H4.5 top features

Top feature 0 in H4.5: (feature 17212)

TOP ACTIVATIONS
MAX = 3.821

right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
voter
Token voter
Feature activation+2.602
might
Token might
Feature activation+3.821
be
Token be
Feature activation+3.389
so
Token so
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
Che
TokenChe
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
guy
Token guy
Feature activation+2.675
in
Token in
Feature activation+3.716
a
Token a
Feature activation+0.365
mask
Token mask
Feature activation+0.000
whose
Token whose
Feature activation+1.297
best
Token best
Feature activation+0.000
pass
Token pass
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
voter
Token voter
Feature activation+2.602
might
Token might
Feature activation+3.821
be
Token be
Feature activation+3.389
so
Token so
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
a
Token a
Feature activation+0.000
neuron
Token neuron
Feature activation+0.000
fire
Token fire
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
neuron
Token neuron
Feature activation+3.384
will
Token will
Feature activation+3.325
also
Token also
Feature activation+2.162
fire
Token fire
Feature activation+0.331
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
got
Token got
Feature activation+0.000
that
Token that
Feature activation+0.000
e
Token e
Feature activation+0.125
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+3.376
.
Token.
Feature activation+0.473
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
By
TokenBy
Feature activation+0.000
neuron
Token neuron
Feature activation+0.000
fire
Token fire
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
neuron
Token neuron
Feature activation+3.384
will
Token will
Feature activation+3.325
also
Token also
Feature activation+2.162
fire
Token fire
Feature activation+0.331
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
call
Token call
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
that
Token that
Feature activation+0.000
rare
Token rare
Feature activation+1.864
f
Tokenf
Feature activation+0.008
ied
Tokenied
Feature activation+0.000
feeling
Token feeling
Feature activation+3.319
of
Token of
Feature activation+3.164
perfect
Token perfect
Feature activation+0.000
immersion
Token immersion
Feature activation+0.000
.
Token.
Feature activation+0.007
You
Token You
Feature activation+0.000
home
Token home
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
that
Token that
Feature activation+0.000
most
Token most
Feature activation+3.285
quint
Token quint
Feature activation+0.450
essential
Tokenessential
Feature activation+3.176
of
Token of
Feature activation+2.503
bu
Token bu
Feature activation+0.000
col
Tokencol
Feature activation+0.000
trust
Token trust
Feature activation+0.048
y
Tokeny
Feature activation+0.645
red
Token red
Feature activation+2.200
square
Token square
Feature activation+1.395
freeze
Token freeze
Feature activation+1.145
button
Token button
Feature activation+3.244
and
Token and
Feature activation+1.864
my
Token my
Feature activation+0.000
collection
Token collection
Feature activation+0.000
began
Token began
Feature activation+0.000
.
Token.
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
voter
Token voter
Feature activation+2.311
might
Token might
Feature activation+3.244
easily
Token easily
Feature activation+0.000
decide
Token decide
Feature activation+0.000
to
Token to
Feature activation+0.000
stick
Token stick
Feature activation+0.000
with
Token with
Feature activation+0.000
hear
Token hear
Feature activation+0.000
that
Token that
Feature activation+0.000
old
Token old
Feature activation+1.373
chest
Token chest
Feature activation+0.574
nut
Tokennut
Feature activation+2.499
of
Token of
Feature activation+3.242
'
Token '
Feature activation+0.105
sc
Tokensc
Feature activation+0.000
rou
Tokenrou
Feature activation+0.000
ng
Tokenng
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
this
Token this
Feature activation+0.000
record
Token record
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
record
Token record
Feature activation+0.515
you
Token you
Feature activation+3.233
also
Token also
Feature activation+0.754
did
Token did
Feature activation+0.042
the
Token the
Feature activation+0.000
M
Token M
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Keep
TokenKeep
Feature activation+0.000
that
Token that
Feature activation+0.000
image
Token image
Feature activation+1.820
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+3.216
while
Token while
Feature activation+0.000
you
Token you
Feature activation+0.000
sav
Token sav
Feature activation+0.000
or
Tokenor
Feature activation+0.000
these
Token these
Feature activation+0.000
holds
Token holds
Feature activation+0.000
value
Token value
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
value
Token value
Feature activation+3.185
can
Token can
Feature activation+2.237
be
Token be
Feature activation+2.338
analysed
Token analysed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
Token But
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
universe
Token universe
Feature activation+3.177
impl
Token impl
Feature activation+1.835
oded
Tokenoded
Feature activation+1.750
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
taxpayers
Token taxpayers
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
that
Token that
Feature activation+0.000
most
Token most
Feature activation+3.285
quint
Token quint
Feature activation+0.450
essential
Tokenessential
Feature activation+3.176
of
Token of
Feature activation+2.503
bu
Token bu
Feature activation+0.000
col
Tokencol
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
British
Token British
Feature activation+0.000
other
Token other
Feature activation+0.000
accomplishments
Token accomplishments
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
gathering
Token gathering
Feature activation+2.845
of
Token of
Feature activation+3.175
Catholic
Token Catholic
Feature activation+0.000
bishops
Token bishops
Feature activation+0.000
from
Token from
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
that
Token that
Feature activation+0.000
beautiful
Token beautiful
Feature activation+2.068
feeling
Token feeling
Feature activation+3.015
you
Token you
Feature activation+3.173
get
Token get
Feature activation+0.000
when
Token when
Feature activation+0.010
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
that
Token that
Feature activation+0.000
whole
Token whole
Feature activation+2.414
community
Token community
Feature activation+1.299
thing
Token thing
Feature activation+3.166
,
Token,
Feature activation+1.451
and
Token and
Feature activation+1.061
we
Token we
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
rare
Token rare
Feature activation+1.864
f
Tokenf
Feature activation+0.008
ied
Tokenied
Feature activation+0.000
feeling
Token feeling
Feature activation+3.319
of
Token of
Feature activation+3.164
perfect
Token perfect
Feature activation+0.000
immersion
Token immersion
Feature activation+0.000
.
Token.
Feature activation+0.007
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

Top DFA by src position
MAX = 4.195

and
Token and
Feature activation+0.007
Top resid features:
Clinton
Token Clinton
Feature activation+0.002
Top resid features:
right
Token right
Feature activation+0.009
Top resid features:
now
Token now
Feature activation+0.020
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
that
Token that
Feature activation+4.010
Top resid features:
voter
Token voter
Feature activation+0.175
Top resid features:
might
Token might
Feature activation+0.047
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
opposed
Token opposed
Feature activation+0.000
Top resid features:
us
Tokenus
Feature activation-0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
Che
TokenChe
Feature activation+0.002
Top resid features:
ek
Tokenek
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+4.195
Top resid features:
guy
Token guy
Feature activation+0.074
Top resid features:
in
Token in
Feature activation-0.029
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
mask
Token mask
Feature activation+0.000
Top resid features:
whose
Token whose
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.005
Top resid features:
now
Token now
Feature activation+0.023
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
that
Token that
Feature activation+3.727
Top resid features:
voter
Token voter
Feature activation+0.043
Top resid features:
might
Token might
Feature activation+0.030
Top resid features:
be
Token be
Feature activation+0.061
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
opposed
Token opposed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
neuron
Token neuron
Feature activation-0.018
Top resid features:
fire
Token fire
Feature activation+0.030
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
that
Token that
Feature activation+3.972
Top resid features:
neuron
Token neuron
Feature activation-0.047
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
fire
Token fire
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
TokenWe
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
ve
Tokenve
Feature activation+0.004
Top resid features:
got
Token got
Feature activation-0.065
Top resid features:
that
Token that
Feature activation+3.873
Top resid features:
e
Token e
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.027
Top resid features:
mail
Tokenmail
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
neuron
Token neuron
Feature activation-0.008
Top resid features:
fire
Token fire
Feature activation+0.022
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
that
Token that
Feature activation+3.648
Top resid features:
neuron
Token neuron
Feature activation+0.218
Top resid features:
will
Token will
Feature activation+0.062
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
fire
Token fire
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
reading
Token reading
Feature activation+0.004
Top resid features:
words
Token words
Feature activation-0.009
Top resid features:
at
Token at
Feature activation-0.005
Top resid features:
all
Token all
Feature activation+0.004
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.080
Top resid features:
that
Token that
Feature activation+3.922
Top resid features:
rare
Token rare
Feature activation+0.014
Top resid features:
f
Tokenf
Feature activation+0.006
Top resid features:
ied
Tokenied
Feature activation+0.129
Top resid features:
feeling
Token feeling
Feature activation-0.185
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ly
Tokenly
Feature activation+0.011
Top resid features:
home
Token home
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
you
Token you
Feature activation+0.032
Top resid features:
have
Token have
Feature activation-0.051
Top resid features:
that
Token that
Feature activation+3.804
Top resid features:
most
Token most
Feature activation-0.030
Top resid features:
quint
Token quint
Feature activation+0.000
Top resid features:
essential
Tokenessential
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
bu
Token bu
Feature activation+0.000
Top resid features:
games
Token games
Feature activation-0.014
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
int
Token int
Feature activation+0.001
Top resid features:
ros
Tokenros
Feature activation-0.002
Top resid features:
via
Token via
Feature activation-0.108
Top resid features:
that
Token that
Feature activation+3.638
Top resid features:
trust
Token trust
Feature activation+0.016
Top resid features:
y
Tokeny
Feature activation-0.005
Top resid features:
red
Token red
Feature activation+0.071
Top resid features:
square
Token square
Feature activation+0.030
Top resid features:
freeze
Token freeze
Feature activation+0.209
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
general
Token general
Feature activation-0.000
Top resid features:
election
Token election
Feature activation-0.016
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
that
Token that
Feature activation+3.643
Top resid features:
voter
Token voter
Feature activation+0.157
Top resid features:
might
Token might
Feature activation-0.011
Top resid features:
easily
Token easily
Feature activation+0.000
Top resid features:
decide
Token decide
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
odd
Tokenodd
Feature activation+0.002
Top resid features:
led
Tokenled
Feature activation+0.001
Top resid features:
',
Token',
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.005
Top resid features:
hear
Token hear
Feature activation-0.017
Top resid features:
that
Token that
Feature activation+3.648
Top resid features:
old
Token old
Feature activation+0.037
Top resid features:
chest
Token chest
Feature activation+0.050
Top resid features:
nut
Tokennut
Feature activation+0.126
Top resid features:
of
Token of
Feature activation-0.098
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
between
Token between
Feature activation+0.022
Top resid features:
this
Token this
Feature activation+0.019
Top resid features:
record
Token record
Feature activation-0.016
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
that
Token that
Feature activation+3.632
Top resid features:
record
Token record
Feature activation+0.121
Top resid features:
you
Token you
Feature activation+0.031
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
cheon
Tokencheon
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
Keep
TokenKeep
Feature activation+0.043
Top resid features:
that
Token that
Feature activation+4.037
Top resid features:
image
Token image
Feature activation-0.076
Top resid features:
in
Token in
Feature activation-0.109
Top resid features:
mind
Token mind
Feature activation-0.133
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.005
Top resid features:
holds
Token holds
Feature activation-0.044
Top resid features:
value
Token value
Feature activation-0.028
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+3.745
Top resid features:
value
Token value
Feature activation+0.018
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
analysed
Token analysed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
But
Token But
Feature activation-0.016
Top resid features:
last
Token last
Feature activation+0.005
Top resid features:
year
Token year
Feature activation-0.071
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
that
Token that
Feature activation+3.906
Top resid features:
universe
Token universe
Feature activation-0.073
Top resid features:
impl
Token impl
Feature activation+0.000
Top resid features:
oded
Tokenoded
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
ly
Tokenly
Feature activation+0.002
Top resid features:
home
Token home
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.016
Top resid features:
have
Token have
Feature activation-0.054
Top resid features:
that
Token that
Feature activation+3.649
Top resid features:
most
Token most
Feature activation+0.008
Top resid features:
quint
Token quint
Feature activation+0.208
Top resid features:
essential
Tokenessential
Feature activation-0.135
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
bu
Token bu
Feature activation+0.000
Top resid features:
Among
Token Among
Feature activation-0.002
Top resid features:
its
Token its
Feature activation-0.005
Top resid features:
other
Token other
Feature activation-0.022
Top resid features:
accomplishments
Token accomplishments
Feature activation-0.086
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
that
Token that
Feature activation+3.788
Top resid features:
gathering
Token gathering
Feature activation+0.097
Top resid features:
of
Token of
Feature activation-0.090
Top resid features:
Catholic
Token Catholic
Feature activation+0.000
Top resid features:
bishops
Token bishops
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
It
TokenIt
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
that
Token that
Feature activation+3.358
Top resid features:
beautiful
Token beautiful
Feature activation+0.175
Top resid features:
feeling
Token feeling
Feature activation+0.120
Top resid features:
you
Token you
Feature activation-0.033
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
all
Token all
Feature activation-0.015
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
there
Token there
Feature activation-0.001
Top resid features:
's
Token's
Feature activation-0.033
Top resid features:
that
Token that
Feature activation+3.576
Top resid features:
whole
Token whole
Feature activation+0.042
Top resid features:
community
Token community
Feature activation+0.043
Top resid features:
thing
Token thing
Feature activation+0.050
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
reading
Token reading
Feature activation+0.002
Top resid features:
words
Token words
Feature activation-0.013
Top resid features:
at
Token at
Feature activation-0.010
Top resid features:
all
Token all
Feature activation+0.005
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.041
Top resid features:
that
Token that
Feature activation+3.819
Top resid features:
rare
Token rare
Feature activation+0.003
Top resid features:
f
Tokenf
Feature activation+0.005
Top resid features:
ied
Tokenied
Feature activation+0.013
Top resid features:
feeling
Token feeling
Feature activation+0.005
Top resid features:
of
Token of
Feature activation-0.149
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.02

Head 3: 0.06

Head 4: 0.03

Head 5: 0.50

Head 6: 0.04

Head 7: 0.08

Head 8: 0.02

Head 9: 0.03

Head 10: 0.01

Head 11: 0.09

Positive logits

ulum1.49

paycheck1.39

AVG1.38

isphere1.36

rious1.35

ASAP1.32

itch1.31

hetic1.30

hump1.30

ylum1.29

mosque1.26

undrum1.26

feeling1.25

milo1.23

thing1.22

acid1.22

headache1.22

ahan1.21

1.20

Gutenberg1.20

Negative logits

Rescue-1.48

ctors-1.45

NEWS-1.45

Marshal-1.44

CAST-1.38

uthor-1.30

Services-1.28

atches-1.28

BACK-1.26

osponsors-1.22

racuse-1.22

Tags-1.22

lishing-1.20

Edited-1.20

english-1.19

dule-1.18

readers-1.18

Guest-1.17

Kal-1.17

veland-1.15

INTERVAL 3.439 - 3.821
CONTAINS 0.000%

right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
voter
Token voter
Feature activation+2.602
might
Token might
Feature activation+3.821
be
Token be
Feature activation+3.389
so
Token so
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.000
Che
TokenChe
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
guy
Token guy
Feature activation+2.675
in
Token in
Feature activation+3.716
a
Token a
Feature activation+0.365
mask
Token mask
Feature activation+0.000
whose
Token whose
Feature activation+1.297
best
Token best
Feature activation+0.000
pass
Token pass
Feature activation+0.000

INTERVAL 3.057 - 3.439
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
border
Token border
Feature activation+2.106
is
Token is
Feature activation+3.086
defined
Token defined
Feature activation+0.000
by
Token by
Feature activation+0.000
three
Token three
Feature activation+0.000
natural
Token natural
Feature activation+0.000
boundaries
Token boundaries
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
that
Token that
Feature activation+0.000
beautiful
Token beautiful
Feature activation+2.068
feeling
Token feeling
Feature activation+3.015
you
Token you
Feature activation+3.173
get
Token get
Feature activation+0.000
when
Token when
Feature activation+0.010
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
big
Token big
Feature activation+2.316
,
Token,
Feature activation+1.283
wide
Token wide
Feature activation+0.000
,
Token,
Feature activation+0.124
ugly
Token ugly
Feature activation+0.612
gap
Token gap
Feature activation+3.123
between
Token between
Feature activation+2.213
downtown
Token downtown
Feature activation+0.000
and
Token and
Feature activation+0.000
River
Token River
Feature activation+0.000
Market
Token Market
Feature activation+0.000
holds
Token holds
Feature activation+0.000
value
Token value
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
value
Token value
Feature activation+3.185
can
Token can
Feature activation+2.237
be
Token be
Feature activation+2.338
analysed
Token analysed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
other
Token other
Feature activation+0.000
accomplishments
Token accomplishments
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
gathering
Token gathering
Feature activation+2.845
of
Token of
Feature activation+3.175
Catholic
Token Catholic
Feature activation+0.000
bishops
Token bishops
Feature activation+0.000
from
Token from
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.675 - 3.057
CONTAINS 0.003%

Reed
Token Reed
Feature activation+0.000
better
Token better
Feature activation+0.000
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
that
Tokenthat
Feature activation+0.006
old
Token old
Feature activation+2.685
guy
Token guy
Feature activation+2.431
who
Token who
Feature activation+2.805
got
Token got
Feature activation+0.904
sold
Token sold
Feature activation+0.000
queer
Token queer
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
vital
Token vital
Feature activation+1.794
ingredient
Token ingredient
Feature activation+2.746
in
Token in
Feature activation+0.925
the
Token the
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Cor
TokenCor
Feature activation+0.000
Potter
Token Potter
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
triumphant
Token triumphant
Feature activation+2.887
hero
Token hero
Feature activation+2.314
,
Token,
Feature activation+2.793
in
Token in
Feature activation+1.191
our
Token our
Feature activation+0.000
lives
Token lives
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
recalls
Token recalls
Feature activation+0.000
that
Token that
Feature activation+0.000
gig
Token gig
Feature activation+1.974
,
Token,
Feature activation+3.024
which
Token which
Feature activation+1.754
W
Token W
Feature activation+0.000
idespread
Tokenidespread
Feature activation+0.000
Panic
Token Panic
Feature activation+0.000
released
Token released
Feature activation+0.000
a
Token a
Feature activation+0.000
Poké
Token Poké
Feature activation+0.000
ball
Tokenball
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
ring
Token ring
Feature activation+2.834
will
Token will
Feature activation+2.240
start
Token start
Feature activation+0.575
to
Token to
Feature activation+0.000
contract
Token contract
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.293 - 2.675
CONTAINS 0.008%

man
Tokenman
Feature activation+0.000
reprodu
Token reprodu
Feature activation+0.000
ces
Tokences
Feature activation+0.000
that
Token that
Feature activation+0.000
email
Token email
Feature activation+2.346
in
Token in
Feature activation+2.566
Ang
Token Ang
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
got
Token got
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
value
Token value
Feature activation+3.185
can
Token can
Feature activation+2.237
be
Token be
Feature activation+2.338
analysed
Token analysed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
of
Token of
Feature activation+0.000
reconnect
Token reconnect
Feature activation+0.000
ing
Tokening
Feature activation+0.000
that
Token that
Feature activation+0.354
urban
Token urban
Feature activation+1.104
fabric
Token fabric
Feature activation+2.663
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Making
TokenMaking
Feature activation+0.000
the
Token the
Feature activation+0.000
America
Token America
Feature activation+0.000
forever
Token forever
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.561
amendment
Token amendment
Feature activation+2.543
--
Token --
Feature activation+1.166
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
rare
Token rare
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
racial
Token racial
Feature activation+0.306
exclus
Token exclus
Feature activation+0.771
ivity
Tokenivity
Feature activation+2.484
was
Token was
Feature activation+1.481
also
Token also
Feature activation+0.964
true
Token true
Feature activation+0.000
for
Token for
Feature activation+0.000
white
Token white
Feature activation+0.000

INTERVAL 1.910 - 2.293
CONTAINS 0.014%

obligations
Token obligations
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+1.971
day
Token day
Feature activation+0.866
tax
Token tax
Feature activation+0.505
hiatus
Token hiatus
Feature activation+2.278
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
into
Token into
Feature activation+0.000
action
Token action
Feature activation+0.000
and
Token and
Feature activation+0.000
saved
Token saved
Feature activation+0.000
that
Token that
Feature activation+0.000
child
Token child
Feature activation+2.051
's
Token's
Feature activation+2.484
life
Token life
Feature activation+1.881
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
being
Token being
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000
that
Token that
Feature activation+0.000
number
Token number
Feature activation+1.934
has
Token has
Feature activation+2.131
balloon
Token balloon
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
25
Token 25
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
Canucks
Token Canucks
Feature activation+0.000
winning
Token winning
Feature activation+0.000
that
Token that
Feature activation+0.123
division
Token division
Feature activation+2.114
,
Token,
Feature activation+1.596
but
Token but
Feature activation+0.252
he
Token he
Feature activation+0.000
sees
Token sees
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
join
Token join
Feature activation+0.000
that
Token that
Feature activation+0.000
growing
Token growing
Feature activation+0.796
list
Token list
Feature activation+1.856
of
Token of
Feature activation+2.000
London
Token London
Feature activation+0.000
Knights
Token Knights
Feature activation+0.000
alumni
Token alumni
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.528 - 1.910
CONTAINS 0.020%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Keep
TokenKeep
Feature activation+0.000
that
Token that
Feature activation+0.000
image
Token image
Feature activation+1.820
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+3.216
while
Token while
Feature activation+0.000
you
Token you
Feature activation+0.000
sav
Token sav
Feature activation+0.000
So
Token So
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
ate
Token ate
Feature activation+0.000
that
Token that
Feature activation+0.722
hot
Token hot
Feature activation+1.788
chick
Token chick
Feature activation+0.748
âĢ
TokenâĢ
Feature activation+0.421
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.021
pussy
Token pussy
Feature activation+0.007
anxiety
Token anxiety
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
lit
Token lit
Feature activation+0.096
any
Tokenany
Feature activation+1.701
of
Token of
Feature activation+1.627
other
Token other
Feature activation+0.000
disorders
Token disorders
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
slider
Token slider
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
pitch
Token pitch
Feature activation+2.087
moved
Token moved
Feature activation+1.884
back
Token back
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
plate
Token plate
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
agency
Token agency
Feature activation+0.000
and
Token and
Feature activation+0.000
gave
Token gave
Feature activation+0.000
that
Token that
Feature activation+0.000
power
Token power
Feature activation+1.740
to
Token to
Feature activation+0.469
an
Token an
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
board
Token board
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.146 - 1.528
CONTAINS 0.026%

.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
bell
Token bell
Feature activation+0.739
tower
Token tower
Feature activation+0.400
also
Token also
Feature activation+2.338
had
Token had
Feature activation+1.320
been
Token been
Feature activation+0.677
recently
Token recently
Feature activation+0.000
restored
Token restored
Feature activation+0.000
with
Token with
Feature activation+0.000
special
Token special
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
Continuing
Token Continuing
Feature activation+0.000
that
Token that
Feature activation+0.000
trend
Token trend
Feature activation+1.308
we
Token we
Feature activation+1.193
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
updated
Token updated
Feature activation+0.000
and
Token and
Feature activation+0.000
primer
Token primer
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
matte
Token matte
Feature activation+0.929
white
Token white
Feature activation+1.430
finish
Token finish
Feature activation+1.364
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
only
Token only
Feature activation+0.000
little
Token little
Feature activation+0.000
issue
Token issue
Feature activation+0.000
AM
TokenAM
Feature activation+0.000
sequence
Token sequence
Feature activation+0.000
or
Token or
Feature activation+0.000
that
Token that
Feature activation+0.000
cle
Token cle
Feature activation+0.314
avage
Tokenavage
Feature activation+1.207
occurred
Token occurred
Feature activation+0.168
as
Token as
Feature activation+0.000
expected
Token expected
Feature activation+0.000
three
Token three
Feature activation+0.000
nucle
Token nucle
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.000
started
Token started
Feature activation+0.000
that
Token that
Feature activation+0.000
band
Token band
Feature activation+0.866
,
Token,
Feature activation+1.520
but
Token but
Feature activation+0.000
prior
Token prior
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 0.764 - 1.146
CONTAINS 0.034%

.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
folly
Token folly
Feature activation+0.163
in
Token in
Feature activation+0.887
another
Token another
Feature activation+0.000
article
Token article
Feature activation+0.000
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
child
Token child
Feature activation+1.004
âĢ
TokenâĢ
Feature activation+0.712
Ļ
TokenĻ
Feature activation+0.217
s
Tokens
Feature activation+0.886
automatically
Token automatically
Feature activation+0.000
an
Token an
Feature activation+0.000
officer
Token officer
Feature activation+0.000
showed
Token showed
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
officer
Token officer
Feature activation+1.031
informed
Token informed
Feature activation+0.716
the
Token the
Feature activation+0.000
cow
Token cow
Feature activation+0.000
poke
Tokenpoke
Feature activation+0.000
that
Token that
Feature activation+0.000
nil
Token nil
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
that
Token that
Feature activation+0.000
variable
Token variable
Feature activation+1.048
nil
Token nil
Feature activation+1.006
because
Token because
Feature activation+0.256
no
Token no
Feature activation+0.000
message
Token message
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
heat
Token heat
Feature activation+0.388
,
Token,
Feature activation+0.956
but
Token but
Feature activation+0.000
James
Token James
Feature activation+0.000
had
Token had
Feature activation+0.000
played
Token played
Feature activation+0.000
33
Token 33
Feature activation+0.000

INTERVAL 0.382 - 0.764
CONTAINS 0.057%

,
Token,
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
drive
Token drive
Feature activation+0.000
that
Token that
Feature activation+0.000
energy
Token energy
Feature activation+1.512
into
Token into
Feature activation+0.717
this
Token this
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
struggling
Token struggling
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
also
Token also
Feature activation+0.087
could
Token could
Feature activation+0.190
have
Token have
Feature activation+0.451
been
Token been
Feature activation+0.495
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.296
Ļ
TokenĻ
Feature activation+0.517
s
Tokens
Feature activation+0.658
encouraging
Token encouraging
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
App
Token App
Feature activation+0.000
Store
Token Store
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
that
Token that
Feature activation+0.000
most
Token most
Feature activation+3.285
quint
Token quint
Feature activation+0.450
essential
Tokenessential
Feature activation+3.176
of
Token of
Feature activation+2.503
bu
Token bu
Feature activation+0.000
col
Tokencol
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
series
Token series
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
post
Token post
Feature activation+0.011
was
Token was
Feature activation+0.592
followed
Token followed
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
job
Token job
Feature activation+0.000
working
Token working
Feature activation+0.000

INTERVAL 0.000 - 0.382
CONTAINS 99.836%

mask
Token mask
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
;
Token;
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
use
Token use
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
C
TokenC
Feature activation+0.000
itizen
Tokenitizen
Feature activation+0.000
science
Token science
Feature activation+0.000
has
Token has
Feature activation+0.000
come
Token come
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
osexual
Tokenosexual
Feature activation+0.000
(
Token (
Feature activation+0.000
heter
Tokenheter
Feature activation+0.000
osexual
Tokenosexual
Feature activation+0.000
,
Token,
Feature activation+0.000
gay
Token gay
Feature activation+0.000
,
Token,
Feature activation+0.000
lesbian
Token lesbian
Feature activation+0.000
)
Token)
Feature activation+0.000
identities
Token identities
Feature activation+0.000
,
Token,
Feature activation+0.000
rulings
Token rulings
Feature activation+0.000
that
Token that
Feature activation+0.000
date
Token date
Feature activation+0.000
back
Token back
Feature activation+0.000
further
Token further
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
invention
Token invention
Feature activation+0.000
of
Token of
Feature activation+0.000
modern
Token modern
Feature activation+0.000
cars
Token cars
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
drunk
Token drunk
Feature activation+0.000
guy
Token guy
Feature activation+0.000
who
Token who
Feature activation+0.000
lives
Token lives
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
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 H4.5: (feature 11833)

TOP ACTIVATIONS
MAX = 4.433

If
Token If
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
one
Token one
Feature activation+0.000
acc
Token acc
Feature activation+0.912
reditation
Tokenreditation
Feature activation+4.433
,
Token,
Feature activation+2.396
it
Token it
Feature activation+0.112
's
Token's
Feature activation+0.000
lever
Token lever
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
threats
Token threats
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.106
movie
Token movie
Feature activation+1.990
theater
Token theater
Feature activation+1.818
has
Token has
Feature activation+4.271
found
Token found
Feature activation+1.410
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
The
TokenThe
Feature activation+0.000
strength
Token strength
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
United
Token United
Feature activation+1.308
Kingdom
Token Kingdom
Feature activation+4.187
comes
Token comes
Feature activation+2.501
from
Token from
Feature activation+1.505
the
Token the
Feature activation+0.000
strength
Token strength
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
TSA
Token TSA
Feature activation+1.710
inspector
Token inspector
Feature activation+4.033
began
Token began
Feature activation+3.533
pulling
Token pulling
Feature activation+0.000
on
Token on
Feature activation+0.000
rubber
Token rubber
Feature activation+0.000
gloves
Token gloves
Feature activation+0.000
felt
Token felt
Feature activation+0.000
like
Token like
Feature activation+0.000
one
Token one
Feature activation+0.000
cultural
Token cultural
Feature activation+2.192
appropriation
Token appropriation
Feature activation+2.139
too
Token too
Feature activation+3.997
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
build
Token build
Feature activation+0.000
one
Token one
Feature activation+0.000
Ang
Token Ang
Feature activation+0.000
ara
Tokenara
Feature activation+0.255
rocket
Token rocket
Feature activation+0.450
this
Token this
Feature activation+3.991
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
next
Token next
Feature activation+0.123
year
Token year
Feature activation+0.000
listening
Token listening
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
one
Token one
Feature activation+0.198
skill
Token skill
Feature activation+2.031
is
Token is
Feature activation+3.925
better
Token better
Feature activation+1.704
than
Token than
Feature activation+0.609
none
Token none
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
get
Token get
Feature activation+0.000
one
Token one
Feature activation+0.000
overdose
Token overdose
Feature activation+0.884
after
Token after
Feature activation+3.876
another
Token another
Feature activation+0.243
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
ER
Token ER
Feature activation+0.000
doors
Token doors
Feature activation+0.000
players
Token players
Feature activation+0.000
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
one
Token one
Feature activation+0.000
phone
Token phone
Feature activation+2.434
call
Token call
Feature activation+3.866
away
Token away
Feature activation+3.200
from
Token from
Feature activation+3.182
playing
Token playing
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
As
Token As
Feature activation+0.000
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
person
Token person
Feature activation+1.686
's
Token's
Feature activation+3.697
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.199
it
Token it
Feature activation+0.250
just
Token just
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
one
Token one
Feature activation+0.000
und
Token und
Feature activation+0.562
ated
Tokenated
Feature activation+1.172
quote
Token quote
Feature activation+2.122
''
Token''
Feature activation+0.279
after
Token after
Feature activation+3.548
it
Token it
Feature activation+0.000
spun
Token spun
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
from
Token from
Feature activation+0.000
be
Token be
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
floor
Token floor
Feature activation+1.790
to
Token to
Feature activation+3.543
the
Token the
Feature activation+3.241
next
Token next
Feature activation+3.058
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
especially
Token especially
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
TSA
Token TSA
Feature activation+1.710
inspector
Token inspector
Feature activation+4.033
began
Token began
Feature activation+3.533
pulling
Token pulling
Feature activation+0.000
on
Token on
Feature activation+0.000
rubber
Token rubber
Feature activation+0.000
gloves
Token gloves
Feature activation+0.000
like
Token like
Feature activation+0.000
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
stage
Token stage
Feature activation+0.991
to
Token to
Feature activation+3.517
the
Token the
Feature activation+1.903
next
Token next
Feature activation+2.724
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
some
Token some
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
anything
Token anything
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
party
Token party
Feature activation+0.505
is
Token is
Feature activation+3.503
lying
Token lying
Feature activation+0.997
about
Token about
Feature activation+0.000
false
Token false
Feature activation+0.000
accomplishments
Token accomplishments
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
logo
Token logo
Feature activation+1.849
must
Token must
Feature activation+2.841
be
Token be
Feature activation+3.471
chosen
Token chosen
Feature activation+1.092
.
Token.
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
Football
Token Football
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
the
Token the
Feature activation+0.000
sight
Token sight
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
eye
Token eye
Feature activation+0.000
following
Token following
Feature activation+3.447
a
Token a
Feature activation+0.739
teenage
Token teenage
Feature activation+0.000
rugby
Token rugby
Feature activation+0.000
accident
Token accident
Feature activation+0.000
.
Token.
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
how
Token how
Feature activation+0.000
one
Token one
Feature activation+0.000
player
Token player
Feature activation+2.545
does
Token does
Feature activation+3.425
.
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
of
Token of
Feature activation+0.000
taking
Token taking
Feature activation+0.000
things
Token things
Feature activation+0.000
one
Token one
Feature activation+0.000
step
Token step
Feature activation+1.362
at
Token at
Feature activation+3.390
time
Token time
Feature activation+0.906
-
Token -
Feature activation+0.000
first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
regime
Token regime
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
one
Token one
Feature activation+0.000
piece
Token piece
Feature activation+0.988
has
Token has
Feature activation+3.369
resur
Token resur
Feature activation+0.000
faced
Tokenfaced
Feature activation+1.243
and
Token and
Feature activation+0.000
found
Token found
Feature activation+0.120
itself
Token itself
Feature activation+0.000

Top DFA by src position
MAX = 5.087

product
Token product
Feature activation+0.026
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
If
Token If
Feature activation+0.057
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.198
Top resid features:
one
Token one
Feature activation+4.847
Top resid features:
acc
Token acc
Feature activation+0.206
Top resid features:
reditation
Tokenreditation
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
face
Token face
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
terrorist
Token terrorist
Feature activation-0.004
Top resid features:
threats
Token threats
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
one
Token one
Feature activation+4.747
Top resid features:
movie
Token movie
Feature activation+0.030
Top resid features:
theater
Token theater
Feature activation+0.410
Top resid features:
has
Token has
Feature activation+0.167
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.010
Top resid features:
"
Token "
Feature activation-0.008
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
strength
Token strength
Feature activation-0.015
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
one
Token one
Feature activation+5.087
Top resid features:
United
Token United
Feature activation+0.135
Top resid features:
Kingdom
Token Kingdom
Feature activation-0.010
Top resid features:
comes
Token comes
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
really
Token really
Feature activation-0.002
Top resid features:
bad
Token bad
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
especially
Token especially
Feature activation+0.012
Top resid features:
as
Token as
Feature activation+0.039
Top resid features:
one
Token one
Feature activation+4.639
Top resid features:
TSA
Token TSA
Feature activation+0.469
Top resid features:
inspector
Token inspector
Feature activation+0.011
Top resid features:
began
Token began
Feature activation+0.000
Top resid features:
pulling
Token pulling
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
may
Token may
Feature activation-0.008
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
felt
Token felt
Feature activation-0.019
Top resid features:
like
Token like
Feature activation+0.026
Top resid features:
one
Token one
Feature activation+4.539
Top resid features:
cultural
Token cultural
Feature activation+0.064
Top resid features:
appropriation
Token appropriation
Feature activation+0.327
Top resid features:
too
Token too
Feature activation+0.100
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.045
Top resid features:
Center
Token Center
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.078
Top resid features:
build
Token build
Feature activation-0.027
Top resid features:
one
Token one
Feature activation+4.439
Top resid features:
Ang
Token Ang
Feature activation+0.054
Top resid features:
ara
Tokenara
Feature activation+0.004
Top resid features:
rocket
Token rocket
Feature activation+0.246
Top resid features:
this
Token this
Feature activation+0.150
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
'm
Token'm
Feature activation+0.004
Top resid features:
listening
Token listening
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
But
Token But
Feature activation+0.101
Top resid features:
one
Token one
Feature activation+4.377
Top resid features:
skill
Token skill
Feature activation+0.381
Top resid features:
is
Token is
Feature activation+0.144
Top resid features:
better
Token better
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
none
Token none
Feature activation+0.000
Top resid features:
after
Token after
Feature activation-0.016
Top resid features:
day
Token day
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
we
Token we
Feature activation+0.011
Top resid features:
get
Token get
Feature activation+0.009
Top resid features:
one
Token one
Feature activation+4.321
Top resid features:
overdose
Token overdose
Feature activation+0.579
Top resid features:
after
Token after
Feature activation+0.004
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
see
Token see
Feature activation+0.012
Top resid features:
players
Token players
Feature activation-0.027
Top resid features:
who
Token who
Feature activation+0.050
Top resid features:
are
Token are
Feature activation+0.021
Top resid features:
one
Token one
Feature activation+4.682
Top resid features:
phone
Token phone
Feature activation+0.006
Top resid features:
call
Token call
Feature activation+0.070
Top resid features:
away
Token away
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
playing
Token playing
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
As
Token As
Feature activation-0.028
Top resid features:
soon
Token soon
Feature activation+0.039
Top resid features:
as
Token as
Feature activation-0.030
Top resid features:
one
Token one
Feature activation+4.655
Top resid features:
person
Token person
Feature activation-0.050
Top resid features:
's
Token's
Feature activation+0.143
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
olation
Tokenolation
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
story
Token story
Feature activation+0.021
Top resid features:
from
Token from
Feature activation+0.010
Top resid features:
one
Token one
Feature activation+3.779
Top resid features:
und
Token und
Feature activation+0.015
Top resid features:
ated
Tokenated
Feature activation+0.021
Top resid features:
quote
Token quote
Feature activation+0.091
Top resid features:
''
Token''
Feature activation+0.282
Top resid features:
after
Token after
Feature activation+0.194
Top resid features:
This
Token This
Feature activation+0.009
Top resid features:
would
Token would
Feature activation+0.021
Top resid features:
be
Token be
Feature activation+0.020
Top resid features:
repeated
Token repeated
Feature activation+0.021
Top resid features:
from
Token from
Feature activation-0.102
Top resid features:
one
Token one
Feature activation+4.480
Top resid features:
floor
Token floor
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.098
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
really
Token really
Feature activation-0.003
Top resid features:
bad
Token bad
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
especially
Token especially
Feature activation-0.012
Top resid features:
as
Token as
Feature activation+0.091
Top resid features:
one
Token one
Feature activation+3.820
Top resid features:
TSA
Token TSA
Feature activation+0.052
Top resid features:
inspector
Token inspector
Feature activation+0.548
Top resid features:
began
Token began
Feature activation+0.171
Top resid features:
pulling
Token pulling
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
support
Token support
Feature activation+0.095
Top resid features:
from
Token from
Feature activation-0.060
Top resid features:
one
Token one
Feature activation+4.380
Top resid features:
stage
Token stage
Feature activation+0.073
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
cut
Tokencut
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
anything
Token anything
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
One
Token One
Feature activation+4.345
Top resid features:
party
Token party
Feature activation+0.044
Top resid features:
is
Token is
Feature activation+0.125
Top resid features:
lying
Token lying
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
false
Token false
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
wear
Token wear
Feature activation+0.006
Top resid features:
caps
Token caps
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
one
Token one
Feature activation+4.143
Top resid features:
logo
Token logo
Feature activation+0.127
Top resid features:
must
Token must
Feature activation+0.099
Top resid features:
be
Token be
Feature activation+0.033
Top resid features:
chosen
Token chosen
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
since
Token since
Feature activation-0.003
Top resid features:
losing
Token losing
Feature activation+0.030
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
sight
Token sight
Feature activation+0.019
Top resid features:
in
Token in
Feature activation+0.036
Top resid features:
one
Token one
Feature activation+4.195
Top resid features:
eye
Token eye
Feature activation+0.084
Top resid features:
following
Token following
Feature activation+0.090
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
teenage
Token teenage
Feature activation+0.000
Top resid features:
rugby
Token rugby
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
focus
Token focus
Feature activation+0.009
Top resid features:
rather
Token rather
Feature activation+0.009
Top resid features:
than
Token than
Feature activation+0.001
Top resid features:
how
Token how
Feature activation-0.132
Top resid features:
one
Token one
Feature activation+4.360
Top resid features:
player
Token player
Feature activation+0.155
Top resid features:
does
Token does
Feature activation+0.218
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
case
Token case
Feature activation+0.023
Top resid features:
of
Token of
Feature activation+0.035
Top resid features:
taking
Token taking
Feature activation+0.094
Top resid features:
things
Token things
Feature activation-0.005
Top resid features:
one
Token one
Feature activation+4.151
Top resid features:
step
Token step
Feature activation+0.014
Top resid features:
at
Token at
Feature activation+0.104
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Nazi
Token Nazi
Feature activation+0.005
Top resid features:
regime
Token regime
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
And
Token And
Feature activation+0.028
Top resid features:
one
Token one
Feature activation+4.064
Top resid features:
piece
Token piece
Feature activation+0.165
Top resid features:
has
Token has
Feature activation+0.087
Top resid features:
resur
Token resur
Feature activation+0.000
Top resid features:
faced
Tokenfaced
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.02

Head 3: 0.09

Head 4: 0.02

Head 5: 0.48

Head 6: 0.04

Head 7: 0.09

Head 8: 0.01

Head 9: 0.04

Head 10: 0.01

Head 11: 0.10

Positive logits

apiece1.76

worth1.56

anooga1.47

opoly1.42

adish1.40

onite1.38

acre1.38

afia1.37

staffer1.37

idon1.36

Lago1.36

meas1.35

essee1.33

inkle1.33

per1.33

](1.32

rant1.32

ode1.31

parcel1.31

iversary1.30

Negative logits

stones-1.67

trenches-1.58

birds-1.52

イト-1.51

instruments-1.51

Arrows-1.49

throats-1.45

-1.40

benches-1.40

ゼウス-1.39

ships-1.38

distributions-1.38

abilities-1.38

markets-1.38

Devices-1.37

apps-1.35

asions-1.34

chambers-1.34

transformations-1.33

otions-1.32

INTERVAL 3.989 - 4.433
CONTAINS 0.001%

threats
Token threats
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.106
movie
Token movie
Feature activation+1.990
theater
Token theater
Feature activation+1.818
has
Token has
Feature activation+4.271
found
Token found
Feature activation+1.410
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
build
Token build
Feature activation+0.000
one
Token one
Feature activation+0.000
Ang
Token Ang
Feature activation+0.000
ara
Tokenara
Feature activation+0.255
rocket
Token rocket
Feature activation+0.450
this
Token this
Feature activation+3.991
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
next
Token next
Feature activation+0.123
year
Token year
Feature activation+0.000
felt
Token felt
Feature activation+0.000
like
Token like
Feature activation+0.000
one
Token one
Feature activation+0.000
cultural
Token cultural
Feature activation+2.192
appropriation
Token appropriation
Feature activation+2.139
too
Token too
Feature activation+3.997
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
If
Token If
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
one
Token one
Feature activation+0.000
acc
Token acc
Feature activation+0.912
reditation
Tokenreditation
Feature activation+4.433
,
Token,
Feature activation+2.396
it
Token it
Feature activation+0.112
's
Token's
Feature activation+0.000
lever
Token lever
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
TSA
Token TSA
Feature activation+1.710
inspector
Token inspector
Feature activation+4.033
began
Token began
Feature activation+3.533
pulling
Token pulling
Feature activation+0.000
on
Token on
Feature activation+0.000
rubber
Token rubber
Feature activation+0.000
gloves
Token gloves
Feature activation+0.000

INTERVAL 3.546 - 3.989
CONTAINS 0.001%

one
Token one
Feature activation+0.000
und
Token und
Feature activation+0.562
ated
Tokenated
Feature activation+1.172
quote
Token quote
Feature activation+2.122
''
Token''
Feature activation+0.279
after
Token after
Feature activation+3.548
it
Token it
Feature activation+0.000
spun
Token spun
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
from
Token from
Feature activation+0.000
As
Token As
Feature activation+0.000
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
person
Token person
Feature activation+1.686
's
Token's
Feature activation+3.697
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.199
it
Token it
Feature activation+0.250
just
Token just
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
players
Token players
Feature activation+0.000
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
one
Token one
Feature activation+0.000
phone
Token phone
Feature activation+2.434
call
Token call
Feature activation+3.866
away
Token away
Feature activation+3.200
from
Token from
Feature activation+3.182
playing
Token playing
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
listening
Token listening
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
one
Token one
Feature activation+0.198
skill
Token skill
Feature activation+2.031
is
Token is
Feature activation+3.925
better
Token better
Feature activation+1.704
than
Token than
Feature activation+0.609
none
Token none
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
get
Token get
Feature activation+0.000
one
Token one
Feature activation+0.000
overdose
Token overdose
Feature activation+0.884
after
Token after
Feature activation+3.876
another
Token another
Feature activation+0.243
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
ER
Token ER
Feature activation+0.000
doors
Token doors
Feature activation+0.000

INTERVAL 3.103 - 3.546
CONTAINS 0.003%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
logo
Token logo
Feature activation+1.849
must
Token must
Feature activation+2.841
be
Token be
Feature activation+3.471
chosen
Token chosen
Feature activation+1.092
.
Token.
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
Football
Token Football
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
library
Token library
Feature activation+0.000
,
Token,
Feature activation+0.000
providing
Token providing
Feature activation+0.000
one
Token one
Feature activation+0.000
function
Token function
Feature activation+1.836
per
Token per
Feature activation+3.327
HTML
Token HTML
Feature activation+0.000
5
Token5
Feature activation+0.000
element
Token element
Feature activation+0.000
,
Token,
Feature activation+0.351
as
Token as
Feature activation+0.345
-
Token-
Feature activation+0.000
leaning
Tokenleaning
Feature activation+0.982
Wall
Token Wall
Feature activation+0.112
Street
Token Street
Feature activation+0.000
lawyer
Token lawyer
Feature activation+1.737
said
Token said
Feature activation+3.289
over
Token over
Feature activation+0.000
lunch
Token lunch
Feature activation+0.000
in
Token in
Feature activation+0.000
mid
Token mid
Feature activation+0.000
town
Tokentown
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
anything
Token anything
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
party
Token party
Feature activation+0.505
is
Token is
Feature activation+3.503
lying
Token lying
Feature activation+0.997
about
Token about
Feature activation+0.000
false
Token false
Feature activation+0.000
accomplishments
Token accomplishments
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
form
Token form
Feature activation+2.442
of
Token of
Feature activation+2.602
methamphetamine
Token methamphetamine
Feature activation+0.000
use
Token use
Feature activation+0.503
amongst
Token amongst
Feature activation+3.198
users
Token users
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
crystal
Token crystal
Feature activation+0.000

INTERVAL 2.660 - 3.103
CONTAINS 0.004%

China
Token China
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
time
Token time
Feature activation+0.813
zone
Token zone
Feature activation+2.770
.
Token.
Feature activation+0.369
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
time
Token time
Feature activation+0.000
zones
Token zones
Feature activation+0.000
its
Token its
Feature activation+0.000
trunk
Token trunk
Feature activation+0.000
:
Token:
Feature activation+0.000
one
Token one
Feature activation+0.000
ring
Token ring
Feature activation+1.975
per
Token per
Feature activation+2.757
year
Token year
Feature activation+0.000
of
Token of
Feature activation+0.000
growth
Token growth
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.073
like
Token like
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
hum
Token hum
Feature activation+1.520
ong
Tokenong
Feature activation+0.000
ous
Tokenous
Feature activation+2.851
chart
Token chart
Feature activation+2.553
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
have
Token have
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
Orange
Token Orange
Feature activation+0.079
County
Token County
Feature activation+1.677
city
Token city
Feature activation+2.845
has
Token has
Feature activation+3.048
already
Token already
Feature activation+1.101
taken
Token taken
Feature activation+0.270
bold
Token bold
Feature activation+0.000
steps
Token steps
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Tokenred
Feature activation+0.000
cities
Token cities
Feature activation+0.000
,
Token,
Feature activation+0.103
one
Token one
Feature activation+0.253
man
Token man
Feature activation+1.039
has
Token has
Feature activation+2.803
emerged
Token emerged
Feature activation+2.589
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
leading
Token leading
Feature activation+0.000
skept
Token skept
Feature activation+0.000

INTERVAL 2.216 - 2.660
CONTAINS 0.007%

sex
Tokensex
Feature activation+0.000
status
Token status
Feature activation+0.000
would
Token would
Feature activation+0.000
treat
Token treat
Feature activation+0.000
one
Token one
Feature activation+0.000
group
Token group
Feature activation+2.383
of
Token of
Feature activation+1.519
people
Token people
Feature activation+0.587
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
characteristic
Token characteristic
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+0.000
becomes
Token becomes
Feature activation+2.467
clear
Token clear
Feature activation+2.402
:
Token:
Feature activation+0.000
in
Token in
Feature activation+0.000
many
Token many
Feature activation+0.000
ways
Token ways
Feature activation+0.000
,
Token,
Feature activation+0.000
point
Token point
Feature activation+0.000
to
Token to
Feature activation+0.000
increases
Token increases
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
form
Token form
Feature activation+2.442
of
Token of
Feature activation+2.602
methamphetamine
Token methamphetamine
Feature activation+0.000
use
Token use
Feature activation+0.503
amongst
Token amongst
Feature activation+3.198
users
Token users
Feature activation+0.000
an
Token an
Feature activation+0.000
application
Token application
Feature activation+0.000
from
Token from
Feature activation+0.000
using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
massive
Token massive
Feature activation+2.311
process
Token process
Feature activation+1.807
(
Token (
Feature activation+0.490
such
Tokensuch
Feature activation+1.114
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
one
Tokenone
Feature activation+0.000
team
Token team
Feature activation+1.061
,
Token,
Feature activation+2.500
one
Token one
Feature activation+0.000
heartbeat
Token heartbeat
Feature activation+1.398
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.220
âĢĶ
Token âĢĶ
Feature activation+0.402

INTERVAL 1.773 - 2.216
CONTAINS 0.010%

put
Token put
Feature activation+0.000
on
Token on
Feature activation+0.000
hold
Token hold
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.257
county
Token county
Feature activation+1.982
alone
Token alone
Feature activation+2.797
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.000
ook
Tokenook
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
threats
Token threats
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.106
movie
Token movie
Feature activation+1.990
theater
Token theater
Feature activation+1.818
has
Token has
Feature activation+4.271
found
Token found
Feature activation+1.410
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
on
Token on
Feature activation+0.000
using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
set
Token set
Feature activation+2.340
of
Token of
Feature activation+2.186
sources
Token sources
Feature activation+1.138
(
Token (
Feature activation+0.652
mostly
Tokenmostly
Feature activation+0.000
completely
Token completely
Feature activation+0.000
discredited
Token discredited
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
really
Token really
Feature activation+0.000
one
Token one
Feature activation+0.000
small
Token small
Feature activation+1.814
piece
Token piece
Feature activation+0.930
in
Token in
Feature activation+1.125
a
Token a
Feature activation+0.273
very
Token very
Feature activation+0.000
large
Token large
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
One
TokenOne
Feature activation+0.000
minute
Token minute
Feature activation+2.077
later
Token later
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.152
the
Token the
Feature activation+0.000

INTERVAL 1.330 - 1.773
CONTAINS 0.016%

of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
firearm
Token firearm
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
specification
Token specification
Feature activation+1.714
of
Token of
Feature activation+1.139
wrongful
Token wrongful
Feature activation+0.000
communication
Token communication
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
?
Token?
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.121
it
Token it
Feature activation+1.334
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
quite
Token quite
Feature activation+0.000
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+0.000
groups
Token groups
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
element
Token element
Feature activation+0.000
is
Token is
Feature activation+1.320
related
Token related
Feature activation+1.530
to
Token to
Feature activation+0.101
the
Token the
Feature activation+0.000
eastern
Token eastern
Feature activation+0.000
farmers
Token farmers
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
but
Token but
Feature activation+0.000
one
Token one
Feature activation+0.000
safe
Token safe
Feature activation+0.000
rule
Token rule
Feature activation+2.282
in
Token in
Feature activation+1.690
dealing
Token dealing
Feature activation+0.000
with
Token with
Feature activation+0.000
black
Token black
Feature activation+0.000
men
Token men
Feature activation+0.000
as
Token as
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
staff
Token staff
Feature activation+0.000
explained
Token explained
Feature activation+1.439
to
Token to
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 0.887 - 1.330
CONTAINS 0.027%

using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
massive
Token massive
Feature activation+2.311
process
Token process
Feature activation+1.807
(
Token (
Feature activation+0.490
such
Tokensuch
Feature activation+1.114
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
really
Token really
Feature activation+0.000
one
Token one
Feature activation+0.000
small
Token small
Feature activation+1.814
piece
Token piece
Feature activation+0.930
in
Token in
Feature activation+1.125
a
Token a
Feature activation+0.273
very
Token very
Feature activation+0.000
large
Token large
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
j
Token j
Feature activation+0.000
one
Token one
Feature activation+0.000
scene
Token scene
Feature activation+0.021
in
Token in
Feature activation+1.652
that
Token that
Feature activation+0.174
movie
Token movie
Feature activation+0.000
that
Token that
Feature activation+1.027
was
Token was
Feature activation+0.000
downright
Token downright
Feature activation+0.000
disturbing
Token disturbing
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
phase
Token phase
Feature activation+1.090
of
Token of
Feature activation+1.220
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
experts
Token experts
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
way
Token way
Feature activation+0.000
is
Token is
Feature activation+1.107
to
Token to
Feature activation+0.124
sort
Token sort
Feature activation+0.000
them
Token them
Feature activation+0.000
by
Token by
Feature activation+0.000
frequency
Token frequency
Feature activation+0.000

INTERVAL 0.443 - 0.887
CONTAINS 0.037%

the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
rumored
Token rumored
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
point
Token point
Feature activation+0.632
to
Token to
Feature activation+0.528
be
Token be
Feature activation+1.101
pushed
Token pushed
Feature activation+0.000
to
Token to
Feature activation+0.000
2017
Token 2017
Feature activation+0.164
appellate
Token appellate
Feature activation+0.000
court
Token court
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
run
Token run
Feature activation+0.000
g
Tokeng
Feature activation+0.540
below
Token below
Feature activation+1.444
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
one
Token one
Feature activation+0.000
hard
Token hard
Feature activation+0.000
-
Token-
Feature activation+0.000
hit
Tokenhit
Feature activation+1.120
single
Token single
Feature activation+2.279
were
Token were
Feature activation+0.860
the
Token the
Feature activation+1.346
only
Token only
Feature activation+0.000
ble
Token ble
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ishes
Tokenishes
Feature activation+0.000
vocal
Token vocal
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
way
Token way
Feature activation+1.259
or
Token or
Feature activation+0.539
another
Token another
Feature activation+0.165
since
Token since
Feature activation+0.000
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
a
Token a
Feature activation+0.026
carefully
Token carefully
Feature activation+0.000
drawn
Token drawn
Feature activation+0.000
up
Token up
Feature activation+0.000
scheme
Token scheme
Feature activation+0.006
for
Token for
Feature activation+0.692
using
Token using
Feature activation+0.000
additional
Token additional
Feature activation+0.000
donations
Token donations
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000

INTERVAL 0.000 - 0.443
CONTAINS 99.894%

and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
even
Token even
Feature activation+0.000
a
Token a
Feature activation+0.000
cr
Token cr
Feature activation+0.000
umb
Tokenumb
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
Was
TokenWas
Feature activation+0.000
his
Token his
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
Aram
Token Aram
Feature activation+0.000
is
Tokenis
Feature activation+0.000
Ay
Token Ay
Feature activation+0.000
ala
Tokenala
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
actors
Token actors
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
or
Token or
Feature activation+0.000
our
Token our
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
seem
Token seem
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
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
with
Token with
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+0.000
attacking
Token attacking
Feature activation+0.000
midfielder
Token midfielder
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
staple
Token staple
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H4.5: (feature 1139)

TOP ACTIVATIONS
MAX = 4.461

Both
Token Both
Feature activation+0.000
victims
Token victims
Feature activation+1.120
of
Token of
Feature activation+0.720
this
Token this
Feature activation+0.865
assassination
Token assassination
Feature activation+0.000
were
Token were
Feature activation+4.461
open
Token open
Feature activation+0.145
opponents
Token opponents
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
little
Token little
Feature activation+0.000
ones
Token ones
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.382
fights
Token fights
Feature activation+2.466
occurred
Token occurred
Feature activation+4.242
on
Token on
Feature activation+2.744
a
Token a
Feature activation+0.407
public
Token public
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
can
Token can
Feature activation+0.000
hear
Token hear
Feature activation+0.000
both
Token both
Feature activation+0.000
tracks
Token tracks
Feature activation+4.235
below
Token below
Feature activation+1.948
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Both
TokenBoth
Feature activation+0.185
men
Token men
Feature activation+1.666
received
Token received
Feature activation+3.822
a
Token a
Feature activation+0.736
standing
Token standing
Feature activation+0.000
o
Token o
Feature activation+0.000
vation
Tokenvation
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+2.120
those
Token those
Feature activation+1.924
cases
Token cases
Feature activation+1.615
presented
Token presented
Feature activation+3.791
factual
Token factual
Feature activation+0.000
and
Token and
Feature activation+0.000
legal
Token legal
Feature activation+0.000
problems
Token problems
Feature activation+0.000
that
Token that
Feature activation+0.000
Both
TokenBoth
Feature activation+0.211
of
Token of
Feature activation+1.497
those
Token those
Feature activation+2.350
matches
Token matches
Feature activation+1.438
technically
Token technically
Feature activation+1.302
came
Token came
Feature activation+3.751
in
Token in
Feature activation+0.984
the
Token the
Feature activation+0.177
stage
Token stage
Feature activation+0.000
directly
Token directly
Feature activation+0.000
preceding
Token preceding
Feature activation+0.000
its
Token its
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+0.428
which
Token which
Feature activation+3.718
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.144
doub
Token doub
Feature activation+0.000
so
Token so
Feature activation+0.000
sad
Token sad
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
players
Token players
Feature activation+1.613
from
Token from
Feature activation+3.714
the
Token the
Feature activation+1.647
greatest
Token greatest
Feature activation+0.000
GSL
Token GSL
Feature activation+0.000
finals
Token finals
Feature activation+0.000
ever
Token ever
Feature activation+0.000
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.000
that
Token that
Feature activation+0.000
both
Token both
Feature activation+0.000
mechanisms
Token mechanisms
Feature activation+2.570
probably
Token probably
Feature activation+3.688
played
Token played
Feature activation+2.926
a
Token a
Feature activation+0.033
role
Token role
Feature activation+0.000
,
Token,
Feature activation+0.000
helped
Token helped
Feature activation+0.000
The
Token The
Feature activation+0.000
correct
Token correct
Feature activation+0.000
answer
Token answer
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
questions
Token questions
Feature activation+3.671
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
res
Token res
Feature activation+0.000
ounding
Tokenounding
Feature activation+0.000
no
Token no
Feature activation+0.000
be
Token be
Feature activation+0.000
available
Token available
Feature activation+0.000
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
gear
Token gear
Feature activation+0.483
boxes
Tokenboxes
Feature activation+3.633
will
Token will
Feature activation+2.683
receive
Token receive
Feature activation+2.682
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Vale
Token Vale
Feature activation+0.000
same
Token same
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
both
Token both
Feature activation+1.451
appear
Token appear
Feature activation+3.067
to
Token to
Feature activation+3.614
be
Token be
Feature activation+2.788
stereo
Token stereo
Feature activation+0.000
audio
Token audio
Feature activation+0.000
mini
Token mini
Feature activation+0.000
plugs
Token plugs
Feature activation+0.000
battle
Token battle
Feature activation+0.000
happened
Token happened
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+0.287
took
Token took
Feature activation+3.519
massive
Token massive
Feature activation+0.000
losses
Token losses
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
defenders
Token defenders
Feature activation+0.000
:
Token:
Feature activation+0.000
Well
Token Well
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.175
responses
Token responses
Feature activation+3.285
bothered
Token bothered
Feature activation+3.518
me
Token me
Feature activation+0.006
somewhat
Token somewhat
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
only
Token only
Feature activation+0.000
Year
Token Year
Feature activation+0.000
Later
Token Later
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.204
specials
Token specials
Feature activation+2.478
received
Token received
Feature activation+3.491
high
Token high
Feature activation+0.000
Nielsen
Token Nielsen
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Especially
Token Especially
Feature activation+0.000
now
Token now
Feature activation+0.000
both
Token both
Feature activation+0.000
companies
Token companies
Feature activation+2.254
are
Token are
Feature activation+3.446
looking
Token looking
Feature activation+3.047
at
Token at
Feature activation+2.831
Asia
Token Asia
Feature activation+0.000
for
Token for
Feature activation+0.000
future
Token future
Feature activation+0.000
Turkish
Token Turkish
Feature activation+0.000
boat
Token boat
Feature activation+0.000
causing
Token causing
Feature activation+0.000
both
Token both
Feature activation+0.000
boats
Token boats
Feature activation+2.687
to
Token to
Feature activation+3.442
collide
Token collide
Feature activation+1.770
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
some
Token some
Feature activation+0.000
very
Token very
Feature activation+0.000
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
men
Token men
Feature activation+2.688
and
Token and
Feature activation+0.000
women
Token women
Feature activation+0.544
were
Token were
Feature activation+3.431
wounded
Token wounded
Feature activation+0.994
.
Token.
Feature activation+0.104
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
i
Tokeni
Feature activation+0.000
and
Token and
Feature activation+0.000
Str
Token Str
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
ucks
Tokenucks
Feature activation+0.000
signed
Token signed
Feature activation+3.405
letters
Token letters
Feature activation+1.775
of
Token of
Feature activation+0.000
intent
Token intent
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
chances
Token chances
Feature activation+2.509
I
Token I
Feature activation+1.176
explained
Token explained
Feature activation+0.426
would
Token would
Feature activation+3.335
have
Token have
Feature activation+2.611
taken
Token taken
Feature activation+1.659
one
Token one
Feature activation+0.000
pass
Token pass
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 5.386

and
Token and
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Russia
Token Russia
Feature activation+0.004
Top resid features:
itself
Token itself
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Both
Token Both
Feature activation+4.645
Top resid features:
victims
Token victims
Feature activation+0.246
Top resid features:
of
Token of
Feature activation+0.098
Top resid features:
this
Token this
Feature activation+0.150
Top resid features:
assassination
Token assassination
Feature activation+0.330
Top resid features:
were
Token were
Feature activation+0.040
Top resid features:
collecting
Token collecting
Feature activation+0.025
Top resid features:
their
Token their
Feature activation+0.009
Top resid features:
little
Token little
Feature activation-0.040
Top resid features:
ones
Token ones
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Both
Token Both
Feature activation+4.896
Top resid features:
fights
Token fights
Feature activation+0.325
Top resid features:
occurred
Token occurred
Feature activation+0.161
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
Bo
Token Bo
Feature activation-0.007
Top resid features:
(
Token (
Feature activation-0.020
Top resid features:
you
Tokenyou
Feature activation+0.011
Top resid features:
can
Token can
Feature activation-0.069
Top resid features:
hear
Token hear
Feature activation+0.010
Top resid features:
both
Token both
Feature activation+5.293
Top resid features:
tracks
Token tracks
Feature activation+0.066
Top resid features:
below
Token below
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
all
Token all
Feature activation-0.005
Top resid features:
humanity
Token humanity
Feature activation+0.005
Top resid features:
."
Token."
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Both
TokenBoth
Feature activation+4.746
Top resid features:
men
Token men
Feature activation-0.070
Top resid features:
received
Token received
Feature activation+0.216
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
standing
Token standing
Feature activation+0.000
Top resid features:
o
Token o
Feature activation+0.000
Top resid features:
impeachment
Token impeachment
Feature activation-0.000
Top resid features:
dossier
Token dossier
Feature activation-0.002
Top resid features:
against
Token against
Feature activation-0.003
Top resid features:
Clinton
Token Clinton
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
both
Token both
Feature activation+4.536
Top resid features:
of
Token of
Feature activation+0.074
Top resid features:
those
Token those
Feature activation+0.159
Top resid features:
cases
Token cases
Feature activation+0.343
Top resid features:
presented
Token presented
Feature activation-0.133
Top resid features:
factual
Token factual
Feature activation+0.000
Top resid features:
Peru
Token Peru
Feature activation+0.003
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
1978
Token 1978
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+0.011
Top resid features:
Both
TokenBoth
Feature activation+3.631
Top resid features:
of
Token of
Feature activation+0.147
Top resid features:
those
Token those
Feature activation+0.358
Top resid features:
matches
Token matches
Feature activation+0.226
Top resid features:
technically
Token technically
Feature activation+0.509
Top resid features:
came
Token came
Feature activation-0.012
Top resid features:
logic
Token logic
Feature activation-0.020
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
its
Token its
Feature activation+0.017
Top resid features:
decisions
Token decisions
Feature activation+0.096
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.029
Top resid features:
both
Token both
Feature activation+5.386
Top resid features:
of
Token of
Feature activation-0.610
Top resid features:
which
Token which
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
#
Token #
Feature activation+0.025
Top resid features:
6
Token6
Feature activation-0.021
Top resid features:
so
Token so
Feature activation-0.047
Top resid features:
sad
Token sad
Feature activation-0.034
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
both
Token both
Feature activation+4.828
Top resid features:
players
Token players
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+0.126
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
greatest
Token greatest
Feature activation+0.000
Top resid features:
GSL
Token GSL
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
but
Token but
Feature activation+0.021
Top resid features:
it
Token it
Feature activation+0.019
Top resid features:
seems
Token seems
Feature activation-0.002
Top resid features:
that
Token that
Feature activation-0.011
Top resid features:
both
Token both
Feature activation+4.449
Top resid features:
mechanisms
Token mechanisms
Feature activation+0.348
Top resid features:
probably
Token probably
Feature activation+0.083
Top resid features:
played
Token played
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
role
Token role
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
The
Token The
Feature activation+0.028
Top resid features:
correct
Token correct
Feature activation+0.062
Top resid features:
answer
Token answer
Feature activation-0.021
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
both
Token both
Feature activation+4.645
Top resid features:
questions
Token questions
Feature activation-0.019
Top resid features:
remains
Token remains
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
res
Token res
Feature activation+0.000
Top resid features:
ounding
Tokenounding
Feature activation+0.000
Top resid features:
)
Token)
Feature activation-0.012
Top resid features:
will
Token will
Feature activation-0.003
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
available
Token available
Feature activation+0.017
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
both
Token both
Feature activation+4.931
Top resid features:
gear
Token gear
Feature activation+0.259
Top resid features:
boxes
Tokenboxes
Feature activation-0.142
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
receive
Token receive
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
look
Token look
Feature activation-0.017
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
same
Token same
Feature activation-0.041
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
They
Token They
Feature activation+0.111
Top resid features:
both
Token both
Feature activation+4.151
Top resid features:
appear
Token appear
Feature activation+0.541
Top resid features:
to
Token to
Feature activation-0.073
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
stereo
Token stereo
Feature activation+0.000
Top resid features:
audio
Token audio
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
huge
Token huge
Feature activation-0.039
Top resid features:
battle
Token battle
Feature activation+0.008
Top resid features:
happened
Token happened
Feature activation+0.053
Top resid features:
,
Token,
Feature activation+0.251
Top resid features:
both
Token both
Feature activation+4.635
Top resid features:
sides
Token sides
Feature activation-0.258
Top resid features:
took
Token took
Feature activation+0.164
Top resid features:
massive
Token massive
Feature activation+0.000
Top resid features:
losses
Token losses
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
David
TokenDavid
Feature activation-0.011
Top resid features:
Swanson
Token Swanson
Feature activation-0.026
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
Well
Token Well
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
both
Token both
Feature activation+4.326
Top resid features:
responses
Token responses
Feature activation+0.406
Top resid features:
bothered
Token bothered
Feature activation-0.047
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
somewhat
Token somewhat
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.018
Top resid features:
One
Token One
Feature activation-0.013
Top resid features:
Year
Token Year
Feature activation-0.018
Top resid features:
Later
Token Later
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Both
Token Both
Feature activation+4.294
Top resid features:
specials
Token specials
Feature activation+0.407
Top resid features:
received
Token received
Feature activation+0.056
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
Nielsen
Token Nielsen
Feature activation+0.000
Top resid features:
ratings
Token ratings
Feature activation+0.000
Top resid features:
both
Token both
Feature activation-0.006
Top resid features:
parties
Token parties
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Especially
Token Especially
Feature activation+0.043
Top resid features:
now
Token now
Feature activation+0.099
Top resid features:
both
Token both
Feature activation+3.883
Top resid features:
companies
Token companies
Feature activation+0.389
Top resid features:
are
Token are
Feature activation+0.104
Top resid features:
looking
Token looking
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Asia
Token Asia
Feature activation+0.000
Top resid features:
towards
Token towards
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Turkish
Token Turkish
Feature activation+0.006
Top resid features:
boat
Token boat
Feature activation-0.000
Top resid features:
causing
Token causing
Feature activation+0.238
Top resid features:
both
Token both
Feature activation+4.079
Top resid features:
boats
Token boats
Feature activation+0.320
Top resid features:
to
Token to
Feature activation-0.163
Top resid features:
collide
Token collide
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
After
Token After
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.241
Top resid features:
scene
Token scene
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.053
Top resid features:
both
Token both
Feature activation+3.791
Top resid features:
men
Token men
Feature activation+0.240
Top resid features:
and
Token and
Feature activation+0.301
Top resid features:
women
Token women
Feature activation+0.009
Top resid features:
were
Token were
Feature activation+0.146
Top resid features:
wounded
Token wounded
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.253
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Both
TokenBoth
Feature activation+3.406
Top resid features:
Ald
Token Ald
Feature activation+0.138
Top resid features:
i
Tokeni
Feature activation+0.037
Top resid features:
and
Token and
Feature activation+0.607
Top resid features:
Str
Token Str
Feature activation+0.070
Top resid features:
ab
Tokenab
Feature activation-0.012
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
great
Token great
Feature activation-0.010
Top resid features:
scoring
Token scoring
Feature activation+0.001
Top resid features:
chance
Token chance
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
Both
Token Both
Feature activation+3.827
Top resid features:
chances
Token chances
Feature activation+0.011
Top resid features:
I
Token I
Feature activation+0.054
Top resid features:
explained
Token explained
Feature activation+0.468
Top resid features:
would
Token would
Feature activation+0.085
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.07

Head 2: 0.02

Head 3: 0.08

Head 4: 0.03

Head 5: 0.48

Head 6: 0.06

Head 7: 0.09

Head 8: 0.02

Head 9: 0.03

Head 10: 0.01

Head 11: 0.09

Positive logits

simultaneously1.97

respectively1.97

alike1.75

sexes1.74

halves1.68

except1.64

equally1.58

aughed1.57

edged1.55

together1.47

sides1.46

respective1.44

currencies1.39

identical1.39

concurrently1.38

administrations1.36

IED1.33

stances1.29

DEN1.28

igators1.28

Negative logits

atown-1.72

metadata-1.50

undo-1.49

affer-1.41

pta-1.40

uria-1.40

arah-1.38

edia-1.38

ctica-1.37

DragonMagazine-1.36

partial-1.35

ername-1.32

pter-1.31

estial-1.30

rol-1.30

aroo-1.30

mud-1.28

linger-1.28

isk-1.26

etter-1.26

INTERVAL 4.015 - 4.461
CONTAINS 0.000%

little
Token little
Feature activation+0.000
ones
Token ones
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.382
fights
Token fights
Feature activation+2.466
occurred
Token occurred
Feature activation+4.242
on
Token on
Feature activation+2.744
a
Token a
Feature activation+0.407
public
Token public
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
victims
Token victims
Feature activation+1.120
of
Token of
Feature activation+0.720
this
Token this
Feature activation+0.865
assassination
Token assassination
Feature activation+0.000
were
Token were
Feature activation+4.461
open
Token open
Feature activation+0.145
opponents
Token opponents
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
(
Token (
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
can
Token can
Feature activation+0.000
hear
Token hear
Feature activation+0.000
both
Token both
Feature activation+0.000
tracks
Token tracks
Feature activation+4.235
below
Token below
Feature activation+1.948
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000

INTERVAL 3.569 - 4.015
CONTAINS 0.001%

Both
TokenBoth
Feature activation+0.211
of
Token of
Feature activation+1.497
those
Token those
Feature activation+2.350
matches
Token matches
Feature activation+1.438
technically
Token technically
Feature activation+1.302
came
Token came
Feature activation+3.751
in
Token in
Feature activation+0.984
the
Token the
Feature activation+0.177
stage
Token stage
Feature activation+0.000
directly
Token directly
Feature activation+0.000
preceding
Token preceding
Feature activation+0.000
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.000
that
Token that
Feature activation+0.000
both
Token both
Feature activation+0.000
mechanisms
Token mechanisms
Feature activation+2.570
probably
Token probably
Feature activation+3.688
played
Token played
Feature activation+2.926
a
Token a
Feature activation+0.033
role
Token role
Feature activation+0.000
,
Token,
Feature activation+0.000
helped
Token helped
Feature activation+0.000
The
Token The
Feature activation+0.000
correct
Token correct
Feature activation+0.000
answer
Token answer
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
questions
Token questions
Feature activation+3.671
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
res
Token res
Feature activation+0.000
ounding
Tokenounding
Feature activation+0.000
no
Token no
Feature activation+0.000
be
Token be
Feature activation+0.000
available
Token available
Feature activation+0.000
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
gear
Token gear
Feature activation+0.483
boxes
Tokenboxes
Feature activation+3.633
will
Token will
Feature activation+2.683
receive
Token receive
Feature activation+2.682
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Vale
Token Vale
Feature activation+0.000
same
Token same
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
both
Token both
Feature activation+1.451
appear
Token appear
Feature activation+3.067
to
Token to
Feature activation+3.614
be
Token be
Feature activation+2.788
stereo
Token stereo
Feature activation+0.000
audio
Token audio
Feature activation+0.000
mini
Token mini
Feature activation+0.000
plugs
Token plugs
Feature activation+0.000

INTERVAL 3.123 - 3.569
CONTAINS 0.003%

be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
at
Token at
Feature activation+0.000
both
Token both
Feature activation+0.083
guard
Token guard
Feature activation+0.041
positions
Token positions
Feature activation+3.168
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
Miami
Token Miami
Feature activation+0.000
.
Token.
Feature activation+0.000
Especially
Token Especially
Feature activation+0.000
now
Token now
Feature activation+0.000
both
Token both
Feature activation+0.000
companies
Token companies
Feature activation+2.254
are
Token are
Feature activation+3.446
looking
Token looking
Feature activation+3.047
at
Token at
Feature activation+2.831
Asia
Token Asia
Feature activation+0.000
for
Token for
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
chances
Token chances
Feature activation+2.509
I
Token I
Feature activation+1.176
explained
Token explained
Feature activation+0.426
would
Token would
Feature activation+3.335
have
Token have
Feature activation+2.611
taken
Token taken
Feature activation+1.659
one
Token one
Feature activation+0.000
pass
Token pass
Feature activation+0.000
.
Token.
Feature activation+0.000
Tin
Token Tin
Feature activation+0.000
Star
Token Star
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
both
Tokenboth
Feature activation+0.000
of
Token of
Feature activation+1.377
which
Token which
Feature activation+3.142
starred
Token starred
Feature activation+1.632
Henry
Token Henry
Feature activation+0.000
F
Token F
Feature activation+0.000
onda
Tokenonda
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
governments
Token governments
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
political
Token political
Feature activation+0.000
persu
Token persu
Feature activation+0.000
asions
Tokenasions
Feature activation+3.272
in
Token in
Feature activation+0.733
Australia
Token Australia
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
states
Token states
Feature activation+0.000

INTERVAL 2.677 - 3.123
CONTAINS 0.005%

It
Token It
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
of
Token of
Feature activation+1.677
these
Token these
Feature activation+2.702
have
Token have
Feature activation+2.779
new
Token new
Feature activation+0.000
URLs
Token URLs
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
o
Tokeno
Feature activation+0.843
and
Token and
Feature activation+0.053
De
Token De
Feature activation+0.000
S
TokenS
Feature activation+0.000
antis
Tokenantis
Feature activation+0.354
are
Token are
Feature activation+2.682
Harvard
Token Harvard
Feature activation+0.000
Law
Token Law
Feature activation+0.000
grad
Token grad
Feature activation+0.104
s
Tokens
Feature activation+0.333
as
Token as
Feature activation+0.630
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
both
Token both
Feature activation+0.687
going
Token going
Feature activation+1.705
to
Token to
Feature activation+2.832
play
Token play
Feature activation+1.224
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
mindset
Token mindset
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
both
Token both
Feature activation+0.000
wars
Token wars
Feature activation+2.100
,
Token,
Feature activation+2.961
the
Token the
Feature activation+0.253
notion
Token notion
Feature activation+0.000
of
Token of
Feature activation+0.000
remembrance
Token remembrance
Feature activation+0.000
is
Token is
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Party
Token Party
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+1.381
whom
Token whom
Feature activation+3.066
have
Token have
Feature activation+2.501
made
Token made
Feature activation+1.030
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
ending
Token ending
Feature activation+0.000

INTERVAL 2.231 - 2.677
CONTAINS 0.006%

.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
of
Token of
Feature activation+0.865
his
Token his
Feature activation+2.297
parents
Token parents
Feature activation+1.992
were
Token were
Feature activation+2.646
immigrants
Token immigrants
Feature activation+0.177
from
Token from
Feature activation+0.037
Germany
Token Germany
Feature activation+0.000
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
both
Token both
Feature activation+0.836
men
Token men
Feature activation+1.393
have
Token have
Feature activation+3.146
made
Token made
Feature activation+2.304
vague
Token vague
Feature activation+0.000
statements
Token statements
Feature activation+0.000
concerning
Token concerning
Feature activation+0.000
their
Token their
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
of
Token of
Feature activation+0.000
police
Token police
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.160
parties
Token parties
Feature activation+0.885
agreed
Token agreed
Feature activation+2.298
to
Token to
Feature activation+0.067
end
Token end
Feature activation+0.000
the
Token the
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
.
Token.
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
(
Token (
Feature activation+0.000
both
Tokenboth
Feature activation+0.000
contracts
Token contracts
Feature activation+2.522
expire
Token expire
Feature activation+3.206
on
Token on
Feature activation+0.789
July
Token July
Feature activation+0.000
1
Token 1
Feature activation+0.000
st
Tokenst
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
political
Token political
Feature activation+1.954
parties
Token parties
Feature activation+2.305
might
Token might
Feature activation+0.728
be
Token be
Feature activation+0.242
prepared
Token prepared
Feature activation+0.000
to
Token to
Feature activation+0.000
embrace
Token embrace
Feature activation+0.000

INTERVAL 1.784 - 2.231
CONTAINS 0.008%

lot
Token lot
Feature activation+0.000
alike
Token alike
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+2.009
privately
Token privately
Feature activation+0.000
owned
Token owned
Feature activation+0.000
businesses
Token businesses
Feature activation+0.317
with
Token with
Feature activation+0.368
extremely
Token extremely
Feature activation+0.000
both
Token both
Feature activation+0.000
Montreal
Token Montreal
Feature activation+0.277
and
Token and
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.000
City
Token City
Feature activation+0.000
are
Token are
Feature activation+1.827
in
Token in
Feature activation+1.725
the
Token the
Feature activation+1.120
sights
Token sights
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Both
TokenBoth
Feature activation+0.000
Moses
Token Moses
Feature activation+0.000
and
Token and
Feature activation+0.000
Jesus
Token Jesus
Feature activation+0.000
ascend
Token ascend
Feature activation+1.961
from
Token from
Feature activation+0.400
a
Token a
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
as
Token as
Feature activation+0.000
climbing
Token climbing
Feature activation+0.000
Scand
Token Scand
Feature activation+0.000
rick
Tokenrick
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
both
Token both
Feature activation+0.000
received
Token received
Feature activation+2.009
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
suspensions
Token suspensions
Feature activation+0.000
,
Token,
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
Camb
Token Camb
Feature activation+0.000
ria
Tokenria
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+1.901
Suff
Token Suff
Feature activation+0.000
ern
Tokenern
Feature activation+0.117
,
Token,
Feature activation+0.218
Rock
Token Rock
Feature activation+0.000
land
Tokenland
Feature activation+0.000

INTERVAL 1.338 - 1.784
CONTAINS 0.010%

Super
Token Super
Feature activation+0.000
hero
Tokenhero
Feature activation+0.000
âĦ¢
TokenâĦ¢
Feature activation+0.000
both
Token both
Feature activation+0.000
fost
Token fost
Feature activation+0.000
ered
Tokenered
Feature activation+1.504
an
Token an
Feature activation+0.000
atmosphere
Token atmosphere
Feature activation+0.000
of
Token of
Feature activation+0.000
hostility
Token hostility
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
both
Token both
Feature activation+0.000
airlines
Token airlines
Feature activation+1.892
later
Token later
Feature activation+1.977
confirmed
Token confirmed
Feature activation+1.488
they
Token they
Feature activation+0.750
did
Token did
Feature activation+0.314
not
Token not
Feature activation+0.000
operate
Token operate
Feature activation+0.000
in
Token in
Feature activation+0.000
come
Token come
Feature activation+0.000
increased
Token increased
Feature activation+0.000
errors
Token errors
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
by
Token by
Feature activation+1.705
voters
Token voters
Feature activation+0.000
and
Token and
Feature activation+0.000
administrators
Token administrators
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
both
Token both
Feature activation+0.687
going
Token going
Feature activation+1.705
to
Token to
Feature activation+2.832
play
Token play
Feature activation+1.224
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+1.113
them
Token them
Feature activation+1.237
are
Token are
Feature activation+1.952
still
Token still
Feature activation+1.639
tens
Token tens
Feature activation+0.000
of
Token of
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
signatures
Token signatures
Feature activation+0.000

INTERVAL 0.892 - 1.338
CONTAINS 0.010%

and
Token and
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
cemetery
Token cemetery
Feature activation+0.000
were
Token were
Feature activation+1.094
unearthed
Token unearthed
Feature activation+0.208
during
Token during
Feature activation+0.000
construction
Token construction
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
orr
Tokenorr
Feature activation+0.000
hea
Tokenhea
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
usually
Token usually
Feature activation+0.000
are
Token are
Feature activation+1.212
fortified
Token fortified
Feature activation+0.000
with
Token with
Feature activation+0.000
another
Token another
Feature activation+0.000
antibiotic
Token antibiotic
Feature activation+0.000
.
Token.
Feature activation+0.000
disenfranch
Token disenfranch
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+0.013
,
Token,
Feature activation+0.962
that
Token that
Feature activation+0.000
at
Token at
Feature activation+0.000
any
Token any
Feature activation+0.000
time
Token time
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
Maver
Token Maver
Feature activation+0.000
ick
Tokenick
Feature activation+0.000
directors
Token directors
Feature activation+0.000
both
Token both
Feature activation+0.000
great
Token great
Feature activation+0.977
(
Token (
Feature activation+0.000
John
TokenJohn
Feature activation+0.000
Woo
Token Woo
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
with
Token with
Feature activation+1.252
and
Token and
Feature activation+0.000
without
Token without
Feature activation+0.000
a
Token a
Feature activation+0.000
7
Token 7
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.446 - 0.892
CONTAINS 0.018%

that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
either
Token either
Feature activation+0.000
outcome
Token outcome
Feature activation+0.130
would
Token would
Feature activation+0.727
be
Token be
Feature activation+0.861
fine
Token fine
Feature activation+0.203
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
one
Token one
Feature activation+0.000
S
Token S
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
streets
Token streets
Feature activation+0.000
were
Token were
Feature activation+0.000
both
Token both
Feature activation+0.291
closed
Token closed
Feature activation+0.720
as
Token as
Feature activation+0.803
authorities
Token authorities
Feature activation+0.000
investigated
Token investigated
Feature activation+0.120
the
Token the
Feature activation+0.000
crash
Token crash
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
both
Token both
Feature activation+0.000
White
Token White
Feature activation+0.492
and
Token and
Feature activation+0.000
Marriott
Token Marriott
Feature activation+0.000
explain
Token explain
Feature activation+1.686
,
Token,
Feature activation+0.716
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
environment
Token environment
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.461
production
Token production
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
incidents
Token incidents
Feature activation+1.742
,
Token,
Feature activation+1.628
âĢ
TokenâĢ
Feature activation+0.608
Ŀ
TokenĿ
Feature activation+0.455
said
Token said
Feature activation+0.000
Orleans
Token Orleans
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000

INTERVAL 0.000 - 0.446
CONTAINS 99.940%

Labor
Token Labor
Feature activation+0.000
),
Token),
Feature activation+0.000
8
Token 8
Feature activation+0.000
77
Token77
Feature activation+0.000
asylum
Token asylum
Feature activation+0.000
seekers
Token seekers
Feature activation+0.000
have
Token have
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
died
Token died
Feature activation+0.000
.
Token.
Feature activation+0.000
Of
Token Of
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
played
Token played
Feature activation+0.000
games
Token games
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
your
Token your
Feature activation+0.000
account
Token account
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
you
Token you
Feature activation+0.000
work
Token work
Feature activation+0.000
smarter
Token smarter
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
typically
Token typically
Feature activation+0.000
requests
Token requests
Feature activation+0.000
le
Tokenle
Feature activation+0.000
,
Token,
Feature activation+0.000
Clint
Token Clint
Feature activation+0.000
Dempsey
Token Dempsey
Feature activation+0.000
and
Token and
Feature activation+0.000
Jan
Token Jan
Feature activation+0.000
Vert
Token Vert
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
hen
Tokenhen
Feature activation+0.000
represent
Token represent
Feature activation+0.000
quality
Token quality
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 H4.5: (feature 13421)

TOP ACTIVATIONS
MAX = 3.772

the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+1.258
pl
Token pl
Feature activation+2.770
amas
Tokenamas
Feature activation+1.456
ach
Tokenach
Feature activation+0.000
self
Token self
Feature activation+3.772
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
ing
Tokening
Feature activation+1.160
o
Token o
Feature activation+1.251
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+2.404
path
Token path
Feature activation+3.722
.
Token.
Feature activation+0.413
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
re
Token re
Feature activation+0.000
h
Tokenh
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.787
Rocket
Token Rocket
Feature activation+1.199
Gr
Token Gr
Feature activation+0.000
unts
Tokenunts
Feature activation+3.455
on
Token on
Feature activation+2.187
every
Token every
Feature activation+0.000
corner
Token corner
Feature activation+0.000
.
Token.
Feature activation+0.043
In
Token In
Feature activation+0.000
cell
Token cell
Feature activation+0.000
towers
Token towers
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Instead
TokenInstead
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+1.258
pl
Token pl
Feature activation+2.770
amas
Tokenamas
Feature activation+1.456
ach
Tokenach
Feature activation+0.000
self
Token self
Feature activation+3.772
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
lifetime
Token lifetime
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+2.404
path
Token path
Feature activation+3.722
.
Token.
Feature activation+0.413
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
re
Token re
Feature activation+0.000
Pont
Token Pont
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.595
suspects
Token suspects
Feature activation+2.385
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
point
Token point
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.787
Rocket
Token Rocket
Feature activation+1.199
Gr
Token Gr
Feature activation+0.000
unts
Tokenunts
Feature activation+3.455
on
Token on
Feature activation+2.187
every
Token every
Feature activation+0.000
corner
Token corner
Feature activation+0.000
.
Token.
Feature activation+0.043
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
IPA
Token IPA
Feature activation+0.000
,
Token,
Feature activation+0.000
following
Token following
Feature activation+0.000
their
Token their
Feature activation+0.000
usual
Token usual
Feature activation+0.392
recipe
Token recipe
Feature activation+2.054
as
Token as
Feature activation+0.891
a
Token a
Feature activation+0.000
pale
Token pale
Feature activation+0.000
golden
Token golden
Feature activation+0.000
,
Token,
Feature activation+0.000
towers
Token towers
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
we
Token we
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
retain
Token retain
Feature activation+0.000
his
Token his
Feature activation+0.000
usual
Token usual
Feature activation+0.182
focus
Token focus
Feature activation+1.836
on
Token on
Feature activation+1.510
political
Token political
Feature activation+0.000
news
Token news
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
usual
Token usual
Feature activation+0.445
bow
Token bow
Feature activation+0.765
-
Token-
Feature activation+0.000
legged
Tokenlegged
Feature activation+1.483
g
Token g
Feature activation+0.266
ait
Tokenait
Feature activation+1.799
,
Token,
Feature activation+1.620
doing
Token doing
Feature activation+0.045
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
an
Tokenan
Feature activation+0.000
ache
Tokenache
Feature activation+0.000
that
Token that
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
the
Token the
Feature activation+0.000
obligatory
Token obligatory
Feature activation+1.785
for
Token for
Feature activation+0.618
king
Tokenking
Feature activation+0.000
to
Token to
Feature activation+1.759
achieve
Token achieve
Feature activation+0.565
the
Token the
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
the
Token the
Feature activation+0.000
obligatory
Token obligatory
Feature activation+1.785
for
Token for
Feature activation+0.618
king
Tokenking
Feature activation+0.000
to
Token to
Feature activation+1.759
achieve
Token achieve
Feature activation+0.565
the
Token the
Feature activation+0.000
look
Token look
Feature activation+1.425
of
Token of
Feature activation+0.000
bark
Token bark
Feature activation+0.000
,
Token,
Feature activation+0.000
expanding
Token expanding
Feature activation+0.000
their
Token their
Feature activation+0.000
usual
Token usual
Feature activation+0.000
set
Token set
Feature activation+0.329
of
Token of
Feature activation+1.645
projects
Token projects
Feature activation+0.891
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ambitious
Token ambitious
Feature activation+0.000
agenda
Token agenda
Feature activation+0.000
bow
Token bow
Feature activation+0.765
-
Token-
Feature activation+0.000
legged
Tokenlegged
Feature activation+1.483
g
Token g
Feature activation+0.266
ait
Tokenait
Feature activation+1.799
,
Token,
Feature activation+1.620
doing
Token doing
Feature activation+0.045
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
best
Token best
Feature activation+0.000
cry
Token cry
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
classic
Token classic
Feature activation+0.762
TV
Token TV
Feature activation+1.187
show
Token show
Feature activation+1.575
,
Token,
Feature activation+0.974
Father
Token Father
Feature activation+0.000
Kn
Token Kn
Feature activation+0.000
ows
Tokenows
Feature activation+0.000
Best
Token Best
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
led
Token led
Feature activation+0.000
but
Token but
Feature activation+0.000
retain
Token retain
Feature activation+0.000
his
Token his
Feature activation+0.000
usual
Token usual
Feature activation+0.182
focus
Token focus
Feature activation+1.836
on
Token on
Feature activation+1.510
political
Token political
Feature activation+0.000
news
Token news
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000

Top DFA by src position
MAX = 4.889

Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Instead
TokenInstead
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.128
Top resid features:
usual
Token usual
Feature activation+4.482
Top resid features:
pl
Token pl
Feature activation+0.098
Top resid features:
amas
Tokenamas
Feature activation+0.017
Top resid features:
ach
Tokenach
Feature activation+0.211
Top resid features:
self
Token self
Feature activation+0.166
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
lifetime
Token lifetime
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
I
Token I
Feature activation+0.024
Top resid features:
took
Token took
Feature activation-0.033
Top resid features:
the
Token the
Feature activation+0.117
Top resid features:
usual
Token usual
Feature activation+4.889
Top resid features:
path
Token path
Feature activation+0.130
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
re
Token re
Feature activation+0.000
Top resid features:
place
Token place
Feature activation-0.037
Top resid features:
was
Token was
Feature activation+0.027
Top resid features:
empty
Token empty
Feature activation-0.016
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
usual
Token usual
Feature activation+4.209
Top resid features:
Rocket
Token Rocket
Feature activation-0.120
Top resid features:
Gr
Token Gr
Feature activation+0.538
Top resid features:
unts
Tokenunts
Feature activation+0.055
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
cell
Token cell
Feature activation+0.014
Top resid features:
towers
Token towers
Feature activation-0.044
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
usual
Token usual
Feature activation+4.319
Top resid features:
investigative
Token investigative
Feature activation+0.175
Top resid features:
shoe
Token shoe
Feature activation+0.000
Top resid features:
leather
Token leather
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
utilizing
Token utilizing
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Instead
TokenInstead
Feature activation-0.007
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
usual
Token usual
Feature activation+3.943
Top resid features:
pl
Token pl
Feature activation+0.095
Top resid features:
amas
Tokenamas
Feature activation+0.000
Top resid features:
ach
Tokenach
Feature activation+0.000
Top resid features:
self
Token self
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
lifetime
Token lifetime
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
I
Token I
Feature activation+0.003
Top resid features:
took
Token took
Feature activation-0.086
Top resid features:
the
Token the
Feature activation+0.221
Top resid features:
usual
Token usual
Feature activation+3.508
Top resid features:
path
Token path
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
re
Token re
Feature activation+0.000
Top resid features:
Ricky
Token Ricky
Feature activation-0.050
Top resid features:
Pont
Token Pont
Feature activation+0.005
Top resid features:
ing
Tokening
Feature activation+0.012
Top resid features:
,
Token,
Feature activation-0.027
Top resid features:
the
Token the
Feature activation+0.080
Top resid features:
usual
Token usual
Feature activation+3.407
Top resid features:
suspects
Token suspects
Feature activation+0.208
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Then
Token Then
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
'd
Token'd
Feature activation+0.000
Top resid features:
place
Token place
Feature activation-0.062
Top resid features:
was
Token was
Feature activation+0.039
Top resid features:
empty
Token empty
Feature activation-0.009
Top resid features:
of
Token of
Feature activation+0.100
Top resid features:
the
Token the
Feature activation+0.139
Top resid features:
usual
Token usual
Feature activation+3.016
Top resid features:
Rocket
Token Rocket
Feature activation-0.046
Top resid features:
Gr
Token Gr
Feature activation+0.038
Top resid features:
unts
Tokenunts
Feature activation+0.147
Top resid features:
on
Token on
Feature activation+0.112
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
illo
Tokenillo
Feature activation-0.007
Top resid features:
IPA
Token IPA
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
following
Token following
Feature activation-0.027
Top resid features:
their
Token their
Feature activation+0.121
Top resid features:
usual
Token usual
Feature activation+2.932
Top resid features:
recipe
Token recipe
Feature activation+0.222
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
pale
Token pale
Feature activation+0.000
Top resid features:
golden
Token golden
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
cell
Token cell
Feature activation+0.004
Top resid features:
towers
Token towers
Feature activation-0.016
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.081
Top resid features:
usual
Token usual
Feature activation+3.387
Top resid features:
investigative
Token investigative
Feature activation-0.060
Top resid features:
shoe
Token shoe
Feature activation-0.027
Top resid features:
leather
Token leather
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
utilizing
Token utilizing
Feature activation+0.000
Top resid features:
entertainment
Token entertainment
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
but
Token but
Feature activation+0.005
Top resid features:
retain
Token retain
Feature activation-0.172
Top resid features:
his
Token his
Feature activation+0.057
Top resid features:
usual
Token usual
Feature activation+3.038
Top resid features:
focus
Token focus
Feature activation+0.136
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
political
Token political
Feature activation+0.000
Top resid features:
news
Token news
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
bound
Token bound
Feature activation+0.004
Top resid features:
ing
Tokening
Feature activation+0.003
Top resid features:
around
Token around
Feature activation+0.011
Top resid features:
with
Token with
Feature activation-0.004
Top resid features:
his
Token his
Feature activation+0.139
Top resid features:
usual
Token usual
Feature activation+2.587
Top resid features:
bow
Token bow
Feature activation+0.068
Top resid features:
-
Token-
Feature activation+0.047
Top resid features:
legged
Tokenlegged
Feature activation-0.048
Top resid features:
g
Token g
Feature activation+0.510
Top resid features:
ait
Tokenait
Feature activation-0.090
Top resid features:
an
Tokenan
Feature activation+0.027
Top resid features:
ache
Tokenache
Feature activation+0.012
Top resid features:
that
Token that
Feature activation+0.043
Top resid features:
allowed
Token allowed
Feature activation-0.102
Top resid features:
the
Token the
Feature activation+0.152
Top resid features:
obligatory
Token obligatory
Feature activation+2.826
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
king
Tokenking
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
achieve
Token achieve
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
an
Tokenan
Feature activation+0.014
Top resid features:
ache
Tokenache
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
allowed
Token allowed
Feature activation+0.132
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
obligatory
Token obligatory
Feature activation+2.438
Top resid features:
for
Token for
Feature activation+0.101
Top resid features:
king
Tokenking
Feature activation+0.306
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
achieve
Token achieve
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
Thursday
Token Thursday
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
expanding
Token expanding
Feature activation-0.264
Top resid features:
their
Token their
Feature activation-0.033
Top resid features:
usual
Token usual
Feature activation+3.320
Top resid features:
set
Token set
Feature activation-0.089
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
projects
Token projects
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
bound
Token bound
Feature activation+0.002
Top resid features:
ing
Tokening
Feature activation+0.007
Top resid features:
around
Token around
Feature activation-0.001
Top resid features:
with
Token with
Feature activation+0.018
Top resid features:
his
Token his
Feature activation+0.177
Top resid features:
usual
Token usual
Feature activation+2.493
Top resid features:
bow
Token bow
Feature activation+0.058
Top resid features:
-
Token-
Feature activation+0.071
Top resid features:
legged
Tokenlegged
Feature activation-0.056
Top resid features:
g
Token g
Feature activation+0.026
Top resid features:
ait
Tokenait
Feature activation+0.090
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
far
Token far
Feature activation-0.005
Top resid features:
cry
Token cry
Feature activation-0.049
Top resid features:
from
Token from
Feature activation-0.032
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
classic
Token classic
Feature activation+2.976
Top resid features:
TV
Token TV
Feature activation-0.067
Top resid features:
show
Token show
Feature activation+0.173
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Father
Token Father
Feature activation+0.000
Top resid features:
Kn
Token Kn
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.046
Top resid features:
cell
Token cell
Feature activation+0.007
Top resid features:
towers
Token towers
Feature activation-0.019
Top resid features:
and
Token and
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.200
Top resid features:
usual
Token usual
Feature activation+2.409
Top resid features:
investigative
Token investigative
Feature activation+0.003
Top resid features:
shoe
Token shoe
Feature activation-0.005
Top resid features:
leather
Token leather
Feature activation+0.144
Top resid features:
,
Token,
Feature activation+0.173
Top resid features:
utilizing
Token utilizing
Feature activation+0.000
Top resid features:
entertainment
Token entertainment
Feature activation-0.021
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
but
Token but
Feature activation+0.016
Top resid features:
retain
Token retain
Feature activation-0.068
Top resid features:
his
Token his
Feature activation+0.063
Top resid features:
usual
Token usual
Feature activation+2.537
Top resid features:
focus
Token focus
Feature activation+0.052
Top resid features:
on
Token on
Feature activation+0.163
Top resid features:
political
Token political
Feature activation+0.000
Top resid features:
news
Token news
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
cell
Token cell
Feature activation+0.009
Top resid features:
towers
Token towers
Feature activation-0.034
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.189
Top resid features:
usual
Token usual
Feature activation+2.840
Top resid features:
investigative
Token investigative
Feature activation-0.053
Top resid features:
shoe
Token shoe
Feature activation-0.005
Top resid features:
leather
Token leather
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
utilizing
Token utilizing
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.06

Head 2: 0.03

Head 3: 0.04

Head 4: 0.03

Head 5: 0.48

Head 6: 0.05

Head 7: 0.08

Head 8: 0.03

Head 9: 0.08

Head 10: 0.02

Head 11: 0.08

Positive logits

itiner1.44

ownt1.39

starve1.37

nose1.35

procedural1.33

blah1.30

pomp1.28

quarantine1.27

beard1.25

sleep1.25

nonsense1.25

makeup1.23

rinse1.22

shade1.21

wardrobe1.19

appearances1.19

wait1.18

dun1.18

cruise1.18

hood1.18

Negative logits

uca-1.64

idates-1.51

"]=>-1.48

ICES-1.44

��-1.43

Printed-1.42

ensibly-1.41

Continued-1.41

iffs-1.40

idas-1.40

izon-1.39

76561-1.37

inas-1.37

���-1.36

CLUD-1.34

��-1.34

icians-1.33

ively-1.31

arest-1.31

ultimate-1.31

INTERVAL 3.394 - 3.772
CONTAINS 0.000%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.787
Rocket
Token Rocket
Feature activation+1.199
Gr
Token Gr
Feature activation+0.000
unts
Tokenunts
Feature activation+3.455
on
Token on
Feature activation+2.187
every
Token every
Feature activation+0.000
corner
Token corner
Feature activation+0.000
.
Token.
Feature activation+0.043
In
Token In
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+2.404
path
Token path
Feature activation+3.722
.
Token.
Feature activation+0.413
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
re
Token re
Feature activation+0.000
h
Tokenh
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+1.258
pl
Token pl
Feature activation+2.770
amas
Tokenamas
Feature activation+1.456
ach
Tokenach
Feature activation+0.000
self
Token self
Feature activation+3.772
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
ing
Tokening
Feature activation+1.160
o
Token o
Feature activation+1.251

INTERVAL 3.017 - 3.394
CONTAINS 0.000%

cell
Token cell
Feature activation+0.000
towers
Token towers
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000

INTERVAL 2.640 - 3.017
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Instead
TokenInstead
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+1.258
pl
Token pl
Feature activation+2.770
amas
Tokenamas
Feature activation+1.456
ach
Tokenach
Feature activation+0.000
self
Token self
Feature activation+3.772
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000

INTERVAL 2.263 - 2.640
CONTAINS 0.000%

Pont
Token Pont
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.595
suspects
Token suspects
Feature activation+2.385
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
point
Token point
Feature activation+0.000
lifetime
Token lifetime
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+2.404
path
Token path
Feature activation+3.722
.
Token.
Feature activation+0.413
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
re
Token re
Feature activation+0.000

INTERVAL 1.886 - 2.263
CONTAINS 0.000%

IPA
Token IPA
Feature activation+0.000
,
Token,
Feature activation+0.000
following
Token following
Feature activation+0.000
their
Token their
Feature activation+0.000
usual
Token usual
Feature activation+0.392
recipe
Token recipe
Feature activation+2.054
as
Token as
Feature activation+0.891
a
Token a
Feature activation+0.000
pale
Token pale
Feature activation+0.000
golden
Token golden
Feature activation+0.000
,
Token,
Feature activation+0.000
towers
Token towers
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
we
Token we
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.787
Rocket
Token Rocket
Feature activation+1.199
Gr
Token Gr
Feature activation+0.000
unts
Tokenunts
Feature activation+3.455
on
Token on
Feature activation+2.187
every
Token every
Feature activation+0.000
corner
Token corner
Feature activation+0.000
.
Token.
Feature activation+0.043
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000

INTERVAL 1.509 - 1.886
CONTAINS 0.001%

the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
led
Token led
Feature activation+0.000
cry
Token cry
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
classic
Token classic
Feature activation+0.762
TV
Token TV
Feature activation+1.187
show
Token show
Feature activation+1.575
,
Token,
Feature activation+0.974
Father
Token Father
Feature activation+0.000
Kn
Token Kn
Feature activation+0.000
ows
Tokenows
Feature activation+0.000
Best
Token Best
Feature activation+0.000
,
Token,
Feature activation+0.000
expanding
Token expanding
Feature activation+0.000
their
Token their
Feature activation+0.000
usual
Token usual
Feature activation+0.000
set
Token set
Feature activation+0.329
of
Token of
Feature activation+1.645
projects
Token projects
Feature activation+0.891
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ambitious
Token ambitious
Feature activation+0.000
agenda
Token agenda
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
retain
Token retain
Feature activation+0.000
his
Token his
Feature activation+0.000
usual
Token usual
Feature activation+0.182
focus
Token focus
Feature activation+1.836
on
Token on
Feature activation+1.510
political
Token political
Feature activation+0.000
news
Token news
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
bow
Token bow
Feature activation+0.765
-
Token-
Feature activation+0.000
legged
Tokenlegged
Feature activation+1.483
g
Token g
Feature activation+0.266
ait
Tokenait
Feature activation+1.799
,
Token,
Feature activation+1.620
doing
Token doing
Feature activation+0.045
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
best
Token best
Feature activation+0.000

INTERVAL 1.131 - 1.509
CONTAINS 0.001%

Perhaps
TokenPerhaps
Feature activation+0.000
impacted
Token impacted
Feature activation+0.000
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
usual
Token usual
Feature activation+0.000
role
Token role
Feature activation+1.193
as
Token as
Feature activation+0.085
a
Token a
Feature activation+0.000
substitute
Token substitute
Feature activation+0.000
,
Token,
Feature activation+0.000
Ale
Token Ale
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.714
investigative
Token investigative
Feature activation+3.078
shoe
Token shoe
Feature activation+1.969
leather
Token leather
Feature activation+1.496
,
Token,
Feature activation+1.542
utilizing
Token utilizing
Feature activation+0.000
those
Token those
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
gu
Token gu
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
which
Token which
Feature activation+1.272
passes
Token passes
Feature activation+0.000
for
Token for
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
heals
Token heals
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
predictable
Token predictable
Feature activation+0.225
answer
Token answer
Feature activation+1.230
that
Token that
Feature activation+0.300
she
Token she
Feature activation+0.000
gave
Token gave
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
empty
Token empty
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.787
Rocket
Token Rocket
Feature activation+1.199
Gr
Token Gr
Feature activation+0.000
unts
Tokenunts
Feature activation+3.455
on
Token on
Feature activation+2.187
every
Token every
Feature activation+0.000
corner
Token corner
Feature activation+0.000

INTERVAL 0.754 - 1.131
CONTAINS 0.003%

to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
past
Token past
Feature activation+0.000
the
Token the
Feature activation+0.000
standard
Token standard
Feature activation+0.814
100
Token 100
Feature activation+1.036
point
Token point
Feature activation+0.000
cap
Token cap
Feature activation+0.648
,
Token,
Feature activation+0.601
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
,
Token,
Feature activation+0.000
following
Token following
Feature activation+0.000
their
Token their
Feature activation+0.000
usual
Token usual
Feature activation+0.392
recipe
Token recipe
Feature activation+2.054
as
Token as
Feature activation+0.891
a
Token a
Feature activation+0.000
pale
Token pale
Feature activation+0.000
golden
Token golden
Feature activation+0.000
,
Token,
Feature activation+0.000
clean
Token clean
Feature activation+0.000
distinct
Token distinct
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
typical
Token typical
Feature activation+0.412
viral
Token viral
Feature activation+0.793
videos
Token videos
Feature activation+0.757
that
Token that
Feature activation+0.530
attract
Token attract
Feature activation+0.000
views
Token views
Feature activation+0.000
through
Token through
Feature activation+0.000
shock
Token shock
Feature activation+0.000
ing
Tokening
Feature activation+0.000
around
Token around
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
usual
Token usual
Feature activation+0.445
bow
Token bow
Feature activation+0.765
-
Token-
Feature activation+0.000
legged
Tokenlegged
Feature activation+1.483
g
Token g
Feature activation+0.266
ait
Tokenait
Feature activation+1.799
,
Token,
Feature activation+1.620
music
Token music
Feature activation+0.000
far
Token far
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
traditional
Token traditional
Feature activation+0.349
holiday
Token holiday
Feature activation+1.050
season
Token season
Feature activation+0.834
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
often
Token often
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000

INTERVAL 0.377 - 0.754
CONTAINS 0.006%

will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
back
Token back
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
familiar
Token familiar
Feature activation+0.753
confines
Token confines
Feature activation+0.031
of
Token of
Feature activation+0.000
AT
Token AT
Feature activation+0.000
&
Token&
Feature activation+0.000
T
TokenT
Feature activation+0.000
different
Token different
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
classic
Token classic
Feature activation+0.540
crispy
Token crispy
Feature activation+0.147
batter
Token batter
Feature activation+0.649
infused
Token infused
Feature activation+0.207
with
Token with
Feature activation+0.000
7
Token 7
Feature activation+0.000
herbs
Token herbs
Feature activation+0.000
&
Token &
Feature activation+0.000
the
Token the
Feature activation+0.000
sector
Token sector
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
predictable
Token predictable
Feature activation+0.000
result
Token result
Feature activation+0.425
being
Token being
Feature activation+0.055
a
Token a
Feature activation+0.000
probable
Token probable
Feature activation+0.000
record
Token record
Feature activation+0.000
year
Token year
Feature activation+0.000
security
Token security
Feature activation+0.000
architecture
Token architecture
Feature activation+0.000
does
Token does
Feature activation+0.000
the
Token the
Feature activation+0.000
obvious
Token obvious
Feature activation+0.000
thing
Token thing
Feature activation+0.654
âĢĵ
Token âĢĵ
Feature activation+0.024
it
Token it
Feature activation+0.000
separates
Token separates
Feature activation+0.000
transaction
Token transaction
Feature activation+0.000
processing
Token processing
Feature activation+0.000
contrast
Token contrast
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
usual
Token usual
Feature activation+0.360
shortages
Token shortages
Feature activation+1.464
in
Token in
Feature activation+0.752
the
Token the
Feature activation+0.809
Red
Token Red
Feature activation+0.000
Army
Token Army
Feature activation+0.000
[
Token[
Feature activation+0.000
c
Tokenc
Feature activation+0.000

INTERVAL 0.000 - 0.377
CONTAINS 99.988%

raid
Tokenraid
Feature activation+0.000
in
Token in
Feature activation+0.000
Core
Token Core
Feature activation+0.000
Design
Token Design
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
1996
Token 1996
Feature activation+0.000
original
Token original
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
fight
Token fight
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
love
Token love
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
None
TokenNone
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
examples
Token examples
Feature activation+0.000
mean
Token mean
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
that
Token that
Feature activation+0.000
bombs
Token bombs
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
expect
Token expect
Feature activation+0.000
the
Token the
Feature activation+0.000
return
Token return
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fireworks
Token fireworks
Feature activation+0.000
in
Token in
Feature activation+0.000
46
Token 46
Feature activation+0.000
states
Token states
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Officials
TokenOfficials
Feature activation+0.000
at
Token at
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
ridge
Tokenridge
Feature activation+0.000
Elementary
Token Elementary
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 H4.5: (feature 14547)

TOP ACTIVATIONS
MAX = 5.299

that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neurons
Token neurons
Feature activation+1.475
are
Token are
Feature activation+5.299
active
Token active
Feature activation+1.928
during
Token during
Feature activation+0.630
two
Token two
Feature activation+0.000
events
Token events
Feature activation+0.000
,
Token,
Feature activation+0.000
expect
Token expect
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.658
period
Token period
Feature activation+4.897
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
definition
Token definition
Feature activation+0.000
is
Token is
Feature activation+0.000
open
Token open
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
article
Token article
Feature activation+2.094
last
Token last
Feature activation+4.807
year
Token year
Feature activation+0.000
,
Token,
Feature activation+1.135
written
Token written
Feature activation+0.000
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.000
samples
Token samples
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.949
anth
Token anth
Feature activation+1.811
rax
Tokenrax
Feature activation+4.616
strain
Token strain
Feature activation+3.955
were
Token were
Feature activation+1.969
shipped
Token shipped
Feature activation+0.932
by
Token by
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
earth
Token earth
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
material
Token material
Feature activation+2.040
could
Token could
Feature activation+4.500
be
Token be
Feature activation+4.431
used
Token used
Feature activation+4.004
in
Token in
Feature activation+1.940
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+0.000
sites
Token sites
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
attributes
Token attributes
Feature activation+0.355
are
Token are
Feature activation+4.498
turned
Token turned
Feature activation+1.886
against
Token against
Feature activation+1.766
the
Token the
Feature activation+0.000
ret
Token ret
Feature activation+0.000
aking
Tokenaking
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
material
Token material
Feature activation+2.040
could
Token could
Feature activation+4.500
be
Token be
Feature activation+4.431
used
Token used
Feature activation+4.004
in
Token in
Feature activation+1.940
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+0.000
p
Token p
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
anti
Token anti
Feature activation+0.141
-
Token-
Feature activation+0.759
Semitic
TokenSemitic
Feature activation+4.409
flyers
Token flyers
Feature activation+3.926
were
Token were
Feature activation+4.240
handed
Token handed
Feature activation+2.586
out
Token out
Feature activation+1.634
by
Token by
Feature activation+0.415
Apply
Token Apply
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
boolean
Token boolean
Feature activation+1.868
flag
Token flag
Feature activation+2.883
to
Token to
Feature activation+4.384
when
Token when
Feature activation+0.000
something
Token something
Feature activation+0.000
important
Token important
Feature activation+0.000
is
Token is
Feature activation+0.000
going
Token going
Feature activation+0.000
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
roles
Token roles
Feature activation+1.776
apply
Token apply
Feature activation+4.376
as
Token as
Feature activation+0.024
is
Token is
Feature activation+0.000
ordained
Token ordained
Feature activation+0.000
in
Token in
Feature activation+0.548
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Downtown
Token Downtown
Feature activation+0.000
playground
Token playground
Feature activation+4.356
s
Tokens
Feature activation+3.568
and
Token and
Feature activation+2.632
block
Token block
Feature activation+1.630
parties
Token parties
Feature activation+0.694
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
show
Token show
Feature activation+1.934
,
Token,
Feature activation+4.349
she
Token she
Feature activation+0.000
created
Token created
Feature activation+0.000
a
Token a
Feature activation+0.000
cake
Token cake
Feature activation+0.000
for
Token for
Feature activation+0.000
Researchers
Token Researchers
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neurons
Token neurons
Feature activation+1.822
are
Token are
Feature activation+4.344
active
Token active
Feature activation+0.394
during
Token during
Feature activation+0.000
both
Token both
Feature activation+0.000
events
Token events
Feature activation+0.000
,
Token,
Feature activation+0.000
same
Token same
Feature activation+0.000
"
Token "
Feature activation+0.000
dec
Tokendec
Feature activation+0.493
arbon
Tokenarbon
Feature activation+0.000
isation
Tokenisation
Feature activation+1.473
"
Token"
Feature activation+4.342
of
Token of
Feature activation+0.339
the
Token the
Feature activation+0.412
economy
Token economy
Feature activation+0.000
could
Token could
Feature activation+1.237
occur
Token occur
Feature activation+2.161
same
Token same
Feature activation+0.000
anti
Token anti
Feature activation+0.141
-
Token-
Feature activation+0.759
Semitic
TokenSemitic
Feature activation+4.409
flyers
Token flyers
Feature activation+3.926
were
Token were
Feature activation+4.240
handed
Token handed
Feature activation+2.586
out
Token out
Feature activation+1.634
by
Token by
Feature activation+0.415
Students
Token Students
Feature activation+0.000
for
Token for
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.897
could
Token could
Feature activation+3.459
be
Token be
Feature activation+3.875
done
Token done
Feature activation+4.099
in
Token in
Feature activation+2.454
the
Token the
Feature activation+0.144
former
Token former
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.000
general
Token general
Feature activation+2.085
lack
Token lack
Feature activation+4.039
of
Token of
Feature activation+2.692
good
Token good
Feature activation+0.000
humor
Token humor
Feature activation+0.702
by
Token by
Feature activation+2.399
most
Token most
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
retail
Token retail
Feature activation+0.000
event
Token event
Feature activation+4.009
with
Token with
Feature activation+2.142
Republican
Token Republican
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.000
policy
Token policy
Feature activation+0.434
applied
Token applied
Feature activation+4.008
to
Token to
Feature activation+3.383
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.000
with
Token with
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
material
Token material
Feature activation+2.040
could
Token could
Feature activation+4.500
be
Token be
Feature activation+4.431
used
Token used
Feature activation+4.004
in
Token in
Feature activation+1.940
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+0.000
p
Token p
Feature activation+0.000
ips
Tokenips
Feature activation+0.000

Top DFA by src position
MAX = 5.706

ists
Tokenists
Feature activation+0.022
Top resid features:
believe
Token believe
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.025
Top resid features:
if
Token if
Feature activation+0.186
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
same
Token same
Feature activation+5.706
Top resid features:
neurons
Token neurons
Feature activation+0.455
Top resid features:
are
Token are
Feature activation-0.098
Top resid features:
active
Token active
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.050
Top resid features:
normally
Token normally
Feature activation+0.093
Top resid features:
expect
Token expect
Feature activation+0.044
Top resid features:
over
Token over
Feature activation-0.020
Top resid features:
the
Token the
Feature activation+0.067
Top resid features:
same
Token same
Feature activation+5.307
Top resid features:
time
Token time
Feature activation+0.218
Top resid features:
period
Token period
Feature activation+0.154
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
definition
Token definition
Feature activation+0.000
Top resid features:
harder
Token harder
Feature activation-0.007
Top resid features:
crackdown
Token crackdown
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
From
Token From
Feature activation+0.146
Top resid features:
the
Token the
Feature activation+0.073
Top resid features:
same
Token same
Feature activation+5.501
Top resid features:
article
Token article
Feature activation+0.185
Top resid features:
last
Token last
Feature activation+0.085
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
written
Token written
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
samples
Token samples
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.106
Top resid features:
same
Token same
Feature activation+5.184
Top resid features:
anth
Token anth
Feature activation+0.209
Top resid features:
rax
Tokenrax
Feature activation+0.056
Top resid features:
strain
Token strain
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
shipped
Token shipped
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.057
Top resid features:
on
Token on
Feature activation+0.037
Top resid features:
earth
Token earth
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
same
Token same
Feature activation+5.528
Top resid features:
material
Token material
Feature activation+0.290
Top resid features:
could
Token could
Feature activation-0.210
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
sites
Token sites
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.060
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
same
Token same
Feature activation+5.244
Top resid features:
attributes
Token attributes
Feature activation+0.373
Top resid features:
are
Token are
Feature activation-0.017
Top resid features:
turned
Token turned
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.041
Top resid features:
on
Token on
Feature activation+0.021
Top resid features:
earth
Token earth
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
same
Token same
Feature activation+5.496
Top resid features:
material
Token material
Feature activation+0.242
Top resid features:
could
Token could
Feature activation-0.078
Top resid features:
be
Token be
Feature activation-0.077
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
flyers
Token flyers
Feature activation+0.031
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
If
Token If
Feature activation+0.062
Top resid features:
the
Token the
Feature activation+0.101
Top resid features:
same
Token same
Feature activation+4.658
Top resid features:
anti
Token anti
Feature activation+0.217
Top resid features:
-
Token-
Feature activation+0.634
Top resid features:
Semitic
TokenSemitic
Feature activation-0.169
Top resid features:
flyers
Token flyers
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
simple
Token simple
Feature activation-0.003
Top resid features:
fix
Token fix
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
Apply
Token Apply
Feature activation-0.090
Top resid features:
the
Token the
Feature activation+0.197
Top resid features:
same
Token same
Feature activation+5.082
Top resid features:
boolean
Token boolean
Feature activation+0.130
Top resid features:
flag
Token flag
Feature activation+0.270
Top resid features:
to
Token to
Feature activation-0.084
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.032
Top resid features:
In
Token In
Feature activation+0.047
Top resid features:
society
Token society
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
same
Token same
Feature activation+5.599
Top resid features:
roles
Token roles
Feature activation+0.005
Top resid features:
apply
Token apply
Feature activation-0.062
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
ordained
Token ordained
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.027
Top resid features:
met
Token met
Feature activation-0.055
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
visiting
Token visiting
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.117
Top resid features:
same
Token same
Feature activation+4.885
Top resid features:
Downtown
Token Downtown
Feature activation+0.499
Top resid features:
playground
Token playground
Feature activation-0.115
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
block
Token block
Feature activation+0.000
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:
In
TokenIn
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
same
Token same
Feature activation+4.771
Top resid features:
show
Token show
Feature activation+0.682
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
created
Token created
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
game
Token game
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Researchers
Token Researchers
Feature activation+0.028
Top resid features:
think
Token think
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
same
Token same
Feature activation+4.800
Top resid features:
neurons
Token neurons
Feature activation+0.484
Top resid features:
are
Token are
Feature activation+0.100
Top resid features:
active
Token active
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
previous
Token previous
Feature activation-0.024
Top resid features:
research
Token research
Feature activation+0.008
Top resid features:
had
Token had
Feature activation-0.007
Top resid features:
shown
Token shown
Feature activation-0.052
Top resid features:
the
Token the
Feature activation+0.112
Top resid features:
same
Token same
Feature activation+5.082
Top resid features:
"
Token "
Feature activation+0.124
Top resid features:
dec
Tokendec
Feature activation+0.054
Top resid features:
arbon
Tokenarbon
Feature activation+0.006
Top resid features:
isation
Tokenisation
Feature activation+0.001
Top resid features:
"
Token"
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
flyers
Token flyers
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
If
Token If
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.067
Top resid features:
same
Token same
Feature activation+4.700
Top resid features:
anti
Token anti
Feature activation+0.110
Top resid features:
-
Token-
Feature activation+0.043
Top resid features:
Semitic
TokenSemitic
Feature activation+0.046
Top resid features:
flyers
Token flyers
Feature activation+0.329
Top resid features:
were
Token were
Feature activation-0.020
Top resid features:
checked
Token checked
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
Flask
Token Flask
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
The
Token The
Feature activation+0.064
Top resid features:
same
Token same
Feature activation+5.302
Top resid features:
thing
Token thing
Feature activation+0.098
Top resid features:
could
Token could
Feature activation+0.042
Top resid features:
be
Token be
Feature activation-0.214
Top resid features:
done
Token done
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
The
TokenThe
Feature activation+0.059
Top resid features:
same
Token same
Feature activation+4.814
Top resid features:
general
Token general
Feature activation+0.285
Top resid features:
lack
Token lack
Feature activation-0.075
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
humor
Token humor
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
At
TokenAt
Feature activation+0.126
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
same
Token same
Feature activation+4.503
Top resid features:
retail
Token retail
Feature activation+0.512
Top resid features:
event
Token event
Feature activation-0.121
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
all
Token all
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
The
TokenThe
Feature activation+0.037
Top resid features:
same
Token same
Feature activation+4.738
Top resid features:
policy
Token policy
Feature activation+0.633
Top resid features:
applied
Token applied
Feature activation-0.118
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.039
Top resid features:
on
Token on
Feature activation+0.026
Top resid features:
earth
Token earth
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
same
Token same
Feature activation+5.125
Top resid features:
material
Token material
Feature activation+0.300
Top resid features:
could
Token could
Feature activation+0.050
Top resid features:
be
Token be
Feature activation-0.121
Top resid features:
used
Token used
Feature activation-0.236
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.08

Head 2: 0.02

Head 3: 0.06

Head 4: 0.02

Head 5: 0.47

Head 6: 0.05

Head 7: 0.09

Head 8: 0.01

Head 9: 0.05

Head 10: 0.01

Head 11: 0.09

Positive logits

exact1.39

same1.38

nes1.36

pomp1.26

roman1.24

twice1.19

arching1.19

Cooke1.18

same1.16

inelli1.12

Async1.09

redes1.09

Acc1.08

INESS1.08

PSU1.07

than1.07

ini1.06

TB1.06

kefeller1.05

ulative1.05

Negative logits

Newsletter-1.72

SPONSORED-1.58

unin-1.56

pes-1.54

casts-1.38

mber-1.35

sugg-1.34

ILE-1.31

ggles-1.26

ZE-1.25

helicop-1.24

contrace-1.24

Msg-1.23

Ging-1.23

imes-1.22

wings-1.21

largeDownload-1.21

pta-1.20

ggle-1.19

pod-1.19

INTERVAL 4.769 - 5.299
CONTAINS 0.000%

expect
Token expect
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.658
period
Token period
Feature activation+4.897
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
definition
Token definition
Feature activation+0.000
is
Token is
Feature activation+0.000
open
Token open
Feature activation+0.000
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neurons
Token neurons
Feature activation+1.475
are
Token are
Feature activation+5.299
active
Token active
Feature activation+1.928
during
Token during
Feature activation+0.630
two
Token two
Feature activation+0.000
events
Token events
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
article
Token article
Feature activation+2.094
last
Token last
Feature activation+4.807
year
Token year
Feature activation+0.000
,
Token,
Feature activation+1.135
written
Token written
Feature activation+0.000
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.000

INTERVAL 4.239 - 4.769
CONTAINS 0.001%

samples
Token samples
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.949
anth
Token anth
Feature activation+1.811
rax
Tokenrax
Feature activation+4.616
strain
Token strain
Feature activation+3.955
were
Token were
Feature activation+1.969
shipped
Token shipped
Feature activation+0.932
by
Token by
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
roles
Token roles
Feature activation+1.776
apply
Token apply
Feature activation+4.376
as
Token as
Feature activation+0.024
is
Token is
Feature activation+0.000
ordained
Token ordained
Feature activation+0.000
in
Token in
Feature activation+0.548
the
Token the
Feature activation+0.000
sites
Token sites
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
attributes
Token attributes
Feature activation+0.355
are
Token are
Feature activation+4.498
turned
Token turned
Feature activation+1.886
against
Token against
Feature activation+1.766
the
Token the
Feature activation+0.000
ret
Token ret
Feature activation+0.000
aking
Tokenaking
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
anti
Token anti
Feature activation+0.141
-
Token-
Feature activation+0.759
Semitic
TokenSemitic
Feature activation+4.409
flyers
Token flyers
Feature activation+3.926
were
Token were
Feature activation+4.240
handed
Token handed
Feature activation+2.586
out
Token out
Feature activation+1.634
by
Token by
Feature activation+0.415
same
Token same
Feature activation+0.000
"
Token "
Feature activation+0.000
dec
Tokendec
Feature activation+0.493
arbon
Tokenarbon
Feature activation+0.000
isation
Tokenisation
Feature activation+1.473
"
Token"
Feature activation+4.342
of
Token of
Feature activation+0.339
the
Token the
Feature activation+0.412
economy
Token economy
Feature activation+0.000
could
Token could
Feature activation+1.237
occur
Token occur
Feature activation+2.161

INTERVAL 3.709 - 4.239
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.000
general
Token general
Feature activation+2.085
lack
Token lack
Feature activation+4.039
of
Token of
Feature activation+2.692
good
Token good
Feature activation+0.000
humor
Token humor
Feature activation+0.702
by
Token by
Feature activation+2.399
most
Token most
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
same
Token same
Feature activation+0.000
policy
Token policy
Feature activation+0.434
applied
Token applied
Feature activation+4.008
to
Token to
Feature activation+3.383
a
Token a
Feature activation+0.000
family
Token family
Feature activation+0.000
with
Token with
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
anti
Token anti
Feature activation+0.141
-
Token-
Feature activation+0.759
Semitic
TokenSemitic
Feature activation+4.409
flyers
Token flyers
Feature activation+3.926
were
Token were
Feature activation+4.240
handed
Token handed
Feature activation+2.586
out
Token out
Feature activation+1.634
by
Token by
Feature activation+0.415
Students
Token Students
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.949
anth
Token anth
Feature activation+1.811
rax
Tokenrax
Feature activation+4.616
strain
Token strain
Feature activation+3.955
were
Token were
Feature activation+1.969
shipped
Token shipped
Feature activation+0.932
by
Token by
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
ins
Tokenins
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.897
could
Token could
Feature activation+3.459
be
Token be
Feature activation+3.875
done
Token done
Feature activation+4.099
in
Token in
Feature activation+2.454
the
Token the
Feature activation+0.144
former
Token former
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 3.179 - 3.709
CONTAINS 0.002%

naturally
Token naturally
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
is
Token is
Feature activation+0.949
true
Token true
Feature activation+3.218
of
Token of
Feature activation+0.000
making
Token making
Feature activation+0.000
games
Token games
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
examines
Token examines
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
issue
Token issue
Feature activation+0.202
in
Token in
Feature activation+3.309
a
Token a
Feature activation+0.138
less
Token less
Feature activation+0.000
tongue
Token tongue
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
"
Token "
Feature activation+0.000
cl
Tokencl
Feature activation+0.302
ay
Tokenay
Feature activation+0.000
"
Token"
Feature activation+3.291
as
Token as
Feature activation+1.551
our
Token our
Feature activation+0.000
own
Token own
Feature activation+0.000
planet
Token planet
Feature activation+0.000
.
Token.
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
amount
Token amount
Feature activation+1.487
of
Token of
Feature activation+3.115
time
Token time
Feature activation+3.665
(
Token (
Feature activation+1.035
both
Tokenboth
Feature activation+0.000
contracts
Token contracts
Feature activation+0.000
expire
Token expire
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
trend
Token trend
Feature activation+1.108
is
Token is
Feature activation+3.612
noticeable
Token noticeable
Feature activation+2.328
in
Token in
Feature activation+0.934
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.649 - 3.179
CONTAINS 0.004%

ology
Tokenology
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
group
Token group
Feature activation+0.698
of
Token of
Feature activation+3.082
researchers
Token researchers
Feature activation+1.895
shows
Token shows
Feature activation+2.169
that
Token that
Feature activation+0.000
gluten
Token gluten
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
multi
Token multi
Feature activation+0.000
-
Token-
Feature activation+0.000
chip
Tokenchip
Feature activation+0.185
module
Token module
Feature activation+2.790
package
Token package
Feature activation+2.869
.
Token.
Feature activation+0.359
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
to
Token to
Feature activation+0.000
experience
Token experience
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
in
Token in
Feature activation+3.080
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
comfort
Token comfort
Feature activation+0.000
as
Token as
Feature activation+0.000
space
Token space
Feature activation+0.000
fielding
Token fielding
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
weapons
Token weapons
Feature activation+0.817
and
Token and
Feature activation+2.371
tactics
Token tactics
Feature activation+2.998
.
Token.
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
agents
Token agents
Feature activation+0.000
and
Token and
Feature activation+0.000
Air
Token Air
Feature activation+0.000
entitled
Token entitled
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
number
Token number
Feature activation+0.365
of
Token of
Feature activation+2.862
electoral
Token electoral
Feature activation+0.000
votes
Token votes
Feature activation+1.047
regardless
Token regardless
Feature activation+0.095
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000

INTERVAL 2.120 - 2.649
CONTAINS 0.006%

all
Token all
Feature activation+0.000
attend
Token attend
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
exclusive
Token exclusive
Feature activation+0.000
schools
Token schools
Feature activation+2.190
?
Token?
Feature activation+0.000
Or
Token Or
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
Ox
Token Ox
Feature activation+0.000
Donovan
Token Donovan
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.158
thing
Token thing
Feature activation+1.490
last
Token last
Feature activation+2.220
year
Token year
Feature activation+0.000
about
Token about
Feature activation+1.198
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.000
that
Token that
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
significant
Token significant
Feature activation+1.728
uptick
Token uptick
Feature activation+3.175
in
Token in
Feature activation+2.424
positive
Token positive
Feature activation+0.000
behaviour
Token behaviour
Feature activation+0.000
and
Token and
Feature activation+0.000
dramatically
Token dramatically
Feature activation+0.000
reduced
Token reduced
Feature activation+0.354
six
Token six
Feature activation+0.000
fold
Tokenfold
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
period
Token period
Feature activation+2.495
to
Token to
Feature activation+0.233
over
Token over
Feature activation+0.000
300
Token 300
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
fielding
Token fielding
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
weapons
Token weapons
Feature activation+0.817
and
Token and
Feature activation+2.371
tactics
Token tactics
Feature activation+2.998
.
Token.
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
agents
Token agents
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.590 - 2.120
CONTAINS 0.010%

are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
category
Token category
Feature activation+1.636
as
Token as
Feature activation+0.220
blacks
Token blacks
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
researching
Token researching
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
topics
Token topics
Feature activation+2.046
as
Token as
Feature activation+1.633
you
Token you
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
.
Token.
Feature activation+0.000
position
Token position
Feature activation+0.000
with
Token with
Feature activation+2.618
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
player
Token player
Feature activation+0.798
to
Token to
Feature activation+1.688
move
Token move
Feature activation+1.186
as
Token as
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
created
Token created
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.082
reasons
Token reasons
Feature activation+1.671
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Then
TokenThen
Feature activation+0.000
"#
Token "#
Feature activation+0.000
(
Token(
Feature activation+0.000
I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
this
Token this
Feature activation+0.000
same
Token same
Feature activation+0.000
question
Token question
Feature activation+1.817
)
Token)
Feature activation+0.478
Sam
Token Sam
Feature activation+0.000
M
Token M
Feature activation+0.000
D
Token D
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000

INTERVAL 1.060 - 1.590
CONTAINS 0.012%

a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
hole
Token hole
Feature activation+1.498
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Wood
TokenWood
Feature activation+0.000
s
Tokens
Feature activation+0.000
Brisbane
Token Brisbane
Feature activation+0.000
suffering
Token suffering
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
problem
Token problem
Feature activation+0.089
of
Token of
Feature activation+1.069
poor
Token poor
Feature activation+0.000
disposal
Token disposal
Feature activation+0.000
that
Token that
Feature activation+0.000
haunted
Token haunted
Feature activation+0.068
the
Token the
Feature activation+0.000
15
Token15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
weapon
Token weapon
Feature activation+1.182
used
Token used
Feature activation+1.516
by
Token by
Feature activation+0.666
Adam
Token Adam
Feature activation+0.000
Lan
Token Lan
Feature activation+0.000
za
Tokenza
Feature activation+0.000
to
Token to
Feature activation+0.000
takes
Token takes
Feature activation+0.000
this
Token this
Feature activation+0.000
same
Token same
Feature activation+0.000
sandbox
Token sandbox
Feature activation+1.336
ed
Tokened
Feature activation+2.030
approach
Token approach
Feature activation+1.375
to
Token to
Feature activation+1.710
running
Token running
Feature activation+0.000
HTML
Token HTML
Feature activation+0.000
5
Token5
Feature activation+0.000
apps
Token apps
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
shares
Token shares
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
name
Token name
Feature activation+1.062
,
Token,
Feature activation+0.736
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
liberation
Token liberation
Feature activation+0.000
war
Token war
Feature activation+0.000

INTERVAL 0.530 - 1.060
CONTAINS 0.017%

the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
neurons
Token neurons
Feature activation+1.475
are
Token are
Feature activation+5.299
active
Token active
Feature activation+1.928
during
Token during
Feature activation+0.630
two
Token two
Feature activation+0.000
events
Token events
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
memory
Token memory
Feature activation+0.000
normally
Token normally
Feature activation+0.000
expect
Token expect
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.658
period
Token period
Feature activation+4.897
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
definition
Token definition
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
analysis
Token analysis
Feature activation+1.554
that
Token that
Feature activation+0.567
applies
Token applies
Feature activation+0.856
to
Token to
Feature activation+0.000
Yates
Token Yates
Feature activation+0.000
now
Token now
Feature activation+0.000
applies
Token applies
Feature activation+0.169
advance
Token advance
Feature activation+0.000
(
Token (
Feature activation+0.000
using
Tokenusing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
maths
Token maths
Feature activation+0.921
as
Token as
Feature activation+0.486
before
Token before
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
gives
Token gives
Feature activation+0.000
showing
Token showing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
severely
Token severely
Feature activation+0.000
damaged
Token damaged
Feature activation+0.824
building
Token building
Feature activation+0.738
,
Token,
Feature activation+1.879
and
Token and
Feature activation+0.283
large
Token large
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.530
CONTAINS 99.947%

trade
Token trade
Feature activation+0.000
-
Token-
Feature activation+0.000
offs
Tokenoffs
Feature activation+0.000
were
Token were
Feature activation+0.000
tough
Token tough
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
choices
Token choices
Feature activation+0.000
were
Token were
Feature activation+0.000
complex
Token complex
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Tokenin
Feature activation+0.000
Cor
Token Cor
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
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
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
around
Token around
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
older
Token older
Feature activation+0.000
than
Token than
Feature activation+0.000
shirt
Tokenshirt
Feature activation+0.000
alt
Token alt
Feature activation+0.000
-
Token-
Feature activation+0.000
right
Tokenright
Feature activation+0.000
en
Token en
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
cers
Tokencers
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
month
Token month
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
package
Token package
Feature activation+0.000
fell
Token fell
Feature activation+0.000
apart
Token apart
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 H4.5: (feature 6239)

TOP ACTIVATIONS
MAX = 5.301

government
Token government
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+2.100
family
Token family
Feature activation+5.301
,
Token,
Feature activation+4.364
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
mind
Token mind
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.653
American
Token American
Feature activation+5.216
,
Token,
Feature activation+4.073
there
Token there
Feature activation+1.093
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.402
internet
Token internet
Feature activation+3.636
user
Token user
Feature activation+5.011
to
Token to
Feature activation+3.565
watch
Token watch
Feature activation+1.786
ABC
Token ABC
Feature activation+0.026
programs
Token programs
Feature activation+0.000
like
Token like
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+1.310
American
Token American
Feature activation+4.913
wanted
Token wanted
Feature activation+2.857
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Law
Token Law
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
consumer
Token consumer
Feature activation+4.357
is
Token is
Feature activation+4.534
more
Token more
Feature activation+0.000
swayed
Token swayed
Feature activation+0.000
by
Token by
Feature activation+0.000
brand
Token brand
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.195
lion
Token lion
Feature activation+4.293
or
Token or
Feature activation+1.432
tiger
Token tiger
Feature activation+4.183
has
Token has
Feature activation+4.473
18
Token 18
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
times
Token times
Feature activation+0.000
less
Token less
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+2.100
family
Token family
Feature activation+5.301
,
Token,
Feature activation+4.364
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
consumer
Token consumer
Feature activation+4.357
is
Token is
Feature activation+4.534
more
Token more
Feature activation+0.000
swayed
Token swayed
Feature activation+0.000
by
Token by
Feature activation+0.000
brand
Token brand
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.195
lion
Token lion
Feature activation+4.293
or
Token or
Feature activation+1.432
tiger
Token tiger
Feature activation+4.183
has
Token has
Feature activation+4.473
18
Token 18
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.195
lion
Token lion
Feature activation+4.293
or
Token or
Feature activation+1.432
tiger
Token tiger
Feature activation+4.183
has
Token has
Feature activation+4.473
18
Token 18
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
times
Token times
Feature activation+0.000
PA
TokenPA
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
NFL
Token NFL
Feature activation+3.381
player
Token player
Feature activation+4.176
salary
Token salary
Feature activation+0.992
exploded
Token exploded
Feature activation+0.757
from
Token from
Feature activation+0.000
$
Token $
Feature activation+0.000
27
Token27
Feature activation+0.000
%
Token%
Feature activation+0.000
better
Token better
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.087
hitter
Token hitter
Feature activation+4.175
;
Token;
Feature activation+0.751
he
Token he
Feature activation+0.000
walks
Token walks
Feature activation+0.000
,
Token,
Feature activation+0.000
hits
Token hits
Feature activation+0.000
mind
Token mind
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.653
American
Token American
Feature activation+5.216
,
Token,
Feature activation+4.073
there
Token there
Feature activation+1.093
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
he
Token he
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+1.749
web
Token web
Feature activation+2.976
developer
Token developer
Feature activation+3.915
,
Token,
Feature activation+2.523
the
Token the
Feature activation+0.035
argument
Token argument
Feature activation+0.000
goes
Token goes
Feature activation+0.000
.
Token.
Feature activation+0.000
than
Token than
Feature activation+0.000
an
Token an
Feature activation+0.000
average
Token average
Feature activation+0.052
Indian
Token Indian
Feature activation+3.137
broadband
Token broadband
Feature activation+1.427
user
Token user
Feature activation+3.811
,
Token,
Feature activation+2.149
making
Token making
Feature activation+0.000
J
Token J
Feature activation+0.000
io
Tokenio
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
home
Token home
Feature activation+3.776
in
Token in
Feature activation+2.623
the
Token the
Feature activation+1.178
borough
Token borough
Feature activation+0.618
at
Token at
Feature activation+0.000
£
Token £
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
amount
Token amount
Feature activation+0.000
spent
Token spent
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
average
Token average
Feature activation+3.702
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.263
Game
TokenGame
Feature activation+2.513
of
Token of
Feature activation+0.000
Thrones
Token Thrones
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
New
Token New
Feature activation+1.958
ham
Tokenham
Feature activation+0.571
home
Token home
Feature activation+3.648
cost
Token cost
Feature activation+0.448
£
Token £
Feature activation+0.000
53
Token53
Feature activation+0.000
,
Token,
Feature activation+0.000
5
Token5
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.649
January
Token January
Feature activation+1.562
low
Token low
Feature activation+3.641
is
Token is
Feature activation+0.720
only
Token only
Feature activation+0.000
7
Token 7
Feature activation+0.000
degrees
Token degrees
Feature activation+0.000
above
Token above
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
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.402
internet
Token internet
Feature activation+3.636
user
Token user
Feature activation+5.011
to
Token to
Feature activation+3.565
watch
Token watch
Feature activation+1.786
ABC
Token ABC
Feature activation+0.026
programs
Token programs
Feature activation+0.000

Top DFA by src position
MAX = 6.255

where
Token where
Feature activation-0.013
Top resid features:
government
Token government
Feature activation-0.041
Top resid features:
can
Token can
Feature activation+0.005
Top resid features:
help
Token help
Feature activation-0.032
Top resid features:
the
Token the
Feature activation+0.180
Top resid features:
average
Token average
Feature activation+6.255
Top resid features:
family
Token family
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
In
TokenIn
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
mind
Token mind
Feature activation+0.038
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.167
Top resid features:
average
Token average
Feature activation+5.946
Top resid features:
American
Token American
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.064
Top resid features:
more
Token more
Feature activation+0.011
Top resid features:
likely
Token likely
Feature activation+0.039
Top resid features:
than
Token than
Feature activation+0.140
Top resid features:
the
Token the
Feature activation+0.162
Top resid features:
average
Token average
Feature activation+5.558
Top resid features:
internet
Token internet
Feature activation+0.233
Top resid features:
user
Token user
Feature activation-0.053
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
watch
Token watch
Feature activation+0.000
Top resid features:
ABC
Token ABC
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
do
Token do
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.022
Top resid features:
what
Token what
Feature activation-0.128
Top resid features:
the
Token the
Feature activation+0.128
Top resid features:
average
Token average
Feature activation+5.997
Top resid features:
American
Token American
Feature activation+0.032
Top resid features:
wanted
Token wanted
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
Steven
Token Steven
Feature activation+0.000
Top resid features:
found
Token found
Feature activation-0.054
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
Instead
Token Instead
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
average
Token average
Feature activation+5.008
Top resid features:
consumer
Token consumer
Feature activation+0.487
Top resid features:
is
Token is
Feature activation+0.015
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
swayed
Token swayed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
issue
Token issue
Feature activation-0.015
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
space
Token space
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
average
Token average
Feature activation+5.054
Top resid features:
lion
Token lion
Feature activation+0.200
Top resid features:
or
Token or
Feature activation+0.222
Top resid features:
tiger
Token tiger
Feature activation+0.085
Top resid features:
has
Token has
Feature activation-0.093
Top resid features:
18
Token 18
Feature activation+0.000
Top resid features:
where
Token where
Feature activation-0.011
Top resid features:
government
Token government
Feature activation-0.042
Top resid features:
can
Token can
Feature activation-0.030
Top resid features:
help
Token help
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.139
Top resid features:
average
Token average
Feature activation+5.138
Top resid features:
family
Token family
Feature activation+0.336
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
found
Token found
Feature activation-0.028
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Instead
Token Instead
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.069
Top resid features:
average
Token average
Feature activation+5.159
Top resid features:
consumer
Token consumer
Feature activation+0.083
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
swayed
Token swayed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
issue
Token issue
Feature activation-0.017
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
space
Token space
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
average
Token average
Feature activation+5.049
Top resid features:
lion
Token lion
Feature activation+0.066
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
tiger
Token tiger
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
18
Token 18
Feature activation+0.000
Top resid features:
issue
Token issue
Feature activation-0.012
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
space
Token space
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
average
Token average
Feature activation+4.932
Top resid features:
lion
Token lion
Feature activation+0.172
Top resid features:
or
Token or
Feature activation+0.151
Top resid features:
tiger
Token tiger
Feature activation-0.049
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
18
Token 18
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
NFL
Token NFL
Feature activation-0.014
Top resid features:
PA
TokenPA
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
average
Token average
Feature activation+5.017
Top resid features:
NFL
Token NFL
Feature activation+0.109
Top resid features:
player
Token player
Feature activation-0.053
Top resid features:
salary
Token salary
Feature activation+0.000
Top resid features:
exploded
Token exploded
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
50
Token 50
Feature activation+0.018
Top resid features:
%
Token%
Feature activation+0.013
Top resid features:
better
Token better
Feature activation-0.018
Top resid features:
than
Token than
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
average
Token average
Feature activation+4.854
Top resid features:
hitter
Token hitter
Feature activation+0.096
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
walks
Token walks
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
In
TokenIn
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
mind
Token mind
Feature activation-0.008
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
average
Token average
Feature activation+4.467
Top resid features:
American
Token American
Feature activation+0.660
Top resid features:
,
Token,
Feature activation-0.091
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.010
Top resid features:
too
Token too
Feature activation+0.047
Top resid features:
tricky
Token tricky
Feature activation-0.032
Top resid features:
for
Token for
Feature activation-0.048
Top resid features:
the
Token the
Feature activation+0.139
Top resid features:
average
Token average
Feature activation+4.632
Top resid features:
web
Token web
Feature activation+0.300
Top resid features:
developer
Token developer
Feature activation-0.196
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
argument
Token argument
Feature activation+0.000
Top resid features:
times
Token times
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+0.017
Top resid features:
data
Token data
Feature activation+0.021
Top resid features:
than
Token than
Feature activation+0.256
Top resid features:
an
Token an
Feature activation+0.078
Top resid features:
average
Token average
Feature activation+4.390
Top resid features:
Indian
Token Indian
Feature activation+0.143
Top resid features:
broadband
Token broadband
Feature activation+0.044
Top resid features:
user
Token user
Feature activation-0.075
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
puts
Token puts
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
cost
Token cost
Feature activation-0.039
Top resid features:
of
Token of
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
average
Token average
Feature activation+4.711
Top resid features:
home
Token home
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
borough
Token borough
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
ous
Tokenous
Feature activation-0.002
Top resid features:
amount
Token amount
Feature activation+0.040
Top resid features:
spent
Token spent
Feature activation-0.017
Top resid features:
on
Token on
Feature activation+0.096
Top resid features:
your
Token your
Feature activation+0.106
Top resid features:
average
Token average
Feature activation+4.354
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Game
TokenGame
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Thrones
Token Thrones
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
records
Token records
Feature activation-0.029
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
average
Token average
Feature activation+4.601
Top resid features:
New
Token New
Feature activation+0.024
Top resid features:
ham
Tokenham
Feature activation-0.041
Top resid features:
home
Token home
Feature activation-0.051
Top resid features:
cost
Token cost
Feature activation+0.000
Top resid features:
£
Token £
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
Maine
Token Maine
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
where
Token where
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
average
Token average
Feature activation+4.263
Top resid features:
January
Token January
Feature activation+0.133
Top resid features:
low
Token low
Feature activation+0.121
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.033
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
likely
Token likely
Feature activation+0.028
Top resid features:
than
Token than
Feature activation+0.077
Top resid features:
the
Token the
Feature activation+0.166
Top resid features:
average
Token average
Feature activation+4.305
Top resid features:
internet
Token internet
Feature activation+0.037
Top resid features:
user
Token user
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
watch
Token watch
Feature activation+0.000
Top resid features:
ABC
Token ABC
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.06

Head 2: 0.03

Head 3: 0.07

Head 4: 0.03

Head 5: 0.47

Head 6: 0.05

Head 7: 0.09

Head 8: 0.02

Head 9: 0.04

Head 10: 0.02

Head 11: 0.10

Positive logits

hero1.50

detail1.44

Yorker1.44

GY1.37

iculty1.32

artist1.32

ilet1.31

*****1.29

ryce1.29

hole1.28

rpm1.27

ateur1.25

jury1.24

Dealer1.24

abuser1.21

asher1.21

Jew1.21

opot1.20

cler1.20

ebted1.19

Negative logits

disbanded-1.61

favourites-1.45

portals-1.36

Okawaru-1.35

acquisitions-1.35

favorites-1.34

exited-1.34

realms-1.31

fronts-1.30

UNESCO-1.27

acio-1.26

spiked-1.26

forth-1.25

iments-1.25

withdrew-1.25

simultane-1.23

merged-1.22

Sharing-1.21

prizes-1.21

avenues-1.20

INTERVAL 4.771 - 5.301
CONTAINS 0.000%

do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+1.310
American
Token American
Feature activation+4.913
wanted
Token wanted
Feature activation+2.857
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Law
Token Law
Feature activation+0.000
the
Token the
Feature activation+0.000
mind
Token mind
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.653
American
Token American
Feature activation+5.216
,
Token,
Feature activation+4.073
there
Token there
Feature activation+1.093
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
government
Token government
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+2.100
family
Token family
Feature activation+5.301
,
Token,
Feature activation+4.364
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.402
internet
Token internet
Feature activation+3.636
user
Token user
Feature activation+5.011
to
Token to
Feature activation+3.565
watch
Token watch
Feature activation+1.786
ABC
Token ABC
Feature activation+0.026
programs
Token programs
Feature activation+0.000
like
Token like
Feature activation+0.000

INTERVAL 4.241 - 4.771
CONTAINS 0.001%

of
Token of
Feature activation+0.000
space
Token space
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.195
lion
Token lion
Feature activation+4.293
or
Token or
Feature activation+1.432
tiger
Token tiger
Feature activation+4.183
has
Token has
Feature activation+4.473
18
Token 18
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.195
lion
Token lion
Feature activation+4.293
or
Token or
Feature activation+1.432
tiger
Token tiger
Feature activation+4.183
has
Token has
Feature activation+4.473
18
Token 18
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
times
Token times
Feature activation+0.000
less
Token less
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
consumer
Token consumer
Feature activation+4.357
is
Token is
Feature activation+4.534
more
Token more
Feature activation+0.000
swayed
Token swayed
Feature activation+0.000
by
Token by
Feature activation+0.000
brand
Token brand
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
consumer
Token consumer
Feature activation+4.357
is
Token is
Feature activation+4.534
more
Token more
Feature activation+0.000
swayed
Token swayed
Feature activation+0.000
by
Token by
Feature activation+0.000
brand
Token brand
Feature activation+0.000
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+2.100
family
Token family
Feature activation+5.301
,
Token,
Feature activation+4.364
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 3.711 - 4.241
CONTAINS 0.001%

PA
TokenPA
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
NFL
Token NFL
Feature activation+3.381
player
Token player
Feature activation+4.176
salary
Token salary
Feature activation+0.992
exploded
Token exploded
Feature activation+0.757
from
Token from
Feature activation+0.000
$
Token $
Feature activation+0.000
27
Token27
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+1.749
web
Token web
Feature activation+2.976
developer
Token developer
Feature activation+3.915
,
Token,
Feature activation+2.523
the
Token the
Feature activation+0.035
argument
Token argument
Feature activation+0.000
goes
Token goes
Feature activation+0.000
.
Token.
Feature activation+0.000
%
Token%
Feature activation+0.000
better
Token better
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.087
hitter
Token hitter
Feature activation+4.175
;
Token;
Feature activation+0.751
he
Token he
Feature activation+0.000
walks
Token walks
Feature activation+0.000
,
Token,
Feature activation+0.000
hits
Token hits
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.195
lion
Token lion
Feature activation+4.293
or
Token or
Feature activation+1.432
tiger
Token tiger
Feature activation+4.183
has
Token has
Feature activation+4.473
18
Token 18
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
times
Token times
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
home
Token home
Feature activation+3.776
in
Token in
Feature activation+2.623
the
Token the
Feature activation+1.178
borough
Token borough
Feature activation+0.618
at
Token at
Feature activation+0.000
£
Token £
Feature activation+0.000

INTERVAL 3.180 - 3.711
CONTAINS 0.001%

San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
average
Token average
Feature activation+0.000
one
Token one
Feature activation+3.388
-
Token-
Feature activation+0.288
bedroom
Tokenbedroom
Feature activation+1.317
apartment
Token apartment
Feature activation+2.629
rents
Token rents
Feature activation+0.165
for
Token for
Feature activation+0.000
.
Token.
Feature activation+0.000
Com
TokenCom
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
national
Token national
Feature activation+3.530
salary
Token salary
Feature activation+1.176
,
Token,
Feature activation+1.320
with
Token with
Feature activation+0.148
bonuses
Token bonuses
Feature activation+0.000
,
Token,
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
PA
TokenPA
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
NFL
Token NFL
Feature activation+3.381
player
Token player
Feature activation+4.176
salary
Token salary
Feature activation+0.992
exploded
Token exploded
Feature activation+0.757
from
Token from
Feature activation+0.000
$
Token $
Feature activation+0.000
iana
Tokeniana
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
embarrass
Token embarrass
Feature activation+0.000
your
Token your
Feature activation+0.000
average
Token average
Feature activation+3.501
salad
Token salad
Feature activation+3.441
-
Token-
Feature activation+1.151
bar
Tokenbar
Feature activation+1.984
fare
Token fare
Feature activation+3.290
.
Token.
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
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.402
internet
Token internet
Feature activation+3.636
user
Token user
Feature activation+5.011
to
Token to
Feature activation+3.565
watch
Token watch
Feature activation+1.786
ABC
Token ABC
Feature activation+0.026
programs
Token programs
Feature activation+0.000

INTERVAL 2.650 - 3.180
CONTAINS 0.001%

for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
I
Token I
Feature activation+0.000
MAX
TokenMAX
Feature activation+0.000
theater
Token theater
Feature activation+0.000
is
Token is
Feature activation+2.694
$
Token $
Feature activation+0.000
4000
Token4000
Feature activation+0.000
-$
Token-$
Feature activation+0.000
5000
Token5000
Feature activation+0.000
per
Token per
Feature activation+0.000
better
Token better
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.245
first
Token first
Feature activation+2.122
baseman
Token baseman
Feature activation+3.111
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Considering
TokenConsidering
Feature activation+0.000
context
Token context
Feature activation+0.000
more
Token more
Feature activation+0.000
data
Token data
Feature activation+0.000
than
Token than
Feature activation+0.000
an
Token an
Feature activation+0.000
average
Token average
Feature activation+0.052
Indian
Token Indian
Feature activation+3.137
broadband
Token broadband
Feature activation+1.427
user
Token user
Feature activation+3.811
,
Token,
Feature activation+2.149
making
Token making
Feature activation+0.000
J
Token J
Feature activation+0.000
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+1.310
American
Token American
Feature activation+4.913
wanted
Token wanted
Feature activation+2.857
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Law
Token Law
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.000
as
Token as
Feature activation+0.000
average
Token average
Feature activation+0.000
end
Token end
Feature activation+0.132
users
Token users
Feature activation+1.543
are
Token are
Feature activation+2.688
concerned
Token concerned
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
difference
Token difference
Feature activation+0.000
between
Token between
Feature activation+0.000

INTERVAL 2.120 - 2.650
CONTAINS 0.002%

cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
home
Token home
Feature activation+3.776
in
Token in
Feature activation+2.623
the
Token the
Feature activation+1.178
borough
Token borough
Feature activation+0.618
at
Token at
Feature activation+0.000
£
Token £
Feature activation+0.000
371
Token371
Feature activation+0.000
moment
Token moment
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
index
Token index
Feature activation+2.517
looks
Token looks
Feature activation+2.271
like
Token like
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
much
Token much
Feature activation+0.000
a
Token a
Feature activation+0.000
statistical
Token statistical
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
average
Token average
Feature activation+3.702
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.263
Game
TokenGame
Feature activation+2.513
of
Token of
Feature activation+0.000
Thrones
Token Thrones
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
episode
Token episode
Feature activation+2.353
Game
TokenGame
Feature activation+2.513
of
Token of
Feature activation+0.000
Thrones
Token Thrones
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
episode
Token episode
Feature activation+2.353
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
Big
Token Big
Feature activation+1.495
Law
Token Law
Feature activation+0.295
Partner
Token Partner
Feature activation+2.574
in
Token in
Feature activation+2.555
the
Token the
Feature activation+0.832
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
makes
Token makes
Feature activation+0.193
$
Token $
Feature activation+0.000

INTERVAL 1.590 - 2.120
CONTAINS 0.002%

beef
Token beef
Feature activation+0.000
while
Token while
Feature activation+0.000
an
Token an
Feature activation+0.000
average
Token average
Feature activation+0.000
Japanese
Token Japanese
Feature activation+1.688
ate
Token ate
Feature activation+1.669
14
Token 14
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
kg
Token kg
Feature activation+0.000
of
Token of
Feature activation+0.000
embarrass
Token embarrass
Feature activation+0.000
your
Token your
Feature activation+0.000
average
Token average
Feature activation+3.501
salad
Token salad
Feature activation+3.441
-
Token-
Feature activation+1.151
bar
Tokenbar
Feature activation+1.984
fare
Token fare
Feature activation+3.290
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
blog
Token blog
Feature activation+0.000
month
Token month
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
median
Token median
Feature activation+0.211
home
Token home
Feature activation+3.301
price
Token price
Feature activation+1.779
is
Token is
Feature activation+2.566
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
collection
Token collection
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
average
Token average
Feature activation+0.428
eBay
Token eBay
Feature activation+1.653
prices
Token prices
Feature activation+0.566
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
reason
Token reason
Feature activation+0.000
I
Token I
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.402
internet
Token internet
Feature activation+3.636
user
Token user
Feature activation+5.011
to
Token to
Feature activation+3.565
watch
Token watch
Feature activation+1.786
ABC
Token ABC
Feature activation+0.026
programs
Token programs
Feature activation+0.000
like
Token like
Feature activation+0.000
"
Token "
Feature activation+0.000
Jimmy
TokenJimmy
Feature activation+0.000

INTERVAL 1.060 - 1.590
CONTAINS 0.002%

deserving
Token deserving
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
of
Token of
Feature activation+0.000
average
Token average
Feature activation+0.000
Americans
Token Americans
Feature activation+2.459
and
Token and
Feature activation+1.383
African
Token African
Feature activation+0.586
Americans
Token Americans
Feature activation+0.250
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
would
Token would
Feature activation+0.000
embarrass
Token embarrass
Feature activation+0.000
your
Token your
Feature activation+0.000
average
Token average
Feature activation+3.501
salad
Token salad
Feature activation+3.441
-
Token-
Feature activation+1.151
bar
Tokenbar
Feature activation+1.984
fare
Token fare
Feature activation+3.290
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
median
Token median
Feature activation+0.000
estimate
Token estimate
Feature activation+1.361
from
Token from
Feature activation+0.413
Fed
Token Fed
Feature activation+0.000
officials
Token officials
Feature activation+0.000
was
Token was
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
ceiling
Token ceiling
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
average
Token average
Feature activation+0.000
approval
Token approval
Feature activation+1.114
rating
Token rating
Feature activation+0.442
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
three
Token three
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Techn
TokenTechn
Feature activation+0.000
ically
Tokenically
Feature activation+0.000
median
Token median
Feature activation+0.000
household
Token household
Feature activation+1.264
income
Token income
Feature activation+0.040
declined
Token declined
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 0.530 - 1.060
CONTAINS 0.004%

approval
Token approval
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
average
Token average
Feature activation+0.000
approval
Token approval
Feature activation+0.722
rating
Token rating
Feature activation+0.136
was
Token was
Feature activation+0.000
down
Token down
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
average
Token average
Feature activation+0.000
,
Token,
Feature activation+1.046
these
Token these
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.000
NFL
Token NFL
Feature activation+3.381
player
Token player
Feature activation+4.176
salary
Token salary
Feature activation+0.992
exploded
Token exploded
Feature activation+0.757
from
Token from
Feature activation+0.000
$
Token $
Feature activation+0.000
27
Token27
Feature activation+0.000
,
Token,
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
average
Token average
Feature activation+0.000
Americans
Token Americans
Feature activation+0.632
aren
Token aren
Feature activation+0.995
't
Token't
Feature activation+0.117
getting
Token getting
Feature activation+0.000
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
deserve
Token deserve
Feature activation+0.000
scouts
Token scouts
Feature activation+0.000
were
Token were
Feature activation+0.000
concerned
Token concerned
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
average
Token average
Feature activation+0.617
physical
Token physical
Feature activation+1.499
tools
Token tools
Feature activation+1.100
(
Token (
Feature activation+0.860
he
Tokenhe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.000 - 0.530
CONTAINS 99.987%

embedded
Token embedded
Feature activation+0.000
onto
Token onto
Feature activation+0.000
the
Token the
Feature activation+0.000
watch
Token watch
Feature activation+0.000
face
Token face
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Gear
Token Gear
Feature activation+0.000
Fit
Token Fit
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Global
Token Global
Feature activation+0.000
Marketing
Token Marketing
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
connected
Token connected
Feature activation+0.000
products
Token products
Feature activation+0.000
division
Token division
Feature activation+0.000
and
Token and
Feature activation+0.000
headed
Token headed
Feature activation+0.000
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
for
Token for
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
-
Token-
Feature activation+0.000
16
Token16
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
in
Token in
Feature activation+0.000
March
Token March
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
determined
Token determined
Feature activation+0.000
what
Token what
Feature activation+0.000
happened
Token happened
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
dead
Token dead
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
N
TokenN
Feature activation+0.000
ga
Tokenga
Feature activation+0.000
io
Tokenio
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
is
Token is
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 H4.5: (feature 23576)

TOP ACTIVATIONS
MAX = 5.167

become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.000
intimidated
Token intimidated
Feature activation+2.188
and
Token and
Feature activation+4.372
traumat
Token traumat
Feature activation+2.976
ized
Tokenized
Feature activation+5.167
from
Token from
Feature activation+2.006
the
Token the
Feature activation+0.216
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+0.000
may
Token may
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
lethal
Token lethal
Feature activation+1.855
and
Token and
Feature activation+4.779
dramatic
Token dramatic
Feature activation+3.003
,
Token,
Feature activation+3.809
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
costs
Token costs
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.000
on
Token on
Feature activation+0.045
erous
Tokenerous
Feature activation+4.560
that
Token that
Feature activation+0.670
the
Token the
Feature activation+0.000
Affordable
Token Affordable
Feature activation+0.000
Care
Token Care
Feature activation+0.000
Act
Token Act
Feature activation+0.000
was
Token was
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+0.886
ur
Tokenur
Feature activation+0.000
ously
Tokenously
Feature activation+4.451
,
Token,
Feature activation+3.327
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
so
Token so
Feature activation+0.000
focused
Token focused
Feature activation+2.810
on
Token on
Feature activation+4.443
the
Token the
Feature activation+2.401
extraction
Token extraction
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
if
Token if
Feature activation+0.000
women
Token women
Feature activation+0.000
become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.000
intimidated
Token intimidated
Feature activation+2.188
and
Token and
Feature activation+4.372
traumat
Token traumat
Feature activation+2.976
ized
Tokenized
Feature activation+5.167
from
Token from
Feature activation+2.006
the
Token the
Feature activation+0.216
experiences
Token experiences
Feature activation+0.000
Mormons
Token Mormons
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.000
caught
Token caught
Feature activation+2.466
up
Token up
Feature activation+3.041
in
Token in
Feature activation+4.315
their
Token their
Feature activation+0.162
doctr
Token doctr
Feature activation+0.000
inal
Tokeninal
Feature activation+0.000
imper
Token imper
Feature activation+0.000
atives
Tokenatives
Feature activation+0.000
ats
Tokenats
Feature activation+0.000
by
Tokenby
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
mysterious
Token mysterious
Feature activation+1.948
,
Token,
Feature activation+4.156
in
Token in
Feature activation+2.887
fact
Token fact
Feature activation+1.388
,
Token,
Feature activation+3.025
that
Token that
Feature activation+2.072
even
Token even
Feature activation+0.000
a
Tokena
Feature activation+0.000
vow
Token vow
Feature activation+0.000
so
Token so
Feature activation+0.000
sw
Token sw
Feature activation+0.000
agger
Tokenagger
Feature activation+3.542
ing
Tokening
Feature activation+4.137
that
Token that
Feature activation+0.107
it
Token it
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
com
Token com
Feature activation+0.000
ical
Tokenical
Feature activation+0.371
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
so
Token so
Feature activation+0.000
smart
Token smart
Feature activation+1.827
,
Token,
Feature activation+4.062
âĢ
TokenâĢ
Feature activation+0.116
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
another
Token another
Feature activation+0.000
.
Token.
Feature activation+0.000
chest
Token chest
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
t
Token t
Feature activation+1.256
aut
Tokenaut
Feature activation+0.608
and
Token and
Feature activation+3.996
burning
Token burning
Feature activation+1.834
hot
Token hot
Feature activation+0.723
it
Token it
Feature activation+0.158
felt
Token felt
Feature activation+0.000
like
Token like
Feature activation+0.000
brazen
Token brazen
Feature activation+0.000
and
Token and
Feature activation+3.340
so
Token so
Feature activation+0.086
un
Token un
Feature activation+0.812
mind
Tokenmind
Feature activation+1.627
ful
Tokenful
Feature activation+3.963
of
Token of
Feature activation+1.270
the
Token the
Feature activation+0.542
constitutional
Token constitutional
Feature activation+0.000
provisions
Token provisions
Feature activation+0.000
as
Token as
Feature activation+0.000
ensuing
Token ensuing
Feature activation+0.000
system
Token system
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
confusing
Token confusing
Feature activation+2.305
,
Token,
Feature activation+3.924
the
Token the
Feature activation+0.833
paperwork
Token paperwork
Feature activation+0.000
so
Token so
Feature activation+0.000
ardu
Token ardu
Feature activation+0.962
ous
Tokenous
Feature activation+3.559
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
surprised
Token surprised
Feature activation+2.455
,
Token,
Feature activation+1.900
and
Token and
Feature activation+3.874
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
we
Token we
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
a
Token a
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
me
Token me
Feature activation+0.000
so
Token so
Feature activation+0.000
sed
Token sed
Feature activation+0.000
ated
Tokenated
Feature activation+3.859
,
Token,
Feature activation+2.973
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
step
Token step
Feature activation+0.000
was
Token was
Feature activation+0.000
The
TokenThe
Feature activation+0.000
technology
Token technology
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
simple
Token simple
Feature activation+2.412
,
Token,
Feature activation+3.855
it
Token it
Feature activation+0.204
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
moving
Token moving
Feature activation+0.000
parts
Token parts
Feature activation+0.000
on
Tokenon
Feature activation+0.000
particle
Token particle
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
dangerous
Token dangerous
Feature activation+1.352
,
Token,
Feature activation+3.810
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
itself
Token itself
Feature activation+0.000
is
Token is
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
lethal
Token lethal
Feature activation+1.855
and
Token and
Feature activation+4.779
dramatic
Token dramatic
Feature activation+3.003
,
Token,
Feature activation+3.809
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
because
Token because
Feature activation+0.000
everything
Token everything
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
spread
Token spread
Feature activation+2.366
out
Token out
Feature activation+3.804
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
so
Tokenso
Feature activation+0.000
elegant
Token elegant
Feature activation+1.709
,
Token,
Feature activation+3.750
organic
Token organic
Feature activation+1.062
and
Token and
Feature activation+2.270
rig
Token rig
Feature activation+0.468
orously
Tokenorously
Feature activation+2.046
logical
Token logical
Feature activation+1.042

Top DFA by src position
MAX = 5.454

.
Token.
Feature activation+0.008
Top resid features:
So
Token So
Feature activation+0.092
Top resid features:
if
Token if
Feature activation+0.050
Top resid features:
women
Token women
Feature activation+0.038
Top resid features:
become
Token become
Feature activation+0.019
Top resid features:
so
Token so
Feature activation+5.094
Top resid features:
intimidated
Token intimidated
Feature activation+0.075
Top resid features:
and
Token and
Feature activation+0.223
Top resid features:
traumat
Token traumat
Feature activation+0.480
Top resid features:
ized
Tokenized
Feature activation+0.077
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
âĢ
Token âĢ
Feature activation-0.010
Top resid features:
ľ
Tokenľ
Feature activation+0.006
Top resid features:
It
TokenIt
Feature activation+0.031
Top resid features:
was
Token was
Feature activation+0.068
Top resid features:
so
Token so
Feature activation+5.275
Top resid features:
lethal
Token lethal
Feature activation+0.173
Top resid features:
and
Token and
Feature activation+0.189
Top resid features:
dramatic
Token dramatic
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
related
Tokenrelated
Feature activation-0.027
Top resid features:
costs
Token costs
Feature activation-0.040
Top resid features:
have
Token have
Feature activation-0.052
Top resid features:
become
Token become
Feature activation+0.100
Top resid features:
so
Token so
Feature activation+5.454
Top resid features:
on
Token on
Feature activation+0.070
Top resid features:
erous
Tokenerous
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Affordable
Token Affordable
Feature activation+0.000
Top resid features:
Doctor
Token Doctor
Feature activation-0.011
Top resid features:
Who
Token Who
Feature activation-0.005
Top resid features:
âĦ¢
TokenâĦ¢
Feature activation-0.007
Top resid features:
was
Token was
Feature activation-0.010
Top resid features:
greeted
Token greeted
Feature activation+0.200
Top resid features:
so
Token so
Feature activation+4.667
Top resid features:
rapt
Token rapt
Feature activation+0.097
Top resid features:
ur
Tokenur
Feature activation+0.530
Top resid features:
ously
Tokenously
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
oring
Tokenoring
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
you
Token you
Feature activation-0.006
Top resid features:
may
Token may
Feature activation-0.101
Top resid features:
be
Token be
Feature activation-0.013
Top resid features:
so
Token so
Feature activation+5.041
Top resid features:
focused
Token focused
Feature activation+0.274
Top resid features:
on
Token on
Feature activation+0.243
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
extraction
Token extraction
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
So
Token So
Feature activation+0.043
Top resid features:
if
Token if
Feature activation+0.038
Top resid features:
women
Token women
Feature activation+0.006
Top resid features:
become
Token become
Feature activation+0.048
Top resid features:
so
Token so
Feature activation+4.648
Top resid features:
intimidated
Token intimidated
Feature activation+0.342
Top resid features:
and
Token and
Feature activation+0.155
Top resid features:
traumat
Token traumat
Feature activation+0.000
Top resid features:
ized
Tokenized
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.015
Top resid features:
impossible
Token impossible
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
Mormons
Token Mormons
Feature activation-0.133
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
so
Token so
Feature activation+4.734
Top resid features:
caught
Token caught
Feature activation+0.135
Top resid features:
up
Token up
Feature activation+0.323
Top resid features:
in
Token in
Feature activation+0.104
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
doctr
Token doctr
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
G
Token G
Feature activation-0.002
Top resid features:
ats
Tokenats
Feature activation-0.005
Top resid features:
by
Tokenby
Feature activation-0.013
Top resid features:
is
Token is
Feature activation-0.016
Top resid features:
so
Token so
Feature activation+4.750
Top resid features:
mysterious
Token mysterious
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+0.243
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
fish
Token fish
Feature activation-0.011
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.042
Top resid features:
a
Tokena
Feature activation-0.108
Top resid features:
vow
Token vow
Feature activation+0.015
Top resid features:
so
Token so
Feature activation+4.918
Top resid features:
sw
Token sw
Feature activation+0.026
Top resid features:
agger
Tokenagger
Feature activation+0.310
Top resid features:
ing
Tokening
Feature activation-0.053
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
President
Token President
Feature activation-0.006
Top resid features:
he
Token he
Feature activation-0.055
Top resid features:
âĢ
TokenâĢ
Feature activation-0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.018
Top resid features:
so
Token so
Feature activation+4.875
Top resid features:
smart
Token smart
Feature activation-0.039
Top resid features:
,
Token,
Feature activation+0.293
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
skin
Token skin
Feature activation+0.024
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
my
Token my
Feature activation+0.006
Top resid features:
chest
Token chest
Feature activation-0.022
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
so
Token so
Feature activation+4.516
Top resid features:
t
Token t
Feature activation+0.122
Top resid features:
aut
Tokenaut
Feature activation+0.153
Top resid features:
and
Token and
Feature activation+0.117
Top resid features:
burning
Token burning
Feature activation+0.000
Top resid features:
hot
Token hot
Feature activation+0.000
Top resid features:
no
Token no
Feature activation-0.008
Top resid features:
other
Token other
Feature activation-0.059
Top resid features:
State
Token State
Feature activation-0.050
Top resid features:
has
Token has
Feature activation+0.025
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
so
Token so
Feature activation+2.334
Top resid features:
brazen
Token brazen
Feature activation+0.056
Top resid features:
and
Token and
Feature activation+0.230
Top resid features:
so
Token so
Feature activation+1.644
Top resid features:
un
Token un
Feature activation+0.067
Top resid features:
mind
Tokenmind
Feature activation+0.665
Top resid features:
But
TokenBut
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
ensuing
Token ensuing
Feature activation-0.057
Top resid features:
system
Token system
Feature activation-0.014
Top resid features:
was
Token was
Feature activation-0.018
Top resid features:
so
Token so
Feature activation+4.450
Top resid features:
confusing
Token confusing
Feature activation+0.221
Top resid features:
,
Token,
Feature activation+0.221
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
paperwork
Token paperwork
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
picked
Token picked
Feature activation+0.007
Top resid features:
Over
Token Over
Feature activation-0.025
Top resid features:
pass
Tokenpass
Feature activation-0.012
Top resid features:
I
Token I
Feature activation-0.051
Top resid features:
was
Token was
Feature activation+0.076
Top resid features:
so
Token so
Feature activation+4.311
Top resid features:
surprised
Token surprised
Feature activation+0.083
Top resid features:
,
Token,
Feature activation+0.254
Top resid features:
and
Token and
Feature activation+0.124
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
All
TokenAll
Feature activation+0.041
Top resid features:
that
Token that
Feature activation-0.018
Top resid features:
left
Token left
Feature activation-0.017
Top resid features:
me
Token me
Feature activation-0.188
Top resid features:
so
Token so
Feature activation+4.350
Top resid features:
sed
Token sed
Feature activation+0.412
Top resid features:
ated
Tokenated
Feature activation+0.244
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.022
Top resid features:
ľ
Tokenľ
Feature activation+0.014
Top resid features:
The
TokenThe
Feature activation+0.036
Top resid features:
technology
Token technology
Feature activation-0.011
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:
so
Token so
Feature activation+4.637
Top resid features:
simple
Token simple
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.219
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
iggs
Tokeniggs
Feature activation-0.011
Top resid features:
bos
Token bos
Feature activation-0.021
Top resid features:
on
Tokenon
Feature activation-0.029
Top resid features:
particle
Token particle
Feature activation-0.037
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
so
Token so
Feature activation+4.591
Top resid features:
dangerous
Token dangerous
Feature activation+0.108
Top resid features:
,
Token,
Feature activation+0.176
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
âĢ
Token âĢ
Feature activation-0.016
Top resid features:
ľ
Tokenľ
Feature activation+0.018
Top resid features:
It
TokenIt
Feature activation+0.019
Top resid features:
was
Token was
Feature activation+0.106
Top resid features:
so
Token so
Feature activation+4.372
Top resid features:
lethal
Token lethal
Feature activation+0.039
Top resid features:
and
Token and
Feature activation+0.231
Top resid features:
dramatic
Token dramatic
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
without
Token without
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.012
Top resid features:
because
Token because
Feature activation+0.093
Top resid features:
everything
Token everything
Feature activation+0.076
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
so
Token so
Feature activation+4.335
Top resid features:
spread
Token spread
Feature activation+0.284
Top resid features:
out
Token out
Feature activation-0.044
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:
that
Token that
Feature activation+0.003
Top resid features:
Go
Token Go
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.027
Top resid features:
âĢ
Token âĢ
Feature activation+0.027
Top resid features:
ľ
Tokenľ
Feature activation+0.046
Top resid features:
so
Tokenso
Feature activation+4.336
Top resid features:
elegant
Token elegant
Feature activation+0.182
Top resid features:
,
Token,
Feature activation+0.181
Top resid features:
organic
Token organic
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
rig
Token rig
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.02

Head 3: 0.03

Head 4: 0.04

Head 5: 0.46

Head 6: 0.05

Head 7: 0.09

Head 8: 0.02

Head 9: 0.09

Head 10: 0.01

Head 11: 0.09

Positive logits

usat1.51

ubb1.45

asse1.45

ozo1.40

antis1.40

azon1.38

artney1.38

ense1.36

ament1.34

amus1.34

Topic1.33

hetic1.33

cellence1.33

eah1.33

esta1.33

"],1.32

yz1.31

ocument1.28

usa1.28

footed1.28

Negative logits

THER-1.36

counselling-1.33

counselor-1.31

solicitor-1.25

preferably-1.21

citizenship-1.21

caucuses-1.20

sergeant-1.18

reader-1.16

splits-1.14

coun-1.13

waiter-1.12

pse-1.12

jumper-1.11

counseling-1.11

streetcar-1.10

tariffs-1.09

permitting-1.09

)-1.09

spouse-1.08

INTERVAL 4.650 - 5.167
CONTAINS 0.000%

become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.000
intimidated
Token intimidated
Feature activation+2.188
and
Token and
Feature activation+4.372
traumat
Token traumat
Feature activation+2.976
ized
Tokenized
Feature activation+5.167
from
Token from
Feature activation+2.006
the
Token the
Feature activation+0.216
experiences
Token experiences
Feature activation+0.000
they
Token they
Feature activation+0.000
may
Token may
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
lethal
Token lethal
Feature activation+1.855
and
Token and
Feature activation+4.779
dramatic
Token dramatic
Feature activation+3.003
,
Token,
Feature activation+3.809
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 4.133 - 4.650
CONTAINS 0.001%

was
Token was
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+0.886
ur
Tokenur
Feature activation+0.000
ously
Tokenously
Feature activation+4.451
,
Token,
Feature activation+3.327
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
if
Token if
Feature activation+0.000
women
Token women
Feature activation+0.000
become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.000
intimidated
Token intimidated
Feature activation+2.188
and
Token and
Feature activation+4.372
traumat
Token traumat
Feature activation+2.976
ized
Tokenized
Feature activation+5.167
from
Token from
Feature activation+2.006
the
Token the
Feature activation+0.216
experiences
Token experiences
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
so
Token so
Feature activation+0.000
focused
Token focused
Feature activation+2.810
on
Token on
Feature activation+4.443
the
Token the
Feature activation+2.401
extraction
Token extraction
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
Mormons
Token Mormons
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.000
caught
Token caught
Feature activation+2.466
up
Token up
Feature activation+3.041
in
Token in
Feature activation+4.315
their
Token their
Feature activation+0.162
doctr
Token doctr
Feature activation+0.000
inal
Tokeninal
Feature activation+0.000
imper
Token imper
Feature activation+0.000
atives
Tokenatives
Feature activation+0.000
a
Tokena
Feature activation+0.000
vow
Token vow
Feature activation+0.000
so
Token so
Feature activation+0.000
sw
Token sw
Feature activation+0.000
agger
Tokenagger
Feature activation+3.542
ing
Tokening
Feature activation+4.137
that
Token that
Feature activation+0.107
it
Token it
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
com
Token com
Feature activation+0.000
ical
Tokenical
Feature activation+0.371

INTERVAL 3.617 - 4.133
CONTAINS 0.001%

on
Tokenon
Feature activation+0.000
particle
Token particle
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
dangerous
Token dangerous
Feature activation+1.352
,
Token,
Feature activation+3.810
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
itself
Token itself
Feature activation+0.000
is
Token is
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
lethal
Token lethal
Feature activation+1.855
and
Token and
Feature activation+4.779
dramatic
Token dramatic
Feature activation+3.003
,
Token,
Feature activation+3.809
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
so
Token so
Feature activation+0.000
smart
Token smart
Feature activation+1.827
,
Token,
Feature activation+4.062
âĢ
TokenâĢ
Feature activation+0.116
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
another
Token another
Feature activation+0.000
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
me
Token me
Feature activation+0.000
so
Token so
Feature activation+0.000
sed
Token sed
Feature activation+0.000
ated
Tokenated
Feature activation+3.859
,
Token,
Feature activation+2.973
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
step
Token step
Feature activation+0.000
was
Token was
Feature activation+0.000
brazen
Token brazen
Feature activation+0.000
and
Token and
Feature activation+3.340
so
Token so
Feature activation+0.086
un
Token un
Feature activation+0.812
mind
Tokenmind
Feature activation+1.627
ful
Tokenful
Feature activation+3.963
of
Token of
Feature activation+1.270
the
Token the
Feature activation+0.542
constitutional
Token constitutional
Feature activation+0.000
provisions
Token provisions
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 3.100 - 3.617
CONTAINS 0.003%

the
Token the
Feature activation+0.000
degradation
Token degradation
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
low
Token low
Feature activation+1.399
,
Token,
Feature activation+3.411
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
performance
Token performance
Feature activation+0.000
a
Token a
Feature activation+0.000
term
Token term
Feature activation+0.000
so
Token so
Feature activation+0.000
am
Token am
Feature activation+0.000
orph
Tokenorph
Feature activation+0.000
ous
Tokenous
Feature activation+3.161
that
Token that
Feature activation+0.112
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
cover
Token cover
Feature activation+0.000
any
Token any
Feature activation+0.000
poverty
Token poverty
Feature activation+0.000
reapp
Token reapp
Feature activation+0.000
ears
Tokenears
Feature activation+0.000
so
Token so
Feature activation+0.000
easily
Token easily
Feature activation+0.726
and
Token and
Feature activation+3.219
is
Token is
Feature activation+0.463
so
Token so
Feature activation+0.000
accessible
Token accessible
Feature activation+2.079
tells
Token tells
Feature activation+0.000
us
Token us
Feature activation+1.665
so
Token so
Feature activation+0.000
recognizable
Token recognizable
Feature activation+1.256
,
Token,
Feature activation+2.906
memorable
Token memorable
Feature activation+0.567
,
Token,
Feature activation+2.132
and
Token and
Feature activation+3.534
seem
Token seem
Feature activation+0.000
to
Token to
Feature activation+0.000
fit
Token fit
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+0.886
ur
Tokenur
Feature activation+0.000
ously
Tokenously
Feature activation+4.451
,
Token,
Feature activation+3.327
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
think
Token think
Feature activation+0.000

INTERVAL 2.583 - 3.100
CONTAINS 0.005%

m
Tokenm
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
grateful
Token grateful
Feature activation+1.728
and
Token and
Feature activation+2.801
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
got
Token got
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
d
Token d
Feature activation+1.261
re
Tokenre
Feature activation+0.000
arily
Tokenarily
Feature activation+2.331
predictable
Token predictable
Feature activation+2.746
.
Token.
Feature activation+1.452
The
Token The
Feature activation+0.000
working
Token working
Feature activation+0.000
-
Token-
Feature activation+0.000
class
Tokenclass
Feature activation+0.000
went
Token went
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
above
Token above
Feature activation+1.458
and
Token and
Feature activation+1.560
beyond
Token beyond
Feature activation+2.718
that
Token that
Feature activation+0.000
my
Token my
Feature activation+0.000
mind
Token mind
Feature activation+0.000
is
Token is
Feature activation+0.000
BL
Token BL
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
matter
Token matter
Feature activation+0.000
so
Token so
Feature activation+0.000
emotionally
Token emotionally
Feature activation+0.525
involved
Token involved
Feature activation+2.845
,
Token,
Feature activation+1.718
and
Token and
Feature activation+2.371
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
by
Tokenby
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
mysterious
Token mysterious
Feature activation+1.948
,
Token,
Feature activation+4.156
in
Token in
Feature activation+2.887
fact
Token fact
Feature activation+1.388
,
Token,
Feature activation+3.025
that
Token that
Feature activation+2.072
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.067 - 2.583
CONTAINS 0.007%

rum
Tokenrum
Feature activation+0.000
I
Token I
Feature activation+0.000
knew
Token knew
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
full
Token full
Feature activation+2.511
of
Token of
Feature activation+3.464
antibodies
Token antibodies
Feature activation+0.000
and
Token and
Feature activation+0.283
nutrients
Token nutrients
Feature activation+0.000
,
Token,
Feature activation+0.193
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
so
Token so
Feature activation+0.000
rep
Token rep
Feature activation+0.779
ulsive
Tokenulsive
Feature activation+2.472
to
Token to
Feature activation+1.163
you
Token you
Feature activation+0.264
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
would
Token would
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
terms
Token terms
Feature activation+0.000
so
Token so
Feature activation+0.000
badly
Token badly
Feature activation+1.330
,
Token,
Feature activation+2.187
is
Token is
Feature activation+0.025
just
Token just
Feature activation+0.000
pure
Token pure
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
aden
Tokenaden
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
resistant
Token resistant
Feature activation+2.973
to
Token to
Feature activation+2.425
reform
Token reform
Feature activation+0.000
,
Token,
Feature activation+1.015
the
Token the
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
it
Token it
Feature activation+0.000
because
Token because
Feature activation+0.000
everything
Token everything
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
spread
Token spread
Feature activation+2.366
out
Token out
Feature activation+3.804
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000

INTERVAL 1.550 - 2.067
CONTAINS 0.011%

lights
Token lights
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
on
Token on
Feature activation+1.667
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
friends
Token friends
Feature activation+0.000
.
Token.
Feature activation+0.000
Feeling
Token Feeling
Feature activation+0.000
so
Token so
Feature activation+0.000
grateful
Token grateful
Feature activation+1.858
I
Token I
Feature activation+0.000
got
Token got
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
this
Token this
Feature activation+0.000
this
Token this
Feature activation+0.000
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
well
Token well
Feature activation+0.000
animated
Token animated
Feature activation+1.715
,
Token,
Feature activation+3.063
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
worked
Token worked
Feature activation+0.000
so
Token so
Feature activation+0.017
hard
Token hard
Feature activation+2.603
on
Token on
Feature activation+1.899
it
Token it
Feature activation+0.798
for
Token for
Feature activation+0.667
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
offend
Token offend
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
so
Token so
Feature activation+0.004
doing
Token doing
Feature activation+1.598
,
Token,
Feature activation+0.448
they
Token they
Feature activation+0.000
knowingly
Token knowingly
Feature activation+0.000
printed
Token printed
Feature activation+0.000
news
Token news
Feature activation+0.000

INTERVAL 1.033 - 1.550
CONTAINS 0.010%

I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
so
Token so
Feature activation+0.666
used
Token used
Feature activation+1.857
to
Token to
Feature activation+1.314
the
Token the
Feature activation+0.831
reflex
Token reflex
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
,
Token,
Feature activation+0.000
condesc
Token condesc
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
lineman
Token lineman
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
good
Token good
Feature activation+0.000
at
Token at
Feature activation+1.241
putting
Token putting
Feature activation+0.303
wins
Token wins
Feature activation+0.000
into
Token into
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
.
Token.
Feature activation+0.000
's
Token's
Feature activation+0.000
"
Token "
Feature activation+0.000
so
Tokenso
Feature activation+0.000
severely
Token severely
Feature activation+1.861
weakened
Token weakened
Feature activation+2.393
as
Token as
Feature activation+1.168
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
last
Token last
Feature activation+0.000
-
Token-
Feature activation+0.000
illas
Tokenillas
Feature activation+0.000
generate
Token generate
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
important
Token important
Feature activation+0.000
for
Token for
Feature activation+1.417
these
Token these
Feature activation+0.000
areas
Token areas
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
prince
Token prince
Feature activation+0.000
generated
Token generated
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
interest
Token interest
Feature activation+1.510
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
In
TokenIn
Feature activation+0.000

INTERVAL 0.517 - 1.033
CONTAINS 0.018%

tactic
Token tactic
Feature activation+0.000
has
Token has
Feature activation+0.000
cast
Token cast
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
shadow
Token shadow
Feature activation+0.664
of
Token of
Feature activation+0.161
fear
Token fear
Feature activation+0.828
over
Token over
Feature activation+0.000
strike
Token strike
Feature activation+0.000
zones
Token zones
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
so
Token so
Feature activation+0.000
happy
Token happy
Feature activation+1.125
to
Token to
Feature activation+0.835
be
Token be
Feature activation+0.518
reunited
Token reunited
Feature activation+0.617
with
Token with
Feature activation+0.000
my
Token my
Feature activation+0.000
best
Token best
Feature activation+0.000
án
Tokenán
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
so
Token so
Feature activation+0.000
determined
Token determined
Feature activation+0.914
to
Token to
Feature activation+2.997
make
Token make
Feature activation+1.397
permanently
Token permanently
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
bliss
Token bliss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Gods
Token Gods
Feature activation+0.000
...
Token...
Feature activation+0.000
was
Token was
Feature activation+0.715
changed
Token changed
Feature activation+0.487
for
Token for
Feature activation+0.000
precious
Token precious
Feature activation+0.000
stones
Token stones
Feature activation+0.000
shining
Token shining
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
so
Token so
Feature activation+0.000
on
Token on
Feature activation+0.045
erous
Tokenerous
Feature activation+4.560
that
Token that
Feature activation+0.670
the
Token the
Feature activation+0.000
Affordable
Token Affordable
Feature activation+0.000
Care
Token Care
Feature activation+0.000
Act
Token Act
Feature activation+0.000
includes
Token includes
Feature activation+0.000

INTERVAL 0.000 - 0.517
CONTAINS 99.944%

minister
Token minister
Feature activation+0.000
,
Token,
Feature activation+0.000
Sir
Token Sir
Feature activation+0.000
John
Token John
Feature activation+0.000
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
donald
Tokendonald
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
ì
Token ì
Feature activation+0.000
ł
Tokenł
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ë
Tokenë
Feature activation+0.000
ł
Tokenł
Feature activation+0.000
Ī
TokenĪ
Feature activation+0.000
ë
Tokenë
Feature activation+0.000
¯
Token¯
Feature activation+0.000
¸
Token¸
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
ocked
Tokenocked
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
read
Token read
Feature activation+0.000
-
Token-
Feature activation+0.000
option
Tokenoption
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.000
at
Token at
Feature activation+0.000
Mississippi
Token Mississippi
Feature activation+0.000
State
Token State
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
unite
Token unite
Feature activation+0.000
the
Token the
Feature activation+0.000
working
Token working
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.000
them
Token them
Feature activation+0.000
together
Token together
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
here
Token here
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
wrap
Token wrap
Feature activation+0.000
on
Token on
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000

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 H4.5: (feature 19666)

TOP ACTIVATIONS
MAX = 2.665

F
Token F
Feature activation+0.024
INE
TokenINE
Feature activation+0.557
Gael
Token Gael
Feature activation+1.542
back
Token back
Feature activation+1.160
ben
Tokenben
Feature activation+1.671
cher
Tokencher
Feature activation+2.665
says
Token says
Feature activation+0.794
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
F
Token F
Feature activation+0.094
INE
TokenINE
Feature activation+0.088
Gael
Token Gael
Feature activation+0.694
back
Token back
Feature activation+0.000
ben
Tokenben
Feature activation+0.000
cher
Tokencher
Feature activation+2.320
says
Token says
Feature activation+1.210
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
COR
Token COR
Feature activation+0.513
ON
TokenON
Feature activation+0.000
ER
TokenER
Feature activation+0.624
has
Token has
Feature activation+2.295
found
Token found
Feature activation+0.000
a
Token a
Feature activation+0.000
direct
Token direct
Feature activation+0.000
link
Token link
Feature activation+0.000
between
Token between
Feature activation+0.000
down
Token down
Feature activation+0.767
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
its
Tokenits
Feature activation+0.000
luck
Token luck
Feature activation+2.280
club
Token club
Feature activation+1.719
playing
Token playing
Feature activation+0.336
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
unt
Token unt
Feature activation+0.000
race
Tokenrace
Feature activation+0.000
able
Tokenable
Feature activation+0.000
cash
Token cash
Feature activation+0.000
transfer
Token transfer
Feature activation+0.000
such
Token such
Feature activation+2.192
as
Token as
Feature activation+1.250
Western
Token Western
Feature activation+0.000
Union
Token Union
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Gy
Token Gy
Feature activation+1.278
ro
Tokenro
Feature activation+1.688
scope
Tokenscope
Feature activation+1.492
?
Token?
Feature activation+2.182
Ċ
TokenĊ
Feature activation+0.218
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
Wikipedia
Token Wikipedia
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.195
neural
Token neural
Feature activation+0.676
network
Token network
Feature activation+0.933
?
Token?
Feature activation+2.123
The
Token The
Feature activation+0.000
human
Token human
Feature activation+0.000
brain
Token brain
Feature activation+0.000
consists
Token consists
Feature activation+0.000
of
Token of
Feature activation+0.000
A
Token A
Feature activation+0.000
tool
Token tool
Feature activation+0.508
-
Token-
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ending
Tokenending
Feature activation+1.568
library
Token library
Feature activation+2.119
was
Token was
Feature activation+0.993
considered
Token considered
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
extension
Token extension
Feature activation+0.000
an
Token an
Feature activation+0.000
open
Token open
Feature activation+0.000
-
Token-
Feature activation+0.000
wheel
Tokenwheel
Feature activation+0.000
driver
Token driver
Feature activation+0.214
such
Token such
Feature activation+2.054
as
Token as
Feature activation+1.422
yourself
Token yourself
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
up
Token up
Feature activation+0.000
Derby
Token Derby
Feature activation+0.000
jew
Token jew
Feature activation+0.000
eller
Tokeneller
Feature activation+1.606
and
Token and
Feature activation+0.915
watch
Token watch
Feature activation+0.000
maker
Tokenmaker
Feature activation+2.042
,
Token,
Feature activation+0.304
ultimately
Token ultimately
Feature activation+0.000
became
Token became
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+0.000
Salvador
Token Salvador
Feature activation+0.878
Dal
Token Dal
Feature activation+0.000
'
Token'
Feature activation+0.000
could
Token could
Feature activation+2.038
design
Token design
Feature activation+0.011
.
Token.
Feature activation+0.000
Stri
Token Stri
Feature activation+0.000
king
Tokenking
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
lam
Tokenlam
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
USA
Token USA
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+1.976
the
Token the
Feature activation+0.000
worlds
Token worlds
Feature activation+0.000
largest
Token largest
Feature activation+0.000
group
Token group
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.067
droid
Token droid
Feature activation+0.528
?
Token?
Feature activation+1.914
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
see
Token see
Feature activation+0.000
all
Token all
Feature activation+0.000
Pe
Token Pe
Feature activation+1.146
anut
Tokenanut
Feature activation+0.132
Butter
Token Butter
Feature activation+1.111
Cup
Token Cup
Feature activation+0.620
Bars
Token Bars
Feature activation+0.635
won
Token won
Feature activation+1.911
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
-
Token-
Feature activation+0.000
one
Tokenone
Feature activation+0.000
dessert
Token dessert
Feature activation+0.000
sp
Token sp
Feature activation+0.000
ook
Tokenook
Feature activation+0.607
/
Token/
Feature activation+0.308
di
Tokendi
Feature activation+0.000
plom
Tokenplom
Feature activation+0.536
at
Tokenat
Feature activation+1.905
,
Token,
Feature activation+1.620
Republicans
Token Republicans
Feature activation+0.000
would
Token would
Feature activation+0.000
rightly
Token rightly
Feature activation+0.000
be
Token be
Feature activation+0.000
N
Token N
Feature activation+0.000
.
Token.
Feature activation+0.000
Y
TokenY
Feature activation+0.000
.,
Token.,
Feature activation+0.811
judge
Token judge
Feature activation+0.753
has
Token has
Feature activation+1.880
ruled
Token ruled
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
contractor
Token contractor
Feature activation+0.000
's
Token's
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.127
beat
Token beat
Feature activation+0.000
sheet
Token sheet
Feature activation+1.269
?
Token?
Feature activation+1.879
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
beat
Token beat
Feature activation+0.000
sheet
Token sheet
Feature activation+1.237
ĺ
Tokenĺ
Feature activation+0.000
C
TokenC
Feature activation+0.000
ave
Tokenave
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
shouldn
Token shouldn
Feature activation+1.877
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.618
be
Token be
Feature activation+1.584
unfamiliar
Token unfamiliar
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.574
quality
Tokenquality
Feature activation+0.567
temp
Token temp
Feature activation+0.208
chain
Token chain
Feature activation+1.099
gives
Token gives
Feature activation+1.851
us
Token us
Feature activation+0.000
29
Token 29
Feature activation+0.000
%
Token%
Feature activation+0.000
slower
Token slower
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
Hert
Token Hert
Feature activation+0.229
ford
Tokenford
Feature activation+0.000
College
Token College
Feature activation+0.000
p
Token p
Feature activation+0.062
orter
Tokenorter
Feature activation+1.830
for
Token for
Feature activation+0.262
going
Token going
Feature activation+0.000
into
Token into
Feature activation+0.000
B
Token B
Feature activation+0.000
PL
TokenPL
Feature activation+0.000

Top DFA by src position
MAX = 3.010

party
Token party
Feature activation-0.007
Top resid features:
fold
Token fold
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
A
TokenA
Feature activation+2.893
Top resid features:
F
Token F
Feature activation+0.002
Top resid features:
INE
TokenINE
Feature activation-0.001
Top resid features:
Gael
Token Gael
Feature activation+0.001
Top resid features:
back
Token back
Feature activation+0.021
Top resid features:
ben
Tokenben
Feature activation+0.253
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
FBI
Token FBI
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.046
Top resid features:
A
TokenA
Feature activation+2.677
Top resid features:
F
Token F
Feature activation+0.012
Top resid features:
INE
TokenINE
Feature activation-0.049
Top resid features:
Gael
Token Gael
Feature activation+0.057
Top resid features:
back
Token back
Feature activation-0.015
Top resid features:
ben
Tokenben
Feature activation+0.269
Top resid features:
problem
Token problem
Feature activation+0.001
Top resid features:
solving
Token solving
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
our
Token our
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.044
Top resid features:
A
TokenA
Feature activation+3.010
Top resid features:
COR
Token COR
Feature activation+0.019
Top resid features:
ON
TokenON
Feature activation+0.019
Top resid features:
ER
TokenER
Feature activation-0.002
Top resid features:
has
Token has
Feature activation-0.140
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
eyes
Token eyes
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
Paris
Token Paris
Feature activation-0.001
Top resid features:
ians
Tokenians
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
A
Token A
Feature activation+2.622
Top resid features:
once
Token once
Feature activation+0.014
Top resid features:
down
Token down
Feature activation+0.008
Top resid features:
âĢij
TokenâĢij
Feature activation-0.001
Top resid features:
at
Tokenat
Feature activation+0.002
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
hundred
Token hundred
Feature activation+0.001
Top resid features:
dollars
Token dollars
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Rather
Token Rather
Feature activation-0.001
Top resid features:
than
Token than
Feature activation+0.018
Top resid features:
an
Token an
Feature activation+2.838
Top resid features:
unt
Token unt
Feature activation-0.017
Top resid features:
race
Tokenrace
Feature activation+0.013
Top resid features:
able
Tokenable
Feature activation-0.006
Top resid features:
cash
Token cash
Feature activation-0.008
Top resid features:
transfer
Token transfer
Feature activation-0.017
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
What
TokenWhat
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.057
Top resid features:
a
Token a
Feature activation+2.851
Top resid features:
Gy
Token Gy
Feature activation+0.039
Top resid features:
ro
Tokenro
Feature activation+0.009
Top resid features:
scope
Tokenscope
Feature activation-0.088
Top resid features:
?
Token?
Feature activation-0.076
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation+0.013
Top resid features:
first
Token first
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
what
Token what
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.064
Top resid features:
a
Token a
Feature activation+2.685
Top resid features:
neural
Token neural
Feature activation+0.025
Top resid features:
network
Token network
Feature activation+0.005
Top resid features:
?
Token?
Feature activation-0.070
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
human
Token human
Feature activation+0.000
Top resid features:
projects
Token projects
Feature activation-0.011
Top resid features:
following
Token following
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.019
Top resid features:
disaster
Token disaster
Feature activation-0.012
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
A
Token A
Feature activation+2.688
Top resid features:
tool
Token tool
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.021
Top resid features:
l
Tokenl
Feature activation+0.002
Top resid features:
ending
Tokenending
Feature activation+0.083
Top resid features:
library
Token library
Feature activation-0.111
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
be
Token be
Feature activation+0.010
Top resid features:
difficult
Token difficult
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.058
Top resid features:
an
Token an
Feature activation+2.627
Top resid features:
open
Token open
Feature activation+0.006
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
wheel
Tokenwheel
Feature activation+0.031
Top resid features:
driver
Token driver
Feature activation+0.027
Top resid features:
such
Token such
Feature activation-0.118
Top resid features:
a
Tokena
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
British
Token British
Feature activation+0.001
Top resid features:
daughter
Token daughter
Feature activation-0.013
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+2.636
Top resid features:
Derby
Token Derby
Feature activation+0.023
Top resid features:
jew
Token jew
Feature activation+0.024
Top resid features:
eller
Tokeneller
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.105
Top resid features:
watch
Token watch
Feature activation+0.111
Top resid features:
capitalist
Tokencapitalist
Feature activation-0.003
Top resid features:
'
Token'
Feature activation-0.004
Top resid features:
wedding
Token wedding
Feature activation-0.014
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
only
Token only
Feature activation-0.037
Top resid features:
a
Token a
Feature activation+2.533
Top resid features:
Salvador
Token Salvador
Feature activation-0.022
Top resid features:
Dal
Token Dal
Feature activation+0.009
Top resid features:
'
Token'
Feature activation+0.188
Top resid features:
could
Token could
Feature activation-0.020
Top resid features:
design
Token design
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.005
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
offense
Token offense
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.034
Top resid features:
A
TokenA
Feature activation+2.552
Top resid features:
Voice
Token Voice
Feature activation+0.003
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
Men
Token Men
Feature activation+0.016
Top resid features:
(
Token (
Feature activation+0.031
Top resid features:
AV
TokenAV
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
What
TokenWhat
Feature activation-0.010
Top resid features:
is
Token is
Feature activation+0.051
Top resid features:
a
Token a
Feature activation+2.502
Top resid features:
droid
Token droid
Feature activation-0.024
Top resid features:
?
Token?
Feature activation-0.116
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
We
TokenWe
Feature activation+0.000
Top resid features:
ibr
Tokenibr
Feature activation+0.002
Top resid features:
ant
Tokenant
Feature activation+0.005
Top resid features:
Vegan
Token Vegan
Feature activation+0.004
Top resid features:
category
Token category
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
a
Token a
Feature activation+2.428
Top resid features:
No
Token No
Feature activation+0.018
Top resid features:
Bake
Token Bake
Feature activation+0.009
Top resid features:
Pe
Token Pe
Feature activation+0.009
Top resid features:
anut
Tokenanut
Feature activation+0.005
Top resid features:
Butter
Token Butter
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.016
Top resid features:
info
Token info
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.044
Top resid features:
a
Token a
Feature activation+2.299
Top resid features:
Russian
Token Russian
Feature activation-0.011
Top resid features:
sp
Token sp
Feature activation+0.012
Top resid features:
ook
Tokenook
Feature activation+0.011
Top resid features:
/
Token/
Feature activation+0.068
Top resid features:
di
Tokendi
Feature activation+0.019
Top resid features:
Follow
TokenFollow
Feature activation+0.004
Top resid features:
Amber
Token Amber
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
Twitter
Token Twitter
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.025
Top resid features:
A
TokenA
Feature activation+2.571
Top resid features:
Suffolk
Token Suffolk
Feature activation+0.006
Top resid features:
County
Token County
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
N
Token N
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
What
TokenWhat
Feature activation-0.003
Top resid features:
is
Token is
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+2.408
Top resid features:
beat
Token beat
Feature activation+0.003
Top resid features:
sheet
Token sheet
Feature activation+0.052
Top resid features:
?
Token?
Feature activation-0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
site
Token site
Feature activation-0.000
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
some
Token some
Feature activation-0.001
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+2.275
Top resid features:
Chromebook
Token Chromebook
Feature activation-0.028
Top resid features:
with
Token with
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
cod
Token cod
Feature activation+0.004
Top resid features:
ename
Tokenename
Feature activation+0.009
Top resid features:
will
Token will
Feature activation-0.006
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.001
Top resid features:
26
Token 26
Feature activation-0.011
Top resid features:
%.
Token%.
Feature activation-0.008
Top resid features:
A
Token A
Feature activation+2.411
Top resid features:
lvl
Token lvl
Feature activation+0.012
Top resid features:
20
Token 20
Feature activation+0.019
Top resid features:
non
Token non
Feature activation-0.008
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
quality
Tokenquality
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Rep
TokenRep
Feature activation-0.014
Top resid features:
orted
Tokenorted
Feature activation-0.030
Top resid features:
by
Token by
Feature activation+0.040
Top resid features:
a
Token a
Feature activation+2.468
Top resid features:
Hert
Token Hert
Feature activation-0.006
Top resid features:
ford
Tokenford
Feature activation+0.006
Top resid features:
College
Token College
Feature activation+0.017
Top resid features:
p
Token p
Feature activation+0.066
Top resid features:
orter
Tokenorter
Feature activation-0.178
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.02

Head 3: 0.09

Head 4: 0.03

Head 5: 0.46

Head 6: 0.06

Head 7: 0.09

Head 8: 0.02

Head 9: 0.03

Head 10: 0.02

Head 11: 0.10

Positive logits

resembling1.97

alyst1.89

consisting1.75

Called1.70

statement1.67

staffer1.64

named1.64

study1.63

assian1.62

similar1.58

cko1.56

clutch1.56

examination1.55

urion1.54

akin1.53

icum1.52

icter1.51

oscope1.50

ifier1.50

Named1.49

Negative logits

Ps-1.96

ities-1.95

channels-1.77

doms-1.72

ulations-1.71

Machines-1.69

ements-1.69

ories-1.68

isms-1.67

avenues-1.67

embassies-1.65

virtues-1.62

establishments-1.61

sites-1.60

rogens-1.59

Units-1.59

quickShipAvailable-1.59

ques-1.58

Brands-1.58

bells-1.57

INTERVAL 2.399 - 2.665
CONTAINS 0.000%

F
Token F
Feature activation+0.024
INE
TokenINE
Feature activation+0.557
Gael
Token Gael
Feature activation+1.542
back
Token back
Feature activation+1.160
ben
Tokenben
Feature activation+1.671
cher
Tokencher
Feature activation+2.665
says
Token says
Feature activation+0.794
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.132 - 2.399
CONTAINS 0.001%

is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Gy
Token Gy
Feature activation+1.278
ro
Tokenro
Feature activation+1.688
scope
Tokenscope
Feature activation+1.492
?
Token?
Feature activation+2.182
Ċ
TokenĊ
Feature activation+0.218
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
Wikipedia
Token Wikipedia
Feature activation+0.000
F
Token F
Feature activation+0.094
INE
TokenINE
Feature activation+0.088
Gael
Token Gael
Feature activation+0.694
back
Token back
Feature activation+0.000
ben
Tokenben
Feature activation+0.000
cher
Tokencher
Feature activation+2.320
says
Token says
Feature activation+1.210
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
unt
Token unt
Feature activation+0.000
race
Tokenrace
Feature activation+0.000
able
Tokenable
Feature activation+0.000
cash
Token cash
Feature activation+0.000
transfer
Token transfer
Feature activation+0.000
such
Token such
Feature activation+2.192
as
Token as
Feature activation+1.250
Western
Token Western
Feature activation+0.000
Union
Token Union
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
COR
Token COR
Feature activation+0.513
ON
TokenON
Feature activation+0.000
ER
TokenER
Feature activation+0.624
has
Token has
Feature activation+2.295
found
Token found
Feature activation+0.000
a
Token a
Feature activation+0.000
direct
Token direct
Feature activation+0.000
link
Token link
Feature activation+0.000
between
Token between
Feature activation+0.000
down
Token down
Feature activation+0.767
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
its
Tokenits
Feature activation+0.000
luck
Token luck
Feature activation+2.280
club
Token club
Feature activation+1.719
playing
Token playing
Feature activation+0.336
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.866 - 2.132
CONTAINS 0.001%

Pe
Token Pe
Feature activation+1.146
anut
Tokenanut
Feature activation+0.132
Butter
Token Butter
Feature activation+1.111
Cup
Token Cup
Feature activation+0.620
Bars
Token Bars
Feature activation+0.635
won
Token won
Feature activation+1.911
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
-
Token-
Feature activation+0.000
one
Tokenone
Feature activation+0.000
dessert
Token dessert
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.127
beat
Token beat
Feature activation+0.000
sheet
Token sheet
Feature activation+1.269
?
Token?
Feature activation+1.879
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
beat
Token beat
Feature activation+0.000
sheet
Token sheet
Feature activation+1.237
ĺ
Tokenĺ
Feature activation+0.000
C
TokenC
Feature activation+0.000
ave
Tokenave
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
shouldn
Token shouldn
Feature activation+1.877
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.618
be
Token be
Feature activation+1.584
unfamiliar
Token unfamiliar
Feature activation+0.000
Derby
Token Derby
Feature activation+0.000
jew
Token jew
Feature activation+0.000
eller
Tokeneller
Feature activation+1.606
and
Token and
Feature activation+0.915
watch
Token watch
Feature activation+0.000
maker
Tokenmaker
Feature activation+2.042
,
Token,
Feature activation+0.304
ultimately
Token ultimately
Feature activation+0.000
became
Token became
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
N
Token N
Feature activation+0.000
.
Token.
Feature activation+0.000
Y
TokenY
Feature activation+0.000
.,
Token.,
Feature activation+0.811
judge
Token judge
Feature activation+0.753
has
Token has
Feature activation+1.880
ruled
Token ruled
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
contractor
Token contractor
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 1.599 - 1.866
CONTAINS 0.003%

non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.574
quality
Tokenquality
Feature activation+0.567
temp
Token temp
Feature activation+0.208
chain
Token chain
Feature activation+1.099
gives
Token gives
Feature activation+1.851
us
Token us
Feature activation+0.000
29
Token 29
Feature activation+0.000
%
Token%
Feature activation+0.000
slower
Token slower
Feature activation+0.000
.
Token.
Feature activation+0.000
what
Token what
Feature activation+0.000
powers
Token powers
Feature activation+0.000
an
Token an
Feature activation+0.000
Acting
Token Acting
Feature activation+0.000
AG
Token AG
Feature activation+0.000
can
Token can
Feature activation+1.626
perform
Token perform
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
event
Token event
Feature activation+0.537
or
Token or
Feature activation+0.000
theme
Token theme
Feature activation+0.000
or
Token or
Feature activation+0.017
setting
Token setting
Feature activation+0.352
is
Token is
Feature activation+1.680
so
Token so
Feature activation+0.606
attractive
Token attractive
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
-
Token-
Feature activation+0.076
the
Tokenthe
Feature activation+0.000
-
Token-
Feature activation+0.000
she
Tokenshe
Feature activation+0.000
lf
Tokenlf
Feature activation+0.000
routine
Token routine
Feature activation+1.790
and
Token and
Feature activation+0.007
just
Token just
Feature activation+0.000
compile
Token compile
Feature activation+0.000
it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
Wing
Token Wing
Feature activation+0.624
-
Token-
Feature activation+0.000
Lo
TokenLo
Feature activation+0.000
ong
Tokenong
Feature activation+1.073
U
Token U
Feature activation+1.829
AV
TokenAV
Feature activation+1.752
costs
Token costs
Feature activation+1.696
about
Token about
Feature activation+0.479
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
million
Token million
Feature activation+0.000

INTERVAL 1.333 - 1.599
CONTAINS 0.006%

Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
carb
Token carb
Feature activation+0.646
uncle
Tokenuncle
Feature activation+1.570
is
Token is
Feature activation+1.333
basically
Token basically
Feature activation+1.361
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
lump
Token lump
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
100
Token 100
Feature activation+0.553
MW
Token MW
Feature activation+0.000
pilot
Token pilot
Feature activation+0.000
wind
Token wind
Feature activation+1.357
farm
Token farm
Feature activation+1.408
is
Token is
Feature activation+1.240
scheduled
Token scheduled
Feature activation+0.916
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.111
online
Token online
Feature activation+0.000
A
TokenA
Feature activation+0.000
geometric
Token geometric
Feature activation+0.000
phase
Token phase
Feature activation+0.000
holog
Token holog
Feature activation+0.569
ram
Tokenram
Feature activation+0.399
is
Token is
Feature activation+1.356
a
Token a
Feature activation+0.042
thin
Token thin
Feature activation+0.000
film
Token film
Feature activation+0.000
that
Token that
Feature activation+0.000
manip
Token manip
Feature activation+0.000
J
Token J
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ark
Tokenark
Feature activation+0.000
hand
Tokenhand
Feature activation+0.000
Muk
Token Muk
Feature activation+0.000
ti
Tokenti
Feature activation+1.424
Mor
Token Mor
Feature activation+0.367
cha
Tokencha
Feature activation+0.000
leader
Token leader
Feature activation+0.397
from
Token from
Feature activation+0.773
J
Token J
Feature activation+0.000
a
Token a
Feature activation+0.000
free
Token free
Feature activation+0.000
,
Token,
Feature activation+0.312
open
Token open
Feature activation+0.007
source
Token source
Feature activation+0.528
software
Token software
Feature activation+1.363
directory
Token directory
Feature activation+0.592
.
Token.
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Due
TokenDue
Feature activation+0.000

INTERVAL 1.066 - 1.333
CONTAINS 0.014%

a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
,
Token,
Feature activation+0.000
round
Token round
Feature activation+0.000
ish
Tokenish
Feature activation+0.075
face
Token face
Feature activation+1.250
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Far
Token Far
Feature activation+0.347
,
Token,
Feature activation+0.000
bull
Token bull
Feature activation+0.001
-
Token-
Feature activation+0.000
should
Tokenshould
Feature activation+0.000
ered
Tokenered
Feature activation+1.243
officer
Token officer
Feature activation+1.067
named
Token named
Feature activation+0.000
Barry
Token Barry
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
pulled
Token pulled
Feature activation+0.000
them
Token them
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
Production
Token Production
Feature activation+0.000
point
Token point
Feature activation+0.000
of
Token of
Feature activation+0.000
view
Token view
Feature activation+1.090
Real
Token Real
Feature activation+0.000
World
Token World
Feature activation+0.000
article
Token article
Feature activation+0.045
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-
Token-
Feature activation+0.000
cling
Tokencling
Feature activation+0.000
in
Tokenin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.305
Ļ
TokenĻ
Feature activation+0.100
literary
Token literary
Feature activation+1.170
assault
Token assault
Feature activation+0.158
dude
Token dude
Feature activation+0.129
who
Token who
Feature activation+0.336
enjoys
Token enjoys
Feature activation+0.000
finding
Token finding
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.526
b
Token b
Feature activation+0.411
antam
Tokenantam
Feature activation+0.000
weight
Tokenweight
Feature activation+0.330
champion
Token champion
Feature activation+1.318
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.000
and
Token and
Feature activation+0.000
trains
Token trains
Feature activation+0.000

INTERVAL 0.800 - 1.066
CONTAINS 0.031%

A
TokenA
Feature activation+0.000
National
Token National
Feature activation+0.030
Aud
Token Aud
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
on
Tokenon
Feature activation+0.000
Society
Token Society
Feature activation+1.021
Guide
Token Guide
Feature activation+0.397
to
Token to
Feature activation+0.048
Nature
Token Nature
Feature activation+0.000
Photography
Token Photography
Feature activation+0.000
(
Token (
Feature activation+0.000
,
Token,
Feature activation+0.073
egg
Token egg
Feature activation+0.000
and
Token and
Feature activation+0.000
cheese
Token cheese
Feature activation+0.345
bisc
Token bisc
Feature activation+0.048
uit
Tokenuit
Feature activation+1.042
from
Token from
Feature activation+0.527
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
fast
Token fast
Feature activation+0.000
inter
Token inter
Feature activation+0.178
-
Token-
Feature activation+0.000
re
Tokenre
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+1.023
in
Token in
Feature activation+0.137
the
Token the
Feature activation+0.000
cluster
Token cluster
Feature activation+0.000
of
Token of
Feature activation+0.000
towns
Token towns
Feature activation+0.000
Italian
TokenItalian
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
dictator
Token dictator
Feature activation+0.000
)
Token)
Feature activation+0.185
like
Token like
Feature activation+0.888
figure
Token figure
Feature activation+0.254
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
establish
Token establish
Feature activation+0.000
a
Token a
Feature activation+0.000
Joint
Token Joint
Feature activation+0.000
Typhoon
Token Typhoon
Feature activation+0.000
Warning
Token Warning
Feature activation+0.000
Center
Token Center
Feature activation+0.801
.[
Token.[
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
The
Token The
Feature activation+0.000
C
Token C
Feature activation+0.000

INTERVAL 0.533 - 0.800
CONTAINS 0.073%

have
Tokenhave
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Tokena
Feature activation+0.000
-
Token-
Feature activation+0.000
white
Tokenwhite
Feature activation+0.000
-
Token-
Feature activation+0.571
history
Tokenhistory
Feature activation+0.000
-
Token-
Feature activation+0.276
month
Tokenmonth
Feature activation+0.000
type
Token type
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
car
Token car
Feature activation+0.000
out
Token out
Feature activation+0.383
of
Token of
Feature activation+0.652
the
Token the
Feature activation+0.000
snow
Token snow
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
what
Token what
Feature activation+0.000
distinguishes
Token distinguishes
Feature activation+0.000
a
Token a
Feature activation+0.000
states
Token states
Feature activation+0.049
man
Tokenman
Feature activation+0.193
from
Token from
Feature activation+0.660
a
Token a
Feature activation+0.000
politician
Token politician
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.475
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
level
Tokenlevel
Feature activation+0.014
,
Token,
Feature activation+0.768
scripting
Token scripting
Feature activation+0.604
(
Token (
Feature activation+0.262
interpret
Tokeninterpret
Feature activation+0.000
ed
Tokened
Feature activation+0.000
)
Token)
Feature activation+0.000
language
Token language
Feature activation+0.762
a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.722
M
TokenM
Feature activation+0.000
ormon
Tokenormon
Feature activation+0.000
should
Token should
Feature activation+0.562
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.267 - 0.533
CONTAINS 0.183%

and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
paper
Token paper
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
paper
Token paper
Feature activation+0.284
about
Token about
Feature activation+0.000
Safe
Token Safe
Feature activation+0.000
Type
TokenType
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
were
Token were
Feature activation+0.000
behind
Token behind
Feature activation+0.000
a
Token a
Feature activation+0.000
politically
Token politically
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
plan
Token plan
Feature activation+0.407
in
Token in
Feature activation+0.000
1982
Token 1982
Feature activation+0.000
to
Token to
Feature activation+0.000
dismantle
Token dismantle
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
top
Token top
Feature activation+0.000
flight
Token flight
Feature activation+0.000
world
Token world
Feature activation+0.251
champion
Token champion
Feature activation+0.214
and
Token and
Feature activation+0.365
now
Token now
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
gets
Token gets
Feature activation+0.000
to
Token to
Feature activation+0.000
Last
Token Last
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
Harper
Token Harper
Feature activation+0.000
tweet
Token tweet
Feature activation+0.433
provided
Token provided
Feature activation+0.000
a
Token a
Feature activation+0.000
lovely
Token lovely
Feature activation+0.000
snapshot
Token snapshot
Feature activation+0.000
of
Token of
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
what
Token what
Feature activation+0.000
a
Token a
Feature activation+0.045
great
Token great
Feature activation+0.000
mathematician
Token mathematician
Feature activation+0.447
said
Token said
Feature activation+0.295
about
Token about
Feature activation+0.000
mathematical
Token mathematical
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.267
CONTAINS 99.688%

of
Token of
Feature activation+0.000
good
Token good
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
h
Tokenh
Feature activation+0.000
of
Token of
Feature activation+0.000
Kemp
Token Kemp
Feature activation+0.000
Klein
Token Klein
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
you
Token you
Feature activation+0.000
wondering
Token wondering
Feature activation+0.000
about
Token about
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
poll
Token poll
Feature activation+0.000
tells
Token tells
Feature activation+0.000
us
Token us
Feature activation+0.000
anything
Token anything
Feature activation+0.000
about
Token about
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
kick
Token kick
Feature activation+0.000
stand
Tokenstand
Feature activation+0.000
used
Token used
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Surface
Token Surface
Feature activation+0.000
Studio
Token Studio
Feature activation+0.000
,
Token,
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.000
Par
Token Par
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
outside
Token outside
Feature activation+0.000
of
Token of
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
started
Token started
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.317
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.317
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
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.317
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+0.317
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+0.317
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
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+0.317
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+0.317
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 H4.5: (feature 11907)

TOP ACTIVATIONS
MAX = 5.976

considered
Token considered
Feature activation+0.000
if
Token if
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.100
candidate
Token candidate
Feature activation+5.976
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
what
Token what
Feature activation+0.000
invisible
Token invisible
Feature activation+0.000
.
Token.
Feature activation+0.000
Under
Token Under
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+2.176
circumstances
Token circumstances
Feature activation+5.390
(
Token (
Feature activation+2.673
e
Tokene
Feature activation+0.111
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.,
Token.,
Feature activation+0.011
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.065
things
Token things
Feature activation+5.326
,
Token,
Feature activation+3.025
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
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
present
Token present
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.530
facts
Token facts
Feature activation+5.319
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
India
TokenIndia
Feature activation+0.000
Today
Token Today
Feature activation+0.000
was
Token was
Feature activation+0.000
heading
Token heading
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.665
direction
Token direction
Feature activation+5.247
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
said
Token said
Feature activation+0.000
together
Token together
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
places
Token places
Feature activation+5.220
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
So
TokenSo
Feature activation+0.000
represent
Token represent
Feature activation+0.000
quality
Token quality
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
price
Token price
Feature activation+5.123
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
look
Token look
Feature activation+0.000
put
Token put
Feature activation+0.000
you
Token you
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.177
position
Token position
Feature activation+5.052
.
Token.
Feature activation+0.000
Unfortunately
Token Unfortunately
Feature activation+0.000
for
Token for
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
kind
Token kind
Feature activation+4.937
of
Token of
Feature activation+4.544
action
Token action
Feature activation+1.451
?
Token?
Feature activation+0.000
Extrem
Token Extrem
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
working
Token working
Feature activation+0.000
correctly
Token correctly
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.509
rates
Token rates
Feature activation+4.930
have
Token have
Feature activation+3.227
been
Token been
Feature activation+0.745
provided
Token provided
Feature activation+0.264
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
lead
Token lead
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.400
person
Token person
Feature activation+4.926
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
people
Token people
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.479
decision
Token decision
Feature activation+4.894
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
Public
Token Public
Feature activation+0.000
Knowledge
Token Knowledge
Feature activation+0.000
and
Token and
Feature activation+0.000
Leicester
Token Leicester
Feature activation+0.000
are
Token are
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
track
Token track
Feature activation+4.891
in
Token in
Feature activation+2.393
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
striker
Token striker
Feature activation+0.000
am
Tokenam
Feature activation+0.000
I
Token I
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.307
spot
Token spot
Feature activation+4.863
?).
Token?).
Feature activation+0.000
The
Token The
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
fly
Token fly
Feature activation+0.000
brain
Token brain
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.014
spaceship
Token spaceship
Feature activation+4.131
for
Token for
Feature activation+4.848
you
Token you
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
and
Token and
Feature activation+0.000
AI
Token AI
Feature activation+0.000
requires
Token requires
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+2.158
kind
Token kind
Feature activation+4.807
of
Token of
Feature activation+4.578
robust
Token robust
Feature activation+0.000
capabilities
Token capabilities
Feature activation+1.095
and
Token and
Feature activation+0.560
controls
Token controls
Feature activation+1.655
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.000
having
Token having
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.275
mindset
Token mindset
Feature activation+4.770
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
As
Token As
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
right
Token right
Feature activation+0.000
operating
Token operating
Feature activation+4.270
model
Token model
Feature activation+4.713
and
Token and
Feature activation+3.370
governance
Token governance
Feature activation+3.525
:
Token:
Feature activation+1.258
Ċ
TokenĊ
Feature activation+0.355
Ċ
TokenĊ
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
finding
Token finding
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.638
combination
Token combination
Feature activation+4.697
of
Token of
Feature activation+3.529
pilot
Token pilot
Feature activation+0.000
,
Token,
Feature activation+0.826
ship
Token ship
Feature activation+0.794
,
Token,
Feature activation+0.392
texture
Token texture
Feature activation+0.000
with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.462
amount
Token amount
Feature activation+4.656
of
Token of
Feature activation+4.395
sweetness
Token sweetness
Feature activation+0.743
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 7.122

are
Token are
Feature activation+0.005
Top resid features:
considered
Token considered
Feature activation+0.004
Top resid features:
if
Token if
Feature activation+0.004
Top resid features:
on
Token on
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
right
Token right
Feature activation+7.122
Top resid features:
candidate
Token candidate
Feature activation-0.092
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
And
TokenAnd
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.006
Top resid features:
invisible
Token invisible
Feature activation-0.031
Top resid features:
.
Token.
Feature activation-0.046
Top resid features:
Under
Token Under
Feature activation+0.105
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
right
Token right
Feature activation+6.408
Top resid features:
circumstances
Token circumstances
Feature activation+0.026
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
e
Tokene
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
g
Tokeng
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
if
Token if
Feature activation-0.066
Top resid features:
they
Token they
Feature activation+0.006
Top resid features:
say
Token say
Feature activation+0.279
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
right
Token right
Feature activation+6.216
Top resid features:
things
Token things
Feature activation-0.037
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
if
Token if
Feature activation-0.023
Top resid features:
we
Token we
Feature activation-0.008
Top resid features:
present
Token present
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
right
Token right
Feature activation+6.417
Top resid features:
facts
Token facts
Feature activation-0.063
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:
India
TokenIndia
Feature activation+0.000
Top resid features:
world
Token world
Feature activation-0.049
Top resid features:
was
Token was
Feature activation+0.110
Top resid features:
heading
Token heading
Feature activation-0.016
Top resid features:
in
Token in
Feature activation+0.069
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
right
Token right
Feature activation+6.360
Top resid features:
direction
Token direction
Feature activation-0.041
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:
She
TokenShe
Feature activation+0.000
Top resid features:
put
Token put
Feature activation-0.027
Top resid features:
together
Token together
Feature activation+0.042
Top resid features:
in
Token in
Feature activation+0.075
Top resid features:
all
Token all
Feature activation-0.020
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
right
Token right
Feature activation+6.310
Top resid features:
places
Token places
Feature activation-0.038
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:
"
Token"
Feature activation+0.000
Top resid features:
hen
Tokenhen
Feature activation-0.002
Top resid features:
represent
Token represent
Feature activation+0.002
Top resid features:
quality
Token quality
Feature activation+0.125
Top resid features:
for
Token for
Feature activation+0.169
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
right
Token right
Feature activation+6.182
Top resid features:
price
Token price
Feature activation-0.243
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:
You
TokenYou
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
put
Token put
Feature activation-0.000
Top resid features:
you
Token you
Feature activation-0.015
Top resid features:
in
Token in
Feature activation+0.083
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
right
Token right
Feature activation+6.203
Top resid features:
position
Token position
Feature activation-0.102
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Unfortunately
Token Unfortunately
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Alex
Token Alex
Feature activation+0.000
Top resid features:
ization
Tokenization
Feature activation-0.022
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:
it
Token it
Feature activation-0.089
Top resid features:
the
Token the
Feature activation+0.127
Top resid features:
right
Token right
Feature activation+6.071
Top resid features:
kind
Token kind
Feature activation-0.066
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
action
Token action
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Extrem
Token Extrem
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
working
Token working
Feature activation-0.037
Top resid features:
correctly
Token correctly
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.117
Top resid features:
right
Token right
Feature activation+6.108
Top resid features:
rates
Token rates
Feature activation-0.107
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
provided
Token provided
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
help
Token help
Feature activation-0.020
Top resid features:
lead
Token lead
Feature activation+0.008
Top resid features:
you
Token you
Feature activation+0.076
Top resid features:
to
Token to
Feature activation+0.135
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
right
Token right
Feature activation+5.938
Top resid features:
person
Token person
Feature activation-0.207
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:
Some
TokenSome
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.048
Top resid features:
them
Token them
Feature activation-0.045
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
make
Token make
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
right
Token right
Feature activation+6.038
Top resid features:
decision
Token decision
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
From
Token From
Feature activation+0.000
Top resid features:
Public
Token Public
Feature activation+0.000
Top resid features:
Knowledge
Token Knowledge
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.022
Top resid features:
Leicester
Token Leicester
Feature activation-0.018
Top resid features:
are
Token are
Feature activation-0.004
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
right
Token right
Feature activation+6.099
Top resid features:
track
Token track
Feature activation-0.029
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
looking
Token looking
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.040
Top resid features:
am
Tokenam
Feature activation+0.006
Top resid features:
I
Token I
Feature activation-0.024
Top resid features:
in
Token in
Feature activation+0.061
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
right
Token right
Feature activation+6.118
Top resid features:
spot
Token spot
Feature activation-0.256
Top resid features:
?).
Token?).
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
fruit
Token fruit
Feature activation+0.000
Top resid features:
fly
Token fly
Feature activation+0.000
Top resid features:
Which
Token Which
Feature activation+0.004
Top resid features:
spaceship
Token spaceship
Feature activation-0.056
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
is
Token is
Feature activation+0.035
Top resid features:
the
Token the
Feature activation-0.050
Top resid features:
right
Token right
Feature activation+5.903
Top resid features:
spaceship
Token spaceship
Feature activation+0.042
Top resid features:
for
Token for
Feature activation-0.041
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
learning
Token learning
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
AI
Token AI
Feature activation+0.029
Top resid features:
requires
Token requires
Feature activation+0.126
Top resid features:
the
Token the
Feature activation+0.123
Top resid features:
right
Token right
Feature activation+5.747
Top resid features:
kind
Token kind
Feature activation-0.077
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
robust
Token robust
Feature activation+0.000
Top resid features:
capabilities
Token capabilities
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
all
Token all
Feature activation-0.012
Top resid features:
about
Token about
Feature activation+0.084
Top resid features:
having
Token having
Feature activation-0.023
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
right
Token right
Feature activation+5.729
Top resid features:
mindset
Token mindset
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
As
Token As
Feature activation+0.000
Top resid features:
customer
Token customer
Feature activation-0.010
Top resid features:
?
Token?
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
The
TokenThe
Feature activation+0.156
Top resid features:
right
Token right
Feature activation+6.270
Top resid features:
operating
Token operating
Feature activation-0.155
Top resid features:
model
Token model
Feature activation-0.132
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
governance
Token governance
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
often
Token often
Feature activation+0.006
Top resid features:
be
Token be
Feature activation+0.054
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
finding
Token finding
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
right
Token right
Feature activation+5.660
Top resid features:
combination
Token combination
Feature activation-0.070
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
pilot
Token pilot
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ship
Token ship
Feature activation+0.000
Top resid features:
uit
Tokenuit
Feature activation-0.027
Top resid features:
texture
Token texture
Feature activation+0.021
Top resid features:
with
Token with
Feature activation+0.058
Top resid features:
just
Token just
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.078
Top resid features:
right
Token right
Feature activation+5.750
Top resid features:
amount
Token amount
Feature activation-0.063
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
sweetness
Token sweetness
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.05

Head 2: 0.02

Head 3: 0.03

Head 4: 0.03

Head 5: 0.45

Head 6: 0.05

Head 7: 0.09

Head 8: 0.02

Head 9: 0.05

Head 10: 0.02

Head 11: 0.16

Positive logits

Cooke1.42

Scand1.39

orient1.26

Cyr1.24

dentist1.19

edin1.18

Berm1.16

Cron1.14

flush1.13

Shape1.13

Zan1.12

VG1.12

hatt1.10

nud1.10

spaced1.10

Malk1.10

Drupal1.10

viz1.09

stim1.09

azaki1.09

Negative logits

cade-1.54

casters-1.51

ardon-1.46

û-1.46

caster-1.44

argon-1.37

existence-1.35

ebus-1.33

sung-1.33

portation-1.32

livion-1.29

pes-1.26

inders-1.22

perty-1.21

antz-1.20

rification-1.20

iots-1.19

talk-1.19

krit-1.18

icken-1.17

INTERVAL 5.378 - 5.976
CONTAINS 0.000%

invisible
Token invisible
Feature activation+0.000
.
Token.
Feature activation+0.000
Under
Token Under
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+2.176
circumstances
Token circumstances
Feature activation+5.390
(
Token (
Feature activation+2.673
e
Tokene
Feature activation+0.111
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.,
Token.,
Feature activation+0.011
considered
Token considered
Feature activation+0.000
if
Token if
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.100
candidate
Token candidate
Feature activation+5.976
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
what
Token what
Feature activation+0.000

INTERVAL 4.781 - 5.378
CONTAINS 0.002%

am
Tokenam
Feature activation+0.000
I
Token I
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.307
spot
Token spot
Feature activation+4.863
?).
Token?).
Feature activation+0.000
The
Token The
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
fly
Token fly
Feature activation+0.000
brain
Token brain
Feature activation+0.000
working
Token working
Feature activation+0.000
correctly
Token correctly
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.509
rates
Token rates
Feature activation+4.930
have
Token have
Feature activation+3.227
been
Token been
Feature activation+0.745
provided
Token provided
Feature activation+0.264
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
represent
Token represent
Feature activation+0.000
quality
Token quality
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
price
Token price
Feature activation+5.123
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
look
Token look
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.479
decision
Token decision
Feature activation+4.894
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
Public
Token Public
Feature activation+0.000
Knowledge
Token Knowledge
Feature activation+0.000
and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.065
things
Token things
Feature activation+5.326
,
Token,
Feature activation+3.025
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

INTERVAL 4.183 - 4.781
CONTAINS 0.002%

with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.462
amount
Token amount
Feature activation+4.656
of
Token of
Feature activation+4.395
sweetness
Token sweetness
Feature activation+0.743
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
E
TokenE
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.158
combination
Token combination
Feature activation+4.494
of
Token of
Feature activation+3.244
drugs
Token drugs
Feature activation+1.289
and
Token and
Feature activation+0.000
behaviors
Token behaviors
Feature activation+2.215
that
Token that
Feature activation+1.271
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.491
thing
Token thing
Feature activation+4.635
to
Token to
Feature activation+2.561
do
Token do
Feature activation+1.654
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
while
Token while
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
right
Token right
Feature activation+0.000
operating
Token operating
Feature activation+4.270
model
Token model
Feature activation+4.713
and
Token and
Feature activation+3.370
governance
Token governance
Feature activation+3.525
:
Token:
Feature activation+1.258
Ċ
TokenĊ
Feature activation+0.355
,
Token,
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
time
Token time
Feature activation+4.599
to
Token to
Feature activation+1.009
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Dam
TokenDam
Feature activation+0.000
ascus
Tokenascus
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.586 - 4.183
CONTAINS 0.002%

he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
man
Token man
Feature activation+3.684
to
Token to
Feature activation+1.851
do
Token do
Feature activation+0.000
so
Token so
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
muscles
Token muscles
Feature activation+0.000
at
Token at
Feature activation+0.000
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.116
time
Token time
Feature activation+4.167
for
Token for
Feature activation+1.290
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
to
Token to
Feature activation+0.000
divert
Token divert
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.711
voice
Token voice
Feature activation+3.549
can
Token can
Feature activation+3.775
influence
Token influence
Feature activation+1.912
listeners
Token listeners
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
headed
Token headed
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.021
cultural
Token cultural
Feature activation+3.615
direction
Token direction
Feature activation+4.089
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
only
Token only
Feature activation+0.000
comes
Token comes
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
precisely
Token precisely
Feature activation+0.000
right
Token right
Feature activation+0.000
point
Token point
Feature activation+4.014
in
Token in
Feature activation+1.009
time
Token time
Feature activation+3.595
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
usual
Token usual
Feature activation+0.000

INTERVAL 2.988 - 3.586
CONTAINS 0.002%

women
Token women
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.224
,
Token,
Feature activation+1.428
the
Token the
Feature activation+3.064
left
Token left
Feature activation+0.000
,
Token,
Feature activation+0.127
Jews
Token Jews
Feature activation+1.352
and
Token and
Feature activation+0.000
Arabs
Token Arabs
Feature activation+0.000
pilot
Token pilot
Feature activation+0.000
,
Token,
Feature activation+0.826
ship
Token ship
Feature activation+0.794
,
Token,
Feature activation+0.392
and
Token and
Feature activation+0.000
situation
Token situation
Feature activation+3.225
as
Token as
Feature activation+1.415
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
just
Token just
Feature activation+0.000
picking
Token picking
Feature activation+0.000
claim
Token claim
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
answer
Token answer
Feature activation+3.228
to
Token to
Feature activation+0.978
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
questions
Token questions
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.000
United
Token United
Feature activation+0.000
should
Token should
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
offer
Token offer
Feature activation+3.355
come
Token come
Feature activation+2.679
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Wolf
Token Wolf
Feature activation+0.000
sburg
Tokensburg
Feature activation+0.000
The
TokenThe
Feature activation+0.000
right
Token right
Feature activation+0.000
operating
Token operating
Feature activation+4.270
model
Token model
Feature activation+4.713
and
Token and
Feature activation+3.370
governance
Token governance
Feature activation+3.525
:
Token:
Feature activation+1.258
Ċ
TokenĊ
Feature activation+0.355
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
erv
Tokenerv
Feature activation+0.000

INTERVAL 2.390 - 2.988
CONTAINS 0.001%

Taylor
Token Taylor
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
right
Token right
Feature activation+0.000
for
Token for
Feature activation+2.445
the
Token the
Feature activation+0.000
trip
Token trip
Feature activation+0.000
.
Token.
Feature activation+0.000
Actually
Token Actually
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
track
Token track
Feature activation+4.891
in
Token in
Feature activation+2.393
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
striker
Token striker
Feature activation+0.000
.
Token.
Feature activation+0.000
general
Token general
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.491
thing
Token thing
Feature activation+4.635
to
Token to
Feature activation+2.561
do
Token do
Feature activation+1.654
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
thing
Token thing
Feature activation+2.967
to
Token to
Feature activation+0.464
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
I
Token I
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
that
Token that
Feature activation+0.000
right
Token right
Feature activation+0.000
combination
Token combination
Feature activation+2.513
of
Token of
Feature activation+0.512
going
Token going
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
hot
Token hot
Feature activation+0.000

INTERVAL 1.793 - 2.390
CONTAINS 0.001%

choosing
Token choosing
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.474
word
Token word
Feature activation+3.089
seem
Token seem
Feature activation+2.113
so
Token so
Feature activation+0.000
effort
Token effort
Feature activation+0.000
less
Tokenless
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
right
Token right
Feature activation+0.158
combination
Token combination
Feature activation+4.494
of
Token of
Feature activation+3.244
drugs
Token drugs
Feature activation+1.289
and
Token and
Feature activation+0.000
behaviors
Token behaviors
Feature activation+2.215
that
Token that
Feature activation+1.271
can
Token can
Feature activation+0.461
limit
Token limit
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
or
Token or
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
or
Token or
Feature activation+0.000
wrong
Token wrong
Feature activation+1.001
things
Token things
Feature activation+2.282
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
thing
Token thing
Feature activation+4.081
to
Token to
Feature activation+2.380
do
Token do
Feature activation+2.063
is
Token is
Feature activation+0.093
give
Token give
Feature activation+0.000
it
Token it
Feature activation+0.000
back
Token back
Feature activation+0.000
.
Token.
Feature activation+0.000
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.000
book
Token book
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+0.000
for
Token for
Feature activation+1.914
us
Token us
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
start
Token start
Feature activation+0.000

INTERVAL 1.195 - 1.793
CONTAINS 0.002%

at
Token at
Feature activation+0.000
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.116
time
Token time
Feature activation+4.167
for
Token for
Feature activation+1.290
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
to
Token to
Feature activation+0.000
divert
Token divert
Feature activation+0.000
off
Token off
Feature activation+0.000
right
Token right
Feature activation+0.000
operating
Token operating
Feature activation+4.270
model
Token model
Feature activation+4.713
and
Token and
Feature activation+3.370
governance
Token governance
Feature activation+3.525
:
Token:
Feature activation+1.258
Ċ
TokenĊ
Feature activation+0.355
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
erv
Tokenerv
Feature activation+0.000
asive
Tokenasive
Feature activation+0.000
.
Token.
Feature activation+0.000
Senators
Token Senators
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
flank
Token flank
Feature activation+1.229
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
shrink
Token shrink
Feature activation+0.000
Medicaid
Token Medicaid
Feature activation+0.000
to
Token to
Feature activation+0.000
world
Token world
Feature activation+0.000
was
Token was
Feature activation+0.000
heading
Token heading
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.665
direction
Token direction
Feature activation+5.247
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
wing
Token wing
Feature activation+0.000
media
Token media
Feature activation+0.000
to
Token to
Feature activation+1.782
avoid
Token avoid
Feature activation+0.000
a
Token a
Feature activation+0.000
primary
Token primary
Feature activation+0.000
challenge
Token challenge
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 0.598 - 1.195
CONTAINS 0.005%

the
Token the
Feature activation+0.000
thin
Token thin
Feature activation+0.000
connector
Token connector
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.052
,
Token,
Feature activation+0.775
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
hot
Token hot
Feature activation+0.000
new
Token new
Feature activation+0.000
and
Token and
Feature activation+0.000
hire
Token hire
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.050
people
Token people
Feature activation+4.012
fast
Token fast
Feature activation+0.942
by
Token by
Feature activation+0.000
posting
Token posting
Feature activation+0.000
to
Token to
Feature activation+0.000
200
Token 200
Feature activation+0.000
+
Token+
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.439
little
Token little
Feature activation+2.993
decisions
Token decisions
Feature activation+3.937
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.854
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.000
mic
Token mic
Feature activation+0.000
roman
Tokenroman
Feature activation+0.000
aging
Tokenaging
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
answer
Token answer
Feature activation+3.228
to
Token to
Feature activation+0.978
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
questions
Token questions
Feature activation+0.000
.
Token.
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
thing
Token thing
Feature activation+3.169
to
Token to
Feature activation+0.695
do
Token do
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
52
Token 52
Feature activation+0.000
percent
Token percent
Feature activation+0.000

INTERVAL 0.000 - 0.598
CONTAINS 99.984%

the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
their
Token their
Feature activation+0.000
journey
Token journey
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
Good
TokenGood
Feature activation+0.000
s
Tokens
Feature activation+0.000
or
Token or
Feature activation+0.000
items
Token items
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
collection
Token collection
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
f
Tokenf
Feature activation+0.000
children
Token children
Feature activation+0.000
.
Token.
Feature activation+0.000
Before
Token Before
Feature activation+0.000
the
Token the
Feature activation+0.000
election
Token election
Feature activation+0.000
'
Token '
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
tech
Tokentech
Feature activation+0.000
'
Token '
Feature activation+0.000
from
Token from
Feature activation+0.000
accusations
Token accusations
Feature activation+0.000
of
Token of
Feature activation+0.000
partisans
Token partisans
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
matter
Token matter
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
responsible
Token responsible
Feature activation+0.000
,
Token,
Feature activation+0.000
believes
Token believes
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
better
Token better
Feature activation+0.000
for
Token for
Feature activation+0.000
business
Token business
Feature activation+0.000
to
Token to
Feature activation+0.000
own
Token own
Feature activation+0.000
more
Token more
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 H4.5: (feature 15761)

TOP ACTIVATIONS
MAX = 5.130

market
Token market
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
record
Token record
Feature activation+3.554
-
Token-
Feature activation+4.447
high
Tokenhigh
Feature activation+5.130
job
Token job
Feature activation+2.934
openings
Token openings
Feature activation+3.308
,
Token,
Feature activation+1.139
which
Token which
Feature activation+0.544
means
Token means
Feature activation+0.000
's
Token's
Feature activation+0.000
currency
Token currency
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.678
low
Token low
Feature activation+4.775
and
Token and
Feature activation+0.083
stocks
Token stocks
Feature activation+0.382
plung
Token plung
Feature activation+2.551
ing
Tokening
Feature activation+2.459
.
Token.
Feature activation+0.000
's
Token's
Feature activation+0.000
fall
Token fall
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.898
high
Token high
Feature activation+4.737
of
Token of
Feature activation+0.862
$
Token $
Feature activation+1.392
147
Token147
Feature activation+1.359
.
Token.
Feature activation+0.972
27
Token27
Feature activation+0.921
in
Token in
Feature activation+0.000
cash
Token cash
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.107
sum
Token sum
Feature activation+4.657
.
Token.
Feature activation+1.045
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
For
TokenFor
Feature activation+0.000
Pass
Token Pass
Feature activation+0.000
,
Token,
Feature activation+0.000
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.413
number
Token number
Feature activation+4.601
of
Token of
Feature activation+4.339
finishes
Token finishes
Feature activation+0.000
as
Token as
Feature activation+0.336
every
Token every
Feature activation+0.000
fight
Token fight
Feature activation+0.000
labor
Token labor
Feature activation+0.000
market
Token market
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
record
Token record
Feature activation+3.554
-
Token-
Feature activation+4.447
high
Tokenhigh
Feature activation+5.130
job
Token job
Feature activation+2.934
openings
Token openings
Feature activation+3.308
,
Token,
Feature activation+1.139
which
Token which
Feature activation+0.544
rate
Token rate
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.441
high
Token high
Feature activation+4.446
.
Token.
Feature activation+0.212
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Across
TokenAcross
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.652
$
Token $
Feature activation+4.383
18
Token18
Feature activation+3.300
billion
Token billion
Feature activation+3.150
(
Token (
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
:
Token:
Feature activation+0.000
,
Token,
Feature activation+0.000
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.413
number
Token number
Feature activation+4.601
of
Token of
Feature activation+4.339
finishes
Token finishes
Feature activation+0.000
as
Token as
Feature activation+0.336
every
Token every
Feature activation+0.000
fight
Token fight
Feature activation+0.000
on
Token on
Feature activation+0.000
Key
TokenKey
Feature activation+0.000
consumer
Token consumer
Feature activation+0.000
debt
Token debt
Feature activation+0.000
measure
Token measure
Feature activation+0.000
hits
Token hits
Feature activation+0.000
record
Token record
Feature activation+4.276
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Net
TokenNet
Feature activation+0.000
worth
Token worth
Feature activation+0.000
boosted
Token boosted
Feature activation+0.000
down
Token down
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
from
Token from
Feature activation+0.000
record
Token record
Feature activation+1.222
prices
Token prices
Feature activation+4.271
in
Token in
Feature activation+3.176
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.884
2008
Token2008
Feature activation+0.767
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.701
number
Token number
Feature activation+4.158
of
Token of
Feature activation+4.137
demonstrators
Token demonstrators
Feature activation+1.131
are
Token are
Feature activation+0.730
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.701
number
Token number
Feature activation+4.158
of
Token of
Feature activation+4.137
demonstrators
Token demonstrators
Feature activation+1.131
are
Token are
Feature activation+0.730
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
after
Token after
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.350
low
Token low
Feature activation+4.127
of
Token of
Feature activation+1.085
nearly
Token nearly
Feature activation+0.000
69
Token 69
Feature activation+0.485
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
allergy
Token allergy
Feature activation+0.000
experts
Token experts
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+3.918
setting
Tokensetting
Feature activation+3.620
snow
Token snow
Feature activation+3.040
fall
Tokenfall
Feature activation+3.365
in
Token in
Feature activation+1.752
some
Token some
Feature activation+0.000
record
Token record
Feature activation+1.421
income
Token income
Feature activation+2.493
inequality
Token inequality
Feature activation+1.592
,
Token,
Feature activation+0.494
record
Token record
Feature activation+0.766
profits
Token profits
Feature activation+3.792
for
Token for
Feature activation+3.494
corporations
Token corporations
Feature activation+0.000
and
Token and
Feature activation+0.000
record
Token record
Feature activation+0.009
wealth
Token wealth
Feature activation+3.396
Ŀ
TokenĿ
Feature activation+0.000
attracted
Token attracted
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.910
-
Token-
Feature activation+3.310
breaking
Tokenbreaking
Feature activation+3.741
8
Token 8
Feature activation+3.134
18
Token18
Feature activation+1.191
undergrad
Token undergrad
Feature activation+0.000
uates
Tokenuates
Feature activation+0.502
this
Token this
Feature activation+0.559
experts
Token experts
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+3.918
setting
Tokensetting
Feature activation+3.620
snow
Token snow
Feature activation+3.040
fall
Tokenfall
Feature activation+3.365
in
Token in
Feature activation+1.752
some
Token some
Feature activation+0.000
regions
Token regions
Feature activation+0.000
a
Token a
Feature activation+0.000
World
Token World
Feature activation+0.000
Series
Token Series
Feature activation+0.000
-
Token-
Feature activation+0.000
record
Tokenrecord
Feature activation+1.520
eight
Token eight
Feature activation+3.575
errors
Token errors
Feature activation+0.405
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.000
coming
Token coming
Feature activation+0.000
general
Token general
Feature activation+0.000
labor
Token labor
Feature activation+0.000
market
Token market
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
record
Token record
Feature activation+3.554
-
Token-
Feature activation+4.447
high
Tokenhigh
Feature activation+5.130
job
Token job
Feature activation+2.934
openings
Token openings
Feature activation+3.308
,
Token,
Feature activation+1.139

Top DFA by src position
MAX = 5.382

general
Token general
Feature activation-0.002
Top resid features:
labor
Token labor
Feature activation-0.037
Top resid features:
market
Token market
Feature activation-0.032
Top resid features:
is
Token is
Feature activation+0.032
Top resid features:
seeing
Token seeing
Feature activation-0.044
Top resid features:
record
Token record
Feature activation+5.322
Top resid features:
-
Token-
Feature activation+0.525
Top resid features:
high
Tokenhigh
Feature activation+0.108
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
openings
Token openings
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
nation
Token nation
Feature activation-0.048
Top resid features:
's
Token's
Feature activation+0.026
Top resid features:
currency
Token currency
Feature activation-0.181
Top resid features:
to
Token to
Feature activation+0.235
Top resid features:
a
Token a
Feature activation+0.135
Top resid features:
record
Token record
Feature activation+5.133
Top resid features:
low
Token low
Feature activation+0.180
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
stocks
Token stocks
Feature activation+0.000
Top resid features:
plung
Token plung
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
oil
Token oil
Feature activation-0.002
Top resid features:
's
Token's
Feature activation+0.048
Top resid features:
fall
Token fall
Feature activation-0.024
Top resid features:
from
Token from
Feature activation+0.326
Top resid features:
a
Token a
Feature activation+0.036
Top resid features:
record
Token record
Feature activation+5.124
Top resid features:
high
Token high
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
147
Token147
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
trillion
Token trillion
Feature activation-0.041
Top resid features:
in
Token in
Feature activation+0.022
Top resid features:
cash
Token cash
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.158
Top resid features:
a
Token a
Feature activation+0.216
Top resid features:
record
Token record
Feature activation+5.182
Top resid features:
sum
Token sum
Feature activation-0.033
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:
"
Token"
Feature activation+0.000
Top resid features:
Fight
Token Fight
Feature activation-0.013
Top resid features:
Pass
Token Pass
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
saw
Token saw
Feature activation-0.009
Top resid features:
a
Token a
Feature activation+0.022
Top resid features:
record
Token record
Feature activation+5.382
Top resid features:
number
Token number
Feature activation+0.072
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
finishes
Token finishes
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
general
Token general
Feature activation-0.006
Top resid features:
labor
Token labor
Feature activation-0.026
Top resid features:
market
Token market
Feature activation-0.017
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
seeing
Token seeing
Feature activation+0.004
Top resid features:
record
Token record
Feature activation+5.178
Top resid features:
-
Token-
Feature activation+0.014
Top resid features:
high
Tokenhigh
Feature activation+0.000
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
openings
Token openings
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
employment
Token employment
Feature activation-0.085
Top resid features:
rate
Token rate
Feature activation-0.057
Top resid features:
is
Token is
Feature activation+0.049
Top resid features:
at
Token at
Feature activation+0.267
Top resid features:
a
Token a
Feature activation+0.065
Top resid features:
record
Token record
Feature activation+4.950
Top resid features:
high
Token high
Feature activation-0.014
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:
Across
TokenAcross
Feature activation+0.000
Top resid features:
money
Token money
Feature activation-0.016
Top resid features:
in
Token in
Feature activation+0.053
Top resid features:
Europe
Token Europe
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.128
Top resid features:
a
Token a
Feature activation+0.068
Top resid features:
record
Token record
Feature activation+4.986
Top resid features:
$
Token $
Feature activation-0.120
Top resid features:
18
Token18
Feature activation+0.000
Top resid features:
billion
Token billion
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Photo
TokenPhoto
Feature activation+0.000
Top resid features:
Fight
Token Fight
Feature activation-0.012
Top resid features:
Pass
Token Pass
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
saw
Token saw
Feature activation-0.009
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
record
Token record
Feature activation+4.646
Top resid features:
number
Token number
Feature activation+0.377
Top resid features:
of
Token of
Feature activation+0.134
Top resid features:
finishes
Token finishes
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
Key
TokenKey
Feature activation-0.017
Top resid features:
consumer
Token consumer
Feature activation-0.026
Top resid features:
debt
Token debt
Feature activation-0.017
Top resid features:
measure
Token measure
Feature activation-0.061
Top resid features:
hits
Token hits
Feature activation+0.358
Top resid features:
record
Token record
Feature activation+4.780
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Net
TokenNet
Feature activation+0.000
Top resid features:
worth
Token worth
Feature activation+0.000
Top resid features:
boosted
Token boosted
Feature activation+0.000
Top resid features:
currently
Token currently
Feature activation-0.016
Top resid features:
down
Token down
Feature activation-0.030
Top resid features:
a
Token a
Feature activation+0.052
Top resid features:
bit
Token bit
Feature activation+0.012
Top resid features:
from
Token from
Feature activation+0.315
Top resid features:
record
Token record
Feature activation+4.925
Top resid features:
prices
Token prices
Feature activation-0.170
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
mid
Token mid
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
2008
Token2008
Feature activation+0.000
Top resid features:
Given
TokenGiven
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
fact
Token fact
Feature activation+0.008
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.023
Top resid features:
record
Token record
Feature activation+4.887
Top resid features:
number
Token number
Feature activation+0.035
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
demonstrators
Token demonstrators
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
expected
Token expected
Feature activation+0.000
Top resid features:
Given
TokenGiven
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
fact
Token fact
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
record
Token record
Feature activation+4.473
Top resid features:
number
Token number
Feature activation+0.469
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
demonstrators
Token demonstrators
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
expected
Token expected
Feature activation+0.000
Top resid features:
per
Token per
Feature activation-0.003
Top resid features:
dollar
Token dollar
Feature activation-0.032
Top resid features:
after
Token after
Feature activation+0.107
Top resid features:
hitting
Token hitting
Feature activation-0.010
Top resid features:
a
Token a
Feature activation+0.090
Top resid features:
record
Token record
Feature activation+4.689
Top resid features:
low
Token low
Feature activation+0.102
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
nearly
Token nearly
Feature activation+0.000
Top resid features:
69
Token 69
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
allergy
Token allergy
Feature activation-0.095
Top resid features:
experts
Token experts
Feature activation-0.016
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
record
Token record
Feature activation+4.812
Top resid features:
-
Token-
Feature activation-0.070
Top resid features:
setting
Tokensetting
Feature activation+0.000
Top resid features:
snow
Token snow
Feature activation+0.000
Top resid features:
fall
Tokenfall
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.017
Top resid features:
record
Token record
Feature activation+0.172
Top resid features:
income
Token income
Feature activation+0.043
Top resid features:
inequality
Token inequality
Feature activation-0.019
Top resid features:
,
Token,
Feature activation+0.426
Top resid features:
record
Token record
Feature activation+4.202
Top resid features:
profits
Token profits
Feature activation-0.129
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
corporations
Token corporations
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
record
Token record
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
attracted
Token attracted
Feature activation-0.015
Top resid features:
a
Token a
Feature activation+0.087
Top resid features:
record
Token record
Feature activation+3.380
Top resid features:
-
Token-
Feature activation+0.503
Top resid features:
breaking
Tokenbreaking
Feature activation+0.574
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
18
Token18
Feature activation+0.000
Top resid features:
undergrad
Token undergrad
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
allergy
Token allergy
Feature activation-0.088
Top resid features:
experts
Token experts
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.116
Top resid features:
record
Token record
Feature activation+3.798
Top resid features:
-
Token-
Feature activation+0.392
Top resid features:
setting
Tokensetting
Feature activation+0.089
Top resid features:
snow
Token snow
Feature activation+0.000
Top resid features:
fall
Tokenfall
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
committed
Token committed
Feature activation-0.107
Top resid features:
a
Token a
Feature activation+0.029
Top resid features:
World
Token World
Feature activation-0.023
Top resid features:
Series
Token Series
Feature activation-0.099
Top resid features:
-
Token-
Feature activation+0.031
Top resid features:
record
Tokenrecord
Feature activation+4.396
Top resid features:
eight
Token eight
Feature activation+0.046
Top resid features:
errors
Token errors
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
general
Token general
Feature activation-0.008
Top resid features:
labor
Token labor
Feature activation-0.022
Top resid features:
market
Token market
Feature activation-0.081
Top resid features:
is
Token is
Feature activation+0.079
Top resid features:
seeing
Token seeing
Feature activation-0.040
Top resid features:
record
Token record
Feature activation+4.332
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
high
Tokenhigh
Feature activation+0.000
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
openings
Token openings
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.45

Head 6: 0.04

Head 7: 0.09

Head 8: 0.02

Head 9: 0.05

Head 10: 0.02

Head 11: 0.12

Positive logits

congr1.38

Tend1.33

1.30

Helsinki1.26

1.26

UNITED1.25

Fifa1.23

Osw1.22

Schwar1.20

Eur1.19

Argentine1.16

guiName1.16

Ladies1.16

Ice1.15

Euros1.15

フォ1.15

WIN1.15

龍�1.13

Sw1.13

Ney1.13

Negative logits

phia-1.42

linger-1.37

amination-1.33

cerpt-1.30

soever-1.28

nikov-1.27

edience-1.26

separately-1.25

continuum-1.24

onson-1.23

other-1.22

sylv-1.22

cox-1.22

Dispatch-1.22

istor-1.21

firsthand-1.21

%%%%-1.21

aming-1.19

blogs-1.19

rentices-1.18

INTERVAL 4.617 - 5.130
CONTAINS 0.000%

's
Token's
Feature activation+0.000
currency
Token currency
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.678
low
Token low
Feature activation+4.775
and
Token and
Feature activation+0.083
stocks
Token stocks
Feature activation+0.382
plung
Token plung
Feature activation+2.551
ing
Tokening
Feature activation+2.459
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
cash
Token cash
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.107
sum
Token sum
Feature activation+4.657
.
Token.
Feature activation+1.045
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
For
TokenFor
Feature activation+0.000
's
Token's
Feature activation+0.000
fall
Token fall
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.898
high
Token high
Feature activation+4.737
of
Token of
Feature activation+0.862
$
Token $
Feature activation+1.392
147
Token147
Feature activation+1.359
.
Token.
Feature activation+0.972
27
Token27
Feature activation+0.921
market
Token market
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
record
Token record
Feature activation+3.554
-
Token-
Feature activation+4.447
high
Tokenhigh
Feature activation+5.130
job
Token job
Feature activation+2.934
openings
Token openings
Feature activation+3.308
,
Token,
Feature activation+1.139
which
Token which
Feature activation+0.544
means
Token means
Feature activation+0.000

INTERVAL 4.104 - 4.617
CONTAINS 0.001%

fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.701
number
Token number
Feature activation+4.158
of
Token of
Feature activation+4.137
demonstrators
Token demonstrators
Feature activation+1.131
are
Token are
Feature activation+0.730
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.000
Key
TokenKey
Feature activation+0.000
consumer
Token consumer
Feature activation+0.000
debt
Token debt
Feature activation+0.000
measure
Token measure
Feature activation+0.000
hits
Token hits
Feature activation+0.000
record
Token record
Feature activation+4.276
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Net
TokenNet
Feature activation+0.000
worth
Token worth
Feature activation+0.000
boosted
Token boosted
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
after
Token after
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.350
low
Token low
Feature activation+4.127
of
Token of
Feature activation+1.085
nearly
Token nearly
Feature activation+0.000
69
Token 69
Feature activation+0.485
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.413
number
Token number
Feature activation+4.601
of
Token of
Feature activation+4.339
finishes
Token finishes
Feature activation+0.000
as
Token as
Feature activation+0.336
every
Token every
Feature activation+0.000
fight
Token fight
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.701
number
Token number
Feature activation+4.158
of
Token of
Feature activation+4.137
demonstrators
Token demonstrators
Feature activation+1.131
are
Token are
Feature activation+0.730
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 3.591 - 4.104
CONTAINS 0.001%

Ŀ
TokenĿ
Feature activation+0.000
attracted
Token attracted
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.910
-
Token-
Feature activation+3.310
breaking
Tokenbreaking
Feature activation+3.741
8
Token 8
Feature activation+3.134
18
Token18
Feature activation+1.191
undergrad
Token undergrad
Feature activation+0.000
uates
Tokenuates
Feature activation+0.502
this
Token this
Feature activation+0.559
record
Token record
Feature activation+1.421
income
Token income
Feature activation+2.493
inequality
Token inequality
Feature activation+1.592
,
Token,
Feature activation+0.494
record
Token record
Feature activation+0.766
profits
Token profits
Feature activation+3.792
for
Token for
Feature activation+3.494
corporations
Token corporations
Feature activation+0.000
and
Token and
Feature activation+0.000
record
Token record
Feature activation+0.009
wealth
Token wealth
Feature activation+3.396
allergy
Token allergy
Feature activation+0.000
experts
Token experts
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+3.918
setting
Tokensetting
Feature activation+3.620
snow
Token snow
Feature activation+3.040
fall
Tokenfall
Feature activation+3.365
in
Token in
Feature activation+1.752
some
Token some
Feature activation+0.000
experts
Token experts
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+3.918
setting
Tokensetting
Feature activation+3.620
snow
Token snow
Feature activation+3.040
fall
Tokenfall
Feature activation+3.365
in
Token in
Feature activation+1.752
some
Token some
Feature activation+0.000
regions
Token regions
Feature activation+0.000

INTERVAL 3.078 - 3.591
CONTAINS 0.002%

,
Token,
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
$
Token $
Feature activation+3.323
485
Token485
Feature activation+1.720
.
Token.
Feature activation+1.359
4
Token4
Feature activation+1.266
million
Token million
Feature activation+1.493
from
Token from
Feature activation+0.000
attracted
Token attracted
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.910
-
Token-
Feature activation+3.310
breaking
Tokenbreaking
Feature activation+3.741
8
Token 8
Feature activation+3.134
18
Token18
Feature activation+1.191
undergrad
Token undergrad
Feature activation+0.000
uates
Tokenuates
Feature activation+0.502
this
Token this
Feature activation+0.559
semester
Token semester
Feature activation+0.000
general
Token general
Feature activation+0.000
labor
Token labor
Feature activation+0.000
market
Token market
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
record
Token record
Feature activation+3.554
-
Token-
Feature activation+4.447
high
Tokenhigh
Feature activation+5.130
job
Token job
Feature activation+2.934
openings
Token openings
Feature activation+3.308
,
Token,
Feature activation+1.139
team
Token team
Feature activation+0.000
,
Token,
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+0.151
64
Token 64
Feature activation+3.527
goals
Token goals
Feature activation+0.669
in
Token in
Feature activation+0.000
52
Token 52
Feature activation+0.000
matches
Token matches
Feature activation+0.000
.
Token.
Feature activation+0.000
-
Token -
Feature activation+0.000
TEAM
Token TEAM
Feature activation+0.000
WORK
TokenWORK
Feature activation+0.000
!
Token!
Feature activation+0.000
Record
Token Record
Feature activation+0.000
setting
Token setting
Feature activation+3.179
rainfall
Token rainfall
Feature activation+3.004
.
Token.
Feature activation+0.224
âĢĶ
Token âĢĶ
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
J
Token J
Feature activation+0.000

INTERVAL 2.565 - 3.078
CONTAINS 0.001%

Hot
Token Hot
Feature activation+0.000
els
Tokenels
Feature activation+0.000
have
Token have
Feature activation+0.000
record
Token record
Feature activation+0.554
occupancy
Token occupancy
Feature activation+1.799
rates
Token rates
Feature activation+2.788
,
Token,
Feature activation+0.905
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
household
Token household
Feature activation+0.000
debt
Token debt
Feature activation+0.000
has
Token has
Feature activation+0.000
hit
Token hit
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.941
.
Token.
Feature activation+0.763
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
measure
Token measure
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
of
Token of
Feature activation+0.000
record
Token record
Feature activation+1.209
unemployment
Token unemployment
Feature activation+2.697
,
Token,
Feature activation+0.113
but
Token but
Feature activation+0.000
indications
Token indications
Feature activation+0.000
early
Token early
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
widely
Token widely
Feature activation+0.000
reported
Token reported
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.252
-
Token-
Feature activation+2.902
breaking
Tokenbreaking
Feature activation+3.193
event
Token event
Feature activation+2.750
(
Token (
Feature activation+0.553
2010
Token2010
Feature activation+0.000
),
Token),
Feature activation+1.515
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.252
-
Token-
Feature activation+2.902
breaking
Tokenbreaking
Feature activation+3.193
event
Token event
Feature activation+2.750
(
Token (
Feature activation+0.553
2010
Token2010
Feature activation+0.000
),
Token),
Feature activation+1.515
[
Token[
Feature activation+0.000
6
Token6
Feature activation+0.000

INTERVAL 2.052 - 2.565
CONTAINS 0.001%

a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.678
low
Token low
Feature activation+4.775
and
Token and
Feature activation+0.083
stocks
Token stocks
Feature activation+0.382
plung
Token plung
Feature activation+2.551
ing
Tokening
Feature activation+2.459
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
continue
Token continue
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+1.858
setting
Tokensetting
Feature activation+2.319
pace
Token pace
Feature activation+0.441
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Packers
Token Packers
Feature activation+0.000
would
Token would
Feature activation+0.000
of
Token of
Feature activation+0.000
discrepancies
Token discrepancies
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+2.137
keeping
Tokenkeeping
Feature activation+0.269
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
euro
Token euro
Feature activation+0.000
zone
Token zone
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
already
Token already
Feature activation+0.000
has
Token has
Feature activation+0.000
record
Token record
Feature activation+1.421
income
Token income
Feature activation+2.493
inequality
Token inequality
Feature activation+1.592
,
Token,
Feature activation+0.494
record
Token record
Feature activation+0.766
profits
Token profits
Feature activation+3.792
for
Token for
Feature activation+3.494
trillion
Token trillion
Feature activation+0.000
in
Token in
Feature activation+0.000
cash
Token cash
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+2.107
sum
Token sum
Feature activation+4.657
.
Token.
Feature activation+1.045
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000

INTERVAL 1.539 - 2.052
CONTAINS 0.001%

oil
Token oil
Feature activation+0.000
's
Token's
Feature activation+0.000
fall
Token fall
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.898
high
Token high
Feature activation+4.737
of
Token of
Feature activation+0.862
$
Token $
Feature activation+1.392
147
Token147
Feature activation+1.359
.
Token.
Feature activation+0.972
result
Token result
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
probable
Token probable
Feature activation+0.000
record
Token record
Feature activation+0.000
year
Token year
Feature activation+1.955
for
Token for
Feature activation+1.900
healthcare
Token healthcare
Feature activation+0.000
lobbying
Token lobbying
Feature activation+0.000
revenue
Token revenue
Feature activation+0.563
.
Token.
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
$
Token $
Feature activation+3.323
485
Token485
Feature activation+1.720
.
Token.
Feature activation+1.359
4
Token4
Feature activation+1.266
million
Token million
Feature activation+1.493
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
probable
Token probable
Feature activation+0.000
record
Token record
Feature activation+0.000
year
Token year
Feature activation+1.955
for
Token for
Feature activation+1.900
healthcare
Token healthcare
Feature activation+0.000
lobbying
Token lobbying
Feature activation+0.000
revenue
Token revenue
Feature activation+0.563
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
you
Token you
Feature activation+0.000
collect
Token collect
Feature activation+0.000
record
Token record
Feature activation+1.930
revenues
Token revenues
Feature activation+3.250
and
Token and
Feature activation+1.393
still
Token still
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.026 - 1.539
CONTAINS 0.003%

for
Token for
Feature activation+3.494
corporations
Token corporations
Feature activation+0.000
and
Token and
Feature activation+0.000
record
Token record
Feature activation+0.009
wealth
Token wealth
Feature activation+3.396
for
Token for
Feature activation+1.046
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
fifth
Token fifth
Feature activation+0.000
record
Token record
Feature activation+0.000
,
Token,
Feature activation+0.000
Big
Token Big
Feature activation+0.198
Balloon
Token Balloon
Feature activation+0.000
,
Token,
Feature activation+1.163
Manchester
Token Manchester
Feature activation+0.000
's
Token's
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.000
Un
Token Un
Feature activation+0.000
cles
Tokencles
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
already
Token already
Feature activation+0.000
has
Token has
Feature activation+0.000
record
Token record
Feature activation+1.421
income
Token income
Feature activation+2.493
inequality
Token inequality
Feature activation+1.592
,
Token,
Feature activation+0.494
record
Token record
Feature activation+0.766
profits
Token profits
Feature activation+3.792
practice
Token practice
Feature activation+0.000
sessions
Token sessions
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
attempt
Token attempt
Feature activation+1.099
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Ass
Token Ass
Feature activation+0.000
am
Tokenam
Feature activation+0.000
region
Token region
Feature activation+0.000
record
Token record
Feature activation+0.556
-
Token-
Feature activation+2.955
breaking
Tokenbreaking
Feature activation+3.136
Christmas
Token Christmas
Feature activation+2.063
toy
Token toy
Feature activation+0.907
donation
Token donation
Feature activation+1.075
".[
Token".[
Feature activation+0.000
11
Token11
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.513 - 1.026
CONTAINS 0.004%

setting
Tokensetting
Feature activation+1.375
,
Token,
Feature activation+0.148
73
Token 73
Feature activation+0.980
-
Token-
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
Warriors
Token Warriors
Feature activation+0.551
.
Token.
Feature activation+0.431
Led
Token Led
Feature activation+0.000
by
Token by
Feature activation+0.000
Curry
Token Curry
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
-
Token-
Feature activation+2.134
setting
Tokensetting
Feature activation+1.375
,
Token,
Feature activation+0.148
73
Token 73
Feature activation+0.980
-
Token-
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
Warriors
Token Warriors
Feature activation+0.551
.
Token.
Feature activation+0.431
Led
Token Led
Feature activation+0.000
record
Token record
Feature activation+1.222
prices
Token prices
Feature activation+4.271
in
Token in
Feature activation+3.176
mid
Token mid
Feature activation+0.000
-
Token-
Feature activation+0.884
2008
Token2008
Feature activation+0.767
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Similar
TokenSimilar
Feature activation+0.000
,
Token,
Feature activation+0.000
But
Token But
Feature activation+0.000
fall
Token fall
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.898
high
Token high
Feature activation+4.737
of
Token of
Feature activation+0.862
$
Token $
Feature activation+1.392
147
Token147
Feature activation+1.359
.
Token.
Feature activation+0.972
27
Token27
Feature activation+0.921
in
Token in
Feature activation+0.301
record
Token record
Feature activation+0.000
year
Token year
Feature activation+1.955
for
Token for
Feature activation+1.900
healthcare
Token healthcare
Feature activation+0.000
lobbying
Token lobbying
Feature activation+0.000
revenue
Token revenue
Feature activation+0.563
.
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

INTERVAL 0.000 - 0.513
CONTAINS 99.985%

the
Token the
Feature activation+0.000
E
Token E
Feature activation+0.000
IA
TokenIA
Feature activation+0.000
C
Token C
Feature activation+0.000
&
Token&
Feature activation+0.000
C
TokenC
Feature activation+0.000
number
Token number
Feature activation+0.000
is
Token is
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
work
Token work
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
glitches
Token glitches
Feature activation+0.000
by
Token by
Feature activation+0.000
communicating
Token communicating
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
,
Token,
Feature activation+0.000
Brighton
Token Brighton
Feature activation+0.000
and
Token and
Feature activation+0.000
Bristol
Token Bristol
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
to
Tokento
Feature activation+0.000
commute
Token commute
Feature activation+0.000
to
Token to
Feature activation+0.000
high
Token high
Feature activation+0.000
T
Token T
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
Longh
Token Longh
Feature activation+0.000
orns
Tokenorns
Feature activation+0.000
host
Token host
Feature activation+0.000
the
Token the
Feature activation+0.000
No
Token No
Feature activation+0.000
.
Token.
Feature activation+0.000
10
Token 10
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
on
Token on
Feature activation+0.000
federal
Token federal
Feature activation+0.000
wiret
Token wiret
Feature activation+0.000
apping
Tokenapping
Feature activation+0.000
charges
Token charges
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
included
Token included
Feature activation+0.000
conspiracy
Token conspiracy
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