H1.5 top features

Top feature 0 in H1.5: (feature 5836)

TOP ACTIVATIONS
MAX = 3.843

women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.843
to
Token to
Feature activation+0.000
interrupt
Token interrupt
Feature activation+0.000
their
Token their
Feature activation+0.000
careers
Token careers
Feature activation+0.533
for
Token for
Feature activation+0.000
An
Token An
Feature activation+0.000
American
Token American
Feature activation+0.000
tourist
Token tourist
Feature activation+0.000
accused
Token accused
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+3.770
of
Token of
Feature activation+0.000
raping
Token raping
Feature activation+0.167
her
Token her
Feature activation+0.242
in
Token in
Feature activation+0.000
D
Token D
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
almost
Token almost
Feature activation+0.000
14
Token 14
Feature activation+0.000
million
Token million
Feature activation+0.000
men
Token men
Feature activation+3.678
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
seven
Token seven
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
five
Token five
Feature activation+0.000
men
Token men
Feature activation+3.659
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
women
Token women
Feature activation+0.159
might
Token might
Feature activation+0.000
suffer
Token suffer
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.576
from
Token from
Feature activation+0.000
declining
Token declining
Feature activation+0.000
productivity
Token productivity
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
77
Token 77
Feature activation+0.000
¢
Token¢
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
men
Token men
Feature activation+3.371
earn
Token earn
Feature activation+0.000
).
Token).
Feature activation+0.000
This
Token This
Feature activation+0.000
national
Token national
Feature activation+0.000
trend
Token trend
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+3.346
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
just
Token just
Feature activation+0.000
more
Token more
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
to
Token to
Feature activation+0.000
grades
Token grades
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.327
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.095
one
Token one
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
six
Token six
Feature activation+0.000
men
Token men
Feature activation+3.302
,
Token,
Feature activation+0.000
suffers
Token suffers
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
assault
Token assault
Feature activation+0.000
are
Token are
Feature activation+0.000
less
Token less
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
American
Token American
Feature activation+0.000
men
Token men
Feature activation+3.279
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
bikes
Token bikes
Feature activation+0.000
in
Token in
Feature activation+0.000
cities
Token cities
Feature activation+0.000
Campbell
Token Campbell
Feature activation+0.000
said
Token said
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
violence
Token violence
Feature activation+0.000
against
Token against
Feature activation+0.000
men
Token men
Feature activation+3.264
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
but
Token but
Feature activation+0.000
-
Token-
Feature activation+0.000
kil
Tokenkil
Feature activation+0.000
ometer
Tokenometer
Feature activation+0.000
hike
Token hike
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+3.248
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
women
Token women
Feature activation+0.114
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
With
TokenWith
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
jobs
Token jobs
Feature activation+0.709
as
Token as
Feature activation+0.000
men
Token men
Feature activation+3.217
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Census
Token Census
Feature activation+0.000
Bureau
Token Bureau
Feature activation+0.000
concludes
Token concludes
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
we
Tokenwe
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
tell
Token tell
Feature activation+0.000
men
Token men
Feature activation+3.209
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
get
Token get
Feature activation+0.000
blackout
Token blackout
Feature activation+0.000
drunk
Token drunk
Feature activation+0.103
working
Token working
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
all
Token all
Feature activation+0.000
-
Token-
Feature activation+0.000
male
Tokenmale
Feature activation+3.093
establishments
Token establishments
Feature activation+0.000
as
Token as
Feature activation+0.000
heated
Token heated
Feature activation+0.000
issues
Token issues
Feature activation+0.000
in
Token in
Feature activation+0.000
r
Tokenr
Feature activation+0.000
and
Token and
Feature activation+0.000
less
Token less
Feature activation+0.000
sexual
Token sexual
Feature activation+0.731
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.066
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
role
Token role
Feature activation+0.000
was
Token was
Feature activation+0.000
prising
Tokenprising
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
revelation
Token revelation
Feature activation+0.000
that
Token that
Feature activation+0.000
men
Token men
Feature activation+3.032
prefer
Token prefer
Feature activation+0.000
higher
Token higher
Feature activation+0.000
voices
Token voices
Feature activation+0.000
in
Token in
Feature activation+0.000
women
Token women
Feature activation+0.277
generations
Token generations
Feature activation+0.198
of
Token of
Feature activation+0.000
mothers
Token mothers
Feature activation+0.519
without
Token without
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+2.959
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
house
Token house
Feature activation+0.105
âĢĶ
Token âĢĶ
Feature activation+0.000
lone
Token lone
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
men
Token men
Feature activation+2.871
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
researchers
Token researchers
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
men
Token men
Feature activation+2.865
to
Token to
Feature activation+0.000
terror
Token terror
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
all
Token all
Feature activation+0.000
women
Token women
Feature activation+0.292

Top DFA by src position
MAX = 4.881

He
Token He
Feature activation+0.036
Top resid features:
also
Token also
Feature activation+0.027
Top resid features:
argues
Token argues
Feature activation+0.028
Top resid features:
that
Token that
Feature activation+0.041
Top resid features:
because
Token because
Feature activation+0.034
Top resid features:
women
Token women
Feature activation+4.881
Top resid features:
are
Token are
Feature activation+0.059
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
likely
Token likely
Feature activation+0.098
Top resid features:
than
Token than
Feature activation+0.088
Top resid features:
men
Token men
Feature activation-0.230
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
crimes
Token crimes
Feature activation+0.037
Top resid features:
reported
Token reported
Feature activation+0.033
Top resid features:
by
Token by
Feature activation+0.023
Top resid features:
foreign
Token foreign
Feature activation+0.042
Top resid features:
women
Token women
Feature activation+3.287
Top resid features:
visiting
Token visiting
Feature activation+0.040
Top resid features:
India
Token India
Feature activation+0.046
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
An
Token An
Feature activation+0.033
Top resid features:
American
Token American
Feature activation+0.069
Top resid features:
June
Token June
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
nearly
Token nearly
Feature activation+0.007
Top resid features:
10
Token 10
Feature activation+0.009
Top resid features:
million
Token million
Feature activation+0.014
Top resid features:
women
Token women
Feature activation+1.806
Top resid features:
were
Token were
Feature activation+0.025
Top resid features:
employed
Token employed
Feature activation+0.022
Top resid features:
nationwide
Token nationwide
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
according
Token according
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
panel
Token panel
Feature activation+0.031
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
seven
Token seven
Feature activation+0.050
Top resid features:
women
Token women
Feature activation+4.584
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
five
Token five
Feature activation+0.037
Top resid features:
men
Token men
Feature activation-0.086
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
durable
Token durable
Feature activation+0.040
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
If
Token If
Feature activation+0.032
Top resid features:
so
Token so
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
women
Token women
Feature activation+3.071
Top resid features:
might
Token might
Feature activation+0.068
Top resid features:
suffer
Token suffer
Feature activation+0.028
Top resid features:
less
Token less
Feature activation+0.041
Top resid features:
than
Token than
Feature activation+0.058
Top resid features:
men
Token men
Feature activation-0.152
Top resid features:
the
Tokenthe
Feature activation+0.021
Top resid features:
Census
Token Census
Feature activation+0.028
Top resid features:
Bureau
Token Bureau
Feature activation+0.023
Top resid features:
concludes
Token concludes
Feature activation+0.037
Top resid features:
that
Token that
Feature activation+0.043
Top resid features:
women
Token women
Feature activation+2.271
Top resid features:
earn
Token earn
Feature activation+0.030
Top resid features:
77
Token 77
Feature activation+0.067
Top resid features:
¢
Token¢
Feature activation+0.071
Top resid features:
for
Token for
Feature activation+0.032
Top resid features:
every
Token every
Feature activation+0.060
Top resid features:
not
Token not
Feature activation+0.025
Top resid features:
solely
Token solely
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
problem
Token problem
Feature activation+0.013
Top resid features:
for
Token for
Feature activation+0.014
Top resid features:
women
Token women
Feature activation+3.183
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
It
Token It
Feature activation+0.029
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ļ
TokenĻ
Feature activation+0.038
Top resid features:
s
Tokens
Feature activation+0.045
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
2016
Token2016
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
test
Token test
Feature activation+0.040
Top resid features:
whether
Token whether
Feature activation+0.050
Top resid features:
women
Token women
Feature activation+4.727
Top resid features:
are
Token are
Feature activation+0.035
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
sensitive
Token sensitive
Feature activation+0.060
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
grades
Token grades
Feature activation+0.079
Top resid features:
one
Token one
Feature activation+0.017
Top resid features:
out
Token out
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
every
Token every
Feature activation+0.021
Top resid features:
four
Token four
Feature activation+0.028
Top resid features:
women
Token women
Feature activation+4.418
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
one
Token one
Feature activation+0.033
Top resid features:
out
Token out
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
's
Token's
Feature activation+0.018
Top resid features:
no
Token no
Feature activation+0.034
Top resid features:
secret
Token secret
Feature activation+0.027
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
American
Token American
Feature activation+0.053
Top resid features:
women
Token women
Feature activation+4.031
Top resid features:
are
Token are
Feature activation+0.057
Top resid features:
less
Token less
Feature activation+0.037
Top resid features:
likely
Token likely
Feature activation+0.108
Top resid features:
than
Token than
Feature activation+0.088
Top resid features:
American
Token American
Feature activation+0.099
Top resid features:
estimates
Token estimates
Feature activation+0.006
Top resid features:
up
Token up
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
one
Token one
Feature activation-0.003
Top resid features:
million
Token million
Feature activation+0.001
Top resid features:
women
Token women
Feature activation+4.238
Top resid features:
experience
Token experience
Feature activation+0.012
Top resid features:
at
Token at
Feature activation-0.004
Top resid features:
least
Token least
Feature activation+0.013
Top resid features:
one
Token one
Feature activation-0.004
Top resid features:
incident
Token incident
Feature activation+0.037
Top resid features:
since
Token since
Feature activation+0.008
Top resid features:
it
Token it
Feature activation-0.004
Top resid features:
remains
Token remains
Feature activation+0.022
Top resid features:
closed
Token closed
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
women
Token women
Feature activation+4.448
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
On
TokenOn
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
studies
Token studies
Feature activation+0.019
Top resid features:
suggest
Token suggest
Feature activation+0.018
Top resid features:
that
Token that
Feature activation+0.035
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
general
Token general
Feature activation+0.038
Top resid features:
women
Token women
Feature activation+3.026
Top resid features:
make
Token make
Feature activation+0.031
Top resid features:
less
Token less
Feature activation+0.038
Top resid features:
doing
Token doing
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
same
Token same
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Suggest
TokenSuggest
Feature activation+0.007
Top resid features:
ing
Tokening
Feature activation-0.003
Top resid features:
women
Token women
Feature activation+4.334
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation+0.002
Top resid features:
drink
Token drink
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
contraceptive
Token contraceptive
Feature activation+0.011
Top resid features:
rights
Token rights
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
working
Token working
Feature activation+0.065
Top resid features:
women
Token women
Feature activation+1.351
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
all
Token all
Feature activation+0.028
Top resid features:
-
Token-
Feature activation-0.010
Top resid features:
male
Tokenmale
Feature activation-0.285
Top resid features:
establishments
Token establishments
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
male
Token male
Feature activation-0.179
Top resid features:
world
Token world
Feature activation+0.013
Top resid features:
;
Token;
Feature activation+0.008
Top resid features:
women
Token women
Feature activation+2.168
Top resid features:
were
Token were
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
be
Token be
Feature activation+0.022
Top resid features:
higher
Token higher
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
guys
Token guys
Feature activation+0.038
Top resid features:
prefer
Token prefer
Feature activation+0.010
Top resid features:
higher
Token higher
Feature activation+0.024
Top resid features:
voices
Token voices
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
women
Token women
Feature activation+4.220
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Equ
TokenEqu
Feature activation+0.028
Top resid features:
ally
Tokenally
Feature activation+0.042
Top resid features:
unsur
Token unsur
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
As
TokenAs
Feature activation+0.010
Top resid features:
many
Token many
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
these
Token these
Feature activation-0.005
Top resid features:
women
Token women
Feature activation+2.504
Top resid features:
become
Token become
Feature activation+0.013
Top resid features:
grandmother
Token grandmother
Feature activation+0.106
Top resid features:
s
Tokens
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
significantly
Token significantly
Feature activation+0.007
Top resid features:
associated
Token associated
Feature activation+0.024
Top resid features:
with
Token with
Feature activation+0.023
Top resid features:
riding
Token riding
Feature activation+0.035
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
women
Token women
Feature activation+3.101
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
but
Token but
Feature activation+0.066
Top resid features:
not
Token not
Feature activation+0.070
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
men
Token men
Feature activation-0.207
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
conspiracy
Token conspiracy
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
subjug
Token subjug
Feature activation+0.007
Top resid features:
ate
Tokenate
Feature activation+0.003
Top resid features:
women
Token women
Feature activation+3.813
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
just
Token just
Feature activation+0.001
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.02

Head 3: 0.01

Head 4: 0.04

Head 5: 0.51

Head 6: 0.12

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.02

Head 11: 0.12

Positive logits

ocracy1.98

د1.97

lishes1.90

behind1.80

aki1.77

ignt1.72

default1.68

Requirements1.67

ollow1.67

iser1.66

aternity1.66

medium1.63

ikk1.63

only1.62

ards1.62

isers1.61

ocus1.60

Shade1.59

ِ1.57

center1.56

Negative logits

leased-1.81

GUN-1.81

smuggled-1.74

��-1.73

kidney-1.72

intestinal-1.66

gross-1.66

airborne-1.65

transports-1.65

zynski-1.63

Seah-1.62

incom-1.61

authorized-1.59

emis-1.57

sailed-1.56

lease-1.56

tten-1.56

lyak-1.55

undown-1.55

entreprene-1.54

INTERVAL 3.459 - 3.843
CONTAINS 0.001%

An
Token An
Feature activation+0.000
American
Token American
Feature activation+0.000
tourist
Token tourist
Feature activation+0.000
accused
Token accused
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+3.770
of
Token of
Feature activation+0.000
raping
Token raping
Feature activation+0.167
her
Token her
Feature activation+0.242
in
Token in
Feature activation+0.000
D
Token D
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
almost
Token almost
Feature activation+0.000
14
Token 14
Feature activation+0.000
million
Token million
Feature activation+0.000
men
Token men
Feature activation+3.678
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
seven
Token seven
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
five
Token five
Feature activation+0.000
men
Token men
Feature activation+3.659
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.843
to
Token to
Feature activation+0.000
interrupt
Token interrupt
Feature activation+0.000
their
Token their
Feature activation+0.000
careers
Token careers
Feature activation+0.533
for
Token for
Feature activation+0.000
women
Token women
Feature activation+0.159
might
Token might
Feature activation+0.000
suffer
Token suffer
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.576
from
Token from
Feature activation+0.000
declining
Token declining
Feature activation+0.000
productivity
Token productivity
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 3.074 - 3.459
CONTAINS 0.001%

more
Token more
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
to
Token to
Feature activation+0.000
grades
Token grades
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.327
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.095
-
Token-
Feature activation+0.000
kil
Tokenkil
Feature activation+0.000
ometer
Tokenometer
Feature activation+0.000
hike
Token hike
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+3.248
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
women
Token women
Feature activation+0.114
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
With
TokenWith
Feature activation+0.000
one
Token one
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
six
Token six
Feature activation+0.000
men
Token men
Feature activation+3.302
,
Token,
Feature activation+0.000
suffers
Token suffers
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
assault
Token assault
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
jobs
Token jobs
Feature activation+0.709
as
Token as
Feature activation+0.000
men
Token men
Feature activation+3.217
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Census
Token Census
Feature activation+0.000
Bureau
Token Bureau
Feature activation+0.000
concludes
Token concludes
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+3.346
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
just
Token just
Feature activation+0.000

INTERVAL 2.690 - 3.074
CONTAINS 0.001%

on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
men
Token men
Feature activation+2.865
to
Token to
Feature activation+0.000
terror
Token terror
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
all
Token all
Feature activation+0.000
women
Token women
Feature activation+0.292
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
men
Token men
Feature activation+2.871
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
researchers
Token researchers
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
telling
Token telling
Feature activation+0.000
men
Token men
Feature activation+2.787
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
blackout
Token blackout
Feature activation+0.000
drunk
Token drunk
Feature activation+0.070
r
Tokenr
Feature activation+0.000
and
Token and
Feature activation+0.000
less
Token less
Feature activation+0.000
sexual
Token sexual
Feature activation+0.731
than
Token than
Feature activation+0.000
men
Token men
Feature activation+3.066
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
role
Token role
Feature activation+0.000
was
Token was
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
after
Tokenafter
Feature activation+0.000
all
Token all
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
are
Tokenare
Feature activation+0.000
children
Token children
Feature activation+2.736
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.098
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 2.306 - 2.690
CONTAINS 0.001%

male
Token male
Feature activation+1.776
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
men
Token men
Feature activation+2.379
make
Token make
Feature activation+0.000
forceful
Token forceful
Feature activation+0.000
gestures
Token gestures
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
careers
Token careers
Feature activation+0.533
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
child
Token child
Feature activation+2.641
care
Token care
Feature activation+0.512
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.000
Yaz
Token Yaz
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
children
Token children
Feature activation+2.313
as
Token as
Feature activation+0.000
slaves
Token slaves
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
full
Token full
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
bree
Token bree
Feature activation+0.000
ch
Tokench
Feature activation+0.000
babies
Token babies
Feature activation+2.446
opt
Token opt
Feature activation+0.000
for
Token for
Feature activation+0.000
ca
Token ca
Feature activation+0.000
es
Tokenes
Feature activation+0.000
are
Tokenare
Feature activation+0.000
connected
Token connected
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
survey
Token survey
Feature activation+0.000
of
Token of
Feature activation+0.000
men
Token men
Feature activation+2.498
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.921 - 2.306
CONTAINS 0.003%

the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
high
Token high
Feature activation+0.000
price
Token price
Feature activation+0.000
of
Token of
Feature activation+0.000
child
Token child
Feature activation+2.116
-
Token-
Feature activation+0.000
re
Tokenre
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000
in
Token in
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
lone
Token lone
Feature activation+0.000
mum
Token mum
Feature activation+0.000
and
Token and
Feature activation+0.000
father
Token father
Feature activation+1.439
less
Tokenless
Feature activation+0.000
children
Token children
Feature activation+2.148
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
expecting
Token expecting
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
be
Token be
Feature activation+0.000
traff
Token traff
Feature activation+0.268
icked
Tokenicked
Feature activation+0.000
in
Token in
Feature activation+0.000
for
Token for
Feature activation+0.000
men
Token men
Feature activation+1.976
to
Token to
Feature activation+0.000
marry
Token marry
Feature activation+0.286
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
stand
Token stand
Feature activation+0.000
in
Token in
Feature activation+0.000
for
Token for
Feature activation+0.000
daddy
Token daddy
Feature activation+2.115
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
made
Token made
Feature activation+0.000
up
Token up
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
of
Token of
Feature activation+0.000
white
Token white
Feature activation+0.000
men
Token men
Feature activation+1.937
.
Token.
Feature activation+0.000
K
Token K
Feature activation+0.000
lo
Tokenlo
Feature activation+0.000
os
Tokenos
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.537 - 1.921
CONTAINS 0.002%

economical
Token economical
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
behind
Token behind
Feature activation+0.000
helping
Token helping
Feature activation+0.000
children
Token children
Feature activation+1.571
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
better
Token better
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
Arabian
Token Arabian
Feature activation+0.000
men
Token men
Feature activation+1.719
known
Token known
Feature activation+0.000
only
Token only
Feature activation+0.000
as
Token as
Feature activation+0.000
Fah
Token Fah
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
d
Tokend
Feature activation+0.000
be
Token be
Feature activation+0.000
licking
Token licking
Feature activation+0.000
up
Token up
Feature activation+0.000
another
Token another
Feature activation+0.000
man
Token man
Feature activation+1.691
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
sperm
Token sperm
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
physical
Token physical
Feature activation+0.000
models
Token models
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
male
Token male
Feature activation+1.776
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
men
Token men
Feature activation+2.379
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+0.000
older
Token older
Feature activation+0.000
guys
Token guys
Feature activation+1.585
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000

INTERVAL 1.153 - 1.537
CONTAINS 0.004%

wind
Tokenwind
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
women
Token women
Feature activation+0.216
and
Token and
Feature activation+0.000
people
Token people
Feature activation+1.462
of
Token of
Feature activation+0.000
color
Token color
Feature activation+0.000
must
Token must
Feature activation+0.000
push
Token push
Feature activation+0.000
against
Token against
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
woman
Token woman
Feature activation+0.000
who
Token who
Feature activation+0.000
played
Token played
Feature activation+0.000
his
Token his
Feature activation+1.207
prec
Token prec
Feature activation+0.000
ocious
Tokenocious
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
,
Token,
Feature activation+0.000
Rudy
Token Rudy
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
women
Token women
Feature activation+0.417
as
Token as
Feature activation+0.000
he
Token he
Feature activation+1.435
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.674
guest
Token guest
Feature activation+0.000
went
Token went
Feature activation+0.000
back
Token back
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
:
Token:
Feature activation+0.000
Naked
Token Naked
Feature activation+0.000
women
Token women
Feature activation+0.122
on
Token on
Feature activation+0.000
dog
Token dog
Feature activation+1.294
le
Token le
Feature activation+0.185
ashes
Tokenashes
Feature activation+0.000
,
Token,
Feature activation+0.000
crawling
Token crawling
Feature activation+0.000
in
Token in
Feature activation+0.000
affordable
Token affordable
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
available
Token available
Feature activation+0.000
as
Token as
Feature activation+0.000
children
Token children
Feature activation+1.209
get
Token get
Feature activation+0.000
older
Token older
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
infant
Token infant
Feature activation+0.010

INTERVAL 0.769 - 1.153
CONTAINS 0.007%

the
Token the
Feature activation+0.000
opposite
Token opposite
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
actual
Token actual
Feature activation+0.000
biological
Token biological
Feature activation+0.837
sex
Token sex
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
when
Token when
Feature activation+0.000
people
Token people
Feature activation+0.593
'd
Token'd
Feature activation+0.000
settle
Token settle
Feature activation+0.000
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000
married
Token married
Feature activation+0.833
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
that
Token that
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
men
Token men
Feature activation+2.728
female
Token female
Feature activation+0.000
chess
Token chess
Feature activation+0.000
community
Token community
Feature activation+0.000
after
Token after
Feature activation+0.000
claiming
Token claiming
Feature activation+0.000
men
Token men
Feature activation+0.915
are
Token are
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
hard
Tokenhard
Feature activation+0.000
wired
Tokenwired
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
globe
Token globe
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Children
TokenChildren
Feature activation+0.958
in
Token in
Feature activation+0.000
lower
Token lower
Feature activation+0.000
-
Token-
Feature activation+0.000
income
Tokenincome
Feature activation+0.000
families
Token families
Feature activation+0.000
to
Token to
Feature activation+0.000
women
Token women
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hair
Token hair
Feature activation+0.929
and
Token and
Feature activation+0.000
noted
Token noted
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 0.384 - 0.769
CONTAINS 0.013%

balance
Token balance
Feature activation+0.000
between
Token between
Feature activation+0.000
their
Token their
Feature activation+0.109
jobs
Token jobs
Feature activation+0.249
and
Token and
Feature activation+0.000
families
Token families
Feature activation+0.765
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Because
TokenBecause
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
woman
Token woman
Feature activation+0.181
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
raped
Token raped
Feature activation+0.618
while
Token while
Feature activation+0.000
a
Token a
Feature activation+0.000
student
Token student
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
obese
Token obese
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.112
'll
Token'll
Feature activation+0.000
hand
Token hand
Feature activation+0.109
them
Token them
Feature activation+0.611
a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
their
Token their
Feature activation+0.475
ľ
Tokenľ
Feature activation+0.000
pot
Tokenpot
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
of
Token of
Feature activation+0.000
human
Token human
Feature activation+0.736
milk
Token milk
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
aware
Token aware
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.441
practicing
Token practicing
Feature activation+0.000
it
Token it
Feature activation+0.000
behind
Token behind
Feature activation+0.000
closed
Token closed
Feature activation+0.000
doors
Token doors
Feature activation+0.000

INTERVAL 0.000 - 0.384
CONTAINS 99.968%

harb
Token harb
Feature activation+0.000
ored
Tokenored
Feature activation+0.000
feature
Token feature
Feature activation+0.000
dreams
Token dreams
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
his
Token his
Feature activation+0.000
FX
Token FX
Feature activation+0.000
background
Token background
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
,
Token,
Feature activation+0.000
260
Token260
Feature activation+0.000
counterfeit
Token counterfeit
Feature activation+0.000
G
Token G
Feature activation+0.000
HD
TokenHD
Feature activation+0.000
hair
Token hair
Feature activation+0.000
-
Token-
Feature activation+0.000
straight
Tokenstraight
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
ir
Token ir
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
being
Token being
Feature activation+0.000
taken
Token taken
Feature activation+0.000
out
Token out
Feature activation+0.000
context
Token context
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
.
Token.
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
's
Token's
Feature activation+0.000
moments
Token moments
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.000
England
Token England
Feature activation+0.000
were
Token were
Feature activation+0.000
behind
Token behind
Feature activation+0.000
within
Token within
Feature activation+0.000
30
Token 30
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
just
Token just
Feature activation+0.000
under
Token under
Feature activation+0.000
1
Token 1
Feature activation+0.000
gallon
Token gallon
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
could
Token could
Feature activation+0.000
fit
Token fit
Feature activation+0.000
400
Token 400
Feature activation+0.000
mL
Token mL
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H1.5: (feature 17102)

TOP ACTIVATIONS
MAX = 2.335

how
Token how
Feature activation+0.000
long
Token long
Feature activation+0.000
a
Token a
Feature activation+0.000
dog
Token dog
Feature activation+0.000
or
Token or
Feature activation+0.000
cat
Token cat
Feature activation+2.335
can
Token can
Feature activation+0.000
spend
Token spend
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
:
Token:
Feature activation+0.000
are
Token are
Feature activation+0.000
dogs
Token dogs
Feature activation+1.682
smarter
Token smarter
Feature activation+0.000
than
Token than
Feature activation+0.000
cats
Token cats
Feature activation+2.071
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
understand
Token understand
Feature activation+0.000
our
Token our
Feature activation+0.000
communication
Token communication
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
are
Token are
Feature activation+0.000
cats
Token cats
Feature activation+1.842
smarter
Token smarter
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
the
Token the
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
care
Token care
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
cats
Token cats
Feature activation+1.756
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
argument
Token argument
Feature activation+0.000
The
Token The
Feature activation+0.000
argument
Token argument
Feature activation+0.000
is
Token is
Feature activation+0.000
:
Token:
Feature activation+0.000
are
Token are
Feature activation+0.000
dogs
Token dogs
Feature activation+1.682
smarter
Token smarter
Feature activation+0.000
than
Token than
Feature activation+0.000
cats
Token cats
Feature activation+2.071
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
them
Token them
Feature activation+0.000
meat
Token meat
Feature activation+0.000
y
Tokeny
Feature activation+0.000
cat
Token cat
Feature activation+0.088
or
Token or
Feature activation+0.000
dog
Token dog
Feature activation+1.456
food
Token food
Feature activation+0.314
and
Token and
Feature activation+0.000
water
Token water
Feature activation+0.024
âĢĵ
Token âĢĵ
Feature activation+0.000
not
Token not
Feature activation+0.000
Try
TokenTry
Feature activation+0.006
to
Token to
Feature activation+0.000
guess
Token guess
Feature activation+0.107
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
child
Token child
Feature activation+1.402
has
Token has
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.086
hand
Token hand
Feature activation+0.416
?
Token?
Feature activation+0.000
fell
Token fell
Feature activation+0.000
off
Token off
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
pit
Token pit
Feature activation+0.039
bull
Token bull
Feature activation+1.398
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
jaws
Token jaws
Feature activation+0.540
locked
Token locked
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
stay
Token stay
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
dog
Token dog
Feature activation+1.341
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
charity
Token charity
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
decide
Token decide
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
child
Token child
Feature activation+1.261
like
Tokenlike
Feature activation+0.086
painting
Token painting
Feature activation+0.704
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
walls
Token walls
Feature activation+0.234
no
Token no
Feature activation+0.000
rules
Token rules
Feature activation+0.000
on
Token on
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
meat
Token meat
Feature activation+1.254
is
Token is
Feature activation+0.000
processed
Token processed
Feature activation+0.000
or
Token or
Feature activation+0.000
sold
Token sold
Feature activation+0.000
.
Token.
Feature activation+0.000
:
Token :
Feature activation+0.000
You
Token You
Feature activation+0.000
also
Token also
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
groom
Token groom
Feature activation+1.178
your
Token your
Feature activation+0.000
dog
Token dog
Feature activation+0.604
properly
Token properly
Feature activation+0.000
before
Token before
Feature activation+0.000
camping
Token camping
Feature activation+1.020
for
Token for
Feature activation+0.000
pets
Token pets
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
people
Token people
Feature activation+1.177
,
Token,
Feature activation+0.000
435
Token 435
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
McL
Token McL
Feature activation+0.000
worth
Token worth
Feature activation+0.000
mentioning
Token mentioning
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
dog
Token dog
Feature activation+0.497
meat
Token meat
Feature activation+1.175
sales
Token sales
Feature activation+0.000
are
Token are
Feature activation+0.000
completely
Token completely
Feature activation+0.000
unregulated
Token unregulated
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
The
TokenThe
Feature activation+0.000
pit
Token pit
Feature activation+0.000
bull
Token bull
Feature activation+1.152
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
owner
Token owner
Feature activation+0.000
had
Token had
Feature activation+0.000
he
Token he
Feature activation+0.000
merely
Token merely
Feature activation+0.000
pet
Token pet
Feature activation+0.016
ting
Tokenting
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+1.035
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
decide
Token decide
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
The
Token The
Feature activation+0.000
tag
Token tag
Feature activation+0.459
should
Token should
Feature activation+0.000
include
Token include
Feature activation+0.000
:
Token:
Feature activation+0.000
dog
Token dog
Feature activation+1.034
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
name
Token name
Feature activation+0.121
,
Token,
Feature activation+0.000
groom
Token groom
Feature activation+1.178
your
Token your
Feature activation+0.000
dog
Token dog
Feature activation+0.604
properly
Token properly
Feature activation+0.000
before
Token before
Feature activation+0.000
camping
Token camping
Feature activation+1.020
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
grooming
Token grooming
Feature activation+0.062
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
he
Token he
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
shooter
Token shooter
Feature activation+0.986
held
Token held
Feature activation+0.000
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
he
Token he
Feature activation+0.000
merely
Token merely
Feature activation+0.000
pet
Token pet
Feature activation+0.272
ting
Tokenting
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.981
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
decide
Token decide
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000

Top DFA by src position
MAX = 3.359

limit
Token limit
Feature activation+0.051
Top resid features:
on
Token on
Feature activation+0.057
Top resid features:
how
Token how
Feature activation+0.040
Top resid features:
long
Token long
Feature activation+0.015
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
dog
Token dog
Feature activation+3.359
Top resid features:
or
Token or
Feature activation+0.054
Top resid features:
cat
Token cat
Feature activation+0.125
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
spend
Token spend
Feature activation+0.000
Top resid features:
looking
Token looking
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.054
Top resid features:
argument
Token argument
Feature activation-0.000
Top resid features:
is
Token is
Feature activation+0.081
Top resid features:
:
Token:
Feature activation+0.012
Top resid features:
are
Token are
Feature activation+0.085
Top resid features:
dogs
Token dogs
Feature activation+1.963
Top resid features:
smarter
Token smarter
Feature activation+0.114
Top resid features:
than
Token than
Feature activation+0.058
Top resid features:
cats
Token cats
Feature activation+0.083
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.020
Top resid features:
argument
Token argument
Feature activation-0.014
Top resid features:
is
Token is
Feature activation+0.027
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
are
Token are
Feature activation+0.024
Top resid features:
dogs
Token dogs
Feature activation+1.884
Top resid features:
smarter
Token smarter
Feature activation+0.013
Top resid features:
than
Token than
Feature activation+0.020
Top resid features:
cats
Token cats
Feature activation+0.027
Top resid features:
because
Token because
Feature activation+0.029
Top resid features:
they
Token they
Feature activation+0.021
Top resid features:
biggest
Token biggest
Feature activation+0.026
Top resid features:
differences
Token differences
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.084
Top resid features:
that
Token that
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
dogs
Token dogs
Feature activation+2.649
Top resid features:
care
Token care
Feature activation+0.129
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
cats
Token cats
Feature activation+0.078
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
dogs
Token dogs
Feature activation+0.090
Top resid features:
care
Token care
Feature activation+0.047
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
cats
Token cats
Feature activation+2.409
Top resid features:
don
Token don
Feature activation+0.034
Top resid features:
't
Token't
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
The
Token The
Feature activation+0.075
Top resid features:
argument
Token argument
Feature activation-0.002
Top resid features:
you
Token you
Feature activation+0.023
Top resid features:
feed
Token feed
Feature activation+0.047
Top resid features:
them
Token them
Feature activation+0.061
Top resid features:
meat
Token meat
Feature activation+0.148
Top resid features:
y
Tokeny
Feature activation+0.075
Top resid features:
cat
Token cat
Feature activation+2.041
Top resid features:
or
Token or
Feature activation+0.058
Top resid features:
dog
Token dog
Feature activation+0.269
Top resid features:
food
Token food
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
very
Token very
Feature activation+0.008
Top resid features:
sharp
Token sharp
Feature activation+0.008
Top resid features:
teeth
Token teeth
Feature activation+0.070
Top resid features:
on
Token on
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
dog
Token dog
Feature activation+0.954
Top resid features:
?
Token?
Feature activation+0.023
Top resid features:
Try
TokenTry
Feature activation+0.097
Top resid features:
to
Token to
Feature activation+0.052
Top resid features:
guess
Token guess
Feature activation+0.086
Top resid features:
what
Token what
Feature activation+0.039
Top resid features:
pit
Token pit
Feature activation+0.003
Top resid features:
bull
Token bull
Feature activation+0.243
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
The
Token The
Feature activation+0.012
Top resid features:
bigger
Token bigger
Feature activation+0.003
Top resid features:
dog
Token dog
Feature activation+1.223
Top resid features:
was
Token was
Feature activation+0.014
Top resid features:
wearing
Token wearing
Feature activation+0.010
Top resid features:
what
Token what
Feature activation+0.011
Top resid features:
looked
Token looked
Feature activation+0.006
Top resid features:
like
Token like
Feature activation+0.009
Top resid features:
how
Token how
Feature activation+0.011
Top resid features:
long
Token long
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
dog
Token dog
Feature activation+0.128
Top resid features:
or
Token or
Feature activation+0.008
Top resid features:
cat
Token cat
Feature activation+1.866
Top resid features:
can
Token can
Feature activation+0.010
Top resid features:
spend
Token spend
Feature activation+0.007
Top resid features:
looking
Token looking
Feature activation+0.012
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
he
Token he
Feature activation+0.049
Top resid features:
merely
Token merely
Feature activation+0.027
Top resid features:
pet
Token pet
Feature activation+0.415
Top resid features:
ting
Tokenting
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.053
Top resid features:
dog
Token dog
Feature activation+0.915
Top resid features:
?
Token?
Feature activation+0.045
Top resid features:
You
Token You
Feature activation+0.053
Top resid features:
decide
Token decide
Feature activation+0.072
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
The
Token The
Feature activation+0.163
Top resid features:
point
Token point
Feature activation+0.011
Top resid features:
worth
Token worth
Feature activation+0.015
Top resid features:
mentioning
Token mentioning
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.027
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
dog
Token dog
Feature activation+1.207
Top resid features:
meat
Token meat
Feature activation-0.020
Top resid features:
sales
Token sales
Feature activation+0.016
Top resid features:
are
Token are
Feature activation+0.037
Top resid features:
completely
Token completely
Feature activation+0.010
Top resid features:
unregulated
Token unregulated
Feature activation+0.019
Top resid features:
The
Token The
Feature activation+0.014
Top resid features:
tag
Token tag
Feature activation+0.046
Top resid features:
should
Token should
Feature activation+0.013
Top resid features:
include
Token include
Feature activation+0.014
Top resid features:
:
Token:
Feature activation+0.013
Top resid features:
dog
Token dog
Feature activation+0.366
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.013
Top resid features:
name
Token name
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
has
Token has
Feature activation+0.045
Top resid features:
space
Token space
Feature activation+0.033
Top resid features:
aval
Token aval
Feature activation+0.021
Top resid features:
iable
Tokeniable
Feature activation+0.039
Top resid features:
for
Token for
Feature activation+0.064
Top resid features:
pets
Token pets
Feature activation+1.766
Top resid features:
and
Token and
Feature activation+0.064
Top resid features:
a
Token a
Feature activation+0.038
Top resid features:
few
Token few
Feature activation+0.046
Top resid features:
people
Token people
Feature activation+0.321
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
point
Token point
Feature activation+0.030
Top resid features:
worth
Token worth
Feature activation+0.067
Top resid features:
mentioning
Token mentioning
Feature activation+0.080
Top resid features:
is
Token is
Feature activation+0.087
Top resid features:
that
Token that
Feature activation+0.034
Top resid features:
dog
Token dog
Feature activation+1.180
Top resid features:
meat
Token meat
Feature activation-0.002
Top resid features:
sales
Token sales
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
completely
Token completely
Feature activation+0.000
Top resid features:
unregulated
Token unregulated
Feature activation+0.000
Top resid features:
pit
Token pit
Feature activation-0.001
Top resid features:
bull
Token bull
Feature activation+0.132
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
The
Token The
Feature activation+0.007
Top resid features:
bigger
Token bigger
Feature activation+0.001
Top resid features:
dog
Token dog
Feature activation+0.739
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
wearing
Token wearing
Feature activation+0.004
Top resid features:
what
Token what
Feature activation+0.005
Top resid features:
looked
Token looked
Feature activation+0.001
Top resid features:
like
Token like
Feature activation+0.004
Top resid features:
?
Token?
Feature activation+0.030
Top resid features:
Or
Token Or
Feature activation+0.039
Top resid features:
is
Token is
Feature activation+0.092
Top resid features:
he
Token he
Feature activation+0.074
Top resid features:
merely
Token merely
Feature activation+0.029
Top resid features:
pet
Token pet
Feature activation+0.634
Top resid features:
ting
Tokenting
Feature activation+0.107
Top resid features:
the
Token the
Feature activation+0.130
Top resid features:
dog
Token dog
Feature activation+0.447
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.069
Top resid features:
tag
Token tag
Feature activation+0.180
Top resid features:
should
Token should
Feature activation+0.053
Top resid features:
include
Token include
Feature activation+0.094
Top resid features:
:
Token:
Feature activation+0.042
Top resid features:
dog
Token dog
Feature activation+0.637
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:
name
Token name
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.033
Top resid features:
need
Token need
Feature activation+0.060
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
groom
Token groom
Feature activation+0.111
Top resid features:
your
Token your
Feature activation+0.022
Top resid features:
dog
Token dog
Feature activation+0.425
Top resid features:
properly
Token properly
Feature activation+0.032
Top resid features:
before
Token before
Feature activation+0.158
Top resid features:
camping
Token camping
Feature activation+0.158
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
For
Token For
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
shooting
Token shooting
Feature activation+0.031
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
dog
Token dog
Feature activation+0.808
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
Louis
Token Louis
Feature activation-0.001
Top resid features:
a
Tokena
Feature activation+0.007
Top resid features:
County
Token County
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.019
Top resid features:
?
Token?
Feature activation+0.020
Top resid features:
Or
Token Or
Feature activation+0.031
Top resid features:
is
Token is
Feature activation+0.073
Top resid features:
he
Token he
Feature activation+0.055
Top resid features:
merely
Token merely
Feature activation+0.038
Top resid features:
pet
Token pet
Feature activation+0.479
Top resid features:
ting
Tokenting
Feature activation+0.089
Top resid features:
the
Token the
Feature activation+0.114
Top resid features:
dog
Token dog
Feature activation+0.236
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.03

Head 3: 0.02

Head 4: 0.05

Head 5: 0.47

Head 6: 0.10

Head 7: 0.06

Head 8: 0.03

Head 9: 0.04

Head 10: 0.02

Head 11: 0.09

Positive logits

sect2.11

Zup1.99

chlor1.91

ib1.83

fluor1.80

ascus1.80

Lindsay1.79

Nem1.77

Mub1.75

Brom1.74

Fas1.74

ersion1.73

medi1.73

])1.73

Jacqu1.70

ã1.69

Sr1.67

Norris1.67

)]1.67

Shad1.66

Negative logits

ICAN-1.98

wardrobe-1.95

pload-1.91

shareholders-1.84

BuyableInstoreAndOnline-1.82

-1.82

ertodd-1.81

enthus-1.80

WORK-1.79

-1.77

ledged-1.77

redes-1.76

-1.73

Die-1.70

shareholder-1.69

-1.69

subscriber-1.69

atra-1.69

-1.67

ailed-1.67

INTERVAL 2.101 - 2.335
CONTAINS 0.000%

how
Token how
Feature activation+0.000
long
Token long
Feature activation+0.000
a
Token a
Feature activation+0.000
dog
Token dog
Feature activation+0.000
or
Token or
Feature activation+0.000
cat
Token cat
Feature activation+2.335
can
Token can
Feature activation+0.000
spend
Token spend
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.868 - 2.101
CONTAINS 0.000%

:
Token:
Feature activation+0.000
are
Token are
Feature activation+0.000
dogs
Token dogs
Feature activation+1.682
smarter
Token smarter
Feature activation+0.000
than
Token than
Feature activation+0.000
cats
Token cats
Feature activation+2.071
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
understand
Token understand
Feature activation+0.000
our
Token our
Feature activation+0.000
communication
Token communication
Feature activation+0.000

INTERVAL 1.634 - 1.868
CONTAINS 0.000%

the
Token the
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
care
Token care
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
cats
Token cats
Feature activation+1.756
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
argument
Token argument
Feature activation+0.000
The
Token The
Feature activation+0.000
argument
Token argument
Feature activation+0.000
is
Token is
Feature activation+0.000
:
Token:
Feature activation+0.000
are
Token are
Feature activation+0.000
dogs
Token dogs
Feature activation+1.682
smarter
Token smarter
Feature activation+0.000
than
Token than
Feature activation+0.000
cats
Token cats
Feature activation+2.071
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
are
Token are
Feature activation+0.000
cats
Token cats
Feature activation+1.842
smarter
Token smarter
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000

INTERVAL 1.401 - 1.634
CONTAINS 0.000%

them
Token them
Feature activation+0.000
meat
Token meat
Feature activation+0.000
y
Tokeny
Feature activation+0.000
cat
Token cat
Feature activation+0.088
or
Token or
Feature activation+0.000
dog
Token dog
Feature activation+1.456
food
Token food
Feature activation+0.314
and
Token and
Feature activation+0.000
water
Token water
Feature activation+0.024
âĢĵ
Token âĢĵ
Feature activation+0.000
not
Token not
Feature activation+0.000
Try
TokenTry
Feature activation+0.006
to
Token to
Feature activation+0.000
guess
Token guess
Feature activation+0.107
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
child
Token child
Feature activation+1.402
has
Token has
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.086
hand
Token hand
Feature activation+0.416
?
Token?
Feature activation+0.000

INTERVAL 1.167 - 1.401
CONTAINS 0.001%

the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
stay
Token stay
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
dog
Token dog
Feature activation+1.341
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
charity
Token charity
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
fell
Token fell
Feature activation+0.000
off
Token off
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
pit
Token pit
Feature activation+0.039
bull
Token bull
Feature activation+1.398
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
jaws
Token jaws
Feature activation+0.540
locked
Token locked
Feature activation+0.000
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
decide
Token decide
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
child
Token child
Feature activation+1.261
like
Tokenlike
Feature activation+0.086
painting
Token painting
Feature activation+0.704
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
walls
Token walls
Feature activation+0.234
no
Token no
Feature activation+0.000
rules
Token rules
Feature activation+0.000
on
Token on
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
meat
Token meat
Feature activation+1.254
is
Token is
Feature activation+0.000
processed
Token processed
Feature activation+0.000
or
Token or
Feature activation+0.000
sold
Token sold
Feature activation+0.000
.
Token.
Feature activation+0.000
worth
Token worth
Feature activation+0.000
mentioning
Token mentioning
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
dog
Token dog
Feature activation+0.497
meat
Token meat
Feature activation+1.175
sales
Token sales
Feature activation+0.000
are
Token are
Feature activation+0.000
completely
Token completely
Feature activation+0.000
unregulated
Token unregulated
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.934 - 1.167
CONTAINS 0.001%

The
Token The
Feature activation+0.000
tag
Token tag
Feature activation+0.459
should
Token should
Feature activation+0.000
include
Token include
Feature activation+0.000
:
Token:
Feature activation+0.000
dog
Token dog
Feature activation+1.034
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
name
Token name
Feature activation+0.121
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
So
TokenSo
Feature activation+0.000
if
Token if
Feature activation+0.000
your
Token your
Feature activation+0.000
dog
Token dog
Feature activation+0.947
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
eat
Token eat
Feature activation+0.788
well
Token well
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
shooter
Token shooter
Feature activation+0.986
held
Token held
Feature activation+0.000
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
he
Token he
Feature activation+0.000
merely
Token merely
Feature activation+0.000
pet
Token pet
Feature activation+0.272
ting
Tokenting
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.981
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
decide
Token decide
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
bags
Token bags
Feature activation+0.324
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.599
's
Token's
Feature activation+0.000
feces
Token feces
Feature activation+0.956
around
Token around
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
hands
Token hands
Feature activation+0.147
.
Token.
Feature activation+0.000

INTERVAL 0.700 - 0.934
CONTAINS 0.002%

a
Token a
Feature activation+0.000
name
Token name
Feature activation+0.000
tag
Token tag
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
dog
Token dog
Feature activation+0.781
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
tag
Token tag
Feature activation+0.459
should
Token should
Feature activation+0.000
include
Token include
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.927
initially
Token initially
Feature activation+0.000
told
Token told
Feature activation+0.000
police
Token police
Feature activation+0.049
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
your
Token your
Feature activation+0.000
veterinarian
Token veterinarian
Feature activation+0.000
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+0.809
location
Token location
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.000
sure
Token sure
Feature activation+0.000
that
Token that
Feature activation+0.000
bug
Token bug
Feature activation+0.200
le
Tokenle
Feature activation+0.129
call
Token call
Feature activation+0.059
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.732
was
Token was
Feature activation+0.000
named
Token named
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
call
Token call
Feature activation+0.273
possibly
Token possibly
Feature activation+0.000
a
Token a
Feature activation+0.000
Labrador
Token Labrador
Feature activation+0.000
-
Token-
Feature activation+0.000
pit
Tokenpit
Feature activation+0.000
bull
Token bull
Feature activation+0.891
mix
Token mix
Feature activation+0.000
-
Token -
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
placed
Token placed
Feature activation+0.000

INTERVAL 0.467 - 0.700
CONTAINS 0.004%

also
Token also
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
groom
Token groom
Feature activation+1.178
your
Token your
Feature activation+0.000
dog
Token dog
Feature activation+0.604
properly
Token properly
Feature activation+0.000
before
Token before
Feature activation+0.000
camping
Token camping
Feature activation+1.020
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Horse
Token Horse
Feature activation+0.699
man
Tokenman
Feature activation+0.634
replied
Token replied
Feature activation+0.000
sens
Token sens
Feature activation+0.000
ibly
Tokenibly
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
appropriately
Token appropriately
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
my
Token my
Feature activation+0.000
dogs
Token dogs
Feature activation+0.542
respond
Token respond
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
day
Token day
Feature activation+0.000
care
Token care
Feature activation+0.000
or
Token or
Feature activation+0.000
dog
Token dog
Feature activation+0.498
parks
Token parks
Feature activation+0.000
or
Token or
Feature activation+0.000
boarding
Token boarding
Feature activation+0.144
overnight
Token overnight
Feature activation+0.000
in
Token in
Feature activation+0.000
vet
Token vet
Feature activation+0.000
right
Token right
Feature activation+0.000
away
Token away
Feature activation+0.000
if
Token if
Feature activation+0.000
their
Token their
Feature activation+0.000
dog
Token dog
Feature activation+0.491
shows
Token shows
Feature activation+0.075
symptoms
Token symptoms
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.233 - 0.467
CONTAINS 0.012%

were
Token were
Feature activation+0.000
no
Token no
Feature activation+0.000
k
Token k
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
el
Tokenel
Feature activation+0.000
staff
Token staff
Feature activation+0.414
present
Token present
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.000
a
Token a
Feature activation+0.000
mon
Token mon
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
loc
Tokenloc
Feature activation+0.000
,
Token,
Feature activation+0.000
someone
Token someone
Feature activation+0.259
comments
Token comments
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
"
Token "
Feature activation+0.000
not
Tokennot
Feature activation+0.000
Watch
Token Watch
Feature activation+0.000
dog
Tokendog
Feature activation+0.000
said
Token said
Feature activation+0.000
today
Token today
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.327
who
Token who
Feature activation+0.000
care
Token care
Feature activation+0.000
about
Token about
Feature activation+0.000
their
Token their
Feature activation+0.000
email
Token email
Feature activation+0.000
trade
Token trade
Feature activation+0.000
so
Token so
Feature activation+0.000
grotesque
Token grotesque
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
dogs
Token dogs
Feature activation+0.345
are
Token are
Feature activation+0.000
purposely
Token purposely
Feature activation+0.000
tortured
Token tortured
Feature activation+0.185
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
as
Token as
Feature activation+0.000
willingly
Token willingly
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
carry
Token carry
Feature activation+0.000
bags
Token bags
Feature activation+0.324
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.599
's
Token's
Feature activation+0.000
feces
Token feces
Feature activation+0.956

INTERVAL 0.000 - 0.233
CONTAINS 99.980%

traffic
Token traffic
Feature activation+0.000
.
Token.
Feature activation+0.000
Different
Token Different
Feature activation+0.000
tires
Token tires
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
with
Token with
Feature activation+0.000
different
Token different
Feature activation+0.000
characteristics
Token characteristics
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
am
Token am
Feature activation+0.000
not
Token not
Feature activation+0.000
sure
Token sure
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
claim
Token claim
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Hum
Token Hum
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
will
Token will
Feature activation+0.000
flat
Token flat
Feature activation+0.000
items
Token items
Feature activation+0.000
.
Token.
Feature activation+0.000
Store
Token Store
Feature activation+0.000
what
Token what
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
--
Token --
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
television
Token television
Feature activation+0.000
news
Token news
Feature activation+0.000
channels
Token channels
Feature activation+0.000
began
Token began
Feature activation+0.000
and
Token and
Feature activation+0.000
research
Token research
Feature activation+0.000
are
Token are
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
human
Token human
Feature activation+0.000
aura
Token aura
Feature activation+0.000
,
Token,
Feature activation+0.000
hyp
Token hyp
Feature activation+0.000
nosis
Tokennosis
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 H1.5: (feature 9743)

TOP ACTIVATIONS
MAX = 3.719

t
Tokent
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
left
Token left
Feature activation+0.000
eye
Token eye
Feature activation+0.000
or
Token or
Feature activation+0.000
right
Token right
Feature activation+3.719
eye
Token eye
Feature activation+0.000
;
Token;
Feature activation+0.000
each
Token each
Feature activation+0.000
camera
Token camera
Feature activation+0.000
captures
Token captures
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
right
Tokenright
Feature activation+3.568
gradient
Token gradient
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
D
Token D
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
Further
TokenFurther
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+3.555
side
Token side
Feature activation+0.459
each
Token each
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
solar
Token solar
Feature activation+0.000
a
Token a
Feature activation+0.000
press
Token press
Feature activation+0.000
release
Token release
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+3.466
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
best
Token best
Feature activation+0.000
used
Tokenused
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
left
Token left
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
right
Tokenright
Feature activation+3.428
asymm
Token asymm
Feature activation+0.000
etric
Tokenetric
Feature activation+0.000
expression
Token expression
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
mute
Token mute
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+3.333
arrows
Token arrows
Feature activation+0.000
to
Token to
Feature activation+0.000
seek
Token seek
Feature activation+0.000
,
Token,
Feature activation+0.000
up
Token up
Feature activation+0.133
e
Tokene
Feature activation+0.000
.,
Token.,
Feature activation+0.000
from
Token from
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+0.000
right
Token right
Feature activation+3.226
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
He
Token He
Feature activation+0.000
scanned
Token scanned
Feature activation+0.000
left
Token left
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
right
Token right
Feature activation+3.145
,
Token,
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
no
Token no
Feature activation+0.000
footsteps
Token footsteps
Feature activation+0.000
in
Token in
Feature activation+0.000
obl
Tokenobl
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+3.099
is
Token is
Feature activation+0.000
stock
Token stock
Feature activation+0.000
I
Token I
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
Ricardo
Token Ricardo
Feature activation+0.000
McF
Token McF
Feature activation+0.000
arlane
Tokenarlane
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+3.043
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
counter
Token counter
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+3.022
wing
Token wing
Feature activation+0.723
demon
Token demon
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
of
Token of
Feature activation+0.000
George
Token George
Feature activation+0.000
positional
Token positional
Feature activation+0.000
properties
Token properties
Feature activation+0.000
(
Token (
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+3.002
,
Token,
Feature activation+0.000
top
Token top
Feature activation+1.639
,
Token,
Feature activation+0.000
bottom
Token bottom
Feature activation+0.000
),
Token),
Feature activation+0.000
two
Token two
Feature activation+0.000
red
Token red
Feature activation+0.000
peaks
Token peaks
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+2.809
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
presence
Token presence
Feature activation+0.000
of
Token of
Feature activation+0.000
dich
Token dich
Feature activation+0.000
Managing
Token Managing
Feature activation+0.000
Editor
Token Editor
Feature activation+0.000
Sean
Token Sean
Feature activation+0.000
Woods
Token Woods
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.790
,
Token,
Feature activation+0.000
walk
Token walk
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
legal
Token legal
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
:
Token:
Feature activation+0.000
old
Token old
Feature activation+0.000
version
Token version
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.790
:
Token:
Feature activation+0.000
new
Token new
Feature activation+0.000
version
Token version
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
a
Token a
Feature activation+0.000
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.752
handed
Token handed
Feature activation+0.000
-
Token-
Feature activation+0.000
f
Tokenf
Feature activation+0.000
encer
Tokenencer
Feature activation+0.000
,
Token,
Feature activation+0.000
Poké
Token Poké
Feature activation+0.000
balls
Tokenballs
Feature activation+0.000
out
Token out
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+2.613
,
Token,
Feature activation+0.000
pay
Token pay
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+0.000
right
Token right
Feature activation+2.504
-
Token -
Feature activation+0.000
Sh
Token Sh
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
,
Token,
Feature activation+0.000
And
Token And
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
harm
Token harm
Feature activation+0.000
done
Token done
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.407
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
just
Token just
Feature activation+0.000
take
Token take
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
green
Token green
Feature activation+0.000
and
Token and
Feature activation+0.000
spun
Token spun
Feature activation+0.000
right
Token right
Feature activation+2.297
to
Token to
Feature activation+0.000
within
Token within
Feature activation+0.000
ten
Token ten
Feature activation+0.000
feet
Token feet
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 4.566

aren
Token aren
Feature activation+0.047
Top resid features:
âĢ
TokenâĢ
Feature activation+0.064
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
t
Tokent
Feature activation+0.003
Top resid features:
dedicated
Token dedicated
Feature activation+0.072
Top resid features:
left
Token left
Feature activation+3.004
Top resid features:
eye
Token eye
Feature activation+0.068
Top resid features:
or
Token or
Feature activation+0.091
Top resid features:
right
Token right
Feature activation-0.093
Top resid features:
eye
Token eye
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
Our
Token Our
Feature activation+0.032
Top resid features:
results
Token results
Feature activation+0.025
Top resid features:
suggest
Token suggest
Feature activation+0.045
Top resid features:
that
Token that
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.052
Top resid features:
left
Token left
Feature activation+4.566
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation+0.011
Top resid features:
right
Tokenright
Feature activation-0.291
Top resid features:
gradient
Token gradient
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:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Further
TokenFurther
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
left
Token left
Feature activation+4.098
Top resid features:
and
Token and
Feature activation+0.108
Top resid features:
right
Token right
Feature activation-0.004
Top resid features:
side
Token side
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
article
Token article
Feature activation-0.019
Top resid features:
shown
Token shown
Feature activation+0.008
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
left
Token left
Feature activation+4.367
Top resid features:
linked
Token linked
Feature activation-0.012
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
corresponding
Token corresponding
Feature activation+0.028
Top resid features:
text
Token text
Feature activation-0.015
Top resid features:
Our
Token Our
Feature activation+0.011
Top resid features:
results
Token results
Feature activation+0.012
Top resid features:
suggest
Token suggest
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
left
Token left
Feature activation+2.432
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation-0.007
Top resid features:
right
Tokenright
Feature activation-0.214
Top resid features:
gradient
Token gradient
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
M
Token M
Feature activation-0.015
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
mute
Token mute
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.092
Top resid features:
left
Token left
Feature activation+4.414
Top resid features:
and
Token and
Feature activation+0.117
Top resid features:
right
Token right
Feature activation-0.082
Top resid features:
arrows
Token arrows
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
seek
Token seek
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.170
Top resid features:
e
Tokene
Feature activation-0.012
Top resid features:
.,
Token.,
Feature activation+0.021
Top resid features:
from
Token from
Feature activation+0.059
Top resid features:
left
Token left
Feature activation+4.113
Top resid features:
to
Token to
Feature activation+0.071
Top resid features:
right
Token right
Feature activation-0.101
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
For
Token For
Feature activation+0.000
Top resid features:
example
Token example
Feature activation+0.000
Top resid features:
ze
Tokenze
Feature activation+0.013
Top resid features:
said
Token said
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
He
Token He
Feature activation+0.012
Top resid features:
scanned
Token scanned
Feature activation+0.032
Top resid features:
left
Token left
Feature activation+3.932
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
then
Token then
Feature activation+0.148
Top resid features:
right
Token right
Feature activation-0.191
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
seeing
Token seeing
Feature activation+0.000
Top resid features:
phone
Token phone
Feature activation+0.020
Top resid features:
has
Token has
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
On
Token On
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
left
Token left
Feature activation+3.882
Top resid features:
is
Token is
Feature activation+0.048
Top resid features:
Mot
Token Mot
Feature activation+0.003
Top resid features:
obl
Tokenobl
Feature activation+0.022
Top resid features:
ur
Tokenur
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
:
Token:
Feature activation-0.009
Top resid features:
Jordan
Token Jordan
Feature activation+0.017
Top resid features:
Hor
Token Hor
Feature activation+0.012
Top resid features:
ner
Tokenner
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
left
Token left
Feature activation+3.879
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
and
Token and
Feature activation+0.086
Top resid features:
Ricardo
Token Ricardo
Feature activation+0.117
Top resid features:
McF
Token McF
Feature activation+0.025
Top resid features:
arlane
Tokenarlane
Feature activation+0.082
Top resid features:
frequently
Token frequently
Feature activation+0.001
Top resid features:
demon
Token demon
Feature activation+0.028
Top resid features:
ized
Tokenized
Feature activation+0.004
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
left
Token left
Feature activation+3.580
Top resid features:
as
Token as
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.028
Top resid features:
counter
Token counter
Feature activation+0.073
Top resid features:
point
Tokenpoint
Feature activation+0.032
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
borders
Token borders
Feature activation-0.001
Top resid features:
),
Token),
Feature activation+0.039
Top resid features:
positional
Token positional
Feature activation+0.011
Top resid features:
properties
Token properties
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+0.131
Top resid features:
left
Tokenleft
Feature activation+3.955
Top resid features:
,
Token,
Feature activation+0.098
Top resid features:
right
Token right
Feature activation-0.061
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.021
Top resid features:
blue
Token blue
Feature activation+0.009
Top resid features:
peak
Token peak
Feature activation+0.004
Top resid features:
on
Token on
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
left
Token left
Feature activation+3.628
Top resid features:
shows
Token shows
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
presence
Token presence
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
chlor
Token chlor
Feature activation+0.022
Top resid features:
Rubin
Token Rubin
Feature activation+0.021
Top resid features:
Er
Token Er
Feature activation+0.013
Top resid features:
de
Tokende
Feature activation-0.004
Top resid features:
ly
Tokenly
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
left
Token left
Feature activation+3.318
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
Rolling
Token Rolling
Feature activation+0.025
Top resid features:
Stone
Token Stone
Feature activation+0.009
Top resid features:
magazine
Token magazine
Feature activation+0.019
Top resid features:
ermanent
Tokenermanent
Feature activation-0.024
Top resid features:
Cast
Token Cast
Feature activation+0.017
Top resid features:
Icon
Token Icon
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
left
Tokenleft
Feature activation+3.675
Top resid features:
:
Token:
Feature activation+0.029
Top resid features:
old
Token old
Feature activation+0.110
Top resid features:
version
Token version
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
right
Token right
Feature activation-0.139
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
re
Tokenre
Feature activation+0.002
Top resid features:
tall
Token tall
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
left
Token left
Feature activation+3.469
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
handed
Tokenhanded
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
sl
Token sl
Feature activation-0.020
Top resid features:
inging
Tokeninging
Feature activation-0.027
Top resid features:
Poké
Token Poké
Feature activation+0.038
Top resid features:
balls
Tokenballs
Feature activation+0.045
Top resid features:
out
Token out
Feature activation+0.081
Top resid features:
left
Token left
Feature activation+3.571
Top resid features:
and
Token and
Feature activation+0.136
Top resid features:
right
Token right
Feature activation-0.049
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
pay
Token pay
Feature activation+0.000
Top resid features:
attention
Token attention
Feature activation+0.000
Top resid features:
About
TokenAbout
Feature activation-0.073
Top resid features:
Us
Token Us
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
From
TokenFrom
Feature activation-0.038
Top resid features:
left
Token left
Feature activation+3.778
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
right
Token right
Feature activation-0.166
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
Sh
Token Sh
Feature activation+0.000
Top resid features:
ai
Tokenai
Feature activation+0.000
Top resid features:
So
TokenSo
Feature activation+0.036
Top resid features:
it
Token it
Feature activation+0.016
Top resid features:
looks
Token looks
Feature activation+0.009
Top resid features:
like
Token like
Feature activation+0.006
Top resid features:
you
Token you
Feature activation+0.015
Top resid features:
left
Token left
Feature activation+2.805
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
store
Token store
Feature activation+0.005
Top resid features:
without
Token without
Feature activation+0.006
Top resid features:
paying
Token paying
Feature activation+0.023
Top resid features:
for
Token for
Feature activation+0.019
Top resid features:
tree
Token tree
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
hit
Token hit
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
front
Token front
Feature activation+0.082
Top resid features:
left
Token left
Feature activation+2.787
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
green
Token green
Feature activation+0.063
Top resid features:
and
Token and
Feature activation+0.081
Top resid features:
spun
Token spun
Feature activation-0.015
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.05

Head 2: 0.04

Head 3: 0.02

Head 4: 0.04

Head 5: 0.46

Head 6: 0.06

Head 7: 0.03

Head 8: 0.03

Head 9: 0.04

Head 10: 0.03

Head 11: 0.12

Positive logits

axis1.99

artif1.97

?????-1.89

thereum1.86

aligned1.85

Caucas1.83

olean1.78

archaic1.67

izabeth1.67

Uk1.66

older1.65

1.65

stimulation1.64

FactoryReloaded1.63

alignment1.62

ultras1.61

equivalents1.60

oldest1.60

colleagues1.59

linem1.58

Negative logits

vre-2.43

gall-2.20

ilo-2.00

ilty-1.96

vine-1.96

vic-1.95

bum-1.87

humane-1.87

adr-1.82

Lonely-1.81

Photograph-1.80

hof-1.79

andre-1.78

agra-1.78

iseum-1.77

advertising-1.76

Fortune-1.75

ades-1.75

laim-1.73

tru-1.72

INTERVAL 3.347 - 3.719
CONTAINS 0.001%

t
Tokent
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
left
Token left
Feature activation+0.000
eye
Token eye
Feature activation+0.000
or
Token or
Feature activation+0.000
right
Token right
Feature activation+3.719
eye
Token eye
Feature activation+0.000
;
Token;
Feature activation+0.000
each
Token each
Feature activation+0.000
camera
Token camera
Feature activation+0.000
captures
Token captures
Feature activation+0.000
a
Token a
Feature activation+0.000
press
Token press
Feature activation+0.000
release
Token release
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+3.466
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
best
Token best
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
right
Tokenright
Feature activation+3.568
gradient
Token gradient
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
D
Token D
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
used
Tokenused
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
left
Token left
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
right
Tokenright
Feature activation+3.428
asymm
Token asymm
Feature activation+0.000
etric
Tokenetric
Feature activation+0.000
expression
Token expression
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Further
TokenFurther
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+3.555
side
Token side
Feature activation+0.459
each
Token each
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
solar
Token solar
Feature activation+0.000

INTERVAL 2.975 - 3.347
CONTAINS 0.001%

a
Token a
Feature activation+0.000
counter
Token counter
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+3.022
wing
Token wing
Feature activation+0.723
demon
Token demon
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
of
Token of
Feature activation+0.000
George
Token George
Feature activation+0.000
e
Tokene
Feature activation+0.000
.,
Token.,
Feature activation+0.000
from
Token from
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+0.000
right
Token right
Feature activation+3.226
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
to
Token to
Feature activation+0.000
mute
Token mute
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+3.333
arrows
Token arrows
Feature activation+0.000
to
Token to
Feature activation+0.000
seek
Token seek
Feature activation+0.000
,
Token,
Feature activation+0.000
up
Token up
Feature activation+0.133
and
Token and
Feature activation+0.000
Ricardo
Token Ricardo
Feature activation+0.000
McF
Token McF
Feature activation+0.000
arlane
Tokenarlane
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+3.043
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
positional
Token positional
Feature activation+0.000
properties
Token properties
Feature activation+0.000
(
Token (
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+3.002
,
Token,
Feature activation+0.000
top
Token top
Feature activation+1.639
,
Token,
Feature activation+0.000
bottom
Token bottom
Feature activation+0.000
),
Token),
Feature activation+0.000

INTERVAL 2.603 - 2.975
CONTAINS 0.001%

Poké
Token Poké
Feature activation+0.000
balls
Tokenballs
Feature activation+0.000
out
Token out
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+2.613
,
Token,
Feature activation+0.000
pay
Token pay
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Managing
Token Managing
Feature activation+0.000
Editor
Token Editor
Feature activation+0.000
Sean
Token Sean
Feature activation+0.000
Woods
Token Woods
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.790
,
Token,
Feature activation+0.000
walk
Token walk
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
legal
Token legal
Feature activation+0.000
two
Token two
Feature activation+0.000
red
Token red
Feature activation+0.000
peaks
Token peaks
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+2.809
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
presence
Token presence
Feature activation+0.000
of
Token of
Feature activation+0.000
dich
Token dich
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
a
Token a
Feature activation+0.000
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.752
handed
Token handed
Feature activation+0.000
-
Token-
Feature activation+0.000
f
Tokenf
Feature activation+0.000
encer
Tokenencer
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
:
Token:
Feature activation+0.000
old
Token old
Feature activation+0.000
version
Token version
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.790
:
Token:
Feature activation+0.000
new
Token new
Feature activation+0.000
version
Token version
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.231 - 2.603
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+0.000
right
Token right
Feature activation+2.504
-
Token -
Feature activation+0.000
Sh
Token Sh
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
,
Token,
Feature activation+0.000
And
Token And
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
green
Token green
Feature activation+0.000
and
Token and
Feature activation+0.000
spun
Token spun
Feature activation+0.000
right
Token right
Feature activation+2.297
to
Token to
Feature activation+0.000
within
Token within
Feature activation+0.000
ten
Token ten
Feature activation+0.000
feet
Token feet
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
harm
Token harm
Feature activation+0.000
done
Token done
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+2.407
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
just
Token just
Feature activation+0.000
take
Token take
Feature activation+0.000

INTERVAL 1.860 - 2.231
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
icked
Tokenicked
Feature activation+0.000
on
Token on
Feature activation+0.000
right
Token right
Feature activation+2.019
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
get
Token get
Feature activation+0.000
-
Token-
Feature activation+0.000
go
Tokengo
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
but
Token but
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.923
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
basis
Token basis
Feature activation+0.000
who
Token who
Feature activation+0.000
uniformly
Token uniformly
Feature activation+0.000
support
Token support
Feature activation+0.000
women
Token women
Feature activation+0.000
's
Token's
Feature activation+0.000
right
Token right
Feature activation+2.029
to
Token to
Feature activation+0.000
choose
Token choose
Feature activation+0.000
,
Token,
Feature activation+0.000
joined
Token joined
Feature activation+0.000
with
Token with
Feature activation+0.000
Load
TokenLoad
Feature activation+0.000
more
Token more
Feature activation+0.000
che
Token che
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ron
Tokenron
Feature activation+0.000
right
Token right
Feature activation+1.893
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
Cos
Token Cos
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000

INTERVAL 1.488 - 1.860
CONTAINS 0.001%

with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
shot
Token shot
Feature activation+0.000
to
Token to
Feature activation+0.000
right
Token right
Feature activation+1.847
field
Token field
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
BRE
TokenBRE
Feature activation+0.000
?
Token?
Feature activation+0.000
When
Token When
Feature activation+0.000
Henderson
Token Henderson
Feature activation+0.000
and
Token and
Feature activation+0.000
Boat
Token Boat
Feature activation+0.000
right
Tokenright
Feature activation+1.628
said
Token said
Feature activation+0.000
no
Token no
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
officer
Token officer
Feature activation+0.000
(
Token (
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+3.002
,
Token,
Feature activation+0.000
top
Token top
Feature activation+1.639
,
Token,
Feature activation+0.000
bottom
Token bottom
Feature activation+0.000
),
Token),
Feature activation+0.000
transformations
Token transformations
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
ph
Token ph
Feature activation+0.000
alan
Tokenalan
Feature activation+0.000
x
Tokenx
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
right
Token right
Feature activation+1.825
T
Token T
Feature activation+0.000
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.116 - 1.488
CONTAINS 0.000%

those
Token those
Feature activation+0.000
likes
Token likes
Feature activation+0.000
donated
Token donated
Feature activation+0.000
$
Token $
Feature activation+0.000
15
Token15
Feature activation+0.000
right
Token right
Feature activation+1.147
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
Battle
Token Battle
Feature activation+0.000
Lizard
Token Lizard
Feature activation+0.000
post
Token post
Feature activation+0.000
unhappy
Token unhappy
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
right
Token right
Feature activation+1.129
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
help
Token help
Feature activation+0.000
"
Token"
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000

INTERVAL 0.744 - 1.116
CONTAINS 0.001%

terrorism
Token terrorism
Feature activation+0.000
between
Token between
Feature activation+0.000
Aug
Token Aug
Feature activation+0.000
2
Token 2
Feature activation+0.000
and
Token and
Feature activation+0.000
Sep
Token Sep
Feature activation+0.933
17
Token 17
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
three
Token three
Feature activation+0.000
foreigners
Token foreigners
Feature activation+0.000
the
Token the
Feature activation+0.000
villagers
Token villagers
Feature activation+0.000
going
Token going
Feature activation+0.000
hungry
Token hungry
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+1.004
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
or
Tokenor
Feature activation+0.000
trucks
Token trucks
Feature activation+0.000
)
Token)
Feature activation+0.000
heading
Token heading
Feature activation+0.000
straight
Token straight
Feature activation+1.053
through
Token through
Feature activation+0.000
an
Token an
Feature activation+0.000
intersection
Token intersection
Feature activation+0.000
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
partner
Token partner
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
center
Token center
Feature activation+0.000
-
Token-
Feature activation+0.000
right
Tokenright
Feature activation+0.791
coalition
Token coalition
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
said
Token said
Feature activation+0.000
Mont
Token Mont
Feature activation+0.000
i
Tokeni
Feature activation+0.000
was
Token was
Feature activation+0.000
destined
Token destined
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.981
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
At
TokenAt
Feature activation+0.000

INTERVAL 0.372 - 0.744
CONTAINS 0.002%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
depths
Token depths
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Sep
Token Sep
Feature activation+0.426
ul
Tokenul
Feature activation+0.000
ch
Tokench
Feature activation+0.000
re
Tokenre
Feature activation+0.000
,
Token,
Feature activation+0.000
starring
Token starring
Feature activation+0.000
counter
Token counter
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+3.022
wing
Token wing
Feature activation+0.723
demon
Token demon
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
of
Token of
Feature activation+0.000
George
Token George
Feature activation+0.000
Soros
Token Soros
Feature activation+0.000
A
Token A
Feature activation+0.000
verett
Tokenverett
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.728
option
Token option
Feature activation+0.000
when
Token when
Feature activation+0.000
Alabama
Token Alabama
Feature activation+0.000
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.000
TV
Token TV
Feature activation+0.000
shows
Token shows
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
a
Token a
Feature activation+0.000
straight
Token straight
Feature activation+0.595
face
Token face
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
explained
Token explained
Feature activation+0.000
that
Token that
Feature activation+0.000
after
Token after
Feature activation+0.000
coming
Token coming
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
flank
Token flank
Feature activation+0.422
the
Token the
Feature activation+0.000
winger
Token winger
Feature activation+0.272
let
Token let
Feature activation+0.000
fly
Token fly
Feature activation+0.000
from
Token from
Feature activation+0.000

INTERVAL 0.000 - 0.372
CONTAINS 99.994%

Regions
Token Regions
Feature activation+0.000
of
Token of
Feature activation+0.000
interest
Token interest
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
executive
Token executive
Feature activation+0.000
network
Token network
Feature activation+0.000
(
Token (
Feature activation+0.000
warm
Tokenwarm
Feature activation+0.000
colors
Token colors
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
54
Token54
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Harmony
Token Harmony
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Comp
TokenComp
Feature activation+0.000
rehens
Tokenrehens
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
can
Token can
Feature activation+0.000
/
Token/
Feature activation+0.000
10
Token10
Feature activation+0.000
/
Token/
Feature activation+0.000
2017
Token2017
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
determined
Token determined
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
service
Token service
Feature activation+0.000
who
Token who
Feature activation+0.000
red
Token red
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
irted
Tokenirted
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
saw
Token saw
Feature activation+0.000
most
Token most
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H1.5: (feature 10021)

TOP ACTIVATIONS
MAX = 1.961

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
As
TokenAs
Feature activation+0.000
he
Token he
Feature activation+1.961
was
Token was
Feature activation+0.000
going
Token going
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.392
bombing
Token bombing
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
He
TokenHe
Feature activation+1.960
's
Token's
Feature activation+0.000
seen
Token seen
Feature activation+0.000
me
Token me
Feature activation+0.469
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.421
also
Token also
Feature activation+0.000
supported
Token supported
Feature activation+0.000
her
Token her
Feature activation+0.598
partner
Token partner
Feature activation+0.472
while
Token while
Feature activation+0.000
he
Token he
Feature activation+1.890
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.374
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
.
Token.
Feature activation+0.000
Through
Token Through
Feature activation+0.000
him
Token him
Feature activation+1.860
she
Token she
Feature activation+0.000
met
Token met
Feature activation+0.076
crucial
Token crucial
Feature activation+0.000
players
Token players
Feature activation+0.302
like
Token like
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
like
Token like
Feature activation+0.000
her
Token her
Feature activation+0.035
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.844
has
Token has
Feature activation+0.000
regrets
Token regrets
Feature activation+0.000
and
Token and
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
further
Token further
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.029
forb
Token forb
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
him
Token him
Feature activation+1.774
from
Token from
Feature activation+0.000
working
Token working
Feature activation+0.000
with
Token with
Feature activation+0.000
Spider
Token Spider
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.374
sent
Token sent
Feature activation+0.000
him
Token him
Feature activation+1.772
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.000
for
Token for
Feature activation+0.000
had
Token had
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
basement
Token basement
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.770
notes
Token notes
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.160
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
killed
Token killed
Feature activation+0.000
two
Token two
Feature activation+0.000
movie
Token movie
Feature activation+0.000
goers
Tokengoers
Feature activation+0.000
and
Token and
Feature activation+0.000
himself
Token himself
Feature activation+1.743
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.290
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
tail
Token tail
Feature activation+0.000
and
Token and
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+1.739
was
Token was
Feature activation+0.000
rubbing
Token rubbing
Feature activation+0.000
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
moving
Token moving
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
met
Token met
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+1.723
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
and
Token and
Feature activation+0.000
f
Token f
Feature activation+0.000
know
Token know
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+1.551
had
Token had
Feature activation+0.000
turned
Token turned
Feature activation+0.000
himself
Token himself
Feature activation+1.692
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
yet
Token yet
Feature activation+0.000
or
Token or
Feature activation+0.000
cheated
Token cheated
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
because
Token because
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.667
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
description
Token description
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hopeless
Token hopeless
Feature activation+0.000
climate
Token climate
Feature activation+0.000
his
Token his
Feature activation+1.646
election
Token election
Feature activation+0.000
win
Token win
Feature activation+0.000
has
Token has
Feature activation+0.000
created
Token created
Feature activation+0.000
.
Token.
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000
minute
Tokenminute
Feature activation+0.000
for
Token for
Feature activation+0.000
him
Token him
Feature activation+1.633
to
Token to
Feature activation+0.000
call
Token call
Feature activation+0.000
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
During
TokenDuring
Feature activation+0.000
his
Token his
Feature activation+1.587
investigation
Token investigation
Feature activation+0.000
,
Token,
Feature activation+0.000
Starr
Token Starr
Feature activation+0.000
learned
Token learned
Feature activation+0.000
that
Token that
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
speedy
Token speedy
Feature activation+0.000
professor
Token professor
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.580
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
completely
Token completely
Feature activation+0.000
different
Token different
Feature activation+0.000
person
Token person
Feature activation+0.021
-
Token-
Feature activation+0.000
38
Token38
Feature activation+0.000
).
Token).
Feature activation+0.000
Then
Token Then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.566
visits
Token visits
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.386
to
Token to
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000
him
Token him
Feature activation+0.997
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
impressed
Token impressed
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+1.556
scholarship
Token scholarship
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
she
Token she
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
know
Token know
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+1.551
had
Token had
Feature activation+0.000
turned
Token turned
Feature activation+0.000
himself
Token himself
Feature activation+1.692
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000

Top DFA by src position
MAX = 2.117

<|endoftext|>
Token<|endoftext|>
Feature activation-0.196
Top resid features:
said
Token said
Feature activation+0.031
Top resid features:
she
Token she
Feature activation+1.609
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
her
Token her
Feature activation+0.610
Top resid features:
sons
Token sons
Feature activation-0.004
Top resid features:
were
Token were
Feature activation+0.028
Top resid features:
getting
Token getting
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.192
Top resid features:
explosion
Token explosion
Feature activation+0.019
Top resid features:
caused
Token caused
Feature activation+0.022
Top resid features:
her
Token her
Feature activation+0.814
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
lose
Token lose
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
part
Token part
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.204
Top resid features:
herself
Token herself
Feature activation+0.749
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
her
Token her
Feature activation+0.358
Top resid features:
daughter
Token daughter
Feature activation+0.102
Top resid features:
but
Token but
Feature activation+0.011
Top resid features:
could
Token could
Feature activation+0.015
Top resid features:
Mr
Token Mr
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Greenberg
Token Greenberg
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
whom
Token whom
Feature activation+0.050
Top resid features:
she
Token she
Feature activation+1.429
Top resid features:
met
Token met
Feature activation+0.028
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
1950
Token 1950
Feature activation+0.041
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
with
Token with
Feature activation+0.021
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.193
Top resid features:
ley
Tokenley
Feature activation+0.047
Top resid features:
)
Token)
Feature activation+0.021
Top resid features:
by
Token by
Feature activation+0.019
Top resid features:
her
Token her
Feature activation+1.224
Top resid features:
side
Token side
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
help
Token help
Feature activation+0.027
Top resid features:
her
Token her
Feature activation+0.501
Top resid features:
lead
Token lead
Feature activation+0.003
Top resid features:
fre
Token fre
Feature activation+0.021
Top resid features:
aked
Tokenaked
Feature activation+0.021
Top resid features:
out
Token out
Feature activation+0.017
Top resid features:
further
Token further
Feature activation+0.011
Top resid features:
when
Token when
Feature activation+0.053
Top resid features:
she
Token she
Feature activation+1.096
Top resid features:
forb
Token forb
Feature activation+0.035
Top resid features:
ade
Tokenade
Feature activation+0.002
Top resid features:
him
Token him
Feature activation-0.040
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.188
Top resid features:
herself
Token herself
Feature activation+0.491
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
her
Token her
Feature activation+0.269
Top resid features:
daughter
Token daughter
Feature activation+0.085
Top resid features:
but
Token but
Feature activation+0.012
Top resid features:
could
Token could
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
book
Token book
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
Mary
Token Mary
Feature activation+0.544
Top resid features:
hurts
Token hurts
Feature activation+0.026
Top resid features:
her
Token her
Feature activation+0.662
Top resid features:
leg
Token leg
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
yells
Token yells
Feature activation+0.027
Top resid features:
at
Token at
Feature activation+0.017
Top resid features:
her
Token her
Feature activation+0.347
Top resid features:
Perfect
Token Perfect
Feature activation+0.008
Top resid features:
star
Token star
Feature activation+0.008
Top resid features:
Rebel
Token Rebel
Feature activation+0.008
Top resid features:
Wilson
Token Wilson
Feature activation+0.015
Top resid features:
says
Token says
Feature activation+0.022
Top resid features:
she
Token she
Feature activation+1.042
Top resid features:
usually
Token usually
Feature activation+0.005
Top resid features:
stays
Token stays
Feature activation+0.012
Top resid features:
far
Token far
Feature activation+0.005
Top resid features:
away
Token away
Feature activation+0.005
Top resid features:
from
Token from
Feature activation+0.019
Top resid features:
said
Token said
Feature activation+0.025
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
he
Token he
Feature activation-0.022
Top resid features:
started
Token started
Feature activation+0.014
Top resid features:
rubbing
Token rubbing
Feature activation+0.020
Top resid features:
her
Token her
Feature activation+0.690
Top resid features:
along
Token along
Feature activation+0.007
Top resid features:
her
Token her
Feature activation+0.338
Top resid features:
back
Token back
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
working
Token working
Feature activation+0.013
Top resid features:
English
Token English
Feature activation+0.008
Top resid features:
at
Token at
Feature activation+0.005
Top resid features:
all
Token all
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
So
Token So
Feature activation+0.009
Top resid features:
she
Token she
Feature activation+1.032
Top resid features:
wandered
Token wandered
Feature activation+0.015
Top resid features:
into
Token into
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
arrivals
Token arrivals
Feature activation-0.020
Top resid features:
hall
Token hall
Feature activation+0.008
Top resid features:
$
Token $
Feature activation+0.018
Top resid features:
20
Token20
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
000
Token000
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
she
Token she
Feature activation+1.001
Top resid features:
said
Token said
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
adding
Token adding
Feature activation+0.030
Top resid features:
that
Token that
Feature activation+0.036
Top resid features:
she
Token she
Feature activation+0.765
Top resid features:
Not
Token Not
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
But
TokenBut
Feature activation+0.015
Top resid features:
she
Token she
Feature activation+0.644
Top resid features:
can
Token can
Feature activation+0.012
Top resid features:
sit
Token sit
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
your
Token your
Feature activation+0.013
Top resid features:
university
Token university
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
Michelle
TokenMichelle
Feature activation+0.381
Top resid features:
Obama
Token Obama
Feature activation-0.030
Top resid features:
fed
Token fed
Feature activation+0.009
Top resid features:
her
Token her
Feature activation+0.828
Top resid features:
husband
Token husband
Feature activation+0.025
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
feud
Token feud
Feature activation+0.014
Top resid features:
with
Token with
Feature activation+0.009
Top resid features:
Donald
Token Donald
Feature activation-0.009
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.176
Top resid features:
herself
Token herself
Feature activation+0.285
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
her
Token her
Feature activation+0.176
Top resid features:
daughter
Token daughter
Feature activation+0.052
Top resid features:
but
Token but
Feature activation+0.013
Top resid features:
could
Token could
Feature activation+0.014
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.207
Top resid features:
her
Token her
Feature activation+2.117
Top resid features:
protest
Token protest
Feature activation+0.039
Top resid features:
ations
Tokenations
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.077
Top resid features:
Ċ
TokenĊ
Feature activation+0.067
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
having
Token having
Feature activation+0.013
Top resid features:
just
Token just
Feature activation+0.006
Top resid features:
finished
Token finished
Feature activation+0.002
Top resid features:
her
Token her
Feature activation+0.810
Top resid features:
last
Token last
Feature activation+0.010
Top resid features:
class
Token class
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
day
Token day
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
angel
Token angel
Feature activation+0.028
Top resid features:
Gabriel
Token Gabriel
Feature activation+0.036
Top resid features:
visits
Token visits
Feature activation+0.021
Top resid features:
Mary
Token Mary
Feature activation+0.844
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
tell
Token tell
Feature activation+0.017
Top resid features:
her
Token her
Feature activation+0.587
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
she
Token she
Feature activation+0.491
Top resid features:
Walker
Token Walker
Feature activation+0.030
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
Kelly
Token Kelly
Feature activation+0.153
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
said
Token said
Feature activation+0.051
Top resid features:
she
Token she
Feature activation+1.623
Top resid features:
had
Token had
Feature activation+0.051
Top resid features:
known
Token known
Feature activation+0.039
Top resid features:
Kelly
Token Kelly
Feature activation+0.109
Top resid features:
for
Token for
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
$
Token $
Feature activation+0.026
Top resid features:
20
Token20
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
000
Token000
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
she
Token she
Feature activation+1.040
Top resid features:
said
Token said
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
adding
Token adding
Feature activation+0.031
Top resid features:
that
Token that
Feature activation+0.040
Top resid features:
she
Token she
Feature activation+0.584
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.03

Head 3: 0.02

Head 4: 0.05

Head 5: 0.46

Head 6: 0.07

Head 7: 0.07

Head 8: 0.04

Head 9: 0.03

Head 10: 0.02

Head 11: 0.11

Positive logits

rig1.74

Ruler1.65

tabl1.63

Corona1.61

axis1.57

avatar1.55

Magn1.55

index1.53

ror1.52

advisory1.52

ut1.51

modelling1.46

AUT1.46

idi1.45

aternity1.45

relative1.45

azel1.44

dow1.44

nut1.44

rieve1.43

Negative logits

Bundy-1.89

acquaint-1.82

emis-1.79

Playoff-1.78

ende-1.77

SOLD-1.76

EW-1.75

Seah-1.72

EDITION-1.72

rongh-1.72

lease-1.71

Seller-1.67

adium-1.65

RELE-1.65

handc-1.63

seller-1.62

WN-1.61

CES-1.60

TD-1.60

deforestation-1.58

INTERVAL 1.765 - 1.961
CONTAINS 0.001%

in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.374
sent
Token sent
Feature activation+0.000
him
Token him
Feature activation+1.772
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.000
for
Token for
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
like
Token like
Feature activation+0.000
her
Token her
Feature activation+0.035
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.844
has
Token has
Feature activation+0.000
regrets
Token regrets
Feature activation+0.000
and
Token and
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
As
TokenAs
Feature activation+0.000
he
Token he
Feature activation+1.961
was
Token was
Feature activation+0.000
going
Token going
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.392
had
Token had
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
basement
Token basement
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.770
notes
Token notes
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.160
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
.
Token.
Feature activation+0.000
Through
Token Through
Feature activation+0.000
him
Token him
Feature activation+1.860
she
Token she
Feature activation+0.000
met
Token met
Feature activation+0.076
crucial
Token crucial
Feature activation+0.000
players
Token players
Feature activation+0.302
like
Token like
Feature activation+0.000

INTERVAL 1.569 - 1.765
CONTAINS 0.001%

she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
met
Token met
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+1.723
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
and
Token and
Feature activation+0.000
f
Token f
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
tail
Token tail
Feature activation+0.000
and
Token and
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+1.739
was
Token was
Feature activation+0.000
rubbing
Token rubbing
Feature activation+0.000
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
moving
Token moving
Feature activation+0.000
killed
Token killed
Feature activation+0.000
two
Token two
Feature activation+0.000
movie
Token movie
Feature activation+0.000
goers
Tokengoers
Feature activation+0.000
and
Token and
Feature activation+0.000
himself
Token himself
Feature activation+1.743
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.290
cheated
Token cheated
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
because
Token because
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.667
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
speedy
Token speedy
Feature activation+0.000
professor
Token professor
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.580
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
completely
Token completely
Feature activation+0.000
different
Token different
Feature activation+0.000
person
Token person
Feature activation+0.021

INTERVAL 1.373 - 1.569
CONTAINS 0.003%

year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
son
Token son
Feature activation+0.970
,
Token,
Feature activation+0.000
Andrew
Token Andrew
Feature activation+1.404
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
"
Token "
Feature activation+0.000
l
Tokenl
Feature activation+0.000
aid
Tokenaid
Feature activation+0.000
to
Token to
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
yet
Token yet
Feature activation+0.000
or
Token or
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+1.463
has
Token has
Feature activation+0.000
retained
Token retained
Feature activation+0.000
an
Token an
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+1.390
Ray
Token Ray
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.042
was
Token was
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+1.400
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
world
Token world
Feature activation+0.000
die
Token die
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.307
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+1.415
once
Token once
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
floor
Token floor
Feature activation+0.000

INTERVAL 1.177 - 1.373
CONTAINS 0.005%

money
Token money
Feature activation+0.000
and
Token and
Feature activation+0.000
Stead
Token Stead
Feature activation+0.000
man
Tokenman
Feature activation+0.000
killed
Token killed
Feature activation+0.000
himself
Token himself
Feature activation+1.184
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
dedication
Token dedication
Feature activation+0.000
to
Token to
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000
Albert
Token Albert
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+1.294
persisted
Token persisted
Feature activation+0.000
in
Token in
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
the
Token the
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
added
Token added
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
interview
Token interview
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+1.275
father
Token father
Feature activation+0.814
"
Token "
Feature activation+0.000
probably
Tokenprobably
Feature activation+0.000
did
Token did
Feature activation+0.000
a
Token a
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
he
Token he
Feature activation+1.259
said
Token said
Feature activation+0.000
/
Token/
Feature activation+0.000
she
Tokenshe
Feature activation+0.000
said
Token said
Feature activation+0.000
stories
Token stories
Feature activation+0.000
Ŀ
TokenĿ
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
He
TokenHe
Feature activation+1.247
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
consistency
Token consistency
Feature activation+0.000
about
Token about
Feature activation+0.000
him
Token him
Feature activation+1.111

INTERVAL 0.981 - 1.177
CONTAINS 0.008%

joy
Tokenjoy
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+1.020
is
Token is
Feature activation+0.000
well
Token well
Feature activation+0.000
studied
Token studied
Feature activation+0.000
in
Token in
Feature activation+0.000
astronomy
Token astronomy
Feature activation+0.000
which
Token which
Feature activation+0.000
Hol
Token Hol
Feature activation+0.000
comb
Tokencomb
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+1.021
alone
Token alone
Feature activation+0.000
could
Token could
Feature activation+0.000
reliably
Token reliably
Feature activation+0.000
command
Token command
Feature activation+0.000
Pence
Token Pence
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
stop
Token stop
Feature activation+0.000
college
Token college
Feature activation+0.000
guys
Token guys
Feature activation+1.154
from
Token from
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
links
Token links
Feature activation+0.000
from
Token from
Feature activation+0.000
Bro
Token Bro
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.132
how
Token how
Feature activation+0.000
years
Token years
Feature activation+0.000
after
Token after
Feature activation+0.000
their
Token their
Feature activation+1.141
divorce
Token divorce
Feature activation+0.000
his
Token his
Feature activation+1.491
painful
Token painful
Feature activation+0.000
words
Token words
Feature activation+0.000
led
Token led
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.000
niece
Token niece
Feature activation+0.857
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.352
brother
Token brother
Feature activation+1.170
so
Token so
Feature activation+0.000
she
Token she
Feature activation+0.385
could
Token could
Feature activation+0.000
go
Token go
Feature activation+0.000
see
Token see
Feature activation+0.000

INTERVAL 0.784 - 0.981
CONTAINS 0.015%

Tor
Token Tor
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
burn
Tokenburn
Feature activation+0.000
woman
Token woman
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.869
carried
Token carried
Feature activation+0.000
out
Token out
Feature activation+0.000
research
Token research
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.784
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
feature
Token feature
Feature activation+0.000
my
Token my
Feature activation+0.842
music
Token music
Feature activation+0.000
but
Token but
Feature activation+0.000
to
Token to
Feature activation+0.000
also
Token also
Feature activation+0.000
do
Token do
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
endorse
Token endorse
Feature activation+0.000
him
Token him
Feature activation+0.868
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
had
Token had
Feature activation+0.000
sex
Token sex
Feature activation+0.000
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.810
was
Token was
Feature activation+0.000
52
Token 52
Feature activation+0.000
and
Token and
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
little
Token little
Feature activation+0.000
children
Token children
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.790
presence
Token presence
Feature activation+0.000
just
Token just
Feature activation+0.000
made
Token made
Feature activation+0.000
me
Token me
Feature activation+0.124
feel
Token feel
Feature activation+0.000

INTERVAL 0.588 - 0.784
CONTAINS 0.016%

18
Token 18
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
his
Token his
Feature activation+0.720
editorial
Token editorial
Feature activation+0.000
,
Token,
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
oen
Tokenoen
Feature activation+0.000
highlights
Token highlights
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
boy
Token boy
Feature activation+0.721
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
pulled
Token pulled
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
I
Token I
Feature activation+0.158
really
Token really
Feature activation+0.000
like
Token like
Feature activation+0.000
them
Token them
Feature activation+0.751
both
Token both
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.188
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
They
TokenThey
Feature activation+0.627
are
Token are
Feature activation+0.000
wasting
Token wasting
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
'
Token'
Feature activation+0.000
money
Token money
Feature activation+0.000
ark
Tokenark
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
leaps
Token leaps
Feature activation+0.000
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.736
bed
Token bed
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 0.392 - 0.588
CONTAINS 0.028%

s
Token s
Feature activation+0.000
ips
Tokenips
Feature activation+0.000
of
Token of
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
between
Token between
Feature activation+0.000
his
Token his
Feature activation+0.397
sentences
Token sentences
Feature activation+0.000
,
Token,
Feature activation+0.000
without
Token without
Feature activation+0.000
it
Token it
Feature activation+0.000
his
Token his
Feature activation+0.202
their
Token their
Feature activation+0.538
own
Token own
Feature activation+0.000
box
Token box
Feature activation+0.000
and
Token and
Feature activation+0.000
express
Token express
Feature activation+0.000
their
Token their
Feature activation+0.481
love
Token love
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.424
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
Yale
Token Yale
Feature activation+0.000
University
Token University
Feature activation+0.000
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
;
Token;
Feature activation+0.000
she
Token she
Feature activation+0.515
currently
Token currently
Feature activation+0.000
serves
Token serves
Feature activation+0.000
as
Token as
Feature activation+0.000
Assistant
Token Assistant
Feature activation+0.000
Professor
Token Professor
Feature activation+0.000
almost
Token almost
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.931
got
Token got
Feature activation+0.000
hers
Token hers
Feature activation+0.543
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
adult
Token adult
Feature activation+0.011
range
Token range
Feature activation+0.000
at
Token at
Feature activation+0.000
.
Token.
Feature activation+0.000
Jane
Token Jane
Feature activation+0.361
Ey
Token Ey
Feature activation+0.000
re
Tokenre
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.465
argues
Token argues
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
truth
Token truth
Feature activation+0.000

INTERVAL 0.196 - 0.392
CONTAINS 0.056%

overweight
Token overweight
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
woman
Token woman
Feature activation+0.270
says
Token says
Feature activation+0.000
if
Token if
Feature activation+0.000
she
Token she
Feature activation+0.000
sees
Token sees
Feature activation+0.000
a
Token a
Feature activation+0.000
to
Token to
Feature activation+0.000
H
Token H
Feature activation+0.000
arts
Tokenarts
Feature activation+0.000
down
Tokendown
Feature activation+0.000
Academy
Token Academy
Feature activation+0.000
herself
Token herself
Feature activation+0.256
after
Token after
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.221
husband
Token husband
Feature activation+1.045
"
Token "
Feature activation+0.000
They
TokenThey
Feature activation+0.800
are
Token are
Feature activation+0.000
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.345
are
Token are
Feature activation+0.000
doing
Token doing
Feature activation+0.000
many
Token many
Feature activation+0.000
things
Token things
Feature activation+0.000
for
Token for
Feature activation+0.000
much
Token much
Feature activation+0.000
understood
Token understood
Feature activation+0.000
her
Token her
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.258
explained
Token explained
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.127
Academy
Token Academy
Feature activation+0.000
herself
Token herself
Feature activation+0.256
after
Token after
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.221
husband
Token husband
Feature activation+1.045
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
teenager
Token teenager
Feature activation+0.015
had
Token had
Feature activation+0.000

INTERVAL 0.000 - 0.196
CONTAINS 99.866%

approved
Token approved
Feature activation+0.000
an
Token an
Feature activation+0.000
extension
Token extension
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Right
Token Right
Feature activation+0.000
to
Token to
Feature activation+0.000
Try
Token Try
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
law
Token law
Feature activation+0.000
secondary
Token secondary
Feature activation+0.000
Share
Token Share
Feature activation+0.000
This
Token This
Feature activation+0.000
Story
Token Story
Feature activation+0.000
On
Token On
Feature activation+0.000
...
Token...
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Facebook
TokenFacebook
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
the
Token the
Feature activation+0.000
function
Token function
Feature activation+0.000
environment
Token environment
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+0.000
of
Token of
Feature activation+0.000
small
Token small
Feature activation+0.000
modular
Token modular
Feature activation+0.000
reactors
Token reactors
Feature activation+0.000
(
Token (
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+0.000
Earlier
Token Earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
ethic
Token ethic
Feature activation+0.000
beats
Token beats
Feature activation+0.000
talent
Token talent
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
38
Token 38
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
,
Token,
Feature activation+0.000
safe
Token safe
Feature activation+0.000
for
Token for
Feature activation+0.000
work
Token work
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H1.5: (feature 2008)

TOP ACTIVATIONS
MAX = 2.536

of
Token of
Feature activation+0.000
presence
Token presence
Feature activation+0.000
.[
Token.[
Feature activation+0.000
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.000
7
Token7
Feature activation+2.536
]
Token]
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
correct
Token correct
Feature activation+0.000
viewing
Token viewing
Feature activation+0.000
China
Token China
Feature activation+0.000
.[
Token.[
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
[
Token [
Feature activation+0.000
7
Token7
Feature activation+2.505
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
more
Token more
Feature activation+0.000
/
Token /
Feature activation+0.000
6
Token 6
Feature activation+0.010
28
Token28
Feature activation+0.000
315
Token315
Feature activation+0.000
/
Token /
Feature activation+0.000
7
Token 7
Feature activation+2.174
17
Token17
Feature activation+0.000
228
Token228
Feature activation+0.000
/
Token /
Feature activation+0.000
9
Token 9
Feature activation+0.890
36
Token36
Feature activation+0.000
erson
Tokenerson
Feature activation+0.000
68
Token 68
Feature activation+0.000
âĢ²
TokenâĢ²
Feature activation+0.000
),
Token),
Feature activation+0.000
Oliver
Token Oliver
Feature activation+0.000
7
Token 7
Feature activation+2.149
(
Token (
Feature activation+0.000
Jar
TokenJar
Feature activation+0.000
un
Tokenun
Feature activation+0.000
75
Token 75
Feature activation+0.000
âĢ²
TokenâĢ²
Feature activation+0.000
5
Token5
Feature activation+0.000
âĪĴ
Token âĪĴ
Feature activation+0.000
6
Token 6
Feature activation+0.000
)
Token)
Feature activation+0.000
ÃĹ
Token ÃĹ
Feature activation+0.000
7
Token 7
Feature activation+2.139
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
can
Tokencan
Feature activation+0.000
be
Token be
Feature activation+0.000
written
Token written
Feature activation+0.000
Offensive
Token Offensive
Feature activation+0.000
(
Token (
Feature activation+0.000
2013
Token2013
Feature activation+0.000
),
Token),
Feature activation+0.000
[
Token[
Feature activation+0.000
7
Token7
Feature activation+2.115
]
Token]
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Read
Token Read
Feature activation+0.000
Free
Token Free
Feature activation+0.000
.
Token.
Feature activation+0.000
Frank
Token Frank
Feature activation+0.000
l
Tokenl
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
7
Token7
Feature activation+2.114
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
changes
Token changes
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
suitable
Token suitable
Feature activation+0.000
for
Token for
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
testing
Token testing
Feature activation+0.000
.[
Token.[
Feature activation+0.000
7
Token7
Feature activation+2.106
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
secret
Token secret
Feature activation+0.000
lands
Tokenlands
Feature activation+0.000
of
Token of
Feature activation+0.000
central
Token central
Feature activation+0.000
India
Token India
Feature activation+0.000
[
Token [
Feature activation+0.000
7
Token7
Feature activation+2.074
].
Token].
Feature activation+0.000
Based
Token Based
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
talk
Token talk
Feature activation+0.000
210
Token210
Feature activation+0.000
!
Token!
Feature activation+0.000
(
Token (
Feature activation+0.000
after
Tokenafter
Feature activation+0.000
January
Token January
Feature activation+0.000
7
Token 7
Feature activation+2.063
th
Tokenth
Feature activation+0.000
$
Token $
Feature activation+0.000
240
Token240
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
summer
Token summer
Feature activation+0.000
continental
Token continental
Feature activation+0.000
climate
Token climate
Feature activation+0.000
zone
Token zone
Feature activation+0.000
[
Token[
Feature activation+0.000
7
Token7
Feature activation+2.036
]
Token]
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
exception
Token exception
Feature activation+0.000
of
Token of
Feature activation+0.000
built
Token built
Feature activation+0.000
up
Token up
Feature activation+0.000
6
Token 6
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
7
Token 7
Feature activation+2.028
kills
Token kills
Feature activation+0.000
/
Token/
Feature activation+0.000
st
Tokenst
Feature activation+0.000
uns
Tokenuns
Feature activation+0.000
needed
Token needed
Feature activation+0.000
RCMP
Token RCMP
Feature activation+0.000
at
Token at
Feature activation+0.000
50
Token 50
Feature activation+0.000
6
Token6
Feature activation+0.057
-
Token-
Feature activation+0.000
8
Token8
Feature activation+1.991
57
Token57
Feature activation+0.000
-
Token-
Feature activation+0.000
24
Token24
Feature activation+0.000
00
Token00
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
theatre
Token theatre
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
7
Token 7
Feature activation+1.987
£
Token £
Feature activation+0.000
31
Token31
Feature activation+0.000
,
Token,
Feature activation+0.000
07
Token07
Feature activation+0.000
2
Token2
Feature activation+0.000
X
Token X
Feature activation+0.000
code
Tokencode
Feature activation+0.000
6
Token 6
Feature activation+0.000
and
Token and
Feature activation+0.000
iOS
Token iOS
Feature activation+0.000
8
Token 8
Feature activation+1.978
,
Token,
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
have
Token have
Feature activation+0.000
created
Token created
Feature activation+0.000
a
Token a
Feature activation+0.000
sales
Token sales
Feature activation+0.000
also
Token also
Feature activation+0.000
dropped
Token dropped
Feature activation+0.000
0
Token 0
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+1.916
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
period
Token period
Feature activation+0.000
to
Token to
Feature activation+0.000
50
Token50
Feature activation+0.000
ft
Token ft
Feature activation+0.000
Range
Token Range
Feature activation+0.000
1200
Token 1200
Feature activation+0.000
km
Token km
Feature activation+0.000
7
Token 7
Feature activation+1.905
46
Token46
Feature activation+0.000
miles
Token miles
Feature activation+0.000
Comments
Token Comments
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
Atari
Token Atari
Feature activation+0.000
Buff
TokenBuff
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
7
Token7
Feature activation+1.904
.
Token.
Feature activation+0.000
m
Token m
Feature activation+0.000
j
Tokenj
Feature activation+0.000
arn
Tokenarn
Feature activation+0.000
old
Tokenold
Feature activation+0.000
99
Token99
Feature activation+0.000
/
Token/
Feature activation+0.000
month
Tokenmonth
Feature activation+0.000
for
Token for
Feature activation+0.000
months
Token months
Feature activation+0.000
7
Token 7
Feature activation+1.896
-
Token -
Feature activation+0.000
9
Token 9
Feature activation+0.709
,
Token,
Feature activation+0.000
$
Token $
Feature activation+0.000
13
Token13
Feature activation+0.000
2
Token 2
Feature activation+0.000
3
Token 3
Feature activation+0.000
4
Token 4
Feature activation+0.000
5
Token 5
Feature activation+0.000
6
Token 6
Feature activation+0.000
7
Token 7
Feature activation+1.876
8
Token 8
Feature activation+1.188
9
Token 9
Feature activation+0.312
10
Token 10
Feature activation+0.000
11
Token 11
Feature activation+0.000
12
Token 12
Feature activation+0.000

Top DFA by src position
MAX = 3.068

increased
Token increased
Feature activation+0.001
Top resid features:
feeling
Token feeling
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
presence
Token presence
Feature activation+0.005
Top resid features:
.[
Token.[
Feature activation+0.082
Top resid features:
6
Token6
Feature activation+3.068
Top resid features:
][
Token][
Feature activation+0.041
Top resid features:
7
Token7
Feature activation+0.347
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Thus
Token Thus
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
them
Token them
Feature activation-0.015
Top resid features:
today
Token today
Feature activation-0.015
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
China
Token China
Feature activation-0.030
Top resid features:
.[
Token.[
Feature activation+0.059
Top resid features:
6
Token6
Feature activation+2.988
Top resid features:
]
Token]
Feature activation+0.007
Top resid features:
[
Token [
Feature activation+0.145
Top resid features:
7
Token7
Feature activation+0.455
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
:
Token:
Feature activation+0.021
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.017
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.007
Top resid features:
/
Token /
Feature activation+0.044
Top resid features:
6
Token 6
Feature activation+1.899
Top resid features:
28
Token28
Feature activation+0.022
Top resid features:
315
Token315
Feature activation+0.026
Top resid features:
/
Token /
Feature activation+0.076
Top resid features:
7
Token 7
Feature activation+0.347
Top resid features:
17
Token17
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.006
Top resid features:
D
Token D
Feature activation-0.002
Top resid features:
ant
Tokenant
Feature activation-0.007
Top resid features:
as
Tokenas
Feature activation-0.005
Top resid features:
6
Token 6
Feature activation+1.613
Top resid features:
(
Token (
Feature activation-0.005
Top resid features:
He
TokenHe
Feature activation-0.003
Top resid features:
inem
Tokeninem
Feature activation-0.006
Top resid features:
ann
Tokenann
Feature activation-0.005
Top resid features:
62
Token 62
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
(
Token(
Feature activation+0.006
Top resid features:
5
Token5
Feature activation+0.061
Top resid features:
âĪĴ
Token âĪĴ
Feature activation+0.031
Top resid features:
6
Token 6
Feature activation+2.835
Top resid features:
)
Token)
Feature activation+0.045
Top resid features:
ÃĹ
Token ÃĹ
Feature activation+0.005
Top resid features:
7
Token 7
Feature activation+0.357
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
event
Token event
Feature activation-0.006
Top resid features:
(
Token (
Feature activation-0.006
Top resid features:
2010
Token2010
Feature activation+0.006
Top resid features:
),
Token),
Feature activation+0.005
Top resid features:
[
Token[
Feature activation-0.004
Top resid features:
6
Token6
Feature activation+2.562
Top resid features:
]
Token]
Feature activation-0.002
Top resid features:
The
Token The
Feature activation-0.018
Top resid features:
Barcl
Token Barcl
Feature activation-0.007
Top resid features:
ay
Tokenay
Feature activation-0.005
Top resid features:
card
Tokencard
Feature activation+0.005
Top resid features:
S
Token S
Feature activation-0.010
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Lewis
Token Lewis
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
6
Token6
Feature activation+2.836
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
When
Token When
Feature activation-0.008
Top resid features:
we
Token we
Feature activation-0.012
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
no
Token no
Feature activation-0.006
Top resid features:
Korea
Token Korea
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Yugoslavia
Token Yugoslavia
Feature activation-0.002
Top resid features:
.[
Token.[
Feature activation+0.004
Top resid features:
6
Token6
Feature activation+2.707
Top resid features:
]
Token]
Feature activation-0.002
Top resid features:
U
Token U
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
Hindi
Token Hindi
Feature activation+0.003
Top resid features:
belt
Token belt
Feature activation+0.004
Top resid features:
[
Token [
Feature activation+0.014
Top resid features:
6
Token6
Feature activation+2.463
Top resid features:
],
Token],
Feature activation-0.013
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
tribal
Token tribal
Feature activation-0.015
Top resid features:
heart
Token heart
Feature activation-0.017
Top resid features:
)
Token)
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Team
TokenTeam
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
6
Token 6
Feature activation+2.574
Top resid features:
-
Token -
Feature activation+0.011
Top resid features:
Now
Token Now
Feature activation+0.002
Top resid features:
$
Token $
Feature activation+0.002
Top resid features:
210
Token210
Feature activation-0.004
Top resid features:
!
Token!
Feature activation+0.009
Top resid features:
with
Token with
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
Polar
Token Polar
Feature activation-0.008
Top resid features:
climate
Token climate
Feature activation-0.010
Top resid features:
.[
Token.[
Feature activation+0.009
Top resid features:
6
Token6
Feature activation+2.419
Top resid features:
]
Token]
Feature activation-0.003
Top resid features:
Land
Token Land
Feature activation-0.011
Top resid features:
locked
Tokenlocked
Feature activation-0.002
Top resid features:
areas
Token areas
Feature activation-0.010
Top resid features:
tend
Token tend
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
ve
Tokenve
Feature activation+0.018
Top resid features:
built
Token built
Feature activation+0.008
Top resid features:
up
Token up
Feature activation+0.006
Top resid features:
6
Token 6
Feature activation+2.761
Top resid features:
out
Token out
Feature activation+0.031
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
7
Token 7
Feature activation+0.372
Top resid features:
kills
Token kills
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
iac
Tokeniac
Feature activation-0.011
Top resid features:
Regional
Token Regional
Feature activation-0.021
Top resid features:
RCMP
Token RCMP
Feature activation+0.024
Top resid features:
at
Token at
Feature activation+0.025
Top resid features:
50
Token 50
Feature activation-0.017
Top resid features:
6
Token6
Feature activation+2.627
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
8
Token8
Feature activation+0.512
Top resid features:
57
Token57
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
24
Token24
Feature activation+0.000
Top resid features:
level
Token level
Feature activation-0.016
Top resid features:
nurse
Token nurse
Feature activation-0.002
Top resid features:
or
Token or
Feature activation-0.011
Top resid features:
mid
Token mid
Feature activation-0.004
Top resid features:
wife
Tokenwife
Feature activation+0.004
Top resid features:
6
Token 6
Feature activation+2.662
Top resid features:
£
Token £
Feature activation-0.002
Top resid features:
26
Token26
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
041
Token041
Feature activation+0.008
Top resid features:
-
Token -
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Now
TokenNow
Feature activation-0.006
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
code
Tokencode
Feature activation-0.001
Top resid features:
6
Token 6
Feature activation+2.642
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
iOS
Token iOS
Feature activation-0.033
Top resid features:
8
Token 8
Feature activation+0.422
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Apple
Token Apple
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
$
Token $
Feature activation-0.006
Top resid features:
47
Token47
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
6
Token6
Feature activation+2.475
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
million
Tokenmillion
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
digital
Token digital
Feature activation-0.018
Top resid features:
sales
Token sales
Feature activation-0.018
Top resid features:
Ce
Token Ce
Feature activation+0.000
Top resid features:
iling
Tokeniling
Feature activation-0.003
Top resid features:
198
Token 198
Feature activation-0.028
Top resid features:
00
Token00
Feature activation+0.001
Top resid features:
m
Token m
Feature activation+0.008
Top resid features:
6
Token 6
Feature activation+2.716
Top resid features:
49
Token49
Feature activation+0.003
Top resid features:
50
Token50
Feature activation-0.004
Top resid features:
ft
Token ft
Feature activation+0.010
Top resid features:
Range
Token Range
Feature activation-0.032
Top resid features:
1200
Token 1200
Feature activation+0.004
Top resid features:
Token
Feature activation-0.003
Top resid features:
ian
Tokenian
Feature activation-0.012
Top resid features:
oid
Tokenoid
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
6
Token6
Feature activation+2.346
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Atari
Token Atari
Feature activation+0.067
Top resid features:
Buff
TokenBuff
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
month
Tokenmonth
Feature activation-0.014
Top resid features:
for
Token for
Feature activation-0.005
Top resid features:
months
Token months
Feature activation-0.008
Top resid features:
4
Token 4
Feature activation+0.037
Top resid features:
-
Token -
Feature activation+0.011
Top resid features:
6
Token 6
Feature activation+2.625
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
$
Token $
Feature activation-0.001
Top resid features:
10
Token10
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
99
Token99
Feature activation+0.010
Top resid features:
1
Token 1
Feature activation+0.006
Top resid features:
2
Token 2
Feature activation+0.022
Top resid features:
3
Token 3
Feature activation+0.009
Top resid features:
4
Token 4
Feature activation+0.038
Top resid features:
5
Token 5
Feature activation+0.165
Top resid features:
6
Token 6
Feature activation+2.392
Top resid features:
7
Token 7
Feature activation+0.278
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
9
Token 9
Feature activation+0.000
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
11
Token 11
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.12

Head 1: 0.06

Head 2: 0.03

Head 3: 0.02

Head 4: 0.04

Head 5: 0.46

Head 6: 0.03

Head 7: 0.04

Head 8: 0.02

Head 9: 0.03

Head 10: 0.02

Head 11: 0.12

Positive logits

ETH1.82

ainer1.81

rm1.76

DPR1.73

BN1.69

Bah1.63

DOD1.61

Trident1.61

DNS1.58

Uri1.56

Aad1.55

brig1.52

apter1.51

electroly1.51

1.50

tooth1.50

1.49

Clean1.49

Crusader1.49

ulia1.47

Negative logits

Klux-1.82

leys-1.78

cised-1.75

Introduced-1.74

Heights-1.68

Scully-1.67

stalk-1.67

cig-1.63

OTOS-1.61

ULTS-1.61

sung-1.60

uncanny-1.60

lumin-1.59

animous-1.59

TABLE-1.58

Street-1.58

omic-1.56

plays-1.54

-1.54

Lovecraft-1.52

INTERVAL 2.282 - 2.536
CONTAINS 0.000%

of
Token of
Feature activation+0.000
presence
Token presence
Feature activation+0.000
.[
Token.[
Feature activation+0.000
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.000
7
Token7
Feature activation+2.536
]
Token]
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
correct
Token correct
Feature activation+0.000
viewing
Token viewing
Feature activation+0.000
China
Token China
Feature activation+0.000
.[
Token.[
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
[
Token [
Feature activation+0.000
7
Token7
Feature activation+2.505
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
more
Token more
Feature activation+0.000

INTERVAL 2.029 - 2.282
CONTAINS 0.001%

Offensive
Token Offensive
Feature activation+0.000
(
Token (
Feature activation+0.000
2013
Token2013
Feature activation+0.000
),
Token),
Feature activation+0.000
[
Token[
Feature activation+0.000
7
Token7
Feature activation+2.115
]
Token]
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Read
Token Read
Feature activation+0.000
Free
Token Free
Feature activation+0.000
suitable
Token suitable
Feature activation+0.000
for
Token for
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
testing
Token testing
Feature activation+0.000
.[
Token.[
Feature activation+0.000
7
Token7
Feature activation+2.106
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
secret
Token secret
Feature activation+0.000
210
Token210
Feature activation+0.000
!
Token!
Feature activation+0.000
(
Token (
Feature activation+0.000
after
Tokenafter
Feature activation+0.000
January
Token January
Feature activation+0.000
7
Token 7
Feature activation+2.063
th
Tokenth
Feature activation+0.000
$
Token $
Feature activation+0.000
240
Token240
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token5
Feature activation+0.000
âĪĴ
Token âĪĴ
Feature activation+0.000
6
Token 6
Feature activation+0.000
)
Token)
Feature activation+0.000
ÃĹ
Token ÃĹ
Feature activation+0.000
7
Token 7
Feature activation+2.139
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
can
Tokencan
Feature activation+0.000
be
Token be
Feature activation+0.000
written
Token written
Feature activation+0.000
/
Token /
Feature activation+0.000
6
Token 6
Feature activation+0.010
28
Token28
Feature activation+0.000
315
Token315
Feature activation+0.000
/
Token /
Feature activation+0.000
7
Token 7
Feature activation+2.174
17
Token17
Feature activation+0.000
228
Token228
Feature activation+0.000
/
Token /
Feature activation+0.000
9
Token 9
Feature activation+0.890
36
Token36
Feature activation+0.000

INTERVAL 1.775 - 2.029
CONTAINS 0.002%

1
Token1
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
2000
Token 2000
Feature activation+0.000
.[
Token.[
Feature activation+0.000
7
Token7
Feature activation+1.788
]
Token]
Feature activation+0.000
Ecuador
Token Ecuador
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
first
Token first
Feature activation+0.000
started
Token started
Feature activation+0.000
6
Token 6
Feature activation+0.193
.
Token.
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
:
Token:
Feature activation+0.000
8
Token 8
Feature activation+1.414
7
Token 7
Feature activation+1.802
.
Token.
Feature activation+0.000
Connecticut
Token Connecticut
Feature activation+0.000
:
Token:
Feature activation+0.000
8
Token 8
Feature activation+1.307
.
Token.
Feature activation+0.000
from
Token from
Feature activation+0.000
6
Token 6
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
-
Token -
Feature activation+0.000
7
Token 7
Feature activation+1.796
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
pm
Token pm
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
50
Token50
Feature activation+0.000
ft
Token ft
Feature activation+0.000
Range
Token Range
Feature activation+0.000
1200
Token 1200
Feature activation+0.000
km
Token km
Feature activation+0.000
7
Token 7
Feature activation+1.905
46
Token46
Feature activation+0.000
miles
Token miles
Feature activation+0.000
Comments
Token Comments
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000
X
Token X
Feature activation+0.000
code
Tokencode
Feature activation+0.000
6
Token 6
Feature activation+0.000
and
Token and
Feature activation+0.000
iOS
Token iOS
Feature activation+0.000
8
Token 8
Feature activation+1.978
,
Token,
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
have
Token have
Feature activation+0.000
created
Token created
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.522 - 1.775
CONTAINS 0.002%

(
Token (
Feature activation+0.000
62
Token62
Feature activation+0.000
people
Token people
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
7
Token 7
Feature activation+1.561
%
Token%
Feature activation+0.000
(
Token (
Feature activation+0.000
23
Token23
Feature activation+0.000
people
Token people
Feature activation+0.000
)
Token)
Feature activation+0.000
][
Token][
Feature activation+0.000
5
Token5
Feature activation+0.000
][
Token][
Feature activation+0.000
6
Token6
Feature activation+0.000
][
Token][
Feature activation+0.000
7
Token7
Feature activation+1.719
][
Token][
Feature activation+0.000
8
Token8
Feature activation+1.142
][
Token][
Feature activation+0.000
9
Token9
Feature activation+0.213
]
Token]
Feature activation+0.000
-
Token-
Feature activation+0.000
cl
Tokencl
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
drug
Token drug
Feature activation+0.000
7
Token 7
Feature activation+1.628
.
Token.
Feature activation+0.000
Hum
Token Hum
Feature activation+0.000
ira
Tokenira
Feature activation+0.000
,
Token,
Feature activation+0.000
arthritis
Token arthritis
Feature activation+0.000
290
Token290
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.297
m
Tokenm
Feature activation+0.000
,
Token,
Feature activation+0.000
7
Token 7
Feature activation+1.606
Man
Token Man
Feature activation+0.000
City
Token City
Feature activation+0.000
âĤ¬
Token âĤ¬
Feature activation+0.000
285
Token285
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token 5
Feature activation+0.264
.
Token.
Feature activation+0.000
Rhode
Token Rhode
Feature activation+0.000
Island
Token Island
Feature activation+0.000
:
Token:
Feature activation+0.000
7
Token 7
Feature activation+1.689
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
6
Token 6
Feature activation+0.193
.
Token.
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000

INTERVAL 1.268 - 1.522
CONTAINS 0.002%

year
Token year
Feature activation+0.000
of
Token of
Feature activation+0.000
college
Token college
Feature activation+0.000
eligibility
Token eligibility
Feature activation+0.000
.[
Token.[
Feature activation+0.000
7
Token7
Feature activation+1.486
]
Token]
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Code
TokenCode
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
nice
Token nice
Feature activation+0.000
lump
Token lump
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
8
Token8
Feature activation+1.383
$.
Token$.
Feature activation+0.000
Feed
Token Feed
Feature activation+0.000
him
Token him
Feature activation+0.000
$
Token $
Feature activation+0.000
2
Token2
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
>
Token >
Feature activation+0.000
6
Token6
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+1.480
Mars
Token Mars
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
activity
Token activity
Feature activation+0.000
!
Token!
Feature activation+0.000
imeter
Tokenimeter
Feature activation+0.000
on
Token on
Feature activation+0.000
February
Token February
Feature activation+0.000
6
Token 6
Feature activation+0.000
February
Token February
Feature activation+0.000
7
Token 7
Feature activation+1.487
,
Token,
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
will
Token will
Feature activation+0.000
discuss
Token discuss
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+0.000
to
Token to
Feature activation+0.000
decom
Token decom
Feature activation+0.000
pose
Tokenpose
Feature activation+0.000
.(
Token.(
Feature activation+0.000
7
Token7
Feature activation+1.432
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Target
TokenTarget
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.014 - 1.268
CONTAINS 0.004%

double
Tokendouble
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
epic
Token epic
Feature activation+0.000
Game
Token Game
Feature activation+0.000
7
Token 7
Feature activation+1.263
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
remembered
Token remembered
Feature activation+0.000
for
Token for
Feature activation+0.000
t
Tokent
Feature activation+0.000
played
Token played
Feature activation+0.000
for
Token for
Feature activation+0.000
six
Token six
Feature activation+0.000
or
Token or
Feature activation+0.000
seven
Token seven
Feature activation+1.173
weeks
Token weeks
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
had
Token had
Feature activation+0.000
3
Token 3
Feature activation+0.000
4
Token 4
Feature activation+0.000
5
Token 5
Feature activation+0.000
6
Token 6
Feature activation+0.000
7
Token 7
Feature activation+1.876
8
Token 8
Feature activation+1.188
9
Token 9
Feature activation+0.312
10
Token 10
Feature activation+0.000
11
Token 11
Feature activation+0.000
12
Token 12
Feature activation+0.000
13
Token 13
Feature activation+0.000
in
Token in
Feature activation+0.000
2024
Token 2024
Feature activation+0.000
-
Token-
Feature activation+0.000
20
Token20
Feature activation+0.000
25
Token25
Feature activation+0.000
seven
Token seven
Feature activation+1.055
Ang
Token Ang
Feature activation+0.000
ara
Tokenara
Feature activation+0.000
-
Token-
Feature activation+0.000
A
TokenA
Feature activation+0.000
5
Token5
Feature activation+0.000
!
Token!
Feature activation+0.000
Kind
Token Kind
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
Offensive
Token Offensive
Feature activation+0.000
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+1.142
]
Token]
Feature activation+0.000
The
Token The
Feature activation+0.000
large
Token large
Feature activation+0.000
scale
Token scale
Feature activation+0.000
2014
Token 2014
Feature activation+0.000

INTERVAL 0.761 - 1.014
CONTAINS 0.004%

Lot
Token Lot
Feature activation+0.000
"
Token"
Feature activation+0.000
4
Token 4
Feature activation+0.000
:
Token:
Feature activation+0.000
46
Token46
Feature activation+0.000
8
Token 8
Feature activation+0.855
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Joy
TokenJoy
Feature activation+0.000
City
Token City
Feature activation+0.000
"
Token"
Feature activation+0.000
be
Token be
Feature activation+0.000
judged
Token judged
Feature activation+0.000
after
Token after
Feature activation+0.000
six
Token six
Feature activation+0.000
,
Token,
Feature activation+0.000
eight
Token eight
Feature activation+0.781
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
12
Token 12
Feature activation+0.000
months
Token months
Feature activation+0.000
.
Token.
Feature activation+0.000
/
Token /
Feature activation+0.000
7
Token 7
Feature activation+2.174
17
Token17
Feature activation+0.000
228
Token228
Feature activation+0.000
/
Token /
Feature activation+0.000
9
Token 9
Feature activation+0.890
36
Token36
Feature activation+0.000
557
Token557
Feature activation+0.000
/
Token /
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
9
Token 9
Feature activation+0.270
11
Token 11
Feature activation+0.000
17
Token 17
Feature activation+0.000
8
Token 8
Feature activation+0.913
.
Token.
Feature activation+0.000
96
Token96
Feature activation+0.000
Notre
Token Notre
Feature activation+0.000
Dame
Token Dame
Feature activation+0.000
6
Token 6
Feature activation+0.000
1
Token1
Feature activation+0.000
)
Token)
Feature activation+0.000
âĪĴ
Token âĪĴ
Feature activation+0.000
41
Token41
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.772
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
âĪĴ
TokenâĪĴ
Feature activation+0.000
43
Token43
Feature activation+0.000

INTERVAL 0.507 - 0.761
CONTAINS 0.006%

In
Token In
Feature activation+0.000
14
Token 14
Feature activation+0.000
November
Token November
Feature activation+0.000
1922
Token 1922
Feature activation+0.000
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.627
]
Token]
Feature activation+0.000
W
Token W
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
14
Token 14
Feature activation+0.000
15
Token 15
Feature activation+0.000
18
Token 18
Feature activation+0.000
9
Token 9
Feature activation+0.691
.
Token.
Feature activation+0.000
82
Token82
Feature activation+0.000
Nebraska
Token Nebraska
Feature activation+0.000
7
Token 7
Feature activation+1.758
-
Token-
Feature activation+0.000
e
Tokene
Feature activation+0.000
3
Token3
Feature activation+0.000
e
Tokene
Feature activation+0.000
2
Token2
Feature activation+0.000
O
TokenO
Feature activation+0.000
8
Token8
Feature activation+0.546
D
TokenD
Feature activation+0.000
f
Tokenf
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
w
Tokenw
Feature activation+0.000
8
Token8
Feature activation+0.469
:
Token:
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
/
Token/
Feature activation+0.000
5
Token5
Feature activation+0.536
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
25
Token 25
Feature activation+0.000
39
Token39
Feature activation+0.000
votes
Token votes
Feature activation+0.000
giving
Token giving
Feature activation+0.000
A
Token A
Feature activation+0.000
&
Token&
Feature activation+0.000
M
TokenM
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.743
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
margin
Token margin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.254 - 0.507
CONTAINS 0.010%

(
Token (
Feature activation+0.000
6
Token6
Feature activation+0.000
oz
Token oz
Feature activation+0.000
bag
Token bag
Feature activation+0.000
,
Token,
Feature activation+0.000
8
Token 8
Feature activation+0.416
cups
Token cups
Feature activation+0.000
)
Token)
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
women
Token women
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+0.000
4
Token4
Feature activation+0.359
,
Token,
Feature activation+0.000
A
Token A
Feature activation+0.000
5
Token5
Feature activation+0.297
and
Token and
Feature activation+0.000
A
Token A
Feature activation+0.000
and
Token and
Feature activation+0.000
increased
Token increased
Feature activation+0.000
stroke
Token stroke
Feature activation+0.000
rate
Token rate
Feature activation+0.000
.[
Token.[
Feature activation+0.000
9
Token9
Feature activation+0.272
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
nature
Token nature
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
7
Token 7
Feature activation+1.683
10
Token 10
Feature activation+0.256
7
Token 7
Feature activation+1.637
10
Token 10
Feature activation+0.359
.
Token.
Feature activation+0.000
37
Token37
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
State
Token State
Feature activation+0.000
7
Token 7
Feature activation+1.596
Thunder
Token Thunder
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
playoff
Token playoff
Feature activation+0.000
game
Token game
Feature activation+0.000
did
Token did
Feature activation+0.000
8
Token 8
Feature activation+0.469
.
Token.
Feature activation+0.000
71
Token71
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.254
CONTAINS 99.970%

sensors
Token sensors
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
and
Token and
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
plot
Token plot
Feature activation+0.000
courses
Token courses
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
collisions
Token collisions
Feature activation+0.000
day
Token day
Feature activation+0.000
to
Token to
Feature activation+0.000
day
Token day
Feature activation+0.000
is
Token is
Feature activation+0.000
spectacular
Token spectacular
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
helped
Token helped
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
%
Token%
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
delay
Token delay
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
circle
Token circle
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
red
Token red
Feature activation+0.000
was
Token was
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tour
Token tour
Feature activation+0.000
party
Token party
Feature activation+0.000
that
Token that
Feature activation+0.000
travels
Token travels
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
USA
Token USA
Feature activation+0.000
on
Token on
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
modern
Token modern
Feature activation+0.000
collection
Token collection
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Museum
Token Museum
Feature activation+0.000
of
Token of
Feature activation+0.000
Modern
Token Modern
Feature activation+0.000
Art
Token Art
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 5 in H1.5: (feature 11308)

TOP ACTIVATIONS
MAX = 2.306

would
Token would
Feature activation+0.000
ever
Token ever
Feature activation+0.000
have
Token have
Feature activation+0.000
refused
Token refused
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
V
Token V
Feature activation+2.306
.
Token.
Feature activation+0.000
Someone
Token Someone
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
IV
Token IV
Feature activation+0.000
;
Token;
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
V
Token V
Feature activation+2.154
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
prett
Token prett
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
,
Token,
Feature activation+0.000
:
Token:
Feature activation+0.000
I
Token I
Feature activation+0.000
,
Token,
Feature activation+0.000
IV
Token IV
Feature activation+0.000
and
Token and
Feature activation+0.000
V
Token V
Feature activation+1.850
,
Token,
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
from
Token from
Feature activation+0.000
Episode
Token Episode
Feature activation+0.000
IV
Token IV
Feature activation+0.000
through
Token through
Feature activation+0.000
Episode
Token Episode
Feature activation+0.000
VI
Token VI
Feature activation+1.679
.
Token.
Feature activation+0.000
Play
Token Play
Feature activation+0.000
as
Token as
Feature activation+0.000
your
Token your
Feature activation+0.000
favorite
Token favorite
Feature activation+0.000
when
Token when
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.616
know
Token know
Feature activation+0.000
most
Token most
Feature activation+0.000
R
Token R
Feature activation+0.000
OH
TokenOH
Feature activation+0.000
fans
Token fans
Feature activation+0.000
this
Token this
Feature activation+0.000
period
Token period
Feature activation+0.000
,
Token,
Feature activation+0.000
King
Token King
Feature activation+0.000
William
Token William
Feature activation+0.000
IV
Token IV
Feature activation+1.414
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
monarch
Token monarch
Feature activation+0.000
to
Token to
Feature activation+0.000
II
Token II
Feature activation+0.000
:
Token:
Feature activation+0.000
Enhanced
Token Enhanced
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.364
sincerely
Token sincerely
Feature activation+0.000
apologize
Token apologize
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+1.340
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
believe
Token believe
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
decision
Token decision
Feature activation+0.000
about
Token about
Feature activation+0.000
whether
Token whether
Feature activation+0.000
I
Token I
Feature activation+1.162
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
race
Token race
Feature activation+0.000
or
Token or
Feature activation+0.000
do
Token do
Feature activation+0.000
King
Token King
Feature activation+0.000
Charles
Token Charles
Feature activation+0.000
VIII
Token VIII
Feature activation+0.000
when
Token when
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
XI
Token XI
Feature activation+0.916
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
of
Token of
Feature activation+0.000
14
Token 14
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.665
would
Token would
Feature activation+0.000
ever
Token ever
Feature activation+0.000
have
Token have
Feature activation+0.000
refused
Token refused
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
protest
Token protest
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
about
Token about
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
I
TokenI
Feature activation+0.591
could
Token could
Feature activation+0.000
never
Token never
Feature activation+0.000
lead
Token lead
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
different
Token different
Feature activation+0.000
experience
Token experience
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.345
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
playing
Token playing
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
of
Token of
Feature activation+0.000
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
II
Token II
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.339
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.000
to
Token to
Feature activation+0.000
discover
Token discover
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
race
Token race
Feature activation+0.000
or
Token or
Feature activation+0.000
do
Token do
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.306
do
Token do
Feature activation+0.000
now
Token now
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Kraft
Token Kraft
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
i
Token i
Feature activation+0.304
can
Token can
Feature activation+0.000
stomach
Token stomach
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
,
Token,
Feature activation+0.000
Final
Token Final
Feature activation+0.000
Fantasy
Token Fantasy
Feature activation+0.000
VII
Token VII
Feature activation+0.286
Rem
Token Rem
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
and
Token and
Feature activation+0.000
Diss
Token Diss
Feature activation+0.000
idia
Tokenidia
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Mad
Token Mad
Feature activation+0.000
du
Tokendu
Feature activation+0.000
x
Tokenx
Feature activation+0.000
in
Token in
Feature activation+0.000
1994
Token 1994
Feature activation+0.255
became
Token became
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.000
i
Tokeni
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
and
Token and
Feature activation+0.000
i
Token i
Feature activation+0.235
run
Token run
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
ache
Tokenache
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Ethics
Token Ethics
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
V
TokenV
Feature activation+0.198
irt
Tokenirt
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 3.420

go
Token go
Feature activation+0.000
Top resid features:
far
Token far
Feature activation+0.007
Top resid features:
beyond
Token beyond
Feature activation+0.007
Top resid features:
what
Token what
Feature activation+0.024
Top resid features:
Civ
Token Civ
Feature activation-0.004
Top resid features:
IV
Token IV
Feature activation+3.420
Top resid features:
did
Token did
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Which
Token Which
Feature activation+0.030
Top resid features:
is
Token is
Feature activation+0.056
Top resid features:
not
Token not
Feature activation+0.009
Top resid features:
m
Tokenm
Feature activation+0.014
Top resid features:
going
Token going
Feature activation+0.040
Top resid features:
back
Token back
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
Civ
Token Civ
Feature activation+0.039
Top resid features:
IV
Token IV
Feature activation+1.964
Top resid features:
;
Token;
Feature activation+0.121
Top resid features:
Civ
Token Civ
Feature activation+0.074
Top resid features:
V
Token V
Feature activation+0.110
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.040
Top resid features:
simpler
Token simpler
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.053
Top resid features:
I
Token I
Feature activation+0.049
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
IV
Token IV
Feature activation+3.280
Top resid features:
and
Token and
Feature activation-0.016
Top resid features:
V
Token V
Feature activation+0.202
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
55
Token 55
Feature activation+0.011
Top resid features:
skins
Token skins
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+0.031
Top resid features:
Episode
Token Episode
Feature activation+0.024
Top resid features:
IV
Token IV
Feature activation+2.888
Top resid features:
through
Token through
Feature activation+0.047
Top resid features:
Episode
Token Episode
Feature activation+0.041
Top resid features:
VI
Token VI
Feature activation+0.185
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Play
Token Play
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Mr
TokenMr
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Wrestling
Token Wrestling
Feature activation+0.009
Top resid features:
III
Token III
Feature activation+2.289
Top resid features:
is
Token is
Feature activation+0.035
Top resid features:
gone
Token gone
Feature activation-0.009
Top resid features:
from
Token from
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
commentary
Token commentary
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
For
Token For
Feature activation+0.007
Top resid features:
instance
Token instance
Feature activation+0.002
Top resid features:
King
Token King
Feature activation+0.014
Top resid features:
George
Token George
Feature activation-0.002
Top resid features:
III
Token III
Feature activation+2.638
Top resid features:
constantly
Token constantly
Feature activation+0.013
Top resid features:
blocked
Token blocked
Feature activation-0.002
Top resid features:
Catholic
Token Catholic
Feature activation+0.001
Top resid features:
E
Token E
Feature activation+0.007
Top resid features:
man
Tokenman
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.040
Top resid features:
Bald
Token Bald
Feature activation+0.052
Top resid features:
ur
Tokenur
Feature activation+0.045
Top resid features:
's
Token's
Feature activation+0.107
Top resid features:
Gate
Token Gate
Feature activation+0.025
Top resid features:
II
Token II
Feature activation+2.125
Top resid features:
:
Token:
Feature activation+0.130
Top resid features:
Enhanced
Token Enhanced
Feature activation+0.039
Top resid features:
Edition
Token Edition
Feature activation+0.074
Top resid features:
.
Token.
Feature activation+0.060
Top resid features:
I
Token I
Feature activation+0.458
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
FE
TokenFE
Feature activation+0.002
Top resid features:
Z
TokenZ
Feature activation+0.005
Top resid features:
II
Token II
Feature activation+1.211
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
cancelled
Token cancelled
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
n
Tokenn
Feature activation+0.008
Top resid features:
ho
Tokenho
Feature activation+0.003
Top resid features:
el
Tokenel
Feature activation+0.007
Top resid features:
zl
Tokenzl
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
III
Token III
Feature activation+1.834
Top resid features:
on
Token on
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
NASCAR
Token NASCAR
Feature activation+0.037
Top resid features:
W
Token W
Feature activation+0.003
Top resid features:
hel
Tokenhel
Feature activation+0.010
Top resid features:
her
Token her
Feature activation+0.020
Top resid features:
young
Token young
Feature activation+0.011
Top resid features:
brother
Token brother
Feature activation+0.023
Top resid features:
King
Token King
Feature activation+0.045
Top resid features:
Charles
Token Charles
Feature activation+0.064
Top resid features:
VIII
Token VIII
Feature activation+1.604
Top resid features:
when
Token when
Feature activation+0.148
Top resid features:
Louis
Token Louis
Feature activation+0.093
Top resid features:
XI
Token XI
Feature activation+0.303
Top resid features:
died
Token died
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
go
Token go
Feature activation-0.003
Top resid features:
far
Token far
Feature activation+0.009
Top resid features:
beyond
Token beyond
Feature activation+0.017
Top resid features:
what
Token what
Feature activation+0.031
Top resid features:
Civ
Token Civ
Feature activation+0.023
Top resid features:
IV
Token IV
Feature activation+1.460
Top resid features:
did
Token did
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Which
Token Which
Feature activation+0.037
Top resid features:
is
Token is
Feature activation+0.101
Top resid features:
not
Token not
Feature activation+0.027
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.258
Top resid features:
III
Token III
Feature activation+1.487
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
brilliant
Token brilliant
Feature activation+0.006
Top resid features:
sche
Token sche
Feature activation-0.006
Top resid features:
ming
Tokenming
Feature activation-0.007
Top resid features:
m
Tokenm
Feature activation+0.003
Top resid features:
going
Token going
Feature activation+0.013
Top resid features:
back
Token back
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
Civ
Token Civ
Feature activation+0.009
Top resid features:
IV
Token IV
Feature activation+0.644
Top resid features:
;
Token;
Feature activation+0.019
Top resid features:
Civ
Token Civ
Feature activation+0.016
Top resid features:
V
Token V
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.050
Top resid features:
far
Token far
Feature activation+0.005
Top resid features:
utter
Token utter
Feature activation+0.021
Top resid features:
destruction
Token destruction
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.079
Top resid features:
World
Token World
Feature activation+0.159
Top resid features:
War
Token War
Feature activation+0.130
Top resid features:
II
Token II
Feature activation+1.135
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
I
Token I
Feature activation+0.441
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
keen
Token keen
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
n
Tokenn
Feature activation+0.008
Top resid features:
ho
Tokenho
Feature activation+0.002
Top resid features:
el
Tokenel
Feature activation+0.007
Top resid features:
zl
Tokenzl
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
III
Token III
Feature activation+1.044
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
NASCAR
Token NASCAR
Feature activation+0.020
Top resid features:
W
Token W
Feature activation+0.002
Top resid features:
hel
Tokenhel
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
FE
TokenFE
Feature activation+0.001
Top resid features:
Z
TokenZ
Feature activation+0.009
Top resid features:
II
Token II
Feature activation+0.676
Top resid features:
is
Token is
Feature activation+0.027
Top resid features:
cancelled
Token cancelled
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
current
Token current
Feature activation+0.019
Top resid features:
projects
Token projects
Feature activation+0.027
Top resid features:
include
Token include
Feature activation-0.011
Top resid features:
Kingdom
Token Kingdom
Feature activation+0.046
Top resid features:
Hearts
Token Hearts
Feature activation+0.081
Top resid features:
III
Token III
Feature activation+0.917
Top resid features:
,
Token,
Feature activation+0.075
Top resid features:
Kingdom
Token Kingdom
Feature activation+0.051
Top resid features:
Hearts
Token Hearts
Feature activation+0.065
Top resid features:
HD
Token HD
Feature activation+0.062
Top resid features:
2
Token 2
Feature activation+0.085
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
Steve
TokenSteve
Feature activation+0.006
Top resid features:
Carlton
Token Carlton
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
1982
Token 1982
Feature activation+1.655
Top resid features:
became
Token became
Feature activation-0.016
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
pitcher
Token pitcher
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
FE
TokenFE
Feature activation+0.001
Top resid features:
Z
TokenZ
Feature activation+0.011
Top resid features:
II
Token II
Feature activation+0.653
Top resid features:
is
Token is
Feature activation+0.034
Top resid features:
cancelled
Token cancelled
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
most
Token most
Feature activation+0.005
Top resid features:
succinct
Token succinct
Feature activation+0.004
Top resid features:
ly
Tokenly
Feature activation+0.021
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
Book
Token Book
Feature activation+0.021
Top resid features:
II
Token II
Feature activation+1.197
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
Nich
Token Nich
Feature activation-0.001
Top resid features:
om
Tokenom
Feature activation+0.032
Top resid features:
ache
Tokenache
Feature activation+0.016
Top resid features:
an
Tokenan
Feature activation+0.039
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.06

Head 2: 0.04

Head 3: 0.02

Head 4: 0.04

Head 5: 0.45

Head 6: 0.04

Head 7: 0.08

Head 8: 0.03

Head 9: 0.03

Head 10: 0.03

Head 11: 0.09

Positive logits

worms1.87

Goth1.81

Zin1.80

Mara1.79

��1.71

Valkyrie1.69

ths1.68

Russians1.68

Ghostbusters1.67

��1.67

��1.64

Haku1.62

argo1.61

Lavrov1.61

Aman1.61

Saint1.60

Franks1.59

Ku1.59

Leon1.59

Kir1.58

Negative logits

ebook-2.62

ounter-2.08

DonaldTrump-2.05

undy-1.94

ancest-1.94

WARN-1.91

arium-1.90

wcsstore-1.87

Indust-1.85

MpServer-1.84

atan-1.83

encia-1.82

rator-1.81

respons-1.81

adas-1.80

itious-1.80

inventoryQuantity-1.79

SHIP-1.76

Pen-1.76

Introduced-1.75

INTERVAL 2.076 - 2.306
CONTAINS 0.000%

would
Token would
Feature activation+0.000
ever
Token ever
Feature activation+0.000
have
Token have
Feature activation+0.000
refused
Token refused
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
V
Token V
Feature activation+2.306
.
Token.
Feature activation+0.000
Someone
Token Someone
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
IV
Token IV
Feature activation+0.000
;
Token;
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
V
Token V
Feature activation+2.154
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
prett
Token prett
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.845 - 2.076
CONTAINS 0.000%

:
Token:
Feature activation+0.000
I
Token I
Feature activation+0.000
,
Token,
Feature activation+0.000
IV
Token IV
Feature activation+0.000
and
Token and
Feature activation+0.000
V
Token V
Feature activation+1.850
,
Token,
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.614 - 1.845
CONTAINS 0.000%

when
Token when
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.616
know
Token know
Feature activation+0.000
most
Token most
Feature activation+0.000
R
Token R
Feature activation+0.000
OH
TokenOH
Feature activation+0.000
fans
Token fans
Feature activation+0.000
from
Token from
Feature activation+0.000
Episode
Token Episode
Feature activation+0.000
IV
Token IV
Feature activation+0.000
through
Token through
Feature activation+0.000
Episode
Token Episode
Feature activation+0.000
VI
Token VI
Feature activation+1.679
.
Token.
Feature activation+0.000
Play
Token Play
Feature activation+0.000
as
Token as
Feature activation+0.000
your
Token your
Feature activation+0.000
favorite
Token favorite
Feature activation+0.000

INTERVAL 1.384 - 1.614
CONTAINS 0.000%

this
Token this
Feature activation+0.000
period
Token period
Feature activation+0.000
,
Token,
Feature activation+0.000
King
Token King
Feature activation+0.000
William
Token William
Feature activation+0.000
IV
Token IV
Feature activation+1.414
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
monarch
Token monarch
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.153 - 1.384
CONTAINS 0.000%

II
Token II
Feature activation+0.000
:
Token:
Feature activation+0.000
Enhanced
Token Enhanced
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.364
sincerely
Token sincerely
Feature activation+0.000
apologize
Token apologize
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
decision
Token decision
Feature activation+0.000
about
Token about
Feature activation+0.000
whether
Token whether
Feature activation+0.000
I
Token I
Feature activation+1.162
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
race
Token race
Feature activation+0.000
or
Token or
Feature activation+0.000
do
Token do
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+1.340
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
believe
Token believe
Feature activation+0.000

INTERVAL 0.922 - 1.153
CONTAINS 0.000%

INTERVAL 0.692 - 0.922
CONTAINS 0.000%

King
Token King
Feature activation+0.000
Charles
Token Charles
Feature activation+0.000
VIII
Token VIII
Feature activation+0.000
when
Token when
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
XI
Token XI
Feature activation+0.916
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
of
Token of
Feature activation+0.000
14
Token 14
Feature activation+0.000

INTERVAL 0.461 - 0.692
CONTAINS 0.000%

is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.665
would
Token would
Feature activation+0.000
ever
Token ever
Feature activation+0.000
have
Token have
Feature activation+0.000
refused
Token refused
Feature activation+0.000
Civ
Token Civ
Feature activation+0.000
protest
Token protest
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
about
Token about
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
I
TokenI
Feature activation+0.591
could
Token could
Feature activation+0.000
never
Token never
Feature activation+0.000
lead
Token lead
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.231 - 0.461
CONTAINS 0.001%

to
Token to
Feature activation+0.000
race
Token race
Feature activation+0.000
or
Token or
Feature activation+0.000
do
Token do
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.306
do
Token do
Feature activation+0.000
now
Token now
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Kraft
Token Kraft
Feature activation+0.000
of
Token of
Feature activation+0.000
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
II
Token II
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.339
was
Token was
Feature activation+0.000
keen
Token keen
Feature activation+0.000
to
Token to
Feature activation+0.000
discover
Token discover
Feature activation+0.000
the
Token the
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
i
Token i
Feature activation+0.304
can
Token can
Feature activation+0.000
stomach
Token stomach
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
different
Token different
Feature activation+0.000
experience
Token experience
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.345
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
playing
Token playing
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
i
Tokeni
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
and
Token and
Feature activation+0.000
i
Token i
Feature activation+0.235
run
Token run
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 0.000 - 0.231
CONTAINS 99.998%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mac
TokenMac
Feature activation+0.000
ron
Tokenron
Feature activation+0.000
is
Token is
Feature activation+0.000
en
Token en
Feature activation+0.000
route
Token route
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Elys
Token Elys
Feature activation+0.000
and
Token and
Feature activation+0.000
videos
Token videos
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
game
Token game
Feature activation+0.000
daily
Token daily
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
spam
Token spam
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
wine
Token wine
Feature activation+0.000
and
Token and
Feature activation+0.000
stay
Token stay
Feature activation+0.000
awake
Token awake
Feature activation+0.000
and
Token and
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
as
Token as
Feature activation+0.000
using
Token using
Feature activation+0.000
pipes
Token pipes
Feature activation+0.000
in
Token in
Feature activation+0.000
bash
Token bash
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
land
Token land
Feature activation+0.000
they
Token they
Feature activation+0.000
created
Token created
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
development
Token development
Feature activation+0.000
of
Token of
Feature activation+0.000
organized
Token organized
Feature activation+0.000
labor
Token labor
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H1.5: (feature 18393)

TOP ACTIVATIONS
MAX = 1.692

never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
they
Token they
Feature activation+0.000
needed
Token needed
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.692
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
point
Token point
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Second
TokenSecond
Feature activation+1.691
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
filament
Token filament
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Cube
Token Cube
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.503
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
can
Token can
Feature activation+0.000
First
Token First
Feature activation+0.000
we
Token we
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.413
we
Token we
Feature activation+0.000
compute
Token compute
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
tax
Token tax
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
.
Token.
Feature activation+0.000
Third
Token Third
Feature activation+1.310
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
we
Token we
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.203
we
Token we
Feature activation+0.000
compare
Token compare
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
set
Token set
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.167
we
Token we
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
paintings
Token paintings
Feature activation+0.000
and
Token and
Feature activation+0.000
were
Token were
Feature activation+0.000
then
Token then
Feature activation+0.256
swept
Token swept
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Second
Token Second
Feature activation+1.123
Round
Token Round
Feature activation+0.000
by
Token by
Feature activation+0.000
eventual
Token eventual
Feature activation+0.000
Quarter
Token Quarter
Feature activation+0.000
final
Tokenfinal
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+0.000
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Secondly
Token Secondly
Feature activation+1.122
,
Token,
Feature activation+0.000
America
Token America
Feature activation+0.000
already
Token already
Feature activation+0.000
sees
Token sees
Feature activation+0.000
us
Token us
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
out
Token out
Feature activation+0.000
large
Token large
Feature activation+0.000
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.101
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
economic
Token economic
Feature activation+0.000
realities
Token realities
Feature activation+0.000
of
Token of
Feature activation+0.000
behind
Token behind
Feature activation+0.000
Lum
Token Lum
Feature activation+0.000
en
Tokenen
Feature activation+0.000
View
Token View
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.030
,
Token,
Feature activation+0.000
Find
Token Find
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Best
TokenBest
Feature activation+0.000
never
Token never
Feature activation+0.000
appropriation
Token appropriation
Feature activation+0.000
too
Token too
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
second
Token second
Feature activation+1.027
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
slack
Token slack
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
of
Token of
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
the
Token the
Feature activation+0.000
probabilities
Token probabilities
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.008
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
paths
Token paths
Feature activation+0.000
probably
Token probably
Feature activation+0.000
yes
Token yes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Long
TokenLong
Feature activation+0.988
version
Token version
Feature activation+0.000
,
Token,
Feature activation+0.000
showing
Token showing
Feature activation+0.000
my
Token my
Feature activation+0.000
work
Token work
Feature activation+0.000
:
Token:
Feature activation+0.000
26
Token26
Feature activation+0.000
-
Token-
Feature activation+0.000
38
Token38
Feature activation+0.000
).
Token).
Feature activation+0.000
Then
Token Then
Feature activation+0.981
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
visits
Token visits
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
to
Token to
Feature activation+0.000
winning
Token winning
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Second
TokenSecond
Feature activation+0.978
:
Token:
Feature activation+0.000
Since
Token Since
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Third
TokenThird
Feature activation+0.910
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+0.000
photos
Token photos
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.894
was
Token was
Feature activation+0.000
Rash
Token Rash
Feature activation+0.000
id
Tokenid
Feature activation+0.000
Khalid
Token Khalid
Feature activation+0.000
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.000
Prop
Token Prop
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.853
Amendment
Token Amendment
Feature activation+0.000
will
Token will
Feature activation+0.000
claim
Token claim
Feature activation+0.000
that
Token that
Feature activation+0.000
banning
Token banning
Feature activation+0.000
like
Token like
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
and
Token and
Feature activation+0.000
Montana
Token Montana
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.843
more
Token more
Feature activation+0.000
challenges
Token challenges
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
drilling
Token drilling
Feature activation+0.000

Top DFA by src position
MAX = 2.429

all
Token all
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.006
Top resid features:
human
Token human
Feature activation+0.003
Top resid features:
labor
Token labor
Feature activation-0.003
Top resid features:
?
Token?
Feature activation+0.003
Top resid features:
First
Token First
Feature activation+2.388
Top resid features:
we
Token we
Feature activation-0.000
Top resid features:
raised
Token raised
Feature activation+0.006
Top resid features:
living
Token living
Feature activation+0.001
Top resid features:
standards
Token standards
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
couple
Token couple
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
reasons
Token reasons
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
First
Token First
Feature activation+2.429
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
all
Token all
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
sheer
Token sheer
Feature activation+0.024
Top resid features:
athleticism
Token athleticism
Feature activation+0.015
Top resid features:
two
Token two
Feature activation-0.009
Top resid features:
simple
Token simple
Feature activation+0.022
Top resid features:
public
Token public
Feature activation-0.008
Top resid features:
commitments
Token commitments
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
First
Token First
Feature activation+2.296
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
3
Token 3
Feature activation+0.006
Top resid features:
D
TokenD
Feature activation+0.015
Top resid features:
Systems
Token Systems
Feature activation+0.007
Top resid features:
can
Token can
Feature activation+0.018
Top resid features:
by
Token by
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
following
Token following
Feature activation+0.015
Top resid features:
process
Token process
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
First
Token First
Feature activation+2.102
Top resid features:
we
Token we
Feature activation+0.025
Top resid features:
guess
Token guess
Feature activation+0.037
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
Then
Token Then
Feature activation+0.413
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
retail
Token retail
Feature activation+0.002
Top resid features:
price
Token price
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Second
Token Second
Feature activation+2.227
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
e
Token e
Feature activation+0.014
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
cigarette
Tokencigarette
Feature activation+0.021
Top resid features:
taxes
Token taxes
Feature activation+0.020
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
following
Token following
Feature activation-0.003
Top resid features:
process
Token process
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
First
Token First
Feature activation+1.851
Top resid features:
we
Token we
Feature activation+0.003
Top resid features:
guess
Token guess
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Then
Token Then
Feature activation+0.185
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
he
Token he
Feature activation+0.006
Top resid features:
explains
Token explains
Feature activation+0.017
Top resid features:
:
Token:
Feature activation+0.037
Top resid features:
"
Token "
Feature activation+0.056
Top resid features:
First
TokenFirst
Feature activation+1.792
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
all
Token all
Feature activation+0.006
Top resid features:
we
Token we
Feature activation+0.003
Top resid features:
can
Token can
Feature activation+0.005
Top resid features:
look
Token look
Feature activation+0.002
Top resid features:
Playoff
Token Playoff
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
They
Token They
Feature activation+0.009
Top resid features:
had
Token had
Feature activation+0.027
Top resid features:
a
Token a
Feature activation+0.025
Top resid features:
First
Token First
Feature activation+2.020
Top resid features:
Round
Token Round
Feature activation+0.019
Top resid features:
Bye
Token Bye
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
but
Token but
Feature activation+0.020
Top resid features:
were
Token were
Feature activation+0.047
Top resid features:
flag
Token flag
Feature activation+0.007
Top resid features:
off
Token off
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
floor
Token floor
Feature activation+0.006
Top resid features:
!
Token!
Feature activation+0.015
Top resid features:
First
Token First
Feature activation+1.780
Top resid features:
off
Token off
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
's
Token's
Feature activation+0.025
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
Western
Token Western
Feature activation+0.001
Top resid features:
media
Token media
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
First
TokenFirst
Feature activation+1.818
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
India
Token India
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
merely
Token merely
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
couple
Token couple
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
problems
Token problems
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
First
Token First
Feature activation+1.807
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
his
Token his
Feature activation+0.015
Top resid features:
idea
Token idea
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
what
Token what
Feature activation+0.009
Top resid features:
wrong
Token wrong
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
both
Token both
Feature activation-0.004
Top resid features:
counts
Token counts
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
First
Token First
Feature activation+1.750
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
other
Token other
Feature activation+0.004
Top resid features:
members
Token members
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.233
Top resid features:
there
Token there
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+0.021
Top resid features:
caveats
Token caveats
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
First
Token First
Feature activation+2.013
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
who
Token who
Feature activation+0.021
Top resid features:
knows
Token knows
Feature activation+0.006
Top resid features:
how
Token how
Feature activation+0.005
Top resid features:
accurate
Token accurate
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
best
Token best
Feature activation+0.017
Top resid features:
?
Token?
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Short
TokenShort
Feature activation+1.708
Top resid features:
version
Token version
Feature activation+0.016
Top resid features:
:
Token:
Feature activation+0.025
Top resid features:
probably
Token probably
Feature activation+0.016
Top resid features:
yes
Token yes
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.182
Top resid features:
First
TokenFirst
Feature activation+1.608
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
all
Token all
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
angel
Token angel
Feature activation+0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.196
Top resid features:
First
TokenFirst
Feature activation+1.669
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
In
Token In
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
last
Token last
Feature activation-0.008
Top resid features:
blog
Token blog
Feature activation-0.007
Top resid features:
ap
Tokenap
Feature activation+0.000
Top resid features:
ia
Tokenia
Feature activation+0.007
Top resid features:
).
Token).
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Secondly
TokenSecondly
Feature activation+1.779
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
hotel
Token hotel
Feature activation-0.003
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
referred
Token referred
Feature activation-0.005
Top resid features:
refused
Token refused
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
go
Token go
Feature activation+0.001
Top resid features:
after
Token after
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
One
Token One
Feature activation+1.385
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
those
Token those
Feature activation-0.002
Top resid features:
individuals
Token individuals
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
Anton
Token Anton
Feature activation+0.005
Top resid features:
gun
Token gun
Feature activation-0.000
Top resid features:
violence
Token violence
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Second
TokenSecond
Feature activation+1.712
Top resid features:
Amendment
Token Amendment
Feature activation+0.000
Top resid features:
advocates
Token advocates
Feature activation+0.024
Top resid features:
will
Token will
Feature activation+0.004
Top resid features:
condemn
Token condemn
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
methane
Token methane
Feature activation+0.018
Top resid features:
rule
Token rule
Feature activation+0.005
Top resid features:
land
Token land
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
First
Token First
Feature activation+1.501
Top resid features:
came
Token came
Feature activation+0.037
Top resid features:
challenges
Token challenges
Feature activation+0.029
Top resid features:
from
Token from
Feature activation+0.016
Top resid features:
drill
Token drill
Feature activation+0.024
Top resid features:
-
Token-
Feature activation+0.018
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.07

Head 2: 0.03

Head 3: 0.02

Head 4: 0.05

Head 5: 0.45

Head 6: 0.05

Head 7: 0.04

Head 8: 0.04

Head 9: 0.03

Head 10: 0.03

Head 11: 0.11

Positive logits

JB2.12

Cyber2.06

Malays1.96

Eston1.95

Franks1.94

uphem1.89

Notable1.88

UTH1.88

Jeb1.87

Bulgar1.86

Leon1.83

Logged1.83

Kyl1.83

ONSORED1.83

Repl1.79

itage1.79

ISA1.78

Hume1.77

YL1.77

KGB1.75

Negative logits

escape-2.13

assisted-2.01

ilty-2.01

seiz-2.00

spread-1.94

ensing-1.85

sac-1.84

bowl-1.78

anship-1.76

acus-1.76

ipation-1.75

itious-1.73

circle-1.73

atan-1.72

ender-1.72

netflix-1.71

collection-1.71

udging-1.70

ixel-1.68

arium-1.68

INTERVAL 1.522 - 1.692
CONTAINS 0.000%

never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
they
Token they
Feature activation+0.000
needed
Token needed
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.692
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
point
Token point
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Second
TokenSecond
Feature activation+1.691
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.353 - 1.522
CONTAINS 0.000%

filament
Token filament
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Cube
Token Cube
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.503
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
can
Token can
Feature activation+0.000
First
Token First
Feature activation+0.000
we
Token we
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.413
we
Token we
Feature activation+0.000
compute
Token compute
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.184 - 1.353
CONTAINS 0.000%

amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
tax
Token tax
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
.
Token.
Feature activation+0.000
Third
Token Third
Feature activation+1.310
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
we
Token we
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.203
we
Token we
Feature activation+0.000
compare
Token compare
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.015 - 1.184
CONTAINS 0.001%

appropriation
Token appropriation
Feature activation+0.000
too
Token too
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
second
Token second
Feature activation+1.027
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
slack
Token slack
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
of
Token of
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
out
Token out
Feature activation+0.000
large
Token large
Feature activation+0.000
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.101
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
economic
Token economic
Feature activation+0.000
realities
Token realities
Feature activation+0.000
of
Token of
Feature activation+0.000
behind
Token behind
Feature activation+0.000
Lum
Token Lum
Feature activation+0.000
en
Tokenen
Feature activation+0.000
View
Token View
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.030
,
Token,
Feature activation+0.000
Find
Token Find
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Best
TokenBest
Feature activation+0.000
never
Token never
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
set
Token set
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.167
we
Token we
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
paintings
Token paintings
Feature activation+0.000
and
Token and
Feature activation+0.000
were
Token were
Feature activation+0.000
then
Token then
Feature activation+0.256
swept
Token swept
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Second
Token Second
Feature activation+1.123
Round
Token Round
Feature activation+0.000
by
Token by
Feature activation+0.000
eventual
Token eventual
Feature activation+0.000
Quarter
Token Quarter
Feature activation+0.000
final
Tokenfinal
Feature activation+0.000

INTERVAL 0.846 - 1.015
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.894
was
Token was
Feature activation+0.000
Rash
Token Rash
Feature activation+0.000
id
Tokenid
Feature activation+0.000
Khalid
Token Khalid
Feature activation+0.000
i
Tokeni
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
the
Token the
Feature activation+0.000
probabilities
Token probabilities
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+1.008
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
paths
Token paths
Feature activation+0.000
probably
Token probably
Feature activation+0.000
yes
Token yes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Long
TokenLong
Feature activation+0.988
version
Token version
Feature activation+0.000
,
Token,
Feature activation+0.000
showing
Token showing
Feature activation+0.000
my
Token my
Feature activation+0.000
work
Token work
Feature activation+0.000
winning
Token winning
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Second
TokenSecond
Feature activation+0.978
:
Token:
Feature activation+0.000
Since
Token Since
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Prop
Token Prop
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.853
Amendment
Token Amendment
Feature activation+0.000
will
Token will
Feature activation+0.000
claim
Token claim
Feature activation+0.000
that
Token that
Feature activation+0.000
banning
Token banning
Feature activation+0.000

INTERVAL 0.677 - 0.846
CONTAINS 0.001%

more
Token more
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
than
Token than
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.771
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
too
Token too
Feature activation+0.000
like
Token like
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
and
Token and
Feature activation+0.000
Montana
Token Montana
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.843
more
Token more
Feature activation+0.000
challenges
Token challenges
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
drilling
Token drilling
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Men
TokenMen
Feature activation+0.000
and
Token and
Feature activation+0.000
women
Token women
Feature activation+0.754
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
are
Token are
Feature activation+0.000
equally
Token equally
Feature activation+0.000
as
Token as
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
year
Token year
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.764
stream
Token stream
Feature activation+0.000
is
Token is
Feature activation+0.000
closely
Token closely
Feature activation+0.000
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Three
TokenThree
Feature activation+0.806
thousand
Token thousand
Feature activation+0.000
migrants
Token migrants
Feature activation+0.000
were
Token were
Feature activation+0.000
coming
Token coming
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.507 - 0.677
CONTAINS 0.001%

!
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
Another
TokenAnother
Feature activation+0.672
called
Token called
Feature activation+0.000
him
Token him
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Jud
TokenJud
Feature activation+0.000
dp
Tokendp
Feature activation+0.000
uf
Tokenuf
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Day
TokenDay
Feature activation+0.000
-
Token-
Feature activation+0.000
night
Tokennight
Feature activation+0.646
Pro
Token Pro
Feature activation+0.000
te
Tokente
Feature activation+0.000
as
Tokenas
Feature activation+0.000
Test
Token Test
Feature activation+0.000
'
Token '
Feature activation+0.000
Car
Token Car
Feature activation+0.000
rigan
Tokenrigan
Feature activation+0.000
was
Token was
Feature activation+0.000
almost
Token almost
Feature activation+0.000
number
Token number
Feature activation+0.000
four
Token four
Feature activation+0.582
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
survived
Token survived
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
optional
Token optional
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.643
the
Token the
Feature activation+0.000
redesign
Token redesign
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
pair
Token pair
Feature activation+0.000
then
Token then
Feature activation+0.608
proceeded
Token proceeded
Feature activation+0.000
to
Token to
Feature activation+0.000
land
Token land
Feature activation+0.000
the
Token the
Feature activation+0.000
plane
Token plane
Feature activation+0.000

INTERVAL 0.338 - 0.507
CONTAINS 0.003%

kicking
Token kicking
Feature activation+0.000
their
Token their
Feature activation+0.000
but
Token but
Feature activation+0.000
ts
Tokents
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.504
the
Token the
Feature activation+0.000
younger
Token younger
Feature activation+0.000
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
A
Token A
Feature activation+0.000
Council
Token Council
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
young
Token young
Feature activation+0.000
male
Token male
Feature activation+0.363
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
decap
Token decap
Feature activation+0.000
itated
Tokenitated
Feature activation+0.000
after
Token after
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.364
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
pulled
Token pulled
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
hurst
Tokenhurst
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
Red
Token Red
Feature activation+0.436
Hat
Token Hat
Feature activation+0.000
only
Token only
Feature activation+0.000
renewed
Token renewed
Feature activation+0.000
24
Token 24
Feature activation+0.000
of
Token of
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
girls
Token girls
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.364
13
Token 13
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.014
14
Token 14
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.169 - 0.338
CONTAINS 0.004%

pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
object
Token object
Feature activation+0.000
),
Token),
Feature activation+0.000
then
Token then
Feature activation+0.172
that
Token that
Feature activation+0.000
weak
Token weak
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
will
Token will
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.224
investigations
Token investigations
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
actions
Token actions
Feature activation+0.000
of
Token of
Feature activation+0.000
member
Token member
Feature activation+0.000
Bowser
Token Bowser
Feature activation+0.000
was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.058
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.235
lawmakers
Token lawmakers
Feature activation+0.000
to
Token to
Feature activation+0.000
call
Token call
Feature activation+0.000
for
Token for
Feature activation+0.000
Gray
Token Gray
Feature activation+0.000
divisions
Token divisions
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
and
Token and
Feature activation+0.000
Third
Token Third
Feature activation+0.280
Arm
Token Arm
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
British
Token British
Feature activation+0.000
on
Token on
Feature activation+0.000
carts
Token carts
Feature activation+0.000
.
Token.
Feature activation+0.000
Fifty
Token Fifty
Feature activation+0.000
or
Token or
Feature activation+0.000
sixty
Token sixty
Feature activation+0.237
bags
Token bags
Feature activation+0.000
full
Token full
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
way
Tokenway
Feature activation+0.000
more
Token more
Feature activation+0.000

INTERVAL 0.000 - 0.169
CONTAINS 99.990%

later
Token later
Feature activation+0.000
use
Token use
Feature activation+0.000
to
Token to
Feature activation+0.000
brand
Token brand
Feature activation+0.000
Al
Token Al
Feature activation+0.000
Gore
Token Gore
Feature activation+0.000
a
Token a
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
,
Token,
Feature activation+0.000
Max
Token Max
Feature activation+0.000
Cle
Token Cle
Feature activation+0.000
not
Token not
Feature activation+0.000
count
Token count
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
atheists
Token atheists
Feature activation+0.000
were
Token were
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
much
Token much
Feature activation+0.000
left
Token left
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
scheduled
Token scheduled
Feature activation+0.000
to
Token to
Feature activation+0.000
run
Token run
Feature activation+0.000
until
Token until
Feature activation+0.000
December
Token December
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
from
Token from
Feature activation+0.000
angry
Token angry
Feature activation+0.000
Lady
Token Lady
Feature activation+0.000
over
Token over
Feature activation+0.000
joining
Token joining
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
in
Token in
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
taking
Token taking
Feature activation+0.000
health
Token health
Feature activation+0.000
.
Token.
Feature activation+0.000
Mobile
Token Mobile
Feature activation+0.000
tele
Token tele
Feature activation+0.000
pres
Tokenpres
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
robots
Token robots
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
a
Tokena
Feature activation+0.000
wheel
Token wheel
Feature activation+0.000
ed
Tokened
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H1.5: (feature 1940)

TOP ACTIVATIONS
MAX = 2.504

carriage
Token carriage
Feature activation+0.000
bolt
Token bolt
Feature activation+0.000
.
Token.
Feature activation+0.000
Screw
Token Screw
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.504
nut
Token nut
Feature activation+0.000
onto
Token onto
Feature activation+0.000
the
Token the
Feature activation+0.000
bolt
Token bolt
Feature activation+0.000
until
Token until
Feature activation+0.000
grow
Token grow
Feature activation+0.000
larger
Token larger
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
third
Token third
Feature activation+2.294
investigated
Token investigated
Feature activation+0.000
what
Token what
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
growth
Token growth
Feature activation+0.000
ward
Token ward
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.279
floor
Token floor
Feature activation+0.000
and
Token and
Feature activation+0.000
meet
Token meet
Feature activation+0.000
to
Token to
Feature activation+0.000
select
Token select
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
tax
Token tax
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
.
Token.
Feature activation+0.000
Third
Token Third
Feature activation+2.250
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
environment
Token environment
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
third
Token third
Feature activation+2.223
basket
Token basket
Feature activation+0.000
nests
Token nests
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
social
Token social
Feature activation+0.000
additional
Token additional
Feature activation+0.000
features
Token features
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.158
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
attach
Token attach
Feature activation+0.000
the
Token the
Feature activation+0.000
printer
Token printer
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.331
,
Token,
Feature activation+0.000
third
Token third
Feature activation+2.136
and
Token and
Feature activation+0.000
fourth
Token fourth
Feature activation+1.159
are
Token are
Feature activation+0.000
present
Token present
Feature activation+0.000
,
Token,
Feature activation+0.000
Ki
Token Ki
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
at
Tokenat
Feature activation+0.000
in
Token in
Feature activation+0.000
third
Token third
Feature activation+2.043
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jo
TokenJo
Feature activation+0.000
P
Token P
Feature activation+0.000
gain
Token gain
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
third
Token third
Feature activation+1.946
indictment
Token indictment
Feature activation+0.000
count
Token count
Feature activation+0.000
alleges
Token alleges
Feature activation+0.000
You
Token You
Feature activation+0.000
n
Tokenn
Feature activation+0.000
:
Token:
Feature activation+0.000
H
Token H
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
o
Tokeno
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+1.847
recorded
Token recorded
Feature activation+0.000
outing
Token outing
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
contr
Token contr
Feature activation+0.000
had
Token had
Feature activation+0.000
runners
Token runners
Feature activation+0.000
at
Token at
Feature activation+0.000
second
Token second
Feature activation+0.000
and
Token and
Feature activation+0.000
third
Token third
Feature activation+1.784
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
gir
Token gir
Feature activation+0.000
affe
Tokenaffe
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
fourth
Token fourth
Feature activation+1.755
character
Token character
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
.
Token.
Feature activation+0.000
Prop
Token Prop
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+1.678
Amendment
Token Amendment
Feature activation+0.000
will
Token will
Feature activation+0.000
claim
Token claim
Feature activation+0.000
that
Token that
Feature activation+0.000
banning
Token banning
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
chip
Token chip
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.661
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
simpl
Token simpl
Feature activation+0.000
ifies
Tokenifies
Feature activation+0.000
ers
Tokeners
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
third
Token third
Feature activation+1.659
stage
Token stage
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
F
Token F
Feature activation+0.000
BR
TokenBR
Feature activation+0.000
The
Token The
Feature activation+0.000
papers
Token papers
Feature activation+0.000
grand
Token grand
Feature activation+0.000
us
Token us
Feature activation+0.000
a
Token a
Feature activation+0.000
first
Token first
Feature activation+1.623
view
Token view
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
distant
Token distant
Feature activation+0.000
future
Token future
Feature activation+0.000
second
Token second
Feature activation+0.000
basket
Token basket
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.606
and
Token and
Feature activation+0.000
represents
Token represents
Feature activation+0.000
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
s
Tokens
Feature activation+0.000
Music
Token Music
Feature activation+0.000
Row
Token Row
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
first
Token first
Feature activation+1.512
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
serve
Token serve
Feature activation+0.000
as
Token as
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
for
Token for
Feature activation+0.000
third
Token third
Feature activation+1.470
-
Token-
Feature activation+0.000
stage
Token stage
Feature activation+0.000
thor
Token thor
Feature activation+0.000
ium
Tokenium
Feature activation+0.000
breed
Token breed
Feature activation+0.000
more
Token more
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
than
Token than
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+1.456
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
too
Token too
Feature activation+0.000

Top DFA by src position
MAX = 3.651

Ċ
TokenĊ
Feature activation+0.010
Top resid features:
9
Token9
Feature activation+0.021
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Screw
Token Screw
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
second
Token second
Feature activation+3.417
Top resid features:
nut
Token nut
Feature activation+0.022
Top resid features:
onto
Token onto
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
carriage
Token carriage
Feature activation+0.019
Top resid features:
bolt
Token bolt
Feature activation+0.016
Top resid features:
become
Token become
Feature activation+0.031
Top resid features:
muscle
Token muscle
Feature activation+0.022
Top resid features:
cells
Token cells
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
second
Token second
Feature activation+3.327
Top resid features:
study
Token study
Feature activation+0.030
Top resid features:
investigated
Token investigated
Feature activation+0.037
Top resid features:
how
Token how
Feature activation+0.030
Top resid features:
muscle
Token muscle
Feature activation+0.029
Top resid features:
might
Token might
Feature activation+0.034
Top resid features:
committee
Token committee
Feature activation+0.022
Top resid features:
people
Tokenpeople
Feature activation+0.011
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
On
Token On
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
second
Token second
Feature activation+1.979
Top resid features:
floor
Token floor
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
out
Token out
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
view
Token view
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
retail
Token retail
Feature activation+0.013
Top resid features:
price
Token price
Feature activation+0.026
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Second
Token Second
Feature activation+3.651
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
e
Token e
Feature activation+0.027
Top resid features:
-
Token-
Feature activation+0.011
Top resid features:
cigarette
Tokencigarette
Feature activation+0.050
Top resid features:
taxes
Token taxes
Feature activation+0.035
Top resid features:
healthy
Token healthy
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
abundant
Token abundant
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
The
Token The
Feature activation+0.010
Top resid features:
second
Token second
Feature activation+3.431
Top resid features:
basket
Token basket
Feature activation+0.022
Top resid features:
rests
Token rests
Feature activation+0.017
Top resid features:
inside
Token inside
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
first
Token first
Feature activation+0.053
Top resid features:
capabilities
Token capabilities
Feature activation+0.009
Top resid features:
built
Token built
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
The
Token The
Feature activation+0.009
Top resid features:
second
Token second
Feature activation+3.080
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
attach
Token attach
Feature activation+0.018
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
printer
Token printer
Feature activation+0.015
Top resid features:
an
Token an
Feature activation+0.024
Top resid features:
example
Token example
Feature activation+0.048
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
if
Token if
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
second
Token second
Feature activation+2.987
Top resid features:
card
Token card
Feature activation+0.027
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
a
Token a
Feature activation+0.035
Top resid features:
pack
Token pack
Feature activation+0.050
Top resid features:
is
Token is
Feature activation+0.062
Top resid features:
h
Tokenh
Feature activation+0.016
Top resid features:
ova
Tokenova
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
Russia
Token Russia
Feature activation+0.038
Top resid features:
into
Token into
Feature activation+0.055
Top resid features:
second
Token second
Feature activation+2.864
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
with
Token with
Feature activation+0.058
Top resid features:
Kenya
Token Kenya
Feature activation+0.074
Top resid features:
's
Token's
Feature activation+0.053
Top resid features:
Ed
Token Ed
Feature activation+0.061
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
United
Token United
Feature activation-0.004
Top resid features:
States
Token States
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
The
Token The
Feature activation-0.016
Top resid features:
second
Token second
Feature activation+3.063
Top resid features:
indictment
Token indictment
Feature activation+0.009
Top resid features:
count
Token count
Feature activation-0.002
Top resid features:
alleges
Token alleges
Feature activation+0.010
Top resid features:
that
Token that
Feature activation-0.009
Top resid features:
You
Token You
Feature activation-0.024
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
The
Token The
Feature activation+0.021
Top resid features:
end
Token end
Feature activation+0.067
Top resid features:
of
Token of
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
second
Token second
Feature activation+2.890
Top resid features:
side
Token side
Feature activation+0.059
Top resid features:
presents
Token presents
Feature activation+0.050
Top resid features:
a
Token a
Feature activation+0.039
Top resid features:
special
Token special
Feature activation+0.091
Top resid features:
treat
Token treat
Feature activation+0.075
Top resid features:
Ver
Token Ver
Feature activation+0.034
Top resid features:
lander
Tokenlander
Feature activation+0.038
Top resid features:
had
Token had
Feature activation+0.082
Top resid features:
runners
Token runners
Feature activation+0.108
Top resid features:
at
Token at
Feature activation+0.060
Top resid features:
second
Token second
Feature activation+3.048
Top resid features:
and
Token and
Feature activation-0.019
Top resid features:
third
Token third
Feature activation+0.284
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
.'
Token.'
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
In
TokenIn
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
second
Token second
Feature activation+2.835
Top resid features:
part
Token part
Feature activation+0.042
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
experiment
Token experiment
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
gun
Token gun
Feature activation+0.024
Top resid features:
violence
Token violence
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Second
TokenSecond
Feature activation+2.745
Top resid features:
Amendment
Token Amendment
Feature activation+0.083
Top resid features:
advocates
Token advocates
Feature activation+0.056
Top resid features:
will
Token will
Feature activation+0.025
Top resid features:
condemn
Token condemn
Feature activation+0.062
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
same
Token same
Feature activation+0.020
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
The
TokenThe
Feature activation+0.016
Top resid features:
second
Token second
Feature activation+2.889
Top resid features:
major
Token major
Feature activation+0.054
Top resid features:
change
Token change
Feature activation+0.016
Top resid features:
is
Token is
Feature activation+0.040
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
Samsung
Token Samsung
Feature activation+0.052
Top resid features:
bre
Token bre
Feature activation+0.018
Top resid features:
eder
Tokeneder
Feature activation-0.017
Top resid features:
reactors
Token reactors
Feature activation-0.030
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
second
Token second
Feature activation+3.123
Top resid features:
stage
Token stage
Feature activation+0.013
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
Th
Token Th
Feature activation+0.018
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
232
Token232
Feature activation+0.015
Top resid features:
Well
Token Well
Feature activation+0.009
Top resid features:
er
Tokener
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
second
Token second
Feature activation+2.875
Top resid features:
part
Token part
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
my
Token my
Feature activation+0.011
Top resid features:
series
Token series
Feature activation+0.081
Top resid features:
about
Token about
Feature activation+0.015
Top resid features:
healthy
Token healthy
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
abundant
Token abundant
Feature activation+0.048
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
The
Token The
Feature activation+0.033
Top resid features:
second
Token second
Feature activation+3.134
Top resid features:
basket
Token basket
Feature activation+0.083
Top resid features:
rests
Token rests
Feature activation+0.100
Top resid features:
inside
Token inside
Feature activation+0.098
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
first
Token first
Feature activation-0.016
Top resid features:
anson
Tokenanson
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.044
Top resid features:
now
Token now
Feature activation+0.027
Top resid features:
building
Token building
Feature activation+0.041
Top resid features:
his
Token his
Feature activation+0.021
Top resid features:
second
Token second
Feature activation+2.896
Top resid features:
Virgin
Token Virgin
Feature activation+0.035
Top resid features:
Hotel
Token Hotel
Feature activation+0.033
Top resid features:
on
Token on
Feature activation+0.037
Top resid features:
Nashville
Token Nashville
Feature activation+0.058
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
F
Token F
Feature activation-0.001
Top resid features:
BR
TokenBR
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
second
Token second
Feature activation+1.716
Top resid features:
stage
Token stage
Feature activation-0.002
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
loaded
Token loaded
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.006
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+0.011
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
Second
Token Second
Feature activation+2.724
Top resid features:
World
Token World
Feature activation+0.022
Top resid features:
War
Token War
Feature activation-0.033
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
German
Token German
Feature activation+0.003
Top resid features:
bombing
Token bombing
Feature activation+0.011
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.05

Head 2: 0.03

Head 3: 0.02

Head 4: 0.05

Head 5: 0.45

Head 6: 0.07

Head 7: 0.04

Head 8: 0.03

Head 9: 0.03

Head 10: 0.03

Head 11: 0.13

Positive logits

Fuk1.87

Notting1.81

heast1.80

equivalents1.74

izabeth1.70

heastern1.68

Everett1.66

Regina1.65

Region1.64

WM1.63

Hawth1.61

ackle1.60

Aki1.56

Episode1.55

=-=-=-=-=-=-=-=-1.54

Yep1.53

argo1.51

Indy1.50

flix1.49

Kazakhstan1.49

Negative logits

pract-2.05

atum-1.89

extortion-1.86

successful-1.80

atan-1.80

pers-1.78

${-1.74

danger-1.71

ooter-1.70

appropri-1.70

itent-1.65

adal-1.65

pen-1.65

transf-1.65

angler-1.63

idable-1.63

humane-1.62

gall-1.57

arial-1.57

blackmail-1.56

INTERVAL 2.254 - 2.504
CONTAINS 0.000%

grow
Token grow
Feature activation+0.000
larger
Token larger
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
third
Token third
Feature activation+2.294
investigated
Token investigated
Feature activation+0.000
what
Token what
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
growth
Token growth
Feature activation+0.000
ward
Token ward
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.279
floor
Token floor
Feature activation+0.000
and
Token and
Feature activation+0.000
meet
Token meet
Feature activation+0.000
to
Token to
Feature activation+0.000
select
Token select
Feature activation+0.000
carriage
Token carriage
Feature activation+0.000
bolt
Token bolt
Feature activation+0.000
.
Token.
Feature activation+0.000
Screw
Token Screw
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.504
nut
Token nut
Feature activation+0.000
onto
Token onto
Feature activation+0.000
the
Token the
Feature activation+0.000
bolt
Token bolt
Feature activation+0.000
until
Token until
Feature activation+0.000

INTERVAL 2.003 - 2.254
CONTAINS 0.001%

amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
tax
Token tax
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
.
Token.
Feature activation+0.000
Third
Token Third
Feature activation+2.250
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
Ki
Token Ki
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
at
Tokenat
Feature activation+0.000
in
Token in
Feature activation+0.000
third
Token third
Feature activation+2.043
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jo
TokenJo
Feature activation+0.000
P
Token P
Feature activation+0.000
a
Token a
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
environment
Token environment
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
third
Token third
Feature activation+2.223
basket
Token basket
Feature activation+0.000
nests
Token nests
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
social
Token social
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.331
,
Token,
Feature activation+0.000
third
Token third
Feature activation+2.136
and
Token and
Feature activation+0.000
fourth
Token fourth
Feature activation+1.159
are
Token are
Feature activation+0.000
present
Token present
Feature activation+0.000
,
Token,
Feature activation+0.000
additional
Token additional
Feature activation+0.000
features
Token features
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+2.158
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
attach
Token attach
Feature activation+0.000
the
Token the
Feature activation+0.000
printer
Token printer
Feature activation+0.000

INTERVAL 1.753 - 2.003
CONTAINS 0.000%

a
Token a
Feature activation+0.000
gir
Token gir
Feature activation+0.000
affe
Tokenaffe
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
fourth
Token fourth
Feature activation+1.755
character
Token character
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
gain
Token gain
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
third
Token third
Feature activation+1.946
indictment
Token indictment
Feature activation+0.000
count
Token count
Feature activation+0.000
alleges
Token alleges
Feature activation+0.000
You
Token You
Feature activation+0.000
n
Tokenn
Feature activation+0.000
had
Token had
Feature activation+0.000
runners
Token runners
Feature activation+0.000
at
Token at
Feature activation+0.000
second
Token second
Feature activation+0.000
and
Token and
Feature activation+0.000
third
Token third
Feature activation+1.784
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
:
Token:
Feature activation+0.000
H
Token H
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
o
Tokeno
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+1.847
recorded
Token recorded
Feature activation+0.000
outing
Token outing
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
contr
Token contr
Feature activation+0.000

INTERVAL 1.503 - 1.753
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
Music
Token Music
Feature activation+0.000
Row
Token Row
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
first
Token first
Feature activation+1.512
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
The
Token The
Feature activation+0.000
papers
Token papers
Feature activation+0.000
grand
Token grand
Feature activation+0.000
us
Token us
Feature activation+0.000
a
Token a
Feature activation+0.000
first
Token first
Feature activation+1.623
view
Token view
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
distant
Token distant
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+0.000
Prop
Token Prop
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+1.678
Amendment
Token Amendment
Feature activation+0.000
will
Token will
Feature activation+0.000
claim
Token claim
Feature activation+0.000
that
Token that
Feature activation+0.000
banning
Token banning
Feature activation+0.000
second
Token second
Feature activation+0.000
basket
Token basket
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.606
and
Token and
Feature activation+0.000
represents
Token represents
Feature activation+0.000
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
ers
Tokeners
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
third
Token third
Feature activation+1.659
stage
Token stage
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
F
Token F
Feature activation+0.000
BR
TokenBR
Feature activation+0.000

INTERVAL 1.252 - 1.503
CONTAINS 0.001%

his
Token his
Feature activation+0.000
first
Token first
Feature activation+1.008
booking
Token booking
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+1.352
minute
Token minute
Feature activation+0.000
of
Token of
Feature activation+0.000
injury
Token injury
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
records
Token records
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.282
half
Token half
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
trades
Token trades
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
written
Token written
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.322
person
Token person
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
book
Token book
Feature activation+0.000
does
Token does
Feature activation+0.000
is
Token is
Feature activation+0.000
absent
Token absent
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.331
,
Token,
Feature activation+0.000
third
Token third
Feature activation+2.136
and
Token and
Feature activation+0.000
fourth
Token fourth
Feature activation+1.159
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
than
Token than
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+1.456
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
too
Token too
Feature activation+0.000

INTERVAL 1.002 - 1.252
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
groups
Token groups
Feature activation+0.000
participating
Token participating
Feature activation+0.000
in
Token in
Feature activation+0.000
First
Token First
Feature activation+1.212
Amendment
Token Amendment
Feature activation+0.000
activities
Token activities
Feature activation+0.000
were
Token were
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
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+0.000
first
Token first
Feature activation+1.139
stage
Token stage
Feature activation+0.000
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
ems
Tokenems
Feature activation+0.000
earned
Token earned
Feature activation+0.000
All
Token All
Feature activation+0.000
-
Token-
Feature activation+0.000
SEC
TokenSEC
Feature activation+0.000
First
Token First
Feature activation+1.108
Team
Token Team
Feature activation+0.000
honors
Token honors
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
senior
Token senior
Feature activation+0.000
second
Token second
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
20
Token 20
Feature activation+0.000
th
Tokenth
Feature activation+1.027
century
Token century
Feature activation+0.000
,
Token,
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
He
TokenHe
Feature activation+0.000
had
Token had
Feature activation+0.000
only
Token only
Feature activation+0.000
received
Token received
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+1.008
booking
Token booking
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+1.352
minute
Token minute
Feature activation+0.000

INTERVAL 0.751 - 1.002
CONTAINS 0.001%

3
Token 3
Feature activation+0.000
ha
Token ha
Feature activation+0.000
uling
Tokenuling
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.929
two
Token two
Feature activation+0.000
career
Token career
Feature activation+0.000
touchdowns
Token touchdowns
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
than
Token than
Feature activation+0.000
average
Token average
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.980
half
Token half
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
shorter
Token shorter
Feature activation+0.000
-
Token-
Feature activation+0.000
round
Tokenround
Feature activation+0.000
selection
Token selection
Feature activation+0.000
(
Token (
Feature activation+0.000
39
Token39
Feature activation+0.000
th
Tokenth
Feature activation+0.781
overall
Token overall
Feature activation+0.154
)
Token)
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
fourth
Token fourth
Feature activation+0.982
-
Token-
Feature activation+0.000
low
Tokenlow
Feature activation+0.000
est
Tokenest
Feature activation+0.000
level
Token level
Feature activation+0.000
nationwide
Token nationwide
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Through
TokenThrough
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.813
quarter
Token quarter
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
Matthews
Token Matthews
Feature activation+0.000

INTERVAL 0.501 - 0.751
CONTAINS 0.002%

the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.569
match
Token match
Feature activation+0.000
since
Token since
Feature activation+0.000
their
Token their
Feature activation+0.000
run
Token run
Feature activation+0.000
in
Token in
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
makes
Token makes
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.673
decision
Token decision
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
roof
Token roof
Feature activation+0.000
,
Token,
Feature activation+0.000
rookie
Token rookie
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
for
Token for
Feature activation+0.000
one
Token one
Feature activation+0.000
third
Token third
Feature activation+0.575
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.531
production
Token production
Feature activation+0.000
in
Token in
Feature activation+0.000
-
Token-
Feature activation+0.000
car
Tokencar
Feature activation+0.000
navigation
Token navigation
Feature activation+0.000
15
Token 15
Feature activation+0.000
-
Token-
Feature activation+0.000
8
Token8
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.670
to
Token to
Feature activation+0.000
emerge
Token emerge
Feature activation+0.000
victorious
Token victorious
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.250 - 0.501
CONTAINS 0.003%

between
Token between
Feature activation+0.000
18
Token 18
Feature activation+0.000
th
Tokenth
Feature activation+0.354
and
Token and
Feature activation+0.000
17
Token 17
Feature activation+0.000
th
Tokenth
Feature activation+0.287
streets
Token streets
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
're
Token're
Feature activation+0.000
red
Token red
Feature activation+0.000
alert
Token alert
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
lasted
Token lasted
Feature activation+0.000
four
Token four
Feature activation+0.273
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.000
concluded
Token concluded
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
night
Token night
Feature activation+0.000
company
Token company
Feature activation+0.000
is
Token is
Feature activation+0.000
planning
Token planning
Feature activation+0.000
a
Token a
Feature activation+0.000
massive
Token massive
Feature activation+0.000
three
Token three
Feature activation+0.447
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
festival
Token festival
Feature activation+0.000
of
Token of
Feature activation+0.000
price
Token price
Feature activation+0.000
Polish
Token Polish
Feature activation+0.000
striker
Token striker
Feature activation+0.000
came
Token came
Feature activation+0.000
off
Token off
Feature activation+0.000
second
Token second
Feature activation+0.325
best
Token best
Feature activation+0.406
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
ulas
Tokenulas
Feature activation+0.000
Global
Token Global
Feature activation+0.000
Post
TokenPost
Feature activation+0.000
story
Token story
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
fourth
Token fourth
Feature activation+0.486
had
Token had
Feature activation+0.000
already
Token already
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.000
church
Token church
Feature activation+0.000

INTERVAL 0.000 - 0.250
CONTAINS 99.991%

a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
ira
Tokenira
Feature activation+0.000
const
Token const
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
ora
Tokenora
Feature activation+0.000
list
Token list
Feature activation+0.000
ada
Tokenada
Feature activation+0.000
em
Token em
Feature activation+0.000
b
Token b
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
searching
Token searching
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
has
Token has
Feature activation+0.000
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Apple
TokenApple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
-
Token-
Feature activation+0.000
Wing
TokenWing
Feature activation+0.000
and
Token and
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
Wing
TokenWing
Feature activation+0.000
star
Token star
Feature activation+0.000
fighters
Tokenfighters
Feature activation+0.000
,
Token,
Feature activation+0.000
players
Token players
Feature activation+0.000
fight
Token fight
Feature activation+0.000
Line
Token Line
Feature activation+0.000
35
Token 35
Feature activation+0.000
:
Token:
Feature activation+0.000
Stop
Token Stop
Feature activation+0.000
Service
Token Service
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
*
Token*
Feature activation+0.000
Line
Token Line
Feature activation+0.000
39
Token 39
Feature activation+0.000
Start
Token Start
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H1.5: (feature 2357)

TOP ACTIVATIONS
MAX = 2.473

to
Token to
Feature activation+0.000
announce
Token announce
Feature activation+0.000
its
Token its
Feature activation+0.000
2015
Token 2015
Feature activation+0.437
-
Token-
Feature activation+0.000
2016
Token2016
Feature activation+2.473
schedule
Token schedule
Feature activation+0.000
in
Token in
Feature activation+0.000
May
Token May
Feature activation+0.000
.
Token.
Feature activation+0.000
Behind
Token Behind
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dave
TokenDave
Feature activation+0.000
's
Token's
Feature activation+0.000
Autumn
Token Autumn
Feature activation+0.000
2014
Token 2014
Feature activation+2.358
tour
Token tour
Feature activation+0.000
wrapped
Token wrapped
Feature activation+0.000
up
Token up
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
fields
Token fields
Feature activation+0.000
that
Token that
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
and
Token and
Feature activation+0.000
2016
Token 2016
Feature activation+2.349
using
Token using
Feature activation+0.000
a
Token a
Feature activation+0.000
Boolean
Token Boolean
Feature activation+0.000
formula
Token formula
Feature activation+0.000
for
Token for
Feature activation+0.000
26
Token26
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2014
Token2014
Feature activation+2.303
:
Token:
Feature activation+0.000
17
Token 17
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
%
Token%
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dave
TokenDave
Feature activation+0.000
's
Token's
Feature activation+0.000
Autumn
Token Autumn
Feature activation+0.000
2014
Token 2014
Feature activation+2.285
Tour
Token Tour
Feature activation+0.000
Wra
Token Wra
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
Up
Token Up
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
through
Token through
Feature activation+0.000
Jan
Token Jan
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
2016
Token 2016
Feature activation+2.242
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
T
Token T
Feature activation+0.000
k
Tokenk
Feature activation+0.000
crowned
Token crowned
Feature activation+0.000
T
Token T
Feature activation+0.000
AW
TokenAW
Feature activation+0.000
A
TokenA
Feature activation+0.000
's
Token's
Feature activation+0.000
2014
Token 2014
Feature activation+2.211
"
Token "
Feature activation+0.000
T
TokenT
Feature activation+0.000
ruck
Tokenruck
Feature activation+0.000
of
Token of
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
#
Token #
Feature activation+0.000
13
Token13
Feature activation+0.000
(
Token (
Feature activation+0.000
101
Token101
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+2.135
)
Token)
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
season
Tokenseason
Feature activation+0.000
face
Token face
Feature activation+0.000
20
Token20
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2013
Token2013
Feature activation+2.098
:
Token:
Feature activation+0.000
15
Token 15
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
%
Token%
Feature activation+0.000
25
Token25
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2012
Token2012
Feature activation+2.050
:
Token:
Feature activation+0.000
13
Token 13
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
%
Token%
Feature activation+0.000
to
Token to
Feature activation+0.000
Feb
Token Feb
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
2016
Token 2016
Feature activation+2.015
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
Nolan
Token Nolan
Feature activation+0.000
and
Token and
Feature activation+0.000
#
Token #
Feature activation+0.000
6
Token6
Feature activation+0.000
(
Token (
Feature activation+0.000
147
Token147
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+2.004
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
#
Token #
Feature activation+0.000
13
Token13
Feature activation+0.000
(
Token (
Feature activation+0.000
housing
Token housing
Feature activation+0.000
market
Token market
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.226
and
Token and
Feature activation+0.000
2015
Token 2015
Feature activation+1.998
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
not
Token not
Feature activation+0.000
due
Token due
Feature activation+0.000
until
Token until
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
or
Token or
Feature activation+0.000
2017
Token 2017
Feature activation+1.969
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
mask
Token mask
Feature activation+0.000
whose
Token whose
Feature activation+0.000
best
Token best
Feature activation+0.000
pass
Token pass
Feature activation+0.000
of
Token of
Feature activation+0.000
2015
Token 2015
Feature activation+1.947
earned
Token earned
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
platform
Token platform
Feature activation+0.000
from
Token from
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
to
Token to
Feature activation+0.000
2017
Token 2017
Feature activation+1.861
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
seen
Token seen
Feature activation+0.000
by
Token by
Feature activation+0.000
about
Token about
Feature activation+0.000
to
Token to
Feature activation+0.000
43
Token 43
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+1.828
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
are
Token are
Feature activation+0.000
deteriorating
Token deteriorating
Feature activation+0.000
entire
Token entire
Feature activation+0.000
balance
Token balance
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
June
Token June
Feature activation+0.000
2013
Token 2013
Feature activation+1.705
note
Token note
Feature activation+0.000
...
Token ...
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.000
#
Token #
Feature activation+0.000
3
Token3
Feature activation+0.000
(
Token (
Feature activation+0.000
158
Token158
Feature activation+0.000
in
Token in
Feature activation+0.000
2016
Token 2016
Feature activation+1.676
),
Token),
Feature activation+0.000
#
Token #
Feature activation+0.000
6
Token6
Feature activation+0.000
(
Token (
Feature activation+0.000
147
Token147
Feature activation+0.000
further
Token further
Feature activation+0.000
construction
Token construction
Feature activation+0.000
in
Token in
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
-
Token-
Feature activation+0.000
2017
Token2017
Feature activation+1.673
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.000

Top DFA by src position
MAX = 3.875

ABC
Token ABC
Feature activation-0.036
Top resid features:
was
Token was
Feature activation-0.041
Top resid features:
to
Token to
Feature activation-0.039
Top resid features:
announce
Token announce
Feature activation-0.046
Top resid features:
its
Token its
Feature activation+0.014
Top resid features:
2015
Token 2015
Feature activation+3.875
Top resid features:
-
Token-
Feature activation-0.032
Top resid features:
2016
Token2016
Feature activation+0.442
Top resid features:
schedule
Token schedule
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
Theatre
Token Theatre
Feature activation+0.004
Top resid features:
18
Token 18
Feature activation-0.009
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
DEC
TokenDEC
Feature activation-0.010
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
2015
Token2015
Feature activation+1.508
Top resid features:
London
Token London
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
United
Token United
Feature activation-0.010
Top resid features:
Kingdom
Token Kingdom
Feature activation+0.002
Top resid features:
Is
Token Is
Feature activation-0.005
Top resid features:
two
Token two
Feature activation+0.014
Top resid features:
calculated
Token calculated
Feature activation+0.003
Top resid features:
fields
Token fields
Feature activation+0.023
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
isolated
Token isolated
Feature activation+0.016
Top resid features:
2015
Token 2015
Feature activation+3.800
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
2016
Token 2016
Feature activation+0.235
Top resid features:
using
Token using
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Boolean
Token Boolean
Feature activation+0.000
Top resid features:
very
Token very
Feature activation-0.009
Top resid features:
successful
Token successful
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
2015
Token2015
Feature activation+3.393
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
14
Token 14
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
8
Token8
Feature activation-0.008
Top resid features:
%
Token%
Feature activation-0.009
Top resid features:
Theatre
Token Theatre
Feature activation+0.006
Top resid features:
18
Token 18
Feature activation-0.010
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
DEC
TokenDEC
Feature activation-0.018
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
2015
Token2015
Feature activation+1.240
Top resid features:
London
Token London
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
United
Token United
Feature activation-0.015
Top resid features:
Kingdom
Token Kingdom
Feature activation+0.007
Top resid features:
Is
Token Is
Feature activation-0.006
Top resid features:
from
Token from
Feature activation-0.034
Top resid features:
Dec
Token Dec
Feature activation-0.031
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
26
Token 26
Feature activation-0.030
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
2015
Token 2015
Feature activation+3.577
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
through
Token through
Feature activation-0.053
Top resid features:
Jan
Token Jan
Feature activation-0.085
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
5
Token 5
Feature activation-0.004
Top resid features:
including
Token including
Feature activation-0.012
Top resid features:
his
Token his
Feature activation-0.021
Top resid features:
article
Token article
Feature activation-0.009
Top resid features:
about
Token about
Feature activation-0.040
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
2015
Token 2015
Feature activation+3.132
Top resid features:
Ford
Token Ford
Feature activation-0.021
Top resid features:
F
Token F
Feature activation+0.015
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
150
Token150
Feature activation+0.003
Top resid features:
being
Token being
Feature activation-0.050
Top resid features:
#
Token #
Feature activation-0.002
Top resid features:
3
Token3
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.009
Top resid features:
158
Token158
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
2016
Token 2016
Feature activation+1.555
Top resid features:
),
Token),
Feature activation+0.003
Top resid features:
#
Token #
Feature activation-0.004
Top resid features:
6
Token6
Feature activation-0.007
Top resid features:
(
Token (
Feature activation-0.014
Top resid features:
147
Token147
Feature activation-0.007
Top resid features:
26
Token26
Feature activation-0.009
Top resid features:
th
Tokenth
Feature activation-0.007
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
2014
Token2014
Feature activation+2.191
Top resid features:
:
Token:
Feature activation+0.005
Top resid features:
17
Token 17
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
5
Token5
Feature activation+0.002
Top resid features:
%
Token%
Feature activation-0.010
Top resid features:
very
Token very
Feature activation-0.005
Top resid features:
successful
Token successful
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
2015
Token2015
Feature activation+1.463
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
14
Token 14
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
8
Token8
Feature activation-0.005
Top resid features:
%
Token%
Feature activation+0.003
Top resid features:
from
Token from
Feature activation-0.002
Top resid features:
Dec
Token Dec
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
1
Token 1
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
2015
Token 2015
Feature activation+2.007
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
Feb
Token Feb
Feature activation-0.040
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
1
Token 1
Feature activation+0.068
Top resid features:
#
Token #
Feature activation-0.002
Top resid features:
2
Token2
Feature activation-0.009
Top resid features:
(
Token (
Feature activation-0.013
Top resid features:
163
Token163
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
2014
Token 2014
Feature activation+2.436
Top resid features:
),
Token),
Feature activation-0.000
Top resid features:
#
Token #
Feature activation-0.006
Top resid features:
3
Token3
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.016
Top resid features:
158
Token158
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Canadian
Token Canadian
Feature activation+0.015
Top resid features:
housing
Token housing
Feature activation-0.003
Top resid features:
market
Token market
Feature activation-0.008
Top resid features:
in
Token in
Feature activation-0.033
Top resid features:
2014
Token 2014
Feature activation+3.115
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
2015
Token 2015
Feature activation+0.367
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:
chip
Token chip
Feature activation+0.006
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
not
Token not
Feature activation+0.006
Top resid features:
due
Token due
Feature activation+0.011
Top resid features:
until
Token until
Feature activation-0.020
Top resid features:
2016
Token 2016
Feature activation+3.283
Top resid features:
or
Token or
Feature activation+0.071
Top resid features:
2017
Token 2017
Feature activation+0.273
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
Premier
Token Premier
Feature activation-0.002
Top resid features:
League
Token League
Feature activation+0.012
Top resid features:
Best
Token Best
Feature activation+0.000
Top resid features:
XI
Token XI
Feature activation-0.011
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
2014
Token 2014
Feature activation+3.150
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
15
Token15
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ok
Token Ok
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
posts
Token posts
Feature activation+0.021
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
platform
Token platform
Feature activation+0.031
Top resid features:
from
Token from
Feature activation+0.052
Top resid features:
2015
Token 2015
Feature activation+3.022
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
2017
Token 2017
Feature activation+0.251
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
country
Token country
Feature activation+0.004
Top resid features:
from
Token from
Feature activation-0.009
Top resid features:
Serbia
Token Serbia
Feature activation+0.011
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
2015
Token 2015
Feature activation+2.898
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.009
Top resid features:
compared
Token compared
Feature activation-0.010
Top resid features:
to
Token to
Feature activation-0.022
Top resid features:
43
Token 43
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.033
Top resid features:
or
Token or
Feature activation+0.006
Top resid features:
about
Token about
Feature activation-0.026
Top resid features:
May
Token May
Feature activation-0.025
Top resid features:
25
Token 25
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
2016
Token 2016
Feature activation+3.259
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
entire
Token entire
Feature activation+0.017
Top resid features:
balance
Token balance
Feature activation-0.027
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.025
Top resid features:
#
Token #
Feature activation-0.009
Top resid features:
2
Token2
Feature activation-0.012
Top resid features:
(
Token (
Feature activation-0.017
Top resid features:
163
Token163
Feature activation-0.009
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
2014
Token 2014
Feature activation+3.014
Top resid features:
),
Token),
Feature activation-0.033
Top resid features:
#
Token #
Feature activation-0.013
Top resid features:
3
Token3
Feature activation+0.004
Top resid features:
(
Token (
Feature activation-0.058
Top resid features:
158
Token158
Feature activation-0.007
Top resid features:
plans
Token plans
Feature activation-0.045
Top resid features:
for
Token for
Feature activation-0.034
Top resid features:
further
Token further
Feature activation-0.018
Top resid features:
construction
Token construction
Feature activation-0.043
Top resid features:
in
Token in
Feature activation-0.053
Top resid features:
2016
Token 2016
Feature activation+2.903
Top resid features:
-
Token-
Feature activation-0.030
Top resid features:
2017
Token2017
Feature activation+0.365
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
according
Token according
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.04

Head 3: 0.02

Head 4: 0.05

Head 5: 0.45

Head 6: 0.05

Head 7: 0.05

Head 8: 0.03

Head 9: 0.03

Head 10: 0.04

Head 11: 0.14

Positive logits

owship1.70

ipolar1.69

Median1.67

Nurs1.65

ruary1.61

Maj1.59

Doctors1.57

lows1.56

counterpart1.54

equivalents1.54

NAS1.53

CrossRef1.49

),"1.49

Regions1.49

GY1.49

chlor1.48

Lets1.47

Intern1.47

Kazakhstan1.47

MRI1.47

Negative logits

eton-1.84

hawk-1.73

Hebdo-1.69

achable-1.68

addons-1.64

machine-1.63

aer-1.59

escape-1.59

render-1.59

videos-1.54

eal-1.54

wearer-1.54

ebook-1.53

animate-1.52

conceal-1.50

ertodd-1.50

isner-1.50

worldly-1.50

aroo-1.49

atan-1.48

INTERVAL 2.226 - 2.473
CONTAINS 0.001%

through
Token through
Feature activation+0.000
Jan
Token Jan
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
2016
Token 2016
Feature activation+2.242
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
T
Token T
Feature activation+0.000
k
Tokenk
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dave
TokenDave
Feature activation+0.000
's
Token's
Feature activation+0.000
Autumn
Token Autumn
Feature activation+0.000
2014
Token 2014
Feature activation+2.358
tour
Token tour
Feature activation+0.000
wrapped
Token wrapped
Feature activation+0.000
up
Token up
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dave
TokenDave
Feature activation+0.000
's
Token's
Feature activation+0.000
Autumn
Token Autumn
Feature activation+0.000
2014
Token 2014
Feature activation+2.285
Tour
Token Tour
Feature activation+0.000
Wra
Token Wra
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
Up
Token Up
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
26
Token26
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2014
Token2014
Feature activation+2.303
:
Token:
Feature activation+0.000
17
Token 17
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
%
Token%
Feature activation+0.000
fields
Token fields
Feature activation+0.000
that
Token that
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
and
Token and
Feature activation+0.000
2016
Token 2016
Feature activation+2.349
using
Token using
Feature activation+0.000
a
Token a
Feature activation+0.000
Boolean
Token Boolean
Feature activation+0.000
formula
Token formula
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 1.979 - 2.226
CONTAINS 0.001%

#
Token #
Feature activation+0.000
6
Token6
Feature activation+0.000
(
Token (
Feature activation+0.000
147
Token147
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+2.004
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
#
Token #
Feature activation+0.000
13
Token13
Feature activation+0.000
(
Token (
Feature activation+0.000
20
Token20
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2013
Token2013
Feature activation+2.098
:
Token:
Feature activation+0.000
15
Token 15
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
%
Token%
Feature activation+0.000
25
Token25
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2012
Token2012
Feature activation+2.050
:
Token:
Feature activation+0.000
13
Token 13
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
%
Token%
Feature activation+0.000
crowned
Token crowned
Feature activation+0.000
T
Token T
Feature activation+0.000
AW
TokenAW
Feature activation+0.000
A
TokenA
Feature activation+0.000
's
Token's
Feature activation+0.000
2014
Token 2014
Feature activation+2.211
"
Token "
Feature activation+0.000
T
TokenT
Feature activation+0.000
ruck
Tokenruck
Feature activation+0.000
of
Token of
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
#
Token #
Feature activation+0.000
13
Token13
Feature activation+0.000
(
Token (
Feature activation+0.000
101
Token101
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+2.135
)
Token)
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
season
Tokenseason
Feature activation+0.000
face
Token face
Feature activation+0.000

INTERVAL 1.731 - 1.979
CONTAINS 0.000%

to
Token to
Feature activation+0.000
43
Token 43
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+1.828
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
are
Token are
Feature activation+0.000
deteriorating
Token deteriorating
Feature activation+0.000
mask
Token mask
Feature activation+0.000
whose
Token whose
Feature activation+0.000
best
Token best
Feature activation+0.000
pass
Token pass
Feature activation+0.000
of
Token of
Feature activation+0.000
2015
Token 2015
Feature activation+1.947
earned
Token earned
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
not
Token not
Feature activation+0.000
due
Token due
Feature activation+0.000
until
Token until
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
or
Token or
Feature activation+0.000
2017
Token 2017
Feature activation+1.969
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
the
Token the
Feature activation+0.000
platform
Token platform
Feature activation+0.000
from
Token from
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
to
Token to
Feature activation+0.000
2017
Token 2017
Feature activation+1.861
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
seen
Token seen
Feature activation+0.000
by
Token by
Feature activation+0.000
about
Token about
Feature activation+0.000

INTERVAL 1.484 - 1.731
CONTAINS 0.001%

Garden
Token Garden
Feature activation+0.000
through
Token through
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2016
Token 2016
Feature activation+1.599
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
moved
Token moved
Feature activation+0.000
to
Token to
Feature activation+0.000
civilians
Token civilians
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
2015
Token 2015
Feature activation+1.636
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
fast
Token fast
Feature activation+0.000
ed
Tokened
Feature activation+0.000
percent
Token percent
Feature activation+0.000
each
Token each
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+1.048
and
Token and
Feature activation+0.000
2014
Token 2014
Feature activation+1.557
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
those
Token those
Feature activation+0.000
boosts
Token boosts
Feature activation+0.000
were
Token were
Feature activation+0.000
6
Token6
Feature activation+0.000
percent
Token percent
Feature activation+0.000
pay
Token pay
Feature activation+0.000
bump
Token bump
Feature activation+0.000
for
Token for
Feature activation+0.000
2017
Token 2017
Feature activation+1.603
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
noted
Token noted
Feature activation+0.000
.
Token.
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
-
Token-
Feature activation+0.000
2017
Token2017
Feature activation+1.531
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.000
C
Token C
Feature activation+0.000
ogl
Tokenogl
Feature activation+0.000
iano
Tokeniano
Feature activation+0.000

INTERVAL 1.237 - 1.484
CONTAINS 0.001%

the
Token the
Feature activation+0.000
program
Token program
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
1987
Token 1987
Feature activation+1.386
death
Token death
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
team
Token team
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
.
Token.
Feature activation+0.000
26
Token 26
Feature activation+0.000
,
Token,
Feature activation+0.000
2015
Token 2015
Feature activation+1.298
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000
Jan
Token Jan
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token 5
Feature activation+0.000
years
Token years
Feature activation+0.000
in
Token in
Feature activation+0.000
prison
Token prison
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
2011
Token 2011
Feature activation+1.287
robbery
Token robbery
Feature activation+0.000
case
Token case
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2014
Token 2014
Feature activation+1.622
on
Token on
Feature activation+0.000
Sep
Token Sep
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+1.483
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
two
Token two
Feature activation+0.000
big
Token big
Feature activation+0.000
that
Token that
Feature activation+0.000
back
Token back
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+1.361
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.989 - 1.237
CONTAINS 0.001%

to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
2018
Token 2018
Feature activation+1.200
to
Token to
Feature activation+0.000
2020
Token 2020
Feature activation+0.041
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
30
Token30
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2011
Token2011
Feature activation+1.160
:
Token:
Feature activation+0.000
17
Token 17
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
%
Token%
Feature activation+0.000
Higher
Token Higher
Feature activation+0.000
Education
Token Education
Feature activation+0.000
from
Token from
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
-
Token-
Feature activation+0.000
2018
Token2018
Feature activation+1.071
and
Token and
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
National
Token National
Feature activation+0.000
University
Token University
Feature activation+0.000
'
Token '
Feature activation+0.000
absolutely
Tokenabsolutely
Feature activation+0.000
'
Token'
Feature activation+0.000
support
Token support
Feature activation+0.000
in
Token in
Feature activation+0.000
2016
Token 2016
Feature activation+1.204
while
Token while
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
with
Token with
Feature activation+0.000
Ma
Token Ma
Feature activation+0.000
ureen
Tokenureen
Feature activation+0.000
a
Token a
Feature activation+0.000
while
Token while
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2015
Token 2015
Feature activation+1.011
,
Token,
Feature activation+0.000
President
Token President
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
visited
Token visited
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.742 - 0.989
CONTAINS 0.002%

In
TokenIn
Feature activation+0.000
one
Token one
Feature activation+0.000
text
Token text
Feature activation+0.000
written
Token written
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.931
,
Token,
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Manafort
Token Manafort
Feature activation+0.000
,
Token,
Feature activation+0.000
years
Token years
Feature activation+0.000
in
Token in
Feature activation+0.000
prison
Token prison
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
2014
Token 2014
Feature activation+0.899
case
Token case
Feature activation+0.000
for
Token for
Feature activation+0.000
burglary
Token burglary
Feature activation+0.000
and
Token and
Feature activation+0.000
possession
Token possession
Feature activation+0.000
ris
Tokenris
Feature activation+0.000
)
Token)
Feature activation+0.000
March
Token March
Feature activation+0.000
24
Token 24
Feature activation+0.000
,
Token,
Feature activation+0.000
2015
Token 2015
Feature activation+0.919
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Talk
TokenTalk
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
final
Token final
Feature activation+0.000
game
Token game
Feature activation+0.000
of
Token of
Feature activation+0.000
2015
Token 2015
Feature activation+0.773
Ice
Token Ice
Feature activation+0.000
Hockey
Token Hockey
Feature activation+0.000
World
Token World
Feature activation+0.000
Championship
Token Championship
Feature activation+0.000
will
Token will
Feature activation+0.000
proceeding
Token proceeding
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
February
Token February
Feature activation+0.000
12
Token 12
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.945
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Death
TokenDeath
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
endorsed
Token endorsed
Feature activation+0.000

INTERVAL 0.495 - 0.742
CONTAINS 0.003%

ac
Tokenac
Feature activation+0.000
Power
Token Power
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2014
Token 2014
Feature activation+0.553
,
Token,
Feature activation+0.000
Kelly
Token Kelly
Feature activation+0.000
formed
Token formed
Feature activation+0.000
a
Token a
Feature activation+0.000
small
Token small
Feature activation+0.000
.
Token.
Feature activation+0.000
Int
Token Int
Feature activation+0.000
.
Token.
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
.
Token.
Feature activation+0.000
2015
Token 2015
Feature activation+0.719
,
Token,
Feature activation+0.000
DOI
Token DOI
Feature activation+0.000
:
Token:
Feature activation+0.000
10
Token 10
Feature activation+0.000
.
Token.
Feature activation+0.000
messages
Token messages
Feature activation+0.000
span
Token span
Feature activation+0.000
from
Token from
Feature activation+0.000
2012
Token 2012
Feature activation+0.649
to
Token to
Feature activation+0.000
2016
Token 2016
Feature activation+0.516
and
Token and
Feature activation+0.000
include
Token include
Feature activation+0.000
references
Token references
Feature activation+0.000
to
Token to
Feature activation+0.000
millions
Token millions
Feature activation+0.000
Studies
Token Studies
Feature activation+0.000
from
Token from
Feature activation+0.000
Yale
Token Yale
Feature activation+0.000
University
Token University
Feature activation+0.000
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+0.596
;
Token;
Feature activation+0.000
she
Token she
Feature activation+0.000
currently
Token currently
Feature activation+0.000
serves
Token serves
Feature activation+0.000
as
Token as
Feature activation+0.000
vaccines
Token vaccines
Feature activation+0.000
for
Token for
Feature activation+0.000
use
Token use
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
2018
Token 2018
Feature activation+0.699
southern
Token southern
Feature activation+0.000
hemisphere
Token hemisphere
Feature activation+0.000
influenza
Token influenza
Feature activation+0.000
season
Token season
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.247 - 0.495
CONTAINS 0.005%

a
Token a
Feature activation+0.000
hole
Token hole
Feature activation+0.000
at
Token at
Feature activation+0.000
corner
Token corner
Feature activation+0.000
for
Token for
Feature activation+0.000
2016
Token 2016
Feature activation+0.395
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
A
Token A
Feature activation+0.000
16
Token 16
Feature activation+0.000
yard
Token yard
Feature activation+0.000
reception
Token reception
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
2014
Token 2014
Feature activation+0.418
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
M
Token M
Feature activation+0.000
ank
Tokenank
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
Union
Token Union
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2020
Token2020
Feature activation+0.338
-
Token -
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+0.000
20
Token 20
Feature activation+0.000
on
Token on
Feature activation+0.000
July
Token July
Feature activation+0.000
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.449
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
missing
Token missing
Feature activation+0.000
from
Token from
Feature activation+0.000
Rs
Token Rs
Feature activation+0.000
39
Token 39
Feature activation+0.000
00
Token00
Feature activation+0.000
crore
Token crore
Feature activation+0.000
by
Token by
Feature activation+0.000
2018
Token 2018
Feature activation+0.333
-
Token-
Feature activation+0.000
19
Token19
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
employs
Token employs
Feature activation+0.000

INTERVAL 0.000 - 0.247
CONTAINS 99.985%

you
Token you
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
communicate
Token communicate
Feature activation+0.000
something
Token something
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
rolled
Token rolled
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
added
Token added
Feature activation+0.000
that
Token that
Feature activation+0.000
voters
Token voters
Feature activation+0.000
were
Token were
Feature activation+0.000
angry
Token angry
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
Los
Token Los
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
(
Token (
Feature activation+0.000
On
TokenOn
Feature activation+0.000
stream
Token stream
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
from
Token from
Feature activation+0.000
their
Token their
Feature activation+0.000
profits
Token profits
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
some
Token some
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
,
Token,
Feature activation+0.000
sales
Token sales
Feature activation+0.000
two
Token two
Feature activation+0.000
entire
Token entire
Feature activation+0.000
dimensions
Token dimensions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
goal
Token goal
Feature activation+0.000
today
Token today
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H1.5: (feature 14324)

TOP ACTIVATIONS
MAX = 2.458

start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.076
conversation
Token conversation
Feature activation+0.000
;
Token;
Feature activation+0.000
(
Token (
Feature activation+0.000
c
Tokenc
Feature activation+2.458
)
Token)
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
incidence
Token incidence
Feature activation+0.000
of
Token of
Feature activation+0.000
diseases
Token diseases
Feature activation+0.000
;
Token;
Feature activation+0.000
c
Token c
Feature activation+2.301
)
Token)
Feature activation+0.000
provide
Token provide
Feature activation+0.000
cur
Token cur
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
2015
Token 2015
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
c
Tokenc
Feature activation+2.097
)
Token)
Feature activation+0.000
Se
Token Se
Feature activation+0.000
clusion
Tokenclusion
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
if
Token if
Feature activation+0.000
old
Tokenold
Feature activation+0.000
b
Token b
Feature activation+0.758
)
Token)
Feature activation+0.000
where
Token where
Feature activation+0.000
pure
Token pure
Feature activation+0.000
a
Token a
Feature activation+1.950
=
Token =
Feature activation+0.000
F
Token F
Feature activation+0.444
(
Token (
Feature activation+0.000
error
Tokenerror
Feature activation+0.000
"
Token "
Feature activation+0.000
when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
c
Token c
Feature activation+1.868
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.785
time
Token time
Feature activation+0.000
traveler
Token traveler
Feature activation+0.000
vised
Tokenvised
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
d
Tokend
Feature activation+1.820
)
Token)
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+0.000
's
Token's
Feature activation+0.000
statue
Token statue
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
B
TokenB
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+1.810
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ste
TokenSte
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
Photos
Token Photos
Feature activation+0.000
B
Token B
Feature activation+0.000
and
Token and
Feature activation+0.000
C
Token C
Feature activation+1.705
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
the
Token the
Feature activation+0.000
template
Token template
Feature activation+0.000
counter
Token counter
Feature activation+0.000
An
Token An
Feature activation+0.000
ac
Tokenac
Feature activation+0.041
onda
Tokenonda
Feature activation+0.000
(
Token (
Feature activation+0.000
8
Token8
Feature activation+0.000
c
Tokenc
Feature activation+1.663
),
Token),
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
cru
Token cru
Feature activation+0.000
x
Tokenx
Feature activation+0.000
k
Token k
Feature activation+0.141
''
Token''
Feature activation+0.000
(
Token (
Feature activation+0.000
P
TokenP
Feature activation+0.210
a
Token a
Feature activation+1.514
a
Token a
Feature activation+1.567
')
Token')
Feature activation+0.000
=
Token =
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.245
a
Token a
Feature activation+1.482
and
Token and
Feature activation+0.000
Gal
Token Gal
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
riel
Tokenriel
Feature activation+0.000
(
Token (
Feature activation+0.000
C
TokenC
Feature activation+1.554
ate
Tokenate
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.000
tt
Tokentt
Feature activation+0.000
)
Token)
Feature activation+0.000
'
Token'
Feature activation+0.000
k
Token k
Feature activation+0.141
''
Token''
Feature activation+0.000
(
Token (
Feature activation+0.000
P
TokenP
Feature activation+0.210
a
Token a
Feature activation+1.514
a
Token a
Feature activation+1.567
')
Token')
Feature activation+0.000
=
Token =
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.245
a
Token a
Feature activation+1.567
')
Token')
Feature activation+0.000
=
Token =
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.245
a
Token a
Feature activation+1.482
)
Token)
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.256
'
Token'
Feature activation+0.000
a
Token a
Feature activation+1.535
who
Token who
Feature activation+0.000
still
Token still
Feature activation+0.000
fall
Token fall
Feature activation+0.000
ill
Token ill
Feature activation+0.000
;
Token;
Feature activation+0.000
d
Token d
Feature activation+1.419
)
Token)
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
and
Token and
Feature activation+0.000
detect
Token detect
Feature activation+0.000
early
Token early
Feature activation+0.000
no
Tokenno
Feature activation+0.000
e
Token e
Feature activation+1.018
")
Token")
Feature activation+0.000
(
Token (
Feature activation+0.000
const
Tokenconst
Feature activation+0.000
a
Token a
Feature activation+1.400
)
Token)
Feature activation+0.000
F
Token F
Feature activation+0.061
op
Token op
Feature activation+0.360
e
Token e
Feature activation+0.717
k
Token k
Feature activation+0.032
op
Tokenop
Feature activation+0.158
'
Token'
Feature activation+0.000
`
Token`
Feature activation+0.000
b
Token b
Feature activation+0.342
)
Token)
Feature activation+0.000
e
Token e
Feature activation+1.391
''
Token''
Feature activation+0.000
=
Token =
Feature activation+0.000
P
Token P
Feature activation+0.409
e
Token e
Feature activation+1.061
e
Token e
Feature activation+0.948
create
Token create
Feature activation+0.000
No
Token No
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
(
Token (
Feature activation+0.000
8
Token8
Feature activation+0.000
c
Tokenc
Feature activation+1.359
+
Token+
Feature activation+0.000
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
to
Token to
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.152
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+1.310
.
Token.
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
charge
Token charge
Feature activation+0.000
a
Token a
Feature activation+0.171
op
Tokenop
Feature activation+0.080
`
Token`
Feature activation+0.000
b
Token b
Feature activation+0.229
)
Token)
Feature activation+0.000
(
Token (
Feature activation+0.000
a
Tokena
Feature activation+1.274
'
Token'
Feature activation+0.000
`
Token `
Feature activation+0.000
op
Tokenop
Feature activation+0.158
'
Token'
Feature activation+0.000
`
Token`
Feature activation+0.000
in
Token in
Feature activation+0.000
each
Token each
Feature activation+0.000
trap
Token trap
Feature activation+0.000
).
Token).
Feature activation+0.000
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+1.245
)
Token)
Feature activation+0.000
Star
Token Star
Feature activation+0.000
vation
Tokenvation
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000
is
Token is
Feature activation+0.000

Top DFA by src position
MAX = 2.858

in
Token in
Feature activation+0.008
Top resid features:
your
Token your
Feature activation+0.007
Top resid features:
opinion
Token opinion
Feature activation-0.010
Top resid features:
;
Token;
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.010
Top resid features:
b
Tokenb
Feature activation+2.746
Top resid features:
)
Token)
Feature activation+0.014
Top resid features:
it
Token it
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
adopt
Token adopt
Feature activation+0.003
Top resid features:
preventive
Token preventive
Feature activation-0.009
Top resid features:
measures
Token measures
Feature activation-0.007
Top resid features:
;
Token;
Feature activation+0.010
Top resid features:
b
Token b
Feature activation+2.858
Top resid features:
)
Token)
Feature activation+0.009
Top resid features:
educate
Token educate
Feature activation+0.002
Top resid features:
communities
Token communities
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
lower
Token lower
Feature activation+0.043
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.046
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
(
Token(
Feature activation+0.008
Top resid features:
b
Tokenb
Feature activation+2.598
Top resid features:
)
Token)
Feature activation+0.009
Top resid features:
Pr
Token Pr
Feature activation-0.002
Top resid features:
one
Tokenone
Feature activation-0.007
Top resid features:
restraint
Token restraint
Feature activation-0.013
Top resid features:
allowed
Token allowed
Feature activation+0.013
Top resid features:
Applic
Token Applic
Feature activation+0.010
Top resid features:
ative
Tokenative
Feature activation-0.019
Top resid features:
(
Token (
Feature activation+0.039
Top resid features:
F
TokenF
Feature activation+0.031
Top resid features:
old
Tokenold
Feature activation+0.007
Top resid features:
b
Token b
Feature activation+1.810
Top resid features:
)
Token)
Feature activation+0.030
Top resid features:
where
Token where
Feature activation+0.099
Top resid features:
pure
Token pure
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.224
Top resid features:
=
Token =
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
very
Token very
Feature activation-0.003
Top resid features:
confused
Token confused
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
b
Token b
Feature activation+2.397
Top resid features:
)
Token)
Feature activation+0.005
Top resid features:
had
Token had
Feature activation+0.001
Top resid features:
only
Token only
Feature activation+0.001
Top resid features:
recently
Token recently
Feature activation-0.001
Top resid features:
awoken
Token awoken
Feature activation+0.005
Top resid features:
2015
Token 2015
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
(
Token(
Feature activation+0.009
Top resid features:
c
Tokenc
Feature activation+1.355
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Se
Token Se
Feature activation+0.002
Top resid features:
clusion
Tokenclusion
Feature activation+0.000
Top resid features:
allowed
Token allowed
Feature activation-0.001
Top resid features:
if
Token if
Feature activation+0.017
Top resid features:
per
Token per
Feature activation+0.027
Top resid features:
cent
Token cent
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
B
TokenB
Feature activation+2.314
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
C
TokenC
Feature activation+0.220
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
Ste
TokenSte
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.019
Top resid features:
chest
Token chest
Feature activation+0.011
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.040
Top resid features:
see
Token see
Feature activation+0.017
Top resid features:
Photos
Token Photos
Feature activation-0.011
Top resid features:
B
Token B
Feature activation+2.181
Top resid features:
and
Token and
Feature activation+0.059
Top resid features:
C
Token C
Feature activation+0.328
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Turn
Token Turn
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.050
Top resid features:
8
Token8
Feature activation+0.013
Top resid features:
b
Tokenb
Feature activation+1.234
Top resid features:
+
Token+
Feature activation-0.003
Top resid features:
),
Token),
Feature activation+0.016
Top resid features:
Cobra
Token Cobra
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+0.023
Top resid features:
8
Token8
Feature activation-0.001
Top resid features:
'
Token'
Feature activation+0.009
Top resid features:
`
Token `
Feature activation+0.007
Top resid features:
op
Tokenop
Feature activation-0.004
Top resid features:
'
Token'
Feature activation+0.011
Top resid features:
`
Token`
Feature activation+0.005
Top resid features:
b
Token b
Feature activation+0.516
Top resid features:
)
Token)
Feature activation+0.016
Top resid features:
e
Token e
Feature activation+0.010
Top resid features:
''
Token''
Feature activation+0.010
Top resid features:
=
Token =
Feature activation+0.023
Top resid features:
P
Token P
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
sinister
Token sinister
Feature activation-0.001
Top resid features:
Nec
Token Nec
Feature activation-0.005
Top resid features:
romancer
Tokenromancer
Feature activation+0.001
Top resid features:
(
Token (
Feature activation-0.000
Top resid features:
B
TokenB
Feature activation+1.813
Top resid features:
ened
Tokenened
Feature activation+0.004
Top resid features:
ict
Tokenict
Feature activation-0.002
Top resid features:
Cumber
Token Cumber
Feature activation-0.001
Top resid features:
batch
Tokenbatch
Feature activation+0.006
Top resid features:
)
Token)
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+0.003
Top resid features:
a
Tokena
Feature activation+0.040
Top resid features:
`
Token `
Feature activation+0.002
Top resid features:
op
Tokenop
Feature activation-0.004
Top resid features:
`
Token`
Feature activation+0.000
Top resid features:
b
Token b
Feature activation+0.486
Top resid features:
)
Token)
Feature activation+0.012
Top resid features:
(
Token (
Feature activation+0.007
Top resid features:
a
Tokena
Feature activation+0.039
Top resid features:
'
Token'
Feature activation+0.010
Top resid features:
`
Token `
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.002
Top resid features:
a
Tokena
Feature activation+0.031
Top resid features:
`
Token `
Feature activation+0.001
Top resid features:
op
Tokenop
Feature activation-0.004
Top resid features:
`
Token`
Feature activation-0.001
Top resid features:
b
Token b
Feature activation+0.474
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
a
Tokena
Feature activation+0.030
Top resid features:
'
Token'
Feature activation+0.006
Top resid features:
`
Token `
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
incidence
Token incidence
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
diseases
Token diseases
Feature activation-0.003
Top resid features:
;
Token;
Feature activation+0.005
Top resid features:
c
Token c
Feature activation+1.341
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
provide
Token provide
Feature activation+0.004
Top resid features:
cur
Token cur
Feature activation+0.028
Top resid features:
ative
Tokenative
Feature activation-0.007
Top resid features:
treatment
Token treatment
Feature activation+0.000
Top resid features:
Applic
Token Applic
Feature activation+0.004
Top resid features:
ative
Tokenative
Feature activation-0.012
Top resid features:
(
Token (
Feature activation+0.008
Top resid features:
F
TokenF
Feature activation+0.017
Top resid features:
old
Tokenold
Feature activation+0.004
Top resid features:
b
Token b
Feature activation+1.386
Top resid features:
)
Token)
Feature activation+0.009
Top resid features:
where
Token where
Feature activation+0.015
Top resid features:
pure
Token pure
Feature activation-0.009
Top resid features:
a
Token a
Feature activation+0.059
Top resid features:
=
Token =
Feature activation+0.002
Top resid features:
'
Token'
Feature activation+0.028
Top resid features:
`
Token `
Feature activation+0.036
Top resid features:
op
Tokenop
Feature activation+0.008
Top resid features:
'
Token'
Feature activation+0.028
Top resid features:
`
Token`
Feature activation+0.027
Top resid features:
b
Token b
Feature activation+0.567
Top resid features:
)
Token)
Feature activation+0.095
Top resid features:
e
Token e
Feature activation+0.137
Top resid features:
''
Token''
Feature activation+0.000
Top resid features:
=
Token =
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
+
Token+
Feature activation-0.000
Top resid features:
),
Token),
Feature activation+0.009
Top resid features:
Cobra
Token Cobra
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+0.006
Top resid features:
8
Token8
Feature activation+0.005
Top resid features:
b
Tokenb
Feature activation+0.942
Top resid features:
),
Token),
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
An
Token An
Feature activation+0.010
Top resid features:
ac
Tokenac
Feature activation+0.048
Top resid features:
onda
Tokenonda
Feature activation-0.004
Top resid features:
months
Token months
Feature activation-0.005
Top resid features:
ago
Token ago
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
pressure
Token pressure
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
B
Token B
Feature activation+1.006
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
C
TokenC
Feature activation+0.238
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.034
Top resid features:
a
Tokena
Feature activation+0.191
Top resid features:
`
Token `
Feature activation+0.050
Top resid features:
op
Tokenop
Feature activation-0.001
Top resid features:
`
Token`
Feature activation+0.026
Top resid features:
b
Token b
Feature activation+0.602
Top resid features:
)
Token)
Feature activation+0.058
Top resid features:
(
Token (
Feature activation+0.102
Top resid features:
a
Tokena
Feature activation+0.171
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
`
Token `
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Bars
Token Bars
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
A
Token A
Feature activation+0.041
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation+0.004
Top resid features:
C
TokenC
Feature activation+1.378
Top resid features:
represent
Token represent
Feature activation-0.002
Top resid features:
average
Token average
Feature activation-0.000
Top resid features:
(
Token (
Feature activation+0.008
Top resid features:
±
Token±
Feature activation+0.001
Top resid features:
SEM
Token SEM
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.06

Head 2: 0.04

Head 3: 0.02

Head 4: 0.05

Head 5: 0.45

Head 6: 0.03

Head 7: 0.05

Head 8: 0.03

Head 9: 0.03

Head 10: 0.02

Head 11: 0.11

Positive logits

1.75

GY1.74

ignment1.74

Norfolk1.74

Hampton1.70

ockey1.70

alignment1.65

iddle1.64

ish1.64

iki1.64

Kenn1.64

argo1.62

oret1.62

odo1.60

iq1.59

Bulldogs1.59

ocrat1.58

uth1.57

OURCE1.57

Highlands1.55

Negative logits

rals-2.09

cens-2.07

Jury-1.98

loads-1.97

interstitial-1.91

scen-1.88

transports-1.86

pers-1.86

ebook-1.85

tremend-1.81

appl-1.79

Reviewer-1.77

advertising-1.76

pard-1.75

quartered-1.75

bum-1.73

vre-1.72

confir-1.70

vec-1.70

scene-1.67

INTERVAL 2.212 - 2.458
CONTAINS 0.000%

start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.076
conversation
Token conversation
Feature activation+0.000
;
Token;
Feature activation+0.000
(
Token (
Feature activation+0.000
c
Tokenc
Feature activation+2.458
)
Token)
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
incidence
Token incidence
Feature activation+0.000
of
Token of
Feature activation+0.000
diseases
Token diseases
Feature activation+0.000
;
Token;
Feature activation+0.000
c
Token c
Feature activation+2.301
)
Token)
Feature activation+0.000
provide
Token provide
Feature activation+0.000
cur
Token cur
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000

INTERVAL 1.966 - 2.212
CONTAINS 0.000%

2015
Token 2015
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
c
Tokenc
Feature activation+2.097
)
Token)
Feature activation+0.000
Se
Token Se
Feature activation+0.000
clusion
Tokenclusion
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
if
Token if
Feature activation+0.000

INTERVAL 1.720 - 1.966
CONTAINS 0.000%

when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
c
Token c
Feature activation+1.868
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.785
time
Token time
Feature activation+0.000
traveler
Token traveler
Feature activation+0.000
vised
Tokenvised
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
d
Tokend
Feature activation+1.820
)
Token)
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+0.000
's
Token's
Feature activation+0.000
statue
Token statue
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
B
TokenB
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+1.810
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ste
TokenSte
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
old
Tokenold
Feature activation+0.000
b
Token b
Feature activation+0.758
)
Token)
Feature activation+0.000
where
Token where
Feature activation+0.000
pure
Token pure
Feature activation+0.000
a
Token a
Feature activation+1.950
=
Token =
Feature activation+0.000
F
Token F
Feature activation+0.444
(
Token (
Feature activation+0.000
error
Tokenerror
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 1.475 - 1.720
CONTAINS 0.001%

An
Token An
Feature activation+0.000
ac
Tokenac
Feature activation+0.041
onda
Tokenonda
Feature activation+0.000
(
Token (
Feature activation+0.000
8
Token8
Feature activation+0.000
c
Tokenc
Feature activation+1.663
),
Token),
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
cru
Token cru
Feature activation+0.000
x
Tokenx
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
Photos
Token Photos
Feature activation+0.000
B
Token B
Feature activation+0.000
and
Token and
Feature activation+0.000
C
Token C
Feature activation+1.705
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
the
Token the
Feature activation+0.000
template
Token template
Feature activation+0.000
counter
Token counter
Feature activation+0.000
k
Token k
Feature activation+0.141
''
Token''
Feature activation+0.000
(
Token (
Feature activation+0.000
P
TokenP
Feature activation+0.210
a
Token a
Feature activation+1.514
a
Token a
Feature activation+1.567
')
Token')
Feature activation+0.000
=
Token =
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.245
a
Token a
Feature activation+1.482
'
Token'
Feature activation+0.000
k
Token k
Feature activation+0.141
''
Token''
Feature activation+0.000
(
Token (
Feature activation+0.000
P
TokenP
Feature activation+0.210
a
Token a
Feature activation+1.514
a
Token a
Feature activation+1.567
')
Token')
Feature activation+0.000
=
Token =
Feature activation+0.000
(
Token (
Feature activation+0.000
k
Tokenk
Feature activation+0.245
and
Token and
Feature activation+0.000
Gal
Token Gal
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
riel
Tokenriel
Feature activation+0.000
(
Token (
Feature activation+0.000
C
TokenC
Feature activation+1.554
ate
Tokenate
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.000
tt
Tokentt
Feature activation+0.000
)
Token)
Feature activation+0.000

INTERVAL 1.229 - 1.475
CONTAINS 0.001%

to
Token to
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
the
Token the
Feature activation+0.000
B
Token B
Feature activation+0.152
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+1.310
.
Token.
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
charge
Token charge
Feature activation+0.000
a
Token a
Feature activation+0.171
no
Tokenno
Feature activation+0.000
e
Token e
Feature activation+1.018
")
Token")
Feature activation+0.000
(
Token (
Feature activation+0.000
const
Tokenconst
Feature activation+0.000
a
Token a
Feature activation+1.400
)
Token)
Feature activation+0.000
F
Token F
Feature activation+0.061
op
Token op
Feature activation+0.360
e
Token e
Feature activation+0.717
k
Token k
Feature activation+0.032
op
Tokenop
Feature activation+0.080
`
Token`
Feature activation+0.000
b
Token b
Feature activation+0.229
)
Token)
Feature activation+0.000
(
Token (
Feature activation+0.000
a
Tokena
Feature activation+1.274
'
Token'
Feature activation+0.000
`
Token `
Feature activation+0.000
op
Tokenop
Feature activation+0.158
'
Token'
Feature activation+0.000
`
Token`
Feature activation+0.000
op
Tokenop
Feature activation+0.158
'
Token'
Feature activation+0.000
`
Token`
Feature activation+0.000
b
Token b
Feature activation+0.342
)
Token)
Feature activation+0.000
e
Token e
Feature activation+1.391
''
Token''
Feature activation+0.000
=
Token =
Feature activation+0.000
P
Token P
Feature activation+0.409
e
Token e
Feature activation+1.061
e
Token e
Feature activation+0.948
who
Token who
Feature activation+0.000
still
Token still
Feature activation+0.000
fall
Token fall
Feature activation+0.000
ill
Token ill
Feature activation+0.000
;
Token;
Feature activation+0.000
d
Token d
Feature activation+1.419
)
Token)
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
and
Token and
Feature activation+0.000
detect
Token detect
Feature activation+0.000
early
Token early
Feature activation+0.000

INTERVAL 0.983 - 1.229
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+1.171
350
Token 350
Feature activation+0.000
degree
Token degree
Feature activation+0.000
Fahrenheit
Token Fahrenheit
Feature activation+0.000
oven
Token oven
Feature activation+0.000
for
Token for
Feature activation+0.000
star
Tokenstar
Feature activation+0.000
craft
Tokencraft
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
pu
Tokenpu
Feature activation+0.000
C
TokenC
Feature activation+1.040
K
TokenK
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+0.000
C
Token C
Feature activation+1.143
:
Token:
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
the
Token the
Feature activation+0.000
Green
Token Green
Feature activation+0.000
B
Token B
Feature activation+0.000
eret
Tokeneret
Feature activation+0.000
from
Token from
Feature activation+0.000
A
Token A
Feature activation+1.216
ver
Tokenver
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
Park
Token Park
Feature activation+0.000
deserves
Token deserves
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+0.000
C
Token C
Feature activation+0.985
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000

INTERVAL 0.737 - 0.983
CONTAINS 0.004%

of
Token of
Feature activation+0.000
issue
Token issue
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.810
FA
TokenFA
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000
Garner
Token Garner
Feature activation+0.000
am
Token am
Feature activation+0.000
unhappy
Token unhappy
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.970
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
help
Token help
Feature activation+0.000
"
Token"
Feature activation+0.000
the
Token the
Feature activation+0.000
girl
Token girl
Feature activation+0.000
but
Token but
Feature activation+0.000
failed
Token failed
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.774
pan
Token pan
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
at
Tokenat
Feature activation+0.000
of
Token of
Feature activation+0.000
Canada
TokenCanada
Feature activation+0.000
reserves
Token reserves
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.924
ultural
Tokenultural
Feature activation+0.000
exception
Token exception
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ext
TokenExt
Feature activation+0.000
um
Token um
Feature activation+0.000
apart
Token apart
Feature activation+0.000
ament
Tokenament
Feature activation+0.000
o
Tokeno
Feature activation+0.000
na
Token na
Feature activation+0.000
c
Token c
Feature activation+0.796
id
Tokenid
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
de
Token de
Feature activation+0.000
S
Token S
Feature activation+0.000
ão
Tokenão
Feature activation+0.000

INTERVAL 0.492 - 0.737
CONTAINS 0.005%

the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
to
Token to
Feature activation+0.000
explode
Token explode
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.509
loud
Token loud
Feature activation+0.000
bang
Token bang
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
unlike
Token unlike
Feature activation+0.000
allows
Token allows
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.533
core
Token core
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
count
Token count
Feature activation+0.000
the
Token the
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
AI
Token AI
Feature activation+0.000
populated
Token populated
Feature activation+0.000
lane
Token lane
Feature activation+0.000
(
Token (
Feature activation+0.000
B
TokenB
Feature activation+0.638
).
Token).
Feature activation+0.000
AI
Token AI
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.105
filler
Token filler
Feature activation+0.000
SS
Token SS
Feature activation+0.000
50
Token50
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
78
Token78
Feature activation+0.000
A
TokenA
Feature activation+0.655
)
Token )
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Solar
TokenSolar
Feature activation+0.000
charge
Token charge
Feature activation+0.000
industry
Token industry
Feature activation+0.000
with
Token with
Feature activation+0.000
movies
Token movies
Feature activation+0.000
like
Token like
Feature activation+0.000
"
Token "
Feature activation+0.000
D
TokenD
Feature activation+0.504
h
Tokenh
Feature activation+0.000
oom
Tokenoom
Feature activation+0.000
",
Token",
Feature activation+0.000
"
Token "
Feature activation+0.000
Yu
TokenYu
Feature activation+0.000

INTERVAL 0.246 - 0.492
CONTAINS 0.009%

Ċ
TokenĊ
Feature activation+0.000
Aud
TokenAud
Feature activation+0.000
i
Tokeni
Feature activation+0.000
osh
Tokenosh
Feature activation+0.000
ield
Tokenield
Feature activation+0.000
w
Token w
Feature activation+0.397
weights
Token weights
Feature activation+0.000
118
Token 118
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
b
Token b
Feature activation+0.000
).
Token).
Feature activation+0.000
These
Token These
Feature activation+0.000
results
Token results
Feature activation+0.000
demonstrate
Token demonstrate
Feature activation+0.000
that
Token that
Feature activation+0.000
A
Token A
Feature activation+0.278
com
Tokencom
Feature activation+0.000
ys
Tokenys
Feature activation+0.000
possess
Token possess
Feature activation+0.000
skin
Token skin
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.426
9
Token 9
Feature activation+0.000
foot
Token foot
Feature activation+0.000
tall
Token tall
Feature activation+0.000
lizard
Token lizard
Feature activation+0.000
man
Token man
Feature activation+0.000
Explosive
Token Explosive
Feature activation+0.000
Device
Token Device
Feature activation+0.000
(
Token (
Feature activation+0.000
B
TokenB
Feature activation+0.000
BI
TokenBI
Feature activation+0.000
ED
TokenED
Feature activation+0.271
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
Impro
Token Impro
Feature activation+0.000
vised
Tokenvised
Feature activation+0.000
Explosive
Token Explosive
Feature activation+0.000
%
Token%
Feature activation+0.000
2
Token2
Feature activation+0.000
B
TokenB
Feature activation+0.083
24
Token24
Feature activation+0.000
per
Tokenper
Feature activation+0.000
c
Tokenc
Feature activation+0.329
.
Token.
Feature activation+0.000
jpg
Tokenjpg
Feature activation+0.000
)
Token)
Feature activation+0.000
A
Token A
Feature activation+0.673
view
Token view
Feature activation+0.000

INTERVAL 0.000 - 0.246
CONTAINS 99.978%

's
Token's
Feature activation+0.000
follows
Token follows
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
Puerto
Token Puerto
Feature activation+0.000
Rican
Token Rican
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
set
Token set
Feature activation+0.000
Inter
Token Inter
Feature activation+0.000
continental
Tokencontinental
Feature activation+0.000
Hotel
Token Hotel
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
menu
Token menu
Feature activation+0.000
"
Token "
Feature activation+0.000
drawn
Tokendrawn
Feature activation+0.000
directly
Token directly
Feature activation+0.000
from
Token from
Feature activation+0.000
Ian
Token Ian
Feature activation+0.000
the
Token the
Feature activation+0.000
Republic
Token Republic
Feature activation+0.000
of
Token of
Feature activation+0.000
Armenia
Token Armenia
Feature activation+0.000
in
Token in
Feature activation+0.000
1994
Token 1994
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Society
Token Society
Feature activation+0.000
,
Token,
Feature activation+0.000
Iowa
Token Iowa
Feature activation+0.000
,
Token,
Feature activation+0.000
Massachusetts
Token Massachusetts
Feature activation+0.000
,
Token,
Feature activation+0.000
New
Token New
Feature activation+0.000
Hampshire
Token Hampshire
Feature activation+0.000
and
Token and
Feature activation+0.000
Vermont
Token Vermont
Feature activation+0.000
,
Token,
Feature activation+0.000
plus
Token plus
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
your
Token your
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
variables
Token variables
Feature activation+0.000
are
Token are
Feature activation+0.000
shown
Token shown
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
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