H6.5 top features

Top feature 0 in H6.5: (feature 19498)

TOP ACTIVATIONS
MAX = 2.981

could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
clearer
Token clearer
Feature activation+0.650
.
Token.
Feature activation+2.981
Ċ
TokenĊ
Feature activation+0.992
Ċ
TokenĊ
Feature activation+1.338
Ret
TokenRet
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
spect
Tokenspect
Feature activation+0.000
until
Token until
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
short
Token short
Feature activation+0.000
of
Token of
Feature activation+2.377
perfect
Token perfect
Feature activation+1.173
.
Token.
Feature activation+0.215
A
Token A
Feature activation+0.000
crew
Token crew
Feature activation+0.000
had
Token had
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
more
Token more
Feature activation+0.742
right
Token right
Feature activation+0.126
.
Token.
Feature activation+1.856
But
Token But
Feature activation+2.170
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
for
Token for
Feature activation+0.598
the
Token the
Feature activation+0.329
involvement
Token involvement
Feature activation+0.000
of
Token of
Feature activation+0.352
China
Token China
Feature activation+0.051
.
Token.
Feature activation+2.063
Ċ
TokenĊ
Feature activation+1.174
Ċ
TokenĊ
Feature activation+0.921
Chinese
TokenChinese
Feature activation+0.000
'
Token '
Feature activation+0.000
arm
Tokenarm
Feature activation+0.000
intent
Token intent
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
clearer
Token clearer
Feature activation+0.156
:
Token:
Feature activation+1.911
the
Token the
Feature activation+0.592
state
Token state
Feature activation+0.000
should
Token should
Feature activation+0.463
suppress
Token suppress
Feature activation+0.000
any
Token any
Feature activation+0.000
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
more
Token more
Feature activation+0.742
right
Token right
Feature activation+0.126
.
Token.
Feature activation+1.856
But
Token But
Feature activation+2.170
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
ignore
Token ignore
Feature activation+0.039
.
Token.
Feature activation+1.792
Ċ
TokenĊ
Feature activation+0.804
Ċ
TokenĊ
Feature activation+0.084
I
TokenI
Feature activation+0.190
know
Token know
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
unfamiliar
Token unfamiliar
Feature activation+0.090
.
Token.
Feature activation+1.724
Likely
Token Likely
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
going
Token going
Feature activation+0.504
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
metal
Token metal
Feature activation+0.000
detector
Token detector
Feature activation+0.000
.
Token.
Feature activation+1.691
You
Token You
Feature activation+0.451
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
queue
Token queue
Feature activation+0.000
to
Token to
Feature activation+1.602
have
Token have
Feature activation+0.977
a
Token a
Feature activation+1.079
good
Token good
Feature activation+0.759
season
Token season
Feature activation+0.158
.
Token.
Feature activation+1.662
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
maintenance
Token maintenance
Feature activation+0.508
of
Token of
Feature activation+1.057
our
Token our
Feature activation+0.479
living
Token living
Feature activation+0.000
environment
Token environment
Feature activation+1.197
.
Token.
Feature activation+1.662
Science
Token Science
Feature activation+0.000
cannot
Token cannot
Feature activation+0.103
fully
Token fully
Feature activation+0.028
mitigate
Token mitigate
Feature activation+0.087
the
Token the
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
denied
Token denied
Feature activation+0.000
again
Token again
Feature activation+0.267
.
Token.
Feature activation+1.625
He
Token He
Feature activation+1.317
scored
Token scored
Feature activation+0.000
41
Token 41
Feature activation+0.000
points
Token points
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
keen
Token keen
Feature activation+0.000
political
Token political
Feature activation+0.000
mind
Token mind
Feature activation+0.000
to
Token to
Feature activation+0.351
notice
Token notice
Feature activation+1.609
that
Token that
Feature activation+1.042
conservatives
Token conservatives
Feature activation+0.000
and
Token and
Feature activation+0.000
liberals
Token liberals
Feature activation+0.000
have
Token have
Feature activation+0.220
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.071
going
Token going
Feature activation+1.439
to
Token to
Feature activation+1.602
have
Token have
Feature activation+0.977
a
Token a
Feature activation+1.079
good
Token good
Feature activation+0.759
season
Token season
Feature activation+0.158
.
Token.
Feature activation+1.662
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
difficult
Token difficult
Feature activation+0.005
subject
Token subject
Feature activation+0.095
?
Token?
Feature activation+1.560
I
Token I
Feature activation+0.972
certainly
Token certainly
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.365
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.080
get
Token get
Feature activation+0.836
things
Token things
Feature activation+0.051
done
Token done
Feature activation+1.001
?
Token?
Feature activation+1.534
Ċ
TokenĊ
Feature activation+0.915
Ċ
TokenĊ
Feature activation+0.881
What
TokenWhat
Feature activation+0.000
we
Token we
Feature activation+0.016
need
Token need
Feature activation+0.000
than
Token than
Feature activation+0.544
through
Token through
Feature activation+1.256
writing
Token writing
Feature activation+1.322
science
Token science
Feature activation+0.159
fiction
Token fiction
Feature activation+0.656
stories
Token stories
Feature activation+1.526
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Although
TokenAlthough
Feature activation+0.000
the
Token the
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
stretch
Token stretch
Feature activation+0.010
to
Token to
Feature activation+0.437
imagine
Token imagine
Feature activation+1.489
Life
Token Life
Feature activation+0.086
is
Token is
Feature activation+0.000
Strange
Token Strange
Feature activation+0.000
under
Token under
Feature activation+0.070
the
Token the
Feature activation+0.370
have
Token have
Feature activation+0.000
done
Token done
Feature activation+0.000
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.707
job
Token job
Feature activation+0.478
.
Token.
Feature activation+1.470
It
Token It
Feature activation+1.280
's
Token's
Feature activation+0.574
a
Token a
Feature activation+0.139
disgrace
Token disgrace
Feature activation+0.000
.
Token.
Feature activation+0.000
present
Token present
Feature activation+0.000
how
Token how
Feature activation+0.556
they
Token they
Feature activation+0.000
wish
Token wish
Feature activation+0.000
,
Token,
Feature activation+0.323
and
Token and
Feature activation+1.464
to
Token to
Feature activation+0.438
be
Token be
Feature activation+0.000
treated
Token treated
Feature activation+0.000
with
Token with
Feature activation+0.000
respect
Token respect
Feature activation+0.000

Top DFA by src position
MAX = 3.051

calculus
Token calculus
Feature activation-0.026
Top resid features:
could
Token could
Feature activation-0.023
Top resid features:
not
Token not
Feature activation+0.021
Top resid features:
have
Token have
Feature activation+0.237
Top resid features:
been
Token been
Feature activation+0.141
Top resid features:
clearer
Token clearer
Feature activation+3.051
Top resid features:
.
Token.
Feature activation+0.090
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ret
TokenRet
Feature activation+0.000
Top resid features:
ro
Tokenro
Feature activation+0.000
Top resid features:
until
Token until
Feature activation+0.001
Top resid features:
they
Token they
Feature activation-0.016
Top resid features:
were
Token were
Feature activation-0.004
Top resid features:
nothing
Token nothing
Feature activation-0.116
Top resid features:
short
Token short
Feature activation+0.522
Top resid features:
of
Token of
Feature activation+2.560
Top resid features:
perfect
Token perfect
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
crew
Token crew
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
He
Token He
Feature activation-0.018
Top resid features:
couldn
Token couldn
Feature activation-0.074
Top resid features:
't
Token't
Feature activation-0.049
Top resid features:
have
Token have
Feature activation+0.155
Top resid features:
been
Token been
Feature activation+0.124
Top resid features:
more
Token more
Feature activation+2.319
Top resid features:
right
Token right
Feature activation+0.094
Top resid features:
.
Token.
Feature activation+0.151
Top resid features:
But
Token But
Feature activation+0.015
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
case
Token case
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
had
Token had
Feature activation-0.004
Top resid features:
it
Token it
Feature activation-0.024
Top resid features:
not
Token not
Feature activation+2.040
Top resid features:
been
Token been
Feature activation+0.096
Top resid features:
for
Token for
Feature activation+0.556
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
involvement
Token involvement
Feature activation+0.038
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation+0.002
Top resid features:
intent
Token intent
Feature activation-0.030
Top resid features:
could
Token could
Feature activation-0.037
Top resid features:
not
Token not
Feature activation+0.051
Top resid features:
be
Token be
Feature activation+0.093
Top resid features:
clearer
Token clearer
Feature activation+2.338
Top resid features:
:
Token:
Feature activation+0.065
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:
suppress
Token suppress
Feature activation+0.000
Top resid features:
He
Token He
Feature activation-0.005
Top resid features:
couldn
Token couldn
Feature activation-0.046
Top resid features:
't
Token't
Feature activation-0.038
Top resid features:
have
Token have
Feature activation+0.180
Top resid features:
been
Token been
Feature activation+0.093
Top resid features:
more
Token more
Feature activation+2.044
Top resid features:
right
Token right
Feature activation+0.166
Top resid features:
.
Token.
Feature activation+0.094
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.025
Top resid features:
can
Token can
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
t
Tokent
Feature activation+0.039
Top resid features:
ignore
Token ignore
Feature activation+1.954
Top resid features:
.
Token.
Feature activation+0.148
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
shouldn
Token shouldn
Feature activation+0.057
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
t
Tokent
Feature activation+0.015
Top resid features:
be
Token be
Feature activation+0.024
Top resid features:
unfamiliar
Token unfamiliar
Feature activation+1.857
Top resid features:
.
Token.
Feature activation+0.152
Top resid features:
Likely
Token Likely
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Nothing
TokenNothing
Feature activation+0.001
Top resid features:
wastes
Token wastes
Feature activation+0.135
Top resid features:
time
Token time
Feature activation+0.093
Top resid features:
more
Token more
Feature activation+0.995
Top resid features:
than
Token than
Feature activation+0.928
Top resid features:
f
Token f
Feature activation+0.022
Top resid features:
umbling
Tokenumbling
Feature activation-0.019
Top resid features:
with
Token with
Feature activation-0.022
Top resid features:
change
Token change
Feature activation+0.007
Top resid features:
reason
Token reason
Feature activation+0.079
Top resid features:
he
Token he
Feature activation-0.007
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
not
Token not
Feature activation+1.882
Top resid features:
going
Token going
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
have
Token have
Feature activation+0.019
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
good
Token good
Feature activation-0.037
Top resid features:
of
Token of
Feature activation+0.058
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
more
Token more
Feature activation+0.557
Top resid features:
misguided
Token misguided
Feature activation+0.062
Top resid features:
application
Token application
Feature activation+0.032
Top resid features:
than
Token than
Feature activation+1.031
Top resid features:
to
Token to
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
maintenance
Token maintenance
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
our
Token our
Feature activation+0.032
Top resid features:
wasn
Token wasn
Feature activation-0.010
Top resid features:
't
Token't
Feature activation-0.030
Top resid features:
going
Token going
Feature activation-0.016
Top resid features:
to
Token to
Feature activation-0.032
Top resid features:
be
Token be
Feature activation-0.022
Top resid features:
denied
Token denied
Feature activation+2.165
Top resid features:
again
Token again
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.127
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
scored
Token scored
Feature activation+0.000
Top resid features:
41
Token 41
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.026
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
keen
Token keen
Feature activation+0.005
Top resid features:
political
Token political
Feature activation+0.005
Top resid features:
mind
Token mind
Feature activation-0.015
Top resid features:
to
Token to
Feature activation+2.073
Top resid features:
notice
Token notice
Feature activation+0.093
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
conservatives
Token conservatives
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
liberals
Token liberals
Feature activation+0.000
Top resid features:
reason
Token reason
Feature activation-0.013
Top resid features:
he
Token he
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
not
Token not
Feature activation+1.948
Top resid features:
going
Token going
Feature activation+0.062
Top resid features:
to
Token to
Feature activation+0.137
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.002
Top resid features:
;
Token;
Feature activation+0.040
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
who
Token who
Feature activation-0.123
Top resid features:
can
Token can
Feature activation+0.239
Top resid features:
blame
Token blame
Feature activation+1.347
Top resid features:
pupils
Token pupils
Feature activation+0.016
Top resid features:
for
Token for
Feature activation+0.116
Top resid features:
dropping
Token dropping
Feature activation-0.013
Top resid features:
what
Token what
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.014
Top resid features:
Who
TokenWho
Feature activation-0.196
Top resid features:
says
Token says
Feature activation+0.729
Top resid features:
this
Token this
Feature activation+0.044
Top resid features:
administration
Token administration
Feature activation+0.026
Top resid features:
doesn
Token doesn
Feature activation+0.352
Top resid features:
't
Token't
Feature activation+0.997
Top resid features:
get
Token get
Feature activation+0.087
Top resid features:
things
Token things
Feature activation+0.018
Top resid features:
done
Token done
Feature activation+0.002
Top resid features:
?
Token?
Feature activation+0.038
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
organizers
Token organizers
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
explore
Token explore
Feature activation+0.006
Top resid features:
their
Token their
Feature activation+0.011
Top resid features:
work
Token work
Feature activation-0.004
Top resid features:
than
Token than
Feature activation+1.653
Top resid features:
through
Token through
Feature activation-0.020
Top resid features:
writing
Token writing
Feature activation+0.081
Top resid features:
science
Token science
Feature activation+0.170
Top resid features:
fiction
Token fiction
Feature activation+0.029
Top resid features:
stories
Token stories
Feature activation+0.029
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
t
Tokent
Feature activation+0.014
Top resid features:
be
Token be
Feature activation+0.032
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
stretch
Token stretch
Feature activation+0.229
Top resid features:
to
Token to
Feature activation+1.337
Top resid features:
imagine
Token imagine
Feature activation+0.290
Top resid features:
Life
Token Life
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Strange
Token Strange
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
could
Token could
Feature activation-0.009
Top resid features:
not
Token not
Feature activation+0.058
Top resid features:
have
Token have
Feature activation+0.263
Top resid features:
done
Token done
Feature activation+0.061
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
better
Token better
Feature activation+1.283
Top resid features:
job
Token job
Feature activation+0.096
Top resid features:
.
Token.
Feature activation+0.049
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.015
Top resid features:
no
Token no
Feature activation-0.035
Top resid features:
woman
Token woman
Feature activation+0.024
Top resid features:
who
Token who
Feature activation+0.086
Top resid features:
does
Token does
Feature activation+0.076
Top resid features:
not
Token not
Feature activation+1.922
Top resid features:
support
Token support
Feature activation+0.008
Top resid features:
any
Token any
Feature activation+0.011
Top resid features:
individuals
Token individuals
Feature activation+0.009
Top resid features:
right
Token right
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.03

Head 3: 0.13

Head 4: 0.05

Head 5: 0.44

Head 6: 0.05

Head 7: 0.06

Head 8: 0.05

Head 9: 0.01

Head 10: 0.02

Head 11: 0.07

Positive logits

2.60

incredible2.55

amazing2.45

gorgeous2.42

astounding2.34

Congratulations2.34

adorable2.32

fascinating2.29

unparalleled2.29

delightful2.28

marvelous2.25

phenomenal2.17

unforgettable2.13

wonderfully2.12

JUL2.09

stunning2.09

beautiful2.07

exhilar2.06

liberating2.06

delight2.04

Negative logits

anymore-4.24

nor-3.29

slightest-2.94

unless-2.73

yet-2.42

altogether-2.33

:(-2.33

necessarily-2.26

Pastebin-2.26

None-2.26

hesitate-2.25

too-2.25

mere-2.24

qus-2.24

ventional-2.24

ocr-2.19

anything-2.19

lacks-2.15

errors-2.15

Sorry-2.14

INTERVAL 2.682 - 2.981
CONTAINS 0.000%

could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
clearer
Token clearer
Feature activation+0.650
.
Token.
Feature activation+2.981
Ċ
TokenĊ
Feature activation+0.992
Ċ
TokenĊ
Feature activation+1.338
Ret
TokenRet
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
spect
Tokenspect
Feature activation+0.000

INTERVAL 2.384 - 2.682
CONTAINS 0.000%

INTERVAL 2.086 - 2.384
CONTAINS 0.000%

have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
more
Token more
Feature activation+0.742
right
Token right
Feature activation+0.126
.
Token.
Feature activation+1.856
But
Token But
Feature activation+2.170
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
until
Token until
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
short
Token short
Feature activation+0.000
of
Token of
Feature activation+2.377
perfect
Token perfect
Feature activation+1.173
.
Token.
Feature activation+0.215
A
Token A
Feature activation+0.000
crew
Token crew
Feature activation+0.000
had
Token had
Feature activation+0.000

INTERVAL 1.788 - 2.086
CONTAINS 0.000%

't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
more
Token more
Feature activation+0.742
right
Token right
Feature activation+0.126
.
Token.
Feature activation+1.856
But
Token But
Feature activation+2.170
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
intent
Token intent
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
clearer
Token clearer
Feature activation+0.156
:
Token:
Feature activation+1.911
the
Token the
Feature activation+0.592
state
Token state
Feature activation+0.000
should
Token should
Feature activation+0.463
suppress
Token suppress
Feature activation+0.000
any
Token any
Feature activation+0.000
for
Token for
Feature activation+0.598
the
Token the
Feature activation+0.329
involvement
Token involvement
Feature activation+0.000
of
Token of
Feature activation+0.352
China
Token China
Feature activation+0.051
.
Token.
Feature activation+2.063
Ċ
TokenĊ
Feature activation+1.174
Ċ
TokenĊ
Feature activation+0.921
Chinese
TokenChinese
Feature activation+0.000
'
Token '
Feature activation+0.000
arm
Tokenarm
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
ignore
Token ignore
Feature activation+0.039
.
Token.
Feature activation+1.792
Ċ
TokenĊ
Feature activation+0.804
Ċ
TokenĊ
Feature activation+0.084
I
TokenI
Feature activation+0.190
know
Token know
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 1.490 - 1.788
CONTAINS 0.001%

maintenance
Token maintenance
Feature activation+0.508
of
Token of
Feature activation+1.057
our
Token our
Feature activation+0.479
living
Token living
Feature activation+0.000
environment
Token environment
Feature activation+1.197
.
Token.
Feature activation+1.662
Science
Token Science
Feature activation+0.000
cannot
Token cannot
Feature activation+0.103
fully
Token fully
Feature activation+0.028
mitigate
Token mitigate
Feature activation+0.087
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
unfamiliar
Token unfamiliar
Feature activation+0.090
.
Token.
Feature activation+1.724
Likely
Token Likely
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
to
Token to
Feature activation+1.602
have
Token have
Feature activation+0.977
a
Token a
Feature activation+1.079
good
Token good
Feature activation+0.759
season
Token season
Feature activation+0.158
.
Token.
Feature activation+1.662
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
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
difficult
Token difficult
Feature activation+0.005
subject
Token subject
Feature activation+0.095
?
Token?
Feature activation+1.560
I
Token I
Feature activation+0.972
certainly
Token certainly
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.365
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.080
get
Token get
Feature activation+0.836
things
Token things
Feature activation+0.051
done
Token done
Feature activation+1.001
?
Token?
Feature activation+1.534
Ċ
TokenĊ
Feature activation+0.915
Ċ
TokenĊ
Feature activation+0.881
What
TokenWhat
Feature activation+0.000
we
Token we
Feature activation+0.016
need
Token need
Feature activation+0.000

INTERVAL 1.192 - 1.490
CONTAINS 0.003%

been
Token been
Feature activation+0.000
down
Token down
Feature activation+0.000
that
Token that
Feature activation+0.000
road
Token road
Feature activation+0.000
before
Token before
Feature activation+0.000
.
Token.
Feature activation+1.451
Ċ
TokenĊ
Feature activation+0.371
Ċ
TokenĊ
Feature activation+0.316
So
TokenSo
Feature activation+0.222
what
Token what
Feature activation+0.000
happens
Token happens
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
thrive
Token thrive
Feature activation+0.000
in
Token in
Feature activation+0.000
peace
Token peace
Feature activation+0.000
.
Token.
Feature activation+1.286
Everybody
Token Everybody
Feature activation+0.000
must
Token must
Feature activation+0.000
have
Token have
Feature activation+0.000
equal
Token equal
Feature activation+0.000
access
Token access
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
ever
Token ever
Feature activation+0.000
disappoint
Token disappoint
Feature activation+0.000
.
Token.
Feature activation+1.197
Below
Token Below
Feature activation+0.208
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
ones
Token ones
Feature activation+0.000
who
Token who
Feature activation+0.000
created
Token created
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+1.247
With
Token With
Feature activation+0.188
Sony
Token Sony
Feature activation+0.000
re
Token re
Feature activation+0.000
aping
Tokenaping
Feature activation+0.000
the
Token the
Feature activation+0.000
't
Token't
Feature activation+0.000
made
Token made
Feature activation+0.456
this
Token this
Feature activation+0.506
call
Token call
Feature activation+0.260
before
Token before
Feature activation+0.000
-
Token -
Feature activation+1.345
when
Token when
Feature activation+1.015
they
Token they
Feature activation+0.218
routinely
Token routinely
Feature activation+0.050
called
Token called
Feature activation+0.051
water
Token water
Feature activation+0.000

INTERVAL 0.894 - 1.192
CONTAINS 0.008%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+1.040
humble
Token humble
Feature activation+1.136
person
Token person
Feature activation+0.930
to
Token to
Feature activation+0.403
speak
Token speak
Feature activation+0.662
with
Token with
Feature activation+0.493
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
findings
Token findings
Feature activation+0.000
or
Token or
Feature activation+0.000
data
Token data
Feature activation+0.000
.
Token.
Feature activation+1.004
In
Token In
Feature activation+0.123
other
Token other
Feature activation+0.000
words
Token words
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ever
Token ever
Feature activation+0.082
trying
Token trying
Feature activation+0.625
one
Token one
Feature activation+0.086
of
Token of
Feature activation+0.242
the
Token the
Feature activation+0.032
most
Token most
Feature activation+1.040
delicious
Token delicious
Feature activation+0.478
cakes
Token cakes
Feature activation+0.181
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
planet
Token planet
Feature activation+0.250
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
stress
Token stress
Feature activation+0.000
enough
Token enough
Feature activation+0.236
how
Token how
Feature activation+0.941
much
Token much
Feature activation+0.443
more
Token more
Feature activation+0.468
effective
Token effective
Feature activation+0.328
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
advancement
Token advancement
Feature activation+0.000
,
Token,
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
seems
Token seems
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
.
Token.
Feature activation+1.092
People
Token People
Feature activation+0.576
can
Token can
Feature activation+0.281
get
Token get
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
features
Token features
Feature activation+0.000

INTERVAL 0.596 - 0.894
CONTAINS 0.018%

re
Tokenre
Feature activation+0.000
not
Token not
Feature activation+0.699
exposed
Token exposed
Feature activation+0.124
to
Token to
Feature activation+0.031
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.790
After
Token After
Feature activation+0.245
harvest
Token harvest
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
great
Token great
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
overly
Token overly
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.512
you
Token you
Feature activation+0.603
just
Token just
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
honest
Token honest
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
partners
Token partners
Feature activation+0.000
than
Token than
Feature activation+0.652
people
Token people
Feature activation+0.914
of
Token of
Feature activation+0.137
other
Token other
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
orient
Token orient
Feature activation+0.000
to
Token to
Feature activation+0.217
the
Token the
Feature activation+0.000
scale
Token scale
Feature activation+0.000
of
Token of
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
.
Token.
Feature activation+0.666
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
where
Token where
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
lost
Token lost
Feature activation+0.000
on
Token on
Feature activation+0.000
Marx
Token Marx
Feature activation+0.000
.
Token.
Feature activation+0.668
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.244
Eth
Token Eth
Feature activation+0.000
n
Tokenn
Feature activation+0.000

INTERVAL 0.298 - 0.596
CONTAINS 0.051%

a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
nonsense
Token nonsense
Feature activation+0.124
âĢĶ
TokenâĢĶ
Feature activation+0.353
they
Tokenthey
Feature activation+0.458
have
Token have
Feature activation+0.327
guns
Token guns
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.672
that
Token that
Feature activation+0.320
St
Token St
Feature activation+0.000
P
Token P
Feature activation+0.000
addy
Tokenaddy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.334
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
trying
Token trying
Feature activation+0.000
too
Token too
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.168
however
Token however
Feature activation+0.074
.
Token.
Feature activation+0.328
The
Token The
Feature activation+0.215
measurement
Token measurement
Feature activation+0.000
of
Token of
Feature activation+0.000
polarization
Token polarization
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
prepared
Token prepared
Feature activation+0.006
than
Token than
Feature activation+0.067
your
Token your
Feature activation+0.000
opponent
Token opponent
Feature activation+0.000
.
Token.
Feature activation+0.401
After
Token After
Feature activation+0.000
seven
Token seven
Feature activation+0.000
conference
Token conference
Feature activation+0.000
titles
Token titles
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 0.298
CONTAINS 99.919%

under
Token under
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
vit
Token vit
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
important
Token important
Feature activation+0.000
for
Token for
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
a
Token a
Feature activation+0.000
crime
Token crime
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
:
Token:
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
206
Token 206
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
80
Token 80
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
expanding
Token expanding
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
a
Token a
Feature activation+0.000
standard
Token standard
Feature activation+0.000
said
Token said
Feature activation+0.000
Wells
Token Wells
Feature activation+0.000
Fargo
Token Fargo
Feature activation+0.000
&
Token &
Feature activation+0.000
Co
Token Co
Feature activation+0.000
and
Token and
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
B
Token B
Feature activation+0.000
tied
Token tied
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
stret
Token stret
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
and
Token and
Feature activation+0.000
transported
Token transported
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H6.5: (feature 17956)

TOP ACTIVATIONS
MAX = 5.808

pounds
Token pounds
Feature activation+0.000
of
Token of
Feature activation+0.000
explosive
Token explosive
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.976
Ċ
TokenĊ
Feature activation+5.808
He
TokenHe
Feature activation+0.000
added
Token added
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Like
TokenLike
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
before
Token before
Feature activation+0.000
1972
Token 1972
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.526
Ċ
TokenĊ
Feature activation+4.305
The
TokenThe
Feature activation+0.000
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
top
Token top
Feature activation+0.000
so
Tokenso
Feature activation+0.000
il
Tokenil
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.620
Ċ
TokenĊ
Feature activation+4.072
"
Token"
Feature activation+0.000
D
TokenD
Feature activation+0.000
eeper
Tokeneeper
Feature activation+0.000
soil
Token soil
Feature activation+0.000
layers
Token layers
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
or
Token or
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.949
Ċ
TokenĊ
Feature activation+4.014
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
desire
Token desire
Feature activation+0.000
even
Token even
Feature activation+0.000
someone
Token someone
Feature activation+0.000
taller
Token taller
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.731
Ċ
TokenĊ
Feature activation+4.006
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.751
I
TokenI
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
its
Token its
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
range
Token range
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.892
I
TokenI
Feature activation+0.000
gave
Token gave
Feature activation+0.000
the
Token the
Feature activation+0.000
Naval
Token Naval
Feature activation+0.000
Air
Token Air
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
radar
Token radar
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.883
Ċ
TokenĊ
Feature activation+3.740
Photo
TokenPhoto
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
addition
Token addition
Feature activation+0.000
the
Token the
Feature activation+0.000
governing
Token governing
Feature activation+0.000
coalition
Token coalition
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.544
Ċ
TokenĊ
Feature activation+3.729
When
TokenWhen
Feature activation+0.000
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
polling
Token polling
Feature activation+0.000
booth
Token booth
Feature activation+0.000
our
Token our
Feature activation+0.000
height
Token height
Feature activation+0.000
difference
Token difference
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.959
Ċ
TokenĊ
Feature activation+3.665
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.575
But
TokenBut
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.575
Ċ
TokenĊ
Feature activation+3.630
By
TokenBy
Feature activation+0.000
all
Token all
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.449
Ph
TokenPh
Feature activation+0.000
oe
Tokenoe
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
Anne
Token Anne
Feature activation+0.000
Moses
Token Moses
Feature activation+0.000
in
Token in
Feature activation+0.000
American
Token American
Feature activation+0.000
history
Token history
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.526
Ċ
TokenĊ
Feature activation+2.778
The
TokenThe
Feature activation+0.000
ball
Token ball
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Death
Token Death
Feature activation+0.000
Star
Token Star
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.313
Ċ
TokenĊ
Feature activation+2.645
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.525
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
design
Token design
Feature activation+0.000
goals
Token goals
Feature activation+0.000
were
Token were
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.562
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
admitted
Token admitted
Feature activation+0.000
,
Token,
Feature activation+0.000
laughing
Token laughing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.516
Marvel
TokenMarvel
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
focus
Token focus
Feature activation+0.000
,
Token,
Feature activation+0.000
restart
Token restart
Feature activation+0.000
your
Token your
Feature activation+0.000
phone
Token phone
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.316
Ċ
TokenĊ
Feature activation+2.413
I
TokenI
Feature activation+0.000
could
Token could
Feature activation+0.000
see
Token see
Feature activation+0.000
that
Token that
Feature activation+0.000
being
Token being
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
delayed
Token delayed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.071
Ċ
TokenĊ
Feature activation+2.228
Despite
TokenDespite
Feature activation+0.000
their
Token their
Feature activation+0.000
small
Token small
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
,
Token,
Feature activation+0.000
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.129
China
TokenChina
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
system
Token system
Feature activation+0.000
electric
Tokenelectric
Feature activation+0.000
power
Token power
Feature activation+0.000
plants
Token plants
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.077
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.642
It
TokenIt
Feature activation+0.000
may
Token may
Feature activation+0.000
000
Token000
Feature activation+0.000
pounds
Token pounds
Feature activation+0.000
of
Token of
Feature activation+0.000
explosive
Token explosive
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.976
Ċ
TokenĊ
Feature activation+5.808
He
TokenHe
Feature activation+0.000
added
Token added
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000

Top DFA by src position
MAX = 6.358

his
Token his
Feature activation-0.008
Top resid features:
hosts
Token hosts
Feature activation-0.021
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.067
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+6.358
Top resid features:
:
Token:
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.108
Top resid features:
Ċ
TokenĊ
Feature activation+0.171
Top resid features:
And
TokenAnd
Feature activation+0.044
Top resid features:
I
Token I
Feature activation-0.005
Top resid features:
confirm
Token confirm
Feature activation-0.004
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+5.125
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.076
Top resid features:
On
TokenOn
Feature activation-0.009
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
climate
Token climate
Feature activation+0.005
Top resid features:
change
Token change
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+4.806
Top resid features:
Ċ
TokenĊ
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.084
Top resid features:
Co
TokenCo
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
author
Tokenauthor
Feature activation+0.032
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
sad
Token sad
Feature activation+0.002
Top resid features:
."
Token."
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.040
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+5.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.072
Top resid features:
Ċ
TokenĊ
Feature activation+0.094
Top resid features:
Resp
TokenResp
Feature activation+0.027
Top resid features:
onding
Tokenonding
Feature activation+0.011
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
height
Token height
Feature activation+0.011
Top resid features:
difference
Token difference
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+3.516
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
Ċ
TokenĊ
Feature activation+0.085
Top resid features:
But
TokenBut
Feature activation+0.007
Top resid features:
that
Token that
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.779
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+4.449
Top resid features:
Ċ
TokenĊ
Feature activation+0.070
Top resid features:
Ċ
TokenĊ
Feature activation+0.071
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
testing
Token testing
Feature activation+0.006
Top resid features:
will
Token will
Feature activation+0.039
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+4.472
Top resid features:
Continue
Token Continue
Feature activation+0.113
Top resid features:
reading
Token reading
Feature activation+0.068
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
main
Token main
Feature activation+0.005
Top resid features:
story
Token story
Feature activation+0.010
Top resid features:
their
Token their
Feature activation+0.003
Top resid features:
district
Token district
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+2.252
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
Ċ
TokenĊ
Feature activation+0.108
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+1.832
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.071
Top resid features:
look
Token look
Feature activation-0.001
Top resid features:
taller
Token taller
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+4.365
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.087
Top resid features:
First
TokenFirst
Feature activation-0.021
Top resid features:
we
Token we
Feature activation-0.058
Top resid features:
started
Token started
Feature activation-0.028
Top resid features:
10
Token 10
Feature activation+0.002
Top resid features:
Republicans
Token Republicans
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+4.158
Top resid features:
Continue
Token Continue
Feature activation+0.181
Top resid features:
reading
Token reading
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
main
Token main
Feature activation+0.004
Top resid features:
story
Token story
Feature activation+0.006
Top resid features:
Shot
TokenShot
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ŀ
TokenĿ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.091
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+3.790
Top resid features:
for
Token for
Feature activation+0.073
Top resid features:
Buffalo
Token Buffalo
Feature activation+0.007
Top resid features:
Bill
Token Bill
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
information
Token information
Feature activation+0.006
Top resid features:
safe
Token safe
Feature activation+0.002
Top resid features:
?
Token?
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.056
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+3.537
Top resid features:
Ċ
TokenĊ
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.080
Top resid features:
The
TokenThe
Feature activation+0.008
Top resid features:
horror
Token horror
Feature activation+0.006
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
lair
Token lair
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+1.122
Top resid features:
Ċ
TokenĊ
Feature activation+0.094
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+0.670
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.056
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+3.814
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.062
Top resid features:
When
TokenWhen
Feature activation-0.003
Top resid features:
asked
Token asked
Feature activation-0.009
Top resid features:
about
Token about
Feature activation-0.008
Top resid features:
for
Token for
Feature activation-0.006
Top resid features:
us
Token us
Feature activation+0.001
Top resid features:
."
Token."
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+3.262
Top resid features:
Ċ
TokenĊ
Feature activation+0.087
Top resid features:
Ċ
TokenĊ
Feature activation+0.129
Top resid features:
But
TokenBut
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Wind
Token Wind
Feature activation+0.001
Top resid features:
oks
Tokenoks
Feature activation-0.002
Top resid features:
blog
Token blog
Feature activation+0.056
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+2.768
Top resid features:
Ċ
TokenĊ
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+0.082
Top resid features:
Obviously
TokenObviously
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
this
Token this
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
cash
Token cash
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.050
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+2.808
Top resid features:
Ċ
TokenĊ
Feature activation+0.080
Top resid features:
Ċ
TokenĊ
Feature activation+0.120
Top resid features:
They
TokenThey
Feature activation-0.025
Top resid features:
arrived
Token arrived
Feature activation+0.041
Top resid features:
at
Token at
Feature activation-0.007
Top resid features:
Conservation
Token Conservation
Feature activation+0.001
Top resid features:
Union
Token Union
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+2.690
Top resid features:
Continue
Token Continue
Feature activation+0.117
Top resid features:
reading
Token reading
Feature activation+0.106
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
main
Token main
Feature activation+0.005
Top resid features:
story
Token story
Feature activation+0.010
Top resid features:
Mountain
Token Mountain
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
China
Token China
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.072
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+2.641
Top resid features:
Ċ
TokenĊ
Feature activation+0.086
Top resid features:
Ċ
TokenĊ
Feature activation+0.107
Top resid features:
(
Token(
Feature activation+0.033
Top resid features:
via
Tokenvia
Feature activation+0.150
Top resid features:
ch
Token ch
Feature activation-0.003
Top resid features:
his
Token his
Feature activation-0.007
Top resid features:
hosts
Token hosts
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.106
Top resid features:
Advertisement
TokenAdvertisement
Feature activation+2.103
Top resid features:
:
Token:
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.177
Top resid features:
Ċ
TokenĊ
Feature activation+0.380
Top resid features:
And
TokenAnd
Feature activation+0.026
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.07

Head 4: 0.06

Head 5: 0.40

Head 6: 0.06

Head 7: 0.05

Head 8: 0.03

Head 9: 0.14

Head 10: 0.07

Head 11: 0.03

Positive logits

enko2.32

Painter2.31

Monstrous2.26

Analysis2.16

CU2.14

Python2.12

iba2.12

VIDEO2.09

QC2.08

mpeg2.07

Neuroscience2.07

Forensic2.06

icago2.06

etc2.05

apo2.03

Gas2.02

Detect1.96

ul1.95

Flight1.94

)),1.94

Negative logits

isSpecialOrderable-2.14

preservation-2.11

ディ-2.08

convenience-2.04

hemer-1.97

akens-1.95

discouraged-1.95

actionGroup-1.89

autions-1.88

availability-1.87

awaited-1.87

postp-1.85

loading-1.83

ocial-1.82

hower-1.80

inactive-1.79

][/-1.79

discour-1.78

placement-1.78

earances-1.78

INTERVAL 5.227 - 5.808
CONTAINS 0.000%

pounds
Token pounds
Feature activation+0.000
of
Token of
Feature activation+0.000
explosive
Token explosive
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.976
Ċ
TokenĊ
Feature activation+5.808
He
TokenHe
Feature activation+0.000
added
Token added
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Like
TokenLike
Feature activation+0.000

INTERVAL 4.646 - 5.227
CONTAINS 0.000%

INTERVAL 4.065 - 4.646
CONTAINS 0.000%

arrived
Token arrived
Feature activation+0.000
before
Token before
Feature activation+0.000
1972
Token 1972
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.526
Ċ
TokenĊ
Feature activation+4.305
The
TokenThe
Feature activation+0.000
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
top
Token top
Feature activation+0.000
so
Tokenso
Feature activation+0.000
il
Tokenil
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.620
Ċ
TokenĊ
Feature activation+4.072
"
Token"
Feature activation+0.000
D
TokenD
Feature activation+0.000
eeper
Tokeneeper
Feature activation+0.000
soil
Token soil
Feature activation+0.000
layers
Token layers
Feature activation+0.000

INTERVAL 3.485 - 4.065
CONTAINS 0.001%

its
Token its
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
range
Token range
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.892
I
TokenI
Feature activation+0.000
gave
Token gave
Feature activation+0.000
the
Token the
Feature activation+0.000
Naval
Token Naval
Feature activation+0.000
Air
Token Air
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.575
Ċ
TokenĊ
Feature activation+3.630
By
TokenBy
Feature activation+0.000
all
Token all
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
governing
Token governing
Feature activation+0.000
coalition
Token coalition
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.544
Ċ
TokenĊ
Feature activation+3.729
When
TokenWhen
Feature activation+0.000
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
polling
Token polling
Feature activation+0.000
booth
Token booth
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
radar
Token radar
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.883
Ċ
TokenĊ
Feature activation+3.740
Photo
TokenPhoto
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
addition
Token addition
Feature activation+0.000
even
Token even
Feature activation+0.000
someone
Token someone
Feature activation+0.000
taller
Token taller
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.731
Ċ
TokenĊ
Feature activation+4.006
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.751
I
TokenI
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000

INTERVAL 2.904 - 3.485
CONTAINS 0.000%

/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.449
Ph
TokenPh
Feature activation+0.000
oe
Tokenoe
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
Anne
Token Anne
Feature activation+0.000
Moses
Token Moses
Feature activation+0.000

INTERVAL 2.323 - 2.904
CONTAINS 0.001%

design
Token design
Feature activation+0.000
goals
Token goals
Feature activation+0.000
were
Token were
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.562
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
admitted
Token admitted
Feature activation+0.000
,
Token,
Feature activation+0.000
laughing
Token laughing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.516
Marvel
TokenMarvel
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
focus
Token focus
Feature activation+0.000
,
Token,
Feature activation+0.000
restart
Token restart
Feature activation+0.000
your
Token your
Feature activation+0.000
phone
Token phone
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.316
Ċ
TokenĊ
Feature activation+2.413
I
TokenI
Feature activation+0.000
could
Token could
Feature activation+0.000
see
Token see
Feature activation+0.000
that
Token that
Feature activation+0.000
being
Token being
Feature activation+0.000
in
Token in
Feature activation+0.000
American
Token American
Feature activation+0.000
history
Token history
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.526
Ċ
TokenĊ
Feature activation+2.778
The
TokenThe
Feature activation+0.000
ball
Token ball
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Death
Token Death
Feature activation+0.000
Star
Token Star
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.313
Ċ
TokenĊ
Feature activation+2.645
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.525
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.742 - 2.323
CONTAINS 0.001%

electric
Tokenelectric
Feature activation+0.000
power
Token power
Feature activation+0.000
plants
Token plants
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.077
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.642
It
TokenIt
Feature activation+0.000
may
Token may
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.731
Ċ
TokenĊ
Feature activation+4.006
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.751
I
TokenI
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
delayed
Token delayed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.071
Ċ
TokenĊ
Feature activation+2.228
Despite
TokenDespite
Feature activation+0.000
their
Token their
Feature activation+0.000
small
Token small
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
pounds
Token pounds
Feature activation+0.000
of
Token of
Feature activation+0.000
explosive
Token explosive
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.976
Ċ
TokenĊ
Feature activation+5.808
He
TokenHe
Feature activation+0.000
added
Token added
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.841
The
TokenThe
Feature activation+0.000
drawing
Token drawing
Feature activation+0.000
of
Token of
Feature activation+0.000
Theresa
Token Theresa
Feature activation+0.000
May
Token May
Feature activation+0.000

INTERVAL 1.162 - 1.742
CONTAINS 0.001%

Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.405
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.400
Romney
TokenRomney
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.959
Ċ
TokenĊ
Feature activation+3.665
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.575
But
TokenBut
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
easy
Token easy
Feature activation+0.000
mode
Token mode
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
menu
Token menu
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.547
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Can
TokenCan
Feature activation+0.000
you
Token you
Feature activation+0.000
put
Token put
Feature activation+0.000
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
union
Token union
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.403
Ireland
TokenIreland
Feature activation+0.000
lead
Token lead
Feature activation+0.000
at
Token at
Feature activation+0.000
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.551
From
TokenFrom
Feature activation+0.000
the
Token the
Feature activation+0.000
start
Token start
Feature activation+0.000
of
Token of
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000

INTERVAL 0.581 - 1.162
CONTAINS 0.003%

or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
someone
Token someone
Feature activation+0.000
taller
Token taller
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.731
Ċ
TokenĊ
Feature activation+4.006
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.751
I
TokenI
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+0.680
Click
TokenClick
Feature activation+0.000
or
Token or
Feature activation+0.000
tap
Token tap
Feature activation+0.000
here
Token here
Feature activation+0.000
to
Token to
Feature activation+0.000
der
Tokender
Feature activation+0.000
y
Tokeny
Feature activation+0.000
asked
Token asked
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.082
Mark
TokenMark
Feature activation+0.000
St
Token St
Feature activation+0.000
ott
Tokenott
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
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
Ċ
TokenĊ
Feature activation+0.685
But
TokenBut
Feature activation+0.000
others
Token others
Feature activation+0.000
were
Token were
Feature activation+0.000
asking
Token asking
Feature activation+0.000
after
Token after
Feature activation+0.000
in
Token in
Feature activation+0.000
top
Token top
Feature activation+0.000
so
Tokenso
Feature activation+0.000
il
Tokenil
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.620
Ċ
TokenĊ
Feature activation+4.072
"
Token"
Feature activation+0.000
D
TokenD
Feature activation+0.000
eeper
Tokeneeper
Feature activation+0.000
soil
Token soil
Feature activation+0.000

INTERVAL 0.000 - 0.581
CONTAINS 99.993%

can
Token can
Feature activation+0.000
promise
Token promise
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
sue
Token sue
Feature activation+0.000
any
Token any
Feature activation+0.000
Cube
Token Cube
Feature activation+0.000
users
Token users
Feature activation+0.000
who
Token who
Feature activation+0.000
use
Token use
Feature activation+0.000
non
Token non
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
true
Token true
Feature activation+0.000
son
Token son
Feature activation+0.000
of
Token of
Feature activation+0.000
Mother
Token Mother
Feature activation+0.000
India
Token India
Feature activation+0.000
and
Token and
Feature activation+0.000
inspiration
Token inspiration
Feature activation+0.000
for
Token for
Feature activation+0.000
symbols
Token symbols
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
shared
Token shared
Feature activation+0.000
object
Token object
Feature activation+0.000
file
Token file
Feature activation+0.000
right
Token right
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
first
Token first
Feature activation+0.000
*
Token *
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Jaguars
Token Jaguars
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
second
Token second
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
cornerback
Token cornerback
Feature activation+0.000
missed
Token missed
Feature activation+0.000
all
Token all
Feature activation+0.000
lands
Token lands
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
on
Token on
Feature activation+0.000
par
Token par
Feature activation+0.000
with
Token with
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.000
far
Token far
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H6.5: (feature 9571)

TOP ACTIVATIONS
MAX = 2.121

Good
Token Good
Feature activation+0.000
hart
Tokenhart
Feature activation+0.000
,
Token,
Feature activation+0.550
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.120
what
Tokenwhat
Feature activation+2.121
is
Token is
Feature activation+0.753
now
Token now
Feature activation+0.589
likely
Token likely
Feature activation+0.061
is
Token is
Feature activation+0.679
that
Token that
Feature activation+0.000
J
TokenJ
Feature activation+0.000
.
Token.
Feature activation+0.450
âĢ
Token âĢ
Feature activation+0.693
ľ
Tokenľ
Feature activation+0.773
GE
TokenGE
Feature activation+0.499
wants
Token wants
Feature activation+1.795
to
Token to
Feature activation+1.449
tap
Token tap
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
branding
Token branding
Feature activation+0.000
M
TokenM
Feature activation+0.000
urch
Tokenurch
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.232
ľ
Tokenľ
Feature activation+1.608
we
Tokenwe
Feature activation+0.915
can
Token can
Feature activation+0.976
just
Token just
Feature activation+0.398
say
Token say
Feature activation+0.000
there
Token there
Feature activation+0.000
the
Token the
Feature activation+0.000
Spiritual
Token Spiritual
Feature activation+0.000
Capital
Token Capital
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
,
Token,
Feature activation+0.333
âĢ
Token âĢ
Feature activation+1.525
ľ
Tokenľ
Feature activation+0.910
Ian
TokenIan
Feature activation+0.786
is
Token is
Feature activation+0.895
an
Token an
Feature activation+0.286
extraordinarily
Token extraordinarily
Feature activation+0.087
.
Token.
Feature activation+0.450
âĢ
Token âĢ
Feature activation+0.693
ľ
Tokenľ
Feature activation+0.773
GE
TokenGE
Feature activation+0.499
wants
Token wants
Feature activation+1.795
to
Token to
Feature activation+1.449
tap
Token tap
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
branding
Token branding
Feature activation+0.000
element
Token element
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
David
Token David
Feature activation+0.000
Or
Token Or
Feature activation+0.000
ban
Tokenban
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+1.375
DA
Token DA
Feature activation+0.009
O
TokenO
Feature activation+0.000
can
Token can
Feature activation+0.378
be
Token be
Feature activation+0.325
a
Token a
Feature activation+0.095
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
Rudy
Token Rudy
Feature activation+0.000
Giuliani
Token Giuliani
Feature activation+0.000
,
Token,
Feature activation+1.000
is
Token is
Feature activation+1.364
smart
Token smart
Feature activation+0.737
.
Token.
Feature activation+0.045
He
Token He
Feature activation+0.211
end
Token end
Feature activation+0.000
orses
Tokenorses
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
Cardinal
Token Cardinal
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.355
ľ
Tokenľ
Feature activation+0.623
to
Tokento
Feature activation+0.000
give
Token give
Feature activation+0.000
their
Token their
Feature activation+0.000
delegates
Token delegates
Feature activation+0.000
tells
Token tells
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
Ah
Token Ah
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
,
Token,
Feature activation+0.630
the
Token the
Feature activation+1.347
stage
Token stage
Feature activation+0.159
has
Token has
Feature activation+0.437
given
Token given
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
Nort
Token Nort
Feature activation+0.000
je
Tokenje
Feature activation+0.000
,
Token,
Feature activation+0.000
26
Token 26
Feature activation+0.000
,
Token,
Feature activation+0.000
Mrs
Token Mrs
Feature activation+1.321
Pot
Token Pot
Feature activation+0.070
g
Tokeng
Feature activation+0.000
iet
Tokeniet
Feature activation+0.000
er
Tokener
Feature activation+0.266
's
Token's
Feature activation+0.135
Capt
Token Capt
Feature activation+0.000
.
Token.
Feature activation+0.000
Tommy
Token Tommy
Feature activation+0.000
Simmons
Token Simmons
Feature activation+0.000
,
Token,
Feature activation+0.000
Keller
Token Keller
Feature activation+1.301
âĢ
TokenâĢ
Feature activation+0.921
Ļ
TokenĻ
Feature activation+0.425
s
Tokens
Feature activation+0.244
patrol
Token patrol
Feature activation+0.007
commander
Token commander
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Mart
Token Mart
Feature activation+0.000
inelli
Tokeninelli
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.238
ľ
Tokenľ
Feature activation+1.186
that
Tokenthat
Feature activation+0.952
person
Token person
Feature activation+0.035
can
Token can
Feature activation+0.000
continue
Token continue
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
M
TokenM
Feature activation+0.000
urch
Tokenurch
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.232
ľ
Tokenľ
Feature activation+1.608
we
Tokenwe
Feature activation+0.915
can
Token can
Feature activation+0.976
just
Token just
Feature activation+0.398
say
Token say
Feature activation+0.000
said
Token said
Feature activation+0.000
Mart
Token Mart
Feature activation+0.000
inelli
Tokeninelli
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.238
ľ
Tokenľ
Feature activation+1.186
that
Tokenthat
Feature activation+0.952
person
Token person
Feature activation+0.035
can
Token can
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
said
Token said
Feature activation+0.000
Good
Token Good
Feature activation+0.000
hart
Tokenhart
Feature activation+0.000
,
Token,
Feature activation+0.550
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.120
what
Tokenwhat
Feature activation+2.121
is
Token is
Feature activation+0.753
now
Token now
Feature activation+0.589
likely
Token likely
Feature activation+0.061
is
Token is
Feature activation+0.679
il
Tokenil
Feature activation+0.000
f
Tokenf
Feature activation+0.000
oyle
Tokenoyle
Feature activation+0.000
,
Token,
Feature activation+0.000
striking
Token striking
Feature activation+1.057
a
Token a
Feature activation+1.118
familiar
Token familiar
Feature activation+0.594
gun
Token gun
Feature activation+0.528
-
Token-
Feature activation+0.000
rights
Tokenrights
Feature activation+0.000
talking
Token talking
Feature activation+0.000
Gu
Token Gu
Feature activation+0.000
il
Tokenil
Feature activation+0.000
f
Tokenf
Feature activation+0.000
oyle
Tokenoyle
Feature activation+0.000
,
Token,
Feature activation+0.000
striking
Token striking
Feature activation+1.057
a
Token a
Feature activation+1.118
familiar
Token familiar
Feature activation+0.594
gun
Token gun
Feature activation+0.528
-
Token-
Feature activation+0.000
rights
Tokenrights
Feature activation+0.000
ali
Tokenali
Feature activation+0.000
B
Token B
Feature activation+0.000
raw
Tokenraw
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.651
now
Token now
Feature activation+1.030
CEO
Token CEO
Feature activation+0.086
of
Token of
Feature activation+0.040
the
Token the
Feature activation+0.000
Spiritual
Token Spiritual
Feature activation+0.000
Capital
Token Capital
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
Rudy
Token Rudy
Feature activation+0.000
Giuliani
Token Giuliani
Feature activation+0.000
,
Token,
Feature activation+1.000
is
Token is
Feature activation+1.364
smart
Token smart
Feature activation+0.737
.
Token.
Feature activation+0.045
He
Token He
Feature activation+0.211
end
Token end
Feature activation+0.000
at
Token at
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.000
hypothes
Token hypothes
Feature activation+0.979
izes
Tokenizes
Feature activation+0.868
that
Token that
Feature activation+0.235
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
I
Token I
Feature activation+0.000

Top DFA by src position
MAX = 2.266

but
Token but
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.089
Top resid features:
said
Token said
Feature activation+0.059
Top resid features:
Good
Token Good
Feature activation+0.022
Top resid features:
hart
Tokenhart
Feature activation+0.122
Top resid features:
,
Token,
Feature activation+2.266
Top resid features:
âĢ
Token âĢ
Feature activation+0.097
Top resid features:
ľ
Tokenľ
Feature activation+0.076
Top resid features:
what
Tokenwhat
Feature activation+0.016
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.002
Top resid features:
said
Token said
Feature activation-0.011
Top resid features:
John
Token John
Feature activation+0.013
Top resid features:
Boyd
Token Boyd
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+1.614
Top resid features:
a
Token a
Feature activation+0.296
Top resid features:
relocation
Token relocation
Feature activation+0.037
Top resid features:
consultant
Token consultant
Feature activation-0.028
Top resid features:
based
Token based
Feature activation+0.045
Top resid features:
in
Token in
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
M
TokenM
Feature activation-0.001
Top resid features:
urch
Tokenurch
Feature activation+0.001
Top resid features:
u
Tokenu
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+1.969
Top resid features:
âĢ
Token âĢ
Feature activation+0.175
Top resid features:
ľ
Tokenľ
Feature activation-0.019
Top resid features:
we
Tokenwe
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
ft
Tokenft
Feature activation-0.003
Top resid features:
ali
Tokenali
Feature activation+0.001
Top resid features:
B
Token B
Feature activation+0.010
Top resid features:
raw
Tokenraw
Feature activation-0.002
Top resid features:
er
Tokener
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.935
Top resid features:
now
Token now
Feature activation+0.122
Top resid features:
CEO
Token CEO
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Spiritual
Token Spiritual
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.003
Top resid features:
John
Token John
Feature activation+0.003
Top resid features:
Boyd
Token Boyd
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+1.520
Top resid features:
a
Token a
Feature activation+0.278
Top resid features:
relocation
Token relocation
Feature activation+0.040
Top resid features:
consultant
Token consultant
Feature activation-0.015
Top resid features:
based
Token based
Feature activation+0.026
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
ur
Tokenur
Feature activation-0.000
Top resid features:
ist
Tokenist
Feature activation+0.043
Top resid features:
David
Token David
Feature activation+0.015
Top resid features:
Or
Token Or
Feature activation+0.033
Top resid features:
ban
Tokenban
Feature activation+0.059
Top resid features:
,
Token,
Feature activation+1.942
Top resid features:
The
Token The
Feature activation+0.022
Top resid features:
DA
Token DA
Feature activation+0.000
Top resid features:
O
TokenO
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
ure
Tokenure
Feature activation+0.068
Top resid features:
,
Token,
Feature activation-0.360
Top resid features:
says
Token says
Feature activation+0.109
Top resid features:
Rudy
Token Rudy
Feature activation+0.125
Top resid features:
Giuliani
Token Giuliani
Feature activation+0.136
Top resid features:
,
Token,
Feature activation+2.068
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
smart
Token smart
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
further
Token further
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
said
Token said
Feature activation-0.015
Top resid features:
the
Token the
Feature activation+0.147
Top resid features:
Cardinal
Token Cardinal
Feature activation-0.018
Top resid features:
,
Token,
Feature activation+2.103
Top resid features:
âĢ
Token âĢ
Feature activation+0.032
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
to
Tokento
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.001
Top resid features:
tells
Token tells
Feature activation+0.075
Top resid features:
Nick
Token Nick
Feature activation+0.049
Top resid features:
Ah
Token Ah
Feature activation+0.029
Top resid features:
ad
Tokenad
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+1.459
Top resid features:
the
Token the
Feature activation+0.275
Top resid features:
stage
Token stage
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
given
Token given
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.001
Top resid features:
said
Token said
Feature activation-0.007
Top resid features:
Susan
Token Susan
Feature activation-0.018
Top resid features:
Nort
Token Nort
Feature activation+0.034
Top resid features:
je
Tokenje
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.829
Top resid features:
26
Token 26
Feature activation+0.206
Top resid features:
,
Token,
Feature activation+0.706
Top resid features:
Mrs
Token Mrs
Feature activation-0.032
Top resid features:
Pot
Token Pot
Feature activation+0.000
Top resid features:
g
Tokeng
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.034
Top resid features:
Capt
Token Capt
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Tommy
Token Tommy
Feature activation+0.029
Top resid features:
Simmons
Token Simmons
Feature activation+0.190
Top resid features:
,
Token,
Feature activation+1.730
Top resid features:
Keller
Token Keller
Feature activation-0.060
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
patrol
Token patrol
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.022
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
said
Token said
Feature activation+0.097
Top resid features:
Mart
Token Mart
Feature activation+0.031
Top resid features:
inelli
Tokeninelli
Feature activation+0.305
Top resid features:
,
Token,
Feature activation+1.590
Top resid features:
âĢ
Token âĢ
Feature activation+0.072
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
that
Tokenthat
Feature activation+0.000
Top resid features:
person
Token person
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
M
TokenM
Feature activation+0.016
Top resid features:
urch
Tokenurch
Feature activation+0.001
Top resid features:
u
Tokenu
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+1.621
Top resid features:
âĢ
Token âĢ
Feature activation+0.074
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
we
Tokenwe
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.059
Top resid features:
Ŀ
TokenĿ
Feature activation-0.008
Top resid features:
said
Token said
Feature activation+0.104
Top resid features:
Mart
Token Mart
Feature activation+0.015
Top resid features:
inelli
Tokeninelli
Feature activation+0.210
Top resid features:
,
Token,
Feature activation+1.532
Top resid features:
âĢ
Token âĢ
Feature activation+0.136
Top resid features:
ľ
Tokenľ
Feature activation-0.064
Top resid features:
that
Tokenthat
Feature activation+0.000
Top resid features:
person
Token person
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
but
Token but
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
said
Token said
Feature activation+0.045
Top resid features:
Good
Token Good
Feature activation+0.036
Top resid features:
hart
Tokenhart
Feature activation+0.153
Top resid features:
,
Token,
Feature activation+1.313
Top resid features:
âĢ
Token âĢ
Feature activation+0.094
Top resid features:
ľ
Tokenľ
Feature activation-0.014
Top resid features:
what
Tokenwhat
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
Kimberly
Token Kimberly
Feature activation+0.005
Top resid features:
Gu
Token Gu
Feature activation+0.017
Top resid features:
il
Tokenil
Feature activation-0.018
Top resid features:
f
Tokenf
Feature activation+0.001
Top resid features:
oyle
Tokenoyle
Feature activation+0.059
Top resid features:
,
Token,
Feature activation+1.263
Top resid features:
striking
Token striking
Feature activation+0.191
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
familiar
Token familiar
Feature activation+0.000
Top resid features:
gun
Token gun
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Kimberly
Token Kimberly
Feature activation+0.014
Top resid features:
Gu
Token Gu
Feature activation+0.012
Top resid features:
il
Tokenil
Feature activation-0.017
Top resid features:
f
Tokenf
Feature activation-0.007
Top resid features:
oyle
Tokenoyle
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+1.322
Top resid features:
striking
Token striking
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
familiar
Token familiar
Feature activation+0.000
Top resid features:
gun
Token gun
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
ft
Tokenft
Feature activation-0.002
Top resid features:
ali
Tokenali
Feature activation-0.003
Top resid features:
B
Token B
Feature activation+0.006
Top resid features:
raw
Tokenraw
Feature activation+0.001
Top resid features:
er
Tokener
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+1.470
Top resid features:
now
Token now
Feature activation+0.028
Top resid features:
CEO
Token CEO
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Spiritual
Token Spiritual
Feature activation+0.000
Top resid features:
ure
Tokenure
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.256
Top resid features:
says
Token says
Feature activation+0.024
Top resid features:
Rudy
Token Rudy
Feature activation+0.095
Top resid features:
Giuliani
Token Giuliani
Feature activation+0.183
Top resid features:
,
Token,
Feature activation+1.661
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
smart
Token smart
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
study
Token study
Feature activation+0.065
Top resid features:
co
Token co
Feature activation+0.009
Top resid features:
author
Tokenauthor
Feature activation-0.013
Top resid features:
Peter
Token Peter
Feature activation-0.006
Top resid features:
Gibson
Token Gibson
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.479
Top resid features:
a
Token a
Feature activation+0.155
Top resid features:
gastro
Token gastro
Feature activation+0.012
Top resid features:
enter
Tokenenter
Feature activation+0.002
Top resid features:
ologist
Tokenologist
Feature activation+0.027
Top resid features:
at
Token at
Feature activation+0.096
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.02

Head 2: 0.04

Head 3: 0.05

Head 4: 0.05

Head 5: 0.40

Head 6: 0.03

Head 7: 0.05

Head 8: 0.08

Head 9: 0.03

Head 10: 0.02

Head 11: 0.13

Positive logits

societies2.25

"[2.05

"…1.91

society1.88

"[1.82

civilizations1.81

governments1.80

".1.73

"...1.73

cos1.71

cause1.71

factors1.70

olson1.68

compounds1.67

Governments1.66

inevitably1.66

societal1.64

smugglers1.62

ifact1.62

Cause1.61

Negative logits

uty-2.08

(@-1.88

extraord-1.85

essor-1.77

Panzer-1.75

joining-1.73

newcom-1.71

ofer-1.71

dexter-1.68

helm-1.66

peg-1.61

Winged-1.61

Fenrir-1.60

rone-1.59

proudly-1.57

istle-1.56

)'-1.56

Slot-1.56

ported-1.52

umn-1.52

INTERVAL 1.909 - 2.121
CONTAINS 0.000%

Good
Token Good
Feature activation+0.000
hart
Tokenhart
Feature activation+0.000
,
Token,
Feature activation+0.550
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.120
what
Tokenwhat
Feature activation+2.121
is
Token is
Feature activation+0.753
now
Token now
Feature activation+0.589
likely
Token likely
Feature activation+0.061
is
Token is
Feature activation+0.679
that
Token that
Feature activation+0.000

INTERVAL 1.697 - 1.909
CONTAINS 0.000%

J
TokenJ
Feature activation+0.000
.
Token.
Feature activation+0.450
âĢ
Token âĢ
Feature activation+0.693
ľ
Tokenľ
Feature activation+0.773
GE
TokenGE
Feature activation+0.499
wants
Token wants
Feature activation+1.795
to
Token to
Feature activation+1.449
tap
Token tap
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
branding
Token branding
Feature activation+0.000

INTERVAL 1.485 - 1.697
CONTAINS 0.000%

M
TokenM
Feature activation+0.000
urch
Tokenurch
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.232
ľ
Tokenľ
Feature activation+1.608
we
Tokenwe
Feature activation+0.915
can
Token can
Feature activation+0.976
just
Token just
Feature activation+0.398
say
Token say
Feature activation+0.000
there
Token there
Feature activation+0.000
the
Token the
Feature activation+0.000
Spiritual
Token Spiritual
Feature activation+0.000
Capital
Token Capital
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
,
Token,
Feature activation+0.333
âĢ
Token âĢ
Feature activation+1.525
ľ
Tokenľ
Feature activation+0.910
Ian
TokenIan
Feature activation+0.786
is
Token is
Feature activation+0.895
an
Token an
Feature activation+0.286
extraordinarily
Token extraordinarily
Feature activation+0.087

INTERVAL 1.273 - 1.485
CONTAINS 0.001%

tells
Token tells
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
Ah
Token Ah
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
,
Token,
Feature activation+0.630
the
Token the
Feature activation+1.347
stage
Token stage
Feature activation+0.159
has
Token has
Feature activation+0.437
given
Token given
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.450
âĢ
Token âĢ
Feature activation+0.693
ľ
Tokenľ
Feature activation+0.773
GE
TokenGE
Feature activation+0.499
wants
Token wants
Feature activation+1.795
to
Token to
Feature activation+1.449
tap
Token tap
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
branding
Token branding
Feature activation+0.000
element
Token element
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
Cardinal
Token Cardinal
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.355
ľ
Tokenľ
Feature activation+0.623
to
Tokento
Feature activation+0.000
give
Token give
Feature activation+0.000
their
Token their
Feature activation+0.000
delegates
Token delegates
Feature activation+0.000
Nort
Token Nort
Feature activation+0.000
je
Tokenje
Feature activation+0.000
,
Token,
Feature activation+0.000
26
Token 26
Feature activation+0.000
,
Token,
Feature activation+0.000
Mrs
Token Mrs
Feature activation+1.321
Pot
Token Pot
Feature activation+0.070
g
Tokeng
Feature activation+0.000
iet
Tokeniet
Feature activation+0.000
er
Tokener
Feature activation+0.266
's
Token's
Feature activation+0.135
Capt
Token Capt
Feature activation+0.000
.
Token.
Feature activation+0.000
Tommy
Token Tommy
Feature activation+0.000
Simmons
Token Simmons
Feature activation+0.000
,
Token,
Feature activation+0.000
Keller
Token Keller
Feature activation+1.301
âĢ
TokenâĢ
Feature activation+0.921
Ļ
TokenĻ
Feature activation+0.425
s
Tokens
Feature activation+0.244
patrol
Token patrol
Feature activation+0.007
commander
Token commander
Feature activation+0.000

INTERVAL 1.061 - 1.273
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
M
TokenM
Feature activation+0.000
urch
Tokenurch
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.232
ľ
Tokenľ
Feature activation+1.608
we
Tokenwe
Feature activation+0.915
can
Token can
Feature activation+0.976
just
Token just
Feature activation+0.398
say
Token say
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Mart
Token Mart
Feature activation+0.000
inelli
Tokeninelli
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.238
ľ
Tokenľ
Feature activation+1.186
that
Tokenthat
Feature activation+0.952
person
Token person
Feature activation+0.035
can
Token can
Feature activation+0.000
continue
Token continue
Feature activation+0.000
said
Token said
Feature activation+0.000
Mart
Token Mart
Feature activation+0.000
inelli
Tokeninelli
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.238
ľ
Tokenľ
Feature activation+1.186
that
Tokenthat
Feature activation+0.952
person
Token person
Feature activation+0.035
can
Token can
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
said
Token said
Feature activation+0.000
Good
Token Good
Feature activation+0.000
hart
Tokenhart
Feature activation+0.000
,
Token,
Feature activation+0.550
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.120
what
Tokenwhat
Feature activation+2.121
is
Token is
Feature activation+0.753
now
Token now
Feature activation+0.589
likely
Token likely
Feature activation+0.061
is
Token is
Feature activation+0.679
il
Tokenil
Feature activation+0.000
f
Tokenf
Feature activation+0.000
oyle
Tokenoyle
Feature activation+0.000
,
Token,
Feature activation+0.000
striking
Token striking
Feature activation+1.057
a
Token a
Feature activation+1.118
familiar
Token familiar
Feature activation+0.594
gun
Token gun
Feature activation+0.528
-
Token-
Feature activation+0.000
rights
Tokenrights
Feature activation+0.000
talking
Token talking
Feature activation+0.000

INTERVAL 0.848 - 1.061
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Tommy
Token Tommy
Feature activation+0.000
Simmons
Token Simmons
Feature activation+0.000
,
Token,
Feature activation+0.000
Keller
Token Keller
Feature activation+1.301
âĢ
TokenâĢ
Feature activation+0.921
Ļ
TokenĻ
Feature activation+0.425
s
Tokens
Feature activation+0.244
patrol
Token patrol
Feature activation+0.007
commander
Token commander
Feature activation+0.000
.
Token.
Feature activation+0.010
Foundation
Token Foundation
Feature activation+0.000
,
Token,
Feature activation+0.333
âĢ
Token âĢ
Feature activation+1.525
ľ
Tokenľ
Feature activation+0.910
Ian
TokenIan
Feature activation+0.786
is
Token is
Feature activation+0.895
an
Token an
Feature activation+0.286
extraordinarily
Token extraordinarily
Feature activation+0.087
bright
Token bright
Feature activation+0.000
guy
Token guy
Feature activation+0.000
with
Token with
Feature activation+0.000
John
Token John
Feature activation+0.000
Kem
Token Kem
Feature activation+0.000
m
Tokenm
Feature activation+0.000
erer
Tokenerer
Feature activation+0.000
,
Token,
Feature activation+0.000
J
Token J
Feature activation+0.902
iff
Tokeniff
Feature activation+0.205
âĢ
TokenâĢ
Feature activation+0.610
Ļ
TokenĻ
Feature activation+0.052
s
Tokens
Feature activation+0.419
vice
Token vice
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.232
ľ
Tokenľ
Feature activation+1.608
we
Tokenwe
Feature activation+0.915
can
Token can
Feature activation+0.976
just
Token just
Feature activation+0.398
say
Token say
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
an
Token an
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
Rudy
Token Rudy
Feature activation+0.000
Giuliani
Token Giuliani
Feature activation+0.000
,
Token,
Feature activation+1.000
is
Token is
Feature activation+1.364
smart
Token smart
Feature activation+0.737
.
Token.
Feature activation+0.045
He
Token He
Feature activation+0.211
end
Token end
Feature activation+0.000

INTERVAL 0.636 - 0.848
CONTAINS 0.004%

il
Tokenil
Feature activation+0.000
ience
Tokenience
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.310
an
Token an
Feature activation+0.270
answer
Token answer
Feature activation+0.671
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.241
In
TokenIn
Feature activation+0.125
short
Token short
Feature activation+0.000
ographer
Tokenographer
Feature activation+0.000
Grant
Token Grant
Feature activation+0.000
De
Token De
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
of
Token of
Feature activation+0.153
the
Token the
Feature activation+0.645
Sc
Token Sc
Feature activation+0.121
ripp
Tokenripp
Feature activation+0.000
s
Tokens
Feature activation+0.000
Institution
Token Institution
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Tokena
Feature activation+0.000
film
Token film
Feature activation+0.000
,
Token,
Feature activation+0.000
mind
Token mind
Feature activation+0.000
you
Token you
Feature activation+0.315
,
Token,
Feature activation+0.760
called
Token called
Feature activation+0.000
fucking
Token fucking
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
M
TokenM
Feature activation+0.000
Pad
Token Pad
Feature activation+0.000
illa
Tokenilla
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
called
Token called
Feature activation+0.825
âĢ
Token âĢ
Feature activation+0.160
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.299
biggest
Token biggest
Feature activation+0.002
mess
Token mess
Feature activation+0.000
-
Token-
Feature activation+0.000
Utah
TokenUtah
Feature activation+0.000
),
Token),
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.306
ĺ
Tokenĺ
Feature activation+0.000
Are
TokenAre
Feature activation+0.658
you
Token you
Feature activation+0.029
just
Token just
Feature activation+0.000
doing
Token doing
Feature activation+0.000
this
Token this
Feature activation+0.000
because
Token because
Feature activation+0.000

INTERVAL 0.424 - 0.636
CONTAINS 0.008%

old
Tokenold
Feature activation+0.000
Pakistani
Token Pakistani
Feature activation+0.000
resident
Token resident
Feature activation+0.000
,
Token,
Feature activation+0.000
last
Token last
Feature activation+0.000
October
Token October
Feature activation+0.470
following
Token following
Feature activation+0.000
his
Token his
Feature activation+0.000
indictment
Token indictment
Feature activation+0.000
in
Token in
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
of
Token of
Feature activation+0.000
Government
Token Government
Feature activation+0.000
at
Token at
Feature activation+0.000
Cornell
Token Cornell
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.450
a
Token a
Feature activation+0.689
drone
Token drone
Feature activation+0.240
produced
Token produced
Feature activation+0.000
by
Token by
Feature activation+0.000
China
Token China
Feature activation+0.000
f
Tokenf
Feature activation+0.000
oyle
Tokenoyle
Feature activation+0.000
,
Token,
Feature activation+0.000
striking
Token striking
Feature activation+1.057
a
Token a
Feature activation+1.118
familiar
Token familiar
Feature activation+0.594
gun
Token gun
Feature activation+0.528
-
Token-
Feature activation+0.000
rights
Tokenrights
Feature activation+0.000
talking
Token talking
Feature activation+0.000
point
Token point
Feature activation+0.230
,
Token,
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Weinstein
Token Weinstein
Feature activation+0.000
,
Token,
Feature activation+0.000
MR
Token MR
Feature activation+0.536
FF
TokenFF
Feature activation+0.000
Advisory
Token Advisory
Feature activation+0.000
Board
Token Board
Feature activation+0.000
member
Token member
Feature activation+0.000
and
Token and
Feature activation+0.000
many
Token many
Feature activation+0.000
,
Token,
Feature activation+0.000
Brock
Token Brock
Feature activation+0.000
adds
Token adds
Feature activation+0.000
,
Token,
Feature activation+0.419
from
Token from
Feature activation+0.606
the
Token the
Feature activation+0.066
Senate
Token Senate
Feature activation+0.000
seat
Token seat
Feature activation+0.000
occupied
Token occupied
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 0.212 - 0.424
CONTAINS 0.026%

,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
Harold
Token Harold
Feature activation+0.000
Brooks
Token Brooks
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.297
National
Token National
Feature activation+0.000
Ocean
Token Ocean
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
and
Token and
Feature activation+0.000
Atmospheric
Token Atmospheric
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
mar
Tokenmar
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.230
Mary
Token Mary
Feature activation+0.000
mount
Tokenmount
Feature activation+0.000
Manhattan
Token Manhattan
Feature activation+0.000
College
Token College
Feature activation+0.000
.
Token.
Feature activation+0.000
Wass
Token Wass
Feature activation+0.000
en
Tokenen
Feature activation+0.000
ber
Tokenber
Feature activation+0.000
gh
Tokengh
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.341
biologist
Token biologist
Feature activation+0.000
at
Token at
Feature activation+0.000
G
Token G
Feature activation+0.000
hent
Tokenhent
Feature activation+0.000
University
Token University
Feature activation+0.000
Ark
Token Ark
Feature activation+0.000
ani
Tokenani
Feature activation+0.000
-
Token-
Feature activation+0.000
H
TokenH
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
,
Token,
Feature activation+0.227
was
Token was
Feature activation+0.000
recognised
Token recognised
Feature activation+0.000
for
Token for
Feature activation+0.000
"
Token "
Feature activation+0.000
original
Tokenoriginal
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Le
Token Le
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.349
states
Token states
Feature activation+0.272
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.254

INTERVAL 0.000 - 0.212
CONTAINS 99.959%

car
Token car
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
extremely
Tokenextremely
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
to
Token to
Feature activation+0.000
every
Token every
Feature activation+0.000
single
Token single
Feature activation+0.000
woman
Token woman
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
border
Token border
Feature activation+0.000
on
Token on
Feature activation+0.000
July
Token July
Feature activation+0.000
16
Token 16
Feature activation+0.000
.
Token.
Feature activation+0.000
Credit
Token Credit
Feature activation+0.000
:
Token:
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
The
Token The
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
point
Token point
Feature activation+0.000
I
Token I
Feature activation+0.000
first
Token first
Feature activation+0.000
made
Token made
Feature activation+0.000
here
Token here
Feature activation+0.000
still
Token still
Feature activation+0.000
holds
Token holds
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
they
Token they
Feature activation+0.000
present
Token present
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Unfortunately
TokenUnfortunately
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
return
Token return
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
all
Token all
Feature activation+0.000
game
Token game
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H6.5: (feature 6688)

TOP ACTIVATIONS
MAX = 2.235

a
Token a
Feature activation+0.000
dé
Token dé
Feature activation+0.000
j
Tokenj
Feature activation+0.000
Ãł
TokenÃł
Feature activation+0.000
v
Token v
Feature activation+0.000
u
Tokenu
Feature activation+2.235
of
Token of
Feature activation+0.782
the
Token the
Feature activation+0.092
103
Token 103
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Grey
Token Grey
Feature activation+0.000
honest
Token honest
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
good
Tokengood
Feature activation+0.000
ness
Tokenness
Feature activation+2.119
sprites
Token sprites
Feature activation+0.319
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.000
processor
Token processor
Feature activation+0.000
an
Token an
Feature activation+0.000
employee
Token employee
Feature activation+0.000
contributes
Token contributes
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
for
Token for
Feature activation+0.000
dollar
Token dollar
Feature activation+1.769
,
Token,
Feature activation+0.941
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.000
kick
Token kick
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Tell
Token Tell
Feature activation+0.450
earlier
Token earlier
Feature activation+1.189
today
Token today
Feature activation+1.373
,
Token,
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
Man
Token Man
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.000
by
Token by
Feature activation+0.000
case
Token case
Feature activation+0.000
basis
Token basis
Feature activation+1.360
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
all
Tokenall
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
-
Token-
Feature activation+0.000
all
Tokenall
Feature activation+0.474
no
Token no
Feature activation+1.327
matter
Token matter
Feature activation+0.000
what
Token what
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
situation
Token situation
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
Tell
Token Tell
Feature activation+0.450
earlier
Token earlier
Feature activation+1.189
today
Token today
Feature activation+1.373
,
Token,
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
blessed
Token blessed
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
measure
Token measure
Feature activation+1.156
and
Token and
Feature activation+0.045
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
far
Token far
Feature activation+0.000
and
Token and
Feature activation+0.000
away
Token away
Feature activation+1.109
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.034
factor
Token factor
Feature activation+0.000
affecting
Token affecting
Feature activation+0.000
the
Token the
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
why
Token why
Feature activation+0.000
,
Token,
Feature activation+0.000
pray
Token pray
Feature activation+0.000
tell
Token tell
Feature activation+0.000
,
Token,
Feature activation+1.048
did
Token did
Feature activation+0.000
they
Token they
Feature activation+0.000
feel
Token feel
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
that
Token that
Feature activation+0.000
cash
Token cash
Feature activation+0.000
-
Token-
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
-
Token-
Feature activation+0.000
freedom
Tokenfreedom
Feature activation+0.993
deals
Token deals
Feature activation+0.000
had
Token had
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
point
Token point
Feature activation+0.000
the
Token the
Feature activation+0.000
profit
Token profit
Feature activation+0.000
motive
Token motive
Feature activation+0.000
,
Token,
Feature activation+0.000
writ
Token writ
Feature activation+0.000
large
Token large
Feature activation+0.963
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
of
Token of
Feature activation+0.000
M
Token M
Feature activation+0.957
is
Token is
Feature activation+0.000
seeing
Token seeing
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
employee
Token employee
Feature activation+0.000
contributes
Token contributes
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
for
Token for
Feature activation+0.000
dollar
Token dollar
Feature activation+1.769
,
Token,
Feature activation+0.941
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.000
kick
Token kick
Feature activation+0.000
in
Token in
Feature activation+0.000
50
Token 50
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
food
Token food
Feature activation+0.000
for
Token for
Feature activation+0.000
thought
Token thought
Feature activation+0.873
.
Token.
Feature activation+0.647
Ċ
TokenĊ
Feature activation+0.177
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
huge
Token huge
Feature activation+0.000
couples
Token couples
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
value
Token value
Feature activation+0.000
for
Token for
Feature activation+0.000
money
Token money
Feature activation+0.869
:
Token:
Feature activation+0.000
until
Token until
Feature activation+0.000
recently
Token recently
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
some
Token some
Feature activation+0.000
form
Token form
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
even
Token even
Feature activation+0.856
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
passing
Token passing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
acclaimed
Token acclaimed
Feature activation+0.000
Wh
Token Wh
Feature activation+0.000
istle
Tokenistle
Feature activation+0.000
Down
Token Down
Feature activation+0.000
the
Token the
Feature activation+0.000
Wind
Token Wind
Feature activation+0.849
(
Token (
Feature activation+0.000
19
Token19
Feature activation+0.000
61
Token61
Feature activation+0.000
),
Token),
Feature activation+0.000
about
Token about
Feature activation+0.000
think
Token think
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
odds
Token odds
Feature activation+0.000
are
Token are
Feature activation+0.000
there
Token there
Feature activation+0.807
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
dé
Token dé
Feature activation+0.000
j
Tokenj
Feature activation+0.000
Ãł
TokenÃł
Feature activation+0.000
v
Token v
Feature activation+0.000
u
Tokenu
Feature activation+2.235
of
Token of
Feature activation+0.782
the
Token the
Feature activation+0.092
103
Token 103
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Grey
Token Grey
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000

Top DFA by src position
MAX = 2.884

a
Token a
Feature activation+0.052
Top resid features:
dé
Token dé
Feature activation+0.342
Top resid features:
j
Tokenj
Feature activation+0.062
Top resid features:
Ãł
TokenÃł
Feature activation+0.076
Top resid features:
v
Token v
Feature activation+0.200
Top resid features:
u
Tokenu
Feature activation+2.490
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
103
Token 103
Feature activation+0.000
Top resid features:
rd
Tokenrd
Feature activation+0.000
Top resid features:
Grey
Token Grey
Feature activation+0.000
Top resid features:
honest
Token honest
Feature activation+0.077
Top resid features:
-
Token-
Feature activation-0.027
Top resid features:
to
Tokento
Feature activation+0.045
Top resid features:
-
Token-
Feature activation+0.162
Top resid features:
good
Tokengood
Feature activation+0.151
Top resid features:
ness
Tokenness
Feature activation+2.368
Top resid features:
sprites
Token sprites
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
video
Token video
Feature activation+0.000
Top resid features:
processor
Token processor
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.060
Top resid features:
employee
Token employee
Feature activation-0.086
Top resid features:
contributes
Token contributes
Feature activation-0.001
Top resid features:
dollar
Token dollar
Feature activation+0.157
Top resid features:
for
Token for
Feature activation-0.184
Top resid features:
dollar
Token dollar
Feature activation+2.884
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
others
Token others
Feature activation+0.000
Top resid features:
kick
Token kick
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.113
Top resid features:
Don
Token Don
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
t
Tokent
Feature activation+0.088
Top resid features:
Tell
Token Tell
Feature activation+1.765
Top resid features:
earlier
Token earlier
Feature activation-0.196
Top resid features:
today
Token today
Feature activation+0.108
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Sen
Token Sen
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
battles
Token battles
Feature activation-0.070
Top resid features:
on
Token on
Feature activation+0.061
Top resid features:
a
Token a
Feature activation+0.025
Top resid features:
case
Token case
Feature activation+0.054
Top resid features:
by
Token by
Feature activation-0.063
Top resid features:
case
Token case
Feature activation+1.906
Top resid features:
basis
Token basis
Feature activation+0.242
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
research
Token research
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.018
Top resid features:
all
Tokenall
Feature activation-0.363
Top resid features:
,
Token,
Feature activation-0.073
Top resid features:
be
Token be
Feature activation+0.034
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
all
Tokenall
Feature activation+2.351
Top resid features:
no
Token no
Feature activation+0.018
Top resid features:
matter
Token matter
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
Don
Token Don
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
t
Tokent
Feature activation+0.007
Top resid features:
Tell
Token Tell
Feature activation+1.528
Top resid features:
earlier
Token earlier
Feature activation+0.028
Top resid features:
today
Token today
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Sen
Token Sen
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.028
Top resid features:
Ļ
TokenĻ
Feature activation+0.021
Top resid features:
m
Tokenm
Feature activation+0.012
Top resid features:
blessed
Token blessed
Feature activation+0.104
Top resid features:
beyond
Token beyond
Feature activation+0.022
Top resid features:
measure
Token measure
Feature activation+1.928
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
By
TokenBy
Feature activation+0.022
Top resid features:
far
Token far
Feature activation+0.337
Top resid features:
and
Token and
Feature activation+0.129
Top resid features:
away
Token away
Feature activation+1.410
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
biggest
Token biggest
Feature activation+0.000
Top resid features:
factor
Token factor
Feature activation+0.000
Top resid features:
affecting
Token affecting
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
And
TokenAnd
Feature activation-0.031
Top resid features:
why
Token why
Feature activation+0.110
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
pray
Token pray
Feature activation-0.031
Top resid features:
tell
Token tell
Feature activation+1.779
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
feel
Token feel
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.047
Top resid features:
cash
Token cash
Feature activation+0.306
Top resid features:
-
Token-
Feature activation+0.046
Top resid features:
for
Tokenfor
Feature activation+0.308
Top resid features:
-
Token-
Feature activation+0.264
Top resid features:
freedom
Tokenfreedom
Feature activation+1.023
Top resid features:
deals
Token deals
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
point
Token point
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
profit
Token profit
Feature activation-0.021
Top resid features:
motive
Token motive
Feature activation+0.079
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
writ
Token writ
Feature activation+0.233
Top resid features:
large
Token large
Feature activation+1.661
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
2012
Token 2012
Feature activation+0.000
Top resid features:
estimate
Token estimate
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.027
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
U
Token U
Feature activation+0.121
Top resid features:
of
Token of
Feature activation+0.327
Top resid features:
M
Token M
Feature activation+1.341
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
seeing
Token seeing
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.024
Top resid features:
employee
Token employee
Feature activation-0.063
Top resid features:
contributes
Token contributes
Feature activation-0.012
Top resid features:
dollar
Token dollar
Feature activation+0.051
Top resid features:
for
Token for
Feature activation+0.192
Top resid features:
dollar
Token dollar
Feature activation+1.576
Top resid features:
,
Token,
Feature activation+0.141
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
others
Token others
Feature activation+0.000
Top resid features:
kick
Token kick
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Just
TokenJust
Feature activation+0.003
Top resid features:
food
Token food
Feature activation+0.023
Top resid features:
for
Token for
Feature activation+1.146
Top resid features:
thought
Token thought
Feature activation+0.609
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:
A
TokenA
Feature activation+0.000
Top resid features:
couples
Token couples
Feature activation+0.037
Top resid features:
looking
Token looking
Feature activation+0.056
Top resid features:
for
Token for
Feature activation+0.030
Top resid features:
value
Token value
Feature activation-0.034
Top resid features:
for
Token for
Feature activation+0.540
Top resid features:
money
Token money
Feature activation+1.100
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
recently
Token recently
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.064
Top resid features:
some
Token some
Feature activation+0.023
Top resid features:
form
Token form
Feature activation+0.004
Top resid features:
or
Token or
Feature activation+0.086
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
other
Token other
Feature activation+1.472
Top resid features:
even
Token even
Feature activation-0.008
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
passing
Token passing
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
acclaimed
Token acclaimed
Feature activation-0.045
Top resid features:
Wh
Token Wh
Feature activation+0.029
Top resid features:
istle
Tokenistle
Feature activation+0.010
Top resid features:
Down
Token Down
Feature activation+0.219
Top resid features:
the
Token the
Feature activation+0.113
Top resid features:
Wind
Token Wind
Feature activation+1.373
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
19
Token19
Feature activation+0.000
Top resid features:
61
Token61
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.010
Top resid features:
think
Token think
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
,
Token,
Feature activation-0.047
Top resid features:
odds
Token odds
Feature activation-0.170
Top resid features:
are
Token are
Feature activation+1.738
Top resid features:
there
Token there
Feature activation-0.014
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
list
Token list
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.090
Top resid features:
dé
Token dé
Feature activation+0.106
Top resid features:
j
Tokenj
Feature activation+0.033
Top resid features:
Ãł
TokenÃł
Feature activation+0.073
Top resid features:
v
Token v
Feature activation+0.259
Top resid features:
u
Tokenu
Feature activation+1.169
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
103
Token 103
Feature activation+0.000
Top resid features:
rd
Tokenrd
Feature activation+0.000
Top resid features:
Grey
Token Grey
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.08

Head 2: 0.04

Head 3: 0.04

Head 4: 0.05

Head 5: 0.40

Head 6: 0.08

Head 7: 0.07

Head 8: 0.11

Head 9: 0.02

Head 10: 0.02

Head 11: 0.05

Positive logits

theless2.53

ablished2.35

adversely2.35

ounced2.34

listed2.33

accelerated2.32

urbed2.26

aided2.26

unresolved2.20

uilt2.17

entimes2.16

etitive2.15

unquestion2.11

comprehens2.11

strengthened2.10

boosted2.10

vividly2.10

igmat2.09

genuine2.09

prominently2.08

Negative logits

Pastebin-3.01

esson-2.35

uez-2.32

ById-2.31

gall-2.27

isma-2.22

Doors-2.20

Palm-2.19

izont-2.16

peria-2.16

Ya-2.16

contrace-2.11

Whats-2.08

acs-2.07

Lies-2.07

Quantity-2.05

hammad-2.05

else-2.05

Horses-2.04

Kavanaugh-2.01

INTERVAL 2.012 - 2.235
CONTAINS 0.000%

a
Token a
Feature activation+0.000
dé
Token dé
Feature activation+0.000
j
Tokenj
Feature activation+0.000
Ãł
TokenÃł
Feature activation+0.000
v
Token v
Feature activation+0.000
u
Tokenu
Feature activation+2.235
of
Token of
Feature activation+0.782
the
Token the
Feature activation+0.092
103
Token 103
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Grey
Token Grey
Feature activation+0.000
honest
Token honest
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
good
Tokengood
Feature activation+0.000
ness
Tokenness
Feature activation+2.119
sprites
Token sprites
Feature activation+0.319
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.000
processor
Token processor
Feature activation+0.000

INTERVAL 1.788 - 2.012
CONTAINS 0.000%

INTERVAL 1.565 - 1.788
CONTAINS 0.000%

an
Token an
Feature activation+0.000
employee
Token employee
Feature activation+0.000
contributes
Token contributes
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
for
Token for
Feature activation+0.000
dollar
Token dollar
Feature activation+1.769
,
Token,
Feature activation+0.941
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.000
kick
Token kick
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.341 - 1.565
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Tell
Token Tell
Feature activation+0.450
earlier
Token earlier
Feature activation+1.189
today
Token today
Feature activation+1.373
,
Token,
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
Man
Token Man
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.000
by
Token by
Feature activation+0.000
case
Token case
Feature activation+0.000
basis
Token basis
Feature activation+1.360
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000

INTERVAL 1.118 - 1.341
CONTAINS 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
Tell
Token Tell
Feature activation+0.450
earlier
Token earlier
Feature activation+1.189
today
Token today
Feature activation+1.373
,
Token,
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
all
Tokenall
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
-
Token-
Feature activation+0.000
all
Tokenall
Feature activation+0.474
no
Token no
Feature activation+1.327
matter
Token matter
Feature activation+0.000
what
Token what
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
situation
Token situation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
blessed
Token blessed
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
measure
Token measure
Feature activation+1.156
and
Token and
Feature activation+0.045
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000

INTERVAL 0.894 - 1.118
CONTAINS 0.001%

And
TokenAnd
Feature activation+0.000
why
Token why
Feature activation+0.000
,
Token,
Feature activation+0.000
pray
Token pray
Feature activation+0.000
tell
Token tell
Feature activation+0.000
,
Token,
Feature activation+1.048
did
Token did
Feature activation+0.000
they
Token they
Feature activation+0.000
feel
Token feel
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
of
Token of
Feature activation+0.000
M
Token M
Feature activation+0.957
is
Token is
Feature activation+0.000
seeing
Token seeing
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
profit
Token profit
Feature activation+0.000
motive
Token motive
Feature activation+0.000
,
Token,
Feature activation+0.000
writ
Token writ
Feature activation+0.000
large
Token large
Feature activation+0.963
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
cash
Token cash
Feature activation+0.000
-
Token-
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
-
Token-
Feature activation+0.000
freedom
Tokenfreedom
Feature activation+0.993
deals
Token deals
Feature activation+0.000
had
Token had
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
point
Token point
Feature activation+0.000
employee
Token employee
Feature activation+0.000
contributes
Token contributes
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
for
Token for
Feature activation+0.000
dollar
Token dollar
Feature activation+1.769
,
Token,
Feature activation+0.941
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.000
kick
Token kick
Feature activation+0.000
in
Token in
Feature activation+0.000
50
Token 50
Feature activation+0.000

INTERVAL 0.671 - 0.894
CONTAINS 0.001%

acclaimed
Token acclaimed
Feature activation+0.000
Wh
Token Wh
Feature activation+0.000
istle
Tokenistle
Feature activation+0.000
Down
Token Down
Feature activation+0.000
the
Token the
Feature activation+0.000
Wind
Token Wind
Feature activation+0.849
(
Token (
Feature activation+0.000
19
Token19
Feature activation+0.000
61
Token61
Feature activation+0.000
),
Token),
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
15
Token 15
Feature activation+0.000
minute
Token minute
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
one
Token one
Feature activation+0.753
talk
Token talk
Feature activation+0.000
.
Token.
Feature activation+0.000
T
Token T
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Labour
TokenLabour
Feature activation+0.000
,
Token,
Feature activation+0.000
yes
Token yes
Feature activation+0.000
and
Token and
Feature activation+0.000
no
Token no
Feature activation+0.000
thank
Token thank
Feature activation+0.000
you
Token you
Feature activation+0.760
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
wife
Token wife
Feature activation+0.000
also
Token also
Feature activation+0.000
some
Token some
Feature activation+0.000
form
Token form
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
even
Token even
Feature activation+0.856
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
passing
Token passing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
think
Token think
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
odds
Token odds
Feature activation+0.000
are
Token are
Feature activation+0.000
there
Token there
Feature activation+0.807
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.447 - 0.671
CONTAINS 0.003%

State
Token State
Feature activation+0.000
of
Token of
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Levant
Token Levant
Feature activation+0.664
,
Token,
Feature activation+0.091
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
prepared
Token prepared
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Like
TokenLike
Feature activation+0.000
it
Token it
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.607
Ripple
Token Ripple
Feature activation+0.000
is
Token is
Feature activation+0.000
Innov
Token Innov
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
sho
Token sho
Feature activation+0.000
est
Tokenest
Feature activation+0.000
ring
Tokenring
Feature activation+0.276
,
Token,
Feature activation+0.473
with
Token with
Feature activation+0.000
family
Token family
Feature activation+0.000
members
Token members
Feature activation+0.000
playing
Token playing
Feature activation+0.000
key
Token key
Feature activation+0.000
To
TokenTo
Feature activation+0.000
add
Token add
Feature activation+0.000
insult
Token insult
Feature activation+0.000
to
Token to
Feature activation+0.000
injury
Token injury
Feature activation+0.306
the
Token the
Feature activation+0.449
Boy
Token Boy
Feature activation+0.000
nton
Tokennton
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
In
Token In
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
food
Token food
Feature activation+0.000
for
Token for
Feature activation+0.000
thought
Token thought
Feature activation+0.873
.
Token.
Feature activation+0.647
Ċ
TokenĊ
Feature activation+0.177
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
huge
Token huge
Feature activation+0.000
weight
Token weight
Feature activation+0.000

INTERVAL 0.224 - 0.447
CONTAINS 0.007%

most
Token most
Feature activation+0.000
part
Token part
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
memory
Token memory
Feature activation+0.000
serves
Token serves
Feature activation+0.374
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
bl
Tokenbl
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
et
Tokenet
Feature activation+0.000
that
Token that
Feature activation+0.000
be
Token be
Feature activation+0.000
believed
Token believed
Feature activation+0.234
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
Flight
Token Flight
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Con
Token Con
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ords
Tokenords
Feature activation+0.303
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
vampire
Token vampire
Feature activation+0.000
mock
Token mock
Feature activation+0.000
ument
Tokenument
Feature activation+0.000
,
Token,
Feature activation+0.000
ladies
Token ladies
Feature activation+0.000
and
Token and
Feature activation+0.000
gentlemen
Token gentlemen
Feature activation+0.248
,
Token,
Feature activation+0.717
I
Token I
Feature activation+0.255
am
Token am
Feature activation+0.000
officially
Token officially
Feature activation+0.000
running
Token running
Feature activation+0.000
for
Token for
Feature activation+0.000
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
better
Token better
Feature activation+0.000
or
Token or
Feature activation+0.000
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.346
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Article
TokenArticle
Feature activation+0.000
Continued
Token Continued
Feature activation+0.000
Below
Token Below
Feature activation+0.000

INTERVAL 0.000 - 0.224
CONTAINS 99.988%

have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
deterrent
Token deterrent
Feature activation+0.000
effect
Token effect
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
org
Tokenorg
Feature activation+0.000
/
Token/
Feature activation+0.000
contact
Tokencontact
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
devices
Token devices
Feature activation+0.000
communicate
Token communicate
Feature activation+0.000
with
Token with
Feature activation+0.000
erson
Tokenerson
Feature activation+0.000
and
Token and
Feature activation+0.000
Tea
Token Tea
Feature activation+0.000
Party
Token Party
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
from
Token from
Feature activation+0.000
around
Token around
Feature activation+0.000
Dallas
Token Dallas
Feature activation+0.000
spent
Token spent
Feature activation+0.000
one
Token one
Feature activation+0.000
night
Token night
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Mem
Token Mem
Feature activation+0.000
o
Tokeno
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
promote
Token promote
Feature activation+0.000
American
Token American
Feature activation+0.000
energy
Token energy
Feature activation+0.000
Following
TokenFollowing
Feature activation+0.000
his
Token his
Feature activation+0.000
comments
Token comments
Feature activation+0.000
,
Token,
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Netanyahu
Token Netanyahu
Feature activation+0.000
announced
Token announced
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
18
Token 18
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H6.5: (feature 7534)

TOP ACTIVATIONS
MAX = 6.658

out
Token out
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
.
Token.
Feature activation+0.889
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
that
Token that
Feature activation+0.000
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
new
Token new
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
.
Token.
Feature activation+0.889
Ċ
TokenĊ
Feature activation+0.195
XML
Token XML
Feature activation+0.000
out
Token out
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
that
Token that
Feature activation+0.000
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
new
Token new
Feature activation+0.000
film
Token film
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+1.779
do
Token do
Feature activation+2.655
not
Token not
Feature activation+1.623
happen
Token happen
Feature activation+0.160
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
probably
Token probably
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+2.081
these
Token these
Feature activation+0.908
patches
Token patches
Feature activation+0.000
contain
Token contain
Feature activation+1.076
wild
Token wild
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+1.779
do
Token do
Feature activation+2.655
not
Token not
Feature activation+1.623
happen
Token happen
Feature activation+0.160
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
oot
Tokenoot
Feature activation+0.000
opia
Tokenopia
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+1.714
arguably
Token arguably
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+1.779
do
Token do
Feature activation+2.655
not
Token not
Feature activation+1.623
happen
Token happen
Feature activation+0.160
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
you
Token you
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+1.350
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
9
Token9
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
that
Token that
Feature activation+0.000
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
,
Token,
Feature activation+1.185
McDonald
Token McDonald
Feature activation+0.301
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+1.226
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.256
Earlier
Token Earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
read
Token read
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+1.185
McDonald
Token McDonald
Feature activation+0.301
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+1.226
There
TokenThere
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.184
Ċ
TokenĊ
Feature activation+0.414
It
TokenIt
Feature activation+0.000
boils
Token boils
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000
probably
Token probably
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+2.081
these
Token these
Feature activation+0.908
patches
Token patches
Feature activation+0.000
contain
Token contain
Feature activation+1.076
wild
Token wild
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
walking
Token walking
Feature activation+0.000
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
probably
Token probably
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+2.081
these
Token these
Feature activation+0.908
patches
Token patches
Feature activation+0.000
contain
Token contain
Feature activation+1.076
wild
Token wild
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
.
Token.
Feature activation+0.889
Ċ
TokenĊ
Feature activation+0.195
Ċ
TokenĊ
Feature activation+0.000
X
TokenX
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
sold
Token sold
Feature activation+0.000
queer
Token queer
Feature activation+0.000
gir
Token gir
Feature activation+0.000
aff
Tokenaff
Feature activation+0.000
es
Tokenes
Feature activation+0.000
"
Token"
Feature activation+0.754
in
Token in
Feature activation+0.000
Ridley
Token Ridley
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
's
Token's
Feature activation+0.000
Gladiator
Token Gladiator
Feature activation+0.000

Top DFA by src position
MAX = 8.183

,
Token,
Feature activation-0.231
Top resid features:
XML
Token XML
Feature activation+0.004
Top resid features:
out
Token out
Feature activation-0.205
Top resid features:
-
Token -
Feature activation+0.002
Top resid features:
you
Token you
Feature activation-0.058
Top resid features:
guessed
Token guessed
Feature activation+8.183
Top resid features:
it
Token it
Feature activation+0.966
Top resid features:
,
Token,
Feature activation+0.702
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.045
Top resid features:
XML
Token XML
Feature activation+0.013
Top resid features:
out
Token out
Feature activation-0.252
Top resid features:
-
Token -
Feature activation-0.039
Top resid features:
you
Token you
Feature activation+0.079
Top resid features:
guessed
Token guessed
Feature activation+4.052
Top resid features:
it
Token it
Feature activation+1.733
Top resid features:
,
Token,
Feature activation+0.871
Top resid features:
we
Token we
Feature activation+0.240
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.003
Top resid features:
?
Token?
Feature activation+0.062
Top resid features:
Yes
Token Yes
Feature activation+0.288
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
you
Token you
Feature activation+0.256
Top resid features:
read
Token read
Feature activation+2.116
Top resid features:
that
Token that
Feature activation+1.286
Top resid features:
correctly
Token correctly
Feature activation+1.877
Top resid features:
:
Token:
Feature activation+0.450
Top resid features:
Disney
Token Disney
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
XML
Token XML
Feature activation+0.024
Top resid features:
out
Token out
Feature activation-0.292
Top resid features:
-
Token -
Feature activation-0.005
Top resid features:
you
Token you
Feature activation+0.082
Top resid features:
guessed
Token guessed
Feature activation+3.183
Top resid features:
it
Token it
Feature activation+1.286
Top resid features:
,
Token,
Feature activation+0.988
Top resid features:
we
Token we
Feature activation+0.902
Top resid features:
do
Token do
Feature activation-0.139
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
XML
Token XML
Feature activation+0.035
Top resid features:
out
Token out
Feature activation-0.201
Top resid features:
-
Token -
Feature activation-0.006
Top resid features:
you
Token you
Feature activation+0.036
Top resid features:
guessed
Token guessed
Feature activation+4.585
Top resid features:
it
Token it
Feature activation+1.346
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.123
Top resid features:
you
Token you
Feature activation+0.127
Top resid features:
read
Token read
Feature activation+0.569
Top resid features:
that
Token that
Feature activation+1.216
Top resid features:
correctly
Token correctly
Feature activation+0.648
Top resid features:
:
Token:
Feature activation+1.509
Top resid features:
Disney
Token Disney
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.078
Top resid features:
as
Token as
Feature activation-0.014
Top resid features:
you
Token you
Feature activation+0.133
Top resid features:
may
Token may
Feature activation-0.007
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
guessed
Token guessed
Feature activation+4.934
Top resid features:
,
Token,
Feature activation+0.359
Top resid features:
do
Token do
Feature activation-0.092
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
happen
Token happen
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.044
Top resid features:
).
Token).
Feature activation+0.171
Top resid features:
As
Token As
Feature activation-0.036
Top resid features:
you
Token you
Feature activation+0.009
Top resid features:
probably
Token probably
Feature activation+0.149
Top resid features:
guessed
Token guessed
Feature activation+3.850
Top resid features:
,
Token,
Feature activation+0.309
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
patches
Token patches
Feature activation+0.000
Top resid features:
contain
Token contain
Feature activation+0.000
Top resid features:
wild
Token wild
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.339
Top resid features:
as
Token as
Feature activation-0.093
Top resid features:
you
Token you
Feature activation+0.173
Top resid features:
may
Token may
Feature activation-0.005
Top resid features:
have
Token have
Feature activation-0.016
Top resid features:
guessed
Token guessed
Feature activation+4.340
Top resid features:
,
Token,
Feature activation+0.375
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
happen
Token happen
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.217
Top resid features:
Yes
Token Yes
Feature activation+0.141
Top resid features:
,
Token,
Feature activation+0.154
Top resid features:
you
Token you
Feature activation+0.061
Top resid features:
read
Token read
Feature activation+0.253
Top resid features:
that
Token that
Feature activation+1.153
Top resid features:
correctly
Token correctly
Feature activation+1.012
Top resid features:
:
Token:
Feature activation+1.070
Top resid features:
Disney
Token Disney
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.027
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.090
Top resid features:
as
Token as
Feature activation-0.013
Top resid features:
you
Token you
Feature activation+0.155
Top resid features:
may
Token may
Feature activation+0.006
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
guessed
Token guessed
Feature activation+3.967
Top resid features:
,
Token,
Feature activation+0.347
Top resid features:
do
Token do
Feature activation-0.223
Top resid features:
not
Token not
Feature activation-0.111
Top resid features:
happen
Token happen
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.071
Top resid features:
can
Token can
Feature activation+0.013
Top resid features:
you
Token you
Feature activation+0.032
Top resid features:
guess
Token guess
Feature activation+1.626
Top resid features:
it
Token it
Feature activation+0.529
Top resid features:
?
Token?
Feature activation+1.784
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
9
Token9
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
11
Token11
Feature activation+0.000
Top resid features:
Yes
Token Yes
Feature activation+0.107
Top resid features:
,
Token,
Feature activation+0.315
Top resid features:
you
Token you
Feature activation+0.454
Top resid features:
read
Token read
Feature activation+0.728
Top resid features:
that
Token that
Feature activation+0.580
Top resid features:
correctly
Token correctly
Feature activation+1.244
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Disney
Token Disney
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:
s
Tokens
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.078
Top resid features:
You
TokenYou
Feature activation+0.037
Top resid features:
read
Token read
Feature activation+0.544
Top resid features:
right
Token right
Feature activation+0.584
Top resid features:
,
Token,
Feature activation+2.165
Top resid features:
McDonald
Token McDonald
Feature activation+0.168
Top resid features:
âĢ
TokenâĢ
Feature activation+0.262
Top resid features:
Ļ
TokenĻ
Feature activation+0.024
Top resid features:
s
Tokens
Feature activation-0.134
Top resid features:
is
Token is
Feature activation+0.235
Top resid features:
Website
Token Website
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.067
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
You
TokenYou
Feature activation+0.022
Top resid features:
read
Token read
Feature activation+1.159
Top resid features:
right
Token right
Feature activation+1.985
Top resid features:
,
Token,
Feature activation+0.789
Top resid features:
McDonald
Token McDonald
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:
s
Tokens
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
Ċ
TokenĊ
Feature activation+0.065
Top resid features:
There
TokenThere
Feature activation-0.030
Top resid features:
you
Token you
Feature activation+0.393
Top resid features:
have
Token have
Feature activation+0.444
Top resid features:
it
Token it
Feature activation+1.696
Top resid features:
.
Token.
Feature activation+0.939
Top resid features:
Ċ
TokenĊ
Feature activation+0.219
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
boils
Token boils
Feature activation+0.000
Top resid features:
games
Token games
Feature activation-0.015
Top resid features:
).
Token).
Feature activation+0.035
Top resid features:
As
Token As
Feature activation+0.013
Top resid features:
you
Token you
Feature activation+0.025
Top resid features:
probably
Token probably
Feature activation+0.166
Top resid features:
guessed
Token guessed
Feature activation+2.600
Top resid features:
,
Token,
Feature activation+0.313
Top resid features:
these
Token these
Feature activation+0.033
Top resid features:
patches
Token patches
Feature activation+0.310
Top resid features:
contain
Token contain
Feature activation+0.042
Top resid features:
wild
Token wild
Feature activation+0.000
Top resid features:
games
Token games
Feature activation-0.006
Top resid features:
).
Token).
Feature activation+0.095
Top resid features:
As
Token As
Feature activation+0.022
Top resid features:
you
Token you
Feature activation+0.027
Top resid features:
probably
Token probably
Feature activation+0.175
Top resid features:
guessed
Token guessed
Feature activation+2.069
Top resid features:
,
Token,
Feature activation+0.584
Top resid features:
these
Token these
Feature activation+0.240
Top resid features:
patches
Token patches
Feature activation+0.000
Top resid features:
contain
Token contain
Feature activation+0.000
Top resid features:
wild
Token wild
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
XML
Token XML
Feature activation-0.007
Top resid features:
out
Token out
Feature activation-0.280
Top resid features:
-
Token -
Feature activation-0.005
Top resid features:
you
Token you
Feature activation+0.238
Top resid features:
guessed
Token guessed
Feature activation+1.261
Top resid features:
it
Token it
Feature activation+0.756
Top resid features:
,
Token,
Feature activation+0.479
Top resid features:
we
Token we
Feature activation+0.400
Top resid features:
do
Token do
Feature activation+0.097
Top resid features:
X
Token X
Feature activation+0.234
Top resid features:
know
Token know
Feature activation+0.049
Top resid features:
Oliver
Token Oliver
Feature activation+0.040
Top resid features:
Reed
Token Reed
Feature activation+0.060
Top resid features:
better
Token better
Feature activation+0.124
Top resid features:
as
Token as
Feature activation+0.419
Top resid features:
"
Token "
Feature activation+1.197
Top resid features:
that
Tokenthat
Feature activation+0.068
Top resid features:
old
Token old
Feature activation+0.059
Top resid features:
guy
Token guy
Feature activation+0.054
Top resid features:
who
Token who
Feature activation+0.069
Top resid features:
got
Token got
Feature activation+0.209
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.03

Head 3: 0.07

Head 4: 0.04

Head 5: 0.39

Head 6: 0.04

Head 7: 0.05

Head 8: 0.11

Head 9: 0.01

Head 10: 0.02

Head 11: 0.13

Positive logits

paces2.17

anism1.75

restricted1.73

arry1.73

mode1.72

atile1.72

Modes1.70

inate1.70

Removal1.70

vable1.70

OPA1.67

dysfunctional1.64

homosexuals1.64

Mondays1.63

lockout1.61

includes1.60

playable1.60

Worldwide1.59

detrimental1.58

park1.58

Negative logits

earchers-2.45

WARN-2.13

eways-2.07

wagen-2.06

assetsadobe-2.01

legram-2.00

swer-1.98

lear-1.94

Clar-1.93

oubted-1.93

iman-1.92

ells-1.91

kindly-1.91

actionDate-1.90

wisdom-1.89

Lear-1.81

arten-1.80

Scrolls-1.79

understanding-1.79

Xer-1.75

INTERVAL 5.992 - 6.658
CONTAINS 0.000%

out
Token out
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000

INTERVAL 5.326 - 5.992
CONTAINS 0.000%

INTERVAL 4.661 - 5.326
CONTAINS 0.000%

INTERVAL 3.995 - 4.661
CONTAINS 0.000%

-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
.
Token.
Feature activation+0.889
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
that
Token that
Feature activation+0.000
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
new
Token new
Feature activation+0.000

INTERVAL 3.329 - 3.995
CONTAINS 0.000%

you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
.
Token.
Feature activation+0.889
Ċ
TokenĊ
Feature activation+0.195

INTERVAL 2.663 - 3.329
CONTAINS 0.000%

XML
Token XML
Feature activation+0.000
out
Token out
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+3.322
,
Token,
Feature activation+6.658
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
that
Token that
Feature activation+0.000
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
new
Token new
Feature activation+0.000
film
Token film
Feature activation+0.000

INTERVAL 1.997 - 2.663
CONTAINS 0.000%

you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+1.779
do
Token do
Feature activation+2.655
not
Token not
Feature activation+1.623
happen
Token happen
Feature activation+0.160
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
probably
Token probably
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+2.081
these
Token these
Feature activation+0.908
patches
Token patches
Feature activation+0.000
contain
Token contain
Feature activation+1.076
wild
Token wild
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000

INTERVAL 1.332 - 1.997
CONTAINS 0.001%

as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+1.779
do
Token do
Feature activation+2.655
not
Token not
Feature activation+1.623
happen
Token happen
Feature activation+0.160
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+1.779
do
Token do
Feature activation+2.655
not
Token not
Feature activation+1.623
happen
Token happen
Feature activation+0.160
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
you
Token you
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+1.350
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
9
Token9
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
read
Token read
Feature activation+0.000
that
Token that
Feature activation+0.000
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
oot
Tokenoot
Feature activation+0.000
opia
Tokenopia
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+1.714
arguably
Token arguably
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000

INTERVAL 0.666 - 1.332
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
read
Token read
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+1.185
McDonald
Token McDonald
Feature activation+0.301
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+1.226
correctly
Token correctly
Feature activation+1.335
:
Token:
Feature activation+4.158
Disney
Token Disney
Feature activation+2.797
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.668
new
Token new
Feature activation+0.000
film
Token film
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
we
Token we
Feature activation+4.163
do
Token do
Feature activation+3.718
X
Token X
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
.
Token.
Feature activation+0.889
Ċ
TokenĊ
Feature activation+0.195
Ċ
TokenĊ
Feature activation+0.000
X
TokenX
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
T
TokenT
Feature activation+0.000
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
probably
Token probably
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
,
Token,
Feature activation+2.081
these
Token these
Feature activation+0.908
patches
Token patches
Feature activation+0.000
contain
Token contain
Feature activation+1.076
wild
Token wild
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000
,
Token,
Feature activation+0.000
There
TokenThere
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.184
Ċ
TokenĊ
Feature activation+0.414
It
TokenIt
Feature activation+0.000
boils
Token boils
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.000 - 0.666
CONTAINS 99.998%

defended
Token defended
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
unfounded
Token unfounded
Feature activation+0.000
claims
Token claims
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
won
Token won
Feature activation+0.000
an
Token an
Feature activation+0.000
election
Token election
Feature activation+0.000
that
Token that
Feature activation+0.000
many
Token many
Feature activation+0.000
ground
Token ground
Feature activation+0.000
lost
Token lost
Feature activation+0.000
in
Token in
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
elections
Token elections
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
seemingly
Token seemingly
Feature activation+0.000
made
Token made
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
north
Token north
Feature activation+0.000
of
Token of
Feature activation+0.000
downtown
Token downtown
Feature activation+0.000
Atlanta
Token Atlanta
Feature activation+0.000
and
Token and
Feature activation+0.000
20
Token 20
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Braves
Token Braves
Feature activation+0.000
routines
Token routines
Feature activation+0.000
and
Token and
Feature activation+0.000
assessed
Token assessed
Feature activation+0.000
their
Token their
Feature activation+0.000
body
Token body
Feature activation+0.000
composition
Token composition
Feature activation+0.000
and
Token and
Feature activation+0.000
timing
Token timing
Feature activation+0.000
of
Token of
Feature activation+0.000
mel
Token mel
Feature activation+0.000
atonin
Tokenatonin
Feature activation+0.000
secretly
Token secretly
Feature activation+0.000
permit
Token permit
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
data
Token data
Feature activation+0.000
streams
Token streams
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
issuance
Token issuance
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H6.5: (feature 1690)

TOP ACTIVATIONS
MAX = 3.585

(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
how
Token how
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
reliable
Token reliable
Feature activation+0.668
we
Token we
Feature activation+0.000
covered
Token covered
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
?
Token?
Feature activation+0.463
The
Token The
Feature activation+1.002
grind
Token grind
Feature activation+0.000
ers
Tokeners
Feature activation+0.025
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
checked
Token checked
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.948
are
Token are
Feature activation+0.743
going
Token going
Feature activation+0.175
usually
Token usually
Feature activation+0.153
win
Token win
Feature activation+0.000
if
Token if
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
reliable
Token reliable
Feature activation+0.668
,
Token,
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
and
Token and
Feature activation+0.000
error
Token error
Feature activation+0.000
all
Token all
Feature activation+0.000
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.948
are
Token are
Feature activation+0.743
going
Token going
Feature activation+0.175
usually
Token usually
Feature activation+0.153
win
Token win
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
reliable
Token reliable
Feature activation+0.668
,
Token,
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
and
Token and
Feature activation+0.000
error
Token error
Feature activation+0.000
-
Token-
Feature activation+0.000
preview
Token preview
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.545
Blue
Token Blue
Feature activation+0.000
Jays
Token Jays
Feature activation+0.000
have
Token have
Feature activation+0.666
an
Token an
Feature activation+0.000
ab
Token ab
Feature activation+0.000
ys
Tokenys
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
mentation
Tokenmentation
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
how
Token how
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
talked
Token talked
Feature activation+0.000
about
Token about
Feature activation+0.000
synergy
Token synergy
Feature activation+0.630
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
noticed
Token noticed
Feature activation+0.000
that
Token that
Feature activation+0.000
divine
Token divine
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
reliable
Token reliable
Feature activation+0.668
,
Token,
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
preview
Token preview
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.545
Blue
Token Blue
Feature activation+0.000
Jays
Token Jays
Feature activation+0.000
have
Token have
Feature activation+0.666
an
Token an
Feature activation+0.000
ab
Token ab
Feature activation+0.000
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.000
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
running
Tokenrunning
Feature activation+0.486
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
loos
Token loos
Feature activation+0.000
have
Token have
Feature activation+0.000
we
Token we
Feature activation+0.000
covered
Token covered
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
?
Token?
Feature activation+0.463
The
Token The
Feature activation+1.002
grind
Token grind
Feature activation+0.000
ers
Tokeners
Feature activation+0.025
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
"
Token"
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
country
Token country
Feature activation+0.000
deserves
Token deserves
Feature activation+0.000
better
Token better
Feature activation+0.000
."
Token."
Feature activation+0.457
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
point
Token point
Feature activation+0.000
about
Token about
Feature activation+0.000
flat
Token flat
Feature activation+0.437
-
Token-
Feature activation+0.000
sharing
Tokensharing
Feature activation+0.064
in
Token in
Feature activation+0.000
books
Token books
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
4
Token 4
Feature activation+0.000
."
Token."
Feature activation+0.000
I
Token I
Feature activation+0.000
say
Token say
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.426
a
Token a
Feature activation+0.375
nice
Token nice
Feature activation+0.000
feature
Token feature
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000

Top DFA by src position
MAX = 4.330

it
Token it
Feature activation-0.071
Top resid features:
all
Token all
Feature activation+0.025
Top resid features:
(
Token (
Feature activation-0.022
Top resid features:
I
TokenI
Feature activation+0.067
Top resid features:
did
Token did
Feature activation+0.115
Top resid features:
say
Token say
Feature activation+4.330
Top resid features:
it
Token it
Feature activation+0.435
Top resid features:
was
Token was
Feature activation+0.112
Top resid features:
creatively
Token creatively
Feature activation+0.000
Top resid features:
twisted
Token twisted
Feature activation+0.000
Top resid features:
!)
Token!)
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.060
Top resid features:
all
Token all
Feature activation+0.036
Top resid features:
(
Token (
Feature activation-0.013
Top resid features:
I
TokenI
Feature activation+0.059
Top resid features:
did
Token did
Feature activation+0.082
Top resid features:
say
Token say
Feature activation+2.772
Top resid features:
it
Token it
Feature activation+0.337
Top resid features:
was
Token was
Feature activation+0.348
Top resid features:
creatively
Token creatively
Feature activation-0.031
Top resid features:
twisted
Token twisted
Feature activation+0.000
Top resid features:
!)
Token!)
Feature activation+0.000
Top resid features:
mentation
Tokenmentation
Feature activation+0.012
Top resid features:
attacks
Token attacks
Feature activation-0.040
Top resid features:
Remember
Token Remember
Feature activation-0.067
Top resid features:
how
Token how
Feature activation+0.325
Top resid features:
I
Token I
Feature activation+0.277
Top resid features:
said
Token said
Feature activation+2.417
Top resid features:
TCP
Token TCP
Feature activation+0.127
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
prov
Tokenprov
Feature activation+0.000
Top resid features:
ides
Tokenides
Feature activation+0.000
Top resid features:
Wings
Token Wings
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
What
Token What
Feature activation+0.046
Top resid features:
have
Token have
Feature activation+0.026
Top resid features:
we
Token we
Feature activation+0.186
Top resid features:
covered
Token covered
Feature activation+1.457
Top resid features:
so
Token so
Feature activation+0.066
Top resid features:
far
Token far
Feature activation+0.109
Top resid features:
?
Token?
Feature activation+0.521
Top resid features:
The
Token The
Feature activation+0.077
Top resid features:
grind
Token grind
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.023
Top resid features:
deck
Token deck
Feature activation+0.046
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.033
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
we
Token we
Feature activation+0.014
Top resid features:
mentioned
Token mentioned
Feature activation+1.873
Top resid features:
that
Token that
Feature activation+0.546
Top resid features:
we
Token we
Feature activation+0.199
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
usually
Token usually
Feature activation+0.000
Top resid features:
mentation
Tokenmentation
Feature activation-0.005
Top resid features:
attacks
Token attacks
Feature activation-0.033
Top resid features:
Remember
Token Remember
Feature activation-0.072
Top resid features:
how
Token how
Feature activation+0.218
Top resid features:
I
Token I
Feature activation+0.165
Top resid features:
said
Token said
Feature activation+1.557
Top resid features:
TCP
Token TCP
Feature activation+0.228
Top resid features:
âĢ
Token âĢ
Feature activation+0.176
Top resid features:
ľ
Tokenľ
Feature activation+0.252
Top resid features:
prov
Tokenprov
Feature activation+0.097
Top resid features:
ides
Tokenides
Feature activation+0.059
Top resid features:
it
Token it
Feature activation-0.032
Top resid features:
all
Token all
Feature activation+0.019
Top resid features:
(
Token (
Feature activation-0.069
Top resid features:
I
TokenI
Feature activation+0.090
Top resid features:
did
Token did
Feature activation+0.228
Top resid features:
say
Token say
Feature activation+1.795
Top resid features:
it
Token it
Feature activation+0.203
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
creatively
Token creatively
Feature activation+0.000
Top resid features:
twisted
Token twisted
Feature activation+0.000
Top resid features:
!)
Token!)
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.014
Top resid features:
deck
Token deck
Feature activation+0.094
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.027
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
we
Token we
Feature activation-0.012
Top resid features:
mentioned
Token mentioned
Feature activation+1.503
Top resid features:
that
Token that
Feature activation+0.491
Top resid features:
we
Token we
Feature activation+0.114
Top resid features:
are
Token are
Feature activation+0.039
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
usually
Token usually
Feature activation+0.000
Top resid features:
mentation
Tokenmentation
Feature activation+0.004
Top resid features:
attacks
Token attacks
Feature activation-0.036
Top resid features:
Remember
Token Remember
Feature activation-0.055
Top resid features:
how
Token how
Feature activation+0.193
Top resid features:
I
Token I
Feature activation+0.201
Top resid features:
said
Token said
Feature activation+1.485
Top resid features:
TCP
Token TCP
Feature activation+0.122
Top resid features:
âĢ
Token âĢ
Feature activation+0.075
Top resid features:
ľ
Tokenľ
Feature activation+0.067
Top resid features:
prov
Tokenprov
Feature activation+0.059
Top resid features:
ides
Tokenides
Feature activation+0.260
Top resid features:
majors
Token majors
Feature activation-0.006
Top resid features:
so
Token so
Feature activation-0.023
Top resid features:
far
Token far
Feature activation-0.025
Top resid features:
.
Token.
Feature activation-0.069
Top resid features:
I
Token I
Feature activation+0.043
Top resid features:
mentioned
Token mentioned
Feature activation+2.044
Top resid features:
in
Token in
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
series
Token series
Feature activation+0.011
Top resid features:
preview
Token preview
Feature activation+0.154
Top resid features:
that
Token that
Feature activation+0.406
Top resid features:
mentation
Tokenmentation
Feature activation+0.008
Top resid features:
attacks
Token attacks
Feature activation-0.025
Top resid features:
Remember
Token Remember
Feature activation-0.032
Top resid features:
how
Token how
Feature activation+0.456
Top resid features:
I
Token I
Feature activation+0.417
Top resid features:
said
Token said
Feature activation+1.077
Top resid features:
TCP
Token TCP
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
prov
Tokenprov
Feature activation+0.000
Top resid features:
ides
Tokenides
Feature activation+0.000
Top resid features:
Last
TokenLast
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
we
Token we
Feature activation+0.100
Top resid features:
talked
Token talked
Feature activation+0.380
Top resid features:
about
Token about
Feature activation+1.156
Top resid features:
synergy
Token synergy
Feature activation+0.224
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
noticed
Token noticed
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
mentation
Tokenmentation
Feature activation+0.001
Top resid features:
attacks
Token attacks
Feature activation-0.044
Top resid features:
Remember
Token Remember
Feature activation-0.049
Top resid features:
how
Token how
Feature activation+0.181
Top resid features:
I
Token I
Feature activation+0.099
Top resid features:
said
Token said
Feature activation+1.454
Top resid features:
TCP
Token TCP
Feature activation+0.170
Top resid features:
âĢ
Token âĢ
Feature activation+0.168
Top resid features:
ľ
Tokenľ
Feature activation+0.149
Top resid features:
prov
Tokenprov
Feature activation+0.007
Top resid features:
ides
Tokenides
Feature activation+0.000
Top resid features:
majors
Token majors
Feature activation-0.005
Top resid features:
so
Token so
Feature activation-0.019
Top resid features:
far
Token far
Feature activation-0.019
Top resid features:
.
Token.
Feature activation-0.052
Top resid features:
I
Token I
Feature activation+0.065
Top resid features:
mentioned
Token mentioned
Feature activation+1.564
Top resid features:
in
Token in
Feature activation+0.088
Top resid features:
the
Token the
Feature activation+0.052
Top resid features:
series
Token series
Feature activation+0.092
Top resid features:
preview
Token preview
Feature activation+0.157
Top resid features:
that
Token that
Feature activation+0.390
Top resid features:
it
Token it
Feature activation-0.080
Top resid features:
all
Token all
Feature activation-0.025
Top resid features:
(
Token (
Feature activation+0.067
Top resid features:
I
TokenI
Feature activation+0.113
Top resid features:
did
Token did
Feature activation+0.293
Top resid features:
say
Token say
Feature activation+1.236
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
creatively
Token creatively
Feature activation+0.000
Top resid features:
twisted
Token twisted
Feature activation+0.000
Top resid features:
!)
Token!)
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
ve
Tokenve
Feature activation+0.002
Top resid features:
been
Token been
Feature activation+0.095
Top resid features:
using
Token using
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
word
Token word
Feature activation+1.838
Top resid features:
âĢ
Token âĢ
Feature activation+0.006
Top resid features:
ľ
Tokenľ
Feature activation-0.050
Top resid features:
running
Tokenrunning
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Wings
Token Wings
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
What
Token What
Feature activation+0.201
Top resid features:
have
Token have
Feature activation-0.005
Top resid features:
we
Token we
Feature activation+0.441
Top resid features:
covered
Token covered
Feature activation+1.139
Top resid features:
so
Token so
Feature activation+0.141
Top resid features:
far
Token far
Feature activation+0.163
Top resid features:
?
Token?
Feature activation+0.194
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
grind
Token grind
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.045
Top resid features:
has
Token has
Feature activation+0.024
Top resid features:
no
Token no
Feature activation+0.010
Top resid features:
interest
Token interest
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
doing
Token doing
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.166
Top resid features:
are
Token are
Feature activation+0.035
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
few
Token few
Feature activation+0.010
Top resid features:
good
Token good
Feature activation+0.013
Top resid features:
men
Token men
Feature activation-0.009
Top resid features:
ident
Tokenident
Feature activation+0.021
Top resid features:
Evil
Token Evil
Feature activation+0.019
Top resid features:
4
Token 4
Feature activation-0.001
Top resid features:
."
Token."
Feature activation-0.021
Top resid features:
I
Token I
Feature activation+0.096
Top resid features:
say
Token say
Feature activation+1.597
Top resid features:
this
Token this
Feature activation+0.270
Top resid features:
was
Token was
Feature activation+0.097
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
nice
Token nice
Feature activation+0.000
Top resid features:
feature
Token feature
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.02

Head 2: 0.05

Head 3: 0.04

Head 4: 0.05

Head 5: 0.39

Head 6: 0.05

Head 7: 0.05

Head 8: 0.08

Head 9: 0.03

Head 10: 0.04

Head 11: 0.13

Positive logits

includes2.15

attracts2.05

+)1.96

phe1.90

inate1.87

helic1.83

reversible1.81

gie1.78

clusive1.77

OUS1.75

entails1.72

~1.72

ulent1.71

vable1.69

downright1.69

inducing1.69

=================================1.68

boasts1.68

cardio1.68

FUL1.67

Negative logits

msg-2.27

Incident-2.05

ucc-2.01

imagined-1.93

eman-1.89

proposition-1.88

consent-1.81

earchers-1.81

-1.81

zeb-1.80

onement-1.80

urred-1.79

fur-1.79

á-1.78

conject-1.77

uma-1.76

-1.75

-1.73

misinterpret-1.73

oiler-1.73

INTERVAL 3.227 - 3.585
CONTAINS 0.000%

(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.868 - 3.227
CONTAINS 0.000%

INTERVAL 2.510 - 2.868
CONTAINS 0.000%

INTERVAL 2.151 - 2.510
CONTAINS 0.000%

I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+0.000

INTERVAL 1.793 - 2.151
CONTAINS 0.000%

INTERVAL 1.434 - 1.793
CONTAINS 0.000%

attacks
Token attacks
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
how
Token how
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
reliable
Token reliable
Feature activation+0.668

INTERVAL 1.076 - 1.434
CONTAINS 0.000%

INTERVAL 0.717 - 1.076
CONTAINS 0.001%

all
Token all
Feature activation+0.000
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
did
Token did
Feature activation+0.000
say
Token say
Feature activation+0.500
it
Token it
Feature activation+0.903
was
Token was
Feature activation+3.585
creatively
Token creatively
Feature activation+2.274
twisted
Token twisted
Feature activation+0.320
!)
Token!)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.948
are
Token are
Feature activation+0.743
going
Token going
Feature activation+0.175
usually
Token usually
Feature activation+0.153
win
Token win
Feature activation+0.000
if
Token if
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.948
are
Token are
Feature activation+0.743
going
Token going
Feature activation+0.175
usually
Token usually
Feature activation+0.153
win
Token win
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
we
Token we
Feature activation+0.000
covered
Token covered
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
?
Token?
Feature activation+0.463
The
Token The
Feature activation+1.002
grind
Token grind
Feature activation+0.000
ers
Tokeners
Feature activation+0.025
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
checked
Token checked
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
reliable
Token reliable
Feature activation+0.668
,
Token,
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
and
Token and
Feature activation+0.000
error
Token error
Feature activation+0.000

INTERVAL 0.359 - 0.717
CONTAINS 0.002%

preview
Token preview
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.545
Blue
Token Blue
Feature activation+0.000
Jays
Token Jays
Feature activation+0.000
have
Token have
Feature activation+0.666
an
Token an
Feature activation+0.000
ab
Token ab
Feature activation+0.000
ys
Tokenys
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
mentation
Tokenmentation
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
how
Token how
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.640
TCP
Token TCP
Feature activation+1.673
âĢ
Token âĢ
Feature activation+0.192
ľ
Tokenľ
Feature activation+0.000
prov
Tokenprov
Feature activation+0.618
ides
Tokenides
Feature activation+0.930
"
Token"
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
country
Token country
Feature activation+0.000
deserves
Token deserves
Feature activation+0.000
better
Token better
Feature activation+0.000
."
Token."
Feature activation+0.457
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
we
Token we
Feature activation+0.000
covered
Token covered
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
?
Token?
Feature activation+0.463
The
Token The
Feature activation+1.002
grind
Token grind
Feature activation+0.000
ers
Tokeners
Feature activation+0.025
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
preview
Token preview
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.545
Blue
Token Blue
Feature activation+0.000
Jays
Token Jays
Feature activation+0.000
have
Token have
Feature activation+0.666
an
Token an
Feature activation+0.000
ab
Token ab
Feature activation+0.000

INTERVAL 0.000 - 0.359
CONTAINS 99.998%

j
Token j
Feature activation+0.000
oust
Tokenoust
Feature activation+0.000
,
Token,
Feature activation+0.000
min
Token min
Feature activation+0.000
st
Tokenst
Feature activation+0.000
rel
Tokenrel
Feature activation+0.000
s
Tokens
Feature activation+0.000
se
Token se
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
the
Token the
Feature activation+0.000
cartel
Token cartel
Feature activation+0.000
's
Token's
Feature activation+0.000
business
Token business
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
1989
Token 1989
Feature activation+0.000
,
Token,
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
public
Token public
Feature activation+0.000
records
Token records
Feature activation+0.000
the
Token the
Feature activation+0.000
amount
Token amount
Feature activation+0.000
invested
Token invested
Feature activation+0.000
was
Token was
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.000
30
Token30
Feature activation+0.000
million
Token million
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
The
TokenThe
Feature activation+0.000
party
Token party
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
state
Token state
Feature activation+0.000
President
Token President
Feature activation+0.000
Y
Token Y
Feature activation+0.000
eddy
Tokeneddy
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
appa
Tokenappa
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
incorporated
Token incorporated
Feature activation+0.000
in
Token in
Feature activation+0.000
many
Token many
Feature activation+0.000
recent
Token recent
Feature activation+0.000
models
Token models
Feature activation+0.000
for
Token for
Feature activation+0.000
shell
Token shell
Feature activation+0.000
growth
Token growth
Feature activation+0.000
(
Token (
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H6.5: (feature 18035)

TOP ACTIVATIONS
MAX = 3.797

.
Token.
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
Brian
TokenBrian
Feature activation+0.000
Snyder
Token Snyder
Feature activation+0.274
Donald
Token Donald
Feature activation+3.797
Trump
Token Trump
Feature activation+2.671
took
Token took
Feature activation+0.525
a
Token a
Feature activation+0.249
shot
Token shot
Feature activation+0.386
at
Token at
Feature activation+0.351
Sean
Token Sean
Feature activation+0.000
Gallup
Token Gallup
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.875
Angela
Token Angela
Feature activation+3.121
Merkel
Token Merkel
Feature activation+1.503
:
Token:
Feature activation+0.600
No
Token No
Feature activation+0.601
special
Token special
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
How
Token How
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.401
Ċ
TokenĊ
Feature activation+2.719
Three
TokenThree
Feature activation+0.485
outs
Token outs
Feature activation+0.094
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
Brian
TokenBrian
Feature activation+0.000
Snyder
Token Snyder
Feature activation+0.274
Donald
Token Donald
Feature activation+3.797
Trump
Token Trump
Feature activation+2.671
took
Token took
Feature activation+0.525
a
Token a
Feature activation+0.249
shot
Token shot
Feature activation+0.386
at
Token at
Feature activation+0.351
President
Token President
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
De
Token De
Feature activation+0.000
aren
Tokenaren
Feature activation+0.000
/
Token /
Feature activation+0.000
AP
Token AP
Feature activation+0.000
Dwight
Token Dwight
Feature activation+2.185
Chandler
Token Chandler
Feature activation+1.851
walks
Token walks
Feature activation+0.324
through
Token through
Feature activation+0.033
his
Token his
Feature activation+0.090
flood
Token flood
Feature activation+0.050
Justin
Token Justin
Feature activation+0.627
Sullivan
Token Sullivan
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.284
Larry
Token Larry
Feature activation+2.158
Ellison
Token Ellison
Feature activation+2.033
just
Token just
Feature activation+1.138
increased
Token increased
Feature activation+0.799
his
Token his
Feature activation+0.000
personal
Token personal
Feature activation+0.000
entially
Tokenentially
Feature activation+0.000
be
Token be
Feature activation+0.000
significant
Token significant
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.233
Ċ
TokenĊ
Feature activation+2.044
Michael
TokenMichael
Feature activation+0.000
Walters
Token Walters
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Sullivan
Token Sullivan
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.284
Larry
Token Larry
Feature activation+2.158
Ellison
Token Ellison
Feature activation+2.033
just
Token just
Feature activation+1.138
increased
Token increased
Feature activation+0.799
his
Token his
Feature activation+0.000
personal
Token personal
Feature activation+0.000
credit
Token credit
Feature activation+0.000
arm
Tokenarm
Feature activation+0.000
id
Tokenid
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
When
Token When
Feature activation+1.996
Australian
Token Australian
Feature activation+0.192
research
Token research
Feature activation+0.000
professor
Token professor
Feature activation+0.151
Paul
Token Paul
Feature activation+0.000
Glas
Token Glas
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
CBC
TokenCBC
Feature activation+0.000
)
Token)
Feature activation+1.055
Ċ
TokenĊ
Feature activation+1.652
Ċ
TokenĊ
Feature activation+1.884
In
TokenIn
Feature activation+0.071
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
Photograph
Token Photograph
Feature activation+0.000
:
Token:
Feature activation+0.000
Public
Token Public
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.531
Ċ
TokenĊ
Feature activation+1.853
If
TokenIf
Feature activation+0.708
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
De
Token De
Feature activation+0.000
aren
Tokenaren
Feature activation+0.000
/
Token /
Feature activation+0.000
AP
Token AP
Feature activation+0.000
Dwight
Token Dwight
Feature activation+2.185
Chandler
Token Chandler
Feature activation+1.851
walks
Token walks
Feature activation+0.324
through
Token through
Feature activation+0.033
his
Token his
Feature activation+0.090
flood
Token flood
Feature activation+0.050
-
Token-
Feature activation+0.000
/
Token /
Feature activation+0.000
Times
Token Times
Feature activation+0.000
Union
Token Union
Feature activation+0.000
)
Token)
Feature activation+0.326
Ronald
Token Ronald
Feature activation+1.767
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
ribbon
Token ribbon
Feature activation+1.814
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
ribbon
Token ribbon
Feature activation+1.814
to
Token to
Feature activation+0.960
officially
Token officially
Feature activation+0.714
open
Token open
Feature activation+1.301
the
Token the
Feature activation+0.596
new
Token new
Feature activation+0.599
Barnes
Token Barnes
Feature activation+0.000
/
Token /
Feature activation+0.000
Times
Token Times
Feature activation+0.000
Union
Token Union
Feature activation+0.000
)
Token)
Feature activation+0.326
Ronald
Token Ronald
Feature activation+1.767
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
ature
Tokenature
Feature activation+0.000
n
Tokenn
Feature activation+0.000
/
Token /
Feature activation+0.000
Getty
Token Getty
Feature activation+0.000
Images
Token Images
Feature activation+0.355
Rep
Token Rep
Feature activation+1.758
.
Token.
Feature activation+0.825
Keith
Token Keith
Feature activation+0.328
Ellison
Token Ellison
Feature activation+0.714
and
Token and
Feature activation+0.013
Sanders
Token Sanders
Feature activation+0.137
)
Token)
Feature activation+0.326
Ronald
Token Ronald
Feature activation+1.767
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
ribbon
Token ribbon
Feature activation+1.814
to
Token to
Feature activation+0.960
officially
Token officially
Feature activation+0.714
open
Token open
Feature activation+1.301
/
Token /
Feature activation+0.000
AFP
Token AFP
Feature activation+0.000
/
Token /
Feature activation+0.000
Getty
Token Getty
Feature activation+0.000
Images
Token Images
Feature activation+0.033
President
Token President
Feature activation+1.751
Obama
Token Obama
Feature activation+0.943
and
Token and
Feature activation+0.148
Oklahoma
Token Oklahoma
Feature activation+0.052
's
Token's
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
179
Token179
Feature activation+0.566
@
Token@
Feature activation+0.000
N
TokenN
Feature activation+0.000
00
Token00
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.619
Ċ
TokenĊ
Feature activation+1.684
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
E
Token E
Feature activation+0.000
ighty
Tokenighty
Feature activation+0.000
percent
Token percent
Feature activation+0.000
Damascus
Token Damascus
Feature activation+0.570
Police
Token Police
Feature activation+0.005
Force
Token Force
Feature activation+0.740
.
Token.
Feature activation+1.111
Ċ
TokenĊ
Feature activation+0.373
Ċ
TokenĊ
Feature activation+1.665
The
TokenThe
Feature activation+0.306
inf
Token inf
Feature activation+0.000
ighting
Tokenighting
Feature activation+0.035
has
Token has
Feature activation+0.000
brought
Token brought
Feature activation+0.000

Top DFA by src position
MAX = 3.048

and
Token and
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.002
Top resid features:
Donald
TokenDonald
Feature activation+0.021
Top resid features:
Trump
Token Trump
Feature activation+0.049
Top resid features:
.
Token.
Feature activation+0.159
Top resid features:
REUTERS
Token REUTERS
Feature activation+3.048
Top resid features:
/
Token/
Feature activation+0.397
Top resid features:
Brian
TokenBrian
Feature activation+0.161
Top resid features:
Snyder
Token Snyder
Feature activation+0.294
Top resid features:
Donald
Token Donald
Feature activation+0.149
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
Chancellor
Token Chancellor
Feature activation-0.007
Top resid features:
Angela
Token Angela
Feature activation-0.002
Top resid features:
Merkel
Token Merkel
Feature activation-0.015
Top resid features:
|
Token |
Feature activation+0.413
Top resid features:
Sean
Token Sean
Feature activation+0.193
Top resid features:
Gallup
Token Gallup
Feature activation+1.424
Top resid features:
/
Token/
Feature activation+0.403
Top resid features:
Getty
TokenGetty
Feature activation+0.771
Top resid features:
Images
Token Images
Feature activation+0.409
Top resid features:
Angela
Token Angela
Feature activation+0.042
Top resid features:
Merkel
Token Merkel
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.097
Top resid features:
Harry
TokenHarry
Feature activation+0.062
Top resid features:
How
Token How
Feature activation+0.025
Top resid features:
/
Token/
Feature activation+0.080
Top resid features:
Getty
TokenGetty
Feature activation+1.151
Top resid features:
Images
Token Images
Feature activation+1.340
Top resid features:
Ċ
TokenĊ
Feature activation+0.674
Top resid features:
Ċ
TokenĊ
Feature activation+0.266
Top resid features:
Three
TokenThree
Feature activation+0.000
Top resid features:
outs
Token outs
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
Donald
TokenDonald
Feature activation+0.018
Top resid features:
Trump
Token Trump
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.229
Top resid features:
REUTERS
Token REUTERS
Feature activation+2.117
Top resid features:
/
Token/
Feature activation+0.352
Top resid features:
Brian
TokenBrian
Feature activation+0.111
Top resid features:
Snyder
Token Snyder
Feature activation+0.123
Top resid features:
Donald
Token Donald
Feature activation+0.165
Top resid features:
Trump
Token Trump
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Jason
TokenJason
Feature activation+0.030
Top resid features:
De
Token De
Feature activation+0.002
Top resid features:
aren
Tokenaren
Feature activation-0.004
Top resid features:
/
Token /
Feature activation+0.513
Top resid features:
AP
Token AP
Feature activation+2.185
Top resid features:
Dwight
Token Dwight
Feature activation+0.072
Top resid features:
Chandler
Token Chandler
Feature activation+0.000
Top resid features:
walks
Token walks
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation-0.003
Top resid features:
umber
Tokenumber
Feature activation-0.007
Top resid features:
one
Tokenone
Feature activation+0.002
Top resid features:
2
Token2
Feature activation-0.003
Top resid features:
/
Token/
Feature activation+0.011
Top resid features:
Flickr
TokenFlickr
Feature activation+1.239
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
Justin
Token Justin
Feature activation+0.049
Top resid features:
Sullivan
Token Sullivan
Feature activation+0.150
Top resid features:
/
Token/
Feature activation+0.093
Top resid features:
Getty
TokenGetty
Feature activation+0.280
Top resid features:
ing
Tokening
Feature activation-0.003
Top resid features:
facility
Token facility
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
(
Token (
Feature activation+0.195
Top resid features:
CBC
TokenCBC
Feature activation+0.028
Top resid features:
)
Token)
Feature activation+2.505
Top resid features:
However
Token However
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
report
Token report
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
en
Tokenen
Feature activation-0.005
Top resid features:
umber
Tokenumber
Feature activation-0.009
Top resid features:
one
Tokenone
Feature activation+0.001
Top resid features:
2
Token2
Feature activation-0.019
Top resid features:
/
Token/
Feature activation+0.038
Top resid features:
Flickr
TokenFlickr
Feature activation+0.785
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
Justin
Token Justin
Feature activation+0.051
Top resid features:
Sullivan
Token Sullivan
Feature activation+0.198
Top resid features:
/
Token/
Feature activation+0.286
Top resid features:
Getty
TokenGetty
Feature activation+0.394
Top resid features:
di
Tokendi
Feature activation-0.003
Top resid features:
arm
Tokenarm
Feature activation+0.018
Top resid features:
id
Tokenid
Feature activation+0.004
Top resid features:
/
Token/
Feature activation+0.694
Top resid features:
Getty
TokenGetty
Feature activation+0.503
Top resid features:
Images
Token Images
Feature activation+1.071
Top resid features:
When
Token When
Feature activation+0.153
Top resid features:
Australian
Token Australian
Feature activation+0.000
Top resid features:
research
Token research
Feature activation+0.000
Top resid features:
professor
Token professor
Feature activation+0.000
Top resid features:
Paul
Token Paul
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
Vancouver
Token Vancouver
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.285
Top resid features:
(
Token (
Feature activation+0.328
Top resid features:
CBC
TokenCBC
Feature activation+0.021
Top resid features:
)
Token)
Feature activation+1.882
Top resid features:
Ċ
TokenĊ
Feature activation+0.233
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
In
TokenIn
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
ic
Tokenic
Feature activation+0.010
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
Kas
Token Kas
Feature activation-0.002
Top resid features:
sel
Tokensel
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.093
Top resid features:
Photograph
Token Photograph
Feature activation+0.976
Top resid features:
:
Token:
Feature activation+0.389
Top resid features:
Public
Token Public
Feature activation+0.052
Top resid features:
ity
Tokenity
Feature activation+0.099
Top resid features:
Ċ
TokenĊ
Feature activation+0.198
Top resid features:
Ċ
TokenĊ
Feature activation+0.089
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Jason
TokenJason
Feature activation+0.009
Top resid features:
De
Token De
Feature activation+0.004
Top resid features:
aren
Tokenaren
Feature activation-0.008
Top resid features:
/
Token /
Feature activation+0.493
Top resid features:
AP
Token AP
Feature activation+1.573
Top resid features:
Dwight
Token Dwight
Feature activation+0.254
Top resid features:
Chandler
Token Chandler
Feature activation+0.139
Top resid features:
walks
Token walks
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
Steve
TokenSteve
Feature activation+0.019
Top resid features:
Barnes
Token Barnes
Feature activation+0.015
Top resid features:
/
Token /
Feature activation+0.133
Top resid features:
Times
Token Times
Feature activation+0.028
Top resid features:
Union
Token Union
Feature activation+0.012
Top resid features:
)
Token)
Feature activation+1.695
Top resid features:
Ronald
Token Ronald
Feature activation+0.206
Top resid features:
McDonald
Token McDonald
Feature activation+0.157
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
cut
Token cut
Feature activation+0.000
Top resid features:
Steve
TokenSteve
Feature activation+0.025
Top resid features:
Barnes
Token Barnes
Feature activation+0.023
Top resid features:
/
Token /
Feature activation+0.268
Top resid features:
Times
Token Times
Feature activation+0.054
Top resid features:
Union
Token Union
Feature activation+0.008
Top resid features:
)
Token)
Feature activation+1.624
Top resid features:
Ronald
Token Ronald
Feature activation+0.146
Top resid features:
McDonald
Token McDonald
Feature activation+0.109
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
children
Token children
Feature activation+0.057
Top resid features:
cut
Token cut
Feature activation+0.007
Top resid features:
Steve
TokenSteve
Feature activation+0.076
Top resid features:
Barnes
Token Barnes
Feature activation+0.062
Top resid features:
/
Token /
Feature activation+0.429
Top resid features:
Times
Token Times
Feature activation+0.087
Top resid features:
Union
Token Union
Feature activation+0.048
Top resid features:
)
Token)
Feature activation+0.980
Top resid features:
Ronald
Token Ronald
Feature activation+0.217
Top resid features:
McDonald
Token McDonald
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
cut
Token cut
Feature activation+0.000
Top resid features:
M
Token M
Feature activation-0.008
Top resid features:
ature
Tokenature
Feature activation+0.020
Top resid features:
n
Tokenn
Feature activation-0.008
Top resid features:
/
Token /
Feature activation+0.453
Top resid features:
Getty
Token Getty
Feature activation+0.807
Top resid features:
Images
Token Images
Feature activation+0.927
Top resid features:
Rep
Token Rep
Feature activation+0.120
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Keith
Token Keith
Feature activation+0.000
Top resid features:
Ellison
Token Ellison
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Steve
TokenSteve
Feature activation+0.031
Top resid features:
Barnes
Token Barnes
Feature activation+0.019
Top resid features:
/
Token /
Feature activation+0.229
Top resid features:
Times
Token Times
Feature activation+0.099
Top resid features:
Union
Token Union
Feature activation+0.016
Top resid features:
)
Token)
Feature activation+1.409
Top resid features:
Ronald
Token Ronald
Feature activation+0.111
Top resid features:
McDonald
Token McDonald
Feature activation+0.085
Top resid features:
and
Token and
Feature activation-0.029
Top resid features:
children
Token children
Feature activation+0.015
Top resid features:
cut
Token cut
Feature activation-0.061
Top resid features:
S
TokenS
Feature activation+0.004
Top resid features:
aul
Tokenaul
Feature activation-0.033
Top resid features:
Lo
Token Lo
Feature activation-0.007
Top resid features:
eb
Tokeneb
Feature activation-0.002
Top resid features:
/
Token /
Feature activation+0.388
Top resid features:
AFP
Token AFP
Feature activation+0.791
Top resid features:
/
Token /
Feature activation+0.182
Top resid features:
Getty
Token Getty
Feature activation+0.359
Top resid features:
Images
Token Images
Feature activation+0.405
Top resid features:
President
Token President
Feature activation+0.085
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
unable
Token unable
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
turn
Token turn
Feature activation-0.000
Top resid features:
around
Token around
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.197
Top resid features:
Flickr
Token Flickr
Feature activation+0.927
Top resid features:
:
Token:
Feature activation+0.597
Top resid features:
43
Token 43
Feature activation+0.157
Top resid features:
008
Token008
Feature activation+0.049
Top resid features:
179
Token179
Feature activation+0.027
Top resid features:
@
Token@
Feature activation+0.024
Top resid features:
Police
Token Police
Feature activation+0.008
Top resid features:
officer
Token officer
Feature activation+0.075
Top resid features:
in
Token in
Feature activation+0.059
Top resid features:
April
Token April
Feature activation+0.064
Top resid features:
.
Token.
Feature activation+0.291
Top resid features:
Photo
Token Photo
Feature activation+1.491
Top resid features:
courtesy
Token courtesy
Feature activation+0.211
Top resid features:
of
Token of
Feature activation+0.065
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
Damascus
Token Damascus
Feature activation+0.011
Top resid features:
Police
Token Police
Feature activation+0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.02

Head 2: 0.06

Head 3: 0.06

Head 4: 0.08

Head 5: 0.39

Head 6: 0.07

Head 7: 0.04

Head 8: 0.08

Head 9: 0.04

Head 10: 0.03

Head 11: 0.07

Positive logits

zens2.37

olars2.24

otin2.14

annabin2.11

cientious2.07

efficients2.07

zees1.96

ients1.96

ashtra1.93

uala1.90

phrine1.87

ivities1.86

ilies1.85

iless1.83

umar1.83

heric1.82

utical1.81

opoly1.79

utic1.78

etitive1.78

Negative logits

��-2.43

Winged-2.23

="/-2.12

blogspot-1.90

Retrieved-1.87

Blog-1.86

Shutterstock-1.84

STL-1.82

ESV-1.81

Reference-1.78

gallery-1.77

Date-1.76

Avenger-1.75

Tribune-1.75

info-1.75

Posts-1.74

-1.74

Norn-1.73

iHUD-1.73

www-1.73

INTERVAL 3.417 - 3.797
CONTAINS 0.000%

.
Token.
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
Brian
TokenBrian
Feature activation+0.000
Snyder
Token Snyder
Feature activation+0.274
Donald
Token Donald
Feature activation+3.797
Trump
Token Trump
Feature activation+2.671
took
Token took
Feature activation+0.525
a
Token a
Feature activation+0.249
shot
Token shot
Feature activation+0.386
at
Token at
Feature activation+0.351

INTERVAL 3.038 - 3.417
CONTAINS 0.000%

Sean
Token Sean
Feature activation+0.000
Gallup
Token Gallup
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.875
Angela
Token Angela
Feature activation+3.121
Merkel
Token Merkel
Feature activation+1.503
:
Token:
Feature activation+0.600
No
Token No
Feature activation+0.601
special
Token special
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000

INTERVAL 2.658 - 3.038
CONTAINS 0.000%

How
Token How
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.401
Ċ
TokenĊ
Feature activation+2.719
Three
TokenThree
Feature activation+0.485
outs
Token outs
Feature activation+0.094
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
Brian
TokenBrian
Feature activation+0.000
Snyder
Token Snyder
Feature activation+0.274
Donald
Token Donald
Feature activation+3.797
Trump
Token Trump
Feature activation+2.671
took
Token took
Feature activation+0.525
a
Token a
Feature activation+0.249
shot
Token shot
Feature activation+0.386
at
Token at
Feature activation+0.351
President
Token President
Feature activation+0.000

INTERVAL 2.278 - 2.658
CONTAINS 0.000%

INTERVAL 1.899 - 2.278
CONTAINS 0.001%

arm
Tokenarm
Feature activation+0.000
id
Tokenid
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
When
Token When
Feature activation+1.996
Australian
Token Australian
Feature activation+0.192
research
Token research
Feature activation+0.000
professor
Token professor
Feature activation+0.151
Paul
Token Paul
Feature activation+0.000
Glas
Token Glas
Feature activation+0.000
entially
Tokenentially
Feature activation+0.000
be
Token be
Feature activation+0.000
significant
Token significant
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.233
Ċ
TokenĊ
Feature activation+2.044
Michael
TokenMichael
Feature activation+0.000
Walters
Token Walters
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Justin
Token Justin
Feature activation+0.627
Sullivan
Token Sullivan
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.284
Larry
Token Larry
Feature activation+2.158
Ellison
Token Ellison
Feature activation+2.033
just
Token just
Feature activation+1.138
increased
Token increased
Feature activation+0.799
his
Token his
Feature activation+0.000
personal
Token personal
Feature activation+0.000
Sullivan
Token Sullivan
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.284
Larry
Token Larry
Feature activation+2.158
Ellison
Token Ellison
Feature activation+2.033
just
Token just
Feature activation+1.138
increased
Token increased
Feature activation+0.799
his
Token his
Feature activation+0.000
personal
Token personal
Feature activation+0.000
credit
Token credit
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
De
Token De
Feature activation+0.000
aren
Tokenaren
Feature activation+0.000
/
Token /
Feature activation+0.000
AP
Token AP
Feature activation+0.000
Dwight
Token Dwight
Feature activation+2.185
Chandler
Token Chandler
Feature activation+1.851
walks
Token walks
Feature activation+0.324
through
Token through
Feature activation+0.033
his
Token his
Feature activation+0.090
flood
Token flood
Feature activation+0.050

INTERVAL 1.519 - 1.899
CONTAINS 0.002%

Barnes
Token Barnes
Feature activation+0.000
/
Token /
Feature activation+0.000
Times
Token Times
Feature activation+0.000
Union
Token Union
Feature activation+0.000
)
Token)
Feature activation+0.326
Ronald
Token Ronald
Feature activation+1.767
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
/
Token /
Feature activation+0.000
Times
Token Times
Feature activation+0.000
Union
Token Union
Feature activation+0.000
)
Token)
Feature activation+0.326
Ronald
Token Ronald
Feature activation+1.767
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
ribbon
Token ribbon
Feature activation+1.814
nd
Tokennd
Feature activation+0.000
W
Token W
Feature activation+0.000
ieg
Tokenieg
Feature activation+0.000
mann
Tokenmann
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.893
Ċ
TokenĊ
Feature activation+1.610
Two
TokenTwo
Feature activation+0.547
of
Token of
Feature activation+0.788
the
Token the
Feature activation+0.310
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.221
Ċ
TokenĊ
Feature activation+1.606
C
TokenC
Feature activation+0.186
alled
Tokenalled
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
preserve
Token preserve
Feature activation+0.000
)
Token)
Feature activation+0.326
Ronald
Token Ronald
Feature activation+1.767
McDonald
Token McDonald
Feature activation+1.836
and
Token and
Feature activation+1.240
children
Token children
Feature activation+1.268
cut
Token cut
Feature activation+1.752
the
Token the
Feature activation+1.209
ribbon
Token ribbon
Feature activation+1.814
to
Token to
Feature activation+0.960
officially
Token officially
Feature activation+0.714
open
Token open
Feature activation+1.301

INTERVAL 1.139 - 1.519
CONTAINS 0.003%

owski
Tokenowski
Feature activation+0.000
/
Token/
Feature activation+0.000
Associated
TokenAssociated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.298
Ċ
TokenĊ
Feature activation+1.502
Former
TokenFormer
Feature activation+0.577
Milwaukee
Token Milwaukee
Feature activation+0.000
Bucks
Token Bucks
Feature activation+0.000
center
Token center
Feature activation+0.196
Larry
Token Larry
Feature activation+0.000
.
Token.
Feature activation+0.000
Reuters
Token Reuters
Feature activation+0.000
/
Token/
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
Reed
Token Reed
Feature activation+0.000
The
Token The
Feature activation+1.506
world
Token world
Feature activation+1.043
has
Token has
Feature activation+0.388
no
Token no
Feature activation+0.066
crystal
Token crystal
Feature activation+0.000
ball
Token ball
Feature activation+0.000
AN
TokenAN
Feature activation+0.000
-
Token -
Feature activation+0.000
All
Token All
Feature activation+0.000
rights
Token rights
Feature activation+0.000
reserved
Token reserved
Feature activation+0.205
Alonso
Token Alonso
Feature activation+1.334
Sol
Token Sol
Feature activation+1.137
is
Tokenis
Feature activation+0.421
of
Token of
Feature activation+0.684
Austin
Token Austin
Feature activation+0.408
was
Token was
Feature activation+0.388
Thomas
TokenThomas
Feature activation+0.000
Picture
Token Picture
Feature activation+0.011
:
Token:
Feature activation+0.000
Barry
Token Barry
Feature activation+0.000
Goodwin
Token Goodwin
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.180
Ċ
TokenĊ
Feature activation+1.140
G
TokenG
Feature activation+0.194
illing
Tokenilling
Feature activation+0.000
ham
Tokenham
Feature activation+0.296
were
Token were
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
Reed
Token Reed
Feature activation+0.000
/
Token/
Feature activation+0.000
Reuters
TokenReuters
Feature activation+0.070
))
Token))
Feature activation+0.000
Two
Token Two
Feature activation+1.298
white
Token white
Feature activation+0.056
supremacists
Token supremacists
Feature activation+0.065
allegedly
Token allegedly
Feature activation+0.000
plotted
Token plotted
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.759 - 1.139
CONTAINS 0.007%

rocket
Token rocket
Feature activation+0.208
.
Token.
Feature activation+0.288
The
Token The
Feature activation+0.562
DJ
TokenDJ
Feature activation+0.019
The
Token The
Feature activation+0.731
conflicting
Token conflicting
Feature activation+0.946
qualities
Token qualities
Feature activation+0.683
in
Token in
Feature activation+0.206
Major
Token Major
Feature activation+0.627
ana
Tokenana
Feature activation+0.263
f
Token f
Feature activation+0.000
Car
TokenCar
Feature activation+0.000
bon
Tokenbon
Feature activation+1.099
B
TokenB
Feature activation+0.000
rief
Tokenrief
Feature activation+0.113
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.853
Different
TokenDifferent
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000
emerge
Token emerge
Feature activation+0.000
when
Token when
Feature activation+0.000
climate
Token climate
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.284
Larry
Token Larry
Feature activation+2.158
Ellison
Token Ellison
Feature activation+2.033
just
Token just
Feature activation+1.138
increased
Token increased
Feature activation+0.799
his
Token his
Feature activation+0.000
personal
Token personal
Feature activation+0.000
credit
Token credit
Feature activation+0.000
line
Token line
Feature activation+0.000
ISH
TokenISH
Feature activation+0.000
-
Token -
Feature activation+0.000
All
Token All
Feature activation+0.000
rights
Token rights
Feature activation+0.000
reserved
Token reserved
Feature activation+0.000
The
Token The
Feature activation+1.069
woman
Token woman
Feature activation+0.511
calls
Token calls
Feature activation+0.131
herself
Token herself
Feature activation+0.083
Jo
Token Jo
Feature activation+0.000
anna
Tokenanna
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.055
News
Token News
Feature activation+0.000
.
Token.
Feature activation+0.616
Ċ
TokenĊ
Feature activation+0.080
Ċ
TokenĊ
Feature activation+0.851
âĢ
TokenâĢ
Feature activation+0.226
ľ
Tokenľ
Feature activation+0.617
By
TokenBy
Feature activation+0.000
talking
Token talking
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.380 - 0.759
CONTAINS 0.028%

Ċ
TokenĊ
Feature activation+0.000
Link
TokenLink
Feature activation+0.000
edin
Tokenedin
Feature activation+0.000
email
Token email
Feature activation+0.000
Print
Token Print
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.503
Ċ
TokenĊ
Feature activation+0.489
Over
TokenOver
Feature activation+0.019
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
va
Tokenva
Feature activation+0.000
/
Token/
Feature activation+0.000
CBC
TokenCBC
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.584
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.000
is
Token is
Feature activation+0.000
always
Token always
Feature activation+0.000
.
Token.
Feature activation+0.288
The
Token The
Feature activation+0.562
DJ
TokenDJ
Feature activation+0.019
The
Token The
Feature activation+0.731
conflicting
Token conflicting
Feature activation+0.946
qualities
Token qualities
Feature activation+0.683
in
Token in
Feature activation+0.206
Major
Token Major
Feature activation+0.627
ana
Tokenana
Feature activation+0.263
f
Token f
Feature activation+0.000
erm
Tokenerm
Feature activation+0.000
L
TokenL
Feature activation+0.000
ONDON
TokenONDON
Feature activation+0.000
(
Token (
Feature activation+0.000
Reuters
TokenReuters
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.430
China
Token China
Feature activation+0.004
has
Token has
Feature activation+0.000
invited
Token invited
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
one
Tokenone
Feature activation+0.000
2
Token2
Feature activation+0.000
/
Token/
Feature activation+0.000
Flickr
TokenFlickr
Feature activation+0.000
,
Token,
Feature activation+0.000
Justin
Token Justin
Feature activation+0.627
Sullivan
Token Sullivan
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.284
Larry
Token Larry
Feature activation+2.158

INTERVAL 0.000 - 0.380
CONTAINS 99.960%

considerably
Token considerably
Feature activation+0.000
better
Token better
Feature activation+0.000
than
Token than
Feature activation+0.000
contempor
Token contempor
Feature activation+0.000
aneous
Tokenaneous
Feature activation+0.000
Snapdragon
Token Snapdragon
Feature activation+0.000
8
Token 8
Feature activation+0.000
10
Token10
Feature activation+0.000
chips
Token chips
Feature activation+0.000
and
Token and
Feature activation+0.000
were
Token were
Feature activation+0.000
major
Token major
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
from
Token from
Feature activation+0.000
Las
Token Las
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
Sands
Token Sands
Feature activation+0.000
Corporation
Token Corporation
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
Sheldon
Token Sheldon
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
research
Token research
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
some
Token some
Feature activation+0.000
studies
Token studies
Feature activation+0.000
investigating
Token investigating
Feature activation+0.000
If
TokenIf
Feature activation+0.000
you
Token you
Feature activation+0.000
would
Token would
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
remove
Token remove
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
B
Token B
Feature activation+0.000
augh
Tokenaugh
Feature activation+0.000
from
Token from
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
show
Token show
Feature activation+0.000
is
Token is
Feature activation+0.000
playing
Token playing
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
like
Token like
Feature activation+0.000
it
Token it
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H6.5: (feature 2238)

TOP ACTIVATIONS
MAX = 4.860

,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.202
,
Token,
Feature activation+4.860
if
Token if
Feature activation+3.587
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
propensity
Token propensity
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
step
Token step
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.946
.
Token.
Feature activation+2.090
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Jun
Token Jun
Feature activation+0.000
cker
Tokencker
Feature activation+0.000
streak
Token streak
Feature activation+0.000
y
Tokeny
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.933
.
Token.
Feature activation+1.705
Other
Token Other
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.202
,
Token,
Feature activation+4.860
if
Token if
Feature activation+3.587
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
perceived
Token perceived
Feature activation+0.000
bad
Token bad
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.202
,
Token,
Feature activation+4.860
if
Token if
Feature activation+3.587
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
sighted
Tokensighted
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
propensity
Token propensity
Feature activation+0.000
to
Token to
Feature activation+0.000
ed
Tokened
Feature activation+0.000
peculiar
Token peculiar
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.181
.
Token.
Feature activation+0.836
Each
Token Each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
argument
Token argument
Feature activation+0.000
step
Token step
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.946
.
Token.
Feature activation+2.090
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Jun
Token Jun
Feature activation+0.000
cker
Tokencker
Feature activation+0.000
even
Token even
Feature activation+0.000
y
Tokeny
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.933
.
Token.
Feature activation+1.705
Other
Token Other
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
games
Token games
Feature activation+0.000
peculiar
Token peculiar
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.181
.
Token.
Feature activation+0.836
Each
Token Each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
argument
Token argument
Feature activation+0.000
you
Token you
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
propensity
Token propensity
Feature activation+0.000
to
Token to
Feature activation+0.000
dwell
Token dwell
Feature activation+0.000
event
Token event
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
yes
Token yes
Feature activation+0.000
vote
Token vote
Feature activation+0.000
.
Token.
Feature activation+0.228
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Will
TokenWill
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.000
still
Token still
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
90
Token 90
Feature activation+0.000
s
Tokens
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.136
but
Token but
Feature activation+0.000
to
Token to
Feature activation+0.000
dismiss
Token dismiss
Feature activation+0.000
AV
Token AV
Feature activation+0.000
right
Token right
Feature activation+0.000
this
Token this
Feature activation+0.000
team
Token team
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
enough
Token enough
Feature activation+0.000
along
Token along
Feature activation+0.024
yet
Token yet
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
worrying
Token worrying
Feature activation+0.000
about
Token about
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
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
<|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
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

Top DFA by src position
MAX = 5.813

bad
Token bad
Feature activation+0.184
Top resid features:
,
Token,
Feature activation-0.830
Top resid features:
to
Token to
Feature activation+0.164
Top resid features:
say
Token say
Feature activation+1.148
Top resid features:
the
Token the
Feature activation+0.465
Top resid features:
least
Token least
Feature activation+5.562
Top resid features:
,
Token,
Feature activation+0.592
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
Apple
Token Apple
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sighted
Tokensighted
Feature activation+0.648
Top resid features:
,
Token,
Feature activation-0.478
Top resid features:
to
Token to
Feature activation+0.293
Top resid features:
say
Token say
Feature activation+0.944
Top resid features:
the
Token the
Feature activation+0.459
Top resid features:
least
Token least
Feature activation+4.766
Top resid features:
,
Token,
Feature activation+0.891
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
considering
Token considering
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
current
Token current
Feature activation+0.000
Top resid features:
extreme
Token extreme
Feature activation+0.060
Top resid features:
step
Token step
Feature activation+0.067
Top resid features:
to
Token to
Feature activation+0.232
Top resid features:
say
Token say
Feature activation+0.393
Top resid features:
the
Token the
Feature activation+0.366
Top resid features:
least
Token least
Feature activation+5.813
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Mr
Token Mr
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Jun
Token Jun
Feature activation+0.000
Top resid features:
cker
Tokencker
Feature activation+0.000
Top resid features:
streak
Token streak
Feature activation-0.101
Top resid features:
y
Tokeny
Feature activation+0.075
Top resid features:
to
Token to
Feature activation+0.234
Top resid features:
say
Token say
Feature activation+0.525
Top resid features:
the
Token the
Feature activation+0.248
Top resid features:
least
Token least
Feature activation+5.789
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Other
Token Other
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
bad
Token bad
Feature activation+0.481
Top resid features:
,
Token,
Feature activation-0.213
Top resid features:
to
Token to
Feature activation+0.117
Top resid features:
say
Token say
Feature activation+0.639
Top resid features:
the
Token the
Feature activation+0.511
Top resid features:
least
Token least
Feature activation+3.416
Top resid features:
,
Token,
Feature activation+0.565
Top resid features:
if
Token if
Feature activation+0.468
Top resid features:
Apple
Token Apple
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
bad
Token bad
Feature activation+0.043
Top resid features:
,
Token,
Feature activation-0.390
Top resid features:
to
Token to
Feature activation+0.369
Top resid features:
say
Token say
Feature activation+0.359
Top resid features:
the
Token the
Feature activation+0.224
Top resid features:
least
Token least
Feature activation+4.661
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
Apple
Token Apple
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sighted
Tokensighted
Feature activation+0.256
Top resid features:
,
Token,
Feature activation-0.096
Top resid features:
to
Token to
Feature activation+0.571
Top resid features:
say
Token say
Feature activation+0.317
Top resid features:
the
Token the
Feature activation+0.219
Top resid features:
least
Token least
Feature activation+4.087
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
considering
Token considering
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
current
Token current
Feature activation+0.000
Top resid features:
sighted
Tokensighted
Feature activation+0.521
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.137
Top resid features:
say
Token say
Feature activation+0.303
Top resid features:
the
Token the
Feature activation+0.385
Top resid features:
least
Token least
Feature activation+2.337
Top resid features:
,
Token,
Feature activation+0.832
Top resid features:
though
Token though
Feature activation+0.096
Top resid features:
considering
Token considering
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
current
Token current
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.002
Top resid features:
peculiar
Token peculiar
Feature activation+0.224
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
say
Token say
Feature activation+0.437
Top resid features:
the
Token the
Feature activation+0.253
Top resid features:
least
Token least
Feature activation+3.984
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Each
Token Each
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
argument
Token argument
Feature activation+0.000
Top resid features:
extreme
Token extreme
Feature activation+0.075
Top resid features:
step
Token step
Feature activation+0.111
Top resid features:
to
Token to
Feature activation+0.159
Top resid features:
say
Token say
Feature activation+0.303
Top resid features:
the
Token the
Feature activation+0.215
Top resid features:
least
Token least
Feature activation+3.143
Top resid features:
.
Token.
Feature activation+0.564
Top resid features:
Mr
Token Mr
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Jun
Token Jun
Feature activation+0.000
Top resid features:
cker
Tokencker
Feature activation+0.000
Top resid features:
streak
Token streak
Feature activation-0.117
Top resid features:
y
Tokeny
Feature activation+0.196
Top resid features:
to
Token to
Feature activation+0.102
Top resid features:
say
Token say
Feature activation+0.534
Top resid features:
the
Token the
Feature activation+0.264
Top resid features:
least
Token least
Feature activation+3.033
Top resid features:
.
Token.
Feature activation+0.757
Top resid features:
Other
Token Other
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation-0.012
Top resid features:
peculiar
Token peculiar
Feature activation+0.691
Top resid features:
to
Token to
Feature activation+0.079
Top resid features:
say
Token say
Feature activation+0.582
Top resid features:
the
Token the
Feature activation+0.324
Top resid features:
least
Token least
Feature activation+1.725
Top resid features:
.
Token.
Feature activation+0.626
Top resid features:
Each
Token Each
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
argument
Token argument
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.888
Top resid features:
iably
Tokeniably
Feature activation-0.030
Top resid features:
labeled
Token labeled
Feature activation-0.001
Top resid features:
as
Token as
Feature activation-0.000
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
adversary
Token adversary
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.181
Top resid features:
There
TokenThere
Feature activation+0.020
Top resid features:
has
Token has
Feature activation-0.004
Top resid features:
been
Token been
Feature activation+0.050
Top resid features:
much
Token much
Feature activation-0.007
Top resid features:
debate
Token debate
Feature activation+0.568
Top resid features:
-
Token -
Feature activation+0.170
Top resid features:
to
Token to
Feature activation+0.079
Top resid features:
put
Token put
Feature activation+0.059
Top resid features:
it
Token it
Feature activation+0.112
Top resid features:
mildly
Token mildly
Feature activation+0.124
Top resid features:
100
Token 100
Feature activation-0.017
Top resid features:
%
Token%
Feature activation-0.004
Top resid features:
effective
Token effective
Feature activation-0.018
Top resid features:
solutions
Token solutions
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.071
Top resid features:
While
Token While
Feature activation+1.478
Top resid features:
there
Token there
Feature activation+0.058
Top resid features:
may
Token may
Feature activation+0.118
Top resid features:
come
Token come
Feature activation+0.038
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
time
Token time
Feature activation-0.063
Top resid features:
think
Token think
Feature activation-0.051
Top resid features:
this
Token this
Feature activation+0.125
Top resid features:
team
Token team
Feature activation+0.877
Top resid features:
is
Token is
Feature activation+0.184
Top resid features:
far
Token far
Feature activation+0.071
Top resid features:
enough
Token enough
Feature activation+1.860
Top resid features:
along
Token along
Feature activation-0.131
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
start
Token start
Feature activation+0.000
Top resid features:
worrying
Token worrying
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.961
Top resid features:
rik
Tokenrik
Feature activation-0.065
Top resid features:
ar
Tokenar
Feature activation-0.042
Top resid features:
said
Token said
Feature activation-0.117
Top resid features:
Saturday
Token Saturday
Feature activation-0.540
Top resid features:
.
Token.
Feature activation-0.107
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.854
Top resid features:
rik
Tokenrik
Feature activation-0.000
Top resid features:
ar
Tokenar
Feature activation-0.048
Top resid features:
said
Token said
Feature activation-0.231
Top resid features:
Saturday
Token Saturday
Feature activation-0.573
Top resid features:
.
Token.
Feature activation-0.189
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.970
Top resid features:
rik
Tokenrik
Feature activation+0.045
Top resid features:
ar
Tokenar
Feature activation-0.152
Top resid features:
said
Token said
Feature activation-0.121
Top resid features:
Saturday
Token Saturday
Feature activation-0.619
Top resid features:
.
Token.
Feature activation-0.164
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.051
Top resid features:
rik
Tokenrik
Feature activation-0.052
Top resid features:
ar
Tokenar
Feature activation-0.048
Top resid features:
said
Token said
Feature activation-0.148
Top resid features:
Saturday
Token Saturday
Feature activation-0.713
Top resid features:
.
Token.
Feature activation-0.305
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.04

Head 3: 0.07

Head 4: 0.04

Head 5: 0.37

Head 6: 0.04

Head 7: 0.06

Head 8: 0.13

Head 9: 0.01

Head 10: 0.02

Head 11: 0.12

Positive logits

.<2.01

ONSORED1.92

Highly1.89

lax1.88

considering1.85

.1.85

etheless1.84

ripe1.79

overall1.79

;;;;;;;;1.77

fragmentation1.76

laughs1.76

sheer1.76

aest1.75

cumbers1.73

exacerbated1.72

acutely1.69

=================================1.69

ASUS1.69

thefts1.69

Negative logits

swer-2.44

essor-2.16

deed-2.09

older-2.09

arez-2.08

ender-2.01

livion-2.00

later-1.99

Else-1.95

Consent-1.94

ulhu-1.94

Next-1.92

ername-1.91

olon-1.88

corporation-1.87

sburg-1.83

guiActive-1.81

instead-1.81

ulu-1.79

eller-1.78

INTERVAL 4.374 - 4.860
CONTAINS 0.000%

,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.202
,
Token,
Feature activation+4.860
if
Token if
Feature activation+3.587
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 3.888 - 4.374
CONTAINS 0.000%

streak
Token streak
Feature activation+0.000
y
Tokeny
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.933
.
Token.
Feature activation+1.705
Other
Token Other
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
propensity
Token propensity
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
step
Token step
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.946
.
Token.
Feature activation+2.090
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Jun
Token Jun
Feature activation+0.000
cker
Tokencker
Feature activation+0.000

INTERVAL 3.402 - 3.888
CONTAINS 0.000%

to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.202
,
Token,
Feature activation+4.860
if
Token if
Feature activation+3.587
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
perceived
Token perceived
Feature activation+0.000

INTERVAL 2.916 - 3.402
CONTAINS 0.000%

bad
Token bad
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.202
,
Token,
Feature activation+4.860
if
Token if
Feature activation+3.587
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
sighted
Tokensighted
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000

INTERVAL 2.430 - 2.916
CONTAINS 0.000%

INTERVAL 1.944 - 2.430
CONTAINS 0.000%

ed
Tokened
Feature activation+0.000
peculiar
Token peculiar
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.181
.
Token.
Feature activation+0.836
Each
Token Each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
argument
Token argument
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
propensity
Token propensity
Feature activation+0.000
to
Token to
Feature activation+0.000
step
Token step
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.946
.
Token.
Feature activation+2.090
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Jun
Token Jun
Feature activation+0.000
cker
Tokencker
Feature activation+0.000
even
Token even
Feature activation+0.000

INTERVAL 1.458 - 1.944
CONTAINS 0.000%

y
Tokeny
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+3.933
.
Token.
Feature activation+1.705
Other
Token Other
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
games
Token games
Feature activation+0.000

INTERVAL 0.972 - 1.458
CONTAINS 0.000%

INTERVAL 0.486 - 0.972
CONTAINS 0.000%

peculiar
Token peculiar
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.181
.
Token.
Feature activation+0.836
Each
Token Each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
argument
Token argument
Feature activation+0.000
you
Token you
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+2.917
,
Token,
Feature activation+4.371
though
Token though
Feature activation+2.277
considering
Token considering
Feature activation+0.506
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
propensity
Token propensity
Feature activation+0.000
to
Token to
Feature activation+0.000
dwell
Token dwell
Feature activation+0.000

INTERVAL 0.000 - 0.486
CONTAINS 99.998%

his
Token his
Feature activation+0.000
when
Token when
Feature activation+0.000
-
Token-
Feature activation+0.000
abouts
Tokenabouts
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
c
Token c
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
out
Token out
Feature activation+0.000
Ge
Token Ge
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
mere
Token mere
Feature activation+0.000
mortal
Token mortal
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
has
Token has
Feature activation+0.000
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.000
,
Token,
Feature activation+0.000
400
Token400
Feature activation+0.000
higher
Token higher
Feature activation+0.000
than
Token than
Feature activation+0.000
Ontario
Token Ontario
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
Brian
Token Brian
Feature activation+0.000
Fallon
Token Fallon
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.000
still
Token still
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
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 8 in H6.5: (feature 13184)

TOP ACTIVATIONS
MAX = 6.275

rating
Token rating
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
batteries
Token batteries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.760
Ċ
TokenĊ
Feature activation+6.211
Prop
TokenProp
Feature activation+2.837
onents
Tokenonents
Feature activation+1.417
of
Token of
Feature activation+0.234
a
Token a
Feature activation+0.143
$
Token $
Feature activation+0.015
photos
Token photos
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.428
Ċ
TokenĊ
Feature activation+5.874
The
TokenThe
Feature activation+0.914
owners
Token owners
Feature activation+0.444
of
Token of
Feature activation+0.767
New
Token New
Feature activation+0.100
York
Token York
Feature activation+0.463
grant
Token grant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
controversy
Token controversy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.220
Ċ
TokenĊ
Feature activation+5.622
Toy
TokenToy
Feature activation+0.511
company
Token company
Feature activation+1.016
Lego
Token Lego
Feature activation+0.087
has
Token has
Feature activation+0.416
done
Token done
Feature activation+0.000
AAA
Token AAA
Feature activation+0.000
rating
Token rating
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
sized
Tokensized
Feature activation+0.000
batteries
Token batteries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.760
Ċ
TokenĊ
Feature activation+6.211
Prop
TokenProp
Feature activation+2.837
onents
Tokenonents
Feature activation+1.417
of
Token of
Feature activation+0.234
a
Token a
Feature activation+0.143
pless
Tokenpless
Feature activation+0.000
photos
Token photos
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.428
Ċ
TokenĊ
Feature activation+5.874
The
TokenThe
Feature activation+0.914
owners
Token owners
Feature activation+0.444
of
Token of
Feature activation+0.767
New
Token New
Feature activation+0.100
bury
Tokenbury
Feature activation+0.000
grant
Token grant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
exhibition
Token exhibition
Feature activation+0.000
controversy
Token controversy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.220
Ċ
TokenĊ
Feature activation+5.622
Toy
TokenToy
Feature activation+0.511
company
Token company
Feature activation+1.016
Lego
Token Lego
Feature activation+0.087
has
Token has
Feature activation+0.416
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.760
Ċ
TokenĊ
Feature activation+6.211
Prop
TokenProp
Feature activation+2.837
onents
Tokenonents
Feature activation+1.417
of
Token of
Feature activation+0.234
a
Token a
Feature activation+0.143
$
Token $
Feature activation+0.015
300
Token300
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
reaff
Token reaff
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Green
Token Green
Feature activation+0.257
has
Token has
Feature activation+0.333
used
Token used
Feature activation+0.000
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Green
Token Green
Feature activation+0.257
has
Token has
Feature activation+0.333
used
Token used
Feature activation+0.000
Question
Token Question
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
reaff
Token reaff
Feature activation+0.000
irmed
Tokenirmed
Feature activation+0.206
Australia
Token Australia
Feature activation+0.000
April
Token April
Feature activation+0.000
12
Token 12
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.260
Ċ
TokenĊ
Feature activation+1.084
Mon
TokenMon
Feature activation+0.000
al
Tokenal
Feature activation+0.000
isa
Tokenisa
Feature activation+0.000
Tre
Token Tre
Feature activation+0.000

Top DFA by src position
MAX = 4.199

AAA
Token AAA
Feature activation+0.006
Top resid features:
rating
Token rating
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.092
Top resid features:
Updated
TokenUpdated
Feature activation+0.634
Top resid features:
Ċ
TokenĊ
Feature activation+3.807
Top resid features:
Ċ
TokenĊ
Feature activation+2.631
Top resid features:
M
TokenM
Feature activation+0.000
Top resid features:
ood
Tokenood
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
sized
Tokensized
Feature activation-0.020
Top resid features:
batteries
Token batteries
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+0.123
Top resid features:
Updated
TokenUpdated
Feature activation+0.701
Top resid features:
Ċ
TokenĊ
Feature activation+3.639
Top resid features:
Ċ
TokenĊ
Feature activation+2.707
Top resid features:
Prop
TokenProp
Feature activation+0.000
Top resid features:
onents
Tokenonents
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
pless
Tokenpless
Feature activation-0.010
Top resid features:
photos
Token photos
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.086
Top resid features:
Ċ
TokenĊ
Feature activation+0.149
Top resid features:
Updated
TokenUpdated
Feature activation+0.696
Top resid features:
Ċ
TokenĊ
Feature activation+3.348
Top resid features:
Ċ
TokenĊ
Feature activation+2.484
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
owners
Token owners
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
bury
Tokenbury
Feature activation+0.001
Top resid features:
grant
Token grant
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.087
Top resid features:
Ċ
TokenĊ
Feature activation+0.123
Top resid features:
Updated
TokenUpdated
Feature activation+0.570
Top resid features:
Ċ
TokenĊ
Feature activation+3.490
Top resid features:
Ċ
TokenĊ
Feature activation+2.425
Top resid features:
T
TokenT
Feature activation+0.000
Top resid features:
as
Tokenas
Feature activation+0.000
Top resid features:
man
Tokenman
Feature activation+0.000
Top resid features:
ian
Tokenian
Feature activation+0.000
Top resid features:
exhibition
Token exhibition
Feature activation-0.007
Top resid features:
controversy
Token controversy
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.100
Top resid features:
Ċ
TokenĊ
Feature activation+0.143
Top resid features:
Updated
TokenUpdated
Feature activation+0.711
Top resid features:
Ċ
TokenĊ
Feature activation+3.506
Top resid features:
Ċ
TokenĊ
Feature activation+2.351
Top resid features:
Toy
TokenToy
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
Lego
Token Lego
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
AAA
Token AAA
Feature activation+0.012
Top resid features:
rating
Token rating
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.119
Top resid features:
Ċ
TokenĊ
Feature activation+0.157
Top resid features:
Updated
TokenUpdated
Feature activation+0.541
Top resid features:
Ċ
TokenĊ
Feature activation+4.199
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
M
TokenM
Feature activation+0.000
Top resid features:
ood
Tokenood
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
sized
Tokensized
Feature activation-0.021
Top resid features:
batteries
Token batteries
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.095
Top resid features:
Ċ
TokenĊ
Feature activation+0.185
Top resid features:
Updated
TokenUpdated
Feature activation+0.607
Top resid features:
Ċ
TokenĊ
Feature activation+3.756
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Prop
TokenProp
Feature activation+0.000
Top resid features:
onents
Tokenonents
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
pless
Tokenpless
Feature activation-0.019
Top resid features:
photos
Token photos
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.118
Top resid features:
Ċ
TokenĊ
Feature activation+0.190
Top resid features:
Updated
TokenUpdated
Feature activation+0.574
Top resid features:
Ċ
TokenĊ
Feature activation+3.334
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
owners
Token owners
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
bury
Tokenbury
Feature activation+0.003
Top resid features:
grant
Token grant
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.124
Top resid features:
Ċ
TokenĊ
Feature activation+0.187
Top resid features:
Updated
TokenUpdated
Feature activation+0.491
Top resid features:
Ċ
TokenĊ
Feature activation+3.499
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
T
TokenT
Feature activation+0.000
Top resid features:
as
Tokenas
Feature activation+0.000
Top resid features:
man
Tokenman
Feature activation+0.000
Top resid features:
ian
Tokenian
Feature activation+0.000
Top resid features:
exhibition
Token exhibition
Feature activation-0.007
Top resid features:
controversy
Token controversy
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.139
Top resid features:
Ċ
TokenĊ
Feature activation+0.205
Top resid features:
Updated
TokenUpdated
Feature activation+0.614
Top resid features:
Ċ
TokenĊ
Feature activation+3.268
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Toy
TokenToy
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
Lego
Token Lego
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.716
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
rather
Token rather
Feature activation-0.001
Top resid features:
than
Token than
Feature activation-0.002
Top resid features:
just
Token just
Feature activation-0.000
Top resid features:
whether
Token whether
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.763
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
directing
Token directing
Feature activation-0.002
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
well
Token well
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
AAA
Token AAA
Feature activation-0.044
Top resid features:
rating
Token rating
Feature activation+0.110
Top resid features:
Ċ
TokenĊ
Feature activation+0.229
Top resid features:
Ċ
TokenĊ
Feature activation+0.209
Top resid features:
Updated
TokenUpdated
Feature activation+0.322
Top resid features:
Ċ
TokenĊ
Feature activation+1.745
Top resid features:
Ċ
TokenĊ
Feature activation+1.660
Top resid features:
M
TokenM
Feature activation-0.023
Top resid features:
ood
Tokenood
Feature activation-0.072
Top resid features:
y
Tokeny
Feature activation+0.019
Top resid features:
's
Token's
Feature activation-0.142
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.725
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
Armen
Token Armen
Feature activation-0.006
Top resid features:
ians
Tokenians
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.650
Top resid features:
of
Token of
Feature activation-0.008
Top resid features:
Armen
Token Armen
Feature activation-0.003
Top resid features:
ians
Tokenians
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.618
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
directing
Token directing
Feature activation-0.002
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
well
Token well
Feature activation-0.000
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.727
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
directing
Token directing
Feature activation-0.004
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
well
Token well
Feature activation-0.000
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.658
Top resid features:
of
Token of
Feature activation-0.020
Top resid features:
Armen
Token Armen
Feature activation-0.004
Top resid features:
ians
Tokenians
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.637
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Armen
Token Armen
Feature activation-0.003
Top resid features:
ians
Tokenians
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.860
Top resid features:
the
Token the
Feature activation-0.061
Top resid features:
part
Token part
Feature activation-0.038
Top resid features:
of
Token of
Feature activation-0.029
Top resid features:
district
Token district
Feature activation+0.006
Top resid features:
officials
Token officials
Feature activation-0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.08

Head 3: 0.04

Head 4: 0.07

Head 5: 0.36

Head 6: 0.15

Head 7: 0.05

Head 8: 0.06

Head 9: 0.01

Head 10: 0.03

Head 11: 0.06

Positive logits

arios2.60

olars2.19

ctors2.05

axies1.99

atics1.95

lawfully1.94

achers1.93

invest1.90

propositions1.87

eson1.85

mun1.85

icts1.83

ewater1.83

oras1.83

inator1.82

efficients1.80

legitimately1.80

ptions1.79

achus1.77

anners1.76

Negative logits

Shutterstock-2.32

の�-2.32

":"/-2.06

utterstock-2.00

Posted-1.97

Perspective-1.96

-1.81

-1.80

Image-1.79

-1.76

Flickr-1.76

Wired-1.75

��-1.75

guiActiveUnfocused-1.75

slideshow-1.74

ドラ-1.73

Contribut-1.72

Hide-1.72

Github-1.71

attribute-1.71

INTERVAL 5.647 - 6.275
CONTAINS 0.000%

batteries
Token batteries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.760
Ċ
TokenĊ
Feature activation+6.211
Prop
TokenProp
Feature activation+2.837
onents
Tokenonents
Feature activation+1.417
of
Token of
Feature activation+0.234
a
Token a
Feature activation+0.143
$
Token $
Feature activation+0.015
photos
Token photos
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.428
Ċ
TokenĊ
Feature activation+5.874
The
TokenThe
Feature activation+0.914
owners
Token owners
Feature activation+0.444
of
Token of
Feature activation+0.767
New
Token New
Feature activation+0.100
York
Token York
Feature activation+0.463
rating
Token rating
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009

INTERVAL 5.020 - 5.647
CONTAINS 0.000%

controversy
Token controversy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.220
Ċ
TokenĊ
Feature activation+5.622
Toy
TokenToy
Feature activation+0.511
company
Token company
Feature activation+1.016
Lego
Token Lego
Feature activation+0.087
has
Token has
Feature activation+0.416
done
Token done
Feature activation+0.000
grant
Token grant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793

INTERVAL 4.392 - 5.020
CONTAINS 0.000%

INTERVAL 3.765 - 4.392
CONTAINS 0.000%

AAA
Token AAA
Feature activation+0.000
rating
Token rating
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350

INTERVAL 3.137 - 3.765
CONTAINS 0.000%

exhibition
Token exhibition
Feature activation+0.000
controversy
Token controversy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.220
Ċ
TokenĊ
Feature activation+5.622
Toy
TokenToy
Feature activation+0.511
company
Token company
Feature activation+1.016
Lego
Token Lego
Feature activation+0.087
has
Token has
Feature activation+0.416
bury
Tokenbury
Feature activation+0.000
grant
Token grant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
sized
Tokensized
Feature activation+0.000
batteries
Token batteries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.760
Ċ
TokenĊ
Feature activation+6.211
Prop
TokenProp
Feature activation+2.837
onents
Tokenonents
Feature activation+1.417
of
Token of
Feature activation+0.234
a
Token a
Feature activation+0.143
pless
Tokenpless
Feature activation+0.000
photos
Token photos
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.428
Ċ
TokenĊ
Feature activation+5.874
The
TokenThe
Feature activation+0.914
owners
Token owners
Feature activation+0.444
of
Token of
Feature activation+0.767
New
Token New
Feature activation+0.100

INTERVAL 2.510 - 3.137
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.760
Ċ
TokenĊ
Feature activation+6.211
Prop
TokenProp
Feature activation+2.837
onents
Tokenonents
Feature activation+1.417
of
Token of
Feature activation+0.234
a
Token a
Feature activation+0.143
$
Token $
Feature activation+0.015
300
Token300
Feature activation+0.000

INTERVAL 1.882 - 2.510
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
reaff
Token reaff
Feature activation+0.000

INTERVAL 1.255 - 1.882
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Green
Token Green
Feature activation+0.257
has
Token has
Feature activation+0.333
used
Token used
Feature activation+0.000
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Green
Token Green
Feature activation+0.257
has
Token has
Feature activation+0.333
used
Token used
Feature activation+0.000
Question
Token Question
Feature activation+0.000
April
Token April
Feature activation+0.000
12
Token 12
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.260
Ċ
TokenĊ
Feature activation+1.084
Mon
TokenMon
Feature activation+0.000
al
Tokenal
Feature activation+0.000
isa
Tokenisa
Feature activation+0.000
Tre
Token Tre
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.184
Ċ
TokenĊ
Feature activation+6.275
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
M
TokenM
Feature activation+2.136
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
reaff
Token reaff
Feature activation+0.000
irmed
Tokenirmed
Feature activation+0.206
Australia
Token Australia
Feature activation+0.000

INTERVAL 0.627 - 1.255
CONTAINS 0.001%

Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.337
Ċ
TokenĊ
Feature activation+5.633
T
TokenT
Feature activation+1.175
as
Tokenas
Feature activation+2.448
man
Tokenman
Feature activation+0.829
ian
Tokenian
Feature activation+1.029
Opposition
Token Opposition
Feature activation+1.793
Leader
Token Leader
Feature activation+1.719
Bryan
Token Bryan
Feature activation+0.000
Green
Token Green
Feature activation+0.257
19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.092
Ċ
TokenĊ
Feature activation+0.939
A
TokenA
Feature activation+0.129
jury
Token jury
Feature activation+0.000
unanimously
Token unanimously
Feature activation+0.000
found
Token found
Feature activation+0.000
former
Token former
Feature activation+0.000
.
Token.
Feature activation+0.000
19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.092
Ċ
TokenĊ
Feature activation+0.939
A
TokenA
Feature activation+0.129
jury
Token jury
Feature activation+0.000
unanimously
Token unanimously
Feature activation+0.000
found
Token found
Feature activation+0.000
ood
Tokenood
Feature activation+1.296
y
Tokeny
Feature activation+1.926
's
Token's
Feature activation+2.350
credit
Token credit
Feature activation+0.009
rating
Token rating
Feature activation+1.293
agency
Token agency
Feature activation+0.952
has
Token has
Feature activation+0.432
reaff
Token reaff
Feature activation+0.000
irmed
Tokenirmed
Feature activation+0.206
Australia
Token Australia
Feature activation+0.000
's
Token's
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Updated
TokenUpdated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.220
Ċ
TokenĊ
Feature activation+5.622
Toy
TokenToy
Feature activation+0.511
company
Token company
Feature activation+1.016
Lego
Token Lego
Feature activation+0.087
has
Token has
Feature activation+0.416
done
Token done
Feature activation+0.000
an
Token an
Feature activation+0.000
about
Token about
Feature activation+0.000

INTERVAL 0.000 - 0.627
CONTAINS 99.997%

h
Tokenh
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
Avenue
Token Avenue
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
stand
Token stand
Feature activation+0.000
still
Tokenstill
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Interstate
Token Interstate
Feature activation+0.000
580
Token 580
Feature activation+0.000
somebody
Token somebody
Feature activation+0.000
is
Token is
Feature activation+0.000
standing
Token standing
Feature activation+0.000
off
Token off
Feature activation+0.000
of
Token of
Feature activation+0.000
school
Token school
Feature activation+0.000
property
Token property
Feature activation+0.000
selling
Token selling
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
how
Token how
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
priest
Token priest
Feature activation+0.000
says
Token says
Feature activation+0.000
that
Token that
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
side
Token side
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
congressional
Token congressional
Feature activation+0.000
level
Token level
Feature activation+0.000
on
Token on
Feature activation+0.000
up
Token up
Feature activation+0.000
out
Tokenout
Feature activation+0.000
reveal
Token reveal
Feature activation+0.000
the
Token the
Feature activation+0.000
vast
Token vast
Feature activation+0.000
extent
Token extent
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
operations
Token operations
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
also
Token also
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H6.5: (feature 19173)

TOP ACTIVATIONS
MAX = 2.951

to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.951
blood
Token blood
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
streets
Token streets
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.864
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
never
Token never
Feature activation+0.000
,
Token,
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
know
Token know
Feature activation+0.002
,
Token,
Feature activation+2.740
mis
Token mis
Feature activation+0.000
cellaneous
Tokencellaneous
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
we
Token we
Feature activation+0.000
hate
Token hate
Feature activation+0.000
real
Token real
Feature activation+0.000
catastrophe
Token catastrophe
Feature activation+0.000
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.590
one
Token one
Feature activation+0.000
that
Token that
Feature activation+0.000
might
Token might
Feature activation+0.000
require
Token require
Feature activation+0.000
actual
Token actual
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.334
have
Token have
Feature activation+0.000
someone
Token someone
Feature activation+0.000
stick
Token stick
Feature activation+0.000
a
Token a
Feature activation+0.000
fork
Token fork
Feature activation+0.000
stem
Token stem
Feature activation+0.000
cells
Token cells
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.275
the
Token the
Feature activation+0.539
ones
Token ones
Feature activation+0.000
our
Token our
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
produce
Token produce
Feature activation+0.000
activity
Token activity
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+2.200
hindsight
Token hindsight
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.078
obvious
Token obvious
Feature activation+0.000
lies
Token lies
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.015
with
Token with
Feature activation+0.000
Gand
Token Gand
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
see
Token see
Feature activation+0.000
,
Token,
Feature activation+1.912
your
Token your
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
always
Token always
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
drive
Token drive
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.701
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
different
Token different
Feature activation+0.000
things
Token things
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.625
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
the
Token the
Feature activation+0.000
Vault
Token Vault
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.494
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Brooks
Token Brooks
Feature activation+0.000
began
Token began
Feature activation+0.000
,
Token,
Feature activation+0.000
moved
Token moved
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.341
Brett
Token Brett
Feature activation+0.000
Fav
Token Fav
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ran
Token ran
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token4
Feature activation+0.000
gasoline
Token gasoline
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
see
Token see
Feature activation+0.000
,
Token,
Feature activation+1.172
this
Token this
Feature activation+0.000
costs
Token costs
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
identity
Token identity
Feature activation+0.000
politics
Token politics
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.151
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
from
Token from
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
-
Token -
Feature activation+1.127
blue
Token blue
Feature activation+0.000
states
Token states
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
states
Token states
Feature activation+0.000
view
Token view
Feature activation+0.000
mirrors
Token mirrors
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.074
I
Token I
Feature activation+0.372
have
Token have
Feature activation+0.000
D
Token D
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
L
TokenL
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.051
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.978
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
other
Token other
Feature activation+0.000
mis
Token mis
Feature activation+0.000
d
Tokend
Feature activation+0.000

Top DFA by src position
MAX = 3.546

shot
Token shot
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.080
Top resid features:
buy
Token buy
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.166
Top resid features:
You
Token You
Feature activation+0.701
Top resid features:
know
Token know
Feature activation+2.615
Top resid features:
,
Token,
Feature activation+1.383
Top resid features:
blood
Token blood
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:
streets
Token streets
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
âĢ
TokenâĢ
Feature activation-0.052
Top resid features:
ľ
Tokenľ
Feature activation-0.031
Top resid features:
You
TokenYou
Feature activation+0.343
Top resid features:
know
Token know
Feature activation+3.105
Top resid features:
,
Token,
Feature activation+1.940
Top resid features:
I
Token I
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:
d
Tokend
Feature activation+0.000
Top resid features:
cut
Token cut
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
taxes
Token taxes
Feature activation+0.127
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.641
Top resid features:
you
Tokenyou
Feature activation+0.471
Top resid features:
know
Token know
Feature activation+1.940
Top resid features:
,
Token,
Feature activation+1.650
Top resid features:
mis
Token mis
Feature activation+0.000
Top resid features:
cellaneous
Tokencellaneous
Feature activation+0.000
Top resid features:
stuff
Token stuff
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.021
Top resid features:
real
Token real
Feature activation+0.031
Top resid features:
catastrophe
Token catastrophe
Feature activation-0.067
Top resid features:
?
Token?
Feature activation+0.220
Top resid features:
You
Token You
Feature activation+0.794
Top resid features:
know
Token know
Feature activation+2.027
Top resid features:
,
Token,
Feature activation+1.761
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
might
Token might
Feature activation+0.000
Top resid features:
require
Token require
Feature activation+0.000
Top resid features:
late
Token late
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.100
Top resid features:
you
Token you
Feature activation+0.068
Top resid features:
-
Token -
Feature activation+0.206
Top resid features:
you
Token you
Feature activation+0.335
Top resid features:
know
Token know
Feature activation+2.185
Top resid features:
,
Token,
Feature activation+1.436
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
someone
Token someone
Feature activation+0.000
Top resid features:
stick
Token stick
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.015
Top resid features:
stem
Token stem
Feature activation+0.030
Top resid features:
cells
Token cells
Feature activation+0.155
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.060
Top resid features:
you
Tokenyou
Feature activation+0.578
Top resid features:
know
Token know
Feature activation+2.008
Top resid features:
,
Token,
Feature activation+1.569
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ones
Token ones
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
bodies
Token bodies
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.012
Top resid features:
activity
Token activity
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
but
Token but
Feature activation-0.031
Top resid features:
you
Token you
Feature activation+0.277
Top resid features:
know
Token know
Feature activation+3.528
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.530
Top resid features:
hindsight
Token hindsight
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
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:
Â
TokenÂ
Feature activation+0.002
Top resid features:
Ģ
TokenĢ
Feature activation-0.011
Top resid features:
Â
TokenÂ
Feature activation+0.006
Top resid features:
Ķ
TokenĶ
Feature activation+0.003
Top resid features:
you
Tokenyou
Feature activation+0.893
Top resid features:
know
Token know
Feature activation+2.480
Top resid features:
,
Token,
Feature activation+1.342
Top resid features:
obvious
Token obvious
Feature activation+0.000
Top resid features:
lies
Token lies
Feature activation+0.000
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
on
Tokenon
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.106
Top resid features:
Because
Token Because
Feature activation+0.169
Top resid features:
,
Token,
Feature activation+0.733
Top resid features:
you
Token you
Feature activation+0.265
Top resid features:
know
Token know
Feature activation+1.692
Top resid features:
,
Token,
Feature activation+1.380
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Gand
Token Gand
Feature activation+0.000
Top resid features:
alf
Tokenalf
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
asked
Token asked
Feature activation-0.034
Top resid features:
him
Token him
Feature activation+0.027
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
You
Token You
Feature activation+0.156
Top resid features:
see
Token see
Feature activation+3.546
Top resid features:
,
Token,
Feature activation+0.462
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
clothes
Token clothes
Feature activation+0.000
Top resid features:
always
Token always
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
maybe
Token maybe
Feature activation+0.008
Top resid features:
drive
Token drive
Feature activation-0.014
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
you
Token you
Feature activation+0.496
Top resid features:
know
Token know
Feature activation+2.835
Top resid features:
,
Token,
Feature activation+0.583
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation-0.060
Top resid features:
ľ
Tokenľ
Feature activation-0.072
Top resid features:
You
TokenYou
Feature activation+0.391
Top resid features:
know
Token know
Feature activation+2.284
Top resid features:
,
Token,
Feature activation+1.424
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.000
Top resid features:
couple
Token couple
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.058
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
Vault
Token Vault
Feature activation-0.053
Top resid features:
,
Token,
Feature activation+0.403
Top resid features:
you
Token you
Feature activation+0.359
Top resid features:
know
Token know
Feature activation+1.962
Top resid features:
,
Token,
Feature activation+1.033
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Brooks
Token Brooks
Feature activation+0.000
Top resid features:
began
Token began
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.093
Top resid features:
moved
Token moved
Feature activation+0.097
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.192
Top resid features:
You
Token You
Feature activation+0.425
Top resid features:
know
Token know
Feature activation+1.887
Top resid features:
,
Token,
Feature activation+0.654
Top resid features:
Brett
Token Brett
Feature activation+0.000
Top resid features:
Fav
Token Fav
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
ran
Token ran
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.072
Top resid features:
4
Token4
Feature activation+0.007
Top resid features:
gasoline
Token gasoline
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
You
Token You
Feature activation+0.250
Top resid features:
see
Token see
Feature activation+2.624
Top resid features:
,
Token,
Feature activation+0.609
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
costs
Token costs
Feature activation+0.000
Top resid features:
jobs
Token jobs
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
beyond
Token beyond
Feature activation-0.078
Top resid features:
identity
Token identity
Feature activation-0.038
Top resid features:
politics
Token politics
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.180
Top resid features:
You
Token You
Feature activation+0.647
Top resid features:
know
Token know
Feature activation+1.888
Top resid features:
,
Token,
Feature activation+0.563
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
think
Token think
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:
the
Token the
Feature activation+0.040
Top resid features:
distribution
Token distribution
Feature activation+0.018
Top resid features:
from
Token from
Feature activation+0.261
Top resid features:
-
Token -
Feature activation-0.008
Top resid features:
you
Token you
Feature activation+0.372
Top resid features:
know
Token know
Feature activation+2.720
Top resid features:
-
Token -
Feature activation+0.218
Top resid features:
blue
Token blue
Feature activation+0.000
Top resid features:
states
Token states
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
red
Token red
Feature activation+0.000
Top resid features:
rear
Token rear
Feature activation+0.085
Top resid features:
view
Token view
Feature activation-0.029
Top resid features:
mirrors
Token mirrors
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.123
Top resid features:
you
Token you
Feature activation+0.539
Top resid features:
know
Token know
Feature activation+1.209
Top resid features:
,
Token,
Feature activation+0.818
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
AP
TokenAP
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.005
Top resid features:
won
Token won
Feature activation+0.061
Top resid features:
't
Token't
Feature activation-0.061
Top resid features:
,
Token,
Feature activation+0.491
Top resid features:
you
Token you
Feature activation+0.412
Top resid features:
know
Token know
Feature activation+2.147
Top resid features:
,
Token,
Feature activation+0.273
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
won
Token won
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
enemies
Token enemies
Feature activation-0.022
Top resid features:
.
Token.
Feature activation+0.223
Top resid features:
And
Token And
Feature activation-0.217
Top resid features:
,
Token,
Feature activation+0.341
Top resid features:
you
Token you
Feature activation+0.348
Top resid features:
know
Token know
Feature activation+2.002
Top resid features:
,
Token,
Feature activation+0.495
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
mis
Token mis
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.04

Head 3: 0.06

Head 4: 0.04

Head 5: 0.36

Head 6: 0.05

Head 7: 0.04

Head 8: 0.20

Head 9: 0.02

Head 10: 0.02

Head 11: 0.06

Positive logits

suspensions1.95

stunts1.83

aughs1.83

abusers1.78

tones1.71

scheduling1.69

complicate1.69

loosely1.69

icky1.68

hedon1.67

weddings1.67

frameworks1.64

handlers1.64

Management1.64

abies1.62

cro1.62

finances1.61

usp1.59

revolves1.58

gatherings1.57

Negative logits

yourselves-2.39

yourself-2.20

actly-2.08

cean-1.95

AAAA-1.92

ALSE-1.92

Lord-1.89

ename-1.84

eware-1.83

deed-1.82

amiliar-1.81

ESH-1.79

yours-1.76

Scrolls-1.75

Org-1.75

Yourself-1.75

Deal-1.74

Your-1.74

elcome-1.74

ndum-1.72

INTERVAL 2.656 - 2.951
CONTAINS 0.000%

to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.951
blood
Token blood
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
streets
Token streets
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.864
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
never
Token never
Feature activation+0.000
,
Token,
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
know
Token know
Feature activation+0.002
,
Token,
Feature activation+2.740
mis
Token mis
Feature activation+0.000
cellaneous
Tokencellaneous
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
we
Token we
Feature activation+0.000
hate
Token hate
Feature activation+0.000

INTERVAL 2.361 - 2.656
CONTAINS 0.000%

real
Token real
Feature activation+0.000
catastrophe
Token catastrophe
Feature activation+0.000
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.590
one
Token one
Feature activation+0.000
that
Token that
Feature activation+0.000
might
Token might
Feature activation+0.000
require
Token require
Feature activation+0.000
actual
Token actual
Feature activation+0.000

INTERVAL 2.066 - 2.361
CONTAINS 0.000%

activity
Token activity
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+2.200
hindsight
Token hindsight
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.334
have
Token have
Feature activation+0.000
someone
Token someone
Feature activation+0.000
stick
Token stick
Feature activation+0.000
a
Token a
Feature activation+0.000
fork
Token fork
Feature activation+0.000
Ģ
TokenĢ
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.078
obvious
Token obvious
Feature activation+0.000
lies
Token lies
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
stem
Token stem
Feature activation+0.000
cells
Token cells
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.275
the
Token the
Feature activation+0.539
ones
Token ones
Feature activation+0.000
our
Token our
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
produce
Token produce
Feature activation+0.000

INTERVAL 1.771 - 2.066
CONTAINS 0.000%

asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
see
Token see
Feature activation+0.000
,
Token,
Feature activation+1.912
your
Token your
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
always
Token always
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+2.015
with
Token with
Feature activation+0.000
Gand
Token Gand
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.475 - 1.771
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.625
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
the
Token the
Feature activation+0.000
Vault
Token Vault
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.494
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Brooks
Token Brooks
Feature activation+0.000
began
Token began
Feature activation+0.000
,
Token,
Feature activation+0.000
drive
Token drive
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.701
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
different
Token different
Feature activation+0.000
things
Token things
Feature activation+0.000

INTERVAL 1.180 - 1.475
CONTAINS 0.000%

moved
Token moved
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.341
Brett
Token Brett
Feature activation+0.000
Fav
Token Fav
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ran
Token ran
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.885 - 1.180
CONTAINS 0.001%

identity
Token identity
Feature activation+0.000
politics
Token politics
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.151
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
view
Token view
Feature activation+0.000
mirrors
Token mirrors
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.074
I
Token I
Feature activation+0.372
have
Token have
Feature activation+0.000
D
Token D
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
L
TokenL
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
from
Token from
Feature activation+0.000
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
-
Token -
Feature activation+1.127
blue
Token blue
Feature activation+0.000
states
Token states
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
states
Token states
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.978
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
other
Token other
Feature activation+0.000
mis
Token mis
Feature activation+0.000
d
Tokend
Feature activation+0.000
the
Token the
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
?
Token?
Feature activation+0.903
Donald
Token Donald
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.590 - 0.885
CONTAINS 0.000%

:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.789
I
Token I
Feature activation+0.000
wait
Token wait
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
power
Token power
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.670
you
Token you
Feature activation+0.000
give
Token give
Feature activation+0.000
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.731
side
Token side
Feature activation+0.000
mirrors
Token mirrors
Feature activation+0.000
and
Token and
Feature activation+0.000
rear
Token rear
Feature activation+0.000
view
Token view
Feature activation+0.000

INTERVAL 0.295 - 0.590
CONTAINS 0.001%

the
Token the
Feature activation+0.000
streets
Token streets
Feature activation+0.000
and
Token and
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.528
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
seven
Token seven
Feature activation+0.000
seasons
Token seasons
Feature activation+0.000
?
Token?
Feature activation+0.000
You
Token You
Feature activation+0.000
bet
Token bet
Feature activation+0.000
.
Token.
Feature activation+0.394
Does
Token Does
Feature activation+0.000
that
Token that
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
.
Token.
Feature activation+0.310
Re
Token Re
Feature activation+0.000
a
Tokena
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
mirrors
Token mirrors
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+1.074
I
Token I
Feature activation+0.372
have
Token have
Feature activation+0.000
D
Token D
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
L
TokenL
Feature activation+0.000
security
Token security
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.565
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
complain
Token complain
Feature activation+0.000
about
Token about
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.295
CONTAINS 99.996%

,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
9
Token 9
Feature activation+0.000
:
Token:
Feature activation+0.000
45
Token45
Feature activation+0.000
p
Token p
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
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
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
image
Tokenimage
Feature activation+0.000
via
Token via
Feature activation+0.000
screen
Token screen
Feature activation+0.000
grab
Tokengrab
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
so
Token so
Feature activation+0.000
disappointed
Token disappointed
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
tourism
Token tourism
Feature activation+0.000
destination
Token destination
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
of
Token of
Feature activation+0.000
wealthy
Token wealthy
Feature activation+0.000
foreigners
Token foreigners
Feature activation+0.000
paying
Token paying
Feature activation+0.000
poor
Token poor
Feature activation+0.000
Indians
Token Indians
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Picture
TokenPicture
Feature activation+0.000
taking
Token taking
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
rear
Token rear
Feature activation+0.000
-
Token-
Feature activation+0.000
facing
Tokenfacing
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