:
hearts
Token hearts
Feature activation+0.000
Top resid features:
ick
Tokenick
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.014
Top resid features:
were
Token were
Feature activation-0.017
Top resid features:
still
Token still
Feature activation-0.012
Top resid features:
together
Token together
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
leaving
Token leaving
Feature activation+4.814
Top resid features:
her
Token her
Feature activation+0.136
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
relationship
Token relationship
Feature activation+0.000
Top resid features:
limbo
Token limbo
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
issue
Token issue
Feature activation+0.006
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
not
Token not
Feature activation+0.032
Top resid features:
leave
Token leave
Feature activation+4.972
Top resid features:
residents
Token residents
Feature activation-0.010
Top resid features:
"
Token "
Feature activation+0.145
Top resid features:
in
Tokenin
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
issue
Token issue
Feature activation+0.008
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
not
Token not
Feature activation+0.025
Top resid features:
leave
Token leave
Feature activation+4.951
Top resid features:
residents
Token residents
Feature activation+0.038
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
in
Tokenin
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
iated
Tokeniated
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
I
Token I
Feature activation+0.005
Top resid features:
'm
Token'm
Feature activation+0.020
Top resid features:
gonna
Token gonna
Feature activation-0.031
Top resid features:
leave
Token leave
Feature activation+4.825
Top resid features:
it
Token it
Feature activation+0.120
Top resid features:
at
Token at
Feature activation+0.117
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
And
Token And
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
outlines
Token outlines
Feature activation-0.033
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
I
Token I
Feature activation+0.008
Top resid features:
left
Token left
Feature activation+4.868
Top resid features:
them
Token them
Feature activation+0.142
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
aker
Tokenaker
Feature activation-0.025
Top resid features:
with
Token with
Feature activation-0.012
Top resid features:
ice
Token ice
Feature activation-0.031
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
then
Token then
Feature activation-0.005
Top resid features:
leave
Token leave
Feature activation+4.849
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
sh
Token sh
Feature activation+0.030
Top resid features:
aker
Tokenaker
Feature activation+0.108
Top resid features:
in
Token in
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
iated
Tokeniated
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
'm
Token'm
Feature activation+0.039
Top resid features:
gonna
Token gonna
Feature activation-0.059
Top resid features:
leave
Token leave
Feature activation+4.981
Top resid features:
it
Token it
Feature activation+0.053
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
And
Token And
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.02

Head 2: 0.02

Head 3: 0.03

Head 4: 0.04

Head 5: 0.08

Head 6: 0.04

Head 7: 0.05

Head 8: 0.07

Head 9: 0.01

Head 10: 0.02

Head 11: 0.52

Positive logits

untouched2.15

unfinished2.12

unanswered1.97

intact1.93

rubble1.87

unsatisf1.77

gaping1.74

undone1.68

unus1.67

orphan1.66

dangling1.66

unatt1.65

charred1.64

ashes1.61

unchanged1.57

residue1.56

neglected1.54

unsolved1.53

unresolved1.52

laure1.47

Negative logits

quickShipAvailable-1.91

Cosponsors-1.86

uesday-1.60

ERA-1.60

ACTIONS-1.58

NESS-1.51

haps-1.47

GW-1.44

tell-1.41

ADE-1.41

SEN-1.38

WARD-1.36

TD-1.36

rera-1.35

riet-1.35

TT-1.34

inances-1.32

dayName-1.32

Ages-1.31

CHAT-1.30

INTERVAL 4.909 - 5.455
CONTAINS 0.000%

aph
Tokenaph
Feature activation+0.000
ones
Tokenones
Feature activation+1.632
,
Token,
Feature activation+0.464
and
Token and
Feature activation+1.399
drums
Token drums
Feature activation+3.387
at
Token at
Feature activation+5.455
home
Token home
Feature activation+1.636
in
Token in
Feature activation+2.342
Kingston
Token Kingston
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000

INTERVAL 4.364 - 4.909
CONTAINS 0.001%

are
Token are
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
in
Token in
Feature activation+3.687
their
Token their
Feature activation+4.566
space
Token space
Feature activation+0.280
âĢĶ
Token âĢĶ
Feature activation+0.460
earnest
Token earnest
Feature activation+0.000
,
Token,
Feature activation+0.000
occasionally
Token occasionally
Feature activation+0.000
style
Token style
Feature activation+0.000
--
Token --
Feature activation+0.000
violated
Token violated
Feature activation+0.000
"
Token "
Feature activation+0.000
leave
Tokenleave
Feature activation+0.000
no
Token no
Feature activation+4.530
trace
Token trace
Feature activation+0.088
"
Token"
Feature activation+0.000
principles
Token principles
Feature activation+0.000
with
Token with
Feature activation+0.000
one
Token one
Feature activation+0.000
entered
Token entered
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
than
Token than
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+4.428
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Who
TokenWho
Feature activation+0.000
is
Token is
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.839
fl
Token fl
Feature activation+0.836
utes
Tokenutes
Feature activation+4.456
,
Token,
Feature activation+3.311
clar
Token clar
Feature activation+0.000
in
Tokenin
Feature activation+0.000
ets
Tokenets
Feature activation+2.277
,
Token,
Feature activation+2.815
Koreans
Token Koreans
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
their
Token their
Feature activation+2.731
fate
Token fate
Feature activation+4.800
to
Token to
Feature activation+3.518
the
Token the
Feature activation+0.862
hated
Token hated
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
when
Token when
Feature activation+0.617

INTERVAL 3.818 - 4.364
CONTAINS 0.002%

the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
leave
Token leave
Feature activation+0.000
residents
Token residents
Feature activation+4.165
"
Token "
Feature activation+4.167
in
Tokenin
Feature activation+3.676
the
Token the
Feature activation+3.677
l
Token l
Feature activation+0.095
urch
Tokenurch
Feature activation+0.439
outlines
Token outlines
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.000
them
Token them
Feature activation+4.097
on
Token on
Feature activation+2.499
for
Token for
Feature activation+1.572
about
Token about
Feature activation+0.052
five
Token five
Feature activation+0.000
minutes
Token minutes
Feature activation+0.129
were
Token were
Feature activation+0.000
still
Token still
Feature activation+0.000
together
Token together
Feature activation+0.000
and
Token and
Feature activation+0.000
leaving
Token leaving
Feature activation+0.559
her
Token her
Feature activation+4.179
in
Token in
Feature activation+2.676
relationship
Token relationship
Feature activation+0.545
limbo
Token limbo
Feature activation+0.005
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
leave
Token leave
Feature activation+0.242
it
Token it
Feature activation+4.083
at
Token at
Feature activation+4.103
that
Token that
Feature activation+2.139
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
yet
Token yet
Feature activation+0.000
that
Token that
Feature activation+0.000
mysterious
Token mysterious
Feature activation+1.018
element
Token element
Feature activation+0.461
of
Token of
Feature activation+0.482
Scottish
Token Scottish
Feature activation+0.000
ness
Tokenness
Feature activation+0.677
in
Token in
Feature activation+3.836
the
Token the
Feature activation+2.138
Canadian
Token Canadian
Feature activation+0.000
psyche
Token psyche
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 3.273 - 3.818
CONTAINS 0.002%

quality
Token quality
Feature activation+0.000
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
left
Token left
Feature activation+0.000
nothing
Token nothing
Feature activation+3.342
on
Token on
Feature activation+1.308
the
Token the
Feature activation+1.608
table
Token table
Feature activation+0.494
,
Token,
Feature activation+0.000
living
Token living
Feature activation+0.000
,
Token,
Feature activation+0.000
blood
Token blood
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+3.372
die
Token die
Feature activation+1.676
in
Token in
Feature activation+0.874
the
Token the
Feature activation+0.605
wilderness
Token wilderness
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
leave
Token leave
Feature activation+0.000
my
Token my
Feature activation+1.645
play
Token play
Feature activation+0.623
books
Tokenbooks
Feature activation+3.539
alone
Token alone
Feature activation+0.423
.
Token.
Feature activation+0.000
Everything
Token Everything
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.208
sh
Token sh
Feature activation+0.080
aker
Tokenaker
Feature activation+3.770
in
Token in
Feature activation+4.097
the
Token the
Feature activation+3.005
freezer
Token freezer
Feature activation+0.623
to
Token to
Feature activation+0.229
chill
Token chill
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
their
Token their
Feature activation+2.731
fate
Token fate
Feature activation+4.800
to
Token to
Feature activation+3.518
the
Token the
Feature activation+0.862
hated
Token hated
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
when
Token when
Feature activation+0.617
they
Token they
Feature activation+0.000

INTERVAL 2.727 - 3.273
CONTAINS 0.005%

leaving
Token leaving
Feature activation+0.000
or
Token or
Feature activation+0.000
charging
Token charging
Feature activation+0.000
a
Token a
Feature activation+0.447
battery
Token battery
Feature activation+2.418
in
Token in
Feature activation+2.760
a
Token a
Feature activation+0.348
hot
Token hot
Feature activation+0.000
environment
Token environment
Feature activation+0.000
can
Token can
Feature activation+0.000
cause
Token cause
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+4.276
there
Token there
Feature activation+2.913
,
Token,
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
broke
Token broke
Feature activation+0.000
down
Token down
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.469
system
Token system
Feature activation+1.611
that
Token that
Feature activation+0.339
much
Token much
Feature activation+2.798
weaker
Token weaker
Feature activation+2.311
in
Token in
Feature activation+0.845
the
Token the
Feature activation+1.611
process
Token process
Feature activation+1.299
.
Token.
Feature activation+0.000
es
Tokenes
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
UFO
Token UFO
Feature activation+0.000
left
Token left
Feature activation+0.000
burns
Token burns
Feature activation+3.000
on
Token on
Feature activation+1.483
the
Token the
Feature activation+0.152
side
Token side
Feature activation+0.407
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
ced
Tokenced
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
policymakers
Token policymakers
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
it
Token it
Feature activation+3.234
alone
Token alone
Feature activation+0.008
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000

INTERVAL 2.182 - 2.727
CONTAINS 0.006%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
boyfriend
Token boyfriend
Feature activation+0.000
or
Token or
Feature activation+0.000
girlfriend
Token girlfriend
Feature activation+0.000
left
Token left
Feature activation+0.000
you
Token you
Feature activation+2.529
,
Token,
Feature activation+0.217
and
Token and
Feature activation+0.061
now
Token now
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
leave
Token leave
Feature activation+0.000
his
Token his
Feature activation+1.173
mother
Token mother
Feature activation+2.453
's
Token's
Feature activation+2.354
eyes
Token eyes
Feature activation+2.165
as
Token as
Feature activation+0.872
she
Token she
Feature activation+0.000
saw
Token saw
Feature activation+0.000
her
Token her
Feature activation+0.000
MMA
Token MMA
Feature activation+0.000
and
Token and
Feature activation+0.000
football
Token football
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Token left
Feature activation+0.000
him
Token him
Feature activation+2.693
struggling
Token struggling
Feature activation+0.937
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
was
Token was
Feature activation+0.000
left
Token left
Feature activation+0.836
in
Token in
Feature activation+2.920
the
Token the
Feature activation+2.520
desert
Token desert
Feature activation+0.462
to
Token to
Feature activation+2.287
die
Token die
Feature activation+1.251
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
ed
Tokened
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
leave
Token leave
Feature activation+0.615
asphalt
Token asphalt
Feature activation+2.526
behind
Token behind
Feature activation+1.049
as
Token as
Feature activation+1.870
a
Token a
Feature activation+1.598
waste
Token waste
Feature activation+0.017
product
Token product
Feature activation+0.000

INTERVAL 1.636 - 2.182
CONTAINS 0.009%

allow
Token allow
Feature activation+0.000
W
Token W
Feature activation+0.000
ND
TokenND
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+1.654
message
Token message
Feature activation+0.219
for
Token for
Feature activation+0.000
Garfield
Token Garfield
Feature activation+0.000
County
Token County
Feature activation+0.000
Mag
Token Mag
Feature activation+0.000
her
Token her
Feature activation+0.000
as
Token as
Feature activation+0.000
she
Token she
Feature activation+0.000
is
Token is
Feature activation+0.000
left
Token left
Feature activation+0.344
with
Token with
Feature activation+2.046
a
Token a
Feature activation+1.413
broken
Token broken
Feature activation+0.229
heart
Token heart
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
me
Token me
Feature activation+1.849
so
Token so
Feature activation+0.895
sed
Token sed
Feature activation+0.380
ated
Tokenated
Feature activation+0.106
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
more
Token more
Feature activation+1.993
money
Token money
Feature activation+3.143
than
Token than
Feature activation+0.768
is
Token is
Feature activation+0.582
wise
Token wise
Feature activation+0.000
on
Token on
Feature activation+1.908
it
Token it
Feature activation+0.000
do
Token do
Feature activation+0.000
to
Token to
Feature activation+0.000
simply
Token simply
Feature activation+0.000
leave
Token leave
Feature activation+0.000
him
Token him
Feature activation+1.850
to
Token to
Feature activation+0.838
present
Token present
Feature activation+0.000
himself
Token himself
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.091 - 1.636
CONTAINS 0.012%

,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
many
Token many
Feature activation+1.342
economists
Token economists
Feature activation+1.867
scratching
Token scratching
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
.
Token.
Feature activation+0.000
St
Token St
Feature activation+0.000
John
Token John
Feature activation+0.000
stone
Tokenstone
Feature activation+0.000
were
Token were
Feature activation+0.000
left
Token left
Feature activation+0.000
chasing
Token chasing
Feature activation+1.455
shadows
Token shadows
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
that
Token that
Feature activation+0.339
much
Token much
Feature activation+2.798
weaker
Token weaker
Feature activation+2.311
in
Token in
Feature activation+0.845
the
Token the
Feature activation+1.611
process
Token process
Feature activation+1.299
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
top
Token top
Feature activation+0.000
prospect
Token prospect
Feature activation+0.000
on
Token on
Feature activation+0.000
I
Token I
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
leave
Token leave
Feature activation+0.000
his
Token his
Feature activation+1.173
mother
Token mother
Feature activation+2.453
's
Token's
Feature activation+2.354
eyes
Token eyes
Feature activation+2.165
as
Token as
Feature activation+0.872
she
Token she
Feature activation+0.000
horns
Token horns
Feature activation+1.207
,
Token,
Feature activation+1.779
s
Token s
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
aph
Tokenaph
Feature activation+0.000
ones
Tokenones
Feature activation+1.632
,
Token,
Feature activation+0.464
and
Token and
Feature activation+1.399
drums
Token drums
Feature activation+3.387
at
Token at
Feature activation+5.455
home
Token home
Feature activation+1.636

INTERVAL 0.545 - 1.091
CONTAINS 0.022%

iated
Tokeniated
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
everything
Token everything
Feature activation+2.004
horribly
Token horribly
Feature activation+2.094
mutated
Token mutated
Feature activation+0.659
and
Token and
Feature activation+0.656
hating
Token hating
Feature activation+0.000
your
Token your
Feature activation+0.000
guts
Token guts
Feature activation+0.000
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
more
Token more
Feature activation+1.993
money
Token money
Feature activation+3.143
than
Token than
Feature activation+0.768
is
Token is
Feature activation+0.582
wise
Token wise
Feature activation+0.000
on
Token on
Feature activation+1.908
the
Token the
Feature activation+0.104
table
Token table
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
still
Token still
Feature activation+0.000
together
Token together
Feature activation+0.000
and
Token and
Feature activation+0.000
leaving
Token leaving
Feature activation+0.559
her
Token her
Feature activation+4.179
in
Token in
Feature activation+2.676
relationship
Token relationship
Feature activation+0.545
limbo
Token limbo
Feature activation+0.005
.
Token.
Feature activation+0.000
him
Token him
Feature activation+0.000
snaps
Token snaps
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
the
Token the
Feature activation+1.054
Ravens
Token Ravens
Feature activation+0.882
down
Token down
Feature activation+0.646
to
Token to
Feature activation+0.000
raw
Token raw
Feature activation+0.000
rookie
Token rookie
Feature activation+0.000
Za
Token Za
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
was
Token was
Feature activation+0.000
left
Token left
Feature activation+0.836
in
Token in
Feature activation+2.920
the
Token the
Feature activation+2.520
desert
Token desert
Feature activation+0.462
to
Token to
Feature activation+2.287
die
Token die
Feature activation+1.251

INTERVAL 0.000 - 0.545
CONTAINS 99.940%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
transitional
Token transitional
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
met
Token met
Feature activation+0.000
to
Token to
Feature activation+0.000
upright
Token upright
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
Watch
Token Watch
Feature activation+0.000
charger
Token charger
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
premium
Token premium
Feature activation+0.000
accessory
Token accessory
Feature activation+0.000
professionalism
Token professionalism
Feature activation+0.000
have
Token have
Feature activation+0.000
corrupted
Token corrupted
Feature activation+0.000
our
Token our
Feature activation+0.000
political
Token political
Feature activation+0.000
culture
Token culture
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
back
Token back
Feature activation+0.000
down
Token down
Feature activation+0.000
hand
Token hand
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
m
Tokenm
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
mother
Token mother
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
terrible
Token terrible
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
dramatic
Token dramatic
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
raised
Token raised
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 H6.11: (feature 6191)

TOP ACTIVATIONS
MAX = 4.515

in
Token in
Feature activation+0.000
action
Token action
Feature activation+0.000
from
Token from
Feature activation+0.000
World
Token World
Feature activation+0.176
War
Token War
Feature activation+1.463
I
Token I
Feature activation+4.515
through
Token through
Feature activation+0.468
Iraq
Token Iraq
Feature activation+0.188
and
Token and
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
will
Token will
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
P
Token P
Feature activation+0.598
aks
Tokenaks
Feature activation+0.309
ong
Tokenong
Feature activation+3.327
back
Token back
Feature activation+1.504
to
Token to
Feature activation+0.000
Pak
Token Pak
Feature activation+0.000
se
Tokense
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
heart
Token heart
Feature activation+0.000
of
Token of
Feature activation+0.000
Palo
Token Palo
Feature activation+0.000
Alto
Token Alto
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+3.261
conception
Token conception
Feature activation+2.951
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
inspired
Token inspired
Feature activation+0.000
the
Token the
Feature activation+0.000
mil
Token mil
Feature activation+0.000
ieu
Tokenieu
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
Proud
Token Proud
Feature activation+1.810
hon
Tokenhon
Feature activation+3.220
to
Token to
Feature activation+0.000
Bak
Token Bak
Feature activation+0.000
unin
Tokenunin
Feature activation+0.377
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
increase
Token increase
Feature activation+0.000
from
Token from
Feature activation+0.000
$
Token $
Feature activation+2.455
187
Token187
Feature activation+2.322
,
Token,
Feature activation+0.107
000
Token000
Feature activation+3.200
to
Token to
Feature activation+0.528
$
Token $
Feature activation+0.000
210
Token210
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
,
Token,
Feature activation+0.000
disruption
Token disruption
Feature activation+0.000
in
Token in
Feature activation+0.000
supplies
Token supplies
Feature activation+0.000
from
Token from
Feature activation+0.000
war
Token war
Feature activation+3.133
,
Token,
Feature activation+0.123
or
Token or
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
weather
Token weather
Feature activation+0.000
changes
Token changes
Feature activation+0.000
October
Token October
Feature activation+0.000
from
Token from
Feature activation+0.000
16
Token 16
Feature activation+2.661
.
Token.
Feature activation+0.264
5
Token5
Feature activation+2.239
million
Token million
Feature activation+3.048
in
Token in
Feature activation+2.281
the
Token the
Feature activation+1.644
12
Token 12
Feature activation+0.124
months
Token months
Feature activation+0.082
to
Token to
Feature activation+0.312
Sharks
Token Sharks
Feature activation+0.000
,
Token,
Feature activation+0.280
from
Token from
Feature activation+0.000
Worcester
Token Worcester
Feature activation+0.781
,
Token,
Feature activation+0.417
Massachusetts
Token Massachusetts
Feature activation+3.033
to
Token to
Feature activation+1.141
San
Token San
Feature activation+0.000
Jose
Token Jose
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.418
history
Token history
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.540
second
Token second
Feature activation+0.762
world
Token world
Feature activation+0.000
war
Token war
Feature activation+3.022
"
Token "
Feature activation+0.201
l
Tokenl
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
itself
Token itself
Feature activation+0.000
towards
Token towards
Feature activation+0.000
:
Token:
Feature activation+0.339
30
Token30
Feature activation+0.834
a
Token a
Feature activation+0.107
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+1.100
.
Token.
Feature activation+2.969
to
Token to
Feature activation+1.105
4
Token 4
Feature activation+0.000
:
Token:
Feature activation+0.000
48
Token48
Feature activation+0.000
a
Token a
Feature activation+0.000
only
Token only
Feature activation+0.000
man
Token man
Feature activation+0.000
standing
Token standing
Feature activation+0.000
from
Token from
Feature activation+0.000
last
Token last
Feature activation+1.188
season
Token season
Feature activation+2.968
âĢ
TokenâĢ
Feature activation+0.402
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.979
audition
Token audition
Feature activation+0.941
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
o
Tokeno
Feature activation+1.991
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.173
s
Tokens
Feature activation+2.961
time
Token time
Feature activation+1.499
playing
Token playing
Feature activation+0.000
rugby
Token rugby
Feature activation+0.000
league
Token league
Feature activation+0.000
in
Token in
Feature activation+0.890
of
Token of
Feature activation+0.000
Palo
Token Palo
Feature activation+0.000
Alto
Token Alto
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+3.261
conception
Token conception
Feature activation+2.951
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
inspired
Token inspired
Feature activation+0.000
the
Token the
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
charge
Token charge
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+1.491
domestic
Token domestic
Feature activation+0.753
violence
Token violence
Feature activation+1.694
complaint
Token complaint
Feature activation+2.879
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.567
ex
Token ex
Feature activation+0.000
-
Token-
Feature activation+0.000
girlfriend
Tokengirlfriend
Feature activation+0.000
from
Token from
Feature activation+0.000
6
Token 6
Feature activation+0.602
a
Token a
Feature activation+1.076
.
Token.
Feature activation+0.020
m
Tokenm
Feature activation+0.948
.
Token.
Feature activation+2.870
to
Token to
Feature activation+0.108
10
Token 10
Feature activation+0.000
a
Token a
Feature activation+0.201
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
by
Token by
Feature activation+0.000
all
Token all
Feature activation+0.000
presidents
Token presidents
Feature activation+0.000
from
Token from
Feature activation+0.000
George
Token George
Feature activation+1.496
Washington
Token Washington
Feature activation+2.867
to
Token to
Feature activation+1.052
George
Token George
Feature activation+0.000
H
Token H
Feature activation+0.000
.
Token.
Feature activation+0.000
W
TokenW
Feature activation+0.000
across
Token across
Feature activation+0.000
six
Token six
Feature activation+0.000
other
Token other
Feature activation+0.000
countries
Token countries
Feature activation+0.000
from
Token from
Feature activation+0.000
Estonia
Token Estonia
Feature activation+2.865
to
Token to
Feature activation+2.195
Bulgaria
Token Bulgaria
Feature activation+0.125
beginning
Token beginning
Feature activation+0.000
in
Token in
Feature activation+0.000
February
Token February
Feature activation+0.000
res
Tokenres
Feature activation+0.000
and
Token and
Feature activation+0.000
corporations
Token corporations
Feature activation+0.000
from
Token from
Feature activation+0.000
telecom
Token telecom
Feature activation+2.093
s
Tokens
Feature activation+2.844
to
Token to
Feature activation+1.317
energy
Token energy
Feature activation+0.105
,
Token,
Feature activation+0.000
real
Token real
Feature activation+0.000
estate
Token estate
Feature activation+0.469
Di
Token Di
Feature activation+0.662
agram
Tokenagram
Feature activation+2.754
4
Token 4
Feature activation+1.925
,
Token,
Feature activation+1.722
we
Token we
Feature activation+2.577
can
Token can
Feature activation+2.779
see
Token see
Feature activation+0.759
that
Token that
Feature activation+0.000
at
Token at
Feature activation+0.000
large
Token large
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
Linux
Token Linux
Feature activation+0.000
project
Token project
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+2.769
start
Token start
Feature activation+0.693
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000

Top DFA by src position
MAX = 5.028

the
Token the
Feature activation+0.005
Top resid features:
military
Token military
Feature activation+0.009
Top resid features:
killed
Token killed
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
action
Token action
Feature activation+0.019
Top resid features:
from
Token from
Feature activation+5.028
Top resid features:
World
Token World
Feature activation+0.028
Top resid features:
War
Token War
Feature activation+0.053
Top resid features:
I
Token I
Feature activation+0.023
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
Iraq
Token Iraq
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
night
Token night
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
From
TokenFrom
Feature activation+3.917
Top resid features:
P
Token P
Feature activation+0.057
Top resid features:
aks
Tokenaks
Feature activation+0.036
Top resid features:
ong
Tokenong
Feature activation+0.015
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
heart
Token heart
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.035
Top resid features:
Palo
Token Palo
Feature activation+0.008
Top resid features:
Alto
Token Alto
Feature activation+0.025
Top resid features:
from
Token from
Feature activation+3.853
Top resid features:
its
Token its
Feature activation-0.020
Top resid features:
conception
Token conception
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
inspired
Token inspired
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
anarchist
Token anarchist
Feature activation+0.003
Top resid features:
mil
Token mil
Feature activation-0.001
Top resid features:
ieu
Tokenieu
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
from
Token from
Feature activation+3.864
Top resid features:
Proud
Token Proud
Feature activation+0.123
Top resid features:
hon
Tokenhon
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Bak
Token Bak
Feature activation+0.000
Top resid features:
unin
Tokenunin
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
saw
Token saw
Feature activation+0.017
Top resid features:
his
Token his
Feature activation+0.004
Top resid features:
salary
Token salary
Feature activation+0.000
Top resid features:
increase
Token increase
Feature activation-0.005
Top resid features:
from
Token from
Feature activation+3.960
Top resid features:
$
Token $
Feature activation+0.007
Top resid features:
187
Token187
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
000
Token000
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
disasters
Token disasters
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
disruption
Token disruption
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.040
Top resid features:
supplies
Token supplies
Feature activation+0.024
Top resid features:
from
Token from
Feature activation+3.756
Top resid features:
war
Token war
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
extreme
Token extreme
Feature activation+0.000
Top resid features:
weather
Token weather
Feature activation+0.000
Top resid features:
batch
Token batch
Feature activation-0.022
Top resid features:
became
Token became
Feature activation-0.029
Top resid features:
available
Token available
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
October
Token October
Feature activation+0.026
Top resid features:
from
Token from
Feature activation+3.869
Top resid features:
16
Token 16
Feature activation+0.101
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
5
Token5
Feature activation-0.010
Top resid features:
million
Token million
Feature activation-0.108
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Worcester
Token Worcester
Feature activation-0.004
Top resid features:
Sharks
Token Sharks
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
from
Token from
Feature activation+3.477
Top resid features:
Worcester
Token Worcester
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.096
Top resid features:
Massachusetts
Token Massachusetts
Feature activation+0.072
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
San
Token San
Feature activation+0.000
Top resid features:
He
TokenHe
Feature activation-0.002
Top resid features:
added
Token added
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
while
Token while
Feature activation-0.031
Top resid features:
history
Token history
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+3.579
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
second
Token second
Feature activation+0.033
Top resid features:
world
Token world
Feature activation+0.043
Top resid features:
war
Token war
Feature activation+0.037
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Sig
Token Sig
Feature activation-0.000
Top resid features:
Alert
TokenAlert
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
be
Token be
Feature activation+0.026
Top resid features:
issued
Token issued
Feature activation+0.077
Top resid features:
from
Token from
Feature activation+3.250
Top resid features:
3
Token 3
Feature activation+0.053
Top resid features:
:
Token:
Feature activation+0.022
Top resid features:
30
Token30
Feature activation+0.068
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
only
Token only
Feature activation-0.033
Top resid features:
man
Token man
Feature activation-0.025
Top resid features:
standing
Token standing
Feature activation+0.030
Top resid features:
from
Token from
Feature activation+3.434
Top resid features:
last
Token last
Feature activation+0.214
Top resid features:
season
Token season
Feature activation+0.031
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
well
Token well
Feature activation+0.030
Top resid features:
aware
Token aware
Feature activation-0.010
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
his
Token his
Feature activation+0.008
Top resid features:
attributes
Token attributes
Feature activation+0.045
Top resid features:
from
Token from
Feature activation+3.409
Top resid features:
Te
Token Te
Feature activation+0.029
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.020
Top resid features:
o
Tokeno
Feature activation+0.136
Top resid features:
âĢ
TokenâĢ
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
heart
Token heart
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
Palo
Token Palo
Feature activation+0.015
Top resid features:
Alto
Token Alto
Feature activation+0.033
Top resid features:
from
Token from
Feature activation+3.440
Top resid features:
its
Token its
Feature activation+0.080
Top resid features:
conception
Token conception
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
inspired
Token inspired
Feature activation+0.000
Top resid features:
jury
Token jury
Feature activation+0.015
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
misdemeanor
Token misdemeanor
Feature activation+0.015
Top resid features:
charge
Token charge
Feature activation+0.020
Top resid features:
from
Token from
Feature activation+3.327
Top resid features:
a
Token a
Feature activation+0.134
Top resid features:
domestic
Token domestic
Feature activation+0.025
Top resid features:
violence
Token violence
Feature activation+0.022
Top resid features:
complaint
Token complaint
Feature activation+0.047
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
effect
Token effect
Feature activation+0.053
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
Jan
Token Jan
Feature activation+0.029
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
22
Token 22
Feature activation+0.037
Top resid features:
from
Token from
Feature activation+3.245
Top resid features:
6
Token 6
Feature activation+0.097
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
m
Tokenm
Feature activation+0.044
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
debt
Token debt
Feature activation-0.002
Top resid features:
accrued
Token accrued
Feature activation+0.007
Top resid features:
by
Token by
Feature activation+0.062
Top resid features:
all
Token all
Feature activation+0.027
Top resid features:
presidents
Token presidents
Feature activation-0.008
Top resid features:
from
Token from
Feature activation+3.450
Top resid features:
George
Token George
Feature activation+0.083
Top resid features:
Washington
Token Washington
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
George
Token George
Feature activation+0.000
Top resid features:
H
Token H
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
across
Token across
Feature activation+0.010
Top resid features:
six
Token six
Feature activation+0.001
Top resid features:
other
Token other
Feature activation-0.010
Top resid features:
countries
Token countries
Feature activation-0.016
Top resid features:
from
Token from
Feature activation+3.574
Top resid features:
Estonia
Token Estonia
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Bulgaria
Token Bulgaria
Feature activation+0.000
Top resid features:
beginning
Token beginning
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
em
Token em
Feature activation+0.001
Top resid features:
ig
Tokenig
Feature activation-0.004
Top resid features:
res
Tokenres
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
corporations
Token corporations
Feature activation-0.015
Top resid features:
from
Token from
Feature activation+3.532
Top resid features:
telecom
Token telecom
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
energy
Token energy
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
one
Token one
Feature activation-0.004
Top resid features:
way
Token way
Feature activation+0.003
Top resid features:
or
Token or
Feature activation+0.003
Top resid features:
another
Token another
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
From
Token From
Feature activation+3.294
Top resid features:
Di
Token Di
Feature activation+0.010
Top resid features:
agram
Tokenagram
Feature activation+0.001
Top resid features:
4
Token 4
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
we
Token we
Feature activation+0.074
Top resid features:
Mob
Token Mob
Feature activation+0.007
Top resid features:
lin
Tokenlin
Feature activation+0.007
Top resid features:
mobile
Token mobile
Feature activation+0.005
Top resid features:
Linux
Token Linux
Feature activation+0.016
Top resid features:
project
Token project
Feature activation+0.030
Top resid features:
from
Token from
Feature activation+3.377
Top resid features:
its
Token its
Feature activation-0.000
Top resid features:
start
Token start
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.12

Head 1: 0.03

Head 2: 0.02

Head 3: 0.03

Head 4: 0.02

Head 5: 0.06

Head 6: 0.03

Head 7: 0.04

Head 8: 0.09

Head 9: 0.01

Head 10: 0.01

Head 11: 0.52

Positive logits

onwards3.31

onward2.78

standpoint2.73

vantage2.17

downwards1.84

perspective1.81

outset1.70

backgrounds1.61

confines1.55

beginnings1.53

sources1.53

mouths1.52

viewpoint1.52

perspectives1.50

shores1.47

sounding1.42

downward1.40

afar1.39

upwards1.37

inception1.37

Negative logits

Share-1.49

Adapt-1.45

eal-1.43

Thiel-1.42

challeng-1.42

Fail-1.38

ANK-1.37

trap-1.37

ask-1.36

brace-1.36

OVA-1.34

TB-1.33

ESE-1.33

reply-1.32

iqueness-1.31

owship-1.31

antidote-1.29

raid-1.28

try-1.27

TPP-1.27

INTERVAL 4.063 - 4.515
CONTAINS 0.000%

in
Token in
Feature activation+0.000
action
Token action
Feature activation+0.000
from
Token from
Feature activation+0.000
World
Token World
Feature activation+0.176
War
Token War
Feature activation+1.463
I
Token I
Feature activation+4.515
through
Token through
Feature activation+0.468
Iraq
Token Iraq
Feature activation+0.188
and
Token and
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 3.612 - 4.063
CONTAINS 0.000%

INTERVAL 3.160 - 3.612
CONTAINS 0.000%

mil
Token mil
Feature activation+0.000
ieu
Tokenieu
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
Proud
Token Proud
Feature activation+1.810
hon
Tokenhon
Feature activation+3.220
to
Token to
Feature activation+0.000
Bak
Token Bak
Feature activation+0.000
unin
Tokenunin
Feature activation+0.377
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
P
Token P
Feature activation+0.598
aks
Tokenaks
Feature activation+0.309
ong
Tokenong
Feature activation+3.327
back
Token back
Feature activation+1.504
to
Token to
Feature activation+0.000
Pak
Token Pak
Feature activation+0.000
se
Tokense
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
increase
Token increase
Feature activation+0.000
from
Token from
Feature activation+0.000
$
Token $
Feature activation+2.455
187
Token187
Feature activation+2.322
,
Token,
Feature activation+0.107
000
Token000
Feature activation+3.200
to
Token to
Feature activation+0.528
$
Token $
Feature activation+0.000
210
Token210
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
heart
Token heart
Feature activation+0.000
of
Token of
Feature activation+0.000
Palo
Token Palo
Feature activation+0.000
Alto
Token Alto
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+3.261
conception
Token conception
Feature activation+2.951
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
inspired
Token inspired
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.709 - 3.160
CONTAINS 0.002%

res
Tokenres
Feature activation+0.000
and
Token and
Feature activation+0.000
corporations
Token corporations
Feature activation+0.000
from
Token from
Feature activation+0.000
telecom
Token telecom
Feature activation+2.093
s
Tokens
Feature activation+2.844
to
Token to
Feature activation+1.317
energy
Token energy
Feature activation+0.105
,
Token,
Feature activation+0.000
real
Token real
Feature activation+0.000
estate
Token estate
Feature activation+0.469
of
Token of
Feature activation+0.000
Palo
Token Palo
Feature activation+0.000
Alto
Token Alto
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+3.261
conception
Token conception
Feature activation+2.951
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
inspired
Token inspired
Feature activation+0.000
the
Token the
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
only
Token only
Feature activation+0.000
man
Token man
Feature activation+0.000
standing
Token standing
Feature activation+0.000
from
Token from
Feature activation+0.000
last
Token last
Feature activation+1.188
season
Token season
Feature activation+2.968
âĢ
TokenâĢ
Feature activation+0.402
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.979
audition
Token audition
Feature activation+0.941
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
disruption
Token disruption
Feature activation+0.000
in
Token in
Feature activation+0.000
supplies
Token supplies
Feature activation+0.000
from
Token from
Feature activation+0.000
war
Token war
Feature activation+3.133
,
Token,
Feature activation+0.123
or
Token or
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
weather
Token weather
Feature activation+0.000
changes
Token changes
Feature activation+0.000
October
Token October
Feature activation+0.000
from
Token from
Feature activation+0.000
16
Token 16
Feature activation+2.661
.
Token.
Feature activation+0.264
5
Token5
Feature activation+2.239
million
Token million
Feature activation+3.048
in
Token in
Feature activation+2.281
the
Token the
Feature activation+1.644
12
Token 12
Feature activation+0.124
months
Token months
Feature activation+0.082
to
Token to
Feature activation+0.312

INTERVAL 2.257 - 2.709
CONTAINS 0.004%

from
Token from
Feature activation+0.000
16
Token 16
Feature activation+2.661
.
Token.
Feature activation+0.264
5
Token5
Feature activation+2.239
million
Token million
Feature activation+3.048
in
Token in
Feature activation+2.281
the
Token the
Feature activation+1.644
12
Token 12
Feature activation+0.124
months
Token months
Feature activation+0.082
to
Token to
Feature activation+0.312
October
Token October
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
the
Token the
Feature activation+0.000
bridge
Token bridge
Feature activation+0.000
from
Token from
Feature activation+0.690
stage
Token stage
Feature activation+2.492
3
Token 3
Feature activation+2.347
to
Token to
Feature activation+0.808
4
Token 4
Feature activation+0.000
to
Token to
Feature activation+0.000
fall
Token fall
Feature activation+0.000
into
Token into
Feature activation+0.000
from
Token from
Feature activation+0.000
trees
Token trees
Feature activation+0.711
and
Token and
Feature activation+0.937
birds
Token birds
Feature activation+1.679
all
Token all
Feature activation+2.718
the
Token the
Feature activation+2.625
way
Token way
Feature activation+1.878
to
Token to
Feature activation+0.059
the
Token the
Feature activation+0.000
ar
Token ar
Feature activation+0.000
throp
Tokenthrop
Feature activation+0.000
"
Token "
Feature activation+0.000
D
TokenD
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
ober
Tokenober
Feature activation+0.000
ta
Tokenta
Feature activation+0.068
"
Token"
Feature activation+2.279
to
Token to
Feature activation+1.053
the
Token the
Feature activation+0.000
sonic
Token sonic
Feature activation+0.000
assault
Token assault
Feature activation+0.000
and
Token and
Feature activation+0.000
G
Token G
Feature activation+0.000
NG
TokenNG
Feature activation+0.000
H
TokenH
Feature activation+0.000
ockey
Tokenockey
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+2.269
beginnings
Token beginnings
Feature activation+2.030
to
Token to
Feature activation+1.022
January
Token January
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.806 - 2.257
CONTAINS 0.012%

each
Token each
Feature activation+0.000
month
Token month
Feature activation+0.000
from
Token from
Feature activation+0.000
6
Token 6
Feature activation+1.695
:
Token:
Feature activation+0.775
00
Token00
Feature activation+1.952
-
Token -
Feature activation+0.062
7
Token 7
Feature activation+0.000
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
pm
Token pm
Feature activation+0.037
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.077
employ
Token employ
Feature activation+0.804
able
Tokenable
Feature activation+2.257
and
Token and
Feature activation+1.090
educated
Token educated
Feature activation+2.178
classes
Token classes
Feature activation+1.432
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
in
Token in
Feature activation+0.000
strong
Token strong
Feature activation+0.000
(
Token (
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
$
Token $
Feature activation+0.231
16
Token16
Feature activation+1.135
.
Token.
Feature activation+0.000
99
Token99
Feature activation+2.233
)
Token)
Feature activation+0.000
as
Token as
Feature activation+0.000
bland
Token bland
Feature activation+0.000
as
Token as
Feature activation+0.000
Buc
Token Buc
Feature activation+0.000
trees
Token trees
Feature activation+0.711
and
Token and
Feature activation+0.937
birds
Token birds
Feature activation+1.679
all
Token all
Feature activation+2.718
the
Token the
Feature activation+2.625
way
Token way
Feature activation+1.878
to
Token to
Feature activation+0.059
the
Token the
Feature activation+0.000
ar
Token ar
Feature activation+0.000
throp
Tokenthrop
Feature activation+0.000
od
Tokenod
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
worked
Token worked
Feature activation+0.000
from
Token from
Feature activation+0.000
internal
Token internal
Feature activation+0.928
prototypes
Token prototypes
Feature activation+1.898
âĢĵ
Token âĢĵ
Feature activation+0.049
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.417
authentic
Token authentic
Feature activation+0.000
experience
Token experience
Feature activation+0.000

INTERVAL 1.354 - 1.806
CONTAINS 0.023%

guild
Token guild
Feature activation+0.000
hall
Token hall
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.599
f
Token f
Feature activation+0.000
oyer
Tokenoyer
Feature activation+1.366
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
vice
Token vice
Feature activation+0.000
versa
Token versa
Feature activation+0.000
).
Token).
Feature activation+0.000
following
Token following
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
grown
Token grown
Feature activation+0.000
from
Token from
Feature activation+0.000
humble
Token humble
Feature activation+1.774
beginnings
Token beginnings
Feature activation+2.054
to
Token to
Feature activation+0.054
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Schumer
Token Schumer
Feature activation+0.000
said
Token said
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+1.242
Senate
Token Senate
Feature activation+1.397
floor
Token floor
Feature activation+1.082
Thursday
Token Thursday
Feature activation+0.268
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Penn
Token Penn
Feature activation+0.000
East
TokenEast
Feature activation+0.000
pipeline
Token pipeline
Feature activation+0.000
project
Token project
Feature activation+0.000
from
Token from
Feature activation+1.579
Pennsylvania
Token Pennsylvania
Feature activation+1.653
to
Token to
Feature activation+1.363
Hop
Token Hop
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
ell
Tokenell
Feature activation+0.701
remains
Token remains
Feature activation+0.000
killed
Token killed
Feature activation+0.000
in
Token in
Feature activation+0.000
action
Token action
Feature activation+0.000
from
Token from
Feature activation+0.000
World
Token World
Feature activation+0.176
War
Token War
Feature activation+1.463
I
Token I
Feature activation+4.515
through
Token through
Feature activation+0.468
Iraq
Token Iraq
Feature activation+0.188
and
Token and
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000

INTERVAL 0.903 - 1.354
CONTAINS 0.052%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
town
Token town
Feature activation+0.035
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.042
willing
Token willing
Feature activation+0.000
prostitutes
Token prostitutes
Feature activation+0.000
or
Token or
Feature activation+0.000
Th
Token Th
Feature activation+0.000
and
Tokenand
Feature activation+0.000
neat
Token neat
Feature activation+0.000
finish
Token finish
Feature activation+0.000
from
Token from
Feature activation+0.069
the
Token the
Feature activation+0.716
edge
Token edge
Feature activation+1.211
of
Token of
Feature activation+0.974
the
Token the
Feature activation+0.604
box
Token box
Feature activation+0.331
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
stage
Token stage
Feature activation+0.000
only
Token only
Feature activation+0.000
item
Token item
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+1.098
forest
Token forest
Feature activation+0.579
ing
Tokening
Feature activation+1.347
-
Token-
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ic
Tokenic
Feature activation+0.278
film
Token film
Feature activation+0.163
that
Token that
Feature activation+0.551
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.023
Late
Token Late
Feature activation+0.000
C
Token C
Feature activation+0.000
ret
Tokenret
Feature activation+0.000
aceous
Tokenaceous
Feature activation+1.159
Period
Token Period
Feature activation+1.358
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.554
marine
Token marine
Feature activation+0.000
depleted
Token depleted
Feature activation+0.000
uranium
Token uranium
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.266
first
Token first
Feature activation+1.028
stage
Token stage
Feature activation+1.138
as
Token as
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
sufficient
Token sufficient
Feature activation+0.000

INTERVAL 0.451 - 0.903
CONTAINS 0.116%

some
Token some
Feature activation+0.000
advice
Token advice
Feature activation+0.000
(
Token (
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
my
Token my
Feature activation+0.912
point
Token point
Feature activation+0.728
of
Token of
Feature activation+0.000
view
Token view
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
fans
Token fans
Feature activation+0.000
and
Token and
Feature activation+0.000
open
Token open
Feature activation+0.000
from
Token from
Feature activation+0.000
8
Token 8
Feature activation+0.495
a
Token a
Feature activation+0.794
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.528
.
Token.
Feature activation+2.050
until
Token until
Feature activation+0.000
entire
Token entire
Feature activation+0.000
primary
Token primary
Feature activation+0.000
process
Token process
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.466
super
Token super
Feature activation+0.234
delegates
Token delegates
Feature activation+1.031
to
Token to
Feature activation+0.000
front
Token front
Feature activation+0.000
-
Token-
Feature activation+0.000
barrels
Token barrels
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.470
week
Token week
Feature activation+0.423
ended
Token ended
Feature activation+0.350
May
Token May
Feature activation+0.850
2
Token 2
Feature activation+1.002
.
Token.
Feature activation+0.000
Analy
Token Analy
Feature activation+0.000
sts
Tokensts
Feature activation+0.000
forecast
Token forecast
Feature activation+0.000
3
Token3
Feature activation+0.000
[
Token [
Feature activation+0.000
exp
Tokenexp
Feature activation+0.000
anded
Tokenanded
Feature activation+0.000
from
Token from
Feature activation+0.000
:
Token:
Feature activation+0.539
GPL
Token GPL
Feature activation+0.000
(
Token (
Feature activation+0.000
âī
Tokenâī
Feature activation+0.000
¥
Token¥
Feature activation+0.000
2
Token 2
Feature activation+0.000

INTERVAL 0.000 - 0.451
CONTAINS 99.791%

in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
seven
Token seven
Feature activation+0.000
years
Token years
Feature activation+0.000
behind
Token behind
Feature activation+0.000
this
Token this
Feature activation+0.000
belief
Token belief
Feature activation+0.000
is
Token is
Feature activation+0.000
two
Token two
Feature activation+0.000
fold
Tokenfold
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
independence
Token independence
Feature activation+0.000
from
Token from
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
colonial
Token colonial
Feature activation+0.000
rule
Token rule
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
swim
Token swim
Feature activation+0.000
follows
Token follows
Feature activation+0.000
a
Token a
Feature activation+0.000
visit
Token visit
Feature activation+0.000
V
Token V
Feature activation+0.000
ulet
Tokenulet
Feature activation+0.000
in
Tokenin
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
).
Token).
Feature activation+0.000
We
Token We
Feature activation+0.000
find
Token find
Feature activation+0.000
that
Token that
Feature activation+0.000
contraction
Token contraction
Feature activation+0.000
ary
Tokenary
Feature activation+0.000
fiscal
Token fiscal
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
devised
Token devised
Feature activation+0.000
a
Token a
Feature activation+0.000
system
Token system
Feature activation+0.000
that
Token that
Feature activation+0.000
weeds
Token weeds
Feature activation+0.000
out
Token out
Feature activation+0.000
sound
Token sound
Feature activation+0.000
clutter
Token clutter
Feature activation+0.000
from
Token from
Feature activation+0.000
underwater
Token underwater
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 H6.11: (feature 23750)

TOP ACTIVATIONS
MAX = 5.959

Soldier
Token Soldier
Feature activation+0.000
Field
Token Field
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
so
Token so
Feature activation+0.694
staggering
Token staggering
Feature activation+5.959
that
Token that
Feature activation+0.444
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
the
Token the
Feature activation+0.000
got
Token got
Feature activation+0.444
cut
Token cut
Feature activation+1.505
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.262
,
Token,
Feature activation+5.684
I
Token I
Feature activation+2.583
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.509
World
Token World
Feature activation+0.000
Report
Token Report
Feature activation+0.000
rankings
Token rankings
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.157
influential
Token influential
Feature activation+5.623
tha
Token tha
Feature activation+0.512
they
Token they
Feature activation+0.147
have
Token have
Feature activation+1.510
become
Token become
Feature activation+1.169
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
so
Token so
Feature activation+0.363
bad
Token bad
Feature activation+3.846
,
Token,
Feature activation+5.559
or
Token or
Feature activation+1.044
so
Token so
Feature activation+0.525
over
Token over
Feature activation+0.365
priced
Tokenpriced
Feature activation+2.249
that
Token that
Feature activation+2.932
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
segment
Token segment
Feature activation+0.000
became
Token became
Feature activation+0.000
so
Token so
Feature activation+0.000
popular
Token popular
Feature activation+5.514
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.024
spun
Token spun
Feature activation+0.000
off
Token off
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
laws
Token laws
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.912
outrageous
Token outrageous
Feature activation+5.506
that
Token that
Feature activation+1.058
you
Token you
Feature activation+0.243
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
heat
Token heat
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.423
great
Token great
Feature activation+5.279
that
Token that
Feature activation+0.000
neither
Token neither
Feature activation+0.084
man
Token man
Feature activation+0.000
nor
Token nor
Feature activation+0.000
beast
Token beast
Feature activation+0.000
ensuing
Token ensuing
Feature activation+0.000
system
Token system
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.519
confusing
Token confusing
Feature activation+4.619
,
Token,
Feature activation+5.098
the
Token the
Feature activation+2.977
paperwork
Token paperwork
Feature activation+0.543
so
Token so
Feature activation+0.000
ardu
Token ardu
Feature activation+0.000
ous
Tokenous
Feature activation+1.296
in
Token in
Feature activation+0.000
federal
Token federal
Feature activation+0.000
law
Token law
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+1.959
broad
Token broad
Feature activation+4.995
that
Token that
Feature activation+0.396
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
viewed
Token viewed
Feature activation+0.000
literally
Token literally
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bal
TokenBal
Feature activation+0.000
rog
Tokenrog
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.254
distraught
Token distraught
Feature activation+4.987
that
Token that
Feature activation+0.581
they
Token they
Feature activation+0.050
quit
Token quit
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+2.515
ur
Tokenur
Feature activation+0.000
ously
Tokenously
Feature activation+3.786
,
Token,
Feature activation+4.891
you
Token you
Feature activation+2.808
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.333
think
Token think
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
Games
Token Games
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.254
polluted
Token polluted
Feature activation+4.802
thanks
Token thanks
Feature activation+0.468
to
Token to
Feature activation+0.174
lax
Token lax
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
Park
Token Park
Feature activation+0.000
are
Token are
Feature activation+0.000
melting
Token melting
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.781
,
Token,
Feature activation+3.228
they
Token they
Feature activation+1.208
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.000
flu
Token flu
Feature activation+0.000
spread
Token spread
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.777
last
Token last
Feature activation+0.840
year
Token year
Feature activation+0.414
that
Token that
Feature activation+0.032
some
Token some
Feature activation+0.009
shelters
Token shelters
Feature activation+0.000
so
Token so
Feature activation+1.125
âĢ
Token âĢ
Feature activation+1.036
ľ
Tokenľ
Feature activation+3.235
cre
Tokencre
Feature activation+0.000
ep
Tokenep
Feature activation+1.686
y
Tokeny
Feature activation+4.763
,
Token,
Feature activation+2.743
rude
Token rude
Feature activation+0.992
,
Token,
Feature activation+0.903
and
Token and
Feature activation+0.039
obnoxious
Token obnoxious
Feature activation+2.920
other
Token other
Feature activation+0.000
factory
Token factory
Feature activation+0.000
waste
Token waste
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.179
toxic
Token toxic
Feature activation+4.637
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ago
Tokenago
Feature activation+0.000
costs
Token costs
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.750
on
Token on
Feature activation+0.000
erous
Tokenerous
Feature activation+4.625
that
Token that
Feature activation+0.491
the
Token the
Feature activation+0.000
Affordable
Token Affordable
Feature activation+0.000
Care
Token Care
Feature activation+0.000
Act
Token Act
Feature activation+0.294
The
Token The
Feature activation+0.000
TV
Token TV
Feature activation+0.000
income
Token income
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.222
high
Token high
Feature activation+4.620
it
Token it
Feature activation+1.160
is
Token is
Feature activation+0.877
seen
Token seen
Feature activation+0.119
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.629
the
Token the
Feature activation+0.000
ensuing
Token ensuing
Feature activation+0.000
system
Token system
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.519
confusing
Token confusing
Feature activation+4.619
,
Token,
Feature activation+5.098
the
Token the
Feature activation+2.977
paperwork
Token paperwork
Feature activation+0.543
so
Token so
Feature activation+0.000
ardu
Token ardu
Feature activation+0.000
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
well
Token well
Feature activation+2.385
animated
Token animated
Feature activation+2.795
,
Token,
Feature activation+4.566
I
Token I
Feature activation+3.350
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+2.922
going
Token going
Feature activation+0.000

Top DFA by src position
MAX = 6.581

's
Token's
Feature activation-0.005
Top resid features:
Soldier
Token Soldier
Feature activation-0.011
Top resid features:
Field
Token Field
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.058
Top resid features:
been
Token been
Feature activation+0.051
Top resid features:
so
Token so
Feature activation+6.581
Top resid features:
staggering
Token staggering
Feature activation+0.119
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.006
Top resid features:
cut
Token cut
Feature activation-0.001
Top resid features:
?
Token?
Feature activation+0.047
Top resid features:
There
Token There
Feature activation-0.001
Top resid features:
were
Token were
Feature activation+0.011
Top resid features:
so
Token so
Feature activation+6.409
Top resid features:
many
Token many
Feature activation-0.117
Top resid features:
scenes
Token scenes
Feature activation+0.074
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
got
Token got
Feature activation-0.020
Top resid features:
cut
Token cut
Feature activation+0.023
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
World
Token World
Feature activation+0.003
Top resid features:
Report
Token Report
Feature activation+0.031
Top resid features:
rankings
Token rankings
Feature activation+0.080
Top resid features:
are
Token are
Feature activation+0.115
Top resid features:
so
Token so
Feature activation+6.176
Top resid features:
influential
Token influential
Feature activation+0.081
Top resid features:
tha
Token tha
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
product
Token product
Feature activation+0.073
Top resid features:
that
Token that
Feature activation+0.142
Top resid features:
is
Token is
Feature activation+0.118
Top resid features:
just
Token just
Feature activation+0.096
Top resid features:
so
Token so
Feature activation+5.701
Top resid features:
bad
Token bad
Feature activation+0.338
Top resid features:
,
Token,
Feature activation+0.115
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
1994
Token 1994
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
segment
Token segment
Feature activation+0.228
Top resid features:
became
Token became
Feature activation-0.009
Top resid features:
so
Token so
Feature activation+6.369
Top resid features:
popular
Token popular
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
spun
Token spun
Feature activation+0.000
Top resid features:
Some
Token Some
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
these
Token these
Feature activation-0.015
Top resid features:
laws
Token laws
Feature activation+0.094
Top resid features:
are
Token are
Feature activation+0.051
Top resid features:
so
Token so
Feature activation+6.191
Top resid features:
outrageous
Token outrageous
Feature activation+0.105
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
but
Token but
Feature activation+0.052
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
heat
Token heat
Feature activation+0.073
Top resid features:
was
Token was
Feature activation+0.117
Top resid features:
so
Token so
Feature activation+5.796
Top resid features:
great
Token great
Feature activation+0.085
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
neither
Token neither
Feature activation+0.000
Top resid features:
man
Token man
Feature activation+0.000
Top resid features:
nor
Token nor
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation-0.023
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
ensuing
Token ensuing
Feature activation-0.083
Top resid features:
system
Token system
Feature activation+0.045
Top resid features:
was
Token was
Feature activation+0.051
Top resid features:
so
Token so
Feature activation+6.069
Top resid features:
confusing
Token confusing
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
paperwork
Token paperwork
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
services
Token services
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
federal
Token federal
Feature activation-0.005
Top resid features:
law
Token law
Feature activation+0.020
Top resid features:
was
Token was
Feature activation+0.077
Top resid features:
so
Token so
Feature activation+5.769
Top resid features:
broad
Token broad
Feature activation+0.078
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
viewed
Token viewed
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Bal
TokenBal
Feature activation+0.005
Top resid features:
rog
Tokenrog
Feature activation-0.033
Top resid features:
was
Token was
Feature activation-0.049
Top resid features:
so
Token so
Feature activation+5.903
Top resid features:
distraught
Token distraught
Feature activation+0.138
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
quit
Token quit
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Doctor
Token Doctor
Feature activation+0.035
Top resid features:
Who
Token Who
Feature activation+0.035
Top resid features:
âĦ¢
TokenâĦ¢
Feature activation+0.047
Top resid features:
was
Token was
Feature activation+0.063
Top resid features:
greeted
Token greeted
Feature activation+0.131
Top resid features:
so
Token so
Feature activation+5.542
Top resid features:
rapt
Token rapt
Feature activation+0.048
Top resid features:
ur
Tokenur
Feature activation-0.000
Top resid features:
ously
Tokenously
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.077
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
upcoming
Token upcoming
Feature activation-0.008
Top resid features:
Games
Token Games
Feature activation+0.004
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.030
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
so
Token so
Feature activation+5.574
Top resid features:
polluted
Token polluted
Feature activation+0.146
Top resid features:
thanks
Token thanks
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
lax
Token lax
Feature activation+0.000
Top resid features:
enforcement
Token enforcement
Feature activation+0.000
Top resid features:
Glacier
Token Glacier
Feature activation-0.002
Top resid features:
National
Token National
Feature activation-0.001
Top resid features:
Park
Token Park
Feature activation-0.015
Top resid features:
are
Token are
Feature activation+0.087
Top resid features:
melting
Token melting
Feature activation+0.019
Top resid features:
so
Token so
Feature activation+5.607
Top resid features:
quickly
Token quickly
Feature activation+0.071
Top resid features:
,
Token,
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:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
dog
Token dog
Feature activation+0.047
Top resid features:
flu
Token flu
Feature activation+0.095
Top resid features:
spread
Token spread
Feature activation+0.150
Top resid features:
so
Token so
Feature activation+5.392
Top resid features:
quickly
Token quickly
Feature activation+0.045
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
can
Tokencan
Feature activation-0.000
Top resid features:
C
Token C
Feature activation+0.004
Top resid features:
et
Tokenet
Feature activation-0.005
Top resid features:
in
Tokenin
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.020
Top resid features:
so
Token so
Feature activation+5.610
Top resid features:
âĢ
Token âĢ
Feature activation-0.037
Top resid features:
ľ
Tokenľ
Feature activation+0.007
Top resid features:
cre
Tokencre
Feature activation+0.077
Top resid features:
ep
Tokenep
Feature activation+0.096
Top resid features:
y
Tokeny
Feature activation+0.094
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
other
Token other
Feature activation-0.004
Top resid features:
factory
Token factory
Feature activation-0.066
Top resid features:
waste
Token waste
Feature activation-0.013
Top resid features:
are
Token are
Feature activation+0.079
Top resid features:
so
Token so
Feature activation+5.405
Top resid features:
toxic
Token toxic
Feature activation+0.149
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
l
Tokenl
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.016
Top resid features:
related
Tokenrelated
Feature activation+0.002
Top resid features:
costs
Token costs
Feature activation+0.035
Top resid features:
have
Token have
Feature activation+0.063
Top resid features:
become
Token become
Feature activation+0.089
Top resid features:
so
Token so
Feature activation+5.363
Top resid features:
on
Token on
Feature activation+0.031
Top resid features:
erous
Tokenerous
Feature activation+0.121
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Affordable
Token Affordable
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
The
Token The
Feature activation+0.034
Top resid features:
TV
Token TV
Feature activation-0.006
Top resid features:
income
Token income
Feature activation+0.033
Top resid features:
is
Token is
Feature activation+0.048
Top resid features:
so
Token so
Feature activation+5.285
Top resid features:
high
Token high
Feature activation+0.087
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
ensuing
Token ensuing
Feature activation-0.089
Top resid features:
system
Token system
Feature activation+0.082
Top resid features:
was
Token was
Feature activation+0.040
Top resid features:
so
Token so
Feature activation+5.451
Top resid features:
confusing
Token confusing
Feature activation+0.086
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
paperwork
Token paperwork
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
,
Token,
Feature activation-0.054
Top resid features:
this
Token this
Feature activation+0.024
Top resid features:
film
Token film
Feature activation+0.057
Top resid features:
is
Token is
Feature activation+0.089
Top resid features:
so
Token so
Feature activation+5.234
Top resid features:
well
Token well
Feature activation-0.068
Top resid features:
animated
Token animated
Feature activation+0.275
Top resid features:
,
Token,
Feature activation+0.128
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.02

Head 3: 0.05

Head 4: 0.02

Head 5: 0.06

Head 6: 0.04

Head 7: 0.05

Head 8: 0.10

Head 9: 0.01

Head 10: 0.02

Head 11: 0.51

Positive logits

href1.72

swer1.61

nen1.56

itas1.53

azz1.51

staff1.50

opus1.49

eous1.46

ccess1.44

ruct1.44

insula1.44

outweigh1.44

isphere1.44

footed1.43

radius1.42

olulu1.42

hoe1.42

ccoli1.39

ripp1.39

vantage1.39

Negative logits

welcome-1.50

"}],"-1.47

statist-1.42

readings-1.42

advoc-1.41

OPER-1.32

supervised-1.31

ECTION-1.30

amnesty-1.28

truthful-1.27

millenn-1.26

challeng-1.26

decriminal-1.23

positives-1.23

ISTER-1.22

complicity-1.20

Reading-1.20

unchanged-1.20

ident-1.19

implicated-1.19

INTERVAL 5.363 - 5.959
CONTAINS 0.001%

Soldier
Token Soldier
Feature activation+0.000
Field
Token Field
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
so
Token so
Feature activation+0.694
staggering
Token staggering
Feature activation+5.959
that
Token that
Feature activation+0.444
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
the
Token the
Feature activation+0.000
got
Token got
Feature activation+0.444
cut
Token cut
Feature activation+1.505
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.262
,
Token,
Feature activation+5.684
I
Token I
Feature activation+2.583
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.509
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
so
Token so
Feature activation+0.363
bad
Token bad
Feature activation+3.846
,
Token,
Feature activation+5.559
or
Token or
Feature activation+1.044
so
Token so
Feature activation+0.525
over
Token over
Feature activation+0.365
priced
Tokenpriced
Feature activation+2.249
that
Token that
Feature activation+2.932
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
segment
Token segment
Feature activation+0.000
became
Token became
Feature activation+0.000
so
Token so
Feature activation+0.000
popular
Token popular
Feature activation+5.514
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.024
spun
Token spun
Feature activation+0.000
off
Token off
Feature activation+0.000
World
Token World
Feature activation+0.000
Report
Token Report
Feature activation+0.000
rankings
Token rankings
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.157
influential
Token influential
Feature activation+5.623
tha
Token tha
Feature activation+0.512
they
Token they
Feature activation+0.147
have
Token have
Feature activation+1.510
become
Token become
Feature activation+1.169
the
Token the
Feature activation+0.000

INTERVAL 4.767 - 5.363
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Bal
TokenBal
Feature activation+0.000
rog
Tokenrog
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.254
distraught
Token distraught
Feature activation+4.987
that
Token that
Feature activation+0.581
they
Token they
Feature activation+0.050
quit
Token quit
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
National
Token National
Feature activation+0.000
Park
Token Park
Feature activation+0.000
are
Token are
Feature activation+0.000
melting
Token melting
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.781
,
Token,
Feature activation+3.228
they
Token they
Feature activation+1.208
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ensuing
Token ensuing
Feature activation+0.000
system
Token system
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.519
confusing
Token confusing
Feature activation+4.619
,
Token,
Feature activation+5.098
the
Token the
Feature activation+2.977
paperwork
Token paperwork
Feature activation+0.543
so
Token so
Feature activation+0.000
ardu
Token ardu
Feature activation+0.000
ous
Tokenous
Feature activation+1.296
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.000
flu
Token flu
Feature activation+0.000
spread
Token spread
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.777
last
Token last
Feature activation+0.840
year
Token year
Feature activation+0.414
that
Token that
Feature activation+0.032
some
Token some
Feature activation+0.009
shelters
Token shelters
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+2.515
ur
Tokenur
Feature activation+0.000
ously
Tokenously
Feature activation+3.786
,
Token,
Feature activation+4.891
you
Token you
Feature activation+2.808
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.333
think
Token think
Feature activation+0.000

INTERVAL 4.171 - 4.767
CONTAINS 0.002%

The
Token The
Feature activation+0.000
TV
Token TV
Feature activation+0.000
income
Token income
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.222
high
Token high
Feature activation+4.620
it
Token it
Feature activation+1.160
is
Token is
Feature activation+0.877
seen
Token seen
Feature activation+0.119
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.629
?
Token?
Feature activation+0.000
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
good
Token good
Feature activation+1.750
,
Token,
Feature activation+4.240
I
Token I
Feature activation+3.356
almost
Token almost
Feature activation+0.000
cried
Token cried
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
costs
Token costs
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.750
on
Token on
Feature activation+0.000
erous
Tokenerous
Feature activation+4.625
that
Token that
Feature activation+0.491
the
Token the
Feature activation+0.000
Affordable
Token Affordable
Feature activation+0.000
Care
Token Care
Feature activation+0.000
Act
Token Act
Feature activation+0.294
Ċ
TokenĊ
Feature activation+0.000
''
Token''
Feature activation+0.000
She
TokenShe
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
emotional
Token emotional
Feature activation+4.197
that
Token that
Feature activation+0.517
staff
Token staff
Feature activation+0.163
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
call
Token call
Feature activation+0.000
the
Token the
Feature activation+0.000
ensuing
Token ensuing
Feature activation+0.000
system
Token system
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.519
confusing
Token confusing
Feature activation+4.619
,
Token,
Feature activation+5.098
the
Token the
Feature activation+2.977
paperwork
Token paperwork
Feature activation+0.543
so
Token so
Feature activation+0.000
ardu
Token ardu
Feature activation+0.000

INTERVAL 3.575 - 4.171
CONTAINS 0.003%

an
Token an
Feature activation+0.000
item
Token item
Feature activation+0.000
so
Token so
Feature activation+0.000
deeply
Token deeply
Feature activation+3.797
discounted
Token discounted
Feature activation+3.235
,
Token,
Feature activation+3.876
they
Token they
Feature activation+3.514
are
Token are
Feature activation+1.943
probably
Token probably
Feature activation+0.000
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
was
Token was
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+2.515
ur
Tokenur
Feature activation+0.000
ously
Tokenously
Feature activation+3.786
,
Token,
Feature activation+4.891
you
Token you
Feature activation+2.808
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.333
that
Token that
Feature activation+0.000
voter
Token voter
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
so
Token so
Feature activation+0.000
opposed
Token opposed
Feature activation+4.018
to
Token to
Feature activation+4.432
Cruz
Token Cruz
Feature activation+0.531
âĢĶ
Token âĢĶ
Feature activation+3.174
especially
Token especially
Feature activation+0.000
during
Token during
Feature activation+0.000
of
Token of
Feature activation+1.753
fear
Token fear
Feature activation+3.404
over
Token over
Feature activation+2.232
strike
Token strike
Feature activation+0.000
zones
Token zones
Feature activation+0.000
that
Token that
Feature activation+3.664
people
Token people
Feature activation+0.026
often
Token often
Feature activation+0.000
wait
Token wait
Feature activation+0.000
for
Token for
Feature activation+0.000
hours
Token hours
Feature activation+0.000
stuck
Token stuck
Feature activation+0.000
so
Token so
Feature activation+0.000
firmly
Token firmly
Feature activation+2.628
in
Token in
Feature activation+0.371
its
Token its
Feature activation+0.000
cheek
Token cheek
Feature activation+3.621
it
Token it
Feature activation+1.291
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
danger
Token danger
Feature activation+0.187
of
Token of
Feature activation+0.000

INTERVAL 2.979 - 3.575
CONTAINS 0.004%

item
Token item
Feature activation+0.000
so
Token so
Feature activation+0.000
deeply
Token deeply
Feature activation+3.797
discounted
Token discounted
Feature activation+3.235
,
Token,
Feature activation+3.876
they
Token they
Feature activation+3.514
are
Token are
Feature activation+1.943
probably
Token probably
Feature activation+0.000
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
loss
Token loss
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+3.538
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
particle
Token particle
Feature activation+0.000
rarely
Token rarely
Feature activation+0.575
interacts
Token interacts
Feature activation+0.000
Park
Token Park
Feature activation+0.000
are
Token are
Feature activation+0.000
melting
Token melting
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.781
,
Token,
Feature activation+3.228
they
Token they
Feature activation+1.208
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
expected
Token expected
Feature activation+0.000
GMOs
Token GMOs
Feature activation+0.000
are
Token are
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+2.327
sensitive
Token sensitive
Feature activation+2.891
area
Token area
Feature activation+3.278
that
Token that
Feature activation+1.145
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
called
Token called
Feature activation+0.000
by
Token by
Feature activation+0.000
display
Token display
Feature activation+0.000
an
Token an
Feature activation+0.000
item
Token item
Feature activation+0.000
so
Token so
Feature activation+0.000
deeply
Token deeply
Feature activation+3.797
discounted
Token discounted
Feature activation+3.235
,
Token,
Feature activation+3.876
they
Token they
Feature activation+3.514
are
Token are
Feature activation+1.943
probably
Token probably
Feature activation+0.000
taking
Token taking
Feature activation+0.000

INTERVAL 2.383 - 2.979
CONTAINS 0.006%

The
Token The
Feature activation+0.000
passing
Token passing
Feature activation+0.000
term
Token term
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
problematic
Token problematic
Feature activation+2.656
.
Token.
Feature activation+0.247
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+1.867
a
Token a
Feature activation+0.000
bitter
Token bitter
Feature activation+0.000
primary
Token primary
Feature activation+0.000
fight
Token fight
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+3.179
that
Token that
Feature activation+2.768
she
Token she
Feature activation+0.354
would
Token would
Feature activation+0.890
pick
Token pick
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
.
Token.
Feature activation+0.000
logos
Token logos
Feature activation+0.000
of
Token of
Feature activation+0.000
some
Token some
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
so
Token so
Feature activation+0.000
recognizable
Token recognizable
Feature activation+2.862
,
Token,
Feature activation+3.196
memorable
Token memorable
Feature activation+0.462
,
Token,
Feature activation+1.375
and
Token and
Feature activation+0.290
seem
Token seem
Feature activation+0.312
Go
Token Go
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
so
Tokenso
Feature activation+0.058
elegant
Token elegant
Feature activation+2.907
,
Token,
Feature activation+3.196
organic
Token organic
Feature activation+0.550
and
Token and
Feature activation+0.000
rig
Token rig
Feature activation+0.000
orously
Tokenorously
Feature activation+0.000
because
Token because
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
shock
Token shock
Feature activation+2.710
,
Token,
Feature activation+1.244
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Dev
Token Dev
Feature activation+0.000
inc
Tokeninc
Feature activation+0.000

INTERVAL 1.788 - 2.383
CONTAINS 0.009%

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
so
Token so
Feature activation+0.000
adorable
Token adorable
Feature activation+1.859
ðŁĻĤ
Token ðŁĻĤ
Feature activation+0.352
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Another
TokenAnother
Feature activation+0.000
thing
Token thing
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
's
Token's
Feature activation+0.000
funding
Token funding
Feature activation+0.000
so
Token so
Feature activation+0.000
severely
Token severely
Feature activation+3.772
that
Token that
Feature activation+1.911
average
Token average
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
this
Token this
Feature activation+0.000
winter
Token winter
Feature activation+0.000
would
Token would
Feature activation+0.407
my
Token my
Feature activation+0.000
chest
Token chest
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.119
t
Token t
Feature activation+0.000
aut
Tokenaut
Feature activation+1.905
and
Token and
Feature activation+1.012
burning
Token burning
Feature activation+0.000
hot
Token hot
Feature activation+1.922
it
Token it
Feature activation+2.558
felt
Token felt
Feature activation+0.437
spark
Token spark
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
and
Token and
Feature activation+0.381
complex
Token complex
Feature activation+0.010
,
Token,
Feature activation+1.659
you
Token you
Feature activation+2.236
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
so
Token so
Feature activation+0.000
sorry
Token sorry
Feature activation+2.374
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.192 - 1.788
CONTAINS 0.015%

crimes
Token crimes
Feature activation+0.000
so
Token so
Feature activation+0.000
violent
Token violent
Feature activation+4.398
or
Token or
Feature activation+2.967
heinous
Token heinous
Feature activation+4.049
that
Token that
Feature activation+1.315
they
Token they
Feature activation+0.154
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
charged
Token charged
Feature activation+0.000
as
Token as
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
terms
Token terms
Feature activation+0.000
so
Token so
Feature activation+0.000
badly
Token badly
Feature activation+1.274
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
pure
Token pure
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
prof
Tokenprof
Feature activation+0.000
itable
Tokenitable
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
powerful
Token powerful
Feature activation+1.194
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
influence
Token influence
Feature activation+0.000
ulsive
Tokenulsive
Feature activation+1.174
to
Token to
Feature activation+0.000
you
Token you
Feature activation+0.123
that
Token that
Feature activation+2.662
you
Token you
Feature activation+0.697
would
Token would
Feature activation+1.696
not
Token not
Feature activation+0.000
obey
Token obey
Feature activation+0.000
?
Token?
Feature activation+0.000
After
Token After
Feature activation+0.000
all
Token all
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
!
Token!
Feature activation+0.000
So
Token So
Feature activation+0.000
much
Token much
Feature activation+0.000
so
Token so
Feature activation+1.477
that
Token that
Feature activation+0.767
De
Token De
Feature activation+0.000
Marco
TokenMarco
Feature activation+1.154
is
Token is
Feature activation+0.431
asking
Token asking
Feature activation+0.000

INTERVAL 0.596 - 1.192
CONTAINS 0.026%

Harris
Token Harris
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.754
,
Token,
Feature activation+2.609
they
Token they
Feature activation+1.624
actually
Token actually
Feature activation+0.630
avoided
Token avoided
Feature activation+0.000
having
Token having
Feature activation+0.000
contact
Token contact
Feature activation+0.000
with
Token with
Feature activation+0.000
him
Token him
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
that
Token that
Feature activation+0.333
song
Token song
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
difficult
Token difficult
Feature activation+0.953
,
Token,
Feature activation+0.807
it
Token it
Feature activation+1.035
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.109
says
Token says
Feature activation+0.000
of
Token of
Feature activation+0.000
Lady
Token Lady
Feature activation+0.000
Gran
Token Gran
Feature activation+0.000
th
Tokenth
Feature activation+0.000
am
Tokenam
Feature activation+0.773
,
Token,
Feature activation+0.508
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.569
nothing
Tokennothing
Feature activation+0.000
can
Token can
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
the
Token the
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
so
Token so
Feature activation+0.000
property
Token property
Feature activation+0.605
owners
Token owners
Feature activation+0.832
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
andestine
Tokenandestine
Feature activation+0.000
Services
Token Services
Feature activation+0.000
someone
Token someone
Feature activation+0.000
so
Token so
Feature activation+0.000
directly
Token directly
Feature activation+0.959
implicated
Token implicated
Feature activation+0.131
in
Token in
Feature activation+0.184
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
practice
Token practice
Feature activation+0.000

INTERVAL 0.000 - 0.596
CONTAINS 99.935%

and
Token and
Feature activation+0.000
built
Token built
Feature activation+0.000
his
Token his
Feature activation+0.000
wealth
Token wealth
Feature activation+0.000
by
Token by
Feature activation+0.000
flooding
Token flooding
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
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
been
Token been
Feature activation+0.000
damaged
Token damaged
Feature activation+0.000
so
Token so
Feature activation+0.000
long
Token long
Feature activation+2.831
its
Token its
Feature activation+2.980
part
Token part
Feature activation+1.116
of
Token of
Feature activation+0.835
congratulated
Token congratulated
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
tweet
Token tweet
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
questionnaire
Token questionnaire
Feature activation+0.000
includes
Token includes
Feature activation+0.000
questions
Token questions
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Koran
Token Koran
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
primary
Token primary
Feature activation+0.000
cooking
Token cooking
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
slowly
Token slowly
Feature activation+0.000
over
Token over
Feature activation+0.000
several
Token several
Feature activation+0.000
hours
Token hours
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H6.11: (feature 13083)

TOP ACTIVATIONS
MAX = 5.663

in
Token in
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.663
will
Token will
Feature activation+4.646
return
Token return
Feature activation+1.443
home
Token home
Feature activation+0.534
with
Token with
Feature activation+0.000
clean
Token clean
Feature activation+0.000
song
Token song
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+1.247
someone
Token someone
Feature activation+5.485
who
Token who
Feature activation+3.779
was
Token was
Feature activation+0.885
interested
Token interested
Feature activation+0.449
in
Token in
Feature activation+0.447
the
Token the
Feature activation+0.105
Hey
Token Hey
Feature activation+0.000
ladies
Token ladies
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
we
Token we
Feature activation+5.430
know
Token know
Feature activation+3.962
what
Token what
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
thinks
Token thinks
Feature activation+0.000
amendment
Token amendment
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.452
been
Token been
Feature activation+5.392
a
Token a
Feature activation+4.019
modest
Token modest
Feature activation+0.816
step
Token step
Feature activation+0.803
in
Token in
Feature activation+0.346
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.032
there
Token there
Feature activation+5.360
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.969
been
Token been
Feature activation+3.961
improvement
Token improvement
Feature activation+0.220
hands
Token hands
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.358
could
Token could
Feature activation+4.727
allocate
Token allocate
Feature activation+1.402
some
Token some
Feature activation+0.000
profits
Token profits
Feature activation+0.000
to
Token to
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+5.243
was
Token was
Feature activation+4.720
seen
Token seen
Feature activation+1.013
as
Token as
Feature activation+0.850
cleaning
Token cleaning
Feature activation+0.000
up
Token up
Feature activation+0.000
heads
Token heads
Feature activation+0.000
off
Token off
Feature activation+0.000
?
Token?
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
have
Token have
Feature activation+5.164
the
Token the
Feature activation+1.414
courtesy
Token courtesy
Feature activation+0.933
to
Token to
Feature activation+2.752
go
Token go
Feature activation+1.336
AW
Token AW
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.520
I
Token I
Feature activation+5.030
didn
Token didn
Feature activation+3.341
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.513
die
Token die
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.019
won
Token won
Feature activation+3.915
't
Token't
Feature activation+4.520
be
Token be
Feature activation+2.322
exposed
Token exposed
Feature activation+0.000
to
Token to
Feature activation+0.000
AI
Token AI
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+4.997
's
Token's
Feature activation+4.546
slightly
Token slightly
Feature activation+0.378
more
Token more
Feature activation+0.162
rel
Token rel
Feature activation+0.000
atable
Tokenatable
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
I
Token I
Feature activation+4.992
drink
Token drink
Feature activation+3.025
beer
Token beer
Feature activation+1.216
.
Token.
Feature activation+0.466
As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.358
could
Token could
Feature activation+4.727
allocate
Token allocate
Feature activation+1.402
some
Token some
Feature activation+0.000
profits
Token profits
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+5.243
was
Token was
Feature activation+4.720
seen
Token seen
Feature activation+1.013
as
Token as
Feature activation+0.850
cleaning
Token cleaning
Feature activation+0.000
up
Token up
Feature activation+0.000
after
Token after
Feature activation+0.089
Brazil
Token Brazil
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.663
will
Token will
Feature activation+4.646
return
Token return
Feature activation+1.443
home
Token home
Feature activation+0.534
with
Token with
Feature activation+0.000
clean
Token clean
Feature activation+0.000
cons
Token cons
Feature activation+0.000
,
Token,
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
at
Token at
Feature activation+4.632
this
Token this
Feature activation+1.085
time
Token time
Feature activation+1.629
,
Token,
Feature activation+0.418
does
Token does
Feature activation+0.490
not
Token not
Feature activation+0.083
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+4.997
's
Token's
Feature activation+4.546
slightly
Token slightly
Feature activation+0.378
more
Token more
Feature activation+0.162
rel
Token rel
Feature activation+0.000
atable
Tokenatable
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.019
won
Token won
Feature activation+3.915
't
Token't
Feature activation+4.520
be
Token be
Feature activation+2.322
exposed
Token exposed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
plan
Token plan
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
and
Token and
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
bring
Token bring
Feature activation+4.207
a
Token a
Feature activation+1.963
small
Token small
Feature activation+0.470
water
Token water
Feature activation+0.000
bottle
Token bottle
Feature activation+0.000
.
Token.
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+3.556
world
Token world
Feature activation+4.128
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.113
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000

Top DFA by src position
MAX = 6.797

fans
Token fans
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.022
Top resid features:
Brazil
Token Brazil
Feature activation+0.021
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
at
Token at
Feature activation+0.055
Top resid features:
least
Token least
Feature activation+6.550
Top resid features:
they
Token they
Feature activation+0.028
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
return
Token return
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
song
Token song
Feature activation-0.030
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
so
Token so
Feature activation-0.035
Top resid features:
at
Token at
Feature activation+0.073
Top resid features:
least
Token least
Feature activation+6.797
Top resid features:
someone
Token someone
Feature activation+0.108
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
interested
Token interested
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
Hey
Token Hey
Feature activation-0.091
Top resid features:
ladies
Token ladies
Feature activation-0.055
Top resid features:
,
Token,
Feature activation-0.039
Top resid features:
at
Token at
Feature activation+0.037
Top resid features:
least
Token least
Feature activation+6.776
Top resid features:
we
Token we
Feature activation-0.020
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
Donald
Token Donald
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
amendment
Token amendment
Feature activation+0.067
Top resid features:
would
Token would
Feature activation+0.173
Top resid features:
have
Token have
Feature activation+0.112
Top resid features:
at
Token at
Feature activation+0.173
Top resid features:
least
Token least
Feature activation+5.910
Top resid features:
been
Token been
Feature activation+0.121
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
modest
Token modest
Feature activation+0.000
Top resid features:
step
Token step
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
ling
Token ling
Feature activation+0.004
Top resid features:
ers
Tokeners
Feature activation-0.075
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
but
Token but
Feature activation+0.034
Top resid features:
at
Token at
Feature activation+0.118
Top resid features:
least
Token least
Feature activation+6.454
Top resid features:
there
Token there
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.013
Top resid features:
hands
Token hands
Feature activation-0.066
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
but
Token but
Feature activation-0.019
Top resid features:
at
Token at
Feature activation+0.142
Top resid features:
least
Token least
Feature activation+6.650
Top resid features:
they
Token they
Feature activation-0.059
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
allocate
Token allocate
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
profits
Token profits
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
powerful
Token powerful
Feature activation-0.047
Top resid features:
politicians
Token politicians
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
at
Token at
Feature activation+0.096
Top resid features:
least
Token least
Feature activation+6.236
Top resid features:
she
Token she
Feature activation+0.065
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
cleaning
Token cleaning
Feature activation+0.000
Top resid features:
little
Token little
Feature activation-0.005
Top resid features:
heads
Token heads
Feature activation-0.003
Top resid features:
off
Token off
Feature activation+0.015
Top resid features:
?
Token?
Feature activation-0.024
Top resid features:
At
Token At
Feature activation+0.028
Top resid features:
least
Token least
Feature activation+6.378
Top resid features:
have
Token have
Feature activation+0.090
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
courtesy
Token courtesy
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
my
Token my
Feature activation-0.004
Top resid features:
back
Token back
Feature activation-0.047
Top resid features:
,
Token,
Feature activation-0.030
Top resid features:
but
Token but
Feature activation+0.034
Top resid features:
at
Token at
Feature activation+0.092
Top resid features:
least
Token least
Feature activation+6.462
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
play
Token play
Feature activation+0.015
Top resid features:
?
Token?
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
At
TokenAt
Feature activation+0.041
Top resid features:
least
Token least
Feature activation+6.248
Top resid features:
they
Token they
Feature activation-0.010
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:
exposed
Token exposed
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
AI
Token AI
Feature activation+0.070
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
but
Token but
Feature activation-0.015
Top resid features:
at
Token at
Feature activation+0.151
Top resid features:
least
Token least
Feature activation+6.030
Top resid features:
she
Token she
Feature activation-0.012
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
slightly
Token slightly
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
rel
Token rel
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.640
Top resid features:
Ċ
TokenĊ
Feature activation-0.066
Top resid features:
Well
TokenWell
Feature activation-0.192
Top resid features:
,
Token,
Feature activation-0.124
Top resid features:
at
Token at
Feature activation+0.073
Top resid features:
least
Token least
Feature activation+6.456
Top resid features:
I
Token I
Feature activation+0.017
Top resid features:
drink
Token drink
Feature activation+0.000
Top resid features:
beer
Token beer
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
As
Token As
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.013
Top resid features:
hands
Token hands
Feature activation-0.022
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
but
Token but
Feature activation-0.027
Top resid features:
at
Token at
Feature activation+0.109
Top resid features:
least
Token least
Feature activation+5.729
Top resid features:
they
Token they
Feature activation+0.060
Top resid features:
could
Token could
Feature activation+0.149
Top resid features:
allocate
Token allocate
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
profits
Token profits
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.024
Top resid features:
powerful
Token powerful
Feature activation-0.027
Top resid features:
politicians
Token politicians
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
at
Token at
Feature activation+0.060
Top resid features:
least
Token least
Feature activation+5.755
Top resid features:
she
Token she
Feature activation+0.156
Top resid features:
was
Token was
Feature activation+0.079
Top resid features:
seen
Token seen
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
cleaning
Token cleaning
Feature activation+0.000
Top resid features:
fans
Token fans
Feature activation-0.038
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
Brazil
Token Brazil
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
at
Token at
Feature activation+0.043
Top resid features:
least
Token least
Feature activation+5.532
Top resid features:
they
Token they
Feature activation+0.092
Top resid features:
will
Token will
Feature activation+0.092
Top resid features:
return
Token return
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Therefore
Token Therefore
Feature activation-0.031
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
Beijing
Token Beijing
Feature activation+0.128
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
at
Token at
Feature activation+0.069
Top resid features:
least
Token least
Feature activation+5.441
Top resid features:
at
Token at
Feature activation+0.166
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
AI
Token AI
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
but
Token but
Feature activation+0.010
Top resid features:
at
Token at
Feature activation+0.134
Top resid features:
least
Token least
Feature activation+5.508
Top resid features:
she
Token she
Feature activation+0.072
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
slightly
Token slightly
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
rel
Token rel
Feature activation+0.000
Top resid features:
play
Token play
Feature activation+0.021
Top resid features:
?
Token?
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
At
TokenAt
Feature activation+0.057
Top resid features:
least
Token least
Feature activation+5.510
Top resid features:
they
Token they
Feature activation+0.089
Top resid features:
won
Token won
Feature activation+0.105
Top resid features:
't
Token't
Feature activation+0.063
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
exposed
Token exposed
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.006
Top resid features:
plan
Token plan
Feature activation+0.069
Top resid features:
ahead
Token ahead
Feature activation+0.161
Top resid features:
and
Token and
Feature activation+0.084
Top resid features:
at
Token at
Feature activation+0.105
Top resid features:
least
Token least
Feature activation+4.884
Top resid features:
bring
Token bring
Feature activation+0.207
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
bottle
Token bottle
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
world
Token world
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
at
Token at
Feature activation+0.066
Top resid features:
least
Token least
Feature activation+4.977
Top resid features:
the
Token the
Feature activation+0.259
Top resid features:
world
Token world
Feature activation-0.042
Top resid features:
inside
Token inside
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.02

Head 3: 0.03

Head 4: 0.04

Head 5: 0.09

Head 6: 0.05

Head 7: 0.03

Head 8: 0.10

Head 9: 0.02

Head 10: 0.02

Head 11: 0.51

Positive logits

acknowledgement1.88

sanity1.82

insofar1.73

usable1.72

indirectly1.66

recogn1.65

sane1.63

marginally1.63

intact1.61

alive1.59

acknowledgment1.55

spared1.55

unim1.55

itle1.55

unaffected1.53

aver1.51

recognise1.51

acknowled1.49

surviv1.48

disapprove1.45

Negative logits

URA-1.54

-1.46

ULT-1.46

-1.44

Cosponsors-1.44

apego-1.40

Hybrid-1.40

ARI-1.39

裏�-1.38

tics-1.38

dfx-1.36

-1.35

iddles-1.34

onica-1.30

Strateg-1.30

Deity-1.30

UL-1.28

Neph-1.28

IDES-1.26

-1.26

INTERVAL 5.097 - 5.663
CONTAINS 0.001%

ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.032
there
Token there
Feature activation+5.360
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.969
been
Token been
Feature activation+3.961
improvement
Token improvement
Feature activation+0.220
hands
Token hands
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.358
could
Token could
Feature activation+4.727
allocate
Token allocate
Feature activation+1.402
some
Token some
Feature activation+0.000
profits
Token profits
Feature activation+0.000
to
Token to
Feature activation+0.000
amendment
Token amendment
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.452
been
Token been
Feature activation+5.392
a
Token a
Feature activation+4.019
modest
Token modest
Feature activation+0.816
step
Token step
Feature activation+0.803
in
Token in
Feature activation+0.346
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
song
Token song
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+1.247
someone
Token someone
Feature activation+5.485
who
Token who
Feature activation+3.779
was
Token was
Feature activation+0.885
interested
Token interested
Feature activation+0.449
in
Token in
Feature activation+0.447
the
Token the
Feature activation+0.105
in
Token in
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.663
will
Token will
Feature activation+4.646
return
Token return
Feature activation+1.443
home
Token home
Feature activation+0.534
with
Token with
Feature activation+0.000
clean
Token clean
Feature activation+0.000

INTERVAL 4.530 - 5.097
CONTAINS 0.001%

AI
Token AI
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+4.997
's
Token's
Feature activation+4.546
slightly
Token slightly
Feature activation+0.378
more
Token more
Feature activation+0.162
rel
Token rel
Feature activation+0.000
atable
Tokenatable
Feature activation+0.000
,
Token,
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
at
Token at
Feature activation+4.632
this
Token this
Feature activation+1.085
time
Token time
Feature activation+1.629
,
Token,
Feature activation+0.418
does
Token does
Feature activation+0.490
not
Token not
Feature activation+0.083
Brazil
Token Brazil
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.663
will
Token will
Feature activation+4.646
return
Token return
Feature activation+1.443
home
Token home
Feature activation+0.534
with
Token with
Feature activation+0.000
clean
Token clean
Feature activation+0.000
cons
Token cons
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
I
Token I
Feature activation+4.992
drink
Token drink
Feature activation+3.025
beer
Token beer
Feature activation+1.216
.
Token.
Feature activation+0.466
As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.019
won
Token won
Feature activation+3.915
't
Token't
Feature activation+4.520
be
Token be
Feature activation+2.322
exposed
Token exposed
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 3.964 - 4.530
CONTAINS 0.001%

he
Token he
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.063
expand
Token expand
Feature activation+4.120
in
Token in
Feature activation+0.362
the
Token the
Feature activation+1.014
G
Token G
Feature activation+0.000
opher
Tokenopher
Feature activation+0.000
State
Token State
Feature activation+0.000
consider
Token consider
Feature activation+0.000
what
Token what
Feature activation+0.000
happens
Token happens
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
to
Token to
Feature activation+3.996
an
Token an
Feature activation+2.568
extent
Token extent
Feature activation+0.250
through
Token through
Feature activation+0.805
the
Token the
Feature activation+0.000
prism
Token prism
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.452
been
Token been
Feature activation+5.392
a
Token a
Feature activation+4.019
modest
Token modest
Feature activation+0.816
step
Token step
Feature activation+0.803
in
Token in
Feature activation+0.346
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
File
TokenFile
Feature activation+0.000
plan
Token plan
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
and
Token and
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
bring
Token bring
Feature activation+4.207
a
Token a
Feature activation+1.963
small
Token small
Feature activation+0.470
water
Token water
Feature activation+0.000
bottle
Token bottle
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.019
won
Token won
Feature activation+3.915
't
Token't
Feature activation+4.520
be
Token be
Feature activation+2.322
exposed
Token exposed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 3.398 - 3.964
CONTAINS 0.001%

,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
a
Token a
Feature activation+3.672
dozen
Token dozen
Feature activation+0.000
more
Token more
Feature activation+0.000
Marvel
Token Marvel
Feature activation+0.000
characters
Token characters
Feature activation+0.000
coming
Token coming
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+3.556
world
Token world
Feature activation+4.128
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.113
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+1.879
Lo
Token Lo
Feature activation+0.000
ons
Tokenons
Feature activation+0.082
won
Token won
Feature activation+3.384
't
Token't
Feature activation+3.853
be
Token be
Feature activation+1.423
missing
Token missing
Feature activation+0.786
any
Token any
Feature activation+0.000
key
Token key
Feature activation+0.000
pieces
Token pieces
Feature activation+0.000
House
Token House
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+2.555
is
Token is
Feature activation+3.902
big
Token big
Feature activation+1.118
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+1.273
do
Token do
Feature activation+0.603
whatever
Token whatever
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+2.133
customer
Token customer
Feature activation+1.105
demanded
Token demanded
Feature activation+3.927
to
Token to
Feature activation+0.959
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
manager
Token manager
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 2.831 - 3.398
CONTAINS 0.001%

strongly
Token strongly
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
these
Token these
Feature activation+3.333
ministries
Token ministries
Feature activation+0.020
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.489
not
Token not
Feature activation+0.000
Trudeau
Token Trudeau
Feature activation+0.000
will
Token will
Feature activation+0.000
hopefully
Token hopefully
Feature activation+0.000
keep
Token keep
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.197
the
Token the
Feature activation+3.045
families
Token families
Feature activation+1.395
Jamie
Token Jamie
Feature activation+0.258
is
Token is
Feature activation+0.752
sworn
Token sworn
Feature activation+0.233
to
Token to
Feature activation+0.000
That
Token That
Feature activation+0.000
guarantees
Token guarantees
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
a
Token a
Feature activation+2.088
good
Token good
Feature activation+2.849
,
Token,
Feature activation+1.058
if
Token if
Feature activation+0.890
not
Token not
Feature activation+0.161
great
Token great
Feature activation+0.920
running
Token running
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+1.879
Lo
Token Lo
Feature activation+0.000
ons
Tokenons
Feature activation+0.082
won
Token won
Feature activation+3.384
't
Token't
Feature activation+3.853
be
Token be
Feature activation+1.423
missing
Token missing
Feature activation+0.786
any
Token any
Feature activation+0.000
key
Token key
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
I
Token I
Feature activation+4.992
drink
Token drink
Feature activation+3.025
beer
Token beer
Feature activation+1.216
.
Token.
Feature activation+0.466
As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
beer
Token beer
Feature activation+0.000

INTERVAL 2.265 - 2.831
CONTAINS 0.002%

At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+5.019
won
Token won
Feature activation+3.915
't
Token't
Feature activation+4.520
be
Token be
Feature activation+2.322
exposed
Token exposed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
extreme
Tokenextreme
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
have
Token have
Feature activation+5.164
the
Token the
Feature activation+1.414
courtesy
Token courtesy
Feature activation+0.933
to
Token to
Feature activation+2.752
go
Token go
Feature activation+1.336
AW
Token AW
Feature activation+0.000
OL
TokenOL
Feature activation+0.000
first
Token first
Feature activation+0.243
.
Token.
Feature activation+0.000
changes
Token changes
Feature activation+0.000
over
Token over
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+1.143
next
Token next
Feature activation+2.456
five
Token five
Feature activation+0.000
years
Token years
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
focused
Token focused
Feature activation+0.000
to
Token to
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.654
raise
Token raise
Feature activation+3.906
the
Token the
Feature activation+0.876
question
Token question
Feature activation+2.508
if
Token if
Feature activation+0.000
other
Token other
Feature activation+0.000
alternatives
Token alternatives
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
or
Token or
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
release
Token release
Feature activation+2.330
new
Token new
Feature activation+0.069
music
Token music
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 1.699 - 2.265
CONTAINS 0.002%

."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+1.879
Lo
Token Lo
Feature activation+0.000
ons
Tokenons
Feature activation+0.082
won
Token won
Feature activation+3.384
't
Token't
Feature activation+3.853
be
Token be
Feature activation+1.423
centre
Token centre
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+1.863
was
Token was
Feature activation+1.356
supposed
Token supposed
Feature activation+0.232
to
Token to
Feature activation+0.451
be
Token be
Feature activation+0.911
.
Token.
Feature activation+0.000
wander
Token wander
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
under
Token under
Feature activation+1.722
the
Token the
Feature activation+0.163
Castle
Token Castle
Feature activation+0.000
Doctrine
Token Doctrine
Feature activation+0.000
if
Token if
Feature activation+0.307
that
Token that
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
and
Token and
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
bring
Token bring
Feature activation+4.207
a
Token a
Feature activation+1.963
small
Token small
Feature activation+0.470
water
Token water
Feature activation+0.000
bottle
Token bottle
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĺ
TokenĹ
Feature activation+0.000
at
Tokenat
Feature activation+0.000
least
Token least
Feature activation+0.000
for
Token for
Feature activation+2.388
the
Token the
Feature activation+2.199
industrialized
Token industrialized
Feature activation+0.000
,
Token,
Feature activation+0.000
imperialist
Token imperialist
Feature activation+0.000
,
Token,
Feature activation+0.000
nations
Token nations
Feature activation+0.000

INTERVAL 1.133 - 1.699
CONTAINS 0.005%

the
Tokenthe
Feature activation+0.000
truth
Token truth
Feature activation+0.000
,"
Token,"
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
according
Token according
Feature activation+1.493
to
Token to
Feature activation+1.071
both
Token both
Feature activation+0.000
NBC
Token NBC
Feature activation+0.000
and
Token and
Feature activation+0.000
ABC
Token ABC
Feature activation+0.000
,
Token,
Feature activation+0.000
once
Token once
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
some
Token some
Feature activation+1.689
convers
Token convers
Feature activation+0.074
ational
Tokenational
Feature activation+0.019
Arabic
Token Arabic
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
hopefully
Token hopefully
Feature activation+0.000
keep
Token keep
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.197
the
Token the
Feature activation+3.045
families
Token families
Feature activation+1.395
Jamie
Token Jamie
Feature activation+0.258
is
Token is
Feature activation+0.752
sworn
Token sworn
Feature activation+0.233
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.394
American
Token American
Feature activation+0.000
culture
Token culture
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.257
,
Token,
Feature activation+1.490
is
Token is
Feature activation+1.367
seen
Token seen
Feature activation+0.185
as
Token as
Feature activation+0.563
a
Token a
Feature activation+0.565
necessary
Token necessary
Feature activation+0.000
struggle
Token struggle
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.000
of
Token of
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
what
Token what
Feature activation+1.665
the
Token the
Feature activation+0.691
CIA
Token CIA
Feature activation+0.000
is
Token is
Feature activation+0.227
claiming
Token claiming
Feature activation+0.000
right
Token right
Feature activation+0.000

INTERVAL 0.566 - 1.133
CONTAINS 0.007%

.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+0.704
it
Token it
Feature activation+0.617
felt
Token felt
Feature activation+0.014
as
Token as
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
some
Token some
Feature activation+2.157
guns
Token guns
Feature activation+0.791
that
Token that
Feature activation+1.034
the
Token the
Feature activation+0.071
teenager
Token teenager
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
young
Token young
Feature activation+0.000
partners
Token partners
Feature activation+0.000
expected
Token expected
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
to
Token to
Feature activation+2.494
match
Token match
Feature activation+0.822
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
investment
Token investment
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+2.088
good
Token good
Feature activation+2.849
,
Token,
Feature activation+1.058
if
Token if
Feature activation+0.890
not
Token not
Feature activation+0.161
great
Token great
Feature activation+0.920
running
Token running
Feature activation+0.000
play
Token play
Feature activation+0.187
for
Token for
Feature activation+0.077
the
Token the
Feature activation+0.000
opponent
Token opponent
Feature activation+0.000
UC
Token UC
Feature activation+0.000
OP
TokenOP
Feature activation+0.000
to
Token to
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.500
tacit
Token tacit
Feature activation+0.964
ly
Tokenly
Feature activation+0.935
acknowledge
Token acknowledge
Feature activation+0.825
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
mis
Token mis
Feature activation+0.000

INTERVAL 0.000 - 0.566
CONTAINS 99.980%

of
Token of
Feature activation+0.000
business
Token business
Feature activation+0.000
groups
Token groups
Feature activation+0.000
by
Token by
Feature activation+0.000
C
Token C
Feature activation+0.000
MI
TokenMI
Feature activation+0.000
E
TokenE
Feature activation+0.000
is
Token is
Feature activation+0.000
largely
Token largely
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
for
Token for
Feature activation+0.000
women
Token women
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
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+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.000
call
Token call
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
explanation
Token explanation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
Line
TokenLine
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bay
TokenBay
Feature activation+0.000
Area
Token Area
Feature activation+0.000
Socialist
Token Socialist
Feature activation+0.000
Organ
Token Organ
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
Help
Token Help
Feature activation+0.000
would
Token would
Feature activation+0.000
seem
Token seem
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
"
Token "
Feature activation+0.000
us
Tokenus
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 H6.11: (feature 3339)

TOP ACTIVATIONS
MAX = 4.686

money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Aunt
Token Aunt
Feature activation+0.741
May
Token May
Feature activation+4.686
from
Token from
Feature activation+0.394
being
Token being
Feature activation+0.000
ev
Token ev
Feature activation+0.000
icted
Tokenicted
Feature activation+0.000
or
Token or
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
law
Token law
Feature activation+0.000
and
Token and
Feature activation+0.467
order
Token order
Feature activation+4.511
for
Token for
Feature activation+0.548
others
Token others
Feature activation+0.033
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
kept
Token kept
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
y
Tokeny
Feature activation+4.335
,
Token,
Feature activation+0.184
the
Token the
Feature activation+0.000
X
Token X
Feature activation+0.000
-
Token-
Feature activation+0.000
Men
TokenMen
Feature activation+1.219
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Americans
Token Americans
Feature activation+4.242
informed
Token informed
Feature activation+0.000
has
Token has
Feature activation+0.000
slipped
Token slipped
Feature activation+0.000
among
Token among
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
for
Token for
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.494
practice
Token practice
Feature activation+4.182
alive
Token alive
Feature activation+1.020
here
Token here
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
States
Token States
Feature activation+0.000
cooking
Token cooking
Feature activation+0.000
process
Token process
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.801
beans
Token beans
Feature activation+3.892
from
Token from
Feature activation+2.181
soft
Token soft
Feature activation+0.182
ening
Tokenening
Feature activation+0.000
.
Token.
Feature activation+0.000
See
Token See
Feature activation+0.000
I
Token I
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
my
Token my
Feature activation+1.109
family
Token family
Feature activation+3.858
safe
Token safe
Feature activation+0.262
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
proud
Token proud
Feature activation+0.000
-
Token-
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
laws
Token laws
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
governments
Token governments
Feature activation+3.786
honest
Token honest
Feature activation+1.161
and
Token and
Feature activation+0.854
First
Token First
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
governments
Token governments
Feature activation+0.000
is
Token is
Feature activation+0.000
taking
Token taking
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
unwanted
Token unwanted
Feature activation+0.385
migrants
Token migrants
Feature activation+3.768
out
Token out
Feature activation+2.409
of
Token of
Feature activation+0.329
the
Token the
Feature activation+0.282
EU
Token EU
Feature activation+0.000
.
Token.
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
the
Token the
Feature activation+0.674
Government
Token Government
Feature activation+3.581
's
Token's
Feature activation+0.505
industrial
Token industrial
Feature activation+0.732
strategy
Token strategy
Feature activation+3.709
relevant
Token relevant
Feature activation+0.760
and
Token and
Feature activation+0.646
hooked
Token hooked
Feature activation+0.127
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.352
Edward
Token Edward
Feature activation+0.913
ian
Tokenian
Feature activation+0.707
Prom
Token Prom
Feature activation+0.210
en
Tokenen
Feature activation+0.000
ade
Tokenade
Feature activation+3.122
online
Token online
Feature activation+3.666
and
Token and
Feature activation+0.846
a
Token a
Feature activation+0.300
free
Token free
Feature activation+0.000
resource
Token resource
Feature activation+0.000
in
Token in
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
noise
Token noise
Feature activation+0.000
,
Token,
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
Jeff
Token Jeff
Feature activation+3.650
up
Token up
Feature activation+0.968
all
Token all
Feature activation+0.290
night
Token night
Feature activation+0.530
,
Token,
Feature activation+0.109
if
Token if
Feature activation+0.000
,
Token,
Feature activation+0.000
keep
Token keep
Feature activation+0.000
ones
Token ones
Feature activation+1.938
/
Token/
Feature activation+0.192
tw
Tokentw
Feature activation+0.509
os
Tokenos
Feature activation+3.643
(
Token (
Feature activation+0.000
click
Tokenclick
Feature activation+0.000
again
Token again
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
kept
Token kept
Feature activation+0.000
local
Token local
Feature activation+1.060
brick
Token brick
Feature activation+1.143
and
Token and
Feature activation+0.000
mortar
Token mortar
Feature activation+3.595
stores
Token stores
Feature activation+3.614
alive
Token alive
Feature activation+1.667
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
the
Token the
Feature activation+0.000
technology
Token technology
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
food
Token food
Feature activation+3.613
fresh
Token fresh
Feature activation+1.737
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
study
Token study
Feature activation+0.000
has
Token has
Feature activation+0.000
kept
Token kept
Feature activation+0.000
local
Token local
Feature activation+1.060
brick
Token brick
Feature activation+1.143
and
Token and
Feature activation+0.000
mortar
Token mortar
Feature activation+3.595
stores
Token stores
Feature activation+3.614
alive
Token alive
Feature activation+1.667
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
important
Token important
Feature activation+0.000
for
Token for
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
the
Token the
Feature activation+0.674
Government
Token Government
Feature activation+3.581
's
Token's
Feature activation+0.505
industrial
Token industrial
Feature activation+0.732
strategy
Token strategy
Feature activation+3.709
relevant
Token relevant
Feature activation+0.760
and
Token and
Feature activation+0.646
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
themselves
Token themselves
Feature activation+0.576
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
children
Token children
Feature activation+3.575
separated
Token separated
Feature activation+0.772
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
dealings
Token dealings
Feature activation+0.000
while
Token while
Feature activation+0.000
The
TokenThe
Feature activation+0.000
serving
Token serving
Feature activation+0.000
kept
Token kept
Feature activation+0.000
UN
Token UN
Feature activation+0.000
M
TokenM
Feature activation+2.182
in
Token in
Feature activation+3.556
sets
Token sets
Feature activation+0.000
and
Token and
Feature activation+0.002
Hilbert
Token Hilbert
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
that
Token that
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
the
Token the
Feature activation+0.893
Kings
Token Kings
Feature activation+2.019
in
Token in
Feature activation+3.534
Sacramento
Token Sacramento
Feature activation+1.709
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000

Top DFA by src position
MAX = 5.496

to
Token to
Feature activation+0.015
Top resid features:
raise
Token raise
Feature activation+0.032
Top resid features:
money
Token money
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
help
Token help
Feature activation+0.090
Top resid features:
keep
Token keep
Feature activation+5.327
Top resid features:
Aunt
Token Aunt
Feature activation+0.066
Top resid features:
May
Token May
Feature activation+0.036
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
ev
Token ev
Feature activation+0.000
Top resid features:
demonstrate
Token demonstrate
Feature activation-0.056
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
need
Token need
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
keep
Token keep
Feature activation+5.496
Top resid features:
law
Token law
Feature activation+0.285
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
order
Token order
Feature activation-0.038
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
others
Token others
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
licensing
Token licensing
Feature activation+0.032
Top resid features:
troubles
Token troubles
Feature activation+0.042
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
have
Token have
Feature activation+0.023
Top resid features:
kept
Token kept
Feature activation+4.892
Top resid features:
Sp
Token Sp
Feature activation+0.468
Top resid features:
ide
Tokenide
Feature activation-0.011
Top resid features:
y
Tokeny
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
ability
Token ability
Feature activation-0.023
Top resid features:
to
Token to
Feature activation+0.053
Top resid features:
keep
Token keep
Feature activation+4.973
Top resid features:
Americans
Token Americans
Feature activation+0.200
Top resid features:
informed
Token informed
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
slipped
Token slipped
Feature activation+0.000
Top resid features:
among
Token among
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.006
Top resid features:
looking
Token looking
Feature activation-0.016
Top resid features:
for
Token for
Feature activation-0.039
Top resid features:
ways
Token ways
Feature activation+0.056
Top resid features:
to
Token to
Feature activation+0.079
Top resid features:
keep
Token keep
Feature activation+4.773
Top resid features:
the
Token the
Feature activation+0.388
Top resid features:
practice
Token practice
Feature activation+0.128
Top resid features:
alive
Token alive
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
bean
Token bean
Feature activation-0.002
Top resid features:
's
Token's
Feature activation-0.027
Top resid features:
cooking
Token cooking
Feature activation-0.017
Top resid features:
process
Token process
Feature activation-0.029
Top resid features:
will
Token will
Feature activation+0.038
Top resid features:
keep
Token keep
Feature activation+4.774
Top resid features:
the
Token the
Feature activation+0.165
Top resid features:
beans
Token beans
Feature activation+0.018
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
soft
Token soft
Feature activation+0.000
Top resid features:
ening
Tokenening
Feature activation+0.000
Top resid features:
NRA
Token NRA
Feature activation-0.012
Top resid features:
gear
Token gear
Feature activation-0.020
Top resid features:
I
Token I
Feature activation+0.007
Top resid features:
need
Token need
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.088
Top resid features:
keep
Token keep
Feature activation+4.506
Top resid features:
my
Token my
Feature activation+0.258
Top resid features:
family
Token family
Feature activation+0.121
Top resid features:
safe
Token safe
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
to
Tokento
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
information
Tokeninformation
Feature activation+0.017
Top resid features:
laws
Token laws
Feature activation+0.015
Top resid features:
help
Token help
Feature activation+0.062
Top resid features:
keep
Token keep
Feature activation+4.680
Top resid features:
governments
Token governments
Feature activation+0.078
Top resid features:
honest
Token honest
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
First
Token First
Feature activation+0.000
Top resid features:
Nations
Token Nations
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
EU
Token EU
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
taking
Token taking
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.054
Top resid features:
keep
Token keep
Feature activation+4.179
Top resid features:
unwanted
Token unwanted
Feature activation+0.225
Top resid features:
migrants
Token migrants
Feature activation+0.183
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
vit
Token vit
Feature activation+0.032
Top resid features:
ally
Tokenally
Feature activation+0.011
Top resid features:
important
Token important
Feature activation+0.023
Top resid features:
for
Token for
Feature activation+0.022
Top resid features:
keeping
Token keeping
Feature activation+4.321
Top resid features:
the
Token the
Feature activation+0.126
Top resid features:
Government
Token Government
Feature activation+0.125
Top resid features:
's
Token's
Feature activation+0.359
Top resid features:
industrial
Token industrial
Feature activation-0.102
Top resid features:
strategy
Token strategy
Feature activation+0.019
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.124
Top resid features:
donation
Token donation
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
keep
Token keep
Feature activation+4.355
Top resid features:
Edward
Token Edward
Feature activation+0.167
Top resid features:
ian
Tokenian
Feature activation+0.017
Top resid features:
Prom
Token Prom
Feature activation+0.035
Top resid features:
en
Tokenen
Feature activation+0.016
Top resid features:
ade
Tokenade
Feature activation-0.044
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
lot
Token lot
Feature activation+0.027
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
noise
Token noise
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
keeping
Token keeping
Feature activation+4.314
Top resid features:
Jeff
Token Jeff
Feature activation+0.130
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
night
Token night
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.049
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
play
Tokenplay
Feature activation-0.094
Top resid features:
random
Token random
Feature activation-0.036
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
keep
Token keep
Feature activation+4.441
Top resid features:
ones
Token ones
Feature activation+0.110
Top resid features:
/
Token/
Feature activation+0.411
Top resid features:
tw
Tokentw
Feature activation+0.074
Top resid features:
os
Tokenos
Feature activation+0.102
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
community
Token community
Feature activation-0.011
Top resid features:
building
Token building
Feature activation-0.000
Top resid features:
that
Token that
Feature activation-0.021
Top resid features:
has
Token has
Feature activation+0.021
Top resid features:
kept
Token kept
Feature activation+4.213
Top resid features:
local
Token local
Feature activation+0.353
Top resid features:
brick
Token brick
Feature activation+0.010
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
mortar
Token mortar
Feature activation+0.101
Top resid features:
stores
Token stores
Feature activation+0.045
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
technology
Token technology
Feature activation-0.017
Top resid features:
needed
Token needed
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.044
Top resid features:
keep
Token keep
Feature activation+4.304
Top resid features:
food
Token food
Feature activation+0.209
Top resid features:
fresh
Token fresh
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
2014
Token 2014
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
community
Token community
Feature activation-0.014
Top resid features:
building
Token building
Feature activation-0.007
Top resid features:
that
Token that
Feature activation-0.004
Top resid features:
has
Token has
Feature activation+0.011
Top resid features:
kept
Token kept
Feature activation+4.284
Top resid features:
local
Token local
Feature activation+0.370
Top resid features:
brick
Token brick
Feature activation-0.028
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
mortar
Token mortar
Feature activation+0.054
Top resid features:
stores
Token stores
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
vit
Token vit
Feature activation+0.013
Top resid features:
ally
Tokenally
Feature activation+0.017
Top resid features:
important
Token important
Feature activation+0.015
Top resid features:
for
Token for
Feature activation+0.012
Top resid features:
keeping
Token keeping
Feature activation+4.182
Top resid features:
the
Token the
Feature activation+0.260
Top resid features:
Government
Token Government
Feature activation+0.067
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
industrial
Token industrial
Feature activation+0.000
Top resid features:
strategy
Token strategy
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
tried
Token tried
Feature activation-0.084
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
keep
Token keep
Feature activation+4.587
Top resid features:
themselves
Token themselves
Feature activation+0.021
Top resid features:
and
Token and
Feature activation+0.322
Top resid features:
their
Token their
Feature activation+0.095
Top resid features:
children
Token children
Feature activation-0.042
Top resid features:
separated
Token separated
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
serving
Token serving
Feature activation-0.120
Top resid features:
kept
Token kept
Feature activation+4.376
Top resid features:
UN
Token UN
Feature activation+0.054
Top resid features:
M
TokenM
Feature activation+0.213
Top resid features:
in
Token in
Feature activation-0.042
Top resid features:
sets
Token sets
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
will
Token will
Feature activation-0.004
Top resid features:
embrace
Token embrace
Feature activation-0.025
Top resid features:
an
Token an
Feature activation+0.005
Top resid features:
outcome
Token outcome
Feature activation-0.041
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
keeps
Token keeps
Feature activation+4.390
Top resid features:
the
Token the
Feature activation+0.174
Top resid features:
Kings
Token Kings
Feature activation+0.126
Top resid features:
in
Token in
Feature activation+0.036
Top resid features:
Sacramento
Token Sacramento
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.13

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.03

Head 5: 0.08

Head 6: 0.04

Head 7: 0.05

Head 8: 0.06

Head 9: 0.01

Head 10: 0.01

Head 11: 0.51

Positive logits

alive2.12

intact2.08

untouched2.06

unchanged2.02

indefinitely1.90

forever1.82

accountable1.80

afloat1.79

perpetually1.77

ticking1.74

crisp1.73

pristine1.72

ASAP1.71

flowing1.68

sterile1.65

until1.65

uninterrupted1.65

eter1.63

indoors1.62

permanently1.60

Negative logits

haps-1.93

ught-1.70

eatures-1.57

asus-1.54

Cosponsors-1.51

atio-1.50

igraph-1.49

uesday-1.49

equivalents-1.46

requisite-1.45

rossover-1.44

lot-1.42

feasibility-1.41

-1.41

-1.39

occasion-1.37

redemption-1.37

rosso-1.36

enario-1.36

soDeliveryDate-1.36

INTERVAL 4.217 - 4.686
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Americans
Token Americans
Feature activation+4.242
informed
Token informed
Feature activation+0.000
has
Token has
Feature activation+0.000
slipped
Token slipped
Feature activation+0.000
among
Token among
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Aunt
Token Aunt
Feature activation+0.741
May
Token May
Feature activation+4.686
from
Token from
Feature activation+0.394
being
Token being
Feature activation+0.000
ev
Token ev
Feature activation+0.000
icted
Tokenicted
Feature activation+0.000
or
Token or
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
law
Token law
Feature activation+0.000
and
Token and
Feature activation+0.467
order
Token order
Feature activation+4.511
for
Token for
Feature activation+0.548
others
Token others
Feature activation+0.033
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
kept
Token kept
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
y
Tokeny
Feature activation+4.335
,
Token,
Feature activation+0.184
the
Token the
Feature activation+0.000
X
Token X
Feature activation+0.000
-
Token-
Feature activation+0.000
Men
TokenMen
Feature activation+1.219

INTERVAL 3.749 - 4.217
CONTAINS 0.001%

for
Token for
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.494
practice
Token practice
Feature activation+4.182
alive
Token alive
Feature activation+1.020
here
Token here
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
States
Token States
Feature activation+0.000
cooking
Token cooking
Feature activation+0.000
process
Token process
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.801
beans
Token beans
Feature activation+3.892
from
Token from
Feature activation+2.181
soft
Token soft
Feature activation+0.182
ening
Tokenening
Feature activation+0.000
.
Token.
Feature activation+0.000
See
Token See
Feature activation+0.000
I
Token I
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
my
Token my
Feature activation+1.109
family
Token family
Feature activation+3.858
safe
Token safe
Feature activation+0.262
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
proud
Token proud
Feature activation+0.000
-
Token-
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
laws
Token laws
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
governments
Token governments
Feature activation+3.786
honest
Token honest
Feature activation+1.161
and
Token and
Feature activation+0.854
First
Token First
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
governments
Token governments
Feature activation+0.000
is
Token is
Feature activation+0.000
taking
Token taking
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
unwanted
Token unwanted
Feature activation+0.385
migrants
Token migrants
Feature activation+3.768
out
Token out
Feature activation+2.409
of
Token of
Feature activation+0.329
the
Token the
Feature activation+0.282
EU
Token EU
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 3.280 - 3.749
CONTAINS 0.002%

Edward
Token Edward
Feature activation+0.913
ian
Tokenian
Feature activation+0.707
Prom
Token Prom
Feature activation+0.210
en
Tokenen
Feature activation+0.000
ade
Tokenade
Feature activation+3.122
online
Token online
Feature activation+3.666
and
Token and
Feature activation+0.846
a
Token a
Feature activation+0.300
free
Token free
Feature activation+0.000
resource
Token resource
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.704
rest
Token rest
Feature activation+2.487
of
Token of
Feature activation+0.123
us
Token us
Feature activation+3.424
alive
Token alive
Feature activation+0.796
and
Token and
Feature activation+1.452
well
Token well
Feature activation+0.971
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
keep
Token keep
Feature activation+0.000
ones
Token ones
Feature activation+1.938
/
Token/
Feature activation+0.192
tw
Tokentw
Feature activation+0.509
os
Tokenos
Feature activation+3.643
(
Token (
Feature activation+0.000
click
Tokenclick
Feature activation+0.000
again
Token again
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
has
Token has
Feature activation+0.000
kept
Token kept
Feature activation+0.000
local
Token local
Feature activation+1.060
brick
Token brick
Feature activation+1.143
and
Token and
Feature activation+0.000
mortar
Token mortar
Feature activation+3.595
stores
Token stores
Feature activation+3.614
alive
Token alive
Feature activation+1.667
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
keeps
Token keeps
Feature activation+0.400
desp
Token desp
Feature activation+0.963
ots
Tokenots
Feature activation+3.056
and
Token and
Feature activation+0.000
dictators
Token dictators
Feature activation+3.365
awake
Token awake
Feature activation+0.531
at
Token at
Feature activation+0.408
night
Token night
Feature activation+0.000
,
Token,
Feature activation+0.000
what
Token what
Feature activation+0.000

INTERVAL 2.812 - 3.280
CONTAINS 0.003%

they
Token they
Feature activation+0.000
keep
Token keep
Feature activation+0.000
a
Token a
Feature activation+0.103
loaded
Token loaded
Feature activation+0.000
murder
Token murder
Feature activation+2.122
weapon
Token weapon
Feature activation+2.862
between
Token between
Feature activation+1.304
their
Token their
Feature activation+0.000
school
Token school
Feature activation+0.000
books
Tokenbooks
Feature activation+0.186
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
children
Token children
Feature activation+3.017
on
Token on
Feature activation+0.938
their
Token their
Feature activation+0.000
policies
Token policies
Feature activation+0.496
until
Token until
Feature activation+0.000
age
Token age
Feature activation+0.000
working
Token working
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
this
Token this
Feature activation+1.468
deal
Token deal
Feature activation+3.086
as
Token as
Feature activation+1.511
narrow
Token narrow
Feature activation+0.000
as
Token as
Feature activation+0.446
possible
Token possible
Feature activation+0.209
.
Token.
Feature activation+0.000
clock
Token clock
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
tracks
Token tracks
Feature activation+2.915
clear
Token clear
Feature activation+0.639
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
David
TokenDavid
Feature activation+0.000
Mickey
Token Mickey
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
her
Token her
Feature activation+3.006
stumbling
Token stumbling
Feature activation+0.140
backward
Token backward
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
are
Token are
Feature activation+0.000
truly
Token truly
Feature activation+0.000

INTERVAL 2.343 - 2.812
CONTAINS 0.003%

t
Tokent
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
roster
Token roster
Feature activation+0.454
spots
Token spots
Feature activation+2.645
with
Token with
Feature activation+0.342
their
Token their
Feature activation+0.125
organizations
Token organizations
Feature activation+1.130
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
taking
Token taking
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
unwanted
Token unwanted
Feature activation+0.385
migrants
Token migrants
Feature activation+3.768
out
Token out
Feature activation+2.409
of
Token of
Feature activation+0.329
the
Token the
Feature activation+0.282
EU
Token EU
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
repairs
Token repairs
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
systems
Token systems
Feature activation+3.196
running
Token running
Feature activation+2.520
safely
Token safely
Feature activation+0.214
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000
$
Token $
Feature activation+0.000
58
Token58
Feature activation+0.013
million
Token million
Feature activation+1.324
in
Token in
Feature activation+0.529
marijuana
Token marijuana
Feature activation+0.058
revenue
Token revenue
Feature activation+2.644
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Regardless
TokenRegardless
Feature activation+0.000
of
Token of
Feature activation+0.000
fairly
Token fairly
Feature activation+0.000
good
Token good
Feature activation+0.000
job
Token job
Feature activation+0.000
of
Token of
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
Americans
Token Americans
Feature activation+2.546
informed
Token informed
Feature activation+0.000
;
Token;
Feature activation+0.000
among
Token among
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.874 - 2.343
CONTAINS 0.005%

s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
them
Token them
Feature activation+0.874
all
Token all
Feature activation+2.316
straight
Token straight
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.065
pain
Token pain
Feature activation+2.088
alive
Token alive
Feature activation+0.893
in
Token in
Feature activation+0.652
our
Token our
Feature activation+0.000
hearts
Token hearts
Feature activation+0.211
and
Token and
Feature activation+0.000
character
Token character
Feature activation+1.357
rank
Token rank
Feature activation+2.130
and
Token and
Feature activation+0.300
character
Token character
Feature activation+0.000
rib
Token rib
Feature activation+0.000
bons
Tokenbons
Feature activation+2.080
and
Token and
Feature activation+0.000
badges
Token badges
Feature activation+2.261
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
CONT
Token CONT
Feature activation+0.000
ENT
TokenENT
Feature activation+0.000
Help
Token Help
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
Common
Token Common
Feature activation+0.000
Dreams
Token Dreams
Feature activation+2.162
Alive
Token Alive
Feature activation+0.788
Our
Token Our
Feature activation+0.466
progressive
Token progressive
Feature activation+0.000
news
Token news
Feature activation+0.000
model
Token model
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+2.035
safe
Token safe
Feature activation+0.000
from
Token from
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000

INTERVAL 1.406 - 1.874
CONTAINS 0.007%

information
Token information
Feature activation+1.823
flowing
Token flowing
Feature activation+0.066
and
Token and
Feature activation+0.000
our
Token our
Feature activation+0.289
hobby
Token hobby
Feature activation+0.654
growing
Token growing
Feature activation+1.637
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Patrick
TokenPatrick
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
everything
Token everything
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
us
Token us
Feature activation+1.597
out
Token out
Feature activation+0.187
of
Token of
Feature activation+0.000
here
Token here
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
tool
Token tool
Feature activation+0.000
in
Token in
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
music
Token music
Feature activation+1.674
labels
Token labels
Feature activation+1.891
on
Token on
Feature activation+1.674
board
Token board
Feature activation+0.100
with
Token with
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
."
Token."
Feature activation+0.000
All
TokenAll
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
keep
Token keep
Feature activation+0.000
your
Token your
Feature activation+1.159
property
Token property
Feature activation+1.462
intruder
Token intruder
Feature activation+2.415
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+0.150
,
Token,
Feature activation+0.018
or
Token or
Feature activation+0.011
be
Token be
Feature activation+0.000
cruel
Token cruel
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Paul
Token Paul
Feature activation+0.485
in
Token in
Feature activation+1.615
permanent
Token permanent
Feature activation+0.008
confinement
Token confinement
Feature activation+0.232
.
Token.
Feature activation+0.000
Sea
Token Sea
Feature activation+0.000
Life
Token Life
Feature activation+0.000

INTERVAL 0.937 - 1.406
CONTAINS 0.012%

interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
helping
Token helping
Feature activation+0.000
people
Token people
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.955
eyes
Token eyes
Feature activation+0.690
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
screen
Token screen
Feature activation+0.206
to
Token to
Feature activation+0.077
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
keep
Token keep
Feature activation+0.000
your
Token your
Feature activation+1.159
property
Token property
Feature activation+1.462
intruder
Token intruder
Feature activation+2.415
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+0.150
,
Token,
Feature activation+0.018
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
a
Token a
Feature activation+0.414
DACA
Token DACA
Feature activation+0.000
fix
Token fix
Feature activation+3.128
separate
Token separate
Feature activation+1.352
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
must
Token must
Feature activation+0.000
-
Token-
Feature activation+0.000
pass
Tokenpass
Feature activation+0.000
closest
Token closest
Feature activation+0.000
to
Token to
Feature activation+0.000
death
Token death
Feature activation+0.000
is
Token is
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
his
Token his
Feature activation+0.999
ratings
Token ratings
Feature activation+1.919
afloat
Token afloat
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
sought
Token sought
Feature activation+0.000
and
Token and
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
back
Token back
Feature activation+0.000
the
Token the
Feature activation+0.195
cases
Token cases
Feature activation+1.014
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
due
Token due
Feature activation+0.000
for
Token for
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000

INTERVAL 0.469 - 0.937
CONTAINS 0.023%

maximum
Token maximum
Feature activation+0.000
employment
Token employment
Feature activation+0.000
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
long
Token long
Feature activation+0.733
term
Token term
Feature activation+0.922
inflation
Token inflation
Feature activation+2.371
expectation
Token expectation
Feature activation+1.967
well
Token well
Feature activation+2.349
anchored
Token anchored
Feature activation+0.869
.
Token.
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
your
Token your
Feature activation+0.791
identity
Token identity
Feature activation+0.645
close
Token close
Feature activation+0.495
to
Token to
Feature activation+0.655
pocket
Token pocket
Feature activation+0.050
,
Token,
Feature activation+0.000
get
Token get
Feature activation+0.000
around
Token around
Feature activation+0.000
Med
Token Med
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ocre
Tokenocre
Feature activation+0.000
teams
Token teams
Feature activation+0.000
stay
Token stay
Feature activation+0.000
mediocre
Token mediocre
Feature activation+0.722
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
1933
Token 1933
Feature activation+0.000
has
Token has
Feature activation+0.000
become
Token become
Feature activation+0.000
possible
Token possible
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
them
Token them
Feature activation+0.825
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
home
Token home
Feature activation+0.000
aquarium
Token aquarium
Feature activation+0.000
.
Token.
Feature activation+0.000
just
Token just
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
things
Token things
Feature activation+2.838
looking
Token looking
Feature activation+1.722
blue
Token blue
Feature activation+0.699
collar
Token collar
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000

INTERVAL 0.000 - 0.469
CONTAINS 99.944%

at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
stand
Token stand
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.000
routine
Token routine
Feature activation+0.000
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
Fill
Token Fill
Feature activation+0.000
more
Tokenmore
Feature activation+0.000
theater
Token theater
Feature activation+0.000
ends
Token ends
Feature activation+0.000
meet
Token meet
Feature activation+0.000
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Wilson
TokenWilson
Feature activation+0.000
worked
Token worked
Feature activation+0.000
extensively
Token extensively
Feature activation+0.000
in
Token in
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
an
Token an
Feature activation+0.362
eye
Token eye
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
skies
Token skies
Feature activation+0.119
.
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
In
TokenIn
Feature activation+0.000
other
Token other
Feature activation+0.000
words
Token words
Feature activation+0.000
,
Token,
Feature activation+0.000
doing
Token doing
Feature activation+0.000
business
Token business
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
aware
Token aware
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
VERY
Token VERY
Feature activation+0.000
CLE
Token CLE
Feature activation+0.000
AR
TokenAR
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 H6.11: (feature 21294)

TOP ACTIVATIONS
MAX = 4.309

him
Token him
Feature activation+0.000
before
Token before
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
it
Token it
Feature activation+4.309
ring
Token ring
Feature activation+2.464
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
then
Token then
Feature activation+0.000
I
Token I
Feature activation+0.000
lobbyists
Token lobbyists
Feature activation+0.000
and
Token and
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
let
Token let
Feature activation+0.000
them
Token them
Feature activation+4.079
stew
Token stew
Feature activation+0.757
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
my
Token my
Feature activation+2.747
reps
Token reps
Feature activation+3.952
handle
Token handle
Feature activation+1.672
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
went
Token went
Feature activation+0.000
rather
Token rather
Feature activation+0.000
City
Token City
Feature activation+0.000
of
Token of
Feature activation+0.000
Petersburg
Token Petersburg
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
everybody
Token everybody
Feature activation+3.920
know
Token know
Feature activation+1.242
that
Token that
Feature activation+0.111
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
here
Token here
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
let
Token let
Feature activation+0.000
this
Token this
Feature activation+3.670
guy
Token guy
Feature activation+3.713
/
Token/
Feature activation+0.000
these
Tokenthese
Feature activation+0.000
guys
Token guys
Feature activation+2.732
know
Token know
Feature activation+0.749
that
Token that
Feature activation+0.061
then
Token then
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
let
Token let
Feature activation+0.000
this
Token this
Feature activation+3.670
guy
Token guy
Feature activation+3.713
/
Token/
Feature activation+0.000
these
Tokenthese
Feature activation+0.000
guys
Token guys
Feature activation+2.732
know
Token know
Feature activation+0.749
John
Token John
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
son
Tokenson
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
that
Token that
Feature activation+3.613
deep
Token deep
Feature activation+1.356
conflict
Token conflict
Feature activation+2.357
of
Token of
Feature activation+0.000
interest
Token interest
Feature activation+0.926
sink
Token sink
Feature activation+1.828
business
Token business
Feature activation+0.000
of
Token of
Feature activation+0.000
letting
Token letting
Feature activation+0.000
the
Token the
Feature activation+2.219
big
Token big
Feature activation+0.831
guy
Token guy
Feature activation+3.608
win
Token win
Feature activation+1.631
,
Token,
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
finding
Token finding
Feature activation+0.000
yeast
Token yeast
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
that
Token that
Feature activation+3.177
get
Token get
Feature activation+3.534
...
Token...
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Gr
TokenGr
Feature activation+0.000
',
Token',
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
everything
Token everything
Feature activation+3.528
continue
Token continue
Feature activation+0.892
its
Token its
Feature activation+0.000
course
Token course
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+0.000
section
Tokensection
Feature activation+0.000
of
Token of
Feature activation+0.000
society
Token society
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.062
them
Token them
Feature activation+3.480
outline
Token outline
Feature activation+0.112
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
felt
Token felt
Feature activation+0.000
ought
Token ought
Feature activation+0.000
the
Token the
Feature activation+0.000
routine
Token routine
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+2.034
child
Token child
Feature activation+3.433
know
Token know
Feature activation+0.208
in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
choosing
Token choosing
Feature activation+0.000
by
Token by
Feature activation+0.000
letting
Token letting
Feature activation+0.000
it
Token it
Feature activation+3.424
drop
Token drop
Feature activation+0.219
âĢĵ
Token âĢĵ
Feature activation+0.000
powering
Token powering
Feature activation+0.000
the
Token the
Feature activation+0.000
prope
Token prope
Feature activation+0.000
sit
Token sit
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.019
it
Token it
Feature activation+3.411
take
Token take
Feature activation+2.381
you
Token you
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Twice
Token Twice
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
Ch
Token Ch
Feature activation+0.322
urnal
Tokenurnal
Feature activation+2.545
ism
Tokenism
Feature activation+3.390
run
Token run
Feature activation+1.027
on
Token on
Feature activation+0.867
any
Token any
Feature activation+0.000
site
Token site
Feature activation+0.000
with
Token with
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.526
their
Token their
Feature activation+2.025
deep
Token deep
Feature activation+0.000
prospect
Token prospect
Feature activation+0.069
pool
Token pool
Feature activation+3.384
do
Token do
Feature activation+2.688
the
Token the
Feature activation+0.170
talking
Token talking
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
possible
Token possible
Feature activation+0.000
21
Token 21
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
that
Token that
Feature activation+3.362
sink
Token sink
Feature activation+1.143
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
F
Token F
Feature activation+0.000
OUR
TokenOUR
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+3.345
get
Token get
Feature activation+1.080
possessed
Token possessed
Feature activation+0.349
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
angel
Token angel
Feature activation+0.213
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
let
Token let
Feature activation+0.031
it
Token it
Feature activation+3.340
set
Token set
Feature activation+1.078
for
Token for
Feature activation+0.288
15
Token 15
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
action
Token action
Feature activation+0.000
,
Token,
Feature activation+0.000
letting
Token letting
Feature activation+0.000
rumours
Token rumours
Feature activation+3.298
spread
Token spread
Feature activation+0.526
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
departure
Token departure
Feature activation+0.000
from
Token from
Feature activation+0.000

Top DFA by src position
MAX = 5.382

to
Token to
Feature activation+0.013
Top resid features:
him
Token him
Feature activation-0.006
Top resid features:
before
Token before
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.021
Top resid features:
I
Token I
Feature activation+0.032
Top resid features:
let
Token let
Feature activation+5.382
Top resid features:
it
Token it
Feature activation+0.109
Top resid features:
ring
Token ring
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
ies
Tokenies
Feature activation-0.015
Top resid features:
lobbyists
Token lobbyists
Feature activation-0.116
Top resid features:
and
Token and
Feature activation+0.074
Top resid features:
Tony
Token Tony
Feature activation-0.002
Top resid features:
Abbott
Token Abbott
Feature activation-0.001
Top resid features:
let
Token let
Feature activation+5.212
Top resid features:
them
Token them
Feature activation-0.003
Top resid features:
stew
Token stew
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
Rend
Token Rend
Feature activation-0.020
Top resid features:
ezvous
Tokenezvous
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.020
Top resid features:
I
Token I
Feature activation-0.028
Top resid features:
let
Token let
Feature activation+5.114
Top resid features:
my
Token my
Feature activation+0.037
Top resid features:
reps
Token reps
Feature activation+0.031
Top resid features:
handle
Token handle
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
City
Token City
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Petersburg
Token Petersburg
Feature activation-0.076
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
let
Token let
Feature activation+5.070
Top resid features:
everybody
Token everybody
Feature activation-0.016
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
're
Token're
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
then
Token then
Feature activation+0.005
Top resid features:
maybe
Token maybe
Feature activation-0.009
Top resid features:
I
Token I
Feature activation-0.036
Top resid features:
can
Token can
Feature activation+0.011
Top resid features:
let
Token let
Feature activation+4.745
Top resid features:
this
Token this
Feature activation+0.039
Top resid features:
guy
Token guy
Feature activation+0.005
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
these
Tokenthese
Feature activation+0.000
Top resid features:
guys
Token guys
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
maybe
Token maybe
Feature activation-0.037
Top resid features:
I
Token I
Feature activation-0.088
Top resid features:
can
Token can
Feature activation-0.007
Top resid features:
let
Token let
Feature activation+4.815
Top resid features:
this
Token this
Feature activation+0.095
Top resid features:
guy
Token guy
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
these
Tokenthese
Feature activation+0.000
Top resid features:
guys
Token guys
Feature activation+0.000
Top resid features:
ble
Tokenble
Feature activation+0.007
Top resid features:
John
Token John
Feature activation+0.002
Top resid features:
Paul
Token Paul
Feature activation-0.002
Top resid features:
son
Tokenson
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.058
Top resid features:
Let
Token Let
Feature activation+4.533
Top resid features:
that
Token that
Feature activation+0.084
Top resid features:
deep
Token deep
Feature activation+0.000
Top resid features:
conflict
Token conflict
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
interest
Token interest
Feature activation+0.000
Top resid features:
)
Token)
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.031
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
business
Token business
Feature activation-0.016
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
letting
Token letting
Feature activation+4.499
Top resid features:
the
Token the
Feature activation+0.177
Top resid features:
big
Token big
Feature activation+0.001
Top resid features:
guy
Token guy
Feature activation+0.060
Top resid features:
win
Token win
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
added
Token added
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
yeast
Token yeast
Feature activation-0.023
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
I
Token I
Feature activation+0.016
Top resid features:
let
Token let
Feature activation+4.569
Top resid features:
that
Token that
Feature activation-0.031
Top resid features:
get
Token get
Feature activation+0.033
Top resid features:
...
Token...
Feature activation+0.000
Top resid features:
Read
Token Read
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
scandal
Token scandal
Feature activation+0.006
Top resid features:
',
Token',
Feature activation+0.002
Top resid features:
at
Token at
Feature activation+0.011
Top resid features:
first
Token first
Feature activation-0.035
Top resid features:
I
Token I
Feature activation-0.012
Top resid features:
let
Token let
Feature activation+4.510
Top resid features:
everything
Token everything
Feature activation+0.031
Top resid features:
continue
Token continue
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
section
Tokensection
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
society
Token society
Feature activation+0.158
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
let
Token let
Feature activation+4.239
Top resid features:
them
Token them
Feature activation+0.189
Top resid features:
outline
Token outline
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:
felt
Token felt
Feature activation+0.000
Top resid features:
changes
Token changes
Feature activation+0.067
Top resid features:
in
Token in
Feature activation+0.015
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
routine
Token routine
Feature activation+0.067
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
let
Token let
Feature activation+4.674
Top resid features:
the
Token the
Feature activation+0.100
Top resid features:
child
Token child
Feature activation-0.123
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
advance
Token advance
Feature activation+0.000
Top resid features:
moment
Token moment
Feature activation+0.047
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
your
Token your
Feature activation-0.027
Top resid features:
choosing
Token choosing
Feature activation-0.045
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
letting
Token letting
Feature activation+4.409
Top resid features:
it
Token it
Feature activation+0.016
Top resid features:
drop
Token drop
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
powering
Token powering
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
sit
Token sit
Feature activation+0.024
Top resid features:
back
Token back
Feature activation+0.030
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
let
Token let
Feature activation+4.152
Top resid features:
it
Token it
Feature activation+0.110
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
affiliates
Token affiliates
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
ability
Token ability
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
let
Token let
Feature activation+4.763
Top resid features:
Ch
Token Ch
Feature activation-0.093
Top resid features:
urnal
Tokenurnal
Feature activation-0.183
Top resid features:
ism
Tokenism
Feature activation-0.013
Top resid features:
run
Token run
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Jets
Token Jets
Feature activation-0.018
Top resid features:
are
Token are
Feature activation-0.018
Top resid features:
prepared
Token prepared
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
let
Token let
Feature activation+4.268
Top resid features:
their
Token their
Feature activation+0.224
Top resid features:
deep
Token deep
Feature activation-0.040
Top resid features:
prospect
Token prospect
Feature activation+0.105
Top resid features:
pool
Token pool
Feature activation-0.025
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
possible
Token possible
Feature activation+0.007
Top resid features:
21
Token 21
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
Let
Token Let
Feature activation+4.206
Top resid features:
that
Token that
Feature activation+0.101
Top resid features:
sink
Token sink
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+0.000
Top resid features:
lied
Token lied
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
me
Token me
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
you
Token you
Feature activation-0.014
Top resid features:
let
Token let
Feature activation+4.112
Top resid features:
me
Token me
Feature activation+0.042
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
possessed
Token possessed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.045
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation-0.028
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
only
Token only
Feature activation+0.242
Top resid features:
let
Token let
Feature activation+3.981
Top resid features:
it
Token it
Feature activation+0.053
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
minutes
Token minutes
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
industrial
Token industrial
Feature activation+0.010
Top resid features:
action
Token action
Feature activation+0.021
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
letting
Token letting
Feature activation+4.286
Top resid features:
rumours
Token rumours
Feature activation-0.012
Top resid features:
spread
Token spread
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
departure
Token departure
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.02

Head 2: 0.03

Head 3: 0.04

Head 4: 0.05

Head 5: 0.07

Head 6: 0.05

Head 7: 0.04

Head 8: 0.08

Head 9: 0.02

Head 10: 0.02

Head 11: 0.50

Positive logits

expire1.94

unfold1.89

shine1.79

grow1.76

flourish1.73

lapse1.65

continue1.56

decide1.55

prevail1.54

proceed1.54

juices1.53

resume1.53

grow1.52

crumble1.52

perish1.51

wraps1.50

suffice1.49

breathe1.49

gaze1.47

slide1.46

Negative logits

etheless-1.63

-1.53

Ranked-1.52

oly-1.47

-1.47

SB-1.41

-1.41

ット-1.39

liest-1.38

furt-1.37

degree-1.34

acea-1.34

-1.34

ALSE-1.31

loss-1.30

OST-1.30

Physical-1.29

ultimate-1.29

(),-1.26

ttp-1.26

INTERVAL 3.878 - 4.309
CONTAINS 0.000%

,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
my
Token my
Feature activation+2.747
reps
Token reps
Feature activation+3.952
handle
Token handle
Feature activation+1.672
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
went
Token went
Feature activation+0.000
rather
Token rather
Feature activation+0.000
him
Token him
Feature activation+0.000
before
Token before
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
it
Token it
Feature activation+4.309
ring
Token ring
Feature activation+2.464
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
then
Token then
Feature activation+0.000
I
Token I
Feature activation+0.000
City
Token City
Feature activation+0.000
of
Token of
Feature activation+0.000
Petersburg
Token Petersburg
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
everybody
Token everybody
Feature activation+3.920
know
Token know
Feature activation+1.242
that
Token that
Feature activation+0.111
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
here
Token here
Feature activation+0.000
lobbyists
Token lobbyists
Feature activation+0.000
and
Token and
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
let
Token let
Feature activation+0.000
them
Token them
Feature activation+4.079
stew
Token stew
Feature activation+0.757
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.447 - 3.878
CONTAINS 0.001%

yeast
Token yeast
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
that
Token that
Feature activation+3.177
get
Token get
Feature activation+3.534
...
Token...
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Gr
TokenGr
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
let
Token let
Feature activation+0.000
this
Token this
Feature activation+3.670
guy
Token guy
Feature activation+3.713
/
Token/
Feature activation+0.000
these
Tokenthese
Feature activation+0.000
guys
Token guys
Feature activation+2.732
know
Token know
Feature activation+0.749
that
Token that
Feature activation+0.061
John
Token John
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
son
Tokenson
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
that
Token that
Feature activation+3.613
deep
Token deep
Feature activation+1.356
conflict
Token conflict
Feature activation+2.357
of
Token of
Feature activation+0.000
interest
Token interest
Feature activation+0.926
sink
Token sink
Feature activation+1.828
',
Token',
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
everything
Token everything
Feature activation+3.528
continue
Token continue
Feature activation+0.892
its
Token its
Feature activation+0.000
course
Token course
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+0.000
then
Token then
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
let
Token let
Feature activation+0.000
this
Token this
Feature activation+3.670
guy
Token guy
Feature activation+3.713
/
Token/
Feature activation+0.000
these
Tokenthese
Feature activation+0.000
guys
Token guys
Feature activation+2.732
know
Token know
Feature activation+0.749

INTERVAL 3.016 - 3.447
CONTAINS 0.002%

If
TokenIf
Feature activation+0.000
voters
Token voters
Feature activation+0.000
agree
Token agree
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
Colorado
Token Colorado
Feature activation+3.065
spend
Token spend
Feature activation+1.975
the
Token the
Feature activation+0.000
tax
Token tax
Feature activation+0.000
money
Token money
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+3.345
get
Token get
Feature activation+1.080
possessed
Token possessed
Feature activation+0.349
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
angel
Token angel
Feature activation+0.213
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
let
Token let
Feature activation+0.031
it
Token it
Feature activation+3.340
set
Token set
Feature activation+1.078
for
Token for
Feature activation+0.288
15
Token 15
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
or
Token or
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
choosing
Token choosing
Feature activation+0.000
by
Token by
Feature activation+0.000
letting
Token letting
Feature activation+0.000
it
Token it
Feature activation+3.424
drop
Token drop
Feature activation+0.219
âĢĵ
Token âĢĵ
Feature activation+0.000
powering
Token powering
Feature activation+0.000
the
Token the
Feature activation+0.000
prope
Token prope
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
while
Token while
Feature activation+0.000
letting
Token letting
Feature activation+0.000
it
Token it
Feature activation+3.023
rip
Token rip
Feature activation+0.278
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
ranges
Token ranges
Feature activation+0.000

INTERVAL 2.585 - 3.016
CONTAINS 0.003%

.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
we
Token we
Feature activation+0.000
let
Token let
Feature activation+0.000
Tim
Token Tim
Feature activation+2.529
have
Token have
Feature activation+2.898
that
Token that
Feature activation+0.000
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
ago
Token ago
Feature activation+0.000
as
Token as
Feature activation+0.000
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+1.280
defense
Token defense
Feature activation+1.148
view
Token view
Feature activation+2.635
the
Token the
Feature activation+0.000
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+0.000
video
Token video
Feature activation+0.000
in
Token in
Feature activation+0.000
foam
Token foam
Feature activation+0.000
bats
Token bats
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
your
Token your
Feature activation+2.085
friends
Token friends
Feature activation+2.997
take
Token take
Feature activation+1.290
a
Token a
Feature activation+0.686
few
Token few
Feature activation+0.000
swings
Token swings
Feature activation+0.000
.
Token.
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
Alert
TokenAlert
Feature activation+0.000
!
Token!
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+2.982
know
Token know
Feature activation+0.594
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
ribbon
Token ribbon
Feature activation+0.000
notification
Token notification
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
team
Token team
Feature activation+0.000
let
Token let
Feature activation+0.000
those
Token those
Feature activation+1.846
babies
Token babies
Feature activation+2.926
make
Token make
Feature activation+0.993
babies
Token babies
Feature activation+0.532
,
Token,
Feature activation+0.061
then
Token then
Feature activation+0.000
let
Token let
Feature activation+0.000

INTERVAL 2.155 - 2.585
CONTAINS 0.005%

with
Token with
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
your
Token your
Feature activation+1.380
veterinarian
Token veterinarian
Feature activation+2.162
know
Token know
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
camping
Token camping
Feature activation+0.000
location
Token location
Feature activation+0.000
our
Token our
Feature activation+0.000
cities
Token cities
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+2.686
player
Token player
Feature activation+2.416
fly
Token fly
Feature activation+0.631
between
Token between
Feature activation+0.000
them
Token them
Feature activation+0.000
and
Token and
Feature activation+0.000
revisit
Token revisit
Feature activation+0.000
the
Token the
Feature activation+0.000
parents
Token parents
Feature activation+0.000
who
Token who
Feature activation+0.000
let
Token let
Feature activation+0.000
your
Token your
Feature activation+0.165
kids
Token kids
Feature activation+2.493
play
Token play
Feature activation+0.188
these
Token these
Feature activation+0.000
sick
Token sick
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
spring
Token spring
Feature activation+0.000
let
Token let
Feature activation+0.000
people
Token people
Feature activation+2.218
speak
Token speak
Feature activation+1.389
freely
Token freely
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
fabulous
Token fabulous
Feature activation+0.000
sponsors
Token sponsors
Feature activation+0.000
.
Token.
Feature activation+0.000
Please
Token Please
Feature activation+0.000
let
Token let
Feature activation+0.000
us
Token us
Feature activation+2.431
know
Token know
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
any
Token any
Feature activation+0.000

INTERVAL 1.724 - 2.155
CONTAINS 0.004%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+1.946
through
Token through
Feature activation+0.000
;
Token;
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
gone
Token gone
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+1.690
ad
Tokenad
Feature activation+2.077
ferment
Token ferment
Feature activation+0.883
fully
Token fully
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
do
Token do
Feature activation+0.000
blew
Token blew
Feature activation+0.000
that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
let
Token let
Feature activation+0.000
all
Token all
Feature activation+2.010
the
Token the
Feature activation+0.739
Max
Token Max
Feature activation+0.000
imus
Tokenimus
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
routine
Token routine
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+2.034
child
Token child
Feature activation+3.433
know
Token know
Feature activation+0.208
in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+0.000
.
Token.
Feature activation+0.000
mountains
Token mountains
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
freedom
Token freedom
Feature activation+2.064
ring
Token ring
Feature activation+0.748
!
Token!
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.293 - 1.724
CONTAINS 0.005%

Def
TokenDef
Feature activation+0.000
initely
Tokeninitely
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
let
Token let
Feature activation+0.000
you
Token you
Feature activation+1.652
know
Token know
Feature activation+0.000
what
Token what
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
said
Token said
Feature activation+0.000
(
Token (
Feature activation+0.000
if
Tokenif
Feature activation+0.000
frozen
Token frozen
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
let
Token let
Feature activation+0.000
it
Token it
Feature activation+1.700
melt
Token melt
Feature activation+1.230
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
skillet
Token skillet
Feature activation+0.000
and
Token and
Feature activation+1.244
the
Token the
Feature activation+2.960
answers
Token answers
Feature activation+2.455
to
Token to
Feature activation+0.000
these
Token these
Feature activation+0.000
questions
Token questions
Feature activation+1.132
slip
Token slip
Feature activation+1.574
away
Token away
Feature activation+0.733
from
Token from
Feature activation+0.000
us
Token us
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sadness
Token sadness
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
let
Token let
Feature activation+0.000
you
Token you
Feature activation+1.711
all
Token all
Feature activation+2.582
know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.000
David
Token David
Feature activation+0.000
's
Token's
Feature activation+0.000
involved
Token involved
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
m
Token m
Feature activation+0.671
be
Token be
Feature activation+1.679
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
actual
Token actual
Feature activation+0.000
RAM
Token RAM
Feature activation+0.000

INTERVAL 0.862 - 1.293
CONTAINS 0.008%

had
Token had
Feature activation+0.000
let
Token let
Feature activation+0.000
out
Token out
Feature activation+0.300
for
Token for
Feature activation+0.479
the
Token the
Feature activation+0.000
day
Token day
Feature activation+1.180
Oct
Token Oct
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
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
let
Token let
Feature activation+0.000
the
Token the
Feature activation+1.099
rain
Token rain
Feature activation+1.238
stop
Token stop
Feature activation+1.341
them
Token them
Feature activation+0.000
either
Token either
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.220
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.039
say
Token say
Feature activation+0.000
it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.000
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.000
let
Token let
Feature activation+0.000
Ch
Token Ch
Feature activation+0.322
urnal
Tokenurnal
Feature activation+2.545
ism
Tokenism
Feature activation+3.390
run
Token run
Feature activation+1.027
on
Token on
Feature activation+0.867
any
Token any
Feature activation+0.000
site
Token site
Feature activation+0.000
with
Token with
Feature activation+0.000
news
Token news
Feature activation+0.000
or
Token or
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
let
Token let
Feature activation+0.000
your
Token your
Feature activation+1.776
fingers
Token fingers
Feature activation+2.519
stop
Token stop
Feature activation+1.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
timer
Token timer
Feature activation+0.000
is
Token is
Feature activation+0.000
running
Token running
Feature activation+0.000

INTERVAL 0.431 - 0.862
CONTAINS 0.012%

Factor
Token Factor
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
Prime
Token Prime
Feature activation+0.721
Division
Token Division
Feature activation+1.188
teach
Token teach
Feature activation+2.301
you
Token you
Feature activation+0.103
the
Token the
Feature activation+0.000
fun
Token fun
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.445
start
Token start
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
down
Token down
Feature activation+0.000
m
Token m
Feature activation+0.000
accordingly
Token accordingly
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
T
Token T
Feature activation+0.462
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
suitable
Token suitable
Feature activation+0.000
length
Token length
Feature activation+0.000
of
Token of
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.205
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.388
put
Token put
Feature activation+0.282
it
Token it
Feature activation+0.511
behind
Token behind
Feature activation+0.000
us
Token us
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.471
give
Token give
Feature activation+0.000
this
Token this
Feature activation+0.001
a
Token a
Feature activation+0.029
live
Token live
Feature activation+0.000
audience
Token audience
Feature activation+0.000

INTERVAL 0.000 - 0.431
CONTAINS 99.960%

âĢĶ
Token âĢĶ
Feature activation+0.000
chemicals
Token chemicals
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
cause
Token cause
Feature activation+0.000
algae
Token algae
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
lake
Token lake
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fair
Token fair
Feature activation+0.000
price
Token price
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
launch
Token launch
Feature activation+0.000
will
Token will
Feature activation+0.000
country
Token country
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
feud
Token feud
Feature activation+0.000
with
Token with
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
Arabia
Token Arabia
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
regional
Token regional
Feature activation+0.000
nations
Token nations
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
doubts
Token doubts
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
now
Token now
Feature activation+0.000
all
Token all
Feature activation+0.000
you
Token you
Feature activation+0.000
see
Token see
Feature activation+0.000
is
Token is
Feature activation+0.000
),
Token),
Feature activation+0.000
then
Token then
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
is
Token is
Feature activation+0.000
compounded
Token compounded
Feature activation+0.000
extensively
Token extensively
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
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 H6.11: (feature 11065)

TOP ACTIVATIONS
MAX = 2.970

businesses
Token businesses
Feature activation+0.000
offer
Token offer
Feature activation+0.000
meaningful
Token meaningful
Feature activation+0.000
employment
Token employment
Feature activation+0.000
at
Token at
Feature activation+0.000
living
Token living
Feature activation+2.970
wages
Token wages
Feature activation+1.686
,
Token,
Feature activation+0.542
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Gonz
Token Gonz
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
it
Token it
Feature activation+0.715
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.194
s
Tokens
Feature activation+2.790
peak
Token peak
Feature activation+0.000
Wo
Token Wo
Feature activation+0.000
W
TokenW
Feature activation+0.000
maintained
Token maintained
Feature activation+0.000
12
Token 12
Feature activation+0.000
K
Token K
Feature activation+0.000
lay
Tokenlay
Feature activation+0.000
men
Tokenmen
Feature activation+0.144
âĢ
TokenâĢ
Feature activation+0.141
Ļ
TokenĻ
Feature activation+0.935
s
Tokens
Feature activation+2.774
rally
Token rally
Feature activation+0.371
,
Token,
Feature activation+0.331
Lac
Token Lac
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
ara
Tokenara
Feature activation+0.000
Today
TokenToday
Feature activation+0.000
at
Token at
Feature activation+0.000
Apple
Token Apple
Feature activation+0.215
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.750
WW
Token WW
Feature activation+0.000
DC
TokenDC
Feature activation+0.000
event
Token event
Feature activation+0.000
in
Token in
Feature activation+0.000
San
Token San
Feature activation+0.000
are
Token are
Feature activation+0.000
encouraging
Token encouraging
Feature activation+0.000
:
Token:
Feature activation+0.000
At
Token At
Feature activation+0.000
Tech
Token Tech
Feature activation+0.224
Crunch
TokenCrunch
Feature activation+2.639
,
Token,
Feature activation+2.184
the
Token the
Feature activation+0.125
movement
Token movement
Feature activation+0.000
to
Token to
Feature activation+0.000
require
Token require
Feature activation+0.000
go
Token go
Feature activation+0.000
at
Token at
Feature activation+0.000
season
Token season
Feature activation+0.936
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.028
s
Tokens
Feature activation+2.630
end
Token end
Feature activation+1.103
in
Token in
Feature activation+0.000
favor
Token favor
Feature activation+0.000
of
Token of
Feature activation+0.000
Chad
Token Chad
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
so
Token so
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+2.251
own
Token own
Feature activation+2.490
peril
Token peril
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
operating
Token operating
Feature activation+0.000
system
Token system
Feature activation+0.000
pe
Tokenpe
Feature activation+0.000
is
Token is
Feature activation+0.000
sold
Token sold
Feature activation+0.000
at
Token at
Feature activation+0.000
substantially
Token substantially
Feature activation+1.040
higher
Token higher
Feature activation+2.468
prices
Token prices
Feature activation+0.000
than
Token than
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
beer
Token beer
Feature activation+0.000
,
Token,
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
at
Token at
Feature activation+0.000
each
Token each
Feature activation+0.639
and
Token and
Feature activation+0.000
every
Token every
Feature activation+2.376
Grand
Token Grand
Feature activation+0.000
Prix
Token Prix
Feature activation+0.021
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
does
Token does
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
military
Token military
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
,
Token,
Feature activation+2.375
inventory
Token inventory
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Manny
Token Manny
Feature activation+0.000
Car
Token Car
Feature activation+0.000
val
Tokenval
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Here
TokenHere
Feature activation+0.000
at
Token at
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
Media
Token Media
Feature activation+0.000
we
Token we
Feature activation+2.333
pride
Token pride
Feature activation+0.192
ourselves
Token ourselves
Feature activation+0.000
at
Token at
Feature activation+0.000
being
Token being
Feature activation+0.268
advocates
Token advocates
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
at
Token at
Feature activation+0.000
premier
Token premier
Feature activation+0.891
tournaments
Token tournaments
Feature activation+2.324
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
,
Token,
Feature activation+0.000
Aram
Token Aram
Feature activation+0.000
b
Tokenb
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
January
Token January
Feature activation+1.617
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.460
s
Tokens
Feature activation+2.314
General
Token General
Feature activation+0.000
Meeting
Token Meeting
Feature activation+0.090
,
Token,
Feature activation+0.506
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+0.000
to
Token to
Feature activation+0.000
purchase
Token purchase
Feature activation+0.000
firearms
Token firearms
Feature activation+0.000
at
Token at
Feature activation+0.000
break
Token break
Feature activation+0.000
neck
Tokenneck
Feature activation+2.278
pace
Token pace
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
reality
Token reality
Feature activation+0.000
has
Token has
Feature activation+0.000
world
Token world
Feature activation+0.000
more
Token more
Feature activation+0.000
intertwined
Token intertwined
Feature activation+0.000
than
Token than
Feature activation+0.000
at
Token at
Feature activation+0.365
any
Token any
Feature activation+2.264
time
Token time
Feature activation+0.151
in
Token in
Feature activation+0.063
human
Token human
Feature activation+0.512
history
Token history
Feature activation+0.000
,"
Token,"
Feature activation+0.000
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.670
school
Token school
Feature activation+2.260
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
practices
Token practices
Feature activation+0.000
include
Token include
Feature activation+0.000
:
Token:
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
so
Token so
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+2.251
own
Token own
Feature activation+2.490
peril
Token peril
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
operating
Token operating
Feature activation+0.000
between
Token between
Feature activation+0.000
promotions
Token promotions
Feature activation+0.000
,
Token,
Feature activation+0.000
time
Token time
Feature activation+0.000
at
Token at
Feature activation+0.066
current
Token current
Feature activation+2.215
job
Token job
Feature activation+0.906
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
nation
Token nation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
at
Token at
Feature activation+0.224
the
Token the
Feature activation+2.204
expense
Token expense
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+0.000
nations
Token nations
Feature activation+0.000
that
Token that
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
'
Token'
Feature activation+0.000
union
Token union
Feature activation+0.000
at
Token at
Feature activation+0.000
Host
Token Host
Feature activation+0.295
ess
Tokeness
Feature activation+2.204
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
:
Token:
Feature activation+0.000

Top DFA by src position
MAX = 3.766

abis
Tokenabis
Feature activation-0.006
Top resid features:
businesses
Token businesses
Feature activation-0.002
Top resid features:
offer
Token offer
Feature activation-0.016
Top resid features:
meaningful
Token meaningful
Feature activation-0.002
Top resid features:
employment
Token employment
Feature activation-0.044
Top resid features:
at
Token at
Feature activation+3.765
Top resid features:
living
Token living
Feature activation+0.020
Top resid features:
wages
Token wages
Feature activation+0.000
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:
fifth
Token fifth
Feature activation+0.005
Top resid features:
on
Token on
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
way
Token way
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
At
Token At
Feature activation+3.487
Top resid features:
it
Token it
Feature activation+0.072
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
s
Tokens
Feature activation-0.027
Top resid features:
peak
Token peak
Feature activation+0.000
Top resid features:
!
Token!
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ŀ
TokenĿ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
At
TokenAt
Feature activation+3.766
Top resid features:
K
Token K
Feature activation-0.081
Top resid features:
lay
Tokenlay
Feature activation+0.005
Top resid features:
men
Tokenmen
Feature activation-0.036
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
Clancy
Token Clancy
Feature activation-0.004
Top resid features:
games
Token games
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.011
Top resid features:
Today
TokenToday
Feature activation-0.034
Top resid features:
at
Token at
Feature activation+3.703
Top resid features:
Apple
Token Apple
Feature activation-0.109
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation-0.016
Top resid features:
s
Tokens
Feature activation-0.050
Top resid features:
WW
Token WW
Feature activation+0.000
Top resid features:
Their
Token Their
Feature activation+0.001
Top resid features:
results
Token results
Feature activation-0.016
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
encouraging
Token encouraging
Feature activation-0.016
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
At
Token At
Feature activation+3.448
Top resid features:
Tech
Token Tech
Feature activation-0.020
Top resid features:
Crunch
TokenCrunch
Feature activation-0.033
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
movement
Token movement
Feature activation+0.000
Top resid features:
Mason
Token Mason
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
promptly
Token promptly
Feature activation-0.009
Top resid features:
let
Token let
Feature activation-0.012
Top resid features:
go
Token go
Feature activation+0.030
Top resid features:
at
Token at
Feature activation+3.197
Top resid features:
season
Token season
Feature activation+0.120
Top resid features:
âĢ
TokenâĢ
Feature activation+0.047
Top resid features:
Ļ
TokenĻ
Feature activation+0.025
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
but
Token but
Feature activation+0.008
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
do
Token do
Feature activation+0.080
Top resid features:
so
Token so
Feature activation+0.014
Top resid features:
at
Token at
Feature activation+2.907
Top resid features:
your
Token your
Feature activation+0.151
Top resid features:
own
Token own
Feature activation+0.007
Top resid features:
peril
Token peril
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Red
Token Red
Feature activation-0.007
Top resid features:
Stri
Token Stri
Feature activation+0.000
Top resid features:
pe
Tokenpe
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.046
Top resid features:
sold
Token sold
Feature activation+0.028
Top resid features:
at
Token at
Feature activation+3.166
Top resid features:
substantially
Token substantially
Feature activation-0.004
Top resid features:
higher
Token higher
Feature activation+0.021
Top resid features:
prices
Token prices
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
domestic
Token domestic
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
show
Token show
Feature activation-0.001
Top resid features:
his
Token his
Feature activation-0.005
Top resid features:
extraordinary
Token extraordinary
Feature activation-0.002
Top resid features:
abilities
Token abilities
Feature activation-0.002
Top resid features:
at
Token at
Feature activation+3.080
Top resid features:
each
Token each
Feature activation+0.055
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
every
Token every
Feature activation-0.010
Top resid features:
Grand
Token Grand
Feature activation+0.000
Top resid features:
Prix
Token Prix
Feature activation+0.000
Top resid features:
Stanley
Token Stanley
Feature activation-0.003
Top resid features:
said
Token said
Feature activation-0.025
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
At
TokenAt
Feature activation+3.207
Top resid features:
Veterans
Token Veterans
Feature activation-0.004
Top resid features:
Village
Token Village
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
which
Token which
Feature activation+0.014
Top resid features:
provides
Token provides
Feature activation-0.052
Top resid features:
TING
TokenTING
Feature activation+0.000
Top resid features:
B
Token B
Feature activation-0.000
Top resid features:
ISON
TokenISON
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.012
Top resid features:
Here
TokenHere
Feature activation-0.018
Top resid features:
at
Token at
Feature activation+3.128
Top resid features:
Sun
Token Sun
Feature activation-0.023
Top resid features:
Media
Token Media
Feature activation-0.012
Top resid features:
we
Token we
Feature activation-0.046
Top resid features:
pride
Token pride
Feature activation+0.000
Top resid features:
ourselves
Token ourselves
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
does
Token does
Feature activation+0.010
Top resid features:
drugs
Token drugs
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
including
Token including
Feature activation-0.040
Top resid features:
at
Token at
Feature activation+2.972
Top resid features:
premier
Token premier
Feature activation+0.056
Top resid features:
tournaments
Token tournaments
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.004
Top resid features:
month
Token month
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
At
TokenAt
Feature activation+2.987
Top resid features:
January
Token January
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation-0.014
Top resid features:
General
Token General
Feature activation+0.000
Top resid features:
Americans
Token Americans
Feature activation-0.016
Top resid features:
continue
Token continue
Feature activation-0.055
Top resid features:
to
Token to
Feature activation-0.017
Top resid features:
purchase
Token purchase
Feature activation-0.028
Top resid features:
firearms
Token firearms
Feature activation-0.003
Top resid features:
at
Token at
Feature activation+2.976
Top resid features:
break
Token break
Feature activation+0.101
Top resid features:
neck
Tokenneck
Feature activation-0.005
Top resid features:
pace
Token pace
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
world
Token world
Feature activation+0.012
Top resid features:
more
Token more
Feature activation+0.021
Top resid features:
intertwined
Token intertwined
Feature activation-0.001
Top resid features:
than
Token than
Feature activation-0.050
Top resid features:
at
Token at
Feature activation+2.966
Top resid features:
any
Token any
Feature activation+0.003
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
human
Token human
Feature activation+0.000
Top resid features:
history
Token history
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
implement
Token implement
Feature activation-0.022
Top resid features:
vigorous
Token vigorous
Feature activation+0.019
Top resid features:
cybersecurity
Token cybersecurity
Feature activation-0.015
Top resid features:
practices
Token practices
Feature activation+0.031
Top resid features:
at
Token at
Feature activation+2.866
Top resid features:
home
Token home
Feature activation-0.047
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
work
Token work
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
and
Token and
Feature activation+0.095
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
but
Token but
Feature activation+0.007
Top resid features:
you
Token you
Feature activation-0.000
Top resid features:
do
Token do
Feature activation+0.091
Top resid features:
so
Token so
Feature activation+0.024
Top resid features:
at
Token at
Feature activation+2.773
Top resid features:
your
Token your
Feature activation+0.058
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
peril
Token peril
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.005
Top resid features:
between
Token between
Feature activation+0.038
Top resid features:
promotions
Token promotions
Feature activation+0.017
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
time
Token time
Feature activation+0.055
Top resid features:
at
Token at
Feature activation+2.783
Top resid features:
current
Token current
Feature activation+0.035
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
number
Token number
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.005
Top resid features:
nation
Token nation
Feature activation+0.015
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
but
Token but
Feature activation-0.019
Top resid features:
not
Token not
Feature activation+0.141
Top resid features:
at
Token at
Feature activation+2.869
Top resid features:
the
Token the
Feature activation-0.049
Top resid features:
expense
Token expense
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
nations
Token nations
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Team
Token Team
Feature activation-0.013
Top resid features:
sters
Tokensters
Feature activation+0.010
Top resid features:
'
Token'
Feature activation+0.001
Top resid features:
union
Token union
Feature activation-0.006
Top resid features:
at
Token at
Feature activation+3.008
Top resid features:
Host
Token Host
Feature activation-0.025
Top resid features:
ess
Tokeness
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.04

Head 2: 0.02

Head 3: 0.02

Head 4: 0.03

Head 5: 0.07

Head 6: 0.03

Head 7: 0.05

Head 8: 0.10

Head 9: 0.02

Head 10: 0.01

Head 11: 0.49

Positive logits

expense2.11

behest1.97

level1.65

mble1.56

levels1.53

intervals1.51

doorstep1.51

tips1.50

speeds1.49

Jav1.47

checkout1.43

detriment1.43

checkpoints1.42

disposal1.40

td1.39

Compare1.38

crossings1.38

gatherings1.35

trib1.35

intersections1.35

Negative logits

hower-1.62

icter-1.53

zsche-1.50

ocus-1.47

etheless-1.37

arnaev-1.34

Taken-1.28

resignation-1.26

ensical-1.26

escription-1.25

ief-1.24

into-1.24

faded-1.22

CARD-1.21

redes-1.21

��-1.20

��-1.19

APTER-1.17

Tile-1.16

redistributed-1.16

INTERVAL 2.673 - 2.970
CONTAINS 0.000%

businesses
Token businesses
Feature activation+0.000
offer
Token offer
Feature activation+0.000
meaningful
Token meaningful
Feature activation+0.000
employment
Token employment
Feature activation+0.000
at
Token at
Feature activation+0.000
living
Token living
Feature activation+2.970
wages
Token wages
Feature activation+1.686
,
Token,
Feature activation+0.542
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Gonz
Token Gonz
Feature activation+0.000
Today
TokenToday
Feature activation+0.000
at
Token at
Feature activation+0.000
Apple
Token Apple
Feature activation+0.215
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.750
WW
Token WW
Feature activation+0.000
DC
TokenDC
Feature activation+0.000
event
Token event
Feature activation+0.000
in
Token in
Feature activation+0.000
San
Token San
Feature activation+0.000
K
Token K
Feature activation+0.000
lay
Tokenlay
Feature activation+0.000
men
Tokenmen
Feature activation+0.144
âĢ
TokenâĢ
Feature activation+0.141
Ļ
TokenĻ
Feature activation+0.935
s
Tokens
Feature activation+2.774
rally
Token rally
Feature activation+0.371
,
Token,
Feature activation+0.331
Lac
Token Lac
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
ara
Tokenara
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
it
Token it
Feature activation+0.715
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.194
s
Tokens
Feature activation+2.790
peak
Token peak
Feature activation+0.000
Wo
Token Wo
Feature activation+0.000
W
TokenW
Feature activation+0.000
maintained
Token maintained
Feature activation+0.000
12
Token 12
Feature activation+0.000

INTERVAL 2.376 - 2.673
CONTAINS 0.001%

go
Token go
Feature activation+0.000
at
Token at
Feature activation+0.000
season
Token season
Feature activation+0.936
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.028
s
Tokens
Feature activation+2.630
end
Token end
Feature activation+1.103
in
Token in
Feature activation+0.000
favor
Token favor
Feature activation+0.000
of
Token of
Feature activation+0.000
Chad
Token Chad
Feature activation+0.000
are
Token are
Feature activation+0.000
encouraging
Token encouraging
Feature activation+0.000
:
Token:
Feature activation+0.000
At
Token At
Feature activation+0.000
Tech
Token Tech
Feature activation+0.224
Crunch
TokenCrunch
Feature activation+2.639
,
Token,
Feature activation+2.184
the
Token the
Feature activation+0.125
movement
Token movement
Feature activation+0.000
to
Token to
Feature activation+0.000
require
Token require
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
at
Token at
Feature activation+0.000
each
Token each
Feature activation+0.639
and
Token and
Feature activation+0.000
every
Token every
Feature activation+2.376
Grand
Token Grand
Feature activation+0.000
Prix
Token Prix
Feature activation+0.021
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
does
Token does
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
so
Token so
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+2.251
own
Token own
Feature activation+2.490
peril
Token peril
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
operating
Token operating
Feature activation+0.000
system
Token system
Feature activation+0.000
pe
Tokenpe
Feature activation+0.000
is
Token is
Feature activation+0.000
sold
Token sold
Feature activation+0.000
at
Token at
Feature activation+0.000
substantially
Token substantially
Feature activation+1.040
higher
Token higher
Feature activation+2.468
prices
Token prices
Feature activation+0.000
than
Token than
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
beer
Token beer
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.079 - 2.376
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
January
Token January
Feature activation+1.617
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.460
s
Tokens
Feature activation+2.314
General
Token General
Feature activation+0.000
Meeting
Token Meeting
Feature activation+0.090
,
Token,
Feature activation+0.506
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+0.000
game
Token game
Feature activation+0.000
at
Token at
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.749
w
Tokenw
Feature activation+0.981
icket
Tokenicket
Feature activation+2.120
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
military
Token military
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
,
Token,
Feature activation+2.375
inventory
Token inventory
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Manny
Token Manny
Feature activation+0.000
Car
Token Car
Feature activation+0.000
val
Tokenval
Feature activation+0.000
responsible
Token responsible
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
at
Token at
Feature activation+0.122
the
Token the
Feature activation+2.198
cost
Token cost
Feature activation+0.267
of
Token of
Feature activation+0.000
not
Token not
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+0.000
between
Token between
Feature activation+0.000
promotions
Token promotions
Feature activation+0.000
,
Token,
Feature activation+0.000
time
Token time
Feature activation+0.000
at
Token at
Feature activation+0.066
current
Token current
Feature activation+2.215
job
Token job
Feature activation+0.906
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.782 - 2.079
CONTAINS 0.004%

can
Token can
Feature activation+0.000
see
Token see
Feature activation+0.000
that
Token that
Feature activation+0.000
at
Token at
Feature activation+0.000
large
Token large
Feature activation+0.938
numbers
Token numbers
Feature activation+2.035
,
Token,
Feature activation+0.511
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
igm
Tokenigm
Feature activation+0.000
oid
Tokenoid
Feature activation+0.000
varying
Token varying
Feature activation+0.000
locations
Token locations
Feature activation+0.000
and
Token and
Feature activation+0.000
at
Token at
Feature activation+0.000
inf
Token inf
Feature activation+0.439
requent
Tokenrequent
Feature activation+1.823
intervals
Token intervals
Feature activation+0.000
.
Token.
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
other
Token other
Feature activation+0.000
digital
Token digital
Feature activation+0.000
wallets
Token wallets
Feature activation+0.000
at
Token at
Feature activation+0.000
other
Token other
Feature activation+1.111
bitcoin
Token bitcoin
Feature activation+1.995
exchanges
Token exchanges
Feature activation+0.000
to
Token to
Feature activation+0.000
which
Token which
Feature activation+0.000
only
Token only
Feature activation+0.000
he
Token he
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
is
Token is
Feature activation+0.000
evaluated
Token evaluated
Feature activation+0.000
at
Token at
Feature activation+0.000
object
Token object
Feature activation+1.342
creation
Token creation
Feature activation+1.934
time
Token time
Feature activation+0.556
@
Token @
Feature activation+0.000
field
Tokenfield
Feature activation+0.273
'
Token '
Feature activation+0.000
created
Tokencreated
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.662
grass
Tokengrass
Feature activation+0.234
,
Token,
Feature activation+0.376
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+2.065
par
Tokenpar
Feature activation+0.000
agus
Tokenagus
Feature activation+0.000
has
Token has
Feature activation+0.000
historically
Token historically
Feature activation+0.000
been
Token been
Feature activation+0.000

INTERVAL 1.485 - 1.782
CONTAINS 0.007%

Beijing
Token Beijing
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+1.533
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
seem
Token seem
Feature activation+0.000
ENCE
TokenENCE
Feature activation+2.129
,
Token,
Feature activation+0.000
HOR
Token HOR
Feature activation+0.000
ROR
TokenROR
Feature activation+1.030
,
Token,
Feature activation+1.258
AND
Token AND
Feature activation+1.668
DE
Token DE
Feature activation+0.000
ATH
TokenATH
Feature activation+1.544
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
latest
Token latest
Feature activation+0.000
spat
Token spat
Feature activation+0.000
coming
Token coming
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.692
bizarre
Token bizarre
Feature activation+1.532
intersection
Token intersection
Feature activation+0.000
of
Token of
Feature activation+0.000
pop
Token pop
Feature activation+0.000
culture
Token culture
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
Lawrence
Token Lawrence
Feature activation+0.000
[
Token [
Feature activation+0.023
A
TokenA
Feature activation+0.000
venue
Tokenvenue
Feature activation+0.000
],
Token],
Feature activation+1.676
people
Token people
Feature activation+0.408
will
Token will
Feature activation+0.037
just
Token just
Feature activation+0.000
roll
Token roll
Feature activation+0.000
through
Token through
Feature activation+0.000
at
Token at
Feature activation+0.000
next
Token next
Feature activation+1.155
week
Token week
Feature activation+1.189
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.751
Google
Token Google
Feature activation+0.000
I
Token I
Feature activation+0.000
/
Token/
Feature activation+0.000
O
TokenO
Feature activation+0.000
developer
Token developer
Feature activation+0.172

INTERVAL 1.188 - 1.485
CONTAINS 0.016%

can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
at
Token at
Feature activation+0.000
around
Token around
Feature activation+0.217
60
Token 60
Feature activation+0.164
percent
Token percent
Feature activation+1.370
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Across
TokenAcross
Feature activation+0.000
Guinea
Token Guinea
Feature activation+0.000
in
Token in
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.853
frightening
Token frightening
Feature activation+1.117
ly
Tokenly
Feature activation+0.842
specific
Token specific
Feature activation+1.469
time
Token time
Feature activation+0.180
of
Token of
Feature activation+0.000
day
Token day
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
time
Token time
Feature activation+0.000
in
Token in
Feature activation+0.000
prison
Token prison
Feature activation+0.000
or
Token or
Feature activation+0.000
at
Token at
Feature activation+0.202
a
Token a
Feature activation+1.365
youth
Token youth
Feature activation+0.400
facility
Token facility
Feature activation+0.044
.
Token.
Feature activation+0.000
âĢĭ
TokenâĢĭ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
coast
Token coast
Feature activation+0.000
at
Token at
Feature activation+0.000
H
Token H
Feature activation+0.000
umb
Tokenumb
Feature activation+0.000
old
Tokenold
Feature activation+0.000
t
Tokent
Feature activation+1.404
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
key
Token key
Feature activation+0.000
to
Token to
Feature activation+0.000
California
Token California
Feature activation+0.000
inter
Tokeninter
Feature activation+0.000
Cell
Token Cell
Feature activation+0.000
at
Token at
Feature activation+0.000
New
Token New
Feature activation+0.779
Reg
Token Reg
Feature activation+0.152
ency
Tokenency
Feature activation+1.308
with
Token with
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
Hardy
Token Hardy
Feature activation+0.000
attached
Token attached
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.891 - 1.188
CONTAINS 0.025%

a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.000
fun
Token fun
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+0.941
expense
Token expense
Feature activation+0.000
.
Token.
Feature activation+0.000
Dress
Token Dress
Feature activation+0.000
up
Token up
Feature activation+0.000
like
Token like
Feature activation+0.000
by
Token by
Feature activation+0.000
f
Token f
Feature activation+0.000
MRI
TokenMRI
Feature activation+0.000
at
Token at
Feature activation+0.000
two
Token two
Feature activation+0.937
critical
Token critical
Feature activation+1.176
points
Token points
Feature activation+0.000
-
Token -
Feature activation+0.000
when
Token when
Feature activation+0.000
subjects
Token subjects
Feature activation+0.000
tried
Token tried
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
by
Token by
Feature activation+0.000
f
Token f
Feature activation+0.000
MRI
TokenMRI
Feature activation+0.000
at
Token at
Feature activation+0.000
two
Token two
Feature activation+0.937
critical
Token critical
Feature activation+1.176
points
Token points
Feature activation+0.000
-
Token -
Feature activation+0.000
when
Token when
Feature activation+0.000
subjects
Token subjects
Feature activation+0.000
much
Token much
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.249
best
Token best
Feature activation+0.083
of
Token of
Feature activation+0.987
times
Token times
Feature activation+0.654
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
researchers
Token researchers
Feature activation+0.000
froze
Token froze
Feature activation+0.000
agricultural
Token agricultural
Feature activation+0.000
yields
Token yields
Feature activation+0.000
at
Token at
Feature activation+0.000
1961
Token 1961
Feature activation+1.111
levels
Token levels
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
population
Token population
Feature activation+0.000

INTERVAL 0.594 - 0.891
CONTAINS 0.051%

the
Token the
Feature activation+0.000
emission
Token emission
Feature activation+0.000
of
Token of
Feature activation+0.000
radiation
Token radiation
Feature activation+0.000
at
Token at
Feature activation+0.000
high
Token high
Feature activation+0.672
temperatures
Token temperatures
Feature activation+0.555
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
advance
Token advance
Feature activation+0.000
that
Token that
Feature activation+0.000
damage
Token damage
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
gun
Token gun
Feature activation+0.000
at
Token at
Feature activation+0.000
100
Token 100
Feature activation+0.773
%.
Token%.
Feature activation+0.000
Don
Token Don
Feature activation+0.000
't
Token't
Feature activation+0.000
call
Token call
Feature activation+0.000
people
Token people
Feature activation+0.000
still
Token still
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.283
28
Token 28
Feature activation+0.000
th
Tokenth
Feature activation+0.437
overall
Token overall
Feature activation+0.813
selection
Token selection
Feature activation+0.390
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
the
Token the
Feature activation+0.000
draft
Token draft
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
been
Token been
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.661
top
Token top
Feature activation+0.058
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
polls
Token polls
Feature activation+0.000
since
Token since
Feature activation+0.000
at
Token at
Feature activation+0.000
Jesse
Token Jesse
Feature activation+0.000
J
Token J
Feature activation+0.000
.
Token.
Feature activation+0.000
McC
Token McC
Feature activation+0.000
rary
Tokenrary
Feature activation+0.662
Jr
Token Jr
Feature activation+0.973
.
Token.
Feature activation+0.489
Elementary
Token Elementary
Feature activation+0.500
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.297 - 0.594
CONTAINS 0.095%

match
Token match
Feature activation+0.000
at
Token at
Feature activation+0.000
Women
Token Women
Feature activation+0.000
's
Token's
Feature activation+0.205
Euro
Token Euro
Feature activation+0.000
2017
Token 2017
Feature activation+0.537
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Samp
Token Samp
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
conference
Token conference
Feature activation+0.000
last
Token last
Feature activation+0.000
December
Token December
Feature activation+0.817
,
Token,
Feature activation+0.566
Sach
Token Sach
Feature activation+0.000
in
Tokenin
Feature activation+0.000
Bans
Token Bans
Feature activation+0.000
al
Tokenal
Feature activation+0.000
,
Token,
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.772
Central
Token Central
Feature activation+0.004
(
Token (
Feature activation+0.000
Community
TokenCommunity
Feature activation+0.000
College
Token College
Feature activation+0.000
)
Token)
Feature activation+0.565
that
Token that
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
into
Token into
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
material
Token material
Feature activation+0.000
was
Token was
Feature activation+0.000
seized
Token seized
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.315
address
Token address
Feature activation+0.000
in
Token in
Feature activation+0.000
San
Token San
Feature activation+0.000
Ro
Token Ro
Feature activation+0.000
que
Tokenque
Feature activation+0.000
into
Token into
Feature activation+0.000
service
Token service
Feature activation+0.000
at
Token at
Feature activation+0.000
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+1.420
agencies
Token agencies
Feature activation+0.552
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
common
Token common
Feature activation+0.000
wealth
Tokenwealth
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.297
CONTAINS 99.799%

we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
testing
Token testing
Feature activation+0.000
on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
local
Token local
Feature activation+0.000
laptop
Token laptop
Feature activation+0.000
for
Token for
Feature activation+0.000
photo
Token photo
Feature activation+0.000
,
Token,
Feature activation+0.000
Suzanne
Token Suzanne
Feature activation+0.000
Meredith
Token Meredith
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
Wal
Token Wal
Feature activation+0.000
pole
Tokenpole
Feature activation+0.000
,
Token,
Feature activation+0.000
Mass
Token Mass
Feature activation+0.000
.,
Token.,
Feature activation+0.000
rear
Token rear
Feature activation+0.000
view
Token view
Feature activation+0.000
mirrors
Token mirrors
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
D
Token D
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
governor
Token governor
Feature activation+0.000
's
Token's
Feature activation+0.000
association
Token association
Feature activation+0.000
with
Token with
Feature activation+0.000
A
Token A
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
player
Token player
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
and
Token and
Feature activation+0.000
move
Token move
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 H6.11: (feature 1388)

TOP ACTIVATIONS
MAX = 5.756

gigantic
Token gigantic
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.376
Pink
Token Pink
Feature activation+1.154
er
Tokener
Feature activation+4.632
is
Token is
Feature activation+5.756
eventually
Token eventually
Feature activation+1.581
reduced
Token reduced
Feature activation+0.440
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Get
TokenGet
Feature activation+0.000
the
Token the
Feature activation+0.000
who
Token who
Feature activation+3.022
follow
Token follow
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
closely
Token closely
Feature activation+0.543
were
Token were
Feature activation+5.748
unaware
Token unaware
Feature activation+0.654
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
changes
Token changes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
Dom
Token Dom
Feature activation+2.554
P
Token P
Feature activation+0.890
agn
Tokenagn
Feature activation+1.035
otti
Tokenotti
Feature activation+5.721
was
Token was
Feature activation+5.054
afraid
Token afraid
Feature activation+1.896
!
Token!
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
bl
Token bl
Feature activation+0.000
ued
Tokenued
Feature activation+0.000
steel
Token steel
Feature activation+0.296
guys
Token guys
Feature activation+0.621
can
Token can
Feature activation+5.265
appreciate
Token appreciate
Feature activation+1.690
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
Dom
Token Dom
Feature activation+2.554
P
Token P
Feature activation+0.890
agn
Tokenagn
Feature activation+1.035
otti
Tokenotti
Feature activation+5.721
was
Token was
Feature activation+5.054
afraid
Token afraid
Feature activation+1.896
!
Token!
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
It
TokenIt
Feature activation+0.000
said
Token said
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+2.155
CBI
Token CBI
Feature activation+1.568
had
Token had
Feature activation+5.015
not
Token not
Feature activation+4.356
properly
Token properly
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
a
Token a
Feature activation+0.000
probe
Token probe
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
election
Token election
Feature activation+0.000
are
Token are
Feature activation+4.864
finding
Token finding
Feature activation+1.712
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
home
Token home
Feature activation+0.000
Even
Token Even
Feature activation+0.000
The
Token The
Feature activation+0.968
New
Token New
Feature activation+0.053
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+2.270
is
Token is
Feature activation+4.759
exploring
Token exploring
Feature activation+0.677
challenging
Token challenging
Feature activation+0.275
the
Token the
Feature activation+0.328
First
Token First
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
so
Token so
Feature activation+0.000
gigantic
Token gigantic
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.376
Pink
Token Pink
Feature activation+1.154
er
Tokener
Feature activation+4.632
is
Token is
Feature activation+5.756
eventually
Token eventually
Feature activation+1.581
reduced
Token reduced
Feature activation+0.440
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Get
TokenGet
Feature activation+0.000
unintended
Token unintended
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
desp
Token desp
Feature activation+0.000
ots
Tokenots
Feature activation+4.609
know
Token know
Feature activation+2.982
that
Token that
Feature activation+0.079
locking
Token locking
Feature activation+0.000
up
Token up
Feature activation+0.000
mouth
Token mouth
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
election
Token election
Feature activation+0.000
are
Token are
Feature activation+4.588
finding
Token finding
Feature activation+1.643
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
home
Token home
Feature activation+0.000
who
Token who
Feature activation+2.683
once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.115
are
Token are
Feature activation+4.587
now
Token now
Feature activation+2.501
calling
Token calling
Feature activation+0.821
for
Token for
Feature activation+0.000
action
Token action
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.046
that
Token that
Feature activation+3.730
site
Token site
Feature activation+3.415
was
Token was
Feature activation+4.432
not
Token not
Feature activation+4.051
open
Token open
Feature activation+2.688
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
said
Token said
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+2.155
CBI
Token CBI
Feature activation+1.568
had
Token had
Feature activation+5.015
not
Token not
Feature activation+4.356
properly
Token properly
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
a
Token a
Feature activation+0.000
probe
Token probe
Feature activation+0.000
into
Token into
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+4.356
official
Token official
Feature activation+1.677
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
warts
Tokenwarts
Feature activation+4.228
who
Token who
Feature activation+1.928
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
warts
Tokenwarts
Feature activation+4.072
who
Token who
Feature activation+2.308
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
economists
Token economists
Feature activation+4.071
who
Token who
Feature activation+2.683
once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.115
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.046
that
Token that
Feature activation+3.730
site
Token site
Feature activation+3.415
was
Token was
Feature activation+4.432
not
Token not
Feature activation+4.051
open
Token open
Feature activation+2.688
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
for
Token for
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
Sanders
Token Sanders
Feature activation+2.127
supporters
Token supporters
Feature activation+3.999
agree
Token agree
Feature activation+1.115
that
Token that
Feature activation+0.021
's
Token's
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 6.491

violence
Token violence
Feature activation-0.025
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
so
Token so
Feature activation-0.010
Top resid features:
gigantic
Token gigantic
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
even
Token even
Feature activation+6.491
Top resid features:
Pink
Token Pink
Feature activation+0.125
Top resid features:
er
Tokener
Feature activation+0.075
Top resid features:
is
Token is
Feature activation+0.077
Top resid features:
eventually
Token eventually
Feature activation+0.000
Top resid features:
reduced
Token reduced
Feature activation+0.000
Top resid features:
so
Token so
Feature activation-0.004
Top resid features:
little
Token little
Feature activation+0.026
Top resid features:
fan
Token fan
Feature activation-0.003
Top resid features:
fare
Tokenfare
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.185
Top resid features:
even
Token even
Feature activation+6.114
Top resid features:
lawyers
Token lawyers
Feature activation-0.043
Top resid features:
who
Token who
Feature activation+0.048
Top resid features:
follow
Token follow
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
issue
Token issue
Feature activation+0.035
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
head
Token head
Feature activation+0.006
Top resid features:
!
Token!
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Even
TokenEven
Feature activation+6.368
Top resid features:
Dom
Token Dom
Feature activation+0.170
Top resid features:
P
Token P
Feature activation+0.026
Top resid features:
agn
Tokenagn
Feature activation-0.010
Top resid features:
otti
Tokenotti
Feature activation+0.063
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
tactical
Token tactical
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
practical
Token practical
Feature activation+0.030
Top resid features:
that
Token that
Feature activation+0.059
Top resid features:
even
Token even
Feature activation+5.753
Top resid features:
the
Token the
Feature activation+0.111
Top resid features:
most
Token most
Feature activation-0.107
Top resid features:
die
Token die
Feature activation-0.004
Top resid features:
hard
Token hard
Feature activation-0.017
Top resid features:
wal
Token wal
Feature activation+0.010
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
head
Token head
Feature activation-0.000
Top resid features:
!
Token!
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Even
TokenEven
Feature activation+5.704
Top resid features:
Dom
Token Dom
Feature activation+0.067
Top resid features:
P
Token P
Feature activation+0.040
Top resid features:
agn
Tokenagn
Feature activation+0.009
Top resid features:
otti
Tokenotti
Feature activation+0.152
Top resid features:
was
Token was
Feature activation+0.049
Top resid features:
itation
Tokenitation
Feature activation+0.001
Top resid features:
fees
Token fees
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
It
TokenIt
Feature activation-0.015
Top resid features:
said
Token said
Feature activation-0.057
Top resid features:
even
Token even
Feature activation+5.822
Top resid features:
the
Token the
Feature activation+0.100
Top resid features:
CBI
Token CBI
Feature activation+0.096
Top resid features:
had
Token had
Feature activation-0.020
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
properly
Token properly
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
riding
Token riding
Feature activation+0.007
Top resid features:
level
Token level
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
Even
Token Even
Feature activation+4.924
Top resid features:
campaign
Token campaign
Feature activation+0.050
Top resid features:
stal
Token stal
Feature activation+0.047
Top resid features:
warts
Tokenwarts
Feature activation+0.067
Top resid features:
who
Token who
Feature activation+0.036
Top resid features:
show
Token show
Feature activation+0.090
Top resid features:
rise
Token rise
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
cyber
Token cyber
Feature activation+0.006
Top resid features:
repression
Token repression
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Even
Token Even
Feature activation+5.427
Top resid features:
The
Token The
Feature activation+0.038
Top resid features:
New
Token New
Feature activation+0.008
Top resid features:
York
Token York
Feature activation-0.033
Top resid features:
Times
Token Times
Feature activation+0.065
Top resid features:
is
Token is
Feature activation+0.057
Top resid features:
violence
Token violence
Feature activation-0.018
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
so
Token so
Feature activation+0.013
Top resid features:
gigantic
Token gigantic
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.086
Top resid features:
even
Token even
Feature activation+5.114
Top resid features:
Pink
Token Pink
Feature activation+0.332
Top resid features:
er
Tokener
Feature activation+0.037
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
eventually
Token eventually
Feature activation+0.000
Top resid features:
reduced
Token reduced
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.018
Top resid features:
wholly
Token wholly
Feature activation+0.002
Top resid features:
unintended
Token unintended
Feature activation+0.031
Top resid features:
consequences
Token consequences
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Even
Token Even
Feature activation+5.163
Top resid features:
desp
Token desp
Feature activation+0.137
Top resid features:
ots
Tokenots
Feature activation+0.090
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
locking
Token locking
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
riding
Token riding
Feature activation+0.009
Top resid features:
level
Token level
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Even
Token Even
Feature activation+4.702
Top resid features:
campaign
Token campaign
Feature activation+0.031
Top resid features:
stal
Token stal
Feature activation+0.053
Top resid features:
warts
Tokenwarts
Feature activation+0.043
Top resid features:
who
Token who
Feature activation+0.032
Top resid features:
show
Token show
Feature activation+0.101
Top resid features:
it
Token it
Feature activation-0.002
Top resid features:
's
Token's
Feature activation-0.006
Top resid features:
no
Token no
Feature activation-0.003
Top resid features:
surprise
Token surprise
Feature activation-0.051
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
even
Token even
Feature activation+4.813
Top resid features:
economists
Token economists
Feature activation+0.069
Top resid features:
who
Token who
Feature activation+0.127
Top resid features:
once
Token once
Feature activation+0.146
Top resid features:
backed
Token backed
Feature activation+0.167
Top resid features:
George
Token George
Feature activation+0.007
Top resid features:
week
Token week
Feature activation-0.018
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
2016
Token 2016
Feature activation+0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.012
Top resid features:
and
Token and
Feature activation-0.066
Top resid features:
even
Token even
Feature activation+5.159
Top resid features:
that
Token that
Feature activation+0.126
Top resid features:
site
Token site
Feature activation-0.085
Top resid features:
was
Token was
Feature activation+0.026
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
itation
Tokenitation
Feature activation+0.001
Top resid features:
fees
Token fees
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
It
TokenIt
Feature activation-0.001
Top resid features:
said
Token said
Feature activation-0.051
Top resid features:
even
Token even
Feature activation+5.238
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
CBI
Token CBI
Feature activation+0.112
Top resid features:
had
Token had
Feature activation+0.010
Top resid features:
not
Token not
Feature activation-0.087
Top resid features:
properly
Token properly
Feature activation+0.000
Top resid features:
ne
Tokenne
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
).
Token).
Feature activation-0.022
Top resid features:
As
Token As
Feature activation-0.048
Top resid features:
even
Token even
Feature activation+5.189
Top resid features:
the
Token the
Feature activation+0.173
Top resid features:
official
Token official
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
riding
Token riding
Feature activation+0.004
Top resid features:
level
Token level
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Even
Token Even
Feature activation+5.025
Top resid features:
campaign
Token campaign
Feature activation-0.019
Top resid features:
stal
Token stal
Feature activation+0.042
Top resid features:
warts
Tokenwarts
Feature activation+0.058
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
riding
Token riding
Feature activation-0.000
Top resid features:
level
Token level
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Even
Token Even
Feature activation+4.828
Top resid features:
campaign
Token campaign
Feature activation-0.043
Top resid features:
stal
Token stal
Feature activation+0.030
Top resid features:
warts
Tokenwarts
Feature activation+0.053
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
no
Token no
Feature activation-0.003
Top resid features:
surprise
Token surprise
Feature activation+0.003
Top resid features:
that
Token that
Feature activation-0.006
Top resid features:
even
Token even
Feature activation+4.720
Top resid features:
economists
Token economists
Feature activation+0.137
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
once
Token once
Feature activation+0.000
Top resid features:
backed
Token backed
Feature activation+0.000
Top resid features:
George
Token George
Feature activation+0.000
Top resid features:
week
Token week
Feature activation-0.012
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
2016
Token 2016
Feature activation+0.006
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.022
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
even
Token even
Feature activation+4.893
Top resid features:
that
Token that
Feature activation+0.105
Top resid features:
site
Token site
Feature activation-0.105
Top resid features:
was
Token was
Feature activation-0.075
Top resid features:
not
Token not
Feature activation+0.039
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.014
Top resid features:
map
Token map
Feature activation+0.013
Top resid features:
for
Token for
Feature activation+0.014
Top resid features:
Clinton
Token Clinton
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Even
Token Even
Feature activation+4.539
Top resid features:
Sanders
Token Sanders
Feature activation+0.274
Top resid features:
supporters
Token supporters
Feature activation+0.037
Top resid features:
agree
Token agree
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.04

Head 2: 0.02

Head 3: 0.07

Head 4: 0.03

Head 5: 0.06

Head 6: 0.04

Head 7: 0.05

Head 8: 0.06

Head 9: 0.02

Head 10: 0.02

Head 11: 0.49

Positive logits

marginally1.95

concedes1.90

occasionally1.80

still1.75

technically1.71

curs1.67

nonetheless1.67

barely1.65

admits1.65

admit1.64

staunch1.62

modest1.60

doubted1.60

still1.57

nevertheless1.55

spared1.54

occasional1.54

doub1.50

considering1.49

survives1.49

Negative logits

isodes-1.71

ptoms-1.68

potion-1.62

onica-1.62

zsche-1.56

masse-1.55

ories-1.50

rex-1.50

-1.46

metry-1.45

oleon-1.42

owship-1.42

ollah-1.41

=>-1.39

ahi-1.39

opter-1.39

WOOD-1.38

_______-1.38

Featured-1.37

umbn-1.37

INTERVAL 5.180 - 5.756
CONTAINS 0.000%

and
Token and
Feature activation+0.000
bl
Token bl
Feature activation+0.000
ued
Tokenued
Feature activation+0.000
steel
Token steel
Feature activation+0.296
guys
Token guys
Feature activation+0.621
can
Token can
Feature activation+5.265
appreciate
Token appreciate
Feature activation+1.690
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
who
Token who
Feature activation+3.022
follow
Token follow
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
closely
Token closely
Feature activation+0.543
were
Token were
Feature activation+5.748
unaware
Token unaware
Feature activation+0.654
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
changes
Token changes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
Dom
Token Dom
Feature activation+2.554
P
Token P
Feature activation+0.890
agn
Tokenagn
Feature activation+1.035
otti
Tokenotti
Feature activation+5.721
was
Token was
Feature activation+5.054
afraid
Token afraid
Feature activation+1.896
!
Token!
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
gigantic
Token gigantic
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.376
Pink
Token Pink
Feature activation+1.154
er
Tokener
Feature activation+4.632
is
Token is
Feature activation+5.756
eventually
Token eventually
Feature activation+1.581
reduced
Token reduced
Feature activation+0.440
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Get
TokenGet
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 4.605 - 5.180
CONTAINS 0.001%

Even
TokenEven
Feature activation+0.000
Dom
Token Dom
Feature activation+2.554
P
Token P
Feature activation+0.890
agn
Tokenagn
Feature activation+1.035
otti
Tokenotti
Feature activation+5.721
was
Token was
Feature activation+5.054
afraid
Token afraid
Feature activation+1.896
!
Token!
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
It
TokenIt
Feature activation+0.000
said
Token said
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+2.155
CBI
Token CBI
Feature activation+1.568
had
Token had
Feature activation+5.015
not
Token not
Feature activation+4.356
properly
Token properly
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
a
Token a
Feature activation+0.000
probe
Token probe
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
election
Token election
Feature activation+0.000
are
Token are
Feature activation+4.864
finding
Token finding
Feature activation+1.712
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
home
Token home
Feature activation+0.000
so
Token so
Feature activation+0.000
gigantic
Token gigantic
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.376
Pink
Token Pink
Feature activation+1.154
er
Tokener
Feature activation+4.632
is
Token is
Feature activation+5.756
eventually
Token eventually
Feature activation+1.581
reduced
Token reduced
Feature activation+0.440
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Get
TokenGet
Feature activation+0.000
unintended
Token unintended
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
desp
Token desp
Feature activation+0.000
ots
Tokenots
Feature activation+4.609
know
Token know
Feature activation+2.982
that
Token that
Feature activation+0.079
locking
Token locking
Feature activation+0.000
up
Token up
Feature activation+0.000
mouth
Token mouth
Feature activation+0.000

INTERVAL 4.029 - 4.605
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+4.356
official
Token official
Feature activation+1.677
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
who
Token who
Feature activation+2.683
once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.115
are
Token are
Feature activation+4.587
now
Token now
Feature activation+2.501
calling
Token calling
Feature activation+0.821
for
Token for
Feature activation+0.000
action
Token action
Feature activation+0.000
to
Token to
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
economists
Token economists
Feature activation+4.071
who
Token who
Feature activation+2.683
once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.115
said
Token said
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+2.155
CBI
Token CBI
Feature activation+1.568
had
Token had
Feature activation+5.015
not
Token not
Feature activation+4.356
properly
Token properly
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
a
Token a
Feature activation+0.000
probe
Token probe
Feature activation+0.000
into
Token into
Feature activation+0.000
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
warts
Tokenwarts
Feature activation+4.072
who
Token who
Feature activation+2.308
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000

INTERVAL 3.454 - 4.029
CONTAINS 0.002%

little
Token little
Feature activation+0.000
fan
Token fan
Feature activation+0.000
fare
Tokenfare
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
lawyers
Token lawyers
Feature activation+3.655
who
Token who
Feature activation+3.022
follow
Token follow
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
closely
Token closely
Feature activation+0.543
which
Token which
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.996
Pun
Token Pun
Feature activation+0.000
isher
Tokenisher
Feature activation+1.435
can
Token can
Feature activation+3.844
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.769
kill
Token kill
Feature activation+0.381
people
Token people
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
chang
Token chang
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+3.887
was
Token was
Feature activation+2.801
actually
Token actually
Feature activation+0.966
conceived
Token conceived
Feature activation+0.095
in
Token in
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+1.280
general
Token general
Feature activation+1.009
labor
Token labor
Feature activation+0.000
market
Token market
Feature activation+2.178
is
Token is
Feature activation+3.602
seeing
Token seeing
Feature activation+1.225
record
Token record
Feature activation+0.000
-
Token-
Feature activation+0.000
high
Tokenhigh
Feature activation+0.000
job
Token job
Feature activation+0.000
.
Token.
Feature activation+0.000
Look
Token Look
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
Apple
Token Apple
Feature activation+1.304
doesn
Token doesn
Feature activation+3.903
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+3.683
do
Token do
Feature activation+0.055
that
Token that
Feature activation+0.000

INTERVAL 2.878 - 3.454
CONTAINS 0.003%

but
Tokenbut
Feature activation+0.000
so
Token so
Feature activation+0.000
popular
Token popular
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.156
his
Token his
Feature activation+2.991
doctor
Token doctor
Feature activation+0.688
wants
Token wants
Feature activation+2.125
a
Token a
Feature activation+0.815
selfie
Token selfie
Feature activation+0.000
with
Token with
Feature activation+0.000
[
Token [
Feature activation+0.010
A
TokenA
Feature activation+0.000
venue
Tokenvenue
Feature activation+0.000
],
Token],
Feature activation+1.883
people
Token people
Feature activation+2.562
will
Token will
Feature activation+3.030
just
Token just
Feature activation+0.201
roll
Token roll
Feature activation+0.000
through
Token through
Feature activation+0.000
making
Token making
Feature activation+0.000
a
Token a
Feature activation+0.000
il
Tokenil
Feature activation+0.000
om
Tokenom
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
"
Token"
Feature activation+0.000
even
Token even
Feature activation+0.494
makes
Token makes
Feature activation+2.899
you
Token you
Feature activation+0.839
think
Token think
Feature activation+0.568
of
Token of
Feature activation+0.467
some
Token some
Feature activation+0.000
classic
Token classic
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
point
Token point
Feature activation+0.000
but
Token but
Feature activation+0.000
even
Token even
Feature activation+0.000
he
Token he
Feature activation+3.439
had
Token had
Feature activation+2.929
already
Token already
Feature activation+0.282
been
Token been
Feature activation+0.185
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.186
and
Token and
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+3.470
never
Token never
Feature activation+3.224
argued
Token argued
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Fed
Token Fed
Feature activation+0.000
should
Token should
Feature activation+0.000

INTERVAL 2.302 - 2.878
CONTAINS 0.005%

once
Token once
Feature activation+0.000
backed
Token backed
Feature activation+0.000
George
Token George
Feature activation+0.000
Osborne
Token Osborne
Feature activation+0.115
are
Token are
Feature activation+4.587
now
Token now
Feature activation+2.501
calling
Token calling
Feature activation+0.821
for
Token for
Feature activation+0.000
action
Token action
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
you
Token you
Feature activation+0.000
even
Token even
Feature activation+0.000
now
Token now
Feature activation+2.355
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FOR
TokenFOR
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
has
Token has
Feature activation+0.000
even
Token even
Feature activation+0.000
caught
Token caught
Feature activation+1.127
the
Token the
Feature activation+0.027
attention
Token attention
Feature activation+0.507
of
Token of
Feature activation+2.425
O
Token O
Feature activation+0.000
zzy
Tokenzzy
Feature activation+0.000
Os
Token Os
Feature activation+0.000
bourne
Tokenbourne
Feature activation+0.074
,
Token,
Feature activation+0.368
,
Token,
Feature activation+2.057
teams
Token teams
Feature activation+0.514
don
Token don
Feature activation+1.311
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.796
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
test
Token test
Feature activation+0.000
Jal
Token Jal
Feature activation+0.000
en
Tokenen
Feature activation+0.000
results
Token results
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
,
Token,
Feature activation+0.735
you
Token you
Feature activation+1.600
can
Token can
Feature activation+2.706
convert
Token convert
Feature activation+1.076
a
Token a
Feature activation+0.365
large
Token large
Feature activation+0.000
number
Token number
Feature activation+0.109
of
Token of
Feature activation+0.000

INTERVAL 1.727 - 2.302
CONTAINS 0.009%

body
Token body
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
in
Token in
Feature activation+1.889
small
Token small
Feature activation+0.106
amounts
Token amounts
Feature activation+2.175
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
National
Token National
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
Stalin
Token Stalin
Feature activation+2.147
urged
Token urged
Feature activation+1.019
caution
Token caution
Feature activation+0.281
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
he
Token he
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.000
obligations
Token obligations
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.000
that
Token that
Feature activation+1.829
one
Token one
Feature activation+0.351
day
Token day
Feature activation+0.683
tax
Token tax
Feature activation+0.654
hiatus
Token hiatus
Feature activation+0.841
has
Token has
Feature activation+2.789
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
who
Token who
Feature activation+0.000
want
Token want
Feature activation+0.000
even
Token even
Feature activation+0.000
a
Token a
Feature activation+2.046
remote
Token remote
Feature activation+0.310
shot
Token shot
Feature activation+0.000
at
Token at
Feature activation+0.000
earning
Token earning
Feature activation+0.000
a
Token a
Feature activation+0.000
fees
Token fees
Feature activation+0.000
.
Token.
Feature activation+0.000
It
TokenIt
Feature activation+0.000
said
Token said
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+2.155
CBI
Token CBI
Feature activation+1.568
had
Token had
Feature activation+5.015
not
Token not
Feature activation+4.356
properly
Token properly
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000

INTERVAL 1.151 - 1.727
CONTAINS 0.016%

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
big
Token big
Feature activation+0.000
cat
Token cat
Feature activation+0.000
even
Token even
Feature activation+0.000
has
Token has
Feature activation+1.644
a
Token a
Feature activation+1.211
Twitter
Token Twitter
Feature activation+0.000
handle
Token handle
Feature activation+0.000
:
Token:
Feature activation+0.000
#
Token #
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.006
those
Token those
Feature activation+1.182
who
Token who
Feature activation+1.317
opposed
Token opposed
Feature activation+0.000
the
Token the
Feature activation+0.000
Comcast
Token Comcast
Feature activation+0.000
deal
Token deal
Feature activation+0.000
concede
Token concede
Feature activation+2.334
exceeds
Token exceeds
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.573
positions
Token positions
Feature activation+0.657
of
Token of
Feature activation+1.224
the
Token the
Feature activation+1.293
most
Token most
Feature activation+0.317
extreme
Token extreme
Feature activation+0.109
global
Token global
Feature activation+0.000
-
Token-
Feature activation+0.000
warming
Tokenwarming
Feature activation+0.000
t
Tokent
Feature activation+0.016
get
Token get
Feature activation+0.000
it
Token it
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+1.200
we
Token we
Feature activation+1.189
can
Token can
Feature activation+1.770
still
Token still
Feature activation+0.000
do
Token do
Feature activation+0.000
well
Token well
Feature activation+0.000
safe
Token safe
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
here
Token here
Feature activation+1.440
,
Token,
Feature activation+1.005
on
Token on
Feature activation+1.350
the
Token the
Feature activation+0.862
Guardian
Token Guardian
Feature activation+0.000
Science
Token Science
Feature activation+0.000
section
Token section
Feature activation+0.000
,
Token,
Feature activation+1.862

INTERVAL 0.576 - 1.151
CONTAINS 0.036%

attacker
Token attacker
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
in
Token in
Feature activation+1.451
the
Token the
Feature activation+0.579
chest
Token chest
Feature activation+0.717
,
Token,
Feature activation+0.271
may
Token may
Feature activation+0.302
not
Token not
Feature activation+0.135
stop
Token stop
Feature activation+0.000
him
Token him
Feature activation+0.000
ball
Tokenball
Feature activation+0.000
machines
Token machines
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
even
Token even
Feature activation+0.000
has
Token has
Feature activation+1.019
an
Token an
Feature activation+0.442
old
Token old
Feature activation+0.000
-
Token-
Feature activation+0.000
school
Tokenschool
Feature activation+0.000
Pac
Token Pac
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+1.146
DNA
Token DNA
Feature activation+1.244
from
Token from
Feature activation+1.747
a
Token a
Feature activation+1.097
hair
Token hair
Feature activation+0.000
foll
Token foll
Feature activation+0.000
icle
Tokenicle
Feature activation+0.115
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
even
Token even
Feature activation+0.000
from
Token from
Feature activation+1.703
some
Token some
Feature activation+0.669
of
Token of
Feature activation+1.295
my
Token my
Feature activation+0.749
colleagues
Token colleagues
Feature activation+0.755
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
to
Token to
Feature activation+0.000
cheer
Token cheer
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.000
at
Token at
Feature activation+0.637
my
Token my
Feature activation+1.035
young
Token young
Feature activation+0.000
age
Token age
Feature activation+0.798
,
Token,
Feature activation+0.949
I
Token I
Feature activation+1.736

INTERVAL 0.000 - 0.576
CONTAINS 99.926%

Partners
Token Partners
Feature activation+0.000
The
Token The
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
and
Token and
Feature activation+0.000
Wildlife
Token Wildlife
Feature activation+0.000
Service
Token Service
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
a
Token a
Feature activation+0.000
closer
Token closer
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
and
Token and
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
army
Token army
Feature activation+0.000
's
Token's
Feature activation+0.000
combined
Token combined
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
New
TokenNew
Feature activation+0.000
York
Token York
Feature activation+0.000
(
Token (
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
)
Token)
Feature activation+0.000
--
Token --
Feature activation+0.000
apologized
Token apologized
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.000
statement
Token statement
Feature activation+0.000
released
Token released
Feature activation+0.000
around
Token around
Feature activation+0.000
midnight
Token midnight
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
vowed
Token vowed
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