H9.7 top features

Top feature 0 in H9.7: (feature 11647)

TOP ACTIVATIONS
MAX = 7.354

in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+3.371
the
Token the
Feature activation+7.354
other
Token other
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Big
TokenBig
Feature activation+0.000
But
Token But
Feature activation+0.000
one
Token one
Feature activation+0.000
skill
Token skill
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.123
than
Token than
Feature activation+7.125
none
Token none
Feature activation+1.412
,
Token,
Feature activation+1.952
so
Token so
Feature activation+0.386
long
Token long
Feature activation+0.000
as
Token as
Feature activation+1.664
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
stage
Token stage
Feature activation+0.670
to
Token to
Feature activation+7.044
the
Token the
Feature activation+6.566
next
Token next
Feature activation+0.184
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
some
Token some
Feature activation+0.000
experts
Token experts
Feature activation+0.000
to
Token to
Feature activation+0.000
distinguish
Token distinguish
Feature activation+0.000
one
Token one
Feature activation+0.000
species
Token species
Feature activation+2.519
from
Token from
Feature activation+6.973
another
Token another
Feature activation+0.636
.
Token.
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
soft
Token soft
Feature activation+0.000
tissues
Token tissues
Feature activation+0.000
up
Token up
Feature activation+0.391
with
Token with
Feature activation+1.227
a
Token a
Feature activation+0.496
better
Token better
Feature activation+0.046
result
Token result
Feature activation+1.929
in
Token in
Feature activation+6.825
the
Token the
Feature activation+5.990
other
Token other
Feature activation+0.000
(
Token (
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
instance
Token instance
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
gives
Token gives
Feature activation+0.000
you
Token you
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+6.789
the
Token the
Feature activation+6.483
other
Token other
Feature activation+0.000
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.000
away
Token away
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+1.015
and
Token and
Feature activation+1.974
not
Token not
Feature activation+6.350
good
Token good
Feature activation+6.539
at
Token at
Feature activation+6.768
others
Token others
Feature activation+3.597
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
and
Token and
Feature activation+0.000
subt
Token subt
Feature activation+0.000
racted
Tokenracted
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+3.475
the
Token the
Feature activation+6.719
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
with
Token with
Feature activation+0.000
and
Token and
Feature activation+0.000
support
Token support
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
stage
Token stage
Feature activation+0.670
to
Token to
Feature activation+7.044
the
Token the
Feature activation+6.566
next
Token next
Feature activation+0.184
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
some
Token some
Feature activation+0.000
extent
Token extent
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+1.015
and
Token and
Feature activation+1.974
not
Token not
Feature activation+6.350
good
Token good
Feature activation+6.539
at
Token at
Feature activation+6.768
others
Token others
Feature activation+3.597
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
One
Token One
Feature activation+0.000
gives
Token gives
Feature activation+0.000
you
Token you
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+6.789
the
Token the
Feature activation+6.483
other
Token other
Feature activation+0.000
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+0.000
best
Token best
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+1.015
and
Token and
Feature activation+1.974
not
Token not
Feature activation+6.350
good
Token good
Feature activation+6.539
at
Token at
Feature activation+6.768
others
Token others
Feature activation+3.597
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
protected
Token protected
Feature activation+0.421
under
Token under
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
legislation
Token legislation
Feature activation+0.366
differently
Token differently
Feature activation+1.528
from
Token from
Feature activation+6.220
other
Token other
Feature activation+0.000
groups
Token groups
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.167
with
Token with
Feature activation+0.000
with
Token with
Feature activation+1.227
a
Token a
Feature activation+0.496
better
Token better
Feature activation+0.046
result
Token result
Feature activation+1.929
in
Token in
Feature activation+6.825
the
Token the
Feature activation+5.990
other
Token other
Feature activation+0.000
(
Token (
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
instance
Token instance
Feature activation+0.000
,
Token,
Feature activation+0.000
progress
Token progress
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
island
Token island
Feature activation+0.205
to
Token to
Feature activation+5.249
the
Token the
Feature activation+5.897
next
Token next
Feature activation+1.050
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
must
Token must
Feature activation+0.000
cross
Token cross
Feature activation+0.405
,
Token,
Feature activation+1.349
and
Token and
Feature activation+1.374
diff
Token diff
Feature activation+0.000
uses
Tokenuses
Feature activation+0.000
to
Token to
Feature activation+4.798
the
Token the
Feature activation+5.881
other
Token other
Feature activation+0.000
side
Token side
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
mantle
Token mantle
Feature activation+0.000
s
Tokens
Feature activation+0.000
proclaimed
Token proclaimed
Feature activation+0.000
area
Token area
Feature activation+0.102
of
Token of
Feature activation+0.000
expertise
Token expertise
Feature activation+1.952
,
Token,
Feature activation+5.872
and
Token and
Feature activation+5.384
just
Token just
Feature activation+0.472
expects
Token expects
Feature activation+0.117
voters
Token voters
Feature activation+0.432
to
Token to
Feature activation+0.000
undet
Token undet
Feature activation+0.000
ect
Tokenect
Feature activation+0.000
able
Tokenable
Feature activation+3.582
,
Token,
Feature activation+5.035
and
Token and
Feature activation+4.968
the
Token the
Feature activation+5.679
other
Token other
Feature activation+0.000
partner
Token partner
Feature activation+0.000
was
Token was
Feature activation+0.428
HIV
Token HIV
Feature activation+0.351
negative
Token negative
Feature activation+0.097
one
Token one
Feature activation+0.262
reason
Token reason
Feature activation+0.167
and
Token and
Feature activation+4.063
uses
Token uses
Feature activation+1.406
it
Token it
Feature activation+0.997
for
Token for
Feature activation+5.603
something
Token something
Feature activation+3.334
completely
Token completely
Feature activation+1.326
different
Token different
Feature activation+1.488
,
Token,
Feature activation+3.059
we
Token we
Feature activation+1.143
proclaimed
Token proclaimed
Feature activation+0.000
area
Token area
Feature activation+0.102
of
Token of
Feature activation+0.000
expertise
Token expertise
Feature activation+1.952
,
Token,
Feature activation+5.872
and
Token and
Feature activation+5.384
just
Token just
Feature activation+0.472
expects
Token expects
Feature activation+0.117
voters
Token voters
Feature activation+0.432
to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000

Top DFA by src position
MAX = 8.562

came
Token came
Feature activation-0.003
Top resid features:
wrapped
Token wrapped
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
tell
Token tell
Feature activation-0.001
Top resid features:
one
Token one
Feature activation+8.562
Top resid features:
from
Token from
Feature activation-0.101
Top resid features:
the
Token the
Feature activation-0.251
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
'm
Token'm
Feature activation-0.005
Top resid features:
listening
Token listening
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
But
Token But
Feature activation+0.009
Top resid features:
one
Token one
Feature activation+7.790
Top resid features:
skill
Token skill
Feature activation+0.109
Top resid features:
is
Token is
Feature activation+0.045
Top resid features:
better
Token better
Feature activation+0.035
Top resid features:
than
Token than
Feature activation-0.016
Top resid features:
none
Token none
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
support
Token support
Feature activation-0.003
Top resid features:
from
Token from
Feature activation-0.018
Top resid features:
one
Token one
Feature activation+7.229
Top resid features:
stage
Token stage
Feature activation+0.375
Top resid features:
to
Token to
Feature activation-0.074
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
allow
Token allow
Feature activation-0.003
Top resid features:
experts
Token experts
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.016
Top resid features:
distinguish
Token distinguish
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+7.803
Top resid features:
species
Token species
Feature activation+0.267
Top resid features:
from
Token from
Feature activation-0.214
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Unlike
Token Unlike
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
any
Token any
Feature activation-0.006
Top resid features:
ground
Token ground
Feature activation-0.002
Top resid features:
lost
Token lost
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
one
Token one
Feature activation+7.223
Top resid features:
of
Token of
Feature activation+0.071
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
elections
Token elections
Feature activation+0.035
Top resid features:
must
Token must
Feature activation-0.000
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
defend
Token defend
Feature activation-0.002
Top resid features:
yourself
Token yourself
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
One
Token One
Feature activation+7.420
Top resid features:
gives
Token gives
Feature activation+0.109
Top resid features:
you
Token you
Feature activation+0.032
Top resid features:
power
Token power
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
best
Token best
Feature activation-0.002
Top resid features:
at
Token at
Feature activation-0.011
Top resid features:
one
Token one
Feature activation+8.046
Top resid features:
thing
Token thing
Feature activation-0.117
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
not
Token not
Feature activation-0.024
Top resid features:
good
Token good
Feature activation+0.026
Top resid features:
at
Token at
Feature activation-0.011
Top resid features:
tuning
Token tuning
Feature activation+0.064
Top resid features:
fork
Token fork
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
subt
Token subt
Feature activation-0.013
Top resid features:
racted
Tokenracted
Feature activation+0.006
Top resid features:
one
Token one
Feature activation+7.354
Top resid features:
from
Token from
Feature activation+0.073
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
support
Token support
Feature activation+0.006
Top resid features:
from
Token from
Feature activation-0.027
Top resid features:
one
Token one
Feature activation+6.274
Top resid features:
stage
Token stage
Feature activation+0.725
Top resid features:
to
Token to
Feature activation+0.107
Top resid features:
the
Token the
Feature activation-0.149
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
best
Token best
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
one
Token one
Feature activation+7.266
Top resid features:
thing
Token thing
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
not
Token not
Feature activation+0.008
Top resid features:
good
Token good
Feature activation-0.001
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
defend
Token defend
Feature activation+0.005
Top resid features:
yourself
Token yourself
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
One
Token One
Feature activation+7.175
Top resid features:
gives
Token gives
Feature activation+0.110
Top resid features:
you
Token you
Feature activation+0.031
Top resid features:
power
Token power
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
the
Token the
Feature activation-0.077
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
best
Token best
Feature activation-0.003
Top resid features:
at
Token at
Feature activation-0.018
Top resid features:
one
Token one
Feature activation+7.106
Top resid features:
thing
Token thing
Feature activation+0.226
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
not
Token not
Feature activation-0.019
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
inter
Token inter
Feature activation+0.003
Top resid features:
sex
Tokensex
Feature activation+0.000
Top resid features:
status
Token status
Feature activation-0.000
Top resid features:
would
Token would
Feature activation-0.008
Top resid features:
treat
Token treat
Feature activation-0.032
Top resid features:
one
Token one
Feature activation+6.999
Top resid features:
group
Token group
Feature activation+0.182
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
people
Token people
Feature activation+0.024
Top resid features:
with
Token with
Feature activation+0.040
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
any
Token any
Feature activation-0.001
Top resid features:
ground
Token ground
Feature activation+0.002
Top resid features:
lost
Token lost
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
one
Token one
Feature activation+6.380
Top resid features:
of
Token of
Feature activation+0.105
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
elections
Token elections
Feature activation+0.061
Top resid features:
must
Token must
Feature activation-0.005
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.005
Top resid features:
To
Token To
Feature activation+0.024
Top resid features:
progress
Token progress
Feature activation-0.006
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
one
Token one
Feature activation+5.947
Top resid features:
island
Token island
Feature activation+0.281
Top resid features:
to
Token to
Feature activation+0.107
Top resid features:
the
Token the
Feature activation-0.072
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
gradient
Token gradient
Feature activation+0.010
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
mantle
Token mantle
Feature activation-0.054
Top resid features:
from
Token from
Feature activation-0.002
Top resid features:
one
Token one
Feature activation+6.344
Top resid features:
spot
Token spot
Feature activation+0.157
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
expression
Token expression
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
how
Token how
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.003
Top resid features:
works
Token works
Feature activation+0.002
Top resid features:
?
Token?
Feature activation-0.017
Top resid features:
One
Token One
Feature activation+5.946
Top resid features:
runs
Token runs
Feature activation+0.071
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
President
Token President
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
refuses
Token refuses
Feature activation+0.024
Top resid features:
o
Tokeno
Feature activation+0.008
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
different
Tokendifferent
Feature activation+0.006
Top resid features:
couples
Token couples
Feature activation+0.017
Top resid features:
where
Token where
Feature activation-0.002
Top resid features:
one
Token one
Feature activation+6.154
Top resid features:
partner
Token partner
Feature activation+0.366
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
HIV
Token HIV
Feature activation+0.011
Top resid features:
positive
Token positive
Feature activation+0.011
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
money
Token money
Feature activation-0.014
Top resid features:
promised
Token promised
Feature activation-0.002
Top resid features:
by
Token by
Feature activation-0.002
Top resid features:
law
Token law
Feature activation+0.170
Top resid features:
for
Token for
Feature activation-0.009
Top resid features:
one
Token one
Feature activation+4.179
Top resid features:
reason
Token reason
Feature activation+0.200
Top resid features:
and
Token and
Feature activation+0.056
Top resid features:
uses
Token uses
Feature activation+0.010
Top resid features:
it
Token it
Feature activation+0.047
Top resid features:
for
Token for
Feature activation+0.037
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
how
Token how
Feature activation-0.001
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
works
Token works
Feature activation-0.003
Top resid features:
?
Token?
Feature activation+0.005
Top resid features:
One
Token One
Feature activation+4.208
Top resid features:
runs
Token runs
Feature activation+0.411
Top resid features:
for
Token for
Feature activation+0.024
Top resid features:
President
Token President
Feature activation+0.016
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
refuses
Token refuses
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.08

Head 2: 0.03

Head 3: 0.05

Head 4: 0.05

Head 5: 0.04

Head 6: 0.03

Head 7: 0.57

Head 8: 0.02

Head 9: 0.03

Head 10: 0.04

Head 11: 0.03

Positive logits

another5.97

another5.60

Another5.50

Another5.21

others4.63

Secondly4.21

other4.02

Secondly3.71

Others3.63

Others3.47

other3.32

else3.30

OTHER3.16

secondly3.04

OTHER3.00

elsewhere2.92

Other2.89

Other2.88

second2.69

���2.61

Negative logits

igible-2.52

respectively-2.25

ardo-2.24

yout-2.21

rall-2.20

EntityItem-2.17

rooting-2.14

uez-2.13

oice-2.06

inese-2.03

atti-1.95

Rouse-1.94

worldly-1.94

to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+3.371
the
Token the
Feature activation+7.354
other
Token other
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Big
TokenBig
Feature activation+0.000
and
Token and
Feature activation+0.000
subt
Token subt
Feature activation+0.000
racted
Tokenracted
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+3.475
the
Token the
Feature activation+6.719
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
with
Token with
Feature activation+0.000
and
Token and
Feature activation+0.000
up
Token up
Feature activation+0.391
with
Token with
Feature activation+1.227
a
Token a
Feature activation+0.496
better
Token better
Feature activation+0.046
result
Token result
Feature activation+1.929
in
Token in
Feature activation+6.825
the
Token the
Feature activation+5.990
other
Token other
Feature activation+0.000
(
Token (
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
instance
Token instance
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+1.015
and
Token and
Feature activation+1.974
not
Token not
Feature activation+6.350
good
Token good
Feature activation+6.539
at
Token at
Feature activation+6.768
others
Token others
Feature activation+3.597
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
gives
Token gives
Feature activation+0.000
you
Token you
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+6.789
the
Token the
Feature activation+6.483
other
Token other
Feature activation+0.000
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.000
away
Token away
Feature activation+0.000

INTERVAL 5.883 - 6.619
CONTAINS 0.001%

support
Token support
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
stage
Token stage
Feature activation+0.670
to
Token to
Feature activation+7.044
the
Token the
Feature activation+6.566
next
Token next
Feature activation+0.184
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
some
Token some
Feature activation+0.000
extent
Token extent
Feature activation+0.000
protected
Token protected
Feature activation+0.421
under
Token under
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
legislation
Token legislation
Feature activation+0.366
differently
Token differently
Feature activation+1.528
from
Token from
Feature activation+6.220
other
Token other
Feature activation+0.000
groups
Token groups
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.167
with
Token with
Feature activation+0.000
best
Token best
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+1.015
and
Token and
Feature activation+1.974
not
Token not
Feature activation+6.350
good
Token good
Feature activation+6.539
at
Token at
Feature activation+6.768
others
Token others
Feature activation+3.597
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
progress
Token progress
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
island
Token island
Feature activation+0.205
to
Token to
Feature activation+5.249
the
Token the
Feature activation+5.897
next
Token next
Feature activation+1.050
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
must
Token must
Feature activation+0.000
cross
Token cross
Feature activation+0.405
One
Token One
Feature activation+0.000
gives
Token gives
Feature activation+0.000
you
Token you
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+6.789
the
Token the
Feature activation+6.483
other
Token other
Feature activation+0.000
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 5.148 - 5.883
CONTAINS 0.001%

was
Token was
Feature activation+0.000
quite
Token quite
Feature activation+0.000
confident
Token confident
Feature activation+0.000
one
Token one
Feature activation+0.000
way
Token way
Feature activation+0.000
or
Token or
Feature activation+5.332
another
Token another
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
Di
Token Di
Feature activation+0.000
agram
Tokenagram
Feature activation+0.000
be
Token be
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
floor
Token floor
Feature activation+0.000
to
Token to
Feature activation+5.234
the
Token the
Feature activation+5.141
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
looked
Token looked
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+4.776
and
Token and
Feature activation+5.183
I
Token I
Feature activation+0.982
swear
Token swear
Feature activation+0.301
if
Token if
Feature activation+0.000
she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
proclaimed
Token proclaimed
Feature activation+0.000
area
Token area
Feature activation+0.102
of
Token of
Feature activation+0.000
expertise
Token expertise
Feature activation+1.952
,
Token,
Feature activation+5.872
and
Token and
Feature activation+5.384
just
Token just
Feature activation+0.472
expects
Token expects
Feature activation+0.117
voters
Token voters
Feature activation+0.432
to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
one
Token one
Feature activation+0.000
partner
Token partner
Feature activation+0.000
was
Token was
Feature activation+0.000
HIV
Token HIV
Feature activation+0.000
positive
Token positive
Feature activation+1.397
and
Token and
Feature activation+5.192
undet
Token undet
Feature activation+0.000
ect
Tokenect
Feature activation+0.000
able
Tokenable
Feature activation+3.582
,
Token,
Feature activation+5.035
and
Token and
Feature activation+4.968

INTERVAL 4.412 - 5.148
CONTAINS 0.003%

after
Token after
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
drowning
Token drowning
Feature activation+0.000
.
Token.
Feature activation+2.585
In
Token In
Feature activation+4.401
the
Token the
Feature activation+4.914
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
,
Token,
Feature activation+0.000
candy
Token candy
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
must
Token must
Feature activation+0.000
.
Token.
Feature activation+4.635
And
Token And
Feature activation+2.883
two
Token two
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
heating
Token heating
Feature activation+0.000
's
Token's
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
absorb
Token absorb
Feature activation+0.000
sunlight
Token sunlight
Feature activation+0.000
.
Token.
Feature activation+4.665
Some
Token Some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+0.000
ice
Token ice
Feature activation+0.000
Delete
TokenDelete
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.693
Ċ
TokenĊ
Feature activation+0.595
Ċ
TokenĊ
Feature activation+4.987
Another
TokenAnother
Feature activation+0.065
called
Token called
Feature activation+0.000
him
Token him
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
their
Token their
Feature activation+0.000
soul
Token soul
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.828
,
Token,
Feature activation+4.889
while
Token while
Feature activation+4.553
others
Token others
Feature activation+0.000
are
Token are
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.677 - 4.412
CONTAINS 0.003%

is
Token is
Feature activation+1.961
to
Token to
Feature activation+0.685
miss
Token miss
Feature activation+4.258
out
Token out
Feature activation+2.052
on
Token on
Feature activation+3.176
the
Token the
Feature activation+3.904
fun
Token fun
Feature activation+0.000
of
Token of
Feature activation+1.504
what
Token what
Feature activation+0.111
is
Token is
Feature activation+0.041
,
Token,
Feature activation+0.154
of
Token of
Feature activation+0.000
soil
Token soil
Feature activation+0.000
and
Token and
Feature activation+0.000
rock
Token rock
Feature activation+0.000
samples
Token samples
Feature activation+0.000
.
Token.
Feature activation+3.874
In
Token In
Feature activation+0.575
the
Token the
Feature activation+0.248
future
Token future
Feature activation+0.000
,
Token,
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000
by
Token by
Feature activation+2.800
law
Token law
Feature activation+0.492
for
Token for
Feature activation+2.162
one
Token one
Feature activation+0.262
reason
Token reason
Feature activation+0.167
and
Token and
Feature activation+4.063
uses
Token uses
Feature activation+1.406
it
Token it
Feature activation+0.997
for
Token for
Feature activation+5.603
something
Token something
Feature activation+3.334
completely
Token completely
Feature activation+1.326
mostly
Tokenmostly
Feature activation+0.000
completely
Token completely
Feature activation+0.000
discredited
Token discredited
Feature activation+0.000
)
Token)
Feature activation+2.348
and
Token and
Feature activation+5.059
ignoring
Token ignoring
Feature activation+4.287
everything
Token everything
Feature activation+2.454
else
Token else
Feature activation+0.388
.
Token.
Feature activation+0.000
Deb
Token Deb
Feature activation+0.000
unk
Tokenunk
Feature activation+0.000
F
Token F
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
One
Token One
Feature activation+0.000
Size
Token Size
Feature activation+0.000
N
Token N
Feature activation+0.000
Leather
Token Leather
Feature activation+3.779
/
Token/
Feature activation+0.000
Sp
TokenSp
Feature activation+0.000
and
Tokenand
Feature activation+0.000
ex
Tokenex
Feature activation+3.641
12
Token 12
Feature activation+1.268

INTERVAL 2.942 - 3.677
CONTAINS 0.004%

is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
level
Token level
Feature activation+0.000
of
Token of
Feature activation+0.000
threat
Token threat
Feature activation+0.000
.
Token.
Feature activation+3.612
But
Token But
Feature activation+0.250
this
Token this
Feature activation+0.341
is
Token is
Feature activation+3.739
what
Token what
Feature activation+0.000
has
Token has
Feature activation+0.000
fork
Token fork
Feature activation+0.000
and
Token and
Feature activation+0.000
subt
Token subt
Feature activation+0.000
racted
Tokenracted
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+3.475
the
Token the
Feature activation+6.719
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.000
with
Token with
Feature activation+0.000
wrapped
Token wrapped
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+3.371
the
Token the
Feature activation+7.354
other
Token other
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
one
Tokenone
Feature activation+0.000
team
Token team
Feature activation+0.000
,
Token,
Feature activation+3.077
one
Token one
Feature activation+0.000
heartbeat
Token heartbeat
Feature activation+0.021
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
consum
Token consum
Feature activation+0.000
mate
Tokenmate
Feature activation+0.000
in
Token in
Feature activation+0.000
virtue
Token virtue
Feature activation+0.267
&
Token &
Feature activation+2.781
vision
Token vision
Feature activation+3.398
,
Token,
Feature activation+4.231
jud
Token jud
Feature activation+0.000
icious
Tokenicious
Feature activation+0.817
,
Token,
Feature activation+0.392
speaking
Token speaking
Feature activation+0.678

INTERVAL 2.206 - 2.942
CONTAINS 0.009%

pin
Token pin
Feature activation+0.000
him
Token him
Feature activation+0.000
and
Token and
Feature activation+0.000
move
Token move
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+2.351
If
Token If
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
honor
Token honor
Feature activation+0.180
,
Token,
Feature activation+3.794
one
Token one
Feature activation+0.000
has
Token has
Feature activation+0.007
given
Token given
Feature activation+1.196
to
Token to
Feature activation+2.696
private
Token private
Feature activation+0.000
and
Token and
Feature activation+0.000
chaotic
Token chaotic
Feature activation+0.265
material
Token material
Feature activation+0.150
a
Token a
Feature activation+0.000
shot
Token shot
Feature activation+0.000
once
Token once
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
,
Token,
Feature activation+2.228
once
Token once
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+1.071
vocal
Token vocal
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
way
Token way
Feature activation+0.000
or
Token or
Feature activation+2.391
another
Token another
Feature activation+0.000
since
Token since
Feature activation+0.404
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
.
Token.
Feature activation+0.557
This
Token This
Feature activation+0.092
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+2.322
Ale
Token Ale
Feature activation+0.000
jandro
Tokenjandro
Feature activation+0.000
J
Token J
Feature activation+0.000
odor
Tokenodor
Feature activation+0.000
owsky
Tokenowsky
Feature activation+0.000

INTERVAL 1.471 - 2.206
CONTAINS 0.015%

different
Token different
Feature activation+0.000
parts
Token parts
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
.
Token.
Feature activation+1.473
If
Token If
Feature activation+0.000
this
Token this
Feature activation+0.000
really
Token really
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
officer
Token officer
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
fired
Token fired
Feature activation+0.216
.
Token.
Feature activation+2.091
The
Token The
Feature activation+1.794
next
Token next
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
Lindsay
Token Lindsay
Feature activation+0.000
called
Token called
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
one
Token one
Feature activation+0.000
goal
Token goal
Feature activation+0.000
.
Token.
Feature activation+1.605
The
Token The
Feature activation+1.584
only
Token only
Feature activation+0.000
goal
Token goal
Feature activation+0.000
is
Token is
Feature activation+0.758
I
Token I
Feature activation+0.000
want
Token want
Feature activation+0.000
with
Token with
Feature activation+0.000
one
Token one
Feature activation+0.000
organism
Token organism
Feature activation+0.089
,
Token,
Feature activation+1.091
and
Token and
Feature activation+1.459
then
Token then
Feature activation+1.720
you
Token you
Feature activation+1.276
find
Token find
Feature activation+3.357
more
Token more
Feature activation+1.504
and
Token and
Feature activation+0.000
more
Token more
Feature activation+2.095
trans
Token trans
Feature activation+0.000
onic
Tokenonic
Feature activation+0.000
(
Token (
Feature activation+0.000
Mach
TokenMach
Feature activation+0.000
number
Token number
Feature activation+0.000
around
Token around
Feature activation+2.025
1
Token 1
Feature activation+0.000
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.000
su
Token su
Feature activation+0.000
person
Tokenperson
Feature activation+0.000

INTERVAL 0.735 - 1.471
CONTAINS 0.038%

t
Token t
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
les
Tokenles
Feature activation+0.246
with
Token with
Feature activation+1.624
suicidal
Token suicidal
Feature activation+0.000
wishes
Token wishes
Feature activation+1.293
a
Token a
Feature activation+0.879
drama
Token drama
Feature activation+0.140
of
Token of
Feature activation+0.214
love
Token love
Feature activation+0.000
and
Token and
Feature activation+0.081
one
Token one
Feature activation+0.000
year
Token year
Feature activation+0.000
of
Token of
Feature activation+0.000
community
Token community
Feature activation+0.000
control
Token control
Feature activation+0.000
and
Token and
Feature activation+0.744
four
Token four
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
probation
Token probation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Source
Token Source
Feature activation+0.000
Agreement
Token Agreement
Feature activation+0.000
.
Token.
Feature activation+0.803
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.146
In
TokenIn
Feature activation+0.677
response
Token response
Feature activation+0.000
to
Token to
Feature activation+0.000
developments
Token developments
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
site
Token site
Feature activation+0.000
.
Token.
Feature activation+0.956
The
Token The
Feature activation+0.891
Sy
Token Sy
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
et
Tokenet
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
arm
Token arm
Feature activation+0.000
resting
Token resting
Feature activation+0.117
on
Token on
Feature activation+0.650
his
Token his
Feature activation+0.689
leg
Token leg
Feature activation+0.103
,
Token,
Feature activation+1.424
answering
Token answering
Feature activation+0.000
every
Token every
Feature activation+0.000
single
Token single
Feature activation+0.000
question
Token question
Feature activation+0.000
put
Token put
Feature activation+0.000

INTERVAL 0.000 - 0.735
CONTAINS 99.925%

af
Tokenaf
Feature activation+0.000
Q
Token Q
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
/
Token/
Feature activation+0.000
Associated
TokenAssociated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
either
Token either
Feature activation+0.000
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
consider
Token consider
Feature activation+0.000
packing
Token packing
Feature activation+0.000
to
Token to
Feature activation+0.000
accept
Token accept
Feature activation+0.000
the
Token the
Feature activation+0.000
invitation
Token invitation
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
opening
Token opening
Feature activation+0.000
prayer
Token prayer
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
Enc
TokenEnc
Feature activation+0.000
ryption
Tokenryption
Feature activation+0.000
of
Token of
Feature activation+0.000
queries
Token queries
Feature activation+0.000
and
Token and
Feature activation+0.000
stores
Token stores
Feature activation+0.000
to
Token to
Feature activation+0.000
flood
Token flood
Feature activation+0.000
fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
for
Token for
Feature activation+0.000
%
Token%
Feature activation+0.000
(
Token (
Feature activation+0.000
146
Token146
Feature activation+0.000
of
Token of
Feature activation+0.000
313
Token 313
Feature activation+0.000
),
Token),
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
they
Token they
Feature activation+0.000
"
Token "
Feature activation+0.000
felt
Tokenfelt
Feature activation+0.000
threatened
Token threatened
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 H9.7: (feature 9789)

TOP ACTIVATIONS
MAX = 8.145

as
Token as
Feature activation+0.399
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
thought
Token thought
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+8.145
too
Token too
Feature activation+0.000
,
Token,
Feature activation+5.018
and
Token and
Feature activation+6.434
their
Token their
Feature activation+0.224
faces
Token faces
Feature activation+0.000
sunk
Token sunk
Feature activation+0.000
en
Tokenen
Feature activation+0.000
and
Token and
Feature activation+4.867
swamp
Token swamp
Feature activation+0.000
y
Tokeny
Feature activation+0.957
,
Token,
Feature activation+7.713
and
Token and
Feature activation+7.595
others
Token others
Feature activation+0.938
cont
Token cont
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
that
Token that
Feature activation+0.000
en
Tokenen
Feature activation+0.000
and
Token and
Feature activation+4.867
swamp
Token swamp
Feature activation+0.000
y
Tokeny
Feature activation+0.957
,
Token,
Feature activation+7.713
and
Token and
Feature activation+7.595
others
Token others
Feature activation+0.938
cont
Token cont
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
some
Token some
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
were
Token were
Feature activation+0.000
fully
Token fully
Feature activation+0.000
clothed
Token clothed
Feature activation+0.000
,
Token,
Feature activation+7.358
others
Token others
Feature activation+0.000
almost
Token almost
Feature activation+0.000
naked
Token naked
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
argued
Token argued
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
origin
Token origin
Feature activation+0.000
,
Token,
Feature activation+7.334
with
Token with
Feature activation+1.791
either
Token either
Feature activation+0.000
rice
Token rice
Feature activation+0.000
agriculture
Token agriculture
Feature activation+0.000
spreading
Token spreading
Feature activation+0.000
require
Token require
Feature activation+0.000
intricate
Token intricate
Feature activation+0.000
and
Token and
Feature activation+0.606
precise
Token precise
Feature activation+0.000
masks
Token masks
Feature activation+0.274
,
Token,
Feature activation+7.175
while
Token while
Feature activation+6.843
for
Token for
Feature activation+6.754
others
Token others
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
read
Tokenread
Feature activation+0.000
Bra
Token Bra
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
.
Token.
Feature activation+5.372
But
Token But
Feature activation+4.728
in
Token in
Feature activation+7.167
this
Token this
Feature activation+0.917
session
Token session
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
encouraging
Token encouraging
Feature activation+0.384
mil
Token mil
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
domest
Token domest
Feature activation+0.000
ication
Tokenication
Feature activation+0.296
,
Token,
Feature activation+7.008
or
Token or
Feature activation+0.110
early
Token early
Feature activation+0.000
mil
Token mil
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
farming
Token farming
Feature activation+0.000
aturally
Tokenaturally
Feature activation+0.000
mature
Token mature
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
age
Token age
Feature activation+0.000
.
Token.
Feature activation+6.863
Others
Token Others
Feature activation+0.424
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
utterly
Token utterly
Feature activation+0.000
hard
Token hard
Feature activation+0.000
intricate
Token intricate
Feature activation+0.000
and
Token and
Feature activation+0.606
precise
Token precise
Feature activation+0.000
masks
Token masks
Feature activation+0.274
,
Token,
Feature activation+7.175
while
Token while
Feature activation+6.843
for
Token for
Feature activation+6.754
others
Token others
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.606
precise
Token precise
Feature activation+0.000
masks
Token masks
Feature activation+0.274
,
Token,
Feature activation+7.175
while
Token while
Feature activation+6.843
for
Token for
Feature activation+6.754
others
Token others
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
edged
Tokenedged
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
definitions
Token definitions
Feature activation+0.000
require
Token require
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+6.726
and
Token and
Feature activation+3.926
some
Token some
Feature activation+0.294
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
.
Token.
Feature activation+2.111
in
Token in
Feature activation+0.009
effect
Token effect
Feature activation+0.000
likely
Token likely
Feature activation+0.000
be
Token be
Feature activation+0.000
permanent
Token permanent
Feature activation+0.071
,
Token,
Feature activation+6.701
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.000
subject
Token subject
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
thing
Token thing
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
,
Token,
Feature activation+2.668
while
Token while
Feature activation+6.686
others
Token others
Feature activation+0.000
call
Token call
Feature activation+0.000
it
Token it
Feature activation+0.000
barbaric
Token barbaric
Feature activation+0.000
.
Token.
Feature activation+0.418
Some
Token Some
Feature activation+0.000
are
Token are
Feature activation+0.000
chosen
Token chosen
Feature activation+0.061
as
Token as
Feature activation+0.000
leaders
Token leaders
Feature activation+0.361
,
Token,
Feature activation+6.607
collecting
Token collecting
Feature activation+0.000
data
Token data
Feature activation+0.559
from
Token from
Feature activation+0.527
the
Token the
Feature activation+0.720
other
Token other
Feature activation+0.000
more
Token more
Feature activation+0.000
prone
Token prone
Feature activation+0.000
to
Token to
Feature activation+0.000
cr
Token cr
Feature activation+0.000
amping
Tokenamping
Feature activation+0.410
,
Token,
Feature activation+6.520
and
Token and
Feature activation+5.459
heat
Token heat
Feature activation+0.000
makes
Token makes
Feature activation+0.087
it
Token it
Feature activation+0.000
worse
Token worse
Feature activation+0.104
some
Token some
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.391
inadequate
Token inadequate
Feature activation+4.971
in
Token in
Feature activation+6.501
other
Token other
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
where
Token where
Feature activation+0.000
thought
Token thought
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+8.145
too
Token too
Feature activation+0.000
,
Token,
Feature activation+5.018
and
Token and
Feature activation+6.434
their
Token their
Feature activation+0.224
faces
Token faces
Feature activation+0.000
gr
Token gr
Feature activation+0.000
aced
Tokenaced
Feature activation+0.000
the
Token the
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
poly
Token poly
Feature activation+0.000
.
Token.
Feature activation+6.429
Occasionally
Token Occasionally
Feature activation+0.393
,
Token,
Feature activation+0.461
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
even
Token even
Feature activation+0.000
giant
Token giant
Feature activation+0.000
's
Token's
Feature activation+0.000
move
Token move
Feature activation+0.000
as
Token as
Feature activation+0.000
insignificant
Token insignificant
Feature activation+0.000
,
Token,
Feature activation+6.390
advocates
Token advocates
Feature activation+0.000
of
Token of
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
state
Token state
Feature activation+0.000
hood
Tokenhood
Feature activation+0.750

Top DFA by src position
MAX = 8.586

masters
Token masters
Feature activation+0.005
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
universe
Token universe
Feature activation+0.002
Top resid features:
;
Token;
Feature activation+0.010
Top resid features:
some
Token some
Feature activation+8.586
Top resid features:
paid
Token paid
Feature activation+0.021
Top resid features:
themselves
Token themselves
Feature activation+0.071
Top resid features:
as
Token as
Feature activation+0.026
Top resid features:
if
Token if
Feature activation+0.042
Top resid features:
they
Token they
Feature activation+0.011
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
scale
Tokenscale
Feature activation-0.006
Top resid features:
construction
Token construction
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.018
Top resid features:
some
Token some
Feature activation+8.445
Top resid features:
character
Token character
Feature activation+0.003
Top resid features:
ising
Tokenising
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
area
Token area
Feature activation+0.001
Top resid features:
as
Token as
Feature activation+0.009
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
scale
Tokenscale
Feature activation+0.000
Top resid features:
construction
Token construction
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
with
Token with
Feature activation+0.017
Top resid features:
some
Token some
Feature activation+8.266
Top resid features:
character
Token character
Feature activation+0.001
Top resid features:
ising
Tokenising
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
area
Token area
Feature activation+0.011
Top resid features:
as
Token as
Feature activation+0.009
Top resid features:
their
Token their
Feature activation-0.000
Top resid features:
own
Token own
Feature activation-0.001
Top resid features:
anomalies
Token anomalies
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.007
Top resid features:
some
Token some
Feature activation+8.008
Top resid features:
bodies
Token bodies
Feature activation+0.042
Top resid features:
were
Token were
Feature activation+0.025
Top resid features:
fully
Token fully
Feature activation-0.011
Top resid features:
clothed
Token clothed
Feature activation+0.085
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
study
Token study
Feature activation+0.002
Top resid features:
explains
Token explains
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
âĢ
Token âĢ
Feature activation+0.036
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
Some
TokenSome
Feature activation+7.764
Top resid features:
have
Token have
Feature activation+0.056
Top resid features:
argued
Token argued
Feature activation+0.057
Top resid features:
for
Token for
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.038
Top resid features:
single
Token single
Feature activation+0.056
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
each
Token each
Feature activation-0.001
Top resid features:
image
Token image
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Some
Token Some
Feature activation+7.683
Top resid features:
scenes
Token scenes
Feature activation+0.015
Top resid features:
may
Token may
Feature activation+0.049
Top resid features:
require
Token require
Feature activation+0.043
Top resid features:
intricate
Token intricate
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
pages
Token pages
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
In
TokenIn
Feature activation-0.016
Top resid features:
some
Token some
Feature activation+7.620
Top resid features:
events
Token events
Feature activation+0.111
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
they
Token they
Feature activation-0.005
Top resid features:
proof
Token proof
Feature activation-0.001
Top resid features:
read
Tokenread
Feature activation-0.003
Top resid features:
study
Token study
Feature activation+0.001
Top resid features:
explains
Token explains
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.006
Top resid features:
Some
TokenSome
Feature activation+7.126
Top resid features:
have
Token have
Feature activation+0.046
Top resid features:
argued
Token argued
Feature activation+0.018
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
single
Token single
Feature activation-0.007
Top resid features:
believe
Token believe
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Some
TokenSome
Feature activation+7.313
Top resid features:
said
Token said
Feature activation+0.255
Top resid features:
he
Token he
Feature activation+0.010
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
unn
Token unn
Feature activation+0.002
Top resid features:
aturally
Tokenaturally
Feature activation-0.001
Top resid features:
different
Token different
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
image
Token image
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Some
Token Some
Feature activation+7.519
Top resid features:
scenes
Token scenes
Feature activation+0.011
Top resid features:
may
Token may
Feature activation+0.040
Top resid features:
require
Token require
Feature activation+0.006
Top resid features:
intricate
Token intricate
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
different
Token different
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
each
Token each
Feature activation-0.005
Top resid features:
image
Token image
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Some
Token Some
Feature activation+7.484
Top resid features:
scenes
Token scenes
Feature activation+0.013
Top resid features:
may
Token may
Feature activation+0.022
Top resid features:
require
Token require
Feature activation+0.007
Top resid features:
intricate
Token intricate
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
trans
Token trans
Feature activation-0.009
Top resid features:
itive
Tokenitive
Feature activation-0.022
Top resid features:
verb
Token verb
Feature activation-0.042
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Some
Token Some
Feature activation+7.500
Top resid features:
definitions
Token definitions
Feature activation+0.039
Top resid features:
require
Token require
Feature activation+0.037
Top resid features:
movement
Token movement
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
ump
Tokenump
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
EU
TokenEU
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
some
Tokensome
Feature activation+7.102
Top resid features:
of
Token of
Feature activation+0.139
Top resid features:
the
Token the
Feature activation+0.071
Top resid features:
measures
Token measures
Feature activation+0.011
Top resid features:
contemplated
Token contemplated
Feature activation-0.009
Top resid features:
would
Token would
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
books
Token books
Feature activation+0.002
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
decades
Token decades
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Some
Token Some
Feature activation+7.264
Top resid features:
officers
Token officers
Feature activation+0.093
Top resid features:
say
Token say
Feature activation+0.018
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
solve
Token solve
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
problem
Token problem
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Some
Token Some
Feature activation+7.057
Top resid features:
are
Token are
Feature activation+0.024
Top resid features:
chosen
Token chosen
Feature activation+0.052
Top resid features:
as
Token as
Feature activation+0.043
Top resid features:
leaders
Token leaders
Feature activation+0.134
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
excessive
Token excessive
Feature activation+0.008
Top resid features:
heat
Token heat
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.051
Top resid features:
Some
TokenSome
Feature activation+7.021
Top resid features:
people
Token people
Feature activation+0.181
Top resid features:
are
Token are
Feature activation+0.024
Top resid features:
naturally
Token naturally
Feature activation+0.011
Top resid features:
more
Token more
Feature activation+0.013
Top resid features:
prone
Token prone
Feature activation+0.049
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
an
Token an
Feature activation+0.004
Top resid features:
adequate
Token adequate
Feature activation-0.002
Top resid features:
justification
Token justification
Feature activation-0.015
Top resid features:
in
Token in
Feature activation-0.009
Top resid features:
some
Token some
Feature activation+7.515
Top resid features:
cases
Token cases
Feature activation-0.047
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
but
Token but
Feature activation-0.024
Top resid features:
inadequate
Token inadequate
Feature activation-0.076
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
masters
Token masters
Feature activation+0.005
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
universe
Token universe
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.012
Top resid features:
some
Token some
Feature activation+6.912
Top resid features:
paid
Token paid
Feature activation+0.032
Top resid features:
themselves
Token themselves
Feature activation+0.053
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
if
Token if
Feature activation-0.003
Top resid features:
they
Token they
Feature activation+0.015
Top resid features:
right
Token right
Feature activation-0.000
Top resid features:
person
Token person
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Some
TokenSome
Feature activation+6.825
Top resid features:
people
Token people
Feature activation+0.119
Top resid features:
will
Token will
Feature activation+0.052
Top resid features:
just
Token just
Feature activation+0.006
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
right
Token right
Feature activation-0.000
Top resid features:
J
TokenJ
Feature activation-0.001
Top resid features:
stream
Tokenstream
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
While
TokenWhile
Feature activation+0.004
Top resid features:
some
Token some
Feature activation+6.663
Top resid features:
net
Token net
Feature activation-0.024
Top resid features:
izens
Tokenizens
Feature activation+0.373
Top resid features:
dismissed
Token dismissed
Feature activation+0.107
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
internet
Token internet
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.09

Head 2: 0.03

Head 3: 0.05

Head 4: 0.06

Head 5: 0.04

Head 6: 0.02

Head 7: 0.56

Head 8: 0.02

Head 9: 0.02

Head 10: 0.07

Head 11: 0.02

Positive logits

others7.66

Others7.01

Others6.81

other3.59

other3.32

rest3.31

Other2.89

Other2.81

remainder2.64

some2.34

newcomers2.32

eva2.25

mates2.24

IV2.22

JUSTICE2.18

OTHER2.17

roup2.13

outsiders2.12

remaining2.10

Pac2.09

Negative logits

ardo-2.55

ulhu-2.50

^^^^-2.46

Twice-2.32

elope-2.32

ftime-2.30

@#&-2.30

igible-2.28

guiActiveUn-2.22

furnace-2.21

-2.18

opausal-2.17

twin-2.16

inez-2.14

igan-2.14

MpServer-2.14

bernatorial-2.13

dl-2.11

dstg-2.11

ilogy-2.10

INTERVAL 7.331 - 8.145
CONTAINS 0.001%

argued
Token argued
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
origin
Token origin
Feature activation+0.000
,
Token,
Feature activation+7.334
with
Token with
Feature activation+1.791
either
Token either
Feature activation+0.000
rice
Token rice
Feature activation+0.000
agriculture
Token agriculture
Feature activation+0.000
spreading
Token spreading
Feature activation+0.000
as
Token as
Feature activation+0.399
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
thought
Token thought
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+8.145
too
Token too
Feature activation+0.000
,
Token,
Feature activation+5.018
and
Token and
Feature activation+6.434
their
Token their
Feature activation+0.224
faces
Token faces
Feature activation+0.000
sunk
Token sunk
Feature activation+0.000
en
Tokenen
Feature activation+0.000
and
Token and
Feature activation+4.867
swamp
Token swamp
Feature activation+0.000
y
Tokeny
Feature activation+0.957
,
Token,
Feature activation+7.713
and
Token and
Feature activation+7.595
others
Token others
Feature activation+0.938
cont
Token cont
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
that
Token that
Feature activation+0.000
en
Tokenen
Feature activation+0.000
and
Token and
Feature activation+4.867
swamp
Token swamp
Feature activation+0.000
y
Tokeny
Feature activation+0.957
,
Token,
Feature activation+7.713
and
Token and
Feature activation+7.595
others
Token others
Feature activation+0.938
cont
Token cont
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
some
Token some
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
were
Token were
Feature activation+0.000
fully
Token fully
Feature activation+0.000
clothed
Token clothed
Feature activation+0.000
,
Token,
Feature activation+7.358
others
Token others
Feature activation+0.000
almost
Token almost
Feature activation+0.000
naked
Token naked
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000

INTERVAL 6.516 - 7.331
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
definitions
Token definitions
Feature activation+0.000
require
Token require
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+6.726
and
Token and
Feature activation+3.926
some
Token some
Feature activation+0.294
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
.
Token.
Feature activation+2.111
intricate
Token intricate
Feature activation+0.000
and
Token and
Feature activation+0.606
precise
Token precise
Feature activation+0.000
masks
Token masks
Feature activation+0.274
,
Token,
Feature activation+7.175
while
Token while
Feature activation+6.843
for
Token for
Feature activation+6.754
others
Token others
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.606
precise
Token precise
Feature activation+0.000
masks
Token masks
Feature activation+0.274
,
Token,
Feature activation+7.175
while
Token while
Feature activation+6.843
for
Token for
Feature activation+6.754
others
Token others
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
edged
Tokenedged
Feature activation+0.000
require
Token require
Feature activation+0.000
intricate
Token intricate
Feature activation+0.000
and
Token and
Feature activation+0.606
precise
Token precise
Feature activation+0.000
masks
Token masks
Feature activation+0.274
,
Token,
Feature activation+7.175
while
Token while
Feature activation+6.843
for
Token for
Feature activation+6.754
others
Token others
Feature activation+0.000
a
Token a
Feature activation+0.000
soft
Token soft
Feature activation+0.000
Some
Token Some
Feature activation+0.000
are
Token are
Feature activation+0.000
chosen
Token chosen
Feature activation+0.061
as
Token as
Feature activation+0.000
leaders
Token leaders
Feature activation+0.361
,
Token,
Feature activation+6.607
collecting
Token collecting
Feature activation+0.000
data
Token data
Feature activation+0.559
from
Token from
Feature activation+0.527
the
Token the
Feature activation+0.720
other
Token other
Feature activation+0.000

INTERVAL 5.702 - 6.516
CONTAINS 0.002%

giant
Token giant
Feature activation+0.000
's
Token's
Feature activation+0.000
move
Token move
Feature activation+0.000
as
Token as
Feature activation+0.000
insignificant
Token insignificant
Feature activation+0.000
,
Token,
Feature activation+6.390
advocates
Token advocates
Feature activation+0.000
of
Token of
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
state
Token state
Feature activation+0.000
hood
Tokenhood
Feature activation+0.750
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
are
Token are
Feature activation+0.000
tough
Token tough
Feature activation+0.000
decisions
Token decisions
Feature activation+0.929
.
Token.
Feature activation+6.303
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.298
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.101
transformative
Token transformative
Feature activation+0.000
technology
Token technology
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
,
Token,
Feature activation+5.959
and
Token and
Feature activation+3.976
the
Token the
Feature activation+0.000
potential
Token potential
Feature activation+0.000
use
Token use
Feature activation+0.000
cases
Token cases
Feature activation+0.000
thought
Token thought
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+8.145
too
Token too
Feature activation+0.000
,
Token,
Feature activation+5.018
and
Token and
Feature activation+6.434
their
Token their
Feature activation+0.224
faces
Token faces
Feature activation+0.000
gr
Token gr
Feature activation+0.000
aced
Tokenaced
Feature activation+0.000
the
Token the
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+0.289
,
Token,
Feature activation+6.190
while
Token while
Feature activation+5.543
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 4.887 - 5.702
CONTAINS 0.003%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
succeed
Token succeed
Feature activation+1.529
as
Token as
Feature activation+0.097
well
Token well
Feature activation+0.938
as
Token as
Feature activation+5.259
we
Token we
Feature activation+0.000
would
Token would
Feature activation+0.000
like
Token like
Feature activation+0.000
.
Token.
Feature activation+1.213
âĢ
TokenâĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
debt
Token debt
Feature activation+0.000
blew
Token blew
Feature activation+0.000
up
Token up
Feature activation+0.417
and
Token and
Feature activation+5.178
was
Token was
Feature activation+0.000
written
Token written
Feature activation+0.000
off
Token off
Feature activation+0.000
.
Token.
Feature activation+4.416
For
Token For
Feature activation+3.802
room
Token room
Feature activation+0.000
for
Token for
Feature activation+0.000
them
Token them
Feature activation+0.253
in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
,
Token,
Feature activation+4.889
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
make
Token make
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
dependent
Token dependent
Feature activation+0.000
on
Token on
Feature activation+0.453
urban
Token urban
Feature activation+0.000
habitat
Token habitat
Feature activation+0.083
,
Token,
Feature activation+5.174
in
Token in
Feature activation+0.298
fact
Token fact
Feature activation+0.000
.
Token.
Feature activation+0.462
For
Token For
Feature activation+0.010
51
Token 51
Feature activation+0.000
hours
Token hours
Feature activation+0.764
of
Token of
Feature activation+0.369
falling
Token falling
Feature activation+0.000
asleep
Token asleep
Feature activation+0.000
,
Token,
Feature activation+5.638
while
Token while
Feature activation+5.674
others
Token others
Feature activation+0.000
might
Token might
Feature activation+0.000
only
Token only
Feature activation+0.000
experience
Token experience
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000

INTERVAL 4.073 - 4.887
CONTAINS 0.003%

the
Token the
Feature activation+0.000
covers
Token covers
Feature activation+0.000
of
Token of
Feature activation+0.000
magazines
Token magazines
Feature activation+0.000
everywhere
Token everywhere
Feature activation+0.000
.
Token.
Feature activation+4.087
But
Token But
Feature activation+0.380
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
own
Token own
Feature activation+0.000
struggles
Token struggles
Feature activation+0.000
with
Token with
Feature activation+0.000
addiction
Token addiction
Feature activation+0.000
,
Token,
Feature activation+5.993
while
Token while
Feature activation+4.369
others
Token others
Feature activation+0.287
described
Token described
Feature activation+0.000
it
Token it
Feature activation+0.036
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.027
as
Token as
Feature activation+0.000
sunk
Token sunk
Feature activation+0.000
en
Tokenen
Feature activation+0.000
and
Token and
Feature activation+4.867
swamp
Token swamp
Feature activation+0.000
y
Tokeny
Feature activation+0.957
,
Token,
Feature activation+7.713
and
Token and
Feature activation+7.595
others
Token others
Feature activation+0.938
ified
Tokenified
Feature activation+0.000
lights
Token lights
Feature activation+0.199
without
Token without
Feature activation+0.000
any
Token any
Feature activation+0.000
issue
Token issue
Feature activation+0.112
.
Token.
Feature activation+4.689
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.254
That
TokenThat
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
can
Token can
Feature activation+0.000
automate
Token automate
Feature activation+0.108
with
Token with
Feature activation+0.000
Task
Token Task
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+4.095
and
Token and
Feature activation+2.745
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+2.382

INTERVAL 3.258 - 4.073
CONTAINS 0.004%

we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
ul
Token ul
Feature activation+0.000
terior
Tokenterior
Feature activation+0.000
motives
Token motives
Feature activation+0.000
,
Token,
Feature activation+3.519
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.999
said
Token said
Feature activation+0.000
Capt
Token Capt
Feature activation+0.000
.
Token.
Feature activation+0.000
produce
Token produce
Feature activation+0.000
trust
Token trust
Feature activation+0.000
-
Token-
Feature activation+0.000
worthy
Tokenworthy
Feature activation+0.000
content
Token content
Feature activation+0.000
.
Token.
Feature activation+3.699
Examples
Token Examples
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Start
TokenStart
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
gluten
Token gluten
Feature activation+0.000
formation
Token formation
Feature activation+0.000
,
Token,
Feature activation+3.876
like
Token like
Feature activation+0.000
bread
Token bread
Feature activation+0.000
and
Token and
Feature activation+0.000
pizza
Token pizza
Feature activation+0.000
dough
Token dough
Feature activation+0.000
the
Token the
Feature activation+0.000
food
Token food
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
lost
Token lost
Feature activation+0.000
,
Token,
Feature activation+3.416
passing
Token passing
Feature activation+0.000
straight
Token straight
Feature activation+0.000
through
Token through
Feature activation+0.009
you
Token you
Feature activation+0.000
.
Token.
Feature activation+2.158
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
500
Token 500
Feature activation+0.000
years
Token years
Feature activation+0.000
old
Token old
Feature activation+0.000
.
Token.
Feature activation+3.636
They
Token They
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
very
Token very
Feature activation+0.000
complex
Token complex
Feature activation+0.000

INTERVAL 2.444 - 3.258
CONTAINS 0.005%

some
Token some
Feature activation+0.000
do
Token do
Feature activation+0.000
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
military
Token military
Feature activation+0.000
backgrounds
Token backgrounds
Feature activation+3.243
there
Token there
Feature activation+0.717
's
Token's
Feature activation+0.940
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
about
Token about
Feature activation+0.000
imports
Token imports
Feature activation+0.000
some
Token some
Feature activation+0.000
goods
Token goods
Feature activation+0.000
from
Token from
Feature activation+0.000
China
Token China
Feature activation+0.580
,
Token,
Feature activation+2.570
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
iPad
Token iPad
Feature activation+0.000
accessories
Token accessories
Feature activation+0.000
and
Token and
Feature activation+0.000
tradition
Token tradition
Feature activation+0.533
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
Enlightenment
Token Enlightenment
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+2.714
that
Tokenthat
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Hot
TokenHot
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
humane
Token humane
Feature activation+0.000
thing
Token thing
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
,
Token,
Feature activation+2.668
while
Token while
Feature activation+6.686
others
Token others
Feature activation+0.000
call
Token call
Feature activation+0.000
it
Token it
Feature activation+0.000
barbaric
Token barbaric
Feature activation+0.000
Devices
Token Devices
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Pebble
Token Pebble
Feature activation+0.000
.
Token.
Feature activation+3.650
For
Token For
Feature activation+2.838
more
Token more
Feature activation+0.000
information
Token information
Feature activation+0.000
,
Token,
Feature activation+0.000
call
Token call
Feature activation+0.000
310
Token 310
Feature activation+0.000

INTERVAL 1.629 - 2.444
CONTAINS 0.010%

shocking
Token shocking
Feature activation+0.000
,
Token,
Feature activation+3.539
some
Token some
Feature activation+0.000
are
Token are
Feature activation+0.000
bizarre
Token bizarre
Feature activation+0.000
,
Token,
Feature activation+2.049
and
Token and
Feature activation+1.783
some
Token some
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
great
Token great
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.081
looking
Token looking
Feature activation+0.013
like
Token like
Feature activation+0.000
peanuts
Token peanuts
Feature activation+0.753
.
Token.
Feature activation+2.159
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Plan
TokenPlan
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
three
Token three
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+2.009
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.037
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
These
TokenThese
Feature activation+0.000
+
Token+
Feature activation+0.000
that
Token that
Feature activation+0.000
occurred
Token occurred
Feature activation+0.000
in
Token in
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+1.785
But
Token But
Feature activation+0.480
testimony
Token testimony
Feature activation+0.000
by
Token by
Feature activation+0.000
various
Token various
Feature activation+0.000
governments
Token governments
Feature activation+0.000
,
Token,
Feature activation+1.826
print
Token print
Feature activation+0.000
able
Tokenable
Feature activation+0.000
PDF
Token PDF
Feature activation+0.000
s
Tokens
Feature activation+0.420
,
Token ,
Feature activation+1.647
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
this
Token this
Feature activation+0.000
handsome
Token handsome
Feature activation+0.000
gent
Token gent
Feature activation+0.000

INTERVAL 0.815 - 1.629
CONTAINS 0.029%

my
Token my
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
kids
Token kids
Feature activation+0.000
.
Token.
Feature activation+1.108
People
Token People
Feature activation+0.000
sent
Token sent
Feature activation+0.000
me
Token me
Feature activation+0.000
death
Token death
Feature activation+0.000
threats
Token threats
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
60
Token60
Feature activation+0.000
s
Tokens
Feature activation+0.084
.
Token.
Feature activation+0.773
At
Token At
Feature activation+0.824
my
Token my
Feature activation+0.000
al
Token al
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
mater
Token mater
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.000
responds
Token responds
Feature activation+0.000
appropriately
Token appropriately
Feature activation+0.044
.
Token.
Feature activation+0.643
For
Token For
Feature activation+1.153
example
Token example
Feature activation+0.000
my
Token my
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
respond
Token respond
Feature activation+0.000
to
Token to
Feature activation+0.000
perennial
Token perennial
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
northern
Token northern
Feature activation+0.000
landscape
Token landscape
Feature activation+0.000
.
Token.
Feature activation+0.853
Some
Token Some
Feature activation+0.000
are
Token are
Feature activation+0.000
actually
Token actually
Feature activation+0.000
founded
Token founded
Feature activation+0.000
in
Token in
Feature activation+0.000
's
Token's
Feature activation+0.000
found
Token found
Feature activation+0.000
itself
Token itself
Feature activation+0.000
in
Token in
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+1.071
and
Token and
Feature activation+0.447
a
Token a
Feature activation+0.575
few
Token few
Feature activation+0.000
minor
Token minor
Feature activation+0.000
forces
Token forces
Feature activation+0.000

INTERVAL 0.000 - 0.815
CONTAINS 99.942%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
health
Token health
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
moral
Token moral
Feature activation+0.000
and
Token and
Feature activation+0.000
just
Token just
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
drove
Token drove
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
motel
Token motel
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
chest
Token chest
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
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
attackers
Token attackers
Feature activation+0.000
grabbed
Token grabbed
Feature activation+0.000
a
Token a
Feature activation+0.000
victim
Token victim
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
morning
Token morning
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
body
Token body
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
were
Token were
Feature activation+0.000
first
Token first
Feature activation+0.000
imagined
Token imagined
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
also
Token also
Feature activation+0.000
been
Token been
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 H9.7: (feature 9233)

TOP ACTIVATIONS
MAX = 4.409

(
Token (
Feature activation+0.000
13
Token13
Feature activation+0.000
-
Token-
Feature activation+0.375
2
Token2
Feature activation+0.000
MMA
Token MMA
Feature activation+0.747
,
Token,
Feature activation+4.409
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
)
Token)
Feature activation+0.000
Native
Token Native
Feature activation+0.000
Hawaiian
Token Hawaiian
Feature activation+0.671
/
Token/
Feature activation+0.000
Pacific
TokenPacific
Feature activation+0.000
Island
Token Island
Feature activation+0.000
er
Tokener
Feature activation+3.819
(
Token (
Feature activation+3.422
18
Token18
Feature activation+0.000
%),
Token%),
Feature activation+0.000
and
Token and
Feature activation+0.000
white
Token white
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
from
Token from
Feature activation+0.000
11
Token 11
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
to
Token to
Feature activation+3.758
5
Token 5
Feature activation+0.033
in
Token in
Feature activation+0.000
2025
Token 2025
Feature activation+0.000
as
Token as
Feature activation+0.000
Kh
Token Kh
Feature activation+0.000
well
Token well
Feature activation+0.000
,
Token,
Feature activation+0.000
averaging
Token averaging
Feature activation+0.000
16
Token 16
Feature activation+0.000
points
Token points
Feature activation+0.000
,
Token,
Feature activation+3.457
three
Token three
Feature activation+0.000
rebounds
Token rebounds
Feature activation+0.378
,
Token,
Feature activation+1.621
and
Token and
Feature activation+1.378
two
Token two
Feature activation+0.000
Hawaiian
Token Hawaiian
Feature activation+0.671
/
Token/
Feature activation+0.000
Pacific
TokenPacific
Feature activation+0.000
Island
Token Island
Feature activation+0.000
er
Tokener
Feature activation+3.819
(
Token (
Feature activation+3.422
18
Token18
Feature activation+0.000
%),
Token%),
Feature activation+0.000
and
Token and
Feature activation+0.000
white
Token white
Feature activation+0.000
and
Token and
Feature activation+0.000
(
Token (
Feature activation+0.000
16
Token16
Feature activation+0.967
-
Token-
Feature activation+2.118
5
Token5
Feature activation+0.000
MMA
Token MMA
Feature activation+0.791
,
Token,
Feature activation+3.417
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.472
0
Token0
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
)
Token)
Feature activation+0.000
said
Token said
Feature activation+0.107
of
Token of
Feature activation+2.305
those
Token those
Feature activation+0.747
16
Token 16
Feature activation+0.196
samples
Token samples
Feature activation+0.285
,
Token,
Feature activation+3.262
seven
Token seven
Feature activation+0.463
were
Token were
Feature activation+0.000
problematic
Token problematic
Feature activation+0.000
having
Token having
Feature activation+0.056
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
16
Token 16
Feature activation+0.000
loans
Token loans
Feature activation+0.000
he
Token he
Feature activation+0.000
reported
Token reported
Feature activation+0.000
,
Token,
Feature activation+3.115
five
Token five
Feature activation+0.000
were
Token were
Feature activation+0.000
worth
Token worth
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
father
Token father
Feature activation+0.000
of
Token of
Feature activation+0.000
16
Token 16
Feature activation+0.000
children
Token children
Feature activation+0.000
,
Token,
Feature activation+3.084
five
Token five
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
are
Token are
Feature activation+0.000
under
Token under
Feature activation+0.000
points
Token points
Feature activation+0.045
in
Token in
Feature activation+0.282
9
Token 9
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.467
including
Token including
Feature activation+3.077
a
Token a
Feature activation+0.164
goal
Token goal
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
assist
Token assist
Feature activation+0.000
vote
Tokenvote
Feature activation+0.000
period
Token period
Feature activation+0.000
in
Token in
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
to
Token to
Feature activation+1.040
only
Token only
Feature activation+3.028
one
Token one
Feature activation+0.140
location
Token location
Feature activation+0.000
open
Token open
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
bl
Tokenbl
Feature activation+0.000
ocked
Tokenocked
Feature activation+0.000
the
Token the
Feature activation+0.000
hosts
Token hosts
Feature activation+0.497
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+2.997
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000
Other
Token Other
Feature activation+0.000
than
Token than
Feature activation+0.000
serving
Token serving
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+1.089
Of
Token Of
Feature activation+0.258
those
Token those
Feature activation+0.000
players
Token players
Feature activation+0.882
,
Token,
Feature activation+2.952
seven
Token seven
Feature activation+0.000
never
Token never
Feature activation+0.000
returned
Token returned
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
from
Token from
Feature activation+0.000
10
Token 10
Feature activation+0.000
%
Token%
Feature activation+0.000
to
Token to
Feature activation+2.888
8
Token 8
Feature activation+0.000
%
Token%
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
July
Token July
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
games
Token games
Feature activation+0.000
to
Token to
Feature activation+0.000
Noble
Token Noble
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.828
17
Token 17
Feature activation+0.000
.
Token.
Feature activation+0.000
Bro
Token Bro
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
Atlanta
Token Atlanta
Feature activation+0.000
Hawks
Token Hawks
Feature activation+0.000
(
Token (
Feature activation+0.000
21
Token21
Feature activation+0.000
points
Token points
Feature activation+0.000
,
Token,
Feature activation+2.732
13
Token 13
Feature activation+0.179
rebounds
Token rebounds
Feature activation+0.211
,
Token,
Feature activation+1.633
3
Token 3
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Sel
Token Sel
Feature activation+0.000
inger
Tokeninger
Feature activation+2.628
and
Token and
Feature activation+1.705
12
Token 12
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
Hawaiian
Token Hawaiian
Feature activation+0.000
/
Token/
Feature activation+0.000
Pacific
TokenPacific
Feature activation+0.000
Island
Token Island
Feature activation+0.000
er
Tokener
Feature activation+0.727
(
Token (
Feature activation+2.570
12
Token12
Feature activation+0.000
%).
Token%).
Feature activation+0.000
Interestingly
Token Interestingly
Feature activation+0.000
,
Token,
Feature activation+0.000
Hawaii
Token Hawaii
Feature activation+0.000
for
Token for
Feature activation+0.000
three
Token three
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.439
with
Token with
Feature activation+0.720
another
Token another
Feature activation+2.542
four
Token four
Feature activation+0.000
that
Token that
Feature activation+0.000
gave
Token gave
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
preseason
Token preseason
Feature activation+0.000
with
Token with
Feature activation+0.000
14
Token 14
Feature activation+0.000
assists
Token assists
Feature activation+0.000
and
Token and
Feature activation+0.512
just
Token just
Feature activation+2.537
one
Token one
Feature activation+0.000
turnover
Token turnover
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
stat
Token stat
Feature activation+0.000

Top DFA by src position
MAX = 5.224

contender
Token contender
Feature activation-0.004
Top resid features:
Luke
Token Luke
Feature activation-0.003
Top resid features:
Rock
Token Rock
Feature activation+0.000
Top resid features:
hold
Tokenhold
Feature activation+0.001
Top resid features:
(
Token (
Feature activation-0.009
Top resid features:
13
Token13
Feature activation+5.224
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
2
Token2
Feature activation-0.016
Top resid features:
MMA
Token MMA
Feature activation-0.052
Top resid features:
,
Token,
Feature activation-0.054
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.017
Top resid features:
white
Token white
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
Asian
Token Asian
Feature activation-0.009
Top resid features:
(
Token (
Feature activation+0.048
Top resid features:
18
Token18
Feature activation+4.298
Top resid features:
%),
Token%),
Feature activation+0.164
Top resid features:
Asian
Token Asian
Feature activation-0.023
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
Native
Token Native
Feature activation-0.005
Top resid features:
Hawaiian
Token Hawaiian
Feature activation+0.012
Top resid features:
would
Token would
Feature activation+0.021
Top resid features:
be
Token be
Feature activation+0.015
Top resid features:
gradually
Token gradually
Feature activation+0.002
Top resid features:
reduced
Token reduced
Feature activation+0.039
Top resid features:
from
Token from
Feature activation-0.007
Top resid features:
11
Token 11
Feature activation+4.686
Top resid features:
this
Token this
Feature activation+0.020
Top resid features:
year
Token year
Feature activation+0.188
Top resid features:
to
Token to
Feature activation-0.607
Top resid features:
5
Token 5
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.011
Top resid features:
performed
Token performed
Feature activation+0.014
Top resid features:
well
Token well
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
averaging
Token averaging
Feature activation+0.023
Top resid features:
16
Token 16
Feature activation+3.746
Top resid features:
points
Token points
Feature activation+0.146
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
three
Token three
Feature activation+0.000
Top resid features:
rebounds
Token rebounds
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
white
Token white
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
Asian
Token Asian
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.020
Top resid features:
18
Token18
Feature activation+3.875
Top resid features:
%),
Token%),
Feature activation+0.029
Top resid features:
Asian
Token Asian
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
Native
Token Native
Feature activation-0.001
Top resid features:
Hawaiian
Token Hawaiian
Feature activation+0.006
Top resid features:
craft
Token craft
Feature activation+0.001
Top resid features:
y
Tokeny
Feature activation+0.000
Top resid features:
Alexis
Token Alexis
Feature activation-0.002
Top resid features:
Davis
Token Davis
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.002
Top resid features:
16
Token16
Feature activation+4.146
Top resid features:
-
Token-
Feature activation+0.032
Top resid features:
5
Token5
Feature activation-0.001
Top resid features:
MMA
Token MMA
Feature activation-0.040
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
Instrument
Token Instrument
Feature activation+0.001
Top resid features:
al
Tokenal
Feature activation+0.000
Top resid features:
Laboratories
Token Laboratories
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
checked
Token checked
Feature activation+0.003
Top resid features:
16
Token 16
Feature activation+2.485
Top resid features:
blood
Token blood
Feature activation+0.029
Top resid features:
samples
Token samples
Feature activation+0.032
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
CBI
Token CBI
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Of
TokenOf
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
16
Token 16
Feature activation+3.654
Top resid features:
loans
Token loans
Feature activation+0.033
Top resid features:
he
Token he
Feature activation+0.015
Top resid features:
reported
Token reported
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
He
TokenHe
Feature activation+0.007
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
father
Token father
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
16
Token 16
Feature activation+3.407
Top resid features:
children
Token children
Feature activation+0.048
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
whom
Token whom
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
exclusive
Token exclusive
Feature activation-0.003
Top resid features:
club
Token club
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
scoring
Token scoring
Feature activation+0.015
Top resid features:
11
Token 11
Feature activation+2.737
Top resid features:
points
Token points
Feature activation+0.143
Top resid features:
in
Token in
Feature activation+0.032
Top resid features:
9
Token 9
Feature activation+0.481
Top resid features:
games
Token games
Feature activation+0.150
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
ford
Tokenford
Feature activation+0.002
Top resid features:
County
Token County
Feature activation+0.009
Top resid features:
alone
Token alone
Feature activation+0.008
Top resid features:
went
Token went
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.021
Top resid features:
16
Token 16
Feature activation+3.504
Top resid features:
polling
Token polling
Feature activation+0.015
Top resid features:
sites
Token sites
Feature activation+0.020
Top resid features:
available
Token available
Feature activation-0.008
Top resid features:
for
Token for
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
bl
Tokenbl
Feature activation-0.017
Top resid features:
ocked
Tokenocked
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
hosts
Token hosts
Feature activation+0.087
Top resid features:
12
Token 12
Feature activation+3.406
Top resid features:
-
Token-
Feature activation+0.063
Top resid features:
3
Token3
Feature activation+0.000
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:
other
Token other
Feature activation-0.004
Top resid features:
collaborators
Token collaborators
Feature activation-0.009
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
they
Token they
Feature activation-0.003
Top resid features:
examined
Token examined
Feature activation+0.001
Top resid features:
18
Token 18
Feature activation+3.450
Top resid features:
players
Token players
Feature activation+0.027
Top resid features:
who
Token who
Feature activation+0.005
Top resid features:
'd
Token'd
Feature activation+0.009
Top resid features:
sustained
Token sustained
Feature activation-0.011
Top resid features:
rupt
Token rupt
Feature activation+0.003
Top resid features:
sales
Token sales
Feature activation+0.010
Top resid features:
tax
Token tax
Feature activation-0.152
Top resid features:
on
Token on
Feature activation+0.037
Top resid features:
marijuana
Token marijuana
Feature activation+0.010
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
10
Token 10
Feature activation+4.305
Top resid features:
%
Token%
Feature activation+0.081
Top resid features:
to
Token to
Feature activation-0.791
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
beginning
Token beginning
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.009
Top resid features:
Nick
Token Nick
Feature activation+0.002
Top resid features:
Noble
Token Noble
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
starting
Token starting
Feature activation+0.005
Top resid features:
13
Token 13
Feature activation+3.218
Top resid features:
games
Token games
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.086
Top resid features:
Noble
Token Noble
Feature activation+0.067
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
against
Token against
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Atlanta
Token Atlanta
Feature activation-0.001
Top resid features:
Hawks
Token Hawks
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
21
Token21
Feature activation+2.885
Top resid features:
points
Token points
Feature activation+0.145
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
13
Token 13
Feature activation+0.000
Top resid features:
rebounds
Token rebounds
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
compared
Token compared
Feature activation+0.006
Top resid features:
with
Token with
Feature activation+0.013
Top resid features:
17
Token 17
Feature activation+2.738
Top resid features:
per
Token per
Feature activation+0.001
Top resid features:
cent
Token cent
Feature activation-0.001
Top resid features:
supporting
Token supporting
Feature activation+0.139
Top resid features:
NDP
Token NDP
Feature activation+0.022
Top resid features:
Leader
Token Leader
Feature activation+0.018
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
white
Token white
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
Asian
Token Asian
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.020
Top resid features:
18
Token18
Feature activation+2.038
Top resid features:
%),
Token%),
Feature activation+0.015
Top resid features:
Asian
Token Asian
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Native
Token Native
Feature activation+0.001
Top resid features:
Hawaiian
Token Hawaiian
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
unfortunate
Token unfortunate
Feature activation-0.009
Top resid features:
record
Token record
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
playing
Token playing
Feature activation+0.009
Top resid features:
14
Token 14
Feature activation+3.000
Top resid features:
NRL
Token NRL
Feature activation+0.015
Top resid features:
games
Token games
Feature activation+0.123
Top resid features:
for
Token for
Feature activation-0.022
Top resid features:
three
Token three
Feature activation-0.041
Top resid features:
clubs
Token clubs
Feature activation+0.041
Top resid features:
facilit
Token facilit
Feature activation+0.002
Top resid features:
ator
Tokenator
Feature activation+0.004
Top resid features:
this
Token this
Feature activation-0.000
Top resid features:
preseason
Token preseason
Feature activation+0.010
Top resid features:
with
Token with
Feature activation+0.026
Top resid features:
14
Token 14
Feature activation+2.744
Top resid features:
assists
Token assists
Feature activation+0.102
Top resid features:
and
Token and
Feature activation+0.124
Top resid features:
just
Token just
Feature activation+0.006
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
turnover
Token turnover
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.04

Head 3: 0.04

Head 4: 0.03

Head 5: 0.06

Head 6: 0.03

Head 7: 0.55

Head 8: 0.03

Head 9: 0.06

Head 10: 0.04

Head 11: 0.04

Positive logits

three2.96

seven2.93

five2.90

nine2.78

Nine2.65

Nine2.62

four2.62

eight2.58

82.54

iera2.53

52.52

isodes2.50

six2.49

Five2.49

32.49

132.47

42.41

Wag2.41

nine2.41

Seven2.40

Negative logits

actionDate-2.89

nah-2.85

dyl-2.59

heit-2.58

ppo-2.46

)?-2.45

tnc-2.45

-2.40

ROR-2.38

ILA-2.38

igmat-2.36

nec-2.30

UTH-2.30

ITNESS-2.27

)}-2.24

-2.24

ADRA-2.22

||-2.21

mits-2.21

deny-2.20

INTERVAL 3.968 - 4.409
CONTAINS 0.000%

(
Token (
Feature activation+0.000
13
Token13
Feature activation+0.000
-
Token-
Feature activation+0.375
2
Token2
Feature activation+0.000
MMA
Token MMA
Feature activation+0.747
,
Token,
Feature activation+4.409
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
)
Token)
Feature activation+0.000

INTERVAL 3.527 - 3.968
CONTAINS 0.000%

reduced
Token reduced
Feature activation+0.000
from
Token from
Feature activation+0.000
11
Token 11
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
to
Token to
Feature activation+3.758
5
Token 5
Feature activation+0.033
in
Token in
Feature activation+0.000
2025
Token 2025
Feature activation+0.000
as
Token as
Feature activation+0.000
Kh
Token Kh
Feature activation+0.000
Native
Token Native
Feature activation+0.000
Hawaiian
Token Hawaiian
Feature activation+0.671
/
Token/
Feature activation+0.000
Pacific
TokenPacific
Feature activation+0.000
Island
Token Island
Feature activation+0.000
er
Tokener
Feature activation+3.819
(
Token (
Feature activation+3.422
18
Token18
Feature activation+0.000
%),
Token%),
Feature activation+0.000
and
Token and
Feature activation+0.000
white
Token white
Feature activation+0.000

INTERVAL 3.086 - 3.527
CONTAINS 0.001%

well
Token well
Feature activation+0.000
,
Token,
Feature activation+0.000
averaging
Token averaging
Feature activation+0.000
16
Token 16
Feature activation+0.000
points
Token points
Feature activation+0.000
,
Token,
Feature activation+3.457
three
Token three
Feature activation+0.000
rebounds
Token rebounds
Feature activation+0.378
,
Token,
Feature activation+1.621
and
Token and
Feature activation+1.378
two
Token two
Feature activation+0.000
the
Token the
Feature activation+0.000
16
Token 16
Feature activation+0.000
loans
Token loans
Feature activation+0.000
he
Token he
Feature activation+0.000
reported
Token reported
Feature activation+0.000
,
Token,
Feature activation+3.115
five
Token five
Feature activation+0.000
were
Token were
Feature activation+0.000
worth
Token worth
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
(
Token (
Feature activation+0.000
16
Token16
Feature activation+0.967
-
Token-
Feature activation+2.118
5
Token5
Feature activation+0.000
MMA
Token MMA
Feature activation+0.791
,
Token,
Feature activation+3.417
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.472
0
Token0
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
)
Token)
Feature activation+0.000
said
Token said
Feature activation+0.107
of
Token of
Feature activation+2.305
those
Token those
Feature activation+0.747
16
Token 16
Feature activation+0.196
samples
Token samples
Feature activation+0.285
,
Token,
Feature activation+3.262
seven
Token seven
Feature activation+0.463
were
Token were
Feature activation+0.000
problematic
Token problematic
Feature activation+0.000
having
Token having
Feature activation+0.056
at
Token at
Feature activation+0.000
Hawaiian
Token Hawaiian
Feature activation+0.671
/
Token/
Feature activation+0.000
Pacific
TokenPacific
Feature activation+0.000
Island
Token Island
Feature activation+0.000
er
Tokener
Feature activation+3.819
(
Token (
Feature activation+3.422
18
Token18
Feature activation+0.000
%),
Token%),
Feature activation+0.000
and
Token and
Feature activation+0.000
white
Token white
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.645 - 3.086
CONTAINS 0.001%

the
Token the
Feature activation+0.000
father
Token father
Feature activation+0.000
of
Token of
Feature activation+0.000
16
Token 16
Feature activation+0.000
children
Token children
Feature activation+0.000
,
Token,
Feature activation+3.084
five
Token five
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
are
Token are
Feature activation+0.000
under
Token under
Feature activation+0.000
points
Token points
Feature activation+0.045
in
Token in
Feature activation+0.282
9
Token 9
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.467
including
Token including
Feature activation+3.077
a
Token a
Feature activation+0.164
goal
Token goal
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
assist
Token assist
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
from
Token from
Feature activation+0.000
10
Token 10
Feature activation+0.000
%
Token%
Feature activation+0.000
to
Token to
Feature activation+2.888
8
Token 8
Feature activation+0.000
%
Token%
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
July
Token July
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
vote
Tokenvote
Feature activation+0.000
period
Token period
Feature activation+0.000
in
Token in
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
to
Token to
Feature activation+1.040
only
Token only
Feature activation+3.028
one
Token one
Feature activation+0.140
location
Token location
Feature activation+0.000
open
Token open
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Atlanta
Token Atlanta
Feature activation+0.000
Hawks
Token Hawks
Feature activation+0.000
(
Token (
Feature activation+0.000
21
Token21
Feature activation+0.000
points
Token points
Feature activation+0.000
,
Token,
Feature activation+2.732
13
Token 13
Feature activation+0.179
rebounds
Token rebounds
Feature activation+0.211
,
Token,
Feature activation+1.633
3
Token 3
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000

INTERVAL 2.204 - 2.645
CONTAINS 0.002%

preseason
Token preseason
Feature activation+0.000
with
Token with
Feature activation+0.000
14
Token 14
Feature activation+0.000
assists
Token assists
Feature activation+0.000
and
Token and
Feature activation+0.512
just
Token just
Feature activation+2.537
one
Token one
Feature activation+0.000
turnover
Token turnover
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
stat
Token stat
Feature activation+0.000
and
Token and
Feature activation+0.000
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.307
In
Token In
Feature activation+2.015
a
Token a
Feature activation+0.202
further
Token further
Feature activation+2.264
55
Token 55
Feature activation+0.000
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
homosexuals
Token homosexuals
Feature activation+0.000
can
Token can
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Sel
Token Sel
Feature activation+0.000
inger
Tokeninger
Feature activation+2.628
and
Token and
Feature activation+1.705
12
Token 12
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
fell
Token fell
Feature activation+0.000
behind
Token behind
Feature activation+0.000
17
Token 17
Feature activation+0.000
-
Token-
Feature activation+2.305
0
Token0
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
than
Token than
Feature activation+0.000
half
Token half
Feature activation+0.000
from
Token from
Feature activation+0.000
nine
Token nine
Feature activation+0.000
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+2.465
four
Token four
Feature activation+0.000
by
Token by
Feature activation+0.000
connecting
Token connecting
Feature activation+0.000
the
Token the
Feature activation+0.000
farms
Token farms
Feature activation+0.000

INTERVAL 1.764 - 2.204
CONTAINS 0.004%

the
Token the
Feature activation+0.000
oil
Token oil
Feature activation+0.000
services
Token services
Feature activation+0.000
sector
Token sector
Feature activation+0.000
and
Token and
Feature activation+0.510
another
Token another
Feature activation+2.013
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
exploration
Token exploration
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
airport
Token airport
Feature activation+0.000
but
Token but
Feature activation+0.000
have
Token have
Feature activation+0.000
released
Token released
Feature activation+1.961
few
Token few
Feature activation+0.000
other
Token other
Feature activation+0.000
details
Token details
Feature activation+0.000
.
Token.
Feature activation+0.536
An
Token An
Feature activation+0.064
10
Token 10
Feature activation+0.000
scripts
Token scripts
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
field
Token field
Feature activation+0.000
,
Token,
Feature activation+1.847
the
Token the
Feature activation+0.000
highest
Token highest
Feature activation+0.000
rank
Token rank
Feature activation+0.000
among
Token among
Feature activation+0.000
them
Token them
Feature activation+0.328
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
âĪĴ
TokenâĪĴ
Feature activation+2.030
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
)
Token)
Feature activation+0.000
âĪĴ
Token âĪĴ
Feature activation+1.028
a
Token a
Feature activation+0.000
final
Token final
Feature activation+0.000
order
Token order
Feature activation+0.000
of
Token of
Feature activation+0.000
removal
Token removal
Feature activation+0.000
,
Token,
Feature activation+1.866
one
Token one
Feature activation+0.673
was
Token was
Feature activation+0.000
granted
Token granted
Feature activation+0.000
voluntary
Token voluntary
Feature activation+0.000
departure
Token departure
Feature activation+0.000

INTERVAL 1.323 - 1.764
CONTAINS 0.006%

45
Token45
Feature activation+0.000
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
,
Token,
Feature activation+1.060
and
Token and
Feature activation+1.486
19
Token 19
Feature activation+0.000
.
Token.
Feature activation+0.000
05
Token05
Feature activation+0.000
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
averaged
Token averaged
Feature activation+0.000
7
Token 7
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
points
Token points
Feature activation+0.000
on
Token on
Feature activation+1.635
47
Token 47
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
percent
Token percent
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
(
Token (
Feature activation+0.000
9
Token9
Feature activation+0.000
-
Token-
Feature activation+0.000
0
Token0
Feature activation+0.000
MMA
Token MMA
Feature activation+0.000
,
Token,
Feature activation+1.466
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
0
Token0
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
),
Token),
Feature activation+0.000
51
Token 51
Feature activation+0.000
years
Token years
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
25
Token 25
Feature activation+0.350
(
Token (
Feature activation+1.714
8
Token8
Feature activation+0.000
%)
Token%)
Feature activation+0.000
were
Token were
Feature activation+0.000
children
Token children
Feature activation+0.000
younger
Token younger
Feature activation+0.000
Mono
Token Mono
Feature activation+0.000
B
TokenB
Feature activation+0.000
variant
Token variant
Feature activation+0.733
which
Token which
Feature activation+0.000
runs
Token runs
Feature activation+0.268
at
Token at
Feature activation+1.326
20
Token 20
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
an
Token an
Feature activation+0.000
additional
Token additional
Feature activation+0.000

INTERVAL 0.882 - 1.323
CONTAINS 0.011%

.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
kg
Token kg
Feature activation+0.000
of
Token of
Feature activation+0.000
pork
Token pork
Feature activation+0.000
,
Token,
Feature activation+1.261
13
Token 13
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
kg
Token kg
Feature activation+0.000
of
Token of
Feature activation+0.000
craft
Token craft
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Alexis
Token Alexis
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
(
Token (
Feature activation+0.000
16
Token16
Feature activation+0.967
-
Token-
Feature activation+2.118
5
Token5
Feature activation+0.000
MMA
Token MMA
Feature activation+0.791
,
Token,
Feature activation+3.417
3
Token 3
Feature activation+0.000
the
Token the
Feature activation+0.000
Broncos
Token Broncos
Feature activation+0.000
tied
Token tied
Feature activation+0.000
the
Token the
Feature activation+0.000
Colts
Token Colts
Feature activation+0.000
at
Token at
Feature activation+0.887
17
Token 17
Feature activation+0.000
and
Token and
Feature activation+0.000
24
Token 24
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
logged
Token logged
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
.
Token.
Feature activation+0.000
Around
Token Around
Feature activation+0.999
35
Token 35
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
ash
Token ash
Feature activation+0.000
âĪĴ
TokenâĪĴ
Feature activation+2.030
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
)
Token)
Feature activation+0.000
âĪĴ
Token âĪĴ
Feature activation+1.028
8
Token8
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.441 - 0.882
CONTAINS 0.022%

fell
Token fell
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Saints
Token Saints
Feature activation+0.000
30
Token 30
Feature activation+0.000
-
Token-
Feature activation+0.564
10
Token10
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
I
TokenI
Feature activation+0.000
fear
Token fear
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
for
Token for
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
seasons
Token seasons
Feature activation+0.016
.
Token.
Feature activation+0.814
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
;
Token;
Feature activation+0.375
counting
Token counting
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
ones
Token ones
Feature activation+0.477
,
Token,
Feature activation+0.541
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
were
Token were
Feature activation+0.000
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
Mold
Token Mold
Feature activation+0.000
ova
Tokenova
Feature activation+0.000
,
Token,
Feature activation+0.757
30
Token 30
Feature activation+0.000
.
Token.
Feature activation+0.000
95
Token95
Feature activation+0.000
%
Token%
Feature activation+0.000
in
Token in
Feature activation+0.000
disease
Token disease
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
systems
Token systems
Feature activation+0.000
.
Token.
Feature activation+0.419
He
Token He
Feature activation+0.000
said
Token said
Feature activation+0.475
international
Token international
Feature activation+0.000
airlines
Token airlines
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
allow
Token allow
Feature activation+0.000

INTERVAL 0.000 - 0.441
CONTAINS 99.954%

based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
reason
Token reason
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
r
Token r
Feature activation+0.000
ationally
Tokenationally
Feature activation+0.000
claim
Token claim
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
blog
Token blog
Feature activation+0.000
Mud
Token Mud
Feature activation+0.000
fl
Tokenfl
Feature activation+0.000
ats
Tokenats
Feature activation+0.000
and
Token and
Feature activation+0.000
Slate
Token Slate
Feature activation+0.000
reporter
Token reporter
Feature activation+0.000
Dave
Token Dave
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
agg
Tokenagg
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
next
Token next
Feature activation+0.000
useful
Token useful
Feature activation+0.000
concept
Token concept
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
archs
Tokenarchs
Feature activation+0.000
moving
Token moving
Feature activation+0.000
to
Token to
Feature activation+0.000
Ontario
Token Ontario
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
need
Token need
Feature activation+0.000
are
Token are
Feature activation+0.000
clean
Token clean
Feature activation+0.000
energy
Token energy
Feature activation+0.000
investments
Token investments
Feature activation+0.000
,
Token,
Feature activation+0.000
properly
Token properly
Feature activation+0.000
inflated
Token inflated
Feature activation+0.000
tires
Token tires
Feature activation+0.000
,
Token,
Feature activation+0.000
Chinese
Token Chinese
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 H9.7: (feature 1509)

TOP ACTIVATIONS
MAX = 5.696

to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
two
Token two
Feature activation+0.000
vertical
Token vertical
Feature activation+0.000
trials
Token trials
Feature activation+0.000
,
Token,
Feature activation+5.696
one
Token one
Feature activation+0.253
of
Token of
Feature activation+0.505
their
Token their
Feature activation+0.160
Is
Token Is
Feature activation+0.000
se
Tokense
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
girls
Token girls
Feature activation+0.000
,
Token,
Feature activation+5.620
one
Token one
Feature activation+0.000
13
Token 13
Feature activation+0.000
and
Token and
Feature activation+1.217
one
Token one
Feature activation+0.000
14
Token 14
Feature activation+0.000
sailed
Token sailed
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
.
Token.
Feature activation+5.569
The
Token The
Feature activation+4.573
measures
Token measures
Feature activation+0.688
now
Token now
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
national
Token national
Feature activation+0.000
identity
Token identity
Feature activation+0.000
stand
Token stand
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+5.308
One
Token One
Feature activation+0.000
is
Token is
Feature activation+0.000
our
Token our
Feature activation+0.000
Anglo
Token Anglo
Feature activation+0.000
-
Token-
Feature activation+0.000
posts
Token posts
Feature activation+0.000
on
Token on
Feature activation+0.317
my
Token my
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
feed
Token feed
Feature activation+1.173
.
Token.
Feature activation+5.299
One
Token One
Feature activation+0.694
stating
Token stating
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
judge
Token judge
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
not
Token not
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
letters
Token letters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+5.220
from
Token from
Feature activation+0.180
William
Token William
Feature activation+0.000
Harris
Token Harris
Feature activation+0.000
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
two
Token two
Feature activation+0.000
pieces
Token pieces
Feature activation+0.000
of
Token of
Feature activation+0.000
trade
Token trade
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
,
Token,
Feature activation+5.056
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
approved
Token approved
Feature activation+1.562
the
Token the
Feature activation+2.231
process
Token process
Feature activation+0.024
,
Token,
Feature activation+0.869
the
Token the
Feature activation+0.950
EC
Token EC
Feature activation+0.000
has
Token has
Feature activation+0.228
rejected
Token rejected
Feature activation+5.038
the
Token the
Feature activation+3.774
proposals
Token proposals
Feature activation+0.891
and
Token and
Feature activation+0.000
commenced
Token commenced
Feature activation+0.000
official
Token official
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
major
Token major
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
.
Token.
Feature activation+4.632
In
Token In
Feature activation+4.925
one
Token one
Feature activation+0.000
case
Token case
Feature activation+0.135
,
Token,
Feature activation+0.085
a
Token a
Feature activation+0.000
teen
Token teen
Feature activation+0.000
them
Token them
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
important
Token important
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
.
Token.
Feature activation+4.899
One
Token One
Feature activation+0.000
,
Token,
Feature activation+0.000
Muscle
Token Muscle
Feature activation+0.000
Soldier
Token Soldier
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
possible
Token possible
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
heart
Token heart
Feature activation+0.000
attack
Token attack
Feature activation+0.000
.
Token.
Feature activation+4.725
(
Token (
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
11
Token11
Feature activation+0.000
:
Token:
Feature activation+0.000
Getty
Token Getty
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
programmers
Token programmers
Feature activation+0.000
,
Token,
Feature activation+4.717
one
Token one
Feature activation+0.101
systems
Token systems
Feature activation+0.000
specialist
Token specialist
Feature activation+0.194
,
Token,
Feature activation+1.097
a
Token a
Feature activation+0.846
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
open
Token open
Feature activation+0.000
.
Token.
Feature activation+2.422
The
Token The
Feature activation+4.683
other
Token other
Feature activation+1.342
was
Token was
Feature activation+0.215
closed
Token closed
Feature activation+0.053
and
Token and
Feature activation+0.793
No
Token No
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
major
Token major
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
.
Token.
Feature activation+4.632
In
Token In
Feature activation+4.925
one
Token one
Feature activation+0.000
case
Token case
Feature activation+0.135
,
Token,
Feature activation+0.085
a
Token a
Feature activation+0.000
global
Token global
Feature activation+0.000
surface
Token surface
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
observational
Token observational
Feature activation+0.000
datasets
Token datasets
Feature activation+0.000
,
Token,
Feature activation+4.607
the
Token the
Feature activation+1.190
UK
Token UK
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
.
Token.
Feature activation+5.569
The
Token The
Feature activation+4.573
measures
Token measures
Feature activation+0.688
now
Token now
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
Governor
Token Governor
Feature activation+0.000
had
Token had
Feature activation+0.000
complained
Token complained
Feature activation+0.000
about
Token about
Feature activation+0.000
two
Token two
Feature activation+0.000
officials
Token officials
Feature activation+0.000
-
Token -
Feature activation+4.482
one
Token one
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Corbyn
Token Corbyn
Feature activation+0.000
has
Token has
Feature activation+0.000
tend
Token tend
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
two
Token two
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
,
Token,
Feature activation+4.453
which
Token which
Feature activation+1.168
outline
Token outline
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
board
Token board
Feature activation+0.000
has
Token has
Feature activation+0.000
endorsed
Token endorsed
Feature activation+0.000
two
Token two
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
,
Token,
Feature activation+4.431
Paul
Token Paul
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
for
Token for
Feature activation+0.097
governor
Token governor
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.154
the
Token the
Feature activation+0.070
Web
Token Web
Feature activation+0.000
GL
TokenGL
Feature activation+0.000
technology
Token technology
Feature activation+0.000
,
Token,
Feature activation+4.407
Web
Token Web
Feature activation+0.000
GL
TokenGL
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
A
Token A
Feature activation+0.000
New
Token New
Feature activation+0.000

Top DFA by src position
MAX = 6.017

I
Token I
Feature activation+0.026
Top resid features:
have
Token have
Feature activation+0.030
Top resid features:
decided
Token decided
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
have
Token have
Feature activation+0.024
Top resid features:
two
Token two
Feature activation+5.773
Top resid features:
vertical
Token vertical
Feature activation+0.079
Top resid features:
trials
Token trials
Feature activation+0.199
Top resid features:
,
Token,
Feature activation+0.057
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
v
Tokenv
Feature activation-0.000
Top resid features:
én
Tokenén
Feature activation-0.000
Top resid features:
ements
Tokenements
Feature activation-0.000
Top resid features:
!
Token!
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.002
Top resid features:
Two
TokenTwo
Feature activation+6.017
Top resid features:
Florida
Token Florida
Feature activation+0.041
Top resid features:
girls
Token girls
Feature activation+0.231
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
13
Token 13
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
development
Token development
Feature activation+0.000
Top resid features:
!
Token!
Feature activation-0.000
Top resid features:
:)
Token :)
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.044
Top resid features:
Two
TokenTwo
Feature activation+5.715
Top resid features:
new
Token new
Feature activation+0.100
Top resid features:
bills
Token bills
Feature activation+0.095
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
increase
Token increase
Feature activation+0.024
Top resid features:
New
Token New
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.005
Top resid features:
2004
Token2004
Feature activation+0.001
Top resid features:
),
Token),
Feature activation+0.022
Top resid features:
two
Token two
Feature activation+5.831
Top resid features:
components
Token components
Feature activation+0.169
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
that
Token that
Feature activation-0.006
Top resid features:
national
Token national
Feature activation-0.004
Top resid features:
identity
Token identity
Feature activation-0.010
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
article
Token article
Feature activation+0.005
Top resid features:
I
Token I
Feature activation+0.026
Top resid features:
just
Token just
Feature activation+0.008
Top resid features:
saw
Token saw
Feature activation+0.005
Top resid features:
two
Token two
Feature activation+5.525
Top resid features:
posts
Token posts
Feature activation+0.111
Top resid features:
on
Token on
Feature activation+0.014
Top resid features:
my
Token my
Feature activation-0.006
Top resid features:
Facebook
Token Facebook
Feature activation+0.011
Top resid features:
feed
Token feed
Feature activation+0.059
Top resid features:
Vietnam
Token Vietnam
Feature activation-0.002
Top resid features:
War
Token War
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Two
TokenTwo
Feature activation+5.026
Top resid features:
not
Token not
Feature activation-0.004
Top resid features:
ar
Tokenar
Feature activation+0.014
Top resid features:
ized
Tokenized
Feature activation-0.006
Top resid features:
letters
Token letters
Feature activation+0.107
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.059
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
Friday
Token Friday
Feature activation+0.003
Top resid features:
tried
Token tried
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
pass
Token pass
Feature activation+0.027
Top resid features:
two
Token two
Feature activation+5.299
Top resid features:
pieces
Token pieces
Feature activation+0.074
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
trade
Token trade
Feature activation+0.005
Top resid features:
legislation
Token legislation
Feature activation+0.144
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
Def
Token Def
Feature activation+0.036
Top resid features:
ra
Tokenra
Feature activation+0.009
Top resid features:
has
Token has
Feature activation-0.009
Top resid features:
tend
Token tend
Feature activation-0.009
Top resid features:
ered
Tokenered
Feature activation-0.004
Top resid features:
two
Token two
Feature activation+5.067
Top resid features:
proposals
Token proposals
Feature activation+0.152
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
which
Token which
Feature activation+0.024
Top resid features:
outline
Token outline
Feature activation+0.001
Top resid features:
plans
Token plans
Feature activation+0.013
Top resid features:
practice
Token practice
Feature activation-0.007
Top resid features:
has
Token has
Feature activation-0.001
Top resid features:
been
Token been
Feature activation-0.001
Top resid features:
highlighted
Token highlighted
Feature activation-0.002
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
two
Token two
Feature activation+3.581
Top resid features:
recent
Token recent
Feature activation+0.088
Top resid features:
incidents
Token incidents
Feature activation+0.018
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+1.467
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
I
TokenI
Feature activation+0.138
Top resid features:
chose
Token chose
Feature activation+0.004
Top resid features:
them
Token them
Feature activation+0.044
Top resid features:
for
Token for
Feature activation+0.015
Top resid features:
two
Token two
Feature activation+4.827
Top resid features:
important
Token important
Feature activation+0.039
Top resid features:
reasons
Token reasons
Feature activation+0.369
Top resid features:
.
Token.
Feature activation+0.071
Top resid features:
One
Token One
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
resume
Token resume
Feature activation-0.012
Top resid features:
sex
Token sex
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Two
TokenTwo
Feature activation+5.083
Top resid features:
groups
Token groups
Feature activation+0.149
Top resid features:
are
Token are
Feature activation+0.022
Top resid features:
urging
Token urging
Feature activation+0.010
Top resid features:
doctors
Token doctors
Feature activation+0.032
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
webpage
Token webpage
Feature activation+0.002
Top resid features:
lists
Token lists
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
team
Token team
Feature activation+0.069
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
two
Token two
Feature activation+5.010
Top resid features:
programmers
Token programmers
Feature activation+0.176
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
systems
Token systems
Feature activation+0.000
Top resid features:
specialist
Token specialist
Feature activation+0.000
Top resid features:
complaints
Token complaints
Feature activation+0.053
Top resid features:
filed
Token filed
Feature activation+0.017
Top resid features:
against
Token against
Feature activation-0.009
Top resid features:
him
Token him
Feature activation+0.009
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.045
Top resid features:
two
Token two
Feature activation+4.599
Top resid features:
that
Token that
Feature activation+0.036
Top resid features:
are
Token are
Feature activation+0.008
Top resid features:
still
Token still
Feature activation-0.001
Top resid features:
open
Token open
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.174
Top resid features:
practice
Token practice
Feature activation-0.016
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
been
Token been
Feature activation-0.003
Top resid features:
highlighted
Token highlighted
Feature activation-0.004
Top resid features:
by
Token by
Feature activation+0.006
Top resid features:
two
Token two
Feature activation+3.495
Top resid features:
recent
Token recent
Feature activation+0.044
Top resid features:
incidents
Token incidents
Feature activation+0.027
Top resid features:
at
Token at
Feature activation-0.014
Top resid features:
two
Token two
Feature activation+1.543
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
This
TokenThis
Feature activation+0.004
Top resid features:
graph
Token graph
Feature activation+0.000
Top resid features:
depicts
Token depicts
Feature activation+0.015
Top resid features:
two
Token two
Feature activation+4.845
Top resid features:
well
Token well
Feature activation-0.001
Top resid features:
known
Token known
Feature activation+0.028
Top resid features:
global
Token global
Feature activation-0.002
Top resid features:
surface
Token surface
Feature activation-0.005
Top resid features:
temperature
Token temperature
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
development
Token development
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.001
Top resid features:
:)
Token :)
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.015
Top resid features:
Two
TokenTwo
Feature activation+4.294
Top resid features:
new
Token new
Feature activation+0.313
Top resid features:
bills
Token bills
Feature activation+0.150
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
increase
Token increase
Feature activation+0.069
Top resid features:
New
Token New
Feature activation+0.006
Top resid features:
leadership
Token leadership
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
had
Token had
Feature activation+0.006
Top resid features:
complained
Token complained
Feature activation+0.002
Top resid features:
about
Token about
Feature activation-0.008
Top resid features:
two
Token two
Feature activation+4.885
Top resid features:
officials
Token officials
Feature activation+0.148
Top resid features:
-
Token -
Feature activation+0.055
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Def
Token Def
Feature activation+0.013
Top resid features:
ra
Tokenra
Feature activation+0.014
Top resid features:
has
Token has
Feature activation-0.007
Top resid features:
tend
Token tend
Feature activation-0.008
Top resid features:
ered
Tokenered
Feature activation-0.004
Top resid features:
two
Token two
Feature activation+4.697
Top resid features:
proposals
Token proposals
Feature activation+0.242
Top resid features:
,
Token,
Feature activation+0.097
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
outline
Token outline
Feature activation+0.000
Top resid features:
plans
Token plans
Feature activation+0.000
Top resid features:
IO
TokenIO
Feature activation-0.025
Top resid features:
executive
Token executive
Feature activation-0.022
Top resid features:
board
Token board
Feature activation+0.003
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
endorsed
Token endorsed
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+4.843
Top resid features:
Democrats
Token Democrats
Feature activation+0.212
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
Paul
Token Paul
Feature activation+0.000
Top resid features:
Davis
Token Davis
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Context
Token Context
Feature activation-0.010
Top resid features:
Information
Token Information
Feature activation-0.003
Top resid features:
Security
Token Security
Feature activation-0.024
Top resid features:
published
Token published
Feature activation+0.004
Top resid features:
two
Token two
Feature activation+4.738
Top resid features:
reports
Token reports
Feature activation+0.207
Top resid features:
critical
Token critical
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
Web
Token Web
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.04

Head 3: 0.05

Head 4: 0.05

Head 5: 0.03

Head 6: 0.03

Head 7: 0.54

Head 8: 0.03

Head 9: 0.04

Head 10: 0.05

Head 11: 0.03

Positive logits

Both5.11

Both5.03

Third4.45

Neither4.45

third4.34

respectively4.32

both4.18

both4.17

Neither4.15

neither3.95

Either3.77

first3.58

third3.48

Firstly3.43

one3.41

Either3.31

Third3.28

fourth3.25

Together3.19

first3.17

Negative logits

clusions-2.25

jen-2.18

alian-2.17

uras-2.11

owsky-2.08

undown-2.07

nen-2.05

zinski-2.00

ubis-1.99

bytes-1.98

teness-1.98

alla-1.98

ako-1.97

ienne-1.97

chell-1.95

CLOSE-1.94

alien-1.94

akeru-1.91

ski-1.90

VID-1.88

INTERVAL 5.126 - 5.696
CONTAINS 0.001%

sailed
Token sailed
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
Legislature
Token Legislature
Feature activation+0.000
.
Token.
Feature activation+5.569
The
Token The
Feature activation+4.573
measures
Token measures
Feature activation+0.688
now
Token now
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
posts
Token posts
Feature activation+0.000
on
Token on
Feature activation+0.317
my
Token my
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
feed
Token feed
Feature activation+1.173
.
Token.
Feature activation+5.299
One
Token One
Feature activation+0.694
stating
Token stating
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
judge
Token judge
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
not
Token not
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
letters
Token letters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+5.220
from
Token from
Feature activation+0.180
William
Token William
Feature activation+0.000
Harris
Token Harris
Feature activation+0.000
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
girls
Token girls
Feature activation+0.000
,
Token,
Feature activation+5.620
one
Token one
Feature activation+0.000
13
Token 13
Feature activation+0.000
and
Token and
Feature activation+1.217
one
Token one
Feature activation+0.000
14
Token 14
Feature activation+0.000
that
Token that
Feature activation+0.000
national
Token national
Feature activation+0.000
identity
Token identity
Feature activation+0.000
stand
Token stand
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+5.308
One
Token One
Feature activation+0.000
is
Token is
Feature activation+0.000
our
Token our
Feature activation+0.000
Anglo
Token Anglo
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 4.557 - 5.126
CONTAINS 0.001%

that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
open
Token open
Feature activation+0.000
.
Token.
Feature activation+2.422
The
Token The
Feature activation+4.683
other
Token other
Feature activation+1.342
was
Token was
Feature activation+0.215
closed
Token closed
Feature activation+0.053
and
Token and
Feature activation+0.793
No
Token No
Feature activation+0.000
them
Token them
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
important
Token important
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
.
Token.
Feature activation+4.899
One
Token One
Feature activation+0.000
,
Token,
Feature activation+0.000
Muscle
Token Muscle
Feature activation+0.000
Soldier
Token Soldier
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
global
Token global
Feature activation+0.000
surface
Token surface
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
observational
Token observational
Feature activation+0.000
datasets
Token datasets
Feature activation+0.000
,
Token,
Feature activation+4.607
the
Token the
Feature activation+1.190
UK
Token UK
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
programmers
Token programmers
Feature activation+0.000
,
Token,
Feature activation+4.717
one
Token one
Feature activation+0.101
systems
Token systems
Feature activation+0.000
specialist
Token specialist
Feature activation+0.194
,
Token,
Feature activation+1.097
a
Token a
Feature activation+0.846
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
major
Token major
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
.
Token.
Feature activation+4.632
In
Token In
Feature activation+4.925
one
Token one
Feature activation+0.000
case
Token case
Feature activation+0.135
,
Token,
Feature activation+0.085
a
Token a
Feature activation+0.000
teen
Token teen
Feature activation+0.000

INTERVAL 3.987 - 4.557
CONTAINS 0.001%

board
Token board
Feature activation+0.000
has
Token has
Feature activation+0.000
endorsed
Token endorsed
Feature activation+0.000
two
Token two
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
,
Token,
Feature activation+4.431
Paul
Token Paul
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
for
Token for
Feature activation+0.097
governor
Token governor
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.154
the
Token the
Feature activation+0.070
Web
Token Web
Feature activation+0.000
GL
TokenGL
Feature activation+0.000
technology
Token technology
Feature activation+0.000
,
Token,
Feature activation+4.407
Web
Token Web
Feature activation+0.000
GL
TokenGL
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
A
Token A
Feature activation+0.000
New
Token New
Feature activation+0.000
Edwards
Token Edwards
Feature activation+0.000
have
Token have
Feature activation+0.000
represented
Token represented
Feature activation+0.000
two
Token two
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+4.145
known
Token known
Feature activation+0.000
only
Token only
Feature activation+0.000
as
Token as
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
Does
Token Does
Feature activation+0.000
has
Token has
Feature activation+0.000
tend
Token tend
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
two
Token two
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
,
Token,
Feature activation+4.453
which
Token which
Feature activation+1.168
outline
Token outline
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
entrances
Token entrances
Feature activation+0.000
from
Token from
Feature activation+0.000
two
Token two
Feature activation+0.000
points
Token points
Feature activation+0.000
to
Token to
Feature activation+4.022
one
Token one
Feature activation+0.140
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+0.000

INTERVAL 3.417 - 3.987
CONTAINS 0.002%

NL
Token NL
Feature activation+0.000
RB
TokenRB
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.174
,
Token,
Feature activation+3.630
giving
Token giving
Feature activation+0.242
his
Token his
Feature activation+0.000
party
Token party
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+3.625
The
Token The
Feature activation+3.898
first
Token first
Feature activation+0.000
person
Token person
Feature activation+0.000
has
Token has
Feature activation+0.000
lived
Token lived
Feature activation+0.000
killed
Token killed
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.000
weeks
Token weeks
Feature activation+0.060
.
Token.
Feature activation+1.161
In
Token In
Feature activation+3.931
Geneva
Token Geneva
Feature activation+0.000
the
Token the
Feature activation+0.000
UN
Token UN
Feature activation+0.000
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+0.000
produce
Token produce
Feature activation+0.000
two
Token two
Feature activation+0.000
rockets
Token rockets
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+3.484
and
Token and
Feature activation+1.024
four
Token four
Feature activation+0.005
in
Token in
Feature activation+0.000
2021
Token 2021
Feature activation+0.000
-
Token-
Feature activation+0.000
als
Tokenals
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
policemen
Token policemen
Feature activation+0.000
.
Token.
Feature activation+2.439
The
Token The
Feature activation+3.528
officers
Token officers
Feature activation+0.555
had
Token had
Feature activation+0.037
led
Token led
Feature activation+0.000
a
Token a
Feature activation+0.000
naked
Token naked
Feature activation+0.000

INTERVAL 2.848 - 3.417
CONTAINS 0.004%

music
Token music
Feature activation+0.000
.
Token.
Feature activation+1.149
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.747
In
TokenIn
Feature activation+3.807
the
Token the
Feature activation+3.084
videos
Token videos
Feature activation+0.000
she
Token she
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
owed
Tokenowed
Feature activation+0.000
lawn
Token lawn
Feature activation+0.000
.
Token.
Feature activation+0.489
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.041
The
TokenThe
Feature activation+3.333
following
Token following
Feature activation+0.000
day
Token day
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.214
third
Token third
Feature activation+0.000
is
Token is
Feature activation+0.000
actually
Token actually
Feature activation+0.000
two
Token two
Feature activation+0.000
separate
Token separate
Feature activation+0.000
problems
Token problems
Feature activation+0.195
.
Token.
Feature activation+3.381
First
Token First
Feature activation+0.000
,
Token,
Feature activation+0.168
the
Token the
Feature activation+0.481
form
Token form
Feature activation+0.000
library
Token library
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Marvel
Token Marvel
Feature activation+0.000
Universe
Token Universe
Feature activation+0.000
.
Token.
Feature activation+3.128
Iron
Token Iron
Feature activation+0.000
Man
Token Man
Feature activation+0.000
,
Token,
Feature activation+0.000
genius
Token genius
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.040
was
Token was
Feature activation+0.000
established
Token established
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+3.352
The
Token The
Feature activation+1.710
two
Token two
Feature activation+0.000
companies
Token companies
Feature activation+0.205
will
Token will
Feature activation+0.278
bring
Token bring
Feature activation+0.000

INTERVAL 2.278 - 2.848
CONTAINS 0.006%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.492
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+2.724
package
Token package
Feature activation+0.000
fell
Token fell
Feature activation+0.000
apart
Token apart
Feature activation+0.000
after
Token after
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
used
Token used
Feature activation+0.000
two
Token two
Feature activation+0.000
pulse
Token pulse
Feature activation+0.000
jet
Tokenjet
Feature activation+0.000
engines
Token engines
Feature activation+0.000
;
Token;
Feature activation+2.386
L
Token L
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
er
Tokener
Feature activation+0.120
improved
Token improved
Feature activation+1.376
the
Token the
Feature activation+2.206
events
Token events
Feature activation+0.000
,
Token,
Feature activation+2.846
a
Token a
Feature activation+2.111
memory
Token memory
Feature activation+0.000
linking
Token linking
Feature activation+2.581
the
Token the
Feature activation+2.766
two
Token two
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
formed
Token formed
Feature activation+1.366
.
Token.
Feature activation+0.000
will
Token will
Feature activation+0.404
absolutely
Token absolutely
Feature activation+0.000
dro
Token dro
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
over
Token over
Feature activation+0.208
:
Token:
Feature activation+2.655
the
Token the
Feature activation+0.571
AC
Token AC
Feature activation+0.000
4
Token4
Feature activation+0.000
C
TokenC
Feature activation+0.000
1
Token1
Feature activation+0.000
in
Token in
Feature activation+0.000
NM
Token NM
Feature activation+0.000
at
Token at
Feature activation+0.000
high
Token high
Feature activation+0.000
altitude
Token altitude
Feature activation+0.000
.
Token.
Feature activation+2.499
They
Token They
Feature activation+0.823
performed
Token performed
Feature activation+0.000
as
Token as
Feature activation+0.000
planned
Token planned
Feature activation+0.203
and
Token and
Feature activation+0.141

INTERVAL 1.709 - 2.278
CONTAINS 0.008%

length
Tokenlength
Feature activation+0.000
running
Token running
Feature activation+0.000
pants
Token pants
Feature activation+0.000
.
Token.
Feature activation+1.495
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.259
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
I
Token I
Feature activation+0.000
,
Token,
Feature activation+5.056
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
approved
Token approved
Feature activation+1.562
the
Token the
Feature activation+2.231
bill
Token bill
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.000
.
Token.
Feature activation+3.081
Ċ
TokenĊ
Feature activation+0.000
feed
Token feed
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
prey
Token prey
Feature activation+0.000
,
Token,
Feature activation+2.106
the
Token the
Feature activation+0.471
au
Token au
Feature activation+0.000
ks
Tokenks
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
conflicted
Token conflicted
Feature activation+0.000
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+1.255
the
Token the
Feature activation+2.145
night
Token night
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fire
Token fire
Feature activation+0.000
.
Token.
Feature activation+0.000
different
Token different
Feature activation+0.000
parts
Token parts
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
.
Token.
Feature activation+1.922
If
Token If
Feature activation+0.000
this
Token this
Feature activation+0.000
really
Token really
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000

INTERVAL 1.139 - 1.709
CONTAINS 0.016%

championship
Token championship
Feature activation+0.000
fight
Token fight
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
card
Token card
Feature activation+0.000
,
Token,
Feature activation+1.620
as
Token as
Feature activation+0.000
Brandon
Token Brandon
Feature activation+0.000
Vera
Token Vera
Feature activation+0.000
will
Token will
Feature activation+0.354
defend
Token defend
Feature activation+0.000
in
Token in
Feature activation+0.084
conjunction
Token conjunction
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
only
Token only
Feature activation+0.248
have
Token have
Feature activation+1.607
one
Token one
Feature activation+0.000
mon
Token mon
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
loc
Tokenloc
Feature activation+0.000
and
Token and
Feature activation+0.991
,
Token,
Feature activation+0.000
consisting
Token consisting
Feature activation+0.000
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
(
Token (
Feature activation+1.484
flu
Tokenflu
Feature activation+0.000
or
Tokenor
Feature activation+0.000
our
Tokenour
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
il
Tokenil
Feature activation+0.000
were
Token were
Feature activation+0.000
unaware
Token unaware
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
changes
Token changes
Feature activation+0.000
.
Token.
Feature activation+1.374
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.631
The
TokenThe
Feature activation+1.798
most
Token most
Feature activation+0.000
far
Token far
Feature activation+0.000
24
Token 24
Feature activation+0.000
02
Token 02
Feature activation+0.000
:
Token:
Feature activation+0.000
24
Token24
Feature activation+0.346
:
Token:
Feature activation+0.000
17
Token17
Feature activation+1.301
2013
Token 2013
Feature activation+0.296
BL
Token BL
Feature activation+0.000
anc
Tokenanc
Feature activation+0.000
zos
Tokenzos
Feature activation+0.328
Time
TokenTime
Feature activation+0.000

INTERVAL 0.570 - 1.139
CONTAINS 0.048%

two
Token two
Feature activation+0.000
philosoph
Token philosoph
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
threads
Token threads
Feature activation+0.000
tie
Token tie
Feature activation+0.000
them
Token them
Feature activation+0.732
together
Token together
Feature activation+0.000
.
Token.
Feature activation+2.711
The
Token The
Feature activation+2.808
stories
Token stories
Feature activation+0.000
explore
Token explore
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
4
Token 4
Feature activation+0.000
daughters
Token daughters
Feature activation+0.000
(
Token (
Feature activation+0.662
D
TokenD
Feature activation+0.000
ove
Tokenove
Feature activation+0.000
,
Token,
Feature activation+0.000
Eden
Token Eden
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
's
Token's
Feature activation+0.000
destruction
Token destruction
Feature activation+0.000
,
Token,
Feature activation+1.116
Arthur
Token Arthur
Feature activation+0.000
Dent
Token Dent
Feature activation+0.000
and
Token and
Feature activation+0.000
Ford
Token Ford
Feature activation+0.000
Pre
Token Pre
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
-
Token-
Feature activation+0.000
Israeli
TokenIsraeli
Feature activation+0.000
community
Token community
Feature activation+0.000
.
Token.
Feature activation+0.797
At
Token At
Feature activation+1.029
the
Token the
Feature activation+0.810
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.304
funeral
Token funeral
Feature activation+0.000
add
Tokenadd
Feature activation+0.000
i
Tokeni
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
destroyed
Token destroyed
Feature activation+0.882
five
Token five
Feature activation+0.000
ISIS
Token ISIS
Feature activation+0.000
-
Token-
Feature activation+0.000
held
Tokenheld
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000

INTERVAL 0.000 - 0.570
CONTAINS 99.914%

Merkel
Token Merkel
Feature activation+0.000
ally
Token ally
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
chairman
Token chairman
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
affairs
Token affairs
Feature activation+0.000
committee
Token committee
Feature activation+0.000
is
Token is
Feature activation+0.000
formidable
Token formidable
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Henderson
Token Henderson
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
But
TokenBut
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
wants
Token wants
Feature activation+0.000
in
Token in
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
it
Token it
Feature activation+0.000
persu
Token persu
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
the
Token the
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
calling
Token calling
Feature activation+0.000
911
Token 911
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
branch
Token branch
Feature activation+0.000
manager
Token manager
Feature activation+0.000
walked
Token walked
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
Adams
TokenAdams
Feature activation+0.000
Park
Token Park
Feature activation+0.000
enjoyed
Token enjoyed
Feature activation+0.000
free
Token free
Feature activation+0.000
food
Token food
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
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 H9.7: (feature 12752)

TOP ACTIVATIONS
MAX = 6.351

the
Token the
Feature activation+0.000
side
Token side
Feature activation+0.000
.
Token.
Feature activation+0.000
Thankfully
Token Thankfully
Feature activation+0.000
he
Token he
Feature activation+3.521
decided
Token decided
Feature activation+6.351
to
Token to
Feature activation+2.165
play
Token play
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
exploding
Token exploding
Feature activation+0.000
oil
Token oil
Feature activation+0.000
trains
Token trains
Feature activation+0.000
.
Token.
Feature activation+2.560
She
Token She
Feature activation+2.719
chose
Token chose
Feature activation+5.406
to
Token to
Feature activation+0.000
resist
Token resist
Feature activation+0.181
because
Token because
Feature activation+0.000
she
Token she
Feature activation+0.000
understands
Token understands
Feature activation+0.000
of
Token of
Feature activation+0.000
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.260
,
Token,
Feature activation+0.345
perhaps
Token perhaps
Feature activation+4.375
more
Token more
Feature activation+0.272
likely
Token likely
Feature activation+2.201
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
simply
Token simply
Feature activation+0.000
-
Token-
Feature activation+0.000
8
Token8
Feature activation+0.000
76
Token76
Feature activation+0.000
-
Token-
Feature activation+0.000
45
Token45
Feature activation+0.000
00
Token00
Feature activation+3.902
.
Token.
Feature activation+1.712
Delivery
Token Delivery
Feature activation+0.000
:
Token:
Feature activation+0.000
Invalid
Token Invalid
Feature activation+0.000
email
Token email
Feature activation+0.000
IRS
Token IRS
Feature activation+0.000
is
Token is
Feature activation+0.024
still
Token still
Feature activation+0.000
to
Token to
Feature activation+0.000
rule
Token rule
Feature activation+0.476
on
Token on
Feature activation+3.851
this
Token this
Feature activation+0.226
).
Token).
Feature activation+0.000
Further
Token Further
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
predictable
Token predictable
Feature activation+0.000
answer
Token answer
Feature activation+0.689
that
Token that
Feature activation+1.569
she
Token she
Feature activation+1.169
gave
Token gave
Feature activation+0.188
was
Token was
Feature activation+3.802
that
Token that
Feature activation+1.614
she
Token she
Feature activation+0.899
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
just
Tokenjust
Feature activation+0.000
?
Token?
Feature activation+0.000
In
Token In
Feature activation+2.071
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+2.031
,
Token,
Feature activation+0.261
it
Token it
Feature activation+3.558
doesn
Token doesn
Feature activation+0.149
't
Token't
Feature activation+1.744
quite
Token quite
Feature activation+1.118
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
,
Token,
Feature activation+0.746
or
Token or
Feature activation+3.530
$
Token $
Feature activation+0.000
500
Token500
Feature activation+0.662
,
Token,
Feature activation+0.226
000
Token000
Feature activation+0.924
if
Token if
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
side
Token side
Feature activation+0.000
.
Token.
Feature activation+0.000
Thankfully
Token Thankfully
Feature activation+0.000
he
Token he
Feature activation+3.521
decided
Token decided
Feature activation+6.351
to
Token to
Feature activation+2.165
play
Token play
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
sideways
Token sideways
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
backward
Token backward
Feature activation+0.000
(
Token (
Feature activation+0.227
or
Tokenor
Feature activation+3.190
if
Token if
Feature activation+0.000
we
Token we
Feature activation+1.013
really
Token really
Feature activation+0.027
even
Token even
Feature activation+0.192
care
Token care
Feature activation+0.000
forces
Token forces
Feature activation+0.000
elsewhere
Token elsewhere
Feature activation+0.000
.
Token.
Feature activation+0.146
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+3.098
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Assad
Token Assad
Feature activation+0.000
has
Token has
Feature activation+0.021
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
prove
Token prove
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+3.095
something
Token something
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.000
bitch
Token bitch
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.694
museum
Token museum
Feature activation+0.000
and
Token and
Feature activation+2.275
cultural
Token cultural
Feature activation+0.000
centre
Token centre
Feature activation+0.030
,
Token,
Feature activation+3.078
and
Token and
Feature activation+2.869
others
Token others
Feature activation+0.331
still
Token still
Feature activation+0.000
think
Token think
Feature activation+0.320
it
Token it
Feature activation+0.077
total
Token total
Feature activation+0.000
wake
Token wake
Feature activation+0.000
fulness
Tokenfulness
Feature activation+0.000
per
Token per
Feature activation+0.000
day
Token day
Feature activation+0.789
,
Token,
Feature activation+3.065
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.511
with
Token with
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
fragmentation
Token fragmentation
Feature activation+0.000
museum
Token museum
Feature activation+0.000
and
Token and
Feature activation+2.275
cultural
Token cultural
Feature activation+0.000
centre
Token centre
Feature activation+0.030
,
Token,
Feature activation+3.078
and
Token and
Feature activation+2.869
others
Token others
Feature activation+0.331
still
Token still
Feature activation+0.000
think
Token think
Feature activation+0.320
it
Token it
Feature activation+0.077
âĢ
TokenâĢ
Feature activation+0.000
said
Token said
Feature activation+0.000
Kraft
Token Kraft
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.195
I
TokenI
Feature activation+0.016
picked
Token picked
Feature activation+2.789
spotting
Token spotting
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
latter
Token latter
Feature activation+0.111
,
Token,
Feature activation+0.350
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
cannot
Token cannot
Feature activation+0.103
do
Token do
Feature activation+2.775
that
Token that
Feature activation+0.746
anymore
Token anymore
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
?
Token?
Feature activation+0.000
Isn
Token Isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.027
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.493
the
Token the
Feature activation+2.738
point
Token point
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
medical
Token medical
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
or
Token or
Feature activation+0.000
divine
Token divine
Feature activation+0.000
intervention
Token intervention
Feature activation+0.130
.
Token.
Feature activation+2.731
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.619
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
and
Token and
Feature activation+0.000
exploding
Token exploding
Feature activation+0.000
oil
Token oil
Feature activation+0.000
trains
Token trains
Feature activation+0.000
.
Token.
Feature activation+2.560
She
Token She
Feature activation+2.719
chose
Token chose
Feature activation+5.406
to
Token to
Feature activation+0.000
resist
Token resist
Feature activation+0.181
because
Token because
Feature activation+0.000
she
Token she
Feature activation+0.000

Top DFA by src position
MAX = 7.014

was
Token was
Feature activation+0.002
Top resid features:
whether
Token whether
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
retire
Token retire
Feature activation+0.000
Top resid features:
then
Token then
Feature activation-0.012
Top resid features:
or
Token or
Feature activation+7.014
Top resid features:
at
Token at
Feature activation+0.016
Top resid features:
his
Token his
Feature activation-0.001
Top resid features:
age
Token age
Feature activation-0.006
Top resid features:
try
Token try
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
jeopard
Token jeopard
Feature activation+0.003
Top resid features:
ized
Tokenized
Feature activation+0.002
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
police
Token police
Feature activation-0.002
Top resid features:
or
Token or
Feature activation+5.808
Top resid features:
by
Token by
Feature activation+0.038
Top resid features:
catastrophic
Token catastrophic
Feature activation+0.033
Top resid features:
climate
Token climate
Feature activation+0.005
Top resid features:
change
Token change
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
essential
Token essential
Feature activation+0.002
Top resid features:
part
Token part
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
life
Token life
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
or
Token or
Feature activation+4.221
Top resid features:
,
Token,
Feature activation+0.157
Top resid features:
perhaps
Token perhaps
Feature activation+0.194
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Please
Token Please
Feature activation-0.007
Top resid features:
try
Token try
Feature activation-0.034
Top resid features:
again
Token again
Feature activation-0.011
Top resid features:
soon
Token soon
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
or
Token or
Feature activation+4.410
Top resid features:
contact
Token contact
Feature activation+0.160
Top resid features:
Customer
Token Customer
Feature activation-0.037
Top resid features:
Service
Token Service
Feature activation+0.021
Top resid features:
at
Token at
Feature activation+0.155
Top resid features:
1
Token 1
Feature activation-0.038
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
plan
Token plan
Feature activation+0.002
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
taxable
Token taxable
Feature activation-0.038
Top resid features:
or
Token or
Feature activation+4.528
Top resid features:
not
Token not
Feature activation+0.044
Top resid features:
(
Token (
Feature activation+0.097
Top resid features:
the
Tokenthe
Feature activation+0.009
Top resid features:
IRS
Token IRS
Feature activation-0.005
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
prayer
Token prayer
Feature activation+0.012
Top resid features:
or
Token or
Feature activation+4.119
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
medicine
Token medicine
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
heals
Token heals
Feature activation+0.001
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.043
Top resid features:
Sandy
Token Sandy
Feature activation+0.013
Top resid features:
just
Token just
Feature activation+0.055
Top resid features:
a
Token a
Feature activation+0.039
Top resid features:
hurricane
Token hurricane
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
or
Token or
Feature activation+3.892
Top resid features:
an
Token an
Feature activation+0.082
Top resid features:
ang
Token ang
Feature activation-0.001
Top resid features:
rier
Tokenrier
Feature activation+0.027
Top resid features:
child
Token child
Feature activation+0.001
Top resid features:
spawned
Token spawned
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
$
Token $
Feature activation-0.002
Top resid features:
100
Token100
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
000
Token000
Feature activation-0.003
Top resid features:
or
Token or
Feature activation+2.065
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
year
Token year
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
jail
Token jail
Feature activation+0.049
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
whether
Token whether
Feature activation+0.127
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
retire
Token retire
Feature activation-0.009
Top resid features:
then
Token then
Feature activation+0.036
Top resid features:
or
Token or
Feature activation+3.951
Top resid features:
at
Token at
Feature activation+0.033
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
age
Token age
Feature activation+0.013
Top resid features:
try
Token try
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
step
Token step
Feature activation-0.004
Top resid features:
forward
Token forward
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
sideways
Token sideways
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+0.077
Top resid features:
or
Token or
Feature activation+2.898
Top resid features:
backward
Token backward
Feature activation+0.152
Top resid features:
(
Token (
Feature activation+0.107
Top resid features:
or
Tokenor
Feature activation+0.667
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.012
Top resid features:
starvation
Token starvation
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
surrender
Token surrender
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
or
Token or
Feature activation+2.563
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
halt
Token halt
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
fighting
Token fighting
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
prove
Token prove
Feature activation-0.035
Top resid features:
they
Token they
Feature activation-0.051
Top resid features:
can
Token can
Feature activation-0.031
Top resid features:
govern
Token govern
Feature activation-0.022
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Or
Token Or
Feature activation+3.913
Top resid features:
prove
Token prove
Feature activation-0.004
Top resid features:
they
Token they
Feature activation+0.008
Top resid features:
can
Token can
Feature activation+0.042
Top resid features:
do
Token do
Feature activation+0.020
Top resid features:
something
Token something
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.023
Top resid features:
become
Token become
Feature activation+0.027
Top resid features:
a
Token a
Feature activation+0.025
Top resid features:
market
Token market
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
others
Token others
Feature activation+3.376
Top resid features:
a
Token a
Feature activation+0.046
Top resid features:
museum
Token museum
Feature activation+0.024
Top resid features:
and
Token and
Feature activation+0.105
Top resid features:
cultural
Token cultural
Feature activation+0.011
Top resid features:
centre
Token centre
Feature activation+0.034
Top resid features:
produced
Token produced
Feature activation-0.014
Top resid features:
26
Token 26
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
5
Token5
Feature activation-0.000
Top resid features:
%
Token%
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+3.642
Top resid features:
17
Token 17
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
4
Token4
Feature activation+0.007
Top resid features:
%
Token%
Feature activation+0.007
Top resid features:
increase
Token increase
Feature activation-0.016
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
become
Token become
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
market
Token market
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
others
Token others
Feature activation+3.345
Top resid features:
a
Token a
Feature activation+0.023
Top resid features:
museum
Token museum
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
cultural
Token cultural
Feature activation+0.006
Top resid features:
centre
Token centre
Feature activation+0.013
Top resid features:
whether
Token whether
Feature activation+0.020
Top resid features:
I
Token I
Feature activation+0.036
Top resid features:
wanted
Token wanted
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
race
Token race
Feature activation-0.018
Top resid features:
or
Token or
Feature activation+3.540
Top resid features:
do
Token do
Feature activation+0.029
Top resid features:
what
Token what
Feature activation-0.004
Top resid features:
I
Token I
Feature activation+0.003
Top resid features:
do
Token do
Feature activation+0.004
Top resid features:
now
Token now
Feature activation-0.002
Top resid features:
today
Token today
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
I
Token I
Feature activation-0.016
Top resid features:
chose
Token chose
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
latter
Token latter
Feature activation+3.251
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
but
Token but
Feature activation+0.026
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
cannot
Token cannot
Feature activation+0.043
Top resid features:
do
Token do
Feature activation+0.026
Top resid features:
osh
Tokenosh
Feature activation-0.006
Top resid features:
oots
Tokenoots
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+0.031
Top resid features:
film
Token film
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
or
Token or
Feature activation+3.377
Top resid features:
something
Token something
Feature activation+0.011
Top resid features:
slipped
Token slipped
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
there
Token there
Feature activation+0.001
Top resid features:
by
Token by
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Either
Token Either
Feature activation+1.401
Top resid features:
through
Token through
Feature activation+0.017
Top resid features:
medical
Token medical
Feature activation+0.009
Top resid features:
treatment
Token treatment
Feature activation+0.027
Top resid features:
or
Token or
Feature activation+1.506
Top resid features:
divine
Token divine
Feature activation+0.012
Top resid features:
intervention
Token intervention
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
jeopard
Token jeopard
Feature activation+0.004
Top resid features:
ized
Tokenized
Feature activation+0.001
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
police
Token police
Feature activation-0.003
Top resid features:
or
Token or
Feature activation+2.264
Top resid features:
by
Token by
Feature activation+0.116
Top resid features:
catastrophic
Token catastrophic
Feature activation+0.012
Top resid features:
climate
Token climate
Feature activation+0.004
Top resid features:
change
Token change
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.06

Head 3: 0.06

Head 4: 0.05

Head 5: 0.05

Head 6: 0.03

Head 7: 0.54

Head 8: 0.03

Head 9: 0.03

Head 10: 0.08

Head 11: 0.02

Positive logits

respectively7.00

latter6.15

Both5.89

Both5.84

whichever5.50

Neither5.39

both5.11

both5.09

neither5.03

depending5.00

Either4.91

Neither4.78

Either4.49

ichever4.35

alike4.01

either3.71

OTH3.39

respective3.32

former3.21

mutually3.21

Negative logits

umbn-2.67

erg-2.56

stown-2.56

veland-2.26

enza-2.22

gres-2.20

sed-2.16

jri-2.09

rice-2.08

nen-2.08

Dmitry-2.07

ollah-2.02

onse-2.02

unes-2.01

thumbnails-2.01

riots-2.00

eli-1.97

ington-1.95

Notting-1.95

ikarp-1.95

INTERVAL 5.716 - 6.351
CONTAINS 0.000%

the
Token the
Feature activation+0.000
side
Token side
Feature activation+0.000
.
Token.
Feature activation+0.000
Thankfully
Token Thankfully
Feature activation+0.000
he
Token he
Feature activation+3.521
decided
Token decided
Feature activation+6.351
to
Token to
Feature activation+2.165
play
Token play
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000

INTERVAL 5.081 - 5.716
CONTAINS 0.000%

exploding
Token exploding
Feature activation+0.000
oil
Token oil
Feature activation+0.000
trains
Token trains
Feature activation+0.000
.
Token.
Feature activation+2.560
She
Token She
Feature activation+2.719
chose
Token chose
Feature activation+5.406
to
Token to
Feature activation+0.000
resist
Token resist
Feature activation+0.181
because
Token because
Feature activation+0.000
she
Token she
Feature activation+0.000
understands
Token understands
Feature activation+0.000

INTERVAL 4.446 - 5.081
CONTAINS 0.000%

INTERVAL 3.811 - 4.446
CONTAINS 0.000%

of
Token of
Feature activation+0.000
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.260
,
Token,
Feature activation+0.345
perhaps
Token perhaps
Feature activation+4.375
more
Token more
Feature activation+0.272
likely
Token likely
Feature activation+2.201
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
simply
Token simply
Feature activation+0.000
IRS
Token IRS
Feature activation+0.000
is
Token is
Feature activation+0.024
still
Token still
Feature activation+0.000
to
Token to
Feature activation+0.000
rule
Token rule
Feature activation+0.476
on
Token on
Feature activation+3.851
this
Token this
Feature activation+0.226
).
Token).
Feature activation+0.000
Further
Token Further
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
-
Token-
Feature activation+0.000
8
Token8
Feature activation+0.000
76
Token76
Feature activation+0.000
-
Token-
Feature activation+0.000
45
Token45
Feature activation+0.000
00
Token00
Feature activation+3.902
.
Token.
Feature activation+1.712
Delivery
Token Delivery
Feature activation+0.000
:
Token:
Feature activation+0.000
Invalid
Token Invalid
Feature activation+0.000
email
Token email
Feature activation+0.000

INTERVAL 3.176 - 3.811
CONTAINS 0.001%

predictable
Token predictable
Feature activation+0.000
answer
Token answer
Feature activation+0.689
that
Token that
Feature activation+1.569
she
Token she
Feature activation+1.169
gave
Token gave
Feature activation+0.188
was
Token was
Feature activation+3.802
that
Token that
Feature activation+1.614
she
Token she
Feature activation+0.899
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
just
Tokenjust
Feature activation+0.000
sideways
Token sideways
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
backward
Token backward
Feature activation+0.000
(
Token (
Feature activation+0.227
or
Tokenor
Feature activation+3.190
if
Token if
Feature activation+0.000
we
Token we
Feature activation+1.013
really
Token really
Feature activation+0.027
even
Token even
Feature activation+0.192
care
Token care
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
side
Token side
Feature activation+0.000
.
Token.
Feature activation+0.000
Thankfully
Token Thankfully
Feature activation+0.000
he
Token he
Feature activation+3.521
decided
Token decided
Feature activation+6.351
to
Token to
Feature activation+2.165
play
Token play
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
?
Token?
Feature activation+0.000
In
Token In
Feature activation+2.071
one
Token one
Feature activation+0.000
sense
Token sense
Feature activation+2.031
,
Token,
Feature activation+0.261
it
Token it
Feature activation+3.558
doesn
Token doesn
Feature activation+0.149
't
Token't
Feature activation+1.744
quite
Token quite
Feature activation+1.118
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
,
Token,
Feature activation+0.746
or
Token or
Feature activation+3.530
$
Token $
Feature activation+0.000
500
Token500
Feature activation+0.662
,
Token,
Feature activation+0.226
000
Token000
Feature activation+0.924
if
Token if
Feature activation+0.000

INTERVAL 2.541 - 3.176
CONTAINS 0.001%

than
Token than
Feature activation+0.000
three
Token three
Feature activation+0.000
times
Token times
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+2.585
latter
Token latter
Feature activation+0.000
.
Token.
Feature activation+0.032
The
Token The
Feature activation+1.242
Republican
Token Republican
Feature activation+0.000
bill
Token bill
Feature activation+0.000
a
Token a
Feature activation+0.694
museum
Token museum
Feature activation+0.000
and
Token and
Feature activation+2.275
cultural
Token cultural
Feature activation+0.000
centre
Token centre
Feature activation+0.030
,
Token,
Feature activation+3.078
and
Token and
Feature activation+2.869
others
Token others
Feature activation+0.331
still
Token still
Feature activation+0.000
think
Token think
Feature activation+0.320
it
Token it
Feature activation+0.077
latter
Token latter
Feature activation+0.111
,
Token,
Feature activation+0.350
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
cannot
Token cannot
Feature activation+0.103
do
Token do
Feature activation+2.775
that
Token that
Feature activation+0.746
anymore
Token anymore
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
total
Token total
Feature activation+0.000
wake
Token wake
Feature activation+0.000
fulness
Tokenfulness
Feature activation+0.000
per
Token per
Feature activation+0.000
day
Token day
Feature activation+0.789
,
Token,
Feature activation+3.065
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.511
with
Token with
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
fragmentation
Token fragmentation
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
prove
Token prove
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+3.095
something
Token something
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.000
bitch
Token bitch
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.905 - 2.541
CONTAINS 0.002%

as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
forward
Token forward
Feature activation+0.000
pass
Token pass
Feature activation+0.000
.
Token.
Feature activation+0.169
In
Token In
Feature activation+2.387
a
Token a
Feature activation+0.000
forward
Token forward
Feature activation+0.000
pass
Token pass
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
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
latter
Token latter
Feature activation+0.000
than
Token than
Feature activation+0.154
the
Token the
Feature activation+2.389
former
Token former
Feature activation+0.000
at
Token at
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
's
Token's
Feature activation+0.000
sarc
Token sarc
Feature activation+0.000
asm
Tokenasm
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.211
,
Token,
Feature activation+0.124
the
Token the
Feature activation+1.947
experience
Token experience
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.906
Last
Token Last
Feature activation+0.000
2
Token 2
Feature activation+0.000
former
Token former
Feature activation+0.000
emphasizing
Token emphasizing
Feature activation+0.000
economic
Token economic
Feature activation+0.000
redistribution
Token redistribution
Feature activation+0.261
,
Token,
Feature activation+1.298
the
Token the
Feature activation+2.423
latter
Token latter
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
more
Token more
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
higher
Token higher
Feature activation+0.000
order
Token order
Feature activation+0.000
function
Token function
Feature activation+0.000
?
Token?
Feature activation+0.105
The
Token The
Feature activation+2.166
latter
Token latter
Feature activation+0.608
has
Token has
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000
moving
Token moving
Feature activation+0.000
parts
Token parts
Feature activation+0.000

INTERVAL 1.270 - 1.905
CONTAINS 0.008%

.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
and
Token and
Feature activation+0.000
2
Token 2
Feature activation+0.000
billion
Token billion
Feature activation+0.000
euros
Token euros
Feature activation+1.570
per
Token per
Feature activation+0.000
year
Token year
Feature activation+0.492
,
Token,
Feature activation+1.751
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.000
division
Token division
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
joke
Token joke
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.340
that
Token that
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.000
and
Token and
Feature activation+0.000
neither
Token neither
Feature activation+0.000
has
Token has
Feature activation+0.000
outwe
Token outwe
Feature activation+0.000
ighed
Tokenighed
Feature activation+0.564
the
Token the
Feature activation+1.764
other
Token other
Feature activation+0.000
quite
Token quite
Feature activation+0.000
enough
Token enough
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
or
Token or
Feature activation+0.000
dog
Token dog
Feature activation+0.000
food
Token food
Feature activation+0.160
and
Token and
Feature activation+0.000
water
Token water
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.543
not
Token not
Feature activation+0.000
bread
Token bread
Feature activation+0.000
and
Token and
Feature activation+0.000
milk
Token milk
Feature activation+0.014
.
Token.
Feature activation+0.000
received
Token received
Feature activation+0.000
33
Token 33
Feature activation+0.000
and
Token and
Feature activation+0.000
24
Token 24
Feature activation+0.000
percent
Token percent
Feature activation+0.158
,
Token,
Feature activation+1.806
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.635 - 1.270
CONTAINS 0.032%

does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
shy
Token shy
Feature activation+0.000
away
Token away
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.912
more
Token more
Feature activation+0.000
visceral
Token visceral
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
so
Token so
Feature activation+0.000
disease
Token disease
Feature activation+0.000
could
Token could
Feature activation+0.000
easily
Token easily
Feature activation+0.000
wipe
Token wipe
Feature activation+0.247
out
Token out
Feature activation+0.905
an
Token an
Feature activation+0.000
entire
Token entire
Feature activation+0.000
population
Token population
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.663
The
Token The
Feature activation+0.768
first
Token first
Feature activation+0.000
person
Token person
Feature activation+0.000
has
Token has
Feature activation+0.000
lived
Token lived
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.713
short
Token short
Feature activation+0.000
report
Token report
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
first
Token first
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.155
You
TokenYou
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.854
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
Horn
Token Horn
Feature activation+0.000
et
Tokenet
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.635
CONTAINS 99.957%

removal
Token removal
Feature activation+0.000
or
Token or
Feature activation+0.000
addition
Token addition
Feature activation+0.000
of
Token of
Feature activation+0.000
specific
Token specific
Feature activation+0.000
algorithms
Token algorithms
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.072
SSH
Token SSH
Feature activation+0.000
-
Token-
Feature activation+0.000
comment
Token comment
Feature activation+0.000
/
Token/
Feature activation+0.000
chat
Tokenchat
Feature activation+0.000
feature
Token feature
Feature activation+0.000
so
Token so
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
seamlessly
Token seamlessly
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
meat
Token meat
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
longest
Token longest
Feature activation+0.000
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Manafort
Token Manafort
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
associates
Token associates
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
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
administration
Token administration
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
the
Token the
Feature activation+0.000
captured
Token captured
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 H9.7: (feature 17878)

TOP ACTIVATIONS
MAX = 8.249

stories
Token stories
Feature activation+0.000
they
Token they
Feature activation+0.000
tell
Token tell
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+8.249
verbal
Token verbal
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
and
Token and
Feature activation+0.802
the
Token the
Feature activation+0.853
destructive
Token destructive
Feature activation+0.466
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
in
Token in
Feature activation+0.000
horrible
Token horrible
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+8.217
emotional
Token emotional
Feature activation+0.000
pain
Token pain
Feature activation+0.000
could
Token could
Feature activation+0.000
happen
Token happen
Feature activation+0.000
to
Token to
Feature activation+0.000
555
Token555
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+7.542
perceptual
Token perceptual
Feature activation+0.000
symptoms
Token symptoms
Feature activation+0.000
are
Token are
Feature activation+0.000
currently
Token currently
Feature activation+0.000
stable
Token stable
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+7.504
mental
Token mental
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.651
typically
Token typically
Feature activation+0.000
ones
Token ones
Feature activation+0.000
risk
Token risk
Feature activation+0.000
of
Token of
Feature activation+0.000
death
Token death
Feature activation+0.000
from
Token from
Feature activation+0.000
physical
Token physical
Feature activation+0.000
or
Token or
Feature activation+7.408
psychological
Token psychological
Feature activation+0.000
causes
Token causes
Feature activation+0.000
is
Token is
Feature activation+0.000
significant
Token significant
Feature activation+0.000
,
Token,
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
physical
Token physical
Feature activation+0.000
or
Token or
Feature activation+7.308
psychological
Token psychological
Feature activation+0.000
condition
Token condition
Feature activation+0.000
of
Token of
Feature activation+0.000
husband
Token husband
Feature activation+0.000
or
Token or
Feature activation+0.206
physical
Tokenphysical
Feature activation+0.000
holding
Token holding
Feature activation+0.000
"
Token"
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+4.090
"
Token "
Feature activation+7.117
rest
Tokenrest
Feature activation+0.000
raint
Tokenraint
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
result
Token result
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.050
physical
Token physical
Feature activation+0.061
,
Token,
Feature activation+7.095
sexual
Token sexual
Feature activation+0.000
or
Token or
Feature activation+6.043
psychological
Token psychological
Feature activation+0.174
harm
Token harm
Feature activation+0.000
or
Token or
Feature activation+0.969
we
Token we
Feature activation+0.000
transition
Token transition
Feature activation+0.000
from
Token from
Feature activation+0.000
physical
Token physical
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
to
Token to
Feature activation+7.004
digital
Token digital
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
change
Token change
Feature activation+0.000
often
Token often
Feature activation+0.000
scar
Token scar
Feature activation+0.000
red
Tokenred
Feature activation+0.000
,
Token,
Feature activation+0.000
physically
Token physically
Feature activation+0.000
and
Token and
Feature activation+6.261
psychologically
Token psychologically
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+4.921
digital
Token digital
Feature activation+0.000
anonymity
Token anonymity
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+6.124
security
Token security
Feature activation+1.588
and
Token and
Feature activation+0.000
encryption
Token encryption
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.050
physical
Token physical
Feature activation+0.061
,
Token,
Feature activation+7.095
sexual
Token sexual
Feature activation+0.000
or
Token or
Feature activation+6.043
psychological
Token psychological
Feature activation+0.174
harm
Token harm
Feature activation+0.000
or
Token or
Feature activation+0.969
suffering
Token suffering
Feature activation+0.051
to
Token to
Feature activation+0.012
repaired
Token repaired
Feature activation+0.023
in
Token in
Feature activation+0.052
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.421
but
Token but
Feature activation+3.251
the
Token the
Feature activation+5.013
effect
Token effect
Feature activation+0.799
this
Token this
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.000
on
Token on
Feature activation+0.010
Tor
Token Tor
Feature activation+0.000
is
Token is
Feature activation+0.000
designed
Token designed
Feature activation+0.000
for
Token for
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+4.921
digital
Token digital
Feature activation+0.000
anonymity
Token anonymity
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+6.124
security
Token security
Feature activation+1.588
.
Token.
Feature activation+0.000
Ment
Token Ment
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
,
Token,
Feature activation+0.000
physically
Token physically
Feature activation+0.000
,
Token,
Feature activation+4.385
he
Token he
Feature activation+0.000
looks
Token looks
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+2.645
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Phys
Token Phys
Feature activation+0.000
ically
Tokenically
Feature activation+0.000
and
Token and
Feature activation+4.147
mentally
Token mentally
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
physical
Tokenphysical
Feature activation+0.000
holding
Token holding
Feature activation+0.000
"
Token"
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+4.090
"
Token "
Feature activation+7.117
rest
Tokenrest
Feature activation+0.000
raint
Tokenraint
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
their
Token their
Feature activation+0.000
state
Token state
Feature activation+0.000
certification
Token certification
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.185
not
Token not
Feature activation+3.750
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
confused
Token confused
Feature activation+0.000
with
Token with
Feature activation+0.398
D
Token D
Feature activation+0.000
be
Token be
Feature activation+0.000
repaired
Token repaired
Feature activation+0.023
in
Token in
Feature activation+0.052
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.421
but
Token but
Feature activation+3.251
the
Token the
Feature activation+5.013
effect
Token effect
Feature activation+0.799
this
Token this
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.000
is
Token is
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
higher
Token higher
Feature activation+0.000
than
Token than
Feature activation+0.119
that
Token that
Feature activation+0.000
in
Token in
Feature activation+3.201
humanities
Token humanities
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
history
Token history
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 9.374

The
Token The
Feature activation+0.005
Top resid features:
stories
Token stories
Feature activation+0.012
Top resid features:
they
Token they
Feature activation+0.002
Top resid features:
tell
Token tell
Feature activation+0.013
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
physical
Token physical
Feature activation+9.210
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
verbal
Token verbal
Feature activation+0.000
Top resid features:
abuse
Token abuse
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bricks
Token bricks
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Being
Token Being
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.029
Top resid features:
horrible
Token horrible
Feature activation+0.049
Top resid features:
physical
Token physical
Feature activation+9.374
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
emotional
Token emotional
Feature activation+0.000
Top resid features:
pain
Token pain
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
happen
Token happen
Feature activation+0.000
Top resid features:
EE
Token EE
Feature activation-0.000
Top resid features:
555
Token555
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.040
Top resid features:
physical
Token physical
Feature activation+8.596
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
perceptual
Token perceptual
Feature activation+0.000
Top resid features:
symptoms
Token symptoms
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
currently
Token currently
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.007
Top resid features:
with
Token with
Feature activation+0.030
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
variety
Token variety
Feature activation+0.034
Top resid features:
of
Token of
Feature activation+0.085
Top resid features:
physical
Token physical
Feature activation+8.376
Top resid features:
and
Token and
Feature activation+0.041
Top resid features:
mental
Token mental
Feature activation+0.000
Top resid features:
issues
Token issues
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
typically
Token typically
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
risk
Token risk
Feature activation+0.051
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
death
Token death
Feature activation+0.020
Top resid features:
from
Token from
Feature activation+0.018
Top resid features:
physical
Token physical
Feature activation+8.322
Top resid features:
or
Token or
Feature activation+0.007
Top resid features:
psychological
Token psychological
Feature activation+0.000
Top resid features:
causes
Token causes
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
significant
Token significant
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.008
Top resid features:
ar
Tokenar
Feature activation+0.007
Top resid features:
ising
Tokenising
Feature activation+0.049
Top resid features:
from
Token from
Feature activation+0.080
Top resid features:
the
Token the
Feature activation+0.103
Top resid features:
physical
Token physical
Feature activation+7.970
Top resid features:
or
Token or
Feature activation+0.027
Top resid features:
psychological
Token psychological
Feature activation+0.000
Top resid features:
condition
Token condition
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
husband
Token husband
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.005
Top resid features:
ambiguity
Token ambiguity
Feature activation-0.009
Top resid features:
,"
Token,"
Feature activation+0.001
Top resid features:
using
Token using
Feature activation+0.032
Top resid features:
"
Token "
Feature activation+0.008
Top resid features:
physical
Tokenphysical
Feature activation+8.094
Top resid features:
holding
Token holding
Feature activation+0.075
Top resid features:
"
Token"
Feature activation+0.027
Top resid features:
instead
Token instead
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.074
Top resid features:
"
Token "
Feature activation+0.049
Top resid features:
likely
Token likely
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.056
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
physical
Token physical
Feature activation+7.631
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
sexual
Token sexual
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
psychological
Token psychological
Feature activation+0.000
Top resid features:
harm
Token harm
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
When
TokenWhen
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.015
Top resid features:
transition
Token transition
Feature activation+0.027
Top resid features:
from
Token from
Feature activation-0.029
Top resid features:
physical
Token physical
Feature activation+8.022
Top resid features:
exchange
Token exchange
Feature activation+0.133
Top resid features:
to
Token to
Feature activation-0.037
Top resid features:
digital
Token digital
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
often
Token often
Feature activation+0.020
Top resid features:
scar
Token scar
Feature activation+0.011
Top resid features:
red
Tokenred
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
physically
Token physically
Feature activation+7.120
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
psychologically
Token psychologically
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Tor
Token Tor
Feature activation+0.016
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
designed
Token designed
Feature activation+0.025
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
physical
Token physical
Feature activation+6.798
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
digital
Token digital
Feature activation+0.241
Top resid features:
anonymity
Token anonymity
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
not
Token not
Feature activation+0.021
Top resid features:
likely
Token likely
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
physical
Token physical
Feature activation+6.221
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
sexual
Token sexual
Feature activation+0.452
Top resid features:
or
Token or
Feature activation+0.030
Top resid features:
psychological
Token psychological
Feature activation+0.000
Top resid features:
harm
Token harm
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
not
Token not
Feature activation+0.008
Top resid features:
so
Token so
Feature activation+0.001
Top resid features:
much
Token much
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
physical
Token physical
Feature activation+5.439
Top resid features:
damage
Token damage
Feature activation+0.113
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
trail
Token trail
Feature activation+0.096
Top resid features:
surface
Token surface
Feature activation+0.132
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Tor
Token Tor
Feature activation+0.024
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
designed
Token designed
Feature activation-0.004
Top resid features:
for
Token for
Feature activation-0.039
Top resid features:
physical
Token physical
Feature activation+5.035
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
digital
Token digital
Feature activation+0.000
Top resid features:
anonymity
Token anonymity
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ment
Token Ment
Feature activation+0.018
Top resid features:
ally
Tokenally
Feature activation+0.478
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
physically
Token physically
Feature activation+4.787
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
looks
Token looks
Feature activation+0.000
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.338
Top resid features:
it
Token it
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.029
Top resid features:
Phys
Token Phys
Feature activation+0.195
Top resid features:
ically
Tokenically
Feature activation+4.967
Top resid features:
and
Token and
Feature activation+0.050
Top resid features:
mentally
Token mentally
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
some
Token some
Feature activation-0.011
Top resid features:
ambiguity
Token ambiguity
Feature activation-0.053
Top resid features:
,"
Token,"
Feature activation-0.001
Top resid features:
using
Token using
Feature activation+0.031
Top resid features:
"
Token "
Feature activation-0.020
Top resid features:
physical
Tokenphysical
Feature activation+5.216
Top resid features:
holding
Token holding
Feature activation+0.060
Top resid features:
"
Token"
Feature activation+0.091
Top resid features:
instead
Token instead
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
suffix
Token suffix
Feature activation-0.005
Top resid features:
PT
Token PT
Feature activation-0.003
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
used
Token used
Feature activation+0.020
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
Physical
Token Physical
Feature activation+4.506
Top resid features:
Ther
Token Ther
Feature activation+0.018
Top resid features:
ap
Tokenap
Feature activation+0.004
Top resid features:
ists
Tokenists
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
denote
Token denote
Feature activation+0.017
Top resid features:
is
Token is
Feature activation+0.019
Top resid features:
not
Token not
Feature activation+0.018
Top resid features:
so
Token so
Feature activation+0.024
Top resid features:
much
Token much
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
physical
Token physical
Feature activation+3.687
Top resid features:
damage
Token damage
Feature activation+0.062
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
trail
Token trail
Feature activation+0.098
Top resid features:
surface
Token surface
Feature activation+0.207
Top resid features:
ature
Tokenature
Feature activation+0.040
Top resid features:
decay
Token decay
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
hard
Token hard
Feature activation+3.526
Top resid features:
sciences
Token sciences
Feature activation+0.269
Top resid features:
such
Token such
Feature activation+0.017
Top resid features:
as
Token as
Feature activation-0.004
Top resid features:
physics
Token physics
Feature activation+0.133
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.07

Head 3: 0.09

Head 4: 0.03

Head 5: 0.05

Head 6: 0.04

Head 7: 0.54

Head 8: 0.03

Head 9: 0.03

Head 10: 0.04

Head 11: 0.03

Positive logits

mental3.59

mental3.49

Virtual3.28

emotional3.19

spiritually3.10

psychological2.99

virtual2.99

psyche2.94

intellectual2.94

Secondly2.88

spiritual2.86

intangible2.85

Mental2.79

secondly2.74

Psy2.65

mentally2.64

emotionally2.60

cognitive2.60

istries2.60

virtual2.59

Negative logits

prev-2.96

prev-2.63

idad-2.61

raw-2.49

Outbreak-2.46

uler-2.33

REC-2.32

Nicol-2.31

een-2.30

redd-2.30

aturday-2.28

Sasuke-2.27

Prev-2.25

today-2.21

ovember-2.20

ifa-2.14

Mubarak-2.09

Yellowstone-2.08

1901-2.08

Mahm-2.08

INTERVAL 7.424 - 8.249
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
in
Token in
Feature activation+0.000
horrible
Token horrible
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+8.217
emotional
Token emotional
Feature activation+0.000
pain
Token pain
Feature activation+0.000
could
Token could
Feature activation+0.000
happen
Token happen
Feature activation+0.000
to
Token to
Feature activation+0.000
555
Token555
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+7.542
perceptual
Token perceptual
Feature activation+0.000
symptoms
Token symptoms
Feature activation+0.000
are
Token are
Feature activation+0.000
currently
Token currently
Feature activation+0.000
stable
Token stable
Feature activation+0.000
stories
Token stories
Feature activation+0.000
they
Token they
Feature activation+0.000
tell
Token tell
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+8.249
verbal
Token verbal
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
and
Token and
Feature activation+0.802
the
Token the
Feature activation+0.853
destructive
Token destructive
Feature activation+0.466
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+7.504
mental
Token mental
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.651
typically
Token typically
Feature activation+0.000
ones
Token ones
Feature activation+0.000

INTERVAL 6.599 - 7.424
CONTAINS 0.001%

physical
Tokenphysical
Feature activation+0.000
holding
Token holding
Feature activation+0.000
"
Token"
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+4.090
"
Token "
Feature activation+7.117
rest
Tokenrest
Feature activation+0.000
raint
Tokenraint
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
physical
Token physical
Feature activation+0.000
or
Token or
Feature activation+7.308
psychological
Token psychological
Feature activation+0.000
condition
Token condition
Feature activation+0.000
of
Token of
Feature activation+0.000
husband
Token husband
Feature activation+0.000
or
Token or
Feature activation+0.206
to
Token to
Feature activation+0.000
result
Token result
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.050
physical
Token physical
Feature activation+0.061
,
Token,
Feature activation+7.095
sexual
Token sexual
Feature activation+0.000
or
Token or
Feature activation+6.043
psychological
Token psychological
Feature activation+0.174
harm
Token harm
Feature activation+0.000
or
Token or
Feature activation+0.969
risk
Token risk
Feature activation+0.000
of
Token of
Feature activation+0.000
death
Token death
Feature activation+0.000
from
Token from
Feature activation+0.000
physical
Token physical
Feature activation+0.000
or
Token or
Feature activation+7.408
psychological
Token psychological
Feature activation+0.000
causes
Token causes
Feature activation+0.000
is
Token is
Feature activation+0.000
significant
Token significant
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
transition
Token transition
Feature activation+0.000
from
Token from
Feature activation+0.000
physical
Token physical
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
to
Token to
Feature activation+7.004
digital
Token digital
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
change
Token change
Feature activation+0.000

INTERVAL 5.774 - 6.599
CONTAINS 0.000%

in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.050
physical
Token physical
Feature activation+0.061
,
Token,
Feature activation+7.095
sexual
Token sexual
Feature activation+0.000
or
Token or
Feature activation+6.043
psychological
Token psychological
Feature activation+0.174
harm
Token harm
Feature activation+0.000
or
Token or
Feature activation+0.969
suffering
Token suffering
Feature activation+0.051
to
Token to
Feature activation+0.012
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+4.921
digital
Token digital
Feature activation+0.000
anonymity
Token anonymity
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+6.124
security
Token security
Feature activation+1.588
and
Token and
Feature activation+0.000
encryption
Token encryption
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
often
Token often
Feature activation+0.000
scar
Token scar
Feature activation+0.000
red
Tokenred
Feature activation+0.000
,
Token,
Feature activation+0.000
physically
Token physically
Feature activation+0.000
and
Token and
Feature activation+6.261
psychologically
Token psychologically
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000

INTERVAL 4.950 - 5.774
CONTAINS 0.000%

repaired
Token repaired
Feature activation+0.023
in
Token in
Feature activation+0.052
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.421
but
Token but
Feature activation+3.251
the
Token the
Feature activation+5.013
effect
Token effect
Feature activation+0.799
this
Token this
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.000
on
Token on
Feature activation+0.010

INTERVAL 4.125 - 4.950
CONTAINS 0.000%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Phys
Token Phys
Feature activation+0.000
ically
Tokenically
Feature activation+0.000
and
Token and
Feature activation+4.147
mentally
Token mentally
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
Tor
Token Tor
Feature activation+0.000
is
Token is
Feature activation+0.000
designed
Token designed
Feature activation+0.000
for
Token for
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+4.921
digital
Token digital
Feature activation+0.000
anonymity
Token anonymity
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+6.124
security
Token security
Feature activation+1.588
.
Token.
Feature activation+0.000
Ment
Token Ment
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
,
Token,
Feature activation+0.000
physically
Token physically
Feature activation+0.000
,
Token,
Feature activation+4.385
he
Token he
Feature activation+0.000
looks
Token looks
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+2.645

INTERVAL 3.300 - 4.125
CONTAINS 0.000%

"
Token "
Feature activation+0.000
physical
Tokenphysical
Feature activation+0.000
holding
Token holding
Feature activation+0.000
"
Token"
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+4.090
"
Token "
Feature activation+7.117
rest
Tokenrest
Feature activation+0.000
raint
Tokenraint
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
their
Token their
Feature activation+0.000
state
Token state
Feature activation+0.000
certification
Token certification
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.185
not
Token not
Feature activation+3.750
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
confused
Token confused
Feature activation+0.000
with
Token with
Feature activation+0.398
D
Token D
Feature activation+0.000

INTERVAL 2.475 - 3.300
CONTAINS 0.001%

front
Token front
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
both
Token both
Feature activation+0.000
with
Token with
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
and
Token and
Feature activation+2.838
software
Token software
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Lead
TokenLead
Feature activation+0.000
ing
Tokening
Feature activation+0.000
is
Token is
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
higher
Token higher
Feature activation+0.000
than
Token than
Feature activation+0.119
that
Token that
Feature activation+0.000
in
Token in
Feature activation+3.201
humanities
Token humanities
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
history
Token history
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+4.385
he
Token he
Feature activation+0.000
looks
Token looks
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+2.645
There
Token There
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
no
Token no
Feature activation+0.588
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
doing
Token doing
Feature activation+0.000
everything
Token everything
Feature activation+0.000
the
Token the
Feature activation+2.744
course
Token course
Feature activation+0.000
requires
Token requires
Feature activation+0.000
manually
Token manually
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
be
Token be
Feature activation+0.000
repaired
Token repaired
Feature activation+0.023
in
Token in
Feature activation+0.052
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.421
but
Token but
Feature activation+3.251
the
Token the
Feature activation+5.013
effect
Token effect
Feature activation+0.799
this
Token this
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 1.650 - 2.475
CONTAINS 0.001%

will
Token will
Feature activation+0.000
explain
Token explain
Feature activation+0.000
the
Token the
Feature activation+0.000
physical
Token physical
Feature activation+0.000
chemistry
Token chemistry
Feature activation+0.000
and
Token and
Feature activation+1.970
ge
Token ge
Feature activation+0.000
omet
Tokenomet
Feature activation+0.000
rical
Tokenrical
Feature activation+0.014
foundations
Token foundations
Feature activation+0.000
of
Token of
Feature activation+0.000
first
Token first
Feature activation+0.000
computer
Token computer
Feature activation+0.000
with
Token with
Feature activation+0.000
native
Token native
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
and
Token and
Feature activation+2.168
software
Token software
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
moments
Token moments
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
h
Tokenh
Feature activation+0.000
verbally
Token verbally
Feature activation+0.000
and
Token and
Feature activation+1.891
physically
Token physically
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
P
Token P
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
as
Token as
Feature activation+0.000
often
Token often
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.540
changed
Token changed
Feature activation+1.661
wives
Token wives
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
hard
Token hard
Feature activation+0.000
cover
Token cover
Feature activation+0.000
versus
Token versus
Feature activation+1.772
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
-
Token-
Feature activation+0.000
Advertisement
Token Advertisement
Feature activation+0.000
-
Token -
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.825 - 1.650
CONTAINS 0.004%

insanity
Token insanity
Feature activation+0.000
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+1.082
over
Token over
Feature activation+0.780
and
Token and
Feature activation+0.000
over
Token over
Feature activation+0.028
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.398
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
represents
Token represents
Feature activation+1.154
society
Token society
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
thri
Token thri
Feature activation+0.000
ves
Tokenves
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
both
Token both
Feature activation+0.000
visually
Token visually
Feature activation+0.000
appealing
Token appealing
Feature activation+0.000
and
Token and
Feature activation+0.910
deliver
Token deliver
Feature activation+0.127
great
Token great
Feature activation+0.197
user
Token user
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
--
Token --
Feature activation+0.000
consistent
Token consistent
Feature activation+0.000
level
Token level
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
and
Token and
Feature activation+0.976
performance
Token performance
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
never
Token never
Feature activation+0.000
seem
Token seem
Feature activation+0.000
to
Token to
Feature activation+0.000
our
Token our
Feature activation+0.000
mail
Token mail
Feature activation+0.000
boxes
Token boxes
Feature activation+0.000
,
Token,
Feature activation+0.036
and
Token and
Feature activation+1.001
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.521
worthwhile
Token worthwhile
Feature activation+0.249
things
Token things
Feature activation+0.267
every
Token every
Feature activation+0.000

INTERVAL 0.000 - 0.825
CONTAINS 99.992%

scrutiny
Token scrutiny
Feature activation+0.000
for
Token for
Feature activation+0.000
pand
Token pand
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Apprentice
Token Apprentice
Feature activation+0.000
boss
Token boss
Feature activation+0.000
,
Token,
Feature activation+0.000
S
Token S
Feature activation+0.000
Trigger
Token Trigger
Feature activation+0.000
warning
Token warning
Feature activation+0.000
-
Token -
Feature activation+0.000
Contains
Token Contains
Feature activation+0.000
references
Token references
Feature activation+0.000
to
Token to
Feature activation+0.000
rape
Token rape
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pain
TokenPain
Feature activation+0.000
ICES
TokenICES
Feature activation+0.000
TER
TokenTER
Feature activation+0.000
/
Token/
Feature activation+0.000
E
TokenE
Feature activation+0.000
VER
TokenVER
Feature activation+0.000
TON
TokenTON
Feature activation+0.000
NBC
Token NBC
Feature activation+0.000
SPORTS
Token SPORTS
Feature activation+0.000
NETWORK
Token NETWORK
Feature activation+0.000
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
Dog
Token Dog
Feature activation+0.000
B
Token B
Feature activation+0.000
ikini
Tokenikini
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Make
TokenMake
Feature activation+0.000
a
Token a
Feature activation+0.000
summer
Token summer
Feature activation+0.000
time
Tokentime
Feature activation+0.000
splash
Token splash
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Using
TokenUsing
Feature activation+0.000
something
Token something
Feature activation+0.000
like
Token like
Feature activation+0.000
a
Token a
Feature activation+0.000
fire
Token fire
Feature activation+0.000
man
Tokenman
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hose
Token hose
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 H9.7: (feature 18097)

TOP ACTIVATIONS
MAX = 5.045

for
Token for
Feature activation+0.000
basic
Token basic
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
,
Token,
Feature activation+0.044
10
Token 10
Feature activation+0.033
for
Token for
Feature activation+5.045
un
Token un
Feature activation+0.000
bur
Tokenbur
Feature activation+0.000
row
Tokenrow
Feature activation+0.000
ed
Tokened
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
regular
Token regular
Feature activation+0.000
season
Token season
Feature activation+0.000
and
Token and
Feature activation+5.015
Stanley
Token Stanley
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
Playoffs
Token Playoffs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
990
Token990
Feature activation+0.000
yen
Token yen
Feature activation+0.000
.
Token.
Feature activation+2.002
The
Token The
Feature activation+4.976
Premium
Token Premium
Feature activation+0.000
Fan
Token Fan
Feature activation+0.000
Box
Token Box
Feature activation+0.000
limited
Token limited
Feature activation+0.000
edition
Token edition
Feature activation+0.000
,
Token,
Feature activation+0.000
med
Token med
Feature activation+0.000
itating
Tokenitating
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+2.483
the
Token the
Feature activation+3.886
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
L
Token L
Feature activation+0.000
PL
TokenPL
Feature activation+0.000
reported
Token reported
Feature activation+0.000
that
Token that
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+3.679
administrative
Token administrative
Feature activation+0.000
expenses
Token expenses
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
stand
Token stand
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
regular
Token regular
Feature activation+0.000
people
Token people
Feature activation+0.000
into
Token into
Feature activation+3.455
Norman
Token Norman
Feature activation+0.000
Te
Token Te
Feature activation+0.000
b
Tokenb
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
and
Token and
Feature activation+0.000
times
Token times
Feature activation+0.000
between
Token between
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
alone
Token alone
Feature activation+0.000
and
Token and
Feature activation+3.316
conventional
Token conventional
Feature activation+1.465
treatment
Token treatment
Feature activation+0.823
plus
Token plus
Feature activation+2.686
fumes
Token fumes
Feature activation+0.000
of
Token of
Feature activation+0.054
abilities
Token abilities
Feature activation+0.000
,
Token,
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
for
Token for
Feature activation+3.297
additional
Token additional
Feature activation+0.000
units
Token units
Feature activation+0.000
hit
Token hit
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
the
Token the
Feature activation+0.000
N
TokenN
Feature activation+0.000
mice
Token mice
Feature activation+0.000
were
Token were
Feature activation+0.000
given
Token given
Feature activation+0.000
normal
Token normal
Feature activation+0.000
or
Token or
Feature activation+3.210
cur
Token cur
Feature activation+0.000
c
Tokenc
Feature activation+0.000
umin
Tokenumin
Feature activation+0.000
supplemented
Token supplemented
Feature activation+0.000
(
Token (
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
match
Token match
Feature activation+0.581
the
Token the
Feature activation+0.795
feelings
Token feelings
Feature activation+0.445
of
Token of
Feature activation+2.975
political
Token political
Feature activation+0.000
pundits
Token pundits
Feature activation+0.000
,
Token,
Feature activation+0.000
lik
Token lik
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
general
Token general
Feature activation+0.000
sense
Token sense
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.312
the
Token the
Feature activation+2.630
more
Token more
Feature activation+2.972
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
karma
Token karma
Feature activation+0.000
is
Token is
Feature activation+0.000
fund
Token fund
Feature activation+0.000
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
220
Token220
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+2.880
from
Token from
Feature activation+1.738
the
Token the
Feature activation+1.127
city
Token city
Feature activation+0.000
's
Token's
Feature activation+1.360
hotel
Token hotel
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
alone
Token alone
Feature activation+0.000
and
Token and
Feature activation+3.316
conventional
Token conventional
Feature activation+1.465
treatment
Token treatment
Feature activation+0.823
plus
Token plus
Feature activation+2.686
fumes
Token fumes
Feature activation+0.000
of
Token of
Feature activation+0.054
tea
Token tea
Feature activation+0.000
tree
Token tree
Feature activation+0.000
essential
Token essential
Feature activation+0.000
production
Token production
Feature activation+0.000
of
Token of
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
,
Token,
Feature activation+0.939
alternative
Token alternative
Feature activation+0.000
and
Token and
Feature activation+2.679
renewable
Token renewable
Feature activation+0.000
sources
Token sources
Feature activation+0.000
of
Token of
Feature activation+0.000
energy
Token energy
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
general
Token general
Feature activation+0.000
sense
Token sense
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.312
the
Token the
Feature activation+2.630
more
Token more
Feature activation+2.972
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
karma
Token karma
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
can
Tokencan
Feature activation+0.000
be
Token be
Feature activation+0.000
written
Token written
Feature activation+0.000
in
Token in
Feature activation+2.591
Polish
Token Polish
Feature activation+0.000
notation
Token notation
Feature activation+0.000
as
Token as
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
remembering
Token remembering
Feature activation+0.000
,
Token,
Feature activation+0.000
med
Token med
Feature activation+0.000
itating
Tokenitating
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+2.483
the
Token the
Feature activation+3.886
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
time
Token time
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
from
Tokenfrom
Feature activation+1.041
something
Token something
Feature activation+1.092
resembling
Token resembling
Feature activation+0.931
more
Token more
Feature activation+2.406
traditional
Token traditional
Feature activation+0.000
temporary
Token temporary
Feature activation+0.000
supports
Token supports
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
next
Token next
Feature activation+0.000
in
Token in
Feature activation+0.000
natural
Token natural
Feature activation+0.000
and
Token and
Feature activation+2.376
intuitive
Token intuitive
Feature activation+0.000
technology
Token technology
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
examined
Token examined
Feature activation+0.000
at
Token at
Feature activation+0.000
baseline
Token baseline
Feature activation+0.000
and
Token and
Feature activation+1.898
again
Token again
Feature activation+1.381
15
Token 15
Feature activation+2.239
-
Token-
Feature activation+0.505
and
Token and
Feature activation+0.000
60
Token 60
Feature activation+0.000
min
Token min
Feature activation+1.143
post
Token post
Feature activation+0.000

Top DFA by src position
MAX = 5.954

GEN
Token GEN
Feature activation-0.003
Top resid features:
ER
TokenER
Feature activation-0.001
Top resid features:
ATION
TokenATION
Feature activation-0.013
Top resid features:
5
Token 5
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.039
Top resid features:
basic
Token basic
Feature activation+5.954
Top resid features:
attacks
Token attacks
Feature activation+0.214
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
10
Token 10
Feature activation-0.025
Top resid features:
for
Token for
Feature activation+0.097
Top resid features:
un
Token un
Feature activation+0.000
Top resid features:
game
Token game
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
both
Token both
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
regular
Token regular
Feature activation+5.674
Top resid features:
season
Token season
Feature activation+0.252
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
Stanley
Token Stanley
Feature activation+0.000
Top resid features:
Cup
Token Cup
Feature activation+0.000
Top resid features:
Playoffs
Token Playoffs
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
standard
Token standard
Feature activation+5.784
Top resid features:
edition
Token edition
Feature activation+0.267
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
cost
Token cost
Feature activation-0.005
Top resid features:
5
Token 5
Feature activation-0.019
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
orship
Tokenorship
Feature activation+0.010
Top resid features:
ing
Tokening
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
In
Token In
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
general
Token general
Feature activation+4.523
Top resid features:
sense
Token sense
Feature activation+0.024
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
can
Token can
Feature activation+0.002
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
understood
Token understood
Feature activation-0.010
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
L
Token L
Feature activation-0.009
Top resid features:
PL
TokenPL
Feature activation+0.108
Top resid features:
reported
Token reported
Feature activation-0.005
Top resid features:
that
Token that
Feature activation-0.008
Top resid features:
general
Token general
Feature activation+4.597
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
administrative
Token administrative
Feature activation+0.000
Top resid features:
expenses
Token expenses
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
turns
Token turns
Feature activation+0.014
Top resid features:
stand
Token stand
Feature activation+0.121
Top resid features:
up
Token up
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
regular
Token regular
Feature activation+4.117
Top resid features:
people
Token people
Feature activation+0.064
Top resid features:
into
Token into
Feature activation+0.046
Top resid features:
Norman
Token Norman
Feature activation+0.000
Top resid features:
Te
Token Te
Feature activation+0.000
Top resid features:
b
Tokenb
Feature activation+0.000
Top resid features:
compare
Token compare
Feature activation-0.016
Top resid features:
wound
Token wound
Feature activation+0.090
Top resid features:
healing
Token healing
Feature activation+0.056
Top resid features:
times
Token times
Feature activation+0.018
Top resid features:
between
Token between
Feature activation-0.008
Top resid features:
conventional
Token conventional
Feature activation+3.739
Top resid features:
treatment
Token treatment
Feature activation+0.111
Top resid features:
alone
Token alone
Feature activation+0.180
Top resid features:
and
Token and
Feature activation+0.070
Top resid features:
conventional
Token conventional
Feature activation+0.000
Top resid features:
treatment
Token treatment
Feature activation+0.000
Top resid features:
GEN
Token GEN
Feature activation-0.000
Top resid features:
ER
TokenER
Feature activation-0.000
Top resid features:
ATION
TokenATION
Feature activation-0.005
Top resid features:
5
Token 5
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
basic
Token basic
Feature activation+3.572
Top resid features:
attacks
Token attacks
Feature activation+0.085
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
10
Token 10
Feature activation-0.005
Top resid features:
for
Token for
Feature activation+0.039
Top resid features:
un
Token un
Feature activation+0.447
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
N
TokenN
Feature activation+0.018
Top resid features:
mice
Token mice
Feature activation+0.030
Top resid features:
were
Token were
Feature activation+0.011
Top resid features:
given
Token given
Feature activation+0.147
Top resid features:
normal
Token normal
Feature activation+3.465
Top resid features:
or
Token or
Feature activation+0.008
Top resid features:
cur
Token cur
Feature activation+0.000
Top resid features:
c
Tokenc
Feature activation+0.000
Top resid features:
umin
Tokenumin
Feature activation+0.000
Top resid features:
supplemented
Token supplemented
Feature activation+0.000
Top resid features:
cha
Tokencha
Feature activation+0.005
Top resid features:
said
Token said
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
feelings
Token feelings
Feature activation-0.007
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
average
Token average
Feature activation+3.561
Top resid features:
Americans
Token Americans
Feature activation+0.500
Top resid features:
don
Token don
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation+0.006
Top resid features:
ña
Tokenña
Feature activation+0.007
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
karma
Token karma
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
general
Token general
Feature activation+3.613
Top resid features:
sense
Token sense
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
In
Token In
Feature activation+0.061
Top resid features:
the
Token the
Feature activation+0.106
Top resid features:
more
Token more
Feature activation+0.006
Top resid features:
39
Token39
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
000
Token000
Feature activation-0.004
Top resid features:
from
Token from
Feature activation+0.065
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
general
Token general
Feature activation+3.462
Top resid features:
fund
Token fund
Feature activation+0.143
Top resid features:
and
Token and
Feature activation+0.041
Top resid features:
$
Token $
Feature activation-0.025
Top resid features:
220
Token220
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
compare
Token compare
Feature activation-0.009
Top resid features:
wound
Token wound
Feature activation+0.116
Top resid features:
healing
Token healing
Feature activation+0.095
Top resid features:
times
Token times
Feature activation+0.023
Top resid features:
between
Token between
Feature activation-0.003
Top resid features:
conventional
Token conventional
Feature activation+2.827
Top resid features:
treatment
Token treatment
Feature activation+0.146
Top resid features:
alone
Token alone
Feature activation+0.126
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
conventional
Token conventional
Feature activation+0.171
Top resid features:
treatment
Token treatment
Feature activation+0.027
Top resid features:
These
Token These
Feature activation+0.010
Top resid features:
activities
Token activities
Feature activation+0.012
Top resid features:
include
Token include
Feature activation+0.010
Top resid features:
production
Token production
Feature activation+0.034
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
conventional
Token conventional
Feature activation+2.757
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
alternative
Token alternative
Feature activation-0.037
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
renewable
Token renewable
Feature activation+0.000
Top resid features:
sources
Token sources
Feature activation+0.000
Top resid features:
ña
Tokenña
Feature activation+0.035
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
karma
Token karma
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
general
Token general
Feature activation+3.244
Top resid features:
sense
Token sense
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
In
Token In
Feature activation+0.188
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
would
Token would
Feature activation+0.003
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
written
Token written
Feature activation-0.002
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
conventional
Token conventional
Feature activation+3.263
Top resid features:
inf
Token inf
Feature activation-0.047
Top resid features:
ix
Tokenix
Feature activation+0.013
Top resid features:
notation
Token notation
Feature activation+0.052
Top resid features:
as
Token as
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
orship
Tokenorship
Feature activation+0.002
Top resid features:
ing
Tokening
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
In
Token In
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
general
Token general
Feature activation+3.229
Top resid features:
sense
Token sense
Feature activation+0.047
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
can
Token can
Feature activation-0.006
Top resid features:
be
Token be
Feature activation+0.005
Top resid features:
understood
Token understood
Feature activation-0.001
Top resid features:
most
Token most
Feature activation+0.002
Top resid features:
people
Token people
Feature activation+0.037
Top resid features:
consider
Token consider
Feature activation+0.009
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
'
Token '
Feature activation-0.006
Top resid features:
basic
Tokenbasic
Feature activation+3.206
Top resid features:
income
Token income
Feature activation+0.182
Top resid features:
'
Token'
Feature activation+0.014
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.005
Top resid features:
that
Tokenthat
Feature activation-0.009
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
next
Token next
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
natural
Token natural
Feature activation+3.103
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
intuitive
Token intuitive
Feature activation+0.000
Top resid features:
technology
Token technology
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
For
Token For
Feature activation+0.000
Top resid features:
Cognitive
Token Cognitive
Feature activation-0.006
Top resid features:
performance
Token performance
Feature activation-0.002
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
examined
Token examined
Feature activation+0.007
Top resid features:
at
Token at
Feature activation-0.012
Top resid features:
baseline
Token baseline
Feature activation+3.251
Top resid features:
and
Token and
Feature activation-0.030
Top resid features:
again
Token again
Feature activation-0.012
Top resid features:
15
Token 15
Feature activation-0.069
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.07

Head 3: 0.08

Head 4: 0.05

Head 5: 0.05

Head 6: 0.03

Head 7: 0.52

Head 8: 0.03

Head 9: 0.03

Head 10: 0.05

Head 11: 0.03

Positive logits

extraordinary3.42

special3.23

special3.22

SPECIAL3.18

Special3.17

xus3.03

extras3.00

exotic2.98

extra2.92

exceptional2.92

videos2.91

specialty2.91

Special2.91

Psy2.86

ZE2.86

specialized2.86

igious2.84

Extra2.80

customized2.73

extra2.72

Negative logits

prev-3.31

cis-2.62

ilet-2.49

................-2.46

plain-2.41

ItemImage-2.36

));-2.30

Plain-2.29

Prev-2.25

baseline-2.22

dayName-2.20

Ct-2.20

aintain-2.18

Population-2.18

before-2.17

predecessor-2.15

empt-2.14

:=-2.13

Earth-2.13

stood-2.13

INTERVAL 4.540 - 5.045
CONTAINS 0.000%

in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
regular
Token regular
Feature activation+0.000
season
Token season
Feature activation+0.000
and
Token and
Feature activation+5.015
Stanley
Token Stanley
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
Playoffs
Token Playoffs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
basic
Token basic
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
,
Token,
Feature activation+0.044
10
Token 10
Feature activation+0.033
for
Token for
Feature activation+5.045
un
Token un
Feature activation+0.000
bur
Tokenbur
Feature activation+0.000
row
Tokenrow
Feature activation+0.000
ed
Tokened
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
990
Token990
Feature activation+0.000
yen
Token yen
Feature activation+0.000
.
Token.
Feature activation+2.002
The
Token The
Feature activation+4.976
Premium
Token Premium
Feature activation+0.000
Fan
Token Fan
Feature activation+0.000
Box
Token Box
Feature activation+0.000
limited
Token limited
Feature activation+0.000
edition
Token edition
Feature activation+0.000

INTERVAL 4.036 - 4.540
CONTAINS 0.000%

INTERVAL 3.531 - 4.036
CONTAINS 0.000%

L
Token L
Feature activation+0.000
PL
TokenPL
Feature activation+0.000
reported
Token reported
Feature activation+0.000
that
Token that
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+3.679
administrative
Token administrative
Feature activation+0.000
expenses
Token expenses
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
,
Token,
Feature activation+0.000
med
Token med
Feature activation+0.000
itating
Tokenitating
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+2.483
the
Token the
Feature activation+3.886
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.027 - 3.531
CONTAINS 0.000%

abilities
Token abilities
Feature activation+0.000
,
Token,
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
for
Token for
Feature activation+3.297
additional
Token additional
Feature activation+0.000
units
Token units
Feature activation+0.000
hit
Token hit
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
the
Token the
Feature activation+0.000
N
TokenN
Feature activation+0.000
mice
Token mice
Feature activation+0.000
were
Token were
Feature activation+0.000
given
Token given
Feature activation+0.000
normal
Token normal
Feature activation+0.000
or
Token or
Feature activation+3.210
cur
Token cur
Feature activation+0.000
c
Tokenc
Feature activation+0.000
umin
Tokenumin
Feature activation+0.000
supplemented
Token supplemented
Feature activation+0.000
(
Token (
Feature activation+0.000
stand
Token stand
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
regular
Token regular
Feature activation+0.000
people
Token people
Feature activation+0.000
into
Token into
Feature activation+3.455
Norman
Token Norman
Feature activation+0.000
Te
Token Te
Feature activation+0.000
b
Tokenb
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
and
Token and
Feature activation+0.000
times
Token times
Feature activation+0.000
between
Token between
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
alone
Token alone
Feature activation+0.000
and
Token and
Feature activation+3.316
conventional
Token conventional
Feature activation+1.465
treatment
Token treatment
Feature activation+0.823
plus
Token plus
Feature activation+2.686
fumes
Token fumes
Feature activation+0.000
of
Token of
Feature activation+0.054

INTERVAL 2.522 - 3.027
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
can
Tokencan
Feature activation+0.000
be
Token be
Feature activation+0.000
written
Token written
Feature activation+0.000
in
Token in
Feature activation+2.591
Polish
Token Polish
Feature activation+0.000
notation
Token notation
Feature activation+0.000
as
Token as
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
fund
Token fund
Feature activation+0.000
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
220
Token220
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+2.880
from
Token from
Feature activation+1.738
the
Token the
Feature activation+1.127
city
Token city
Feature activation+0.000
's
Token's
Feature activation+1.360
hotel
Token hotel
Feature activation+0.000
the
Token the
Feature activation+0.000
general
Token general
Feature activation+0.000
sense
Token sense
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.312
the
Token the
Feature activation+2.630
more
Token more
Feature activation+2.972
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
karma
Token karma
Feature activation+0.000
production
Token production
Feature activation+0.000
of
Token of
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
,
Token,
Feature activation+0.939
alternative
Token alternative
Feature activation+0.000
and
Token and
Feature activation+2.679
renewable
Token renewable
Feature activation+0.000
sources
Token sources
Feature activation+0.000
of
Token of
Feature activation+0.000
energy
Token energy
Feature activation+0.000
,
Token,
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
match
Token match
Feature activation+0.581
the
Token the
Feature activation+0.795
feelings
Token feelings
Feature activation+0.445
of
Token of
Feature activation+2.975
political
Token political
Feature activation+0.000
pundits
Token pundits
Feature activation+0.000
,
Token,
Feature activation+0.000
lik
Token lik
Feature activation+0.000
ening
Tokenening
Feature activation+0.000

INTERVAL 2.018 - 2.522
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
next
Token next
Feature activation+0.000
in
Token in
Feature activation+0.000
natural
Token natural
Feature activation+0.000
and
Token and
Feature activation+2.376
intuitive
Token intuitive
Feature activation+0.000
technology
Token technology
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
system
Token system
Feature activation+0.000
and
Token and
Feature activation+0.000
comp
Token comp
Feature activation+0.000
iles
Tokeniles
Feature activation+0.000
base
Token base
Feature activation+0.000
and
Token and
Feature activation+2.197
some
Token some
Feature activation+1.260
other
Token other
Feature activation+0.000
libraries
Token libraries
Feature activation+0.000
.
Token.
Feature activation+0.000
--
Token --
Feature activation+0.000
time
Token time
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
from
Tokenfrom
Feature activation+1.041
something
Token something
Feature activation+1.092
resembling
Token resembling
Feature activation+0.931
more
Token more
Feature activation+2.406
traditional
Token traditional
Feature activation+0.000
temporary
Token temporary
Feature activation+0.000
supports
Token supports
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
remembering
Token remembering
Feature activation+0.000
,
Token,
Feature activation+0.000
med
Token med
Feature activation+0.000
itating
Tokenitating
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+2.483
the
Token the
Feature activation+3.886
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
examined
Token examined
Feature activation+0.000
at
Token at
Feature activation+0.000
baseline
Token baseline
Feature activation+0.000
and
Token and
Feature activation+1.898
again
Token again
Feature activation+1.381
15
Token 15
Feature activation+2.239
-
Token-
Feature activation+0.505
and
Token and
Feature activation+0.000
60
Token 60
Feature activation+0.000
min
Token min
Feature activation+1.143
post
Token post
Feature activation+0.000

INTERVAL 1.513 - 2.018
CONTAINS 0.001%

minutes
Token minutes
Feature activation+0.000
Cook
Token Cook
Feature activation+0.000
Time
Token Time
Feature activation+0.000
:
Token:
Feature activation+0.000
10
Token 10
Feature activation+0.000
minutes
Token minutes
Feature activation+1.524
Total
Token Total
Feature activation+0.000
Time
Token Time
Feature activation+0.000
:
Token:
Feature activation+0.000
20
Token 20
Feature activation+0.000
minutes
Token minutes
Feature activation+0.119
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
220
Token220
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+2.880
from
Token from
Feature activation+1.738
the
Token the
Feature activation+1.127
city
Token city
Feature activation+0.000
's
Token's
Feature activation+1.360
hotel
Token hotel
Feature activation+0.000
tax
Token tax
Feature activation+0.000
performance
Token performance
Feature activation+0.000
was
Token was
Feature activation+0.000
examined
Token examined
Feature activation+0.000
at
Token at
Feature activation+0.000
baseline
Token baseline
Feature activation+0.000
and
Token and
Feature activation+1.898
again
Token again
Feature activation+1.381
15
Token 15
Feature activation+2.239
-
Token-
Feature activation+0.505
and
Token and
Feature activation+0.000
60
Token 60
Feature activation+0.000
Bal
Token Bal
Feature activation+0.000
och
Tokenoch
Feature activation+0.000
men
Token men
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
some
Token some
Feature activation+1.876
w
Token w
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
ened
Tokenened
Feature activation+0.543
old
Token old
Feature activation+0.000
women
Token women
Feature activation+0.000
assessed
Token assessed
Feature activation+0.000
at
Token at
Feature activation+0.631
baseline
Token baseline
Feature activation+0.000
and
Token and
Feature activation+1.614
then
Token then
Feature activation+0.908
10
Token 10
Feature activation+1.561
-,
Token-,
Feature activation+0.000
35
Token 35
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.000
80
Token 80
Feature activation+0.000

INTERVAL 1.009 - 1.513
CONTAINS 0.006%

ones
Token ones
Feature activation+0.000
and
Token and
Feature activation+0.026
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
12
Token12
Feature activation+0.000
for
Token for
Feature activation+1.151
the
Token the
Feature activation+1.309
larger
Token larger
Feature activation+0.000
ones
Token ones
Feature activation+0.000
.
Token.
Feature activation+0.000
Die
Token Die
Feature activation+0.000
and
Token and
Feature activation+0.000
comp
Token comp
Feature activation+0.000
iles
Tokeniles
Feature activation+0.000
base
Token base
Feature activation+0.000
and
Token and
Feature activation+2.197
some
Token some
Feature activation+1.260
other
Token other
Feature activation+0.000
libraries
Token libraries
Feature activation+0.000
.
Token.
Feature activation+0.000
--
Token --
Feature activation+0.000
prof
Tokenprof
Feature activation+0.000
if
Token if
Feature activation+0.050
their
Token their
Feature activation+0.000
sound
Token sound
Feature activation+0.000
is
Token is
Feature activation+0.175
a
Token a
Feature activation+0.477
more
Token more
Feature activation+1.239
a
Token a
Feature activation+0.000
melting
Token melting
Feature activation+0.000
pot
Token pot
Feature activation+0.000
of
Token of
Feature activation+0.000
influences
Token influences
Feature activation+0.000
covered
Token covered
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
some
Token some
Feature activation+1.227
of
Token of
Feature activation+0.460
the
Token the
Feature activation+1.363
more
Token more
Feature activation+0.252
advanced
Token advanced
Feature activation+0.000
features
Token features
Feature activation+0.000
we
Token we
Feature activation+0.000
transition
Token transition
Feature activation+0.000
from
Token from
Feature activation+0.000
physical
Token physical
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
to
Token to
Feature activation+1.345
digital
Token digital
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
change
Token change
Feature activation+0.000

INTERVAL 0.504 - 1.009
CONTAINS 0.014%

and
Token and
Feature activation+0.000
asset
Token asset
Feature activation+0.000
managers
Token managers
Feature activation+0.000
,
Token,
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
and
Token and
Feature activation+0.718
international
Token international
Feature activation+0.000
,
Token,
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
these
Token these
Feature activation+0.000
find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
line
Token line
Feature activation+0.000
between
Token between
Feature activation+0.000
reality
Token reality
Feature activation+0.000
and
Token and
Feature activation+0.775
fiction
Token fiction
Feature activation+0.000
.
Token.
Feature activation+0.000
Within
Token Within
Feature activation+0.000
the
Token the
Feature activation+0.000
profile
Token profile
Feature activation+0.000
everyday
Token everyday
Feature activation+0.000
functioning
Token functioning
Feature activation+0.000
.
Token.
Feature activation+0.000
Others
Token Others
Feature activation+0.000
manage
Token manage
Feature activation+0.279
better
Token better
Feature activation+0.980
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.275
recognizing
Token recognizing
Feature activation+0.000
the
Token the
Feature activation+0.000
limits
Token limits
Feature activation+0.000
or
Token or
Feature activation+0.000
article
Token article
Feature activation+0.000
in
Token in
Feature activation+0.000
url
Token url
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.856
all
Token all
Feature activation+0.306
these
Token these
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
removed
Token removed
Feature activation+0.000
over
Token over
Feature activation+0.000
time
Token time
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
from
Tokenfrom
Feature activation+1.041
something
Token something
Feature activation+1.092
resembling
Token resembling
Feature activation+0.931
more
Token more
Feature activation+2.406
traditional
Token traditional
Feature activation+0.000
temporary
Token temporary
Feature activation+0.000
supports
Token supports
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.504
CONTAINS 99.977%

,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
two
Token two
Feature activation+0.000
new
Token new
Feature activation+0.000
,
Token,
Feature activation+0.000
important
Token important
Feature activation+0.000
features
Token features
Feature activation+0.000
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
getting
Token getting
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
deserve
Token deserve
Feature activation+0.000
;
Token;
Feature activation+0.000
only
Token only
Feature activation+0.000
12
Token 12
Feature activation+0.000
fall
Token fall
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
T
Token T
Feature activation+0.000
are
Tokenare
Feature activation+0.000
e
Tokene
Feature activation+0.000
Wing
Token Wing
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
they
Token they
Feature activation+0.000
just
Token just
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
stra
Token stra
Feature activation+0.000
ighter
Tokenighter
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
use
Token use
Feature activation+0.000
your
Token your
Feature activation+0.000
new
Token new
Feature activation+0.000
for
Token for
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
,
Token,
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
phones
Token phones
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
âĦ¢
TokenâĦ¢
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H9.7: (feature 2997)

TOP ACTIVATIONS
MAX = 5.975

necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
both
Token both
Feature activation+0.000
big
Token big
Feature activation+0.000
and
Token and
Feature activation+5.975
smaller
Token smaller
Feature activation+0.000
teams
Token teams
Feature activation+0.000
;
Token;
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
representing
Token representing
Feature activation+0.000
both
Token both
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+5.425
small
Token small
Feature activation+0.000
brewers
Token brewers
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
-
Token-
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
ending
Tokenending
Feature activation+0.405
clubs
Token clubs
Feature activation+0.000
towards
Token towards
Feature activation+5.254
the
Token the
Feature activation+5.279
ones
Token ones
Feature activation+1.703
who
Token who
Feature activation+0.111
can
Token can
Feature activation+0.065
spend
Token spend
Feature activation+0.119
wisely
Token wisely
Feature activation+0.000
big
Token big
Feature activation+0.000
-
Token-
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
ending
Tokenending
Feature activation+0.405
clubs
Token clubs
Feature activation+0.000
towards
Token towards
Feature activation+5.254
the
Token the
Feature activation+5.279
ones
Token ones
Feature activation+1.703
who
Token who
Feature activation+0.111
can
Token can
Feature activation+0.065
spend
Token spend
Feature activation+0.119
are
Token are
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
historic
Token historic
Feature activation+0.000
homes
Token homes
Feature activation+0.000
big
Token big
Feature activation+0.000
and
Token and
Feature activation+5.228
small
Token small
Feature activation+0.000
in
Token in
Feature activation+0.000
various
Token various
Feature activation+0.000
styles
Token styles
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
with
Token with
Feature activation+2.891
a
Token a
Feature activation+4.794
small
Token small
Feature activation+0.000
phase
Token phase
Feature activation+0.000
angle
Token angle
Feature activation+0.000
between
Token between
Feature activation+0.000
caloric
Token caloric
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
in
Token in
Feature activation+0.000
towns
Token towns
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+4.220
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
within
Token within
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000
against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
and
Token and
Feature activation+0.170
China
Token China
Feature activation+0.000
,
Token,
Feature activation+1.155
and
Token and
Feature activation+4.217
a
Token a
Feature activation+0.912
half
Token half
Feature activation+0.000
war
Token war
Feature activation+0.181
in
Token in
Feature activation+0.295
Korea
Token Korea
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
nations
Token nations
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+3.621
small
Token small
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
hand
Token hand
Feature activation+0.331
,
Token,
Feature activation+1.386
we
Token we
Feature activation+0.000
have
Token have
Feature activation+3.599
institutional
Token institutional
Feature activation+0.000
investors
Token investors
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
small
Token small
Feature activation+0.000
brewers
Token brewers
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+3.308
imp
Token imp
Feature activation+0.000
orters
Tokenorters
Feature activation+0.000
and
Token and
Feature activation+0.403
industry
Token industry
Feature activation+0.000
suppliers
Token suppliers
Feature activation+0.000
to
Token to
Feature activation+0.000
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
Big
Token Big
Feature activation+0.000
vs
Token vs
Feature activation+3.301
Small
Token Small
Feature activation+0.000
,
Token,
Feature activation+0.000
David
Token David
Feature activation+0.000
vs
Token vs
Feature activation+0.000
G
Token G
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
major
Token major
Feature activation+0.000
events
Token events
Feature activation+0.000
;
Token;
Feature activation+0.170
the
Token the
Feature activation+3.145
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.248
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
more
Token more
Feature activation+0.000
flexibility
Token flexibility
Feature activation+0.000
for
Token for
Feature activation+0.000
navigation
Token navigation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+3.065
they
Token they
Feature activation+0.000
also
Token also
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000
more
Token more
Feature activation+0.000
(
Token (
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
with
Token with
Feature activation+2.891
a
Token a
Feature activation+4.794
small
Token small
Feature activation+0.000
phase
Token phase
Feature activation+0.000
angle
Token angle
Feature activation+0.000
between
Token between
Feature activation+0.000
larger
Token larger
Feature activation+0.000
jars
Token jars
Feature activation+0.000
feel
Token feel
Feature activation+0.000
free
Token free
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+2.705
more
Token more
Feature activation+0.346
salt
Token salt
Feature activation+0.000
but
Token but
Feature activation+0.003
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+0.000
-
Token-
Feature activation+0.000
scale
Tokenscale
Feature activation+0.000
linear
Token linear
Feature activation+0.000
harmonic
Token harmonic
Feature activation+0.000
structure
Token structure
Feature activation+0.000
over
Token over
Feature activation+2.612
the
Token the
Feature activation+0.080
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
sections
Token sections
Feature activation+0.000
and
Token and
Feature activation+0.000
communities
Token communities
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+0.000
global
Token global
Feature activation+0.000
and
Token and
Feature activation+2.611
local
Token local
Feature activation+0.000
scale
Token scale
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
grown
Token grown
Feature activation+0.000
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+2.402
children
Token children
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Take
TokenTake
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
AC
Token AC
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+2.397
smaller
Token smaller
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000

Top DFA by src position
MAX = 6.834

is
Token is
Feature activation+0.003
Top resid features:
necessary
Token necessary
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
benefit
Token benefit
Feature activation-0.027
Top resid features:
both
Token both
Feature activation-0.040
Top resid features:
big
Token big
Feature activation+6.834
Top resid features:
and
Token and
Feature activation+0.048
Top resid features:
smaller
Token smaller
Feature activation+0.000
Top resid features:
teams
Token teams
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
brewing
Token brewing
Feature activation-0.024
Top resid features:
industry
Token industry
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
representing
Token representing
Feature activation-0.013
Top resid features:
both
Token both
Feature activation-0.037
Top resid features:
large
Token large
Feature activation+6.293
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
brewers
Token brewers
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
shifting
Token shifting
Feature activation-0.004
Top resid features:
advantage
Token advantage
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+0.025
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
big
Token big
Feature activation+5.693
Top resid features:
-
Token-
Feature activation+0.108
Top resid features:
sp
Tokensp
Feature activation+0.003
Top resid features:
ending
Tokenending
Feature activation+0.201
Top resid features:
clubs
Token clubs
Feature activation+0.010
Top resid features:
towards
Token towards
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
shifting
Token shifting
Feature activation-0.002
Top resid features:
advantage
Token advantage
Feature activation+0.005
Top resid features:
from
Token from
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
big
Token big
Feature activation+5.712
Top resid features:
-
Token-
Feature activation+0.119
Top resid features:
sp
Tokensp
Feature activation+0.003
Top resid features:
ending
Tokenending
Feature activation+0.106
Top resid features:
clubs
Token clubs
Feature activation+0.013
Top resid features:
towards
Token towards
Feature activation+0.013
Top resid features:
There
Token There
Feature activation-0.003
Top resid features:
are
Token are
Feature activation-0.004
Top resid features:
beautiful
Token beautiful
Feature activation+0.032
Top resid features:
historic
Token historic
Feature activation-0.000
Top resid features:
homes
Token homes
Feature activation-0.007
Top resid features:
big
Token big
Feature activation+5.987
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
various
Token various
Feature activation+0.000
Top resid features:
styles
Token styles
Feature activation+0.000
Top resid features:
participants
Token participants
Feature activation-0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation-0.002
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
large
Token large
Feature activation+5.508
Top resid features:
phase
Token phase
Feature activation+0.075
Top resid features:
angle
Token angle
Feature activation+0.024
Top resid features:
(
Token (
Feature activation+0.005
Top resid features:
time
Tokentime
Feature activation-0.007
Top resid features:
difference
Token difference
Feature activation+0.005
Top resid features:
across
Token across
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
country
Token country
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
towns
Token towns
Feature activation-0.008
Top resid features:
large
Token large
Feature activation+5.002
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
within
Token within
Feature activation+0.000
Top resid features:
a
Tokena
Feature activation+0.001
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
half
Tokenhalf
Feature activation+0.004
Top resid features:
wars
Token wars
Feature activation+0.040
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.024
Top resid features:
big
Tokenbig
Feature activation+4.506
Top resid features:
wars
Token wars
Feature activation+0.101
Top resid features:
against
Token against
Feature activation+0.075
Top resid features:
Russia
Token Russia
Feature activation+0.087
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
China
Token China
Feature activation+0.029
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
women
Token women
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.008
Top resid features:
of
Token of
Feature activation-0.008
Top resid features:
nations
Token nations
Feature activation-0.037
Top resid features:
large
Token large
Feature activation+4.541
Top resid features:
and
Token and
Feature activation-0.032
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.005
Top resid features:
hand
Token hand
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
we
Token we
Feature activation+0.002
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
big
Token big
Feature activation+3.663
Top resid features:
companies
Token companies
Feature activation+0.162
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
predominantly
Token predominantly
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
brewing
Token brewing
Feature activation-0.038
Top resid features:
industry
Token industry
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
representing
Token representing
Feature activation-0.009
Top resid features:
both
Token both
Feature activation-0.012
Top resid features:
large
Token large
Feature activation+4.129
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
small
Token small
Feature activation-0.037
Top resid features:
brewers
Token brewers
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
as
Token as
Feature activation+0.006
Top resid features:
want
Token want
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
talk
Token talk
Feature activation-0.005
Top resid features:
about
Token about
Feature activation+0.013
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
Big
Token Big
Feature activation+4.029
Top resid features:
vs
Token vs
Feature activation+0.070
Top resid features:
Small
Token Small
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
vs
Token vs
Feature activation+0.000
Top resid features:
art
Tokenart
Feature activation+0.008
Top resid features:
sports
Token sports
Feature activation-0.017
Top resid features:
venues
Token venues
Feature activation-0.025
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
The
Token The
Feature activation+0.005
Top resid features:
larger
Token larger
Feature activation+3.879
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
two
Token two
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
want
Token want
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
download
Token download
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
L
Token L
Feature activation-0.012
Top resid features:
arger
Tokenarger
Feature activation+3.659
Top resid features:
areas
Token areas
Feature activation+0.060
Top resid features:
will
Token will
Feature activation+0.035
Top resid features:
give
Token give
Feature activation+0.018
Top resid features:
you
Token you
Feature activation+0.006
Top resid features:
more
Token more
Feature activation+0.038
Top resid features:
participants
Token participants
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation-0.015
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
large
Token large
Feature activation+3.805
Top resid features:
phase
Token phase
Feature activation+0.030
Top resid features:
angle
Token angle
Feature activation+0.005
Top resid features:
(
Token (
Feature activation+0.005
Top resid features:
time
Tokentime
Feature activation-0.014
Top resid features:
difference
Token difference
Feature activation+0.005
Top resid features:
If
Token If
Feature activation+0.004
Top resid features:
you
Token you
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
working
Token working
Feature activation+0.002
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
larger
Token larger
Feature activation+3.229
Top resid features:
jars
Token jars
Feature activation+0.050
Top resid features:
feel
Token feel
Feature activation+0.012
Top resid features:
free
Token free
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
add
Token add
Feature activation+0.046
Top resid features:
theory
Token theory
Feature activation+0.025
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
fine
Token fine
Feature activation-0.007
Top resid features:
for
Token for
Feature activation+0.013
Top resid features:
explain
Token explain
Feature activation+0.001
Top resid features:
large
Token large
Feature activation+3.013
Top resid features:
-
Token-
Feature activation+0.092
Top resid features:
scale
Tokenscale
Feature activation+0.200
Top resid features:
linear
Token linear
Feature activation+0.044
Top resid features:
harmonic
Token harmonic
Feature activation-0.025
Top resid features:
structure
Token structure
Feature activation+0.058
Top resid features:
benefits
Token benefits
Feature activation-0.009
Top resid features:
communities
Token communities
Feature activation-0.030
Top resid features:
on
Token on
Feature activation-0.040
Top resid features:
both
Token both
Feature activation-0.025
Top resid features:
a
Token a
Feature activation-0.032
Top resid features:
global
Token global
Feature activation+3.569
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
local
Token local
Feature activation+0.000
Top resid features:
scale
Token scale
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
propag
Token propag
Feature activation+0.006
Top resid features:
ated
Tokenated
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
among
Token among
Feature activation-0.012
Top resid features:
grown
Token grown
Feature activation+2.786
Top resid features:
-
Token-
Feature activation+0.058
Top resid features:
ups
Tokenups
Feature activation+0.091
Top resid features:
as
Token as
Feature activation+0.010
Top resid features:
well
Token well
Feature activation+0.009
Top resid features:
as
Token as
Feature activation-0.008
Top resid features:
two
Token two
Feature activation-0.028
Top resid features:
device
Token device
Feature activation-0.020
Top resid features:
boxes
Token boxes
Feature activation-0.016
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
larger
Token larger
Feature activation+3.394
Top resid features:
one
Token one
Feature activation-0.010
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
AC
Token AC
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.06

Head 3: 0.07

Head 4: 0.03

Head 5: 0.04

Head 6: 0.05

Head 7: 0.52

Head 8: 0.02

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

smaller4.78

small4.51

smallest4.35

small4.33

tiny3.86

Small3.85

tiny3.82

lesser3.80

Small3.61

minimal3.54

humble3.51

modest3.49

quieter3.49

little3.48

manageable3.45

Minor3.41

little3.40

quiet3.32

slow3.31

scattered3.28

Negative logits

Trafford-2.62

osis-2.61

wagen-2.39

Vision-2.35

htaking-2.34

••-2.30

azeera-2.29

EDITION-2.25

webkit-2.25

UTC-2.23

erection-2.22

Psychiatric-2.21

hammad-2.21

GOODMAN-2.17

itri-2.16

osate-2.15

Offensive-2.14

Ramsay-2.14

Almighty-2.12

ERROR-2.11

INTERVAL 5.377 - 5.975
CONTAINS 0.000%

necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
both
Token both
Feature activation+0.000
big
Token big
Feature activation+0.000
and
Token and
Feature activation+5.975
smaller
Token smaller
Feature activation+0.000
teams
Token teams
Feature activation+0.000
;
Token;
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
representing
Token representing
Feature activation+0.000
both
Token both
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+5.425
small
Token small
Feature activation+0.000
brewers
Token brewers
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000

INTERVAL 4.780 - 5.377
CONTAINS 0.000%

are
Token are
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
historic
Token historic
Feature activation+0.000
homes
Token homes
Feature activation+0.000
big
Token big
Feature activation+0.000
and
Token and
Feature activation+5.228
small
Token small
Feature activation+0.000
in
Token in
Feature activation+0.000
various
Token various
Feature activation+0.000
styles
Token styles
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
with
Token with
Feature activation+2.891
a
Token a
Feature activation+4.794
small
Token small
Feature activation+0.000
phase
Token phase
Feature activation+0.000
angle
Token angle
Feature activation+0.000
between
Token between
Feature activation+0.000
caloric
Token caloric
Feature activation+0.000
big
Token big
Feature activation+0.000
-
Token-
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
ending
Tokenending
Feature activation+0.405
clubs
Token clubs
Feature activation+0.000
towards
Token towards
Feature activation+5.254
the
Token the
Feature activation+5.279
ones
Token ones
Feature activation+1.703
who
Token who
Feature activation+0.111
can
Token can
Feature activation+0.065
spend
Token spend
Feature activation+0.119
-
Token-
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
ending
Tokenending
Feature activation+0.405
clubs
Token clubs
Feature activation+0.000
towards
Token towards
Feature activation+5.254
the
Token the
Feature activation+5.279
ones
Token ones
Feature activation+1.703
who
Token who
Feature activation+0.111
can
Token can
Feature activation+0.065
spend
Token spend
Feature activation+0.119
wisely
Token wisely
Feature activation+0.000

INTERVAL 4.182 - 4.780
CONTAINS 0.000%

against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
and
Token and
Feature activation+0.170
China
Token China
Feature activation+0.000
,
Token,
Feature activation+1.155
and
Token and
Feature activation+4.217
a
Token a
Feature activation+0.912
half
Token half
Feature activation+0.000
war
Token war
Feature activation+0.181
in
Token in
Feature activation+0.295
Korea
Token Korea
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
in
Token in
Feature activation+0.000
towns
Token towns
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+4.220
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
within
Token within
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000

INTERVAL 3.585 - 4.182
CONTAINS 0.000%

the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
hand
Token hand
Feature activation+0.331
,
Token,
Feature activation+1.386
we
Token we
Feature activation+0.000
have
Token have
Feature activation+3.599
institutional
Token institutional
Feature activation+0.000
investors
Token investors
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
nations
Token nations
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+3.621
small
Token small
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.987 - 3.585
CONTAINS 0.001%

to
Token to
Feature activation+0.000
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
Big
Token Big
Feature activation+0.000
vs
Token vs
Feature activation+3.301
Small
Token Small
Feature activation+0.000
,
Token,
Feature activation+0.000
David
Token David
Feature activation+0.000
vs
Token vs
Feature activation+0.000
G
Token G
Feature activation+0.000
small
Token small
Feature activation+0.000
brewers
Token brewers
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+3.308
imp
Token imp
Feature activation+0.000
orters
Tokenorters
Feature activation+0.000
and
Token and
Feature activation+0.403
industry
Token industry
Feature activation+0.000
suppliers
Token suppliers
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
major
Token major
Feature activation+0.000
events
Token events
Feature activation+0.000
;
Token;
Feature activation+0.170
the
Token the
Feature activation+3.145
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.248
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
more
Token more
Feature activation+0.000
flexibility
Token flexibility
Feature activation+0.000
for
Token for
Feature activation+0.000
navigation
Token navigation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+3.065
they
Token they
Feature activation+0.000
also
Token also
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000
more
Token more
Feature activation+0.000

INTERVAL 2.390 - 2.987
CONTAINS 0.001%

grown
Token grown
Feature activation+0.000
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+2.402
children
Token children
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Take
TokenTake
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
AC
Token AC
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+2.397
smaller
Token smaller
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
larger
Token larger
Feature activation+0.000
jars
Token jars
Feature activation+0.000
feel
Token feel
Feature activation+0.000
free
Token free
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+2.705
more
Token more
Feature activation+0.346
salt
Token salt
Feature activation+0.000
but
Token but
Feature activation+0.003
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+0.000
(
Token (
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
with
Token with
Feature activation+2.891
a
Token a
Feature activation+4.794
small
Token small
Feature activation+0.000
phase
Token phase
Feature activation+0.000
angle
Token angle
Feature activation+0.000
between
Token between
Feature activation+0.000
-
Token-
Feature activation+0.000
scale
Tokenscale
Feature activation+0.000
linear
Token linear
Feature activation+0.000
harmonic
Token harmonic
Feature activation+0.000
structure
Token structure
Feature activation+0.000
over
Token over
Feature activation+2.612
the
Token the
Feature activation+0.080
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
sections
Token sections
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.792 - 2.390
CONTAINS 0.002%

big
Token big
Feature activation+0.380
and
Token and
Feature activation+1.002
small
Token small
Feature activation+0.405
would
Token would
Feature activation+0.919
be
Token be
Feature activation+0.851
too
Token too
Feature activation+1.880
small
Token small
Feature activation+0.129
...
Token...
Feature activation+0.000
Also
Token Also
Feature activation+0.000
ships
Token ships
Feature activation+0.000
super
Token super
Feature activation+0.000
great
Token great
Feature activation+0.000
(
Token (
Feature activation+0.000
John
TokenJohn
Feature activation+0.000
Woo
Token Woo
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+2.218
awful
Token awful
Feature activation+0.169
(
Token (
Feature activation+0.000
Michael
TokenMichael
Feature activation+0.000
Bay
Token Bay
Feature activation+0.000
)
Token)
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
orders
Token orders
Feature activation+0.000
,
Token,
Feature activation+0.000
explicit
Token explicit
Feature activation+0.000
or
Token or
Feature activation+1.918
implicit
Token implicit
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
kill
Token kill
Feature activation+0.000
their
Token their
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
budget
Token budget
Feature activation+0.000
blueprint
Token blueprint
Feature activation+0.000
in
Token in
Feature activation+0.000
favor
Token favor
Feature activation+0.463
of
Token of
Feature activation+1.884
a
Token a
Feature activation+2.044
simpler
Token simpler
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
masks
Token masks
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
for
Token for
Feature activation+0.000
others
Token others
Feature activation+1.532
a
Token a
Feature activation+1.819
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
edged
Tokenedged
Feature activation+0.000
mask
Token mask
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 1.195 - 1.792
CONTAINS 0.005%

body
Token body
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.433
is
Token is
Feature activation+1.486
actually
Token actually
Feature activation+1.487
composed
Token composed
Feature activation+1.254
of
Token of
Feature activation+1.168
many
Token many
Feature activation+0.593
tiny
Token tiny
Feature activation+0.168
cells
Token cells
Feature activation+0.000
,
Token,
Feature activation+0.000
welcome
Token welcome
Feature activation+0.000
increase
Token increase
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
hot
Token hot
Feature activation+0.000
and
Token and
Feature activation+1.242
cold
Token cold
Feature activation+0.000
cere
Token cere
Feature activation+0.000
als
Tokenals
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
speed
Token speed
Feature activation+0.000
thorough
Token thorough
Feature activation+0.000
fare
Tokenfare
Feature activation+0.000
into
Token into
Feature activation+1.487
a
Token a
Feature activation+1.717
slower
Token slower
Feature activation+0.485
moving
Token moving
Feature activation+0.135
bou
Token bou
Feature activation+0.000
levard
Tokenlevard
Feature activation+0.000
effect
Token effect
Feature activation+0.000
likely
Token likely
Feature activation+0.000
be
Token be
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.205
even
Token even
Feature activation+0.601
subject
Token subject
Feature activation+0.000
to
Token to
Feature activation+0.395
the
Token the
Feature activation+0.000
sort
Token sort
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
real
Token real
Feature activation+0.000
estate
Token estate
Feature activation+0.000
major
Token major
Feature activation+0.000
and
Token and
Feature activation+1.196
six
Token six
Feature activation+0.585
of
Token of
Feature activation+0.823
its
Token its
Feature activation+0.000
top
Token top
Feature activation+0.000
executives
Token executives
Feature activation+0.000

INTERVAL 0.597 - 1.195
CONTAINS 0.016%

inational
Tokeninational
Feature activation+0.000
s
Tokens
Feature activation+0.000
can
Token can
Feature activation+0.000
divert
Token divert
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.842
lower
Token lower
Feature activation+0.000
-
Token-
Feature activation+0.000
tax
Tokentax
Feature activation+0.000
jurisdictions
Token jurisdictions
Feature activation+0.000
by
Token by
Feature activation+0.000
relationships
Token relationships
Feature activation+0.000
between
Token between
Feature activation+0.000
celebrity
Token celebrity
Feature activation+0.000
fathers
Token fathers
Feature activation+0.000
and
Token and
Feature activation+0.634
their
Token their
Feature activation+0.687
children
Token children
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
the
Token the
Feature activation+0.000
pancakes
Token pancakes
Feature activation+0.000
so
Token so
Feature activation+0.000
he
Token he
Feature activation+0.000
opted
Token opted
Feature activation+0.000
for
Token for
Feature activation+0.877
that
Token that
Feature activation+0.000
,'
Token,'
Feature activation+0.000
explained
Token explained
Feature activation+0.000
inn
Token inn
Feature activation+0.000
manager
Token manager
Feature activation+0.000
or
Tokenor
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.892
the
Token the
Feature activation+1.278
"
Token "
Feature activation+0.000
sub
Tokensub
Feature activation+0.000
par
Tokenpar
Feature activation+0.000
"
Token"
Feature activation+0.000
wealthy
Token wealthy
Feature activation+0.000
,
Token,
Feature activation+0.000
yet
Token yet
Feature activation+0.000
pushed
Token pushed
Feature activation+0.000
upon
Token upon
Feature activation+0.572
the
Token the
Feature activation+1.096
working
Token working
Feature activation+0.000
classes
Token classes
Feature activation+0.000
who
Token who
Feature activation+0.000
simply
Token simply
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000

INTERVAL 0.000 - 0.597
CONTAINS 99.975%

Beast
Token Beast
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
things
Token things
Feature activation+0.000
.
Token.
Feature activation+0.000
Right
Token Right
Feature activation+0.000
now
Token now
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
anything
Token anything
Feature activation+0.000
was
Token was
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
"
Token"
Feature activation+0.000
T
TokenT
Feature activation+0.000
od
Tokenod
Feature activation+0.000
s
Tokens
Feature activation+0.000
tutorial
Token tutorial
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
people
Token people
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Captain
Token Captain
Feature activation+0.000
Marvel
Token Marvel
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
story
Token story
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
usp
Tokenusp
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 H9.7: (feature 14110)

TOP ACTIVATIONS
MAX = 7.669

how
Token how
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
the
Token the
Feature activation+0.000
probabilities
Token probabilities
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+7.669
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
injuries
Token injuries
Feature activation+0.000
result
Token result
Feature activation+0.000
from
Token from
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
.
Token.
Feature activation+7.621
The
Token The
Feature activation+1.040
brain
Token brain
Feature activation+0.000
floats
Token floats
Feature activation+0.000
in
Token in
Feature activation+0.000
fluid
Token fluid
Feature activation+0.000
skin
Token skin
Feature activation+0.000
remains
Token remains
Feature activation+0.000
in
Token in
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
condition
Token condition
Feature activation+0.000
.
Token.
Feature activation+7.410
Similarly
Token Similarly
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
brain
Token brain
Feature activation+0.000
can
Token can
Feature activation+0.000
sure
Token sure
Feature activation+0.000
what
Token what
Feature activation+0.000
a
Token a
Feature activation+0.000
form
Token form
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+7.167
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
First
Token First
Feature activation+0.000
we
Token we
Feature activation+0.009
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+7.124
Then
Token Then
Feature activation+0.605
we
Token we
Feature activation+0.309
compute
Token compute
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
a
Token a
Feature activation+0.000
century
Token century
Feature activation+0.000
of
Token of
Feature activation+0.000
futile
Token futile
Feature activation+0.000
warfare
Token warfare
Feature activation+0.000
.
Token.
Feature activation+7.082
Also
Token Also
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
Gear
Token Gear
Feature activation+0.000
different
Token different
Feature activation+0.000
sectors
Token sectors
Feature activation+0.000
of
Token of
Feature activation+0.000
Argentine
Token Argentine
Feature activation+0.000
society
Token society
Feature activation+0.000
;
Token;
Feature activation+7.050
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
their
Token their
Feature activation+0.000
Ju
Token Ju
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
en
Tokenen
Feature activation+0.000
Club
Token Club
Feature activation+0.000
.
Token.
Feature activation+6.910
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
older
Token older
Feature activation+0.000
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
perceived
Token perceived
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
.
Token.
Feature activation+6.901
Case
Token Case
Feature activation+0.000
in
Token in
Feature activation+0.000
point
Token point
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
appropriation
Token appropriation
Feature activation+0.000
too
Token too
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+6.540
And
Token And
Feature activation+6.751
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
slack
Token slack
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
in
Token in
Feature activation+0.000
fluid
Token fluid
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
skull
Token skull
Feature activation+0.000
.
Token.
Feature activation+6.657
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
is
Token is
Feature activation+0.000
snapped
Token snapped
Feature activation+0.000
from
Token from
Feature activation+0.000
Box
Token Box
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
device
Token device
Feature activation+0.000
.
Token.
Feature activation+6.640
This
Token This
Feature activation+0.000
feature
Token feature
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
for
Token for
Feature activation+0.000
one
Token one
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
appropriation
Token appropriation
Feature activation+0.000
too
Token too
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+6.540
And
Token And
Feature activation+6.751
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
slack
Token slack
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+0.000
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+6.359
Secondly
Token Secondly
Feature activation+0.000
,
Token,
Feature activation+0.047
America
Token America
Feature activation+0.000
already
Token already
Feature activation+0.000
sees
Token sees
Feature activation+0.000
is
Token is
Feature activation+0.000
behind
Token behind
Feature activation+0.000
Lum
Token Lum
Feature activation+0.000
en
Tokenen
Feature activation+0.000
View
Token View
Feature activation+0.000
.
Token.
Feature activation+6.314
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
Find
Token Find
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Best
TokenBest
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
leads
Token leads
Feature activation+0.000
to
Token to
Feature activation+0.000
conviction
Token conviction
Feature activation+0.000
.
Token.
Feature activation+6.217
As
Token As
Feature activation+0.000
an
Token an
Feature activation+0.000
analogy
Token analogy
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
library
Token library
Feature activation+0.000
).
Token).
Feature activation+6.193
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.870
Qu
TokenQu
Feature activation+0.000
eries
Tokeneries
Feature activation+0.000
return
Token return
Feature activation+0.000
ancestors
Token ancestors
Feature activation+0.000
never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
they
Token they
Feature activation+0.000
needed
Token needed
Feature activation+0.000
.
Token.
Feature activation+6.083
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
rend
Token rend
Feature activation+0.000
ezvous
Tokenezvous
Feature activation+0.000
point
Token point
Feature activation+0.000
.
Token.
Feature activation+6.036
An
Token An
Feature activation+0.023
onym
Tokenonym
Feature activation+0.000
ously
Tokenously
Feature activation+0.000
,
Token,
Feature activation+0.641
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.000
documents
Token documents
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
road
Token road
Feature activation+0.000
.
Token.
Feature activation+6.019
In
Token In
Feature activation+0.444
addition
Token addition
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
added
Token added
Feature activation+0.000

Top DFA by src position
MAX = 8.316

<|endoftext|>
Token<|endoftext|>
Feature activation+0.261
Top resid features:
there
Token there
Feature activation+0.008
Top resid features:
are
Token are
Feature activation+0.009
Top resid features:
caveats
Token caveats
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
First
Token First
Feature activation+8.316
Top resid features:
,
Token,
Feature activation+0.138
Top resid features:
who
Token who
Feature activation-0.000
Top resid features:
knows
Token knows
Feature activation+0.001
Top resid features:
how
Token how
Feature activation-0.002
Top resid features:
accurate
Token accurate
Feature activation+0.003
Top resid features:
have
Token have
Feature activation+0.005
Top resid features:
some
Token some
Feature activation-0.000
Top resid features:
technological
Token technological
Feature activation+0.003
Top resid features:
limitations
Token limitations
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
First
Token First
Feature activation+8.236
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
many
Token many
Feature activation-0.025
Top resid features:
head
Token head
Feature activation-0.002
Top resid features:
injuries
Token injuries
Feature activation+0.027
Top resid features:
result
Token result
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.003
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
technological
Token technological
Feature activation+0.003
Top resid features:
limitations
Token limitations
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
First
Token First
Feature activation+8.032
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
many
Token many
Feature activation-0.008
Top resid features:
head
Token head
Feature activation+0.005
Top resid features:
injuries
Token injuries
Feature activation+0.013
Top resid features:
result
Token result
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
ve
Tokenve
Feature activation+0.000
Top resid features:
looked
Token looked
Feature activation-0.001
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
First
Token First
Feature activation+7.797
Top resid features:
,
Token,
Feature activation+0.088
Top resid features:
they
Token they
Feature activation+0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
re
Tokenre
Feature activation+0.008
Top resid features:
by
Token by
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
following
Token following
Feature activation+0.006
Top resid features:
process
Token process
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
First
Token First
Feature activation+7.464
Top resid features:
we
Token we
Feature activation+0.285
Top resid features:
guess
Token guess
Feature activation+0.114
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.080
Top resid features:
Then
Token Then
Feature activation+0.000
Top resid features:
troubled
Token troubled
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.015
Top resid features:
larger
Token larger
Feature activation-0.015
Top resid features:
issues
Token issues
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
First
Token First
Feature activation+7.653
Top resid features:
,
Token,
Feature activation+0.114
Top resid features:
he
Token he
Feature activation+0.032
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
concerned
Token concerned
Feature activation+0.006
Top resid features:
by
Token by
Feature activation-0.011
Top resid features:
Camb
Token Camb
Feature activation+0.005
Top resid features:
iem
Tokeniem
Feature activation-0.000
Top resid features:
os
Tokenos
Feature activation+0.003
Top resid features:
project
Token project
Feature activation-0.002
Top resid features:
:
Token:
Feature activation+0.025
Top resid features:
first
Token first
Feature activation+6.505
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
foremost
Token foremost
Feature activation+1.367
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
build
Token build
Feature activation+0.022
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
shot
Token shot
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
hell
Token hell
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
First
Token First
Feature activation+7.350
Top resid features:
there
Token there
Feature activation+0.144
Top resid features:
's
Token's
Feature activation+0.082
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
N
Token N
Feature activation+0.015
Top resid features:
ats
Tokenats
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
couple
Token couple
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
reasons
Token reasons
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
First
Token First
Feature activation+6.748
Top resid features:
of
Token of
Feature activation+0.415
Top resid features:
all
Token all
Feature activation+0.280
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
sheer
Token sheer
Feature activation-0.002
Top resid features:
athleticism
Token athleticism
Feature activation+0.049
Top resid features:
wrong
Token wrong
Feature activation-0.000
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
both
Token both
Feature activation-0.003
Top resid features:
counts
Token counts
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
First
Token First
Feature activation+7.248
Top resid features:
,
Token,
Feature activation+0.168
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
other
Token other
Feature activation+0.015
Top resid features:
members
Token members
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
have
Token have
Feature activation+0.001
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
technological
Token technological
Feature activation+0.002
Top resid features:
limitations
Token limitations
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
First
Token First
Feature activation+7.332
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
many
Token many
Feature activation-0.013
Top resid features:
head
Token head
Feature activation+0.003
Top resid features:
injuries
Token injuries
Feature activation+0.016
Top resid features:
result
Token result
Feature activation+0.001
Top resid features:
several
Token several
Feature activation-0.000
Top resid features:
highly
Token highly
Feature activation+0.001
Top resid features:
requested
Token requested
Feature activation-0.001
Top resid features:
features
Token features
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
First
Token First
Feature activation+7.170
Top resid features:
,
Token,
Feature activation+0.233
Top resid features:
we
Token we
Feature activation+0.046
Top resid features:
added
Token added
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
ability
Token ability
Feature activation+0.003
Top resid features:
wrong
Token wrong
Feature activation-0.000
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
both
Token both
Feature activation-0.001
Top resid features:
counts
Token counts
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
First
Token First
Feature activation+7.083
Top resid features:
,
Token,
Feature activation+0.165
Top resid features:
the
Token the
Feature activation+0.075
Top resid features:
other
Token other
Feature activation+0.018
Top resid features:
members
Token members
Feature activation+0.010
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
flag
Token flag
Feature activation-0.002
Top resid features:
off
Token off
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
floor
Token floor
Feature activation-0.009
Top resid features:
!
Token!
Feature activation+0.002
Top resid features:
First
Token First
Feature activation+6.249
Top resid features:
off
Token off
Feature activation+0.826
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
it
Token it
Feature activation+0.027
Top resid features:
's
Token's
Feature activation+0.024
Top resid features:
not
Token not
Feature activation+0.021
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
couple
Token couple
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
problems
Token problems
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
First
Token First
Feature activation+6.916
Top resid features:
,
Token,
Feature activation+0.147
Top resid features:
his
Token his
Feature activation+0.016
Top resid features:
idea
Token idea
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
what
Token what
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
First
TokenFirst
Feature activation+6.556
Top resid features:
,
Token,
Feature activation+0.223
Top resid features:
who
Token who
Feature activation-0.016
Top resid features:
is
Token is
Feature activation-0.005
Top resid features:
being
Token being
Feature activation+0.004
Top resid features:
killed
Token killed
Feature activation+0.039
Top resid features:
our
Token our
Feature activation+0.043
Top resid features:
public
Token public
Feature activation+0.009
Top resid features:
GitHub
Token GitHub
Feature activation+0.005
Top resid features:
repository
Token repository
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
First
Token First
Feature activation+6.986
Top resid features:
make
Token make
Feature activation+0.109
Top resid features:
sure
Token sure
Feature activation+0.049
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
set
Token set
Feature activation+0.009
Top resid features:
up
Token up
Feature activation+0.003
Top resid features:
all
Token all
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
human
Token human
Feature activation+0.000
Top resid features:
labor
Token labor
Feature activation+0.009
Top resid features:
?
Token?
Feature activation+0.009
Top resid features:
First
Token First
Feature activation+6.683
Top resid features:
we
Token we
Feature activation+0.191
Top resid features:
raised
Token raised
Feature activation+0.010
Top resid features:
living
Token living
Feature activation+0.007
Top resid features:
standards
Token standards
Feature activation+0.009
Top resid features:
(
Token (
Feature activation+0.005
Top resid features:
anonymity
Token anonymity
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
extreme
Token extreme
Feature activation-0.004
Top resid features:
levels
Token levels
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
First
Token First
Feature activation+6.071
Top resid features:
,
Token,
Feature activation+0.266
Top resid features:
their
Token their
Feature activation+0.025
Top resid features:
clients
Token clients
Feature activation+0.048
Top resid features:
approach
Token approach
Feature activation+0.135
Top resid features:
Tor
Token Tor
Feature activation+0.020
Top resid features:
several
Token several
Feature activation+0.000
Top resid features:
highly
Token highly
Feature activation+0.004
Top resid features:
requested
Token requested
Feature activation-0.001
Top resid features:
features
Token features
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
First
Token First
Feature activation+6.590
Top resid features:
,
Token,
Feature activation+0.180
Top resid features:
we
Token we
Feature activation+0.075
Top resid features:
added
Token added
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
ability
Token ability
Feature activation-0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.11

Head 2: 0.02

Head 3: 0.04

Head 4: 0.07

Head 5: 0.04

Head 6: 0.04

Head 7: 0.52

Head 8: 0.02

Head 9: 0.03

Head 10: 0.05

Head 11: 0.03

Positive logits

Second7.88

Secondly7.21

secondly6.88

second6.86

Second6.83

second6.82

Secondly6.73

Next4.29

then4.22

later3.96

Then3.90

sec3.86

Next3.79

third3.74

later3.69

Third3.62

nd3.56

Then3.52

fifth3.37

third3.37

Negative logits

hetical-2.48

unciation-2.44

oji-2.35

webkit-2.32

-2.30

=-=--2.23

imation-2.21

AST-2.21

oubted-2.20

aped-2.20

Dwell-2.18

ItemLevel-2.16

utenberg-2.13

arel-2.08

oj-2.06

hub-2.05

cial-2.05

unci-2.03

ibo-2.02

045-2.00

INTERVAL 6.902 - 7.669
CONTAINS 0.001%

how
Token how
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
the
Token the
Feature activation+0.000
probabilities
Token probabilities
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+7.669
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
First
Token First
Feature activation+0.000
we
Token we
Feature activation+0.009
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+7.124
Then
Token Then
Feature activation+0.605
we
Token we
Feature activation+0.309
compute
Token compute
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
a
Token a
Feature activation+0.000
century
Token century
Feature activation+0.000
of
Token of
Feature activation+0.000
futile
Token futile
Feature activation+0.000
warfare
Token warfare
Feature activation+0.000
.
Token.
Feature activation+7.082
Also
Token Also
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
Gear
Token Gear
Feature activation+0.000
their
Token their
Feature activation+0.000
Ju
Token Ju
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
en
Tokenen
Feature activation+0.000
Club
Token Club
Feature activation+0.000
.
Token.
Feature activation+6.910
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
older
Token older
Feature activation+0.000
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
skin
Token skin
Feature activation+0.000
remains
Token remains
Feature activation+0.000
in
Token in
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
condition
Token condition
Feature activation+0.000
.
Token.
Feature activation+7.410
Similarly
Token Similarly
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
brain
Token brain
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 6.135 - 6.902
CONTAINS 0.001%

perceived
Token perceived
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
.
Token.
Feature activation+6.901
Case
Token Case
Feature activation+0.000
in
Token in
Feature activation+0.000
point
Token point
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
fluid
Token fluid
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
skull
Token skull
Feature activation+0.000
.
Token.
Feature activation+6.657
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
is
Token is
Feature activation+0.000
snapped
Token snapped
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+0.000
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+6.359
Secondly
Token Secondly
Feature activation+0.000
,
Token,
Feature activation+0.047
America
Token America
Feature activation+0.000
already
Token already
Feature activation+0.000
sees
Token sees
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
library
Token library
Feature activation+0.000
).
Token).
Feature activation+6.193
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.870
Qu
TokenQu
Feature activation+0.000
eries
Tokeneries
Feature activation+0.000
return
Token return
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
leads
Token leads
Feature activation+0.000
to
Token to
Feature activation+0.000
conviction
Token conviction
Feature activation+0.000
.
Token.
Feature activation+6.217
As
Token As
Feature activation+0.000
an
Token an
Feature activation+0.000
analogy
Token analogy
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000

INTERVAL 5.368 - 6.135
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
event
Token event
Feature activation+0.000
:
Token:
Feature activation+0.990
Ċ
TokenĊ
Feature activation+1.579
Ċ
TokenĊ
Feature activation+5.569
All
TokenAll
Feature activation+0.000
the
Token the
Feature activation+0.000
heroes
Token heroes
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
key
Token key
Feature activation+0.000
documents
Token documents
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
road
Token road
Feature activation+0.000
.
Token.
Feature activation+6.019
In
Token In
Feature activation+0.444
addition
Token addition
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
added
Token added
Feature activation+0.000
be
Token be
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
and
Token and
Feature activation+0.000
abundant
Token abundant
Feature activation+0.000
.
Token.
Feature activation+3.359
The
Token The
Feature activation+5.403
second
Token second
Feature activation+0.000
basket
Token basket
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
etic
Tokenetic
Feature activation+0.000
acid
Token acid
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+1.528
breathe
Token breathe
Feature activation+0.000
),
Token),
Feature activation+5.542
with
Token with
Feature activation+2.328
the
Token the
Feature activation+0.493
fragments
Token fragments
Feature activation+0.000
bearing
Token bearing
Feature activation+0.000
the
Token the
Feature activation+0.000
ancestors
Token ancestors
Feature activation+0.000
never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
they
Token they
Feature activation+0.000
needed
Token needed
Feature activation+0.000
.
Token.
Feature activation+6.083
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 4.601 - 5.368
CONTAINS 0.001%

first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
full
Token full
Feature activation+0.000
fitness
Token fitness
Feature activation+0.025
and
Token and
Feature activation+4.912
then
Token then
Feature activation+0.000
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
bike
Token bike
Feature activation+0.000
step
Token step
Feature activation+0.220
Systems
Token Systems
Feature activation+0.000
filament
Token filament
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Cube
Token Cube
Feature activation+0.000
.
Token.
Feature activation+5.157
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
form
Token form
Feature activation+0.000
input
Token input
Feature activation+0.000
.
Token.
Feature activation+3.588
But
Token But
Feature activation+4.960
the
Token the
Feature activation+4.043
real
Token real
Feature activation+0.000
problem
Token problem
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
The
Token The
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Caller
Token Caller
Feature activation+0.000
,
Token,
Feature activation+0.915
Â
Token Â
Feature activation+0.000
ĵ
Tokenĵ
Feature activation+4.729
but
Tokenbut
Feature activation+1.972
having
Token having
Feature activation+0.000
talked
Token talked
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
okay
Token okay
Feature activation+0.000
and
Token and
Feature activation+4.695
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+0.000
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 3.834 - 4.601
CONTAINS 0.001%

be
Token be
Feature activation+0.000
far
Token far
Feature activation+0.000
better
Token better
Feature activation+0.000
.
Token.
Feature activation+4.126
Ċ
TokenĊ
Feature activation+0.228
Ċ
TokenĊ
Feature activation+3.868
As
TokenAs
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+0.000
was
Token was
Feature activation+0.000
discovered
Token discovered
Feature activation+0.000
.
Token.
Feature activation+0.828
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.830
The
TokenThe
Feature activation+3.898
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
might
Token might
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
me
Token me
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
,
Token,
Feature activation+2.517
but
Token but
Feature activation+3.835
I
Token I
Feature activation+2.713
was
Token was
Feature activation+1.153
persistent
Token persistent
Feature activation+0.105
.
Token.
Feature activation+0.985
Several
Token Several
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
class
Token class
Feature activation+0.000
!
Token!
Feature activation+3.088
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.419
There
TokenThere
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
the
Token the
Feature activation+0.000
object
Token object
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
freed
Token freed
Feature activation+0.000
.
Token.
Feature activation+4.389
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
reference
Token reference
Feature activation+0.000

INTERVAL 3.067 - 3.834
CONTAINS 0.002%

acting
Token acting
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
form
Token form
Feature activation+0.000
input
Token input
Feature activation+0.000
.
Token.
Feature activation+3.588
But
Token But
Feature activation+4.960
the
Token the
Feature activation+4.043
real
Token real
Feature activation+0.000
problem
Token problem
Feature activation+0.000
is
Token is
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
SC
TokenSC
Feature activation+0.000
).
Token).
Feature activation+0.569
Ċ
TokenĊ
Feature activation+0.223
Ċ
TokenĊ
Feature activation+3.288
W
TokenW
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
also
Token also
Feature activation+0.000
believes
Token believes
Feature activation+0.000
Russia
Token Russia
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+2.502
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.394
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.122
But
TokenBut
Feature activation+0.907
that
Token that
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
and
Token and
Feature activation+0.000
abundant
Token abundant
Feature activation+0.000
.
Token.
Feature activation+3.359
The
Token The
Feature activation+5.403
second
Token second
Feature activation+0.000
basket
Token basket
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
mess
Token mess
Feature activation+0.000
.
Token.
Feature activation+4.204
Ċ
TokenĊ
Feature activation+0.342
Ċ
TokenĊ
Feature activation+3.408
Which
TokenWhich
Feature activation+0.000
is
Token is
Feature activation+0.000
why
Token why
Feature activation+0.000
we
Token we
Feature activation+0.000
try
Token try
Feature activation+0.000

INTERVAL 2.301 - 3.067
CONTAINS 0.004%

acid
Token acid
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+1.528
breathe
Token breathe
Feature activation+0.000
),
Token),
Feature activation+5.542
with
Token with
Feature activation+2.328
the
Token the
Feature activation+0.493
fragments
Token fragments
Feature activation+0.000
bearing
Token bearing
Feature activation+0.000
the
Token the
Feature activation+0.000
structures
Token structures
Feature activation+0.000
easily
Token easily
Feature activation+0.000
doubled
Token doubled
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+2.502
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.394
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.122
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.028
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.515
Charlie
TokenCharlie
Feature activation+0.000
Angus
Token Angus
Feature activation+0.000
,
Token,
Feature activation+0.000
MP
Token MP
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
discovered
Token discovered
Feature activation+0.000
.
Token.
Feature activation+0.828
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.830
The
TokenThe
Feature activation+3.898
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
might
Token might
Feature activation+0.000
not
Token not
Feature activation+0.000
first
Token first
Feature activation+0.000
on
Token on
Feature activation+0.000
developing
Token developing
Feature activation+0.000
grind
Token grind
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
.
Token.
Feature activation+2.500
Gr
Token Gr
Feature activation+0.000
inders
Tokeninders
Feature activation+0.000
are
Token are
Feature activation+0.000
needed
Token needed
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.534 - 2.301
CONTAINS 0.007%

has
Token has
Feature activation+0.000
networking
Token networking
Feature activation+0.000
capabilities
Token capabilities
Feature activation+0.000
built
Token built
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+2.071
The
Token The
Feature activation+2.401
second
Token second
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
attach
Token attach
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+1.590
landslide
Token landslide
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
swept
Token swept
Feature activation+0.000
just
Token just
Feature activation+0.000
two
Token two
Feature activation+0.000
games
Token games
Feature activation+0.000
per
Token per
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+2.078
fifth
Token fifth
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
run
Token run
Feature activation+0.000
saw
Token saw
Feature activation+0.000
Pl
Token Pl
Feature activation+0.000
playing
Token playing
Feature activation+0.000
time
Token time
Feature activation+0.000
on
Token on
Feature activation+0.000
special
Token special
Feature activation+0.000
teams
Token teams
Feature activation+0.000
the
Token the
Feature activation+2.111
next
Token next
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
partially
Token partially
Feature activation+0.000
dialogue
Token dialogue
Feature activation+0.000
was
Token was
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
first
Token first
Feature activation+0.000
,
Token,
Feature activation+1.800
and
Token and
Feature activation+1.819
anim
Token anim
Feature activation+0.000
ators
Tokenators
Feature activation+0.736
created
Token created
Feature activation+0.000
their
Token their
Feature activation+0.000
facial
Token facial
Feature activation+0.000

INTERVAL 0.767 - 1.534
CONTAINS 0.018%

average
Token average
Feature activation+0.000
first
Token first
Feature activation+0.000
baseman
Token baseman
Feature activation+0.000
.
Token.
Feature activation+1.101
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.309
Considering
TokenConsidering
Feature activation+0.000
context
Token context
Feature activation+0.000
,
Token,
Feature activation+0.000
Freeman
Token Freeman
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
,
Token,
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
explained
Token explained
Feature activation+0.000
.
Token.
Feature activation+0.945
The
Token The
Feature activation+0.218
officers
Token officers
Feature activation+0.000
gave
Token gave
Feature activation+0.000
Mull
Token Mull
Feature activation+0.000
igan
Tokenigan
Feature activation+0.000
and
Token and
Feature activation+0.000
wipes
Token wipes
Feature activation+0.000
his
Token his
Feature activation+0.000
hands
Token hands
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+1.257
sweat
Token sweat
Feature activation+0.000
-
Token-
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
otted
Tokenotted
Feature activation+0.000
shirt
Token shirt
Feature activation+0.000
and
Token and
Feature activation+1.748
then
Token then
Feature activation+1.334
encrypt
Token encrypt
Feature activation+0.597
other
Token other
Feature activation+0.000
folders
Token folders
Feature activation+1.727
.
Token.
Feature activation+0.898
The
Token The
Feature activation+0.374
last
Token last
Feature activation+0.000
folder
Token folder
Feature activation+0.058
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
reported
Token reported
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.943
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
Tet
Token Tet
Feature activation+0.000
zel
Tokenzel
Feature activation+0.000

INTERVAL 0.000 - 0.767
CONTAINS 99.964%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
barely
Token barely
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
Clippers
Token Clippers
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Besides
TokenBesides
Feature activation+0.000
him
Token him
Feature activation+0.000
c
Token c
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
ing
Tokening
Feature activation+0.000
me
Token me
Feature activation+0.000
out
Token out
Feature activation+0.000
disappearance
Token disappearance
Feature activation+0.000
of
Token of
Feature activation+0.000
guitarist
Token guitarist
Feature activation+0.000
and
Token and
Feature activation+0.000
lyric
Token lyric
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
,
Token,
Feature activation+0.000
Richie
Token Richie
Feature activation+0.000
Edwards
Token Edwards
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
military
Token military
Feature activation+0.000
medic
Token medic
Feature activation+0.000
and
Token and
Feature activation+0.000
another
Token another
Feature activation+0.000
penned
Token penned
Feature activation+0.000
by
Token by
Feature activation+0.000
one
Token one
Feature activation+0.000
op
Tokenop
Feature activation+0.000
and
Token and
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
.
Token.
Feature activation+0.000
Things
Token Things
Feature activation+0.000
are
Token are
Feature activation+0.000
weird
Token weird
Feature activation+0.000
but
Token but
Feature activation+0.000
they
Token they
Feature activation+0.000
could
Token could
Feature activation+0.000
always
Token always
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 H9.7: (feature 5358)

TOP ACTIVATIONS
MAX = 6.752

faith
Token faith
Feature activation+0.000
,
Token,
Feature activation+0.000
Old
Token Old
Feature activation+0.000
World
Token World
Feature activation+0.000
vs
Token vs
Feature activation+6.199
.
Token.
Feature activation+6.752
New
Token New
Feature activation+0.000
-
Token -
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+1.336
bring
Token bring
Feature activation+3.442
in
Token in
Feature activation+4.606
the
Token the
Feature activation+6.636
new
Token new
Feature activation+0.011
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.085
,
Token,
Feature activation+0.281
word
Token word
Feature activation+0.000
a
Token a
Feature activation+0.000
retrospective
Token retrospective
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+6.213
new
Token new
Feature activation+0.000
songs
Token songs
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.123
string
Token string
Feature activation+0.000
.
Token.
Feature activation+0.000
faith
Token faith
Feature activation+0.000
,
Token,
Feature activation+0.000
Old
Token Old
Feature activation+0.000
World
Token World
Feature activation+0.000
vs
Token vs
Feature activation+6.199
.
Token.
Feature activation+6.752
New
Token New
Feature activation+0.000
-
Token -
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.006
but
Token but
Feature activation+0.000
ts
Tokents
Feature activation+0.000
,
Token,
Feature activation+0.933
then
Token then
Feature activation+0.191
the
Token the
Feature activation+5.836
younger
Token younger
Feature activation+0.000
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
A
Token A
Feature activation+0.000
ya
Tokenya
Feature activation+0.000
=
Token =
Feature activation+0.000
24
Token 24
Feature activation+0.000
h
Token h
Feature activation+0.000
)
Token)
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+5.701
young
Token young
Feature activation+0.000
(
Token (
Feature activation+0.338
med
Tokenmed
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
survival
Token survival
Feature activation+0.000
h
Token h
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
is
Token is
Feature activation+1.281
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+2.112
the
Token the
Feature activation+5.400
one
Token one
Feature activation+1.878
-
Token-
Feature activation+0.000
eyed
Tokeneyed
Feature activation+0.000
guy
Token guy
Feature activation+0.252
,
Token,
Feature activation+0.000
:
Token:
Feature activation+0.000
old
Token old
Feature activation+0.000
version
Token version
Feature activation+0.000
,
Token,
Feature activation+1.081
right
Token right
Feature activation+0.755
:
Token:
Feature activation+5.382
new
Token new
Feature activation+0.418
version
Token version
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.000
discour
Token discour
Feature activation+0.000
agement
Tokenagement
Feature activation+0.000
in
Token in
Feature activation+3.121
the
Token the
Feature activation+5.340
young
Token young
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
fix
Token fix
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+3.186
in
Token in
Feature activation+4.571
a
Token a
Feature activation+4.814
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
dump
Token dump
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+1.336
bring
Token bring
Feature activation+3.442
in
Token in
Feature activation+4.606
the
Token the
Feature activation+6.636
new
Token new
Feature activation+0.011
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.085
,
Token,
Feature activation+0.281
code
Token code
Feature activation+0.000
to
Token to
Feature activation+0.000
fix
Token fix
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+3.186
in
Token in
Feature activation+4.571
a
Token a
Feature activation+4.814
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
it
Token it
Feature activation+0.000
vised
Tokenvised
Feature activation+0.000
.
Token.
Feature activation+0.000
Switch
Token Switch
Feature activation+0.000
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+1.115
a
Token a
Feature activation+3.663
different
Token different
Feature activation+0.000
browser
Token browser
Feature activation+0.000
may
Token may
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
and
Token and
Feature activation+1.909
part
Token part
Feature activation+0.357
of
Token of
Feature activation+3.018
the
Token the
Feature activation+3.600
cemetery
Token cemetery
Feature activation+0.683
were
Token were
Feature activation+0.000
unearthed
Token unearthed
Feature activation+0.014
during
Token during
Feature activation+0.000
construction
Token construction
Feature activation+0.000
brother
Token brother
Feature activation+0.000
and
Token and
Feature activation+0.139
maybe
Token maybe
Feature activation+0.000
none
Token none
Feature activation+0.000
for
Token for
Feature activation+2.995
a
Token a
Feature activation+3.591
sibling
Token sibling
Feature activation+0.330
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
to
Token to
Feature activation+0.000
dump
Token dump
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+1.336
bring
Token bring
Feature activation+3.442
in
Token in
Feature activation+4.606
the
Token the
Feature activation+6.636
new
Token new
Feature activation+0.011
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.085
of
Token of
Feature activation+0.000
code
Token code
Feature activation+0.000
to
Token to
Feature activation+0.000
fix
Token fix
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+3.186
in
Token in
Feature activation+4.571
a
Token a
Feature activation+4.814
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
hopeless
Token hopeless
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.000
discour
Token discour
Feature activation+0.000
agement
Tokenagement
Feature activation+0.000
in
Token in
Feature activation+3.121
the
Token the
Feature activation+5.340
young
Token young
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
verses
Token verses
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Old
Token Old
Feature activation+0.000
and
Token and
Feature activation+3.074
New
Token New
Feature activation+0.000
Testament
Token Testament
Feature activation+0.000
that
Token that
Feature activation+0.000
endorse
Token endorse
Feature activation+0.000
and
Token and
Feature activation+0.000
City
Token City
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
and
Token and
Feature activation+1.909
part
Token part
Feature activation+0.357
of
Token of
Feature activation+3.018
the
Token the
Feature activation+3.600
cemetery
Token cemetery
Feature activation+0.683
were
Token were
Feature activation+0.000
unearthed
Token unearthed
Feature activation+0.014
during
Token during
Feature activation+0.000

Top DFA by src position
MAX = 7.739

science
Token science
Feature activation-0.022
Top resid features:
vs
Token vs
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
faith
Token faith
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
Old
Token Old
Feature activation+7.739
Top resid features:
World
Token World
Feature activation+0.051
Top resid features:
vs
Token vs
Feature activation+0.062
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.137
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
dump
Token dump
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
old
Token old
Feature activation+6.746
Top resid features:
and
Token and
Feature activation+0.144
Top resid features:
bring
Token bring
Feature activation+0.109
Top resid features:
in
Token in
Feature activation+0.348
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
presented
Token presented
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
retrospective
Token retrospective
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
its
Token its
Feature activation-0.033
Top resid features:
old
Token old
Feature activation+6.967
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
songs
Token songs
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
science
Token science
Feature activation-0.022
Top resid features:
vs
Token vs
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.060
Top resid features:
faith
Token faith
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
Old
Token Old
Feature activation+7.218
Top resid features:
World
Token World
Feature activation+0.035
Top resid features:
vs
Token vs
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation+0.009
Top resid features:
Club
Token Club
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
If
Token If
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
older
Token older
Feature activation+6.398
Top resid features:
sister
Token sister
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Maya
Token Maya
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
isn
Token isn
Feature activation+0.002
Top resid features:
resistance
Token resistance
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
significantly
Token significantly
Feature activation-0.001
Top resid features:
lower
Token lower
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
old
Token old
Feature activation+6.111
Top resid features:
CS
Token CS
Feature activation-0.059
Top resid features:
flies
Token flies
Feature activation+0.048
Top resid features:
(
Token (
Feature activation-0.001
Top resid features:
med
Tokenmed
Feature activation+0.003
Top resid features:
ian
Tokenian
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
This
TokenThis
Feature activation-0.002
Top resid features:
old
Token old
Feature activation+5.943
Top resid features:
h
Token h
Feature activation+0.026
Top resid features:
ag
Tokenag
Feature activation+0.137
Top resid features:
is
Token is
Feature activation+0.060
Top resid features:
worse
Token worse
Feature activation+0.010
Top resid features:
than
Token than
Feature activation+0.045
Top resid features:
Icon
Token Icon
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
left
Tokenleft
Feature activation-0.011
Top resid features:
:
Token:
Feature activation+0.022
Top resid features:
old
Token old
Feature activation+5.605
Top resid features:
version
Token version
Feature activation+0.142
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
right
Token right
Feature activation-0.031
Top resid features:
:
Token:
Feature activation+0.053
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
sense
Token sense
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
regret
Token regret
Feature activation-0.006
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
older
Token older
Feature activation+6.113
Top resid features:
people
Token people
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
sense
Token sense
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
bugs
Token bugs
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Usually
Token Usually
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
an
Token an
Feature activation+0.004
Top resid features:
old
Token old
Feature activation+5.843
Top resid features:
2
Token 2
Feature activation-0.152
Top resid features:
D
TokenD
Feature activation-0.023
Top resid features:
Nintendo
Token Nintendo
Feature activation-0.001
Top resid features:
game
Token game
Feature activation+0.041
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.142
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
dump
Token dump
Feature activation+0.084
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
old
Token old
Feature activation+4.815
Top resid features:
and
Token and
Feature activation+0.150
Top resid features:
bring
Token bring
Feature activation+0.176
Top resid features:
in
Token in
Feature activation+0.130
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
bugs
Token bugs
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Usually
Token Usually
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
an
Token an
Feature activation+0.013
Top resid features:
old
Token old
Feature activation+5.496
Top resid features:
2
Token 2
Feature activation-0.064
Top resid features:
D
TokenD
Feature activation-0.012
Top resid features:
Nintendo
Token Nintendo
Feature activation-0.011
Top resid features:
game
Token game
Feature activation+0.018
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
rever
Token rever
Feature activation+0.008
Top resid features:
ting
Tokenting
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
an
Token an
Feature activation+0.007
Top resid features:
older
Token older
Feature activation+4.004
Top resid features:
version
Token version
Feature activation+0.062
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
browser
Token browser
Feature activation+0.170
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
both
Token both
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
corner
Token corner
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
old
Token old
Feature activation+4.475
Top resid features:
City
Token City
Feature activation+0.058
Top resid features:
Hall
Token Hall
Feature activation+0.108
Top resid features:
foundation
Token foundation
Feature activation+0.082
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
part
Token part
Feature activation+0.015
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
term
Token term
Feature activation+0.011
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
an
Token an
Feature activation+0.003
Top resid features:
older
Token older
Feature activation+4.135
Top resid features:
sister
Token sister
Feature activation+0.079
Top resid features:
or
Token or
Feature activation-0.017
Top resid features:
younger
Token younger
Feature activation+0.081
Top resid features:
brother
Token brother
Feature activation+0.014
Top resid features:
and
Token and
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.193
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
dump
Token dump
Feature activation+0.087
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
old
Token old
Feature activation+3.783
Top resid features:
and
Token and
Feature activation+0.200
Top resid features:
bring
Token bring
Feature activation+0.064
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
bugs
Token bugs
Feature activation+0.041
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
Usually
Token Usually
Feature activation+0.028
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
an
Token an
Feature activation+0.014
Top resid features:
old
Token old
Feature activation+3.787
Top resid features:
2
Token 2
Feature activation-0.003
Top resid features:
D
TokenD
Feature activation-0.001
Top resid features:
Nintendo
Token Nintendo
Feature activation-0.013
Top resid features:
game
Token game
Feature activation+0.027
Top resid features:
a
Token a
Feature activation+0.034
Top resid features:
sense
Token sense
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
regret
Token regret
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
older
Token older
Feature activation+3.765
Top resid features:
people
Token people
Feature activation+0.177
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
sense
Token sense
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
numerous
Token numerous
Feature activation-0.005
Top resid features:
verses
Token verses
Feature activation+0.020
Top resid features:
from
Token from
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
Old
Token Old
Feature activation+3.952
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
Testament
Token Testament
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
endorse
Token endorse
Feature activation+0.000
Top resid features:
both
Token both
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
corner
Token corner
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
old
Token old
Feature activation+3.592
Top resid features:
City
Token City
Feature activation+0.028
Top resid features:
Hall
Token Hall
Feature activation+0.167
Top resid features:
foundation
Token foundation
Feature activation+0.201
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
part
Token part
Feature activation+0.011
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.09

Head 3: 0.07

Head 4: 0.03

Head 5: 0.05

Head 6: 0.04

Head 7: 0.52

Head 8: 0.03

Head 9: 0.02

Head 10: 0.04

Head 11: 0.02

Positive logits

new4.89

newer4.76

new4.62

younger3.80

newest3.78

young3.67

newcomers3.55

revived3.53

NEW3.38

NEW3.27

newly3.19

innovate3.18

young3.12

youngsters3.11

modern3.10

ffe3.05

rebuilt3.03

revamped3.03

reformed3.01

20182.89

Negative logits

embargo-2.32

Mich-2.17

dict-2.09

Mort-2.09

disclaimer-2.09

Aust-2.08

obligation-2.06

Rs-2.06

attribution-2.05

tab-2.05

dom-2.03

audible-2.01

deductible-1.98

MacDonald-1.97

dues-1.97

tropes-1.95

limitation-1.94

./-1.92

doms-1.91

Tot-1.91

INTERVAL 6.077 - 6.752
CONTAINS 0.000%

a
Token a
Feature activation+0.000
retrospective
Token retrospective
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+6.213
new
Token new
Feature activation+0.000
songs
Token songs
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.123
string
Token string
Feature activation+0.000
.
Token.
Feature activation+0.000
faith
Token faith
Feature activation+0.000
,
Token,
Feature activation+0.000
Old
Token Old
Feature activation+0.000
World
Token World
Feature activation+0.000
vs
Token vs
Feature activation+6.199
.
Token.
Feature activation+6.752
New
Token New
Feature activation+0.000
-
Token -
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
faith
Token faith
Feature activation+0.000
,
Token,
Feature activation+0.000
Old
Token Old
Feature activation+0.000
World
Token World
Feature activation+0.000
vs
Token vs
Feature activation+6.199
.
Token.
Feature activation+6.752
New
Token New
Feature activation+0.000
-
Token -
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+1.336
bring
Token bring
Feature activation+3.442
in
Token in
Feature activation+4.606
the
Token the
Feature activation+6.636
new
Token new
Feature activation+0.011
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.085
,
Token,
Feature activation+0.281
word
Token word
Feature activation+0.000

INTERVAL 5.402 - 6.077
CONTAINS 0.000%

their
Token their
Feature activation+0.006
but
Token but
Feature activation+0.000
ts
Tokents
Feature activation+0.000
,
Token,
Feature activation+0.933
then
Token then
Feature activation+0.191
the
Token the
Feature activation+5.836
younger
Token younger
Feature activation+0.000
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
A
Token A
Feature activation+0.000
ya
Tokenya
Feature activation+0.000
=
Token =
Feature activation+0.000
24
Token 24
Feature activation+0.000
h
Token h
Feature activation+0.000
)
Token)
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+5.701
young
Token young
Feature activation+0.000
(
Token (
Feature activation+0.338
med
Tokenmed
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
survival
Token survival
Feature activation+0.000

INTERVAL 4.726 - 5.402
CONTAINS 0.000%

to
Token to
Feature activation+0.000
fix
Token fix
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+3.186
in
Token in
Feature activation+4.571
a
Token a
Feature activation+4.814
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.000
discour
Token discour
Feature activation+0.000
agement
Tokenagement
Feature activation+0.000
in
Token in
Feature activation+3.121
the
Token the
Feature activation+5.340
young
Token young
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
that
Token that
Feature activation+0.000
h
Token h
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
is
Token is
Feature activation+1.281
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+2.112
the
Token the
Feature activation+5.400
one
Token one
Feature activation+1.878
-
Token-
Feature activation+0.000
eyed
Tokeneyed
Feature activation+0.000
guy
Token guy
Feature activation+0.252
,
Token,
Feature activation+0.000
:
Token:
Feature activation+0.000
old
Token old
Feature activation+0.000
version
Token version
Feature activation+0.000
,
Token,
Feature activation+1.081
right
Token right
Feature activation+0.755
:
Token:
Feature activation+5.382
new
Token new
Feature activation+0.418
version
Token version
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 4.051 - 4.726
CONTAINS 0.000%

code
Token code
Feature activation+0.000
to
Token to
Feature activation+0.000
fix
Token fix
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+3.186
in
Token in
Feature activation+4.571
a
Token a
Feature activation+4.814
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
it
Token it
Feature activation+0.000
dump
Token dump
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+1.336
bring
Token bring
Feature activation+3.442
in
Token in
Feature activation+4.606
the
Token the
Feature activation+6.636
new
Token new
Feature activation+0.011
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.085
,
Token,
Feature activation+0.281

INTERVAL 3.376 - 4.051
CONTAINS 0.000%

Hall
Token Hall
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
and
Token and
Feature activation+1.909
part
Token part
Feature activation+0.357
of
Token of
Feature activation+3.018
the
Token the
Feature activation+3.600
cemetery
Token cemetery
Feature activation+0.683
were
Token were
Feature activation+0.000
unearthed
Token unearthed
Feature activation+0.014
during
Token during
Feature activation+0.000
construction
Token construction
Feature activation+0.000
vised
Tokenvised
Feature activation+0.000
.
Token.
Feature activation+0.000
Switch
Token Switch
Feature activation+0.000
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+1.115
a
Token a
Feature activation+3.663
different
Token different
Feature activation+0.000
browser
Token browser
Feature activation+0.000
may
Token may
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
brother
Token brother
Feature activation+0.000
and
Token and
Feature activation+0.139
maybe
Token maybe
Feature activation+0.000
none
Token none
Feature activation+0.000
for
Token for
Feature activation+2.995
a
Token a
Feature activation+3.591
sibling
Token sibling
Feature activation+0.330
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
to
Token to
Feature activation+0.000
dump
Token dump
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
and
Token and
Feature activation+1.336
bring
Token bring
Feature activation+3.442
in
Token in
Feature activation+4.606
the
Token the
Feature activation+6.636
new
Token new
Feature activation+0.011
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.085

INTERVAL 2.701 - 3.376
CONTAINS 0.001%

last
Token last
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
old
Token old
Feature activation+0.000
men
Token men
Feature activation+0.000
,
Token,
Feature activation+2.726
heads
Token heads
Feature activation+0.000
held
Token held
Feature activation+0.000
high
Token high
Feature activation+0.000
,
Token,
Feature activation+0.243
marching
Token marching
Feature activation+0.000
City
Token City
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
and
Token and
Feature activation+1.909
part
Token part
Feature activation+0.357
of
Token of
Feature activation+3.018
the
Token the
Feature activation+3.600
cemetery
Token cemetery
Feature activation+0.683
were
Token were
Feature activation+0.000
unearthed
Token unearthed
Feature activation+0.014
during
Token during
Feature activation+0.000
younger
Token younger
Feature activation+0.000
brother
Token brother
Feature activation+0.000
and
Token and
Feature activation+0.139
maybe
Token maybe
Feature activation+0.000
none
Token none
Feature activation+0.000
for
Token for
Feature activation+2.995
a
Token a
Feature activation+3.591
sibling
Token sibling
Feature activation+0.330
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
could
Token could
Feature activation+0.000
of
Token of
Feature activation+0.000
code
Token code
Feature activation+0.000
to
Token to
Feature activation+0.000
fix
Token fix
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+3.186
in
Token in
Feature activation+4.571
a
Token a
Feature activation+4.814
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
hopeless
Token hopeless
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.000
discour
Token discour
Feature activation+0.000
agement
Tokenagement
Feature activation+0.000
in
Token in
Feature activation+3.121
the
Token the
Feature activation+5.340
young
Token young
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000

INTERVAL 2.026 - 2.701
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.088
no
Token no
Feature activation+0.160
viable
Token viable
Feature activation+0.585
plan
Token plan
Feature activation+0.000
for
Token for
Feature activation+2.102
its
Token its
Feature activation+1.842
redevelopment
Token redevelopment
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
have
Token have
Feature activation+0.000
aged
Token aged
Feature activation+0.000
battery
Token battery
Feature activation+0.000
is
Token is
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
with
Token with
Feature activation+1.382
a
Token a
Feature activation+2.098
new
Token new
Feature activation+0.229
one
Token one
Feature activation+0.147
,
Token,
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
performance
Token performance
Feature activation+0.000
old
Token old
Feature activation+0.000
h
Token h
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
is
Token is
Feature activation+1.281
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+2.112
the
Token the
Feature activation+5.400
one
Token one
Feature activation+1.878
-
Token-
Feature activation+0.000
eyed
Tokeneyed
Feature activation+0.000
guy
Token guy
Feature activation+0.252
realistic
Token realistic
Feature activation+0.000
,
Token,
Feature activation+0.000
why
Token why
Feature activation+0.000
not
Token not
Feature activation+0.602
offer
Token offer
Feature activation+1.039
them
Token them
Feature activation+2.509
up
Token up
Feature activation+0.879
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+0.000
-
Token-
Feature activation+0.000
coming
Tokencoming
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
start
Token start
Feature activation+0.000
looking
Token looking
Feature activation+0.789
into
Token into
Feature activation+2.130
what
Token what
Feature activation+0.370
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
new
Token new
Feature activation+0.000

INTERVAL 1.350 - 2.026
CONTAINS 0.004%

a
Token a
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
limited
Token limited
Feature activation+0.000
partnership
Token partnership
Feature activation+0.000
and
Token and
Feature activation+2.451
the
Token the
Feature activation+1.414
BC
Token BC
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
digital
Token digital
Feature activation+0.000
token
Token token
Feature activation+0.000
,
Token,
Feature activation+0.000
already
Token already
Feature activation+0.000
have
Token have
Feature activation+0.000
and
Token and
Feature activation+1.581
set
Token set
Feature activation+0.573
up
Token up
Feature activation+2.059
the
Token the
Feature activation+1.559
following
Token following
Feature activation+0.258
activities
Token activities
Feature activation+0.000
for
Token for
Feature activation+0.960
your
Token your
Feature activation+0.253
pet
Token pet
Feature activation+0.000
from
Token from
Feature activation+0.000
other
Token other
Feature activation+0.000
sections
Token sections
Feature activation+0.000
and
Token and
Feature activation+0.709
highlighting
Token highlighting
Feature activation+1.144
its
Token its
Feature activation+1.683
vital
Token vital
Feature activation+0.424
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.000
usability
Token usability
Feature activation+0.000
.
Token.
Feature activation+0.000
existing
Token existing
Feature activation+0.000
toys
Token toys
Feature activation+0.000
you
Token you
Feature activation+0.000
already
Token already
Feature activation+0.000
have
Token have
Feature activation+0.000
and
Token and
Feature activation+1.581
set
Token set
Feature activation+0.573
up
Token up
Feature activation+2.059
the
Token the
Feature activation+1.559
following
Token following
Feature activation+0.258
activities
Token activities
Feature activation+0.000
nice
Token nice
Feature activation+0.000
and
Token and
Feature activation+0.000
quiet
Token quiet
Feature activation+0.000
bus
Token bus
Feature activation+0.000
with
Token with
Feature activation+0.974
a
Token a
Feature activation+1.388
party
Token party
Feature activation+0.000
-
Token-
Feature activation+0.000
style
Tokenstyle
Feature activation+0.000
bus
Token bus
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.675 - 1.350
CONTAINS 0.014%

Price
TokenPrice
Feature activation+0.000
et
Token et
Feature activation+0.000
al
Token al
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.419
this
Token this
Feature activation+1.347
study
Token study
Feature activation+0.000
(
Token (
Feature activation+0.000
De
TokenDe
Feature activation+0.000
Ste
TokenSte
Feature activation+0.000
f
Tokenf
Feature activation+0.000
,
Token,
Feature activation+0.000
why
Token why
Feature activation+0.000
not
Token not
Feature activation+0.602
offer
Token offer
Feature activation+1.039
them
Token them
Feature activation+2.509
up
Token up
Feature activation+0.879
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+0.000
-
Token-
Feature activation+0.000
coming
Tokencoming
Feature activation+0.000
product
Token product
Feature activation+0.000
was
Token was
Feature activation+0.000
widely
Token widely
Feature activation+0.000
accepted
Token accepted
Feature activation+0.000
--
Token --
Feature activation+0.000
and
Token and
Feature activation+0.080
then
Token then
Feature activation+0.809
a
Token a
Feature activation+1.266
lot
Token lot
Feature activation+0.988
of
Token of
Feature activation+0.910
smart
Token smart
Feature activation+0.000
people
Token people
Feature activation+0.000
and
Token and
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+1.471
the
Token the
Feature activation+1.609
a
Token a
Feature activation+0.803
hist
Tokenhist
Feature activation+0.000
orical
Tokenorical
Feature activation+0.000
,
Token,
Feature activation+0.107
yet
Token yet
Feature activation+0.411
more
Token more
Feature activation+1.184
than
Token than
Feature activation+0.000
three
Token three
Feature activation+0.000
times
Token times
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.032
the
Token the
Feature activation+0.990
latter
Token latter
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.035
Republican
Token Republican
Feature activation+0.000
bill
Token bill
Feature activation+0.000

INTERVAL 0.000 - 0.675
CONTAINS 99.978%

for
Token for
Feature activation+0.000
navigation
Token navigation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
they
Token they
Feature activation+0.000
also
Token also
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000
more
Token more
Feature activation+0.000
storage
Token storage
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
late
Token late
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
been
Token been
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
forefront
Token forefront
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
league
Token league
Feature activation+0.000
laundering
Token laundering
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
approved
Token approved
Feature activation+0.000
a
Token a
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
deal
Token deal
Feature activation+0.000
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
help
Token help
Feature activation+0.000
but
Token but
Feature activation+0.000
get
Token get
Feature activation+0.000
excited
Token excited
Feature activation+0.000
knowing
Token knowing
Feature activation+0.000
that
Token that
Feature activation+0.000
Redmond
Token Redmond
Feature activation+0.000
is
Token is
Feature activation+0.000
In
TokenIn
Feature activation+0.000
May
Token May
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
,
Token,
Feature activation+0.000
Swiss
Token Swiss
Feature activation+0.000
historian
Token historian
Feature activation+0.000
Dan
Token Dan
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
le
Tokenle
Feature activation+0.000
G
Token G
Feature activation+0.000
ans
Tokenans
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