H10.1 top features

Top feature 0 in H10.1: (feature 16771)

TOP ACTIVATIONS
MAX = 12.395

.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.118
and
Token and
Feature activation+0.433
above
Token above
Feature activation+0.000
:
Token:
Feature activation+4.501
the
Token the
Feature activation+12.395
up
Token up
Feature activation+0.000
values
Tokenvalues
Feature activation+0.236
are
Token are
Feature activation+1.339
mut
Token mut
Feature activation+0.000
able
Tokenable
Feature activation+1.357
function
Token function
Feature activation+4.394
environment
Token environment
Feature activation+1.264
with
Token with
Feature activation+9.433
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+12.186
up
Token up
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
called
Token called
Feature activation+10.140
_
Token _
Feature activation+6.174
EN
TokenEN
Feature activation+0.000
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+12.186
up
Token up
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
called
Token called
Feature activation+10.140
_
Token _
Feature activation+6.174
EN
TokenEN
Feature activation+0.000
V
TokenV
Feature activation+0.000
.
Token .
Feature activation+7.911
You
Token You
Feature activation+0.000
2
Token2
Feature activation+0.549
replaced
Token replaced
Feature activation+3.497
the
Token the
Feature activation+8.957
function
Token function
Feature activation+4.394
environment
Token environment
Feature activation+1.264
with
Token with
Feature activation+9.433
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+12.186
up
Token up
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
Lua
TokenLua
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.549
replaced
Token replaced
Feature activation+3.497
the
Token the
Feature activation+8.957
function
Token function
Feature activation+4.394
environment
Token environment
Feature activation+1.264
with
Token with
Feature activation+9.433
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
.
Token.
Feature activation+0.519
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.478
When
TokenWhen
Feature activation+2.685
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
variable
Token variable
Feature activation+0.605
.
Token .
Feature activation+7.911
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
read
Token read
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+8.508
this
Token this
Feature activation+6.322
in
Token in
Feature activation+0.272
my
Token my
Feature activation+1.114
companion
Token companion
Feature activation+1.914
guide
Token guide
Feature activation+0.046
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ups
Token ups
Feature activation+0.000
and
Token and
Feature activation+8.336
downs
Token downs
Feature activation+0.000
and
Token and
Feature activation+0.000
everything
Token everything
Feature activation+0.000
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
my
Token my
Feature activation+1.114
companion
Token companion
Feature activation+1.914
guide
Token guide
Feature activation+0.046
:
Token:
Feature activation+6.906
Implement
Token Implement
Feature activation+4.070
ing
Tokening
Feature activation+8.103
set
Token set
Feature activation+0.206
f
Tokenf
Feature activation+0.000
env
Tokenenv
Feature activation+1.465
in
Token in
Feature activation+1.045
Lua
Token Lua
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
called
Token called
Feature activation+10.140
_
Token _
Feature activation+6.174
EN
TokenEN
Feature activation+0.000
V
TokenV
Feature activation+0.000
.
Token .
Feature activation+7.911
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
read
Token read
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+8.508
're
Token're
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
."
Token."
Feature activation+7.873
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.847
G
TokenG
Feature activation+0.000
ambling
Tokenambling
Feature activation+0.000
has
Token has
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.478
When
TokenWhen
Feature activation+2.685
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
variable
Token variable
Feature activation+0.605
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
finally
Token finally
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ups
Token ups
Feature activation+0.000
and
Token and
Feature activation+7.650
downs
Token downs
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
lives
Token lives
Feature activation+0.000
after
Token after
Feature activation+0.000
Lua
Token Lua
Feature activation+0.000
.
Token.
Feature activation+0.519
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.478
When
TokenWhen
Feature activation+2.685
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
the
Token the
Feature activation+0.000
securities
Token securities
Feature activation+0.000
regulator
Token regulator
Feature activation+0.000
offers
Token offers
Feature activation+1.840
rewards
Token rewards
Feature activation+1.828
of
Token of
Feature activation+7.518
up
Token up
Feature activation+0.000
to
Token to
Feature activation+2.294
$
Token $
Feature activation+0.000
5
Token5
Feature activation+0.000
million
Token million
Feature activation+0.000
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
variable
Token variable
Feature activation+0.605
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
copied
Token copied
Feature activation+0.000
the
Token the
Feature activation+0.000
spin
Token spin
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+7.134
down
Token down
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.000
When
TokenWhen
Feature activation+2.685
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
variable
Token variable
Feature activation+0.605
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
arrows
Token arrows
Feature activation+0.000
to
Token to
Feature activation+0.000
seek
Token seek
Feature activation+0.000
,
Token,
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+7.038
down
Token down
Feature activation+0.000
arrows
Token arrows
Feature activation+0.000
for
Token for
Feature activation+0.000
volume
Token volume
Feature activation+0.000
.
Token.
Feature activation+0.000
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
up
Token up
Feature activation+0.000
's
Token's
Feature activation+0.719
and
Token and
Feature activation+7.019
downs
Token downs
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
thought
Token thought
Feature activation+0.000
I
Token I
Feature activation+0.000

Top DFA by src position
MAX = 12.589

The
Token The
Feature activation+0.006
Top resid features:
function
Token function
Feature activation+0.086
Top resid features:
environment
Token environment
Feature activation-0.127
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
up
Token up
Feature activation+12.589
Top resid features:
values
Tokenvalues
Feature activation+0.105
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
mut
Token mut
Feature activation+0.057
Top resid features:
able
Tokenable
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
function
Token function
Feature activation-0.029
Top resid features:
environment
Token environment
Feature activation-0.175
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
up
Token up
Feature activation+10.947
Top resid features:
values
Tokenvalues
Feature activation+0.083
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
mut
Token mut
Feature activation+0.047
Top resid features:
able
Tokenable
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
function
Token function
Feature activation-0.003
Top resid features:
environment
Token environment
Feature activation-0.039
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
up
Token up
Feature activation+5.425
Top resid features:
values
Tokenvalues
Feature activation+0.055
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
mut
Token mut
Feature activation+0.022
Top resid features:
able
Tokenable
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
The
Token The
Feature activation+0.007
Top resid features:
function
Token function
Feature activation+0.019
Top resid features:
environment
Token environment
Feature activation-0.027
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
up
Token up
Feature activation+8.892
Top resid features:
values
Tokenvalues
Feature activation+0.017
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
mut
Token mut
Feature activation-0.002
Top resid features:
able
Tokenable
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
The
Token The
Feature activation+0.013
Top resid features:
function
Token function
Feature activation+0.010
Top resid features:
environment
Token environment
Feature activation-0.030
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
up
Token up
Feature activation+7.452
Top resid features:
values
Tokenvalues
Feature activation+0.018
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
mut
Token mut
Feature activation-0.004
Top resid features:
able
Tokenable
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
environment
Token environment
Feature activation-0.000
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
specially
Token specially
Feature activation-0.009
Top resid features:
named
Token named
Feature activation-0.004
Top resid features:
up
Token up
Feature activation+4.001
Top resid features:
value
Tokenvalue
Feature activation-0.023
Top resid features:
called
Token called
Feature activation+0.004
Top resid features:
_
Token _
Feature activation+0.027
Top resid features:
EN
TokenEN
Feature activation+0.028
Top resid features:
V
TokenV
Feature activation+0.016
Top resid features:
environment
Token environment
Feature activation+0.006
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
specially
Token specially
Feature activation-0.025
Top resid features:
named
Token named
Feature activation+0.007
Top resid features:
up
Token up
Feature activation+5.922
Top resid features:
value
Tokenvalue
Feature activation+0.013
Top resid features:
called
Token called
Feature activation+0.004
Top resid features:
_
Token _
Feature activation+0.100
Top resid features:
EN
TokenEN
Feature activation+0.022
Top resid features:
V
TokenV
Feature activation+0.001
Top resid features:
forward
Token forward
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
ups
Token ups
Feature activation+8.580
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
downs
Token downs
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
everything
Token everything
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
environment
Token environment
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
specially
Token specially
Feature activation-0.055
Top resid features:
named
Token named
Feature activation-0.010
Top resid features:
up
Token up
Feature activation+5.247
Top resid features:
value
Tokenvalue
Feature activation+0.018
Top resid features:
called
Token called
Feature activation+0.002
Top resid features:
_
Token _
Feature activation+0.061
Top resid features:
EN
TokenEN
Feature activation+0.026
Top resid features:
V
TokenV
Feature activation-0.009
Top resid features:
environment
Token environment
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
specially
Token specially
Feature activation-0.026
Top resid features:
named
Token named
Feature activation-0.016
Top resid features:
up
Token up
Feature activation+4.656
Top resid features:
value
Tokenvalue
Feature activation+0.001
Top resid features:
called
Token called
Feature activation+0.004
Top resid features:
_
Token _
Feature activation+0.130
Top resid features:
EN
TokenEN
Feature activation+0.014
Top resid features:
V
TokenV
Feature activation+0.006
Top resid features:
police
Token police
Feature activation+0.030
Top resid features:
Sgt
Token Sgt
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Dar
Token Dar
Feature activation-0.004
Top resid features:
in
Tokenin
Feature activation+0.001
Top resid features:
Up
Token Up
Feature activation+8.325
Top resid features:
still
Tokenstill
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
adding
Token adding
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
environment
Token environment
Feature activation-0.002
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
specially
Token specially
Feature activation-0.008
Top resid features:
named
Token named
Feature activation-0.004
Top resid features:
up
Token up
Feature activation+3.968
Top resid features:
value
Tokenvalue
Feature activation+0.006
Top resid features:
called
Token called
Feature activation+0.001
Top resid features:
_
Token _
Feature activation+0.043
Top resid features:
EN
TokenEN
Feature activation+0.020
Top resid features:
V
TokenV
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
finally
Token finally
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
ups
Token ups
Feature activation+7.976
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
downs
Token downs
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation+0.000
Top resid features:
environment
Token environment
Feature activation-0.001
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
specially
Token specially
Feature activation-0.008
Top resid features:
named
Token named
Feature activation-0.005
Top resid features:
up
Token up
Feature activation+3.421
Top resid features:
value
Tokenvalue
Feature activation-0.009
Top resid features:
called
Token called
Feature activation+0.001
Top resid features:
_
Token _
Feature activation+0.016
Top resid features:
EN
TokenEN
Feature activation+0.019
Top resid features:
V
TokenV
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Rew
TokenRew
Feature activation-0.042
Top resid features:
ards
Tokenards
Feature activation-0.249
Top resid features:
of
Token of
Feature activation-0.014
Top resid features:
up
Token up
Feature activation+8.208
Top resid features:
to
Token to
Feature activation+0.157
Top resid features:
$
Token $
Feature activation+0.026
Top resid features:
5
Token5
Feature activation+0.028
Top resid features:
million
Token million
Feature activation-0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
environment
Token environment
Feature activation-0.018
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
specially
Token specially
Feature activation-0.004
Top resid features:
named
Token named
Feature activation-0.005
Top resid features:
up
Token up
Feature activation+4.565
Top resid features:
value
Tokenvalue
Feature activation-0.009
Top resid features:
called
Token called
Feature activation+0.002
Top resid features:
_
Token _
Feature activation+0.019
Top resid features:
EN
TokenEN
Feature activation+0.012
Top resid features:
V
TokenV
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
spin
Token spin
Feature activation+0.024
Top resid features:
can
Token can
Feature activation+0.085
Top resid features:
be
Token be
Feature activation+0.048
Top resid features:
up
Token up
Feature activation+7.404
Top resid features:
and
Token and
Feature activation+0.078
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
environment
Token environment
Feature activation-0.005
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
specially
Token specially
Feature activation-0.029
Top resid features:
named
Token named
Feature activation-0.014
Top resid features:
up
Token up
Feature activation+3.084
Top resid features:
value
Tokenvalue
Feature activation-0.002
Top resid features:
called
Token called
Feature activation+0.003
Top resid features:
_
Token _
Feature activation+0.020
Top resid features:
EN
TokenEN
Feature activation+0.008
Top resid features:
V
TokenV
Feature activation+0.001
Top resid features:
right
Token right
Feature activation+0.036
Top resid features:
arrows
Token arrows
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
seek
Token seek
Feature activation-0.024
Top resid features:
,
Token,
Feature activation-0.050
Top resid features:
up
Token up
Feature activation+7.411
Top resid features:
and
Token and
Feature activation+0.091
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
arrows
Token arrows
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
volume
Token volume
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
been
Token been
Feature activation+0.003
Top resid features:
filled
Token filled
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
some
Token some
Feature activation+0.002
Top resid features:
up
Token up
Feature activation+4.155
Top resid features:
's
Token's
Feature activation+3.196
Top resid features:
and
Token and
Feature activation+0.132
Top resid features:
downs
Token downs
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.53

Head 2: 0.05

Head 3: 0.06

Head 4: 0.03

Head 5: 0.03

Head 6: 0.03

Head 7: 0.08

Head 8: 0.05

Head 9: 0.03

Head 10: 0.04

Head 11: 0.03

Positive logits

Up6.48

Up6.18

Down5.85

Down5.68

up5.66

UP5.57

up5.44

down5.23

down5.05

UP4.99

DOWN4.82

downs4.33

Ups4.27

ups4.27

downs4.23

ups4.17

DOWN3.99

Downs3.96

upt3.69

upt3.60

Negative logits

ndra-2.64

ici-2.35

Pure-2.32

shadow-2.21

naire-2.20

ALSE-2.18

Natural-2.18

ocal-2.16

fitting-2.14

veyard-2.14

Hollow-2.14

unnatural-2.13

fecture-2.13

illed-2.12

illusion-2.12

Pure-2.11

Rogue-2.11

orean-2.11

mere-2.10

lore-2.07

INTERVAL 11.155 - 12.395
CONTAINS 0.000%

.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.118
and
Token and
Feature activation+0.433
above
Token above
Feature activation+0.000
:
Token:
Feature activation+4.501
the
Token the
Feature activation+12.395
up
Token up
Feature activation+0.000
values
Tokenvalues
Feature activation+0.236
are
Token are
Feature activation+1.339
mut
Token mut
Feature activation+0.000
able
Tokenable
Feature activation+1.357
function
Token function
Feature activation+4.394
environment
Token environment
Feature activation+1.264
with
Token with
Feature activation+9.433
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+12.186
up
Token up
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
called
Token called
Feature activation+10.140
_
Token _
Feature activation+6.174
EN
TokenEN
Feature activation+0.000

INTERVAL 9.916 - 11.155
CONTAINS 0.000%

a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+12.186
up
Token up
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
called
Token called
Feature activation+10.140
_
Token _
Feature activation+6.174
EN
TokenEN
Feature activation+0.000
V
TokenV
Feature activation+0.000
.
Token .
Feature activation+7.911
You
Token You
Feature activation+0.000

INTERVAL 8.676 - 9.916
CONTAINS 0.000%

Lua
TokenLua
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.549
replaced
Token replaced
Feature activation+3.497
the
Token the
Feature activation+8.957
function
Token function
Feature activation+4.394
environment
Token environment
Feature activation+1.264
with
Token with
Feature activation+9.433
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
2
Token2
Feature activation+0.549
replaced
Token replaced
Feature activation+3.497
the
Token the
Feature activation+8.957
function
Token function
Feature activation+4.394
environment
Token environment
Feature activation+1.264
with
Token with
Feature activation+9.433
a
Token a
Feature activation+3.997
specially
Token specially
Feature activation+0.000
named
Token named
Feature activation+12.186
up
Token up
Feature activation+0.000
value
Tokenvalue
Feature activation+1.762
.
Token.
Feature activation+0.519
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.478
When
TokenWhen
Feature activation+2.685
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
variable
Token variable
Feature activation+0.605

INTERVAL 7.437 - 8.676
CONTAINS 0.001%

,
Token,
Feature activation+0.000
finally
Token finally
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ups
Token ups
Feature activation+0.000
and
Token and
Feature activation+7.650
downs
Token downs
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
lives
Token lives
Feature activation+0.000
after
Token after
Feature activation+0.000
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ups
Token ups
Feature activation+0.000
and
Token and
Feature activation+8.336
downs
Token downs
Feature activation+0.000
and
Token and
Feature activation+0.000
everything
Token everything
Feature activation+0.000
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.478
When
TokenWhen
Feature activation+2.685
assigning
Token assigning
Feature activation+7.599
a
Token a
Feature activation+8.874
function
Token function
Feature activation+4.713
to
Token to
Feature activation+7.825
a
Token a
Feature activation+7.074
new
Token new
Feature activation+7.182
variable
Token variable
Feature activation+0.605
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
securities
Token securities
Feature activation+0.000
regulator
Token regulator
Feature activation+0.000
offers
Token offers
Feature activation+1.840
rewards
Token rewards
Feature activation+1.828
of
Token of
Feature activation+7.518
up
Token up
Feature activation+0.000
to
Token to
Feature activation+2.294
$
Token $
Feature activation+0.000
5
Token5
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token .
Feature activation+7.911
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
read
Token read
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+8.508
this
Token this
Feature activation+6.322
in
Token in
Feature activation+0.272
my
Token my
Feature activation+1.114
companion
Token companion
Feature activation+1.914
guide
Token guide
Feature activation+0.046

INTERVAL 6.197 - 7.437
CONTAINS 0.001%

arrows
Token arrows
Feature activation+0.000
to
Token to
Feature activation+0.000
seek
Token seek
Feature activation+0.000
,
Token,
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+7.038
down
Token down
Feature activation+0.000
arrows
Token arrows
Feature activation+0.000
for
Token for
Feature activation+0.000
volume
Token volume
Feature activation+0.000
.
Token.
Feature activation+0.000
regardless
Token regardless
Feature activation+0.000
of
Token of
Feature activation+0.000
budgets
Token budgets
Feature activation+0.000
up
Token up
Feature activation+0.000
or
Token or
Feature activation+6.355
budgets
Token budgets
Feature activation+6.642
down
Token down
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
people
Token people
Feature activation+0.000
will
Token will
Feature activation+0.000
from
Token from
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
vets
Token vets
Feature activation+6.451
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+2.303
this
Token this
Feature activation+6.322
in
Token in
Feature activation+0.272
my
Token my
Feature activation+1.114
companion
Token companion
Feature activation+1.914
guide
Token guide
Feature activation+0.046
:
Token:
Feature activation+6.906
Implement
Token Implement
Feature activation+4.070
ing
Tokening
Feature activation+8.103
set
Token set
Feature activation+0.206
f
Tokenf
Feature activation+0.000
env
Tokenenv
Feature activation+1.465
is
Token is
Feature activation+0.132
£
Token £
Feature activation+0.000
217
Token217
Feature activation+0.000
,
Token,
Feature activation+0.000
888
Token888
Feature activation+1.314
,
Token,
Feature activation+6.608
while
Token while
Feature activation+0.000
in
Token in
Feature activation+0.000
London
Token London
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.749

INTERVAL 4.958 - 6.197
CONTAINS 0.001%

aves
Tokenaves
Feature activation+0.000
history
Token history
Feature activation+0.000
to
Token to
Feature activation+0.000
scroll
Token scroll
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+5.615
look
Token look
Feature activation+3.545
back
Token back
Feature activation+0.378
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
clarify
Token clarify
Feature activation+0.000
you
Token you
Feature activation+0.000
fix
Token fix
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+5.713
How
TokenHow
Feature activation+0.000
do
Token do
Feature activation+0.494
I
Token I
Feature activation+0.017
clean
Token clean
Feature activation+0.000
up
Token up
Feature activation+0.000
copied
Token copied
Feature activation+0.000
.
Token.
Feature activation+0.963
Just
Token Just
Feature activation+0.175
like
Token like
Feature activation+2.504
tables
Token tables
Feature activation+0.000
,
Token,
Feature activation+5.381
function
Token function
Feature activation+3.292
values
Token values
Feature activation+0.000
are
Token are
Feature activation+0.414
actually
Token actually
Feature activation+1.350
pointers
Token pointers
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+5.312
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
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Ontario
Token Ontario
Feature activation+0.000
Reign
Token Reign
Feature activation+0.082
will
Token will
Feature activation+0.286
move
Token move
Feature activation+6.158
to
Token to
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.000
,
Token,
Feature activation+0.000
New
Token New
Feature activation+0.000
Hampshire
Token Hampshire
Feature activation+0.000

INTERVAL 3.718 - 4.958
CONTAINS 0.002%

annually
Token annually
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
general
Token general
Feature activation+0.000
fund
Token fund
Feature activation+0.000
and
Token and
Feature activation+4.030
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.000
million
Token million
Feature activation+0.000
grants
Token grants
Feature activation+0.000
in
Token in
Feature activation+0.471
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Vik
Token Vik
Feature activation+0.000
as
Tokenas
Feature activation+1.651
Sw
Token Sw
Feature activation+0.389
ar
Tokenar
Feature activation+4.031
up
Tokenup
Feature activation+0.000
(@
Token (@
Feature activation+0.000
ME
TokenME
Feature activation+0.000
A
TokenA
Feature activation+0.000
India
TokenIndia
Feature activation+0.000
re
Tokenre
Feature activation+0.000
under
Token under
Feature activation+0.000
age
Token age
Feature activation+0.000
50
Token 50
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+4.382
$
Token $
Feature activation+0.000
22
Token22
Feature activation+0.000
,
Token,
Feature activation+0.000
500
Token500
Feature activation+0.896
if
Token if
Feature activation+0.000
71
Token71
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+2.020
,
Token,
Feature activation+6.617
which
Token which
Feature activation+0.167
was
Token was
Feature activation+4.287
much
Token much
Feature activation+1.110
tougher
Token tougher
Feature activation+0.000
competition
Token competition
Feature activation+0.859
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
us
Token us
Feature activation+0.000
actually
Token actually
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
statutes
Token statutes
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+3.798
passing
Token passing
Feature activation+0.000
them
Token them
Feature activation+0.171
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
changing
Token changing
Feature activation+0.000

INTERVAL 2.479 - 3.718
CONTAINS 0.005%

though
Token though
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.082
true
Token true
Feature activation+2.891
for
Token for
Feature activation+0.571
years
Token years
Feature activation+2.883
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
worked
Token worked
Feature activation+0.000
fine
Token fine
Feature activation+4.858
under
Token under
Feature activation+0.000
size
Token size
Feature activation+0.000
up
Token up
Feature activation+0.000
and
Token and
Feature activation+0.795
a
Token a
Feature activation+0.000
cup
Token cup
Feature activation+1.529
size
Token size
Feature activation+3.442
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
I
Token I
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
with
Token with
Feature activation+0.000
.
Token.
Feature activation+2.716
We
Token We
Feature activation+0.000
bring
Token bring
Feature activation+0.000
in
Token in
Feature activation+1.842
players
Token players
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Update
TokenUpdate
Feature activation+0.000
2
Token 2
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
App
Token App
Feature activation+2.854
Ind
TokenInd
Feature activation+0.000
icator
Tokenicator
Feature activation+0.000
features
Token features
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
es
Tokenes
Feature activation+0.000
in
Token in
Feature activation+0.000
midfield
Token midfield
Feature activation+0.000
.
Token.
Feature activation+0.000
Tab
Token Tab
Feature activation+0.000
Ramos
Token Ramos
Feature activation+2.540
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
free
Token free
Feature activation+0.000
kick
Token kick
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.239 - 2.479
CONTAINS 0.019%

did
Token did
Feature activation+0.000
6
Token 6
Feature activation+0.000
.
Token.
Feature activation+0.000
14
Token14
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+1.262
.
Token.
Feature activation+0.085
For
Token For
Feature activation+0.000
a
Token a
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
,
Token,
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
but
Token but
Feature activation+1.255
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
62
Token 62
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
.
Token.
Feature activation+0.000
wh
Tokenwh
Feature activation+0.000
ats
Tokenats
Feature activation+0.000
app
Tokenapp
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.331
Credits
TokenCredits
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.030
+
Token+
Feature activation+0.000
Imm
Token Imm
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Vik
Token Vik
Feature activation+0.000
as
Tokenas
Feature activation+2.066
Sw
Token Sw
Feature activation+0.000
ar
Tokenar
Feature activation+3.781
up
Tokenup
Feature activation+0.000
(@
Token (@
Feature activation+0.000
ME
TokenME
Feature activation+0.000
Ups
Token Ups
Feature activation+0.000
:
Token:
Feature activation+0.000
Any
Token Any
Feature activation+0.000
type
Token type
Feature activation+0.000
of
Token of
Feature activation+0.000
push
Token push
Feature activation+1.870
ups
Tokenups
Feature activation+0.000
exercise
Token exercise
Feature activation+0.000
works
Token works
Feature activation+0.000
great
Token great
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.000 - 1.239
CONTAINS 99.970%

the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
would
Token would
Feature activation+0.000
stop
Token stop
Feature activation+0.000
moving
Token moving
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
Ken
Token Ken
Feature activation+0.000
Cald
Token Cald
Feature activation+0.000
do
Token do
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
other
Token other
Feature activation+0.000
people
Token people
Feature activation+0.000
push
Token push
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
being
Token being
Feature activation+0.000
bought
Token bought
Feature activation+0.000
play
Token play
Feature activation+0.000
these
Token these
Feature activation+0.000
sick
Token sick
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
blood
Token blood
Feature activation+0.000
is
Token is
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
hands
Token hands
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
won
Token won
Feature activation+0.000
102
Token 102
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
mean
Token mean
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
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 H10.1: (feature 6296)

TOP ACTIVATIONS
MAX = 10.754

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.517
A
TokenA
Feature activation+0.000
F
Token F
Feature activation+0.000
INE
TokenINE
Feature activation+4.823
Gael
Token Gael
Feature activation+10.754
back
Token back
Feature activation+0.000
ben
Tokenben
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000
it
Token it
Feature activation+0.000
fades
Token fades
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.700
you
Token you
Feature activation+0.665
do
Token do
Feature activation+9.773
what
Token what
Feature activation+1.618
?'
Token?'
Feature activation+0.000
she
Token she
Feature activation+0.000
ad
Token ad
Feature activation+0.000
or
Tokenor
Feature activation+0.000
of
Token of
Feature activation+3.746
the
Token the
Feature activation+1.214
military
Token military
Feature activation+0.000
gear
Token gear
Feature activation+0.098
made
Token made
Feature activation+0.074
for
Token for
Feature activation+7.958
Starship
Token Starship
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
opers
Tokenopers
Feature activation+0.571
was
Token was
Feature activation+0.039
re
Token re
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
in
Token in
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
(
Token (
Feature activation+0.000
who
Tokenwho
Feature activation+0.000
associated
Token associated
Feature activation+7.757
the
Token the
Feature activation+4.102
agency
Token agency
Feature activation+0.000
with
Token with
Feature activation+3.420
the
Token the
Feature activation+2.834
Clinton
Token Clinton
Feature activation+0.000
US
Token US
Feature activation+1.043
government
Token government
Feature activation+0.120
should
Token should
Feature activation+0.957
stop
Token stop
Feature activation+6.707
railing
Token railing
Feature activation+0.000
against
Token against
Feature activation+7.649
encryption
Token encryption
Feature activation+0.493
and
Token and
Feature activation+1.708
should
Token should
Feature activation+0.000
support
Token support
Feature activation+7.127
strong
Token strong
Feature activation+1.008
and
Token and
Feature activation+0.000
curb
Token curb
Feature activation+4.661
its
Token its
Feature activation+0.220
authority
Token authority
Feature activation+0.000
.
Token.
Feature activation+5.122
Although
Token Although
Feature activation+7.599
some
Token some
Feature activation+5.505
health
Token health
Feature activation+0.000
IT
Token IT
Feature activation+0.000
companies
Token companies
Feature activation+0.000
see
Token see
Feature activation+9.092
it
Token it
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
long
Token long
Feature activation+0.000
before
Token before
Feature activation+7.509
other
Token other
Feature activation+4.124
handset
Token handset
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
offer
Token offer
Feature activation+2.259
the
Token the
Feature activation+3.984
around
Token around
Feature activation+0.056
in
Token in
Feature activation+0.074
2010
Token 2010
Feature activation+0.000
that
Token that
Feature activation+0.030
would
Token would
Feature activation+0.000
require
Token require
Feature activation+7.469
back
Token back
Feature activation+0.000
doors
Tokendoors
Feature activation+0.000
in
Token in
Feature activation+2.245
encrypted
Token encrypted
Feature activation+1.245
communication
Token communication
Feature activation+0.000
railing
Token railing
Feature activation+0.000
against
Token against
Feature activation+7.649
encryption
Token encryption
Feature activation+0.493
and
Token and
Feature activation+1.708
should
Token should
Feature activation+0.000
support
Token support
Feature activation+7.127
strong
Token strong
Feature activation+1.008
crypto
Token crypto
Feature activation+0.144
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+2.279
asking
Token asking
Feature activation+1.177
concerns
Token concerns
Feature activation+0.000
about
Token about
Feature activation+1.649
the
Token the
Feature activation+3.601
security
Token security
Feature activation+0.000
of
Token of
Feature activation+4.720
the
Token the
Feature activation+7.074
first
Token first
Feature activation+0.408
method
Token method
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.240
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.535
where
Token where
Feature activation+0.247
your
Token your
Feature activation+1.216
your
Token your
Feature activation+0.981
favourite
Token favourite
Feature activation+7.028
authors
Token authors
Feature activation+0.106
and
Token and
Feature activation+0.526
events
Token events
Feature activation+0.150
took
Token took
Feature activation+0.000
place
Token place
Feature activation+0.863
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
NSA
Token NSA
Feature activation+0.373
,
Token,
Feature activation+0.000
thinks
Token thinks
Feature activation+6.831
the
Token the
Feature activation+4.335
US
Token US
Feature activation+1.043
government
Token government
Feature activation+0.120
should
Token should
Feature activation+0.957
stop
Token stop
Feature activation+6.707
thinks
Token thinks
Feature activation+6.831
the
Token the
Feature activation+4.335
US
Token US
Feature activation+1.043
government
Token government
Feature activation+0.120
should
Token should
Feature activation+0.957
stop
Token stop
Feature activation+6.707
railing
Token railing
Feature activation+0.000
against
Token against
Feature activation+7.649
encryption
Token encryption
Feature activation+0.493
and
Token and
Feature activation+1.708
should
Token should
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
screen
Token screen
Feature activation+0.000
moves
Token moves
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+6.519
forth
Token forth
Feature activation+0.000
accordingly
Token accordingly
Feature activation+0.000
,
Token,
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
back
Token back
Feature activation+0.000
the
Token the
Feature activation+4.472
phone
Token phone
Feature activation+0.000
.
Token.
Feature activation+2.743
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.575
The
TokenThe
Feature activation+6.316
idea
Token idea
Feature activation+0.000
works
Token works
Feature activation+0.000
well
Token well
Feature activation+0.000
enough
Token enough
Feature activation+0.000
,
Token,
Feature activation+0.356
Body
Token Body
Feature activation+0.000
Armor
Token Armor
Feature activation+0.000
and
Token and
Feature activation+0.000
Helm
Token Helm
Feature activation+0.000
ets
Tokenets
Feature activation+0.000
from
Token from
Feature activation+6.209
Starship
Token Starship
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
opers
Tokenopers
Feature activation+0.000
,
Token,
Feature activation+0.737
Planet
Token Planet
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
strong
Token strong
Feature activation+0.000
evidence
Token evidence
Feature activation+0.189
to
Token to
Feature activation+6.149
back
Token back
Feature activation+0.000
a
Token a
Feature activation+0.000
licensed
Token licensed
Feature activation+0.000
cannabis
Token cannabis
Feature activation+0.000
-
Token-
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.407
ĺ
Tokenĺ
Feature activation+5.999
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
bill
Token bill
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
40
Token 40
Feature activation+0.000
yards
Token yards
Feature activation+0.396
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
touchdown
Token touchdown
Feature activation+2.925
.
Token.
Feature activation+5.872
As
Token As
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
letting
Token letting
Feature activation+0.000
strangers
Token strangers
Feature activation+0.000
in
Token in
Feature activation+0.584
to
Token to
Feature activation+0.122
the
Token the
Feature activation+5.838
security
Token security
Feature activation+0.000
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 11.580

<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
A
TokenA
Feature activation-0.008
Top resid features:
F
Token F
Feature activation-0.018
Top resid features:
INE
TokenINE
Feature activation-0.018
Top resid features:
Gael
Token Gael
Feature activation+0.011
Top resid features:
back
Token back
Feature activation+11.580
Top resid features:
ben
Tokenben
Feature activation+0.036
Top resid features:
cher
Tokencher
Feature activation-0.115
Top resid features:
says
Token says
Feature activation+0.006
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
how
Token how
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
do
Token do
Feature activation+0.001
Top resid features:
back
Token back
Feature activation+8.110
Top resid features:
-
Token-
Feature activation+1.384
Top resid features:
up
Tokenup
Feature activation+0.729
Top resid features:
vocals
Token vocals
Feature activation+0.056
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
re
Token re
Feature activation-0.005
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
pur
Tokenpur
Feature activation-0.001
Top resid features:
posed
Tokenposed
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
Back
Token Back
Feature activation+5.319
Top resid features:
To
Token To
Feature activation+0.007
Top resid features:
The
Token The
Feature activation+0.004
Top resid features:
Future
Token Future
Feature activation-0.007
Top resid features:
Part
Token Part
Feature activation-0.017
Top resid features:
II
Token II
Feature activation-0.002
Top resid features:
lower
Token lower
Feature activation-0.046
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
back
Tokenback
Feature activation+0.307
Top resid features:
pain
Token pain
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Back
Token Back
Feature activation+6.325
Top resid features:
surgeons
Token surgeons
Feature activation+0.006
Top resid features:
went
Token went
Feature activation-0.009
Top resid features:
ballistic
Token ballistic
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
Strong
Token Strong
Feature activation+0.001
Top resid features:
ly
Tokenly
Feature activation-0.002
Top resid features:
*
Token *
Feature activation-0.004
Top resid features:
Against
TokenAgainst
Feature activation-0.007
Top resid features:
*
Token*
Feature activation-0.009
Top resid features:
Back
Token Back
Feature activation+7.792
Top resid features:
door
Tokendoor
Feature activation+0.481
Top resid features:
ing
Tokening
Feature activation+0.036
Top resid features:
Enc
Token Enc
Feature activation-0.021
Top resid features:
ryption
Tokenryption
Feature activation+0.116
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
lower
Token lower
Feature activation-0.010
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
back
Tokenback
Feature activation+0.173
Top resid features:
pain
Token pain
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
Back
Token Back
Feature activation+6.592
Top resid features:
surgeons
Token surgeons
Feature activation+0.004
Top resid features:
went
Token went
Feature activation-0.002
Top resid features:
ballistic
Token ballistic
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
In
Token In
Feature activation-0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
mode
Token mode
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Back
Token Back
Feature activation+7.661
Top resid features:
fl
Tokenfl
Feature activation+0.007
Top resid features:
ip
Tokenip
Feature activation+0.019
Top resid features:
displays
Token displays
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
clock
Token clock
Feature activation-0.006
Top resid features:
Live
Token Live
Feature activation-0.096
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
modified
Token modified
Feature activation-0.080
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
include
Token include
Feature activation-0.005
Top resid features:
back
Token back
Feature activation+7.799
Top resid features:
doors
Tokendoors
Feature activation+0.110
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
allow
Token allow
Feature activation-0.005
Top resid features:
FBI
Token FBI
Feature activation+0.266
Top resid features:
surveillance
Token surveillance
Feature activation+0.027
Top resid features:
Strong
Token Strong
Feature activation+0.006
Top resid features:
ly
Tokenly
Feature activation-0.008
Top resid features:
*
Token *
Feature activation-0.003
Top resid features:
Against
TokenAgainst
Feature activation-0.023
Top resid features:
*
Token*
Feature activation-0.007
Top resid features:
Back
Token Back
Feature activation+7.376
Top resid features:
door
Tokendoor
Feature activation+0.436
Top resid features:
ing
Tokening
Feature activation+0.078
Top resid features:
Enc
Token Enc
Feature activation+0.015
Top resid features:
ryption
Tokenryption
Feature activation+0.109
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation-0.007
Top resid features:
stored
Token stored
Feature activation-0.010
Top resid features:
on
Token on
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
back
Token back
Feature activation+6.738
Top resid features:
-
Token-
Feature activation+1.049
Top resid features:
end
Tokenend
Feature activation+0.067
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
then
Token then
Feature activation+0.005
Top resid features:
checked
Token checked
Feature activation+0.056
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
most
Token most
Feature activation+0.005
Top resid features:
beautiful
Token beautiful
Feature activation-0.024
Top resid features:
back
Token back
Feature activation+7.898
Top resid features:
drops
Tokendrops
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
Harbour
Token Harbour
Feature activation-0.036
Top resid features:
front
Tokenfront
Feature activation-0.020
Top resid features:
Centre
Token Centre
Feature activation-0.059
Top resid features:
Strong
Token Strong
Feature activation+0.008
Top resid features:
ly
Tokenly
Feature activation-0.013
Top resid features:
*
Token *
Feature activation-0.011
Top resid features:
Against
TokenAgainst
Feature activation-0.028
Top resid features:
*
Token*
Feature activation+0.001
Top resid features:
Back
Token Back
Feature activation+6.935
Top resid features:
door
Tokendoor
Feature activation+0.510
Top resid features:
ing
Tokening
Feature activation+0.035
Top resid features:
Enc
Token Enc
Feature activation-0.001
Top resid features:
ryption
Tokenryption
Feature activation+0.116
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Strong
Token Strong
Feature activation+0.001
Top resid features:
ly
Tokenly
Feature activation-0.003
Top resid features:
*
Token *
Feature activation-0.003
Top resid features:
Against
TokenAgainst
Feature activation-0.015
Top resid features:
*
Token*
Feature activation+0.003
Top resid features:
Back
Token Back
Feature activation+6.674
Top resid features:
door
Tokendoor
Feature activation+0.636
Top resid features:
ing
Tokening
Feature activation+0.098
Top resid features:
Enc
Token Enc
Feature activation-0.005
Top resid features:
ryption
Tokenryption
Feature activation+0.101
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ŀ
TokenĿ
Feature activation+0.019
Top resid features:
The
Token The
Feature activation+0.026
Top resid features:
screen
Token screen
Feature activation+0.042
Top resid features:
moves
Token moves
Feature activation+0.042
Top resid features:
back
Token back
Feature activation+7.071
Top resid features:
and
Token and
Feature activation+0.133
Top resid features:
forth
Token forth
Feature activation+0.000
Top resid features:
accordingly
Token accordingly
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
pushing
Token pushing
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
mode
Token mode
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
Back
Token Back
Feature activation+6.437
Top resid features:
fl
Tokenfl
Feature activation+0.005
Top resid features:
ip
Tokenip
Feature activation-0.019
Top resid features:
displays
Token displays
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
clock
Token clock
Feature activation-0.021
Top resid features:
re
Token re
Feature activation-0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
pur
Tokenpur
Feature activation-0.002
Top resid features:
posed
Tokenposed
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
Back
Token Back
Feature activation+3.763
Top resid features:
To
Token To
Feature activation+0.012
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
Future
Token Future
Feature activation+0.036
Top resid features:
Part
Token Part
Feature activation-0.016
Top resid features:
II
Token II
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
no
Token no
Feature activation+0.006
Top resid features:
strong
Token strong
Feature activation-0.006
Top resid features:
evidence
Token evidence
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
back
Token back
Feature activation+7.004
Top resid features:
a
Token a
Feature activation+0.039
Top resid features:
licensed
Token licensed
Feature activation-0.027
Top resid features:
cannabis
Token cannabis
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
ext
Tokenext
Feature activation-0.000
Top resid features:
term
Token term
Feature activation-0.003
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.015
Top resid features:
ĺ
Tokenĺ
Feature activation-0.036
Top resid features:
back
Tokenback
Feature activation+6.634
Top resid features:
door
Tokendoor
Feature activation+0.086
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
so
Token so
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.046
Top resid features:
back
Token back
Feature activation+6.105
Top resid features:
âĢ
TokenâĢ
Feature activation+0.245
Top resid features:
Ļ
TokenĻ
Feature activation+0.095
Top resid features:
s
Tokens
Feature activation+0.045
Top resid features:
stat
Token stat
Feature activation-0.018
Top resid features:
line
Token line
Feature activation+0.020
Top resid features:
leaves
Token leaves
Feature activation-0.173
Top resid features:
in
Token in
Feature activation+0.015
Top resid features:
front
Token front
Feature activation+0.045
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
back
Token back
Feature activation+5.824
Top resid features:
door
Token door
Feature activation+0.061
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
went
Token went
Feature activation+0.002
Top resid features:
out
Token out
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.50

Head 2: 0.04

Head 3: 0.12

Head 4: 0.03

Head 5: 0.02

Head 6: 0.05

Head 7: 0.07

Head 8: 0.03

Head 9: 0.02

Head 10: 0.06

Head 11: 0.04

Positive logits

Back7.00

back6.69

Back6.55

BACK6.42

back6.33

backs5.62

backs5.35

BACK5.09

backend4.24

front3.74

Front3.64

backward3.47

backwards3.46

front3.38

backer3.37

Front3.33

backdoor3.25

forth3.19

backing3.05

backed3.03

Negative logits

Ideal-2.22

Chosen-2.20

adish-2.05

lime-2.00

ese-1.92

inite-1.92

amaru-1.88

anth-1.85

Phill-1.84

ominated-1.84

Hate-1.84

iscopal-1.82

religiously-1.81

DonaldTrump-1.81

Won-1.79

Medium-1.78

Average-1.78

ose-1.77

unob-1.77

Equal-1.77

INTERVAL 9.678 - 10.754
CONTAINS 0.000%

it
Token it
Feature activation+0.000
fades
Token fades
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.700
you
Token you
Feature activation+0.665
do
Token do
Feature activation+9.773
what
Token what
Feature activation+1.618
?'
Token?'
Feature activation+0.000
she
Token she
Feature activation+0.000
ad
Token ad
Feature activation+0.000
or
Tokenor
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.517
A
TokenA
Feature activation+0.000
F
Token F
Feature activation+0.000
INE
TokenINE
Feature activation+4.823
Gael
Token Gael
Feature activation+10.754
back
Token back
Feature activation+0.000
ben
Tokenben
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 8.603 - 9.678
CONTAINS 0.000%

INTERVAL 7.528 - 8.603
CONTAINS 0.000%

US
Token US
Feature activation+1.043
government
Token government
Feature activation+0.120
should
Token should
Feature activation+0.957
stop
Token stop
Feature activation+6.707
railing
Token railing
Feature activation+0.000
against
Token against
Feature activation+7.649
encryption
Token encryption
Feature activation+0.493
and
Token and
Feature activation+1.708
should
Token should
Feature activation+0.000
support
Token support
Feature activation+7.127
strong
Token strong
Feature activation+1.008
Republicans
Token Republicans
Feature activation+0.000
in
Token in
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
(
Token (
Feature activation+0.000
who
Tokenwho
Feature activation+0.000
associated
Token associated
Feature activation+7.757
the
Token the
Feature activation+4.102
agency
Token agency
Feature activation+0.000
with
Token with
Feature activation+3.420
the
Token the
Feature activation+2.834
Clinton
Token Clinton
Feature activation+0.000
and
Token and
Feature activation+0.000
curb
Token curb
Feature activation+4.661
its
Token its
Feature activation+0.220
authority
Token authority
Feature activation+0.000
.
Token.
Feature activation+5.122
Although
Token Although
Feature activation+7.599
some
Token some
Feature activation+5.505
health
Token health
Feature activation+0.000
IT
Token IT
Feature activation+0.000
companies
Token companies
Feature activation+0.000
see
Token see
Feature activation+9.092
of
Token of
Feature activation+3.746
the
Token the
Feature activation+1.214
military
Token military
Feature activation+0.000
gear
Token gear
Feature activation+0.098
made
Token made
Feature activation+0.074
for
Token for
Feature activation+7.958
Starship
Token Starship
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
opers
Tokenopers
Feature activation+0.571
was
Token was
Feature activation+0.039
re
Token re
Feature activation+0.000

INTERVAL 6.452 - 7.528
CONTAINS 0.001%

concerns
Token concerns
Feature activation+0.000
about
Token about
Feature activation+1.649
the
Token the
Feature activation+3.601
security
Token security
Feature activation+0.000
of
Token of
Feature activation+4.720
the
Token the
Feature activation+7.074
first
Token first
Feature activation+0.408
method
Token method
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.240
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.535
where
Token where
Feature activation+0.247
your
Token your
Feature activation+1.216
your
Token your
Feature activation+0.981
favourite
Token favourite
Feature activation+7.028
authors
Token authors
Feature activation+0.106
and
Token and
Feature activation+0.526
events
Token events
Feature activation+0.150
took
Token took
Feature activation+0.000
place
Token place
Feature activation+0.863
around
Token around
Feature activation+0.056
in
Token in
Feature activation+0.074
2010
Token 2010
Feature activation+0.000
that
Token that
Feature activation+0.030
would
Token would
Feature activation+0.000
require
Token require
Feature activation+7.469
back
Token back
Feature activation+0.000
doors
Tokendoors
Feature activation+0.000
in
Token in
Feature activation+2.245
encrypted
Token encrypted
Feature activation+1.245
communication
Token communication
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
screen
Token screen
Feature activation+0.000
moves
Token moves
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+6.519
forth
Token forth
Feature activation+0.000
accordingly
Token accordingly
Feature activation+0.000
,
Token,
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
back
Token back
Feature activation+0.000
railing
Token railing
Feature activation+0.000
against
Token against
Feature activation+7.649
encryption
Token encryption
Feature activation+0.493
and
Token and
Feature activation+1.708
should
Token should
Feature activation+0.000
support
Token support
Feature activation+7.127
strong
Token strong
Feature activation+1.008
crypto
Token crypto
Feature activation+0.144
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+2.279
asking
Token asking
Feature activation+1.177

INTERVAL 5.377 - 6.452
CONTAINS 0.002%

&
Token&
Feature activation+0.000
M
TokenM
Feature activation+1.090
club
Token club
Feature activation+0.000
.
Token.
Feature activation+5.824
Ċ
TokenĊ
Feature activation+0.332
Ċ
TokenĊ
Feature activation+5.730
Close
TokenClose
Feature activation+0.000
of
Token of
Feature activation+0.845
play
Token play
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.280
to
Token to
Feature activation+0.000
letting
Token letting
Feature activation+0.000
strangers
Token strangers
Feature activation+0.000
in
Token in
Feature activation+0.584
to
Token to
Feature activation+0.122
the
Token the
Feature activation+5.838
security
Token security
Feature activation+0.000
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
strong
Token strong
Feature activation+0.000
evidence
Token evidence
Feature activation+0.189
to
Token to
Feature activation+6.149
back
Token back
Feature activation+0.000
a
Token a
Feature activation+0.000
licensed
Token licensed
Feature activation+0.000
cannabis
Token cannabis
Feature activation+0.000
-
Token-
Feature activation+0.000
40
Token 40
Feature activation+0.000
yards
Token yards
Feature activation+0.396
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
touchdown
Token touchdown
Feature activation+2.925
.
Token.
Feature activation+5.872
As
Token As
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token"
Feature activation+0.000
without
Token without
Feature activation+0.000
navigating
Token navigating
Feature activation+0.000
to
Token to
Feature activation+1.149
a
Token a
Feature activation+3.066
different
Token different
Feature activation+5.693
page
Token page
Feature activation+0.040
and
Token and
Feature activation+0.000
knowing
Token knowing
Feature activation+0.000
about
Token about
Feature activation+0.000
available
Token available
Feature activation+3.548

INTERVAL 4.301 - 5.377
CONTAINS 0.002%

budget
Token budget
Feature activation+0.000
and
Token and
Feature activation+0.000
curb
Token curb
Feature activation+4.661
its
Token its
Feature activation+0.220
authority
Token authority
Feature activation+0.000
.
Token.
Feature activation+5.122
Although
Token Although
Feature activation+7.599
some
Token some
Feature activation+5.505
health
Token health
Feature activation+0.000
IT
Token IT
Feature activation+0.000
companies
Token companies
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.053
s
Tokens
Feature activation+0.884
budget
Token budget
Feature activation+0.000
and
Token and
Feature activation+0.000
curb
Token curb
Feature activation+4.661
its
Token its
Feature activation+0.220
authority
Token authority
Feature activation+0.000
.
Token.
Feature activation+5.122
Although
Token Although
Feature activation+7.599
some
Token some
Feature activation+5.505
laws
Token laws
Feature activation+0.000
would
Token would
Feature activation+0.674
represent
Token represent
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
roll
Token roll
Feature activation+4.363
back
Tokenback
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
's
Token's
Feature activation+0.000
felt
Token felt
Feature activation+0.000
so
Token so
Feature activation+0.000
damn
Token damn
Feature activation+0.000
good
Token good
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+4.483
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
transition
Token transition
Feature activation+0.000
phrases
Token phrases
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+2.229
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
in
Token in
Feature activation+1.590
:
Token:
Feature activation+4.817
You
Token You
Feature activation+0.223
bought
Token bought
Feature activation+0.474
your
Token your
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
dress
Token dress
Feature activation+0.588

INTERVAL 3.226 - 4.301
CONTAINS 0.004%

,
Token,
Feature activation+0.000
before
Token before
Feature activation+0.000
promising
Token promising
Feature activation+1.912
to
Token to
Feature activation+1.319
'
Token '
Feature activation+0.386
try
Tokentry
Feature activation+3.359
not
Token not
Feature activation+0.583
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.153
it
Token it
Feature activation+0.000
sound
Token sound
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
in
Token in
Feature activation+0.000
Week
Token Week
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+3.374
F
Token F
Feature activation+0.000
ourn
Tokenourn
Feature activation+0.000
ette
Tokenette
Feature activation+0.000
early
Token early
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
tracts
Token tracts
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
.[
Token.[
Feature activation+0.000
3
Token3
Feature activation+0.000
]
Token]
Feature activation+3.917
The
Token The
Feature activation+1.836
ideas
Token ideas
Feature activation+0.000
of
Token of
Feature activation+4.557
modern
Token modern
Feature activation+2.694
hom
Token hom
Feature activation+0.000
Street
Token Street
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
acc
Token acc
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
les
Token les
Feature activation+3.234
me
Token me
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
urs
Tokenurs
Feature activation+0.000
é
Token é
Feature activation+0.000
c
Tokenc
Feature activation+0.000
drive
Token drive
Feature activation+0.000
to
Token to
Feature activation+0.595
hire
Token hire
Feature activation+0.702
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
500
Token500
Feature activation+3.228
new
Token new
Feature activation+2.357
work
Token work
Feature activation+0.000
coaches
Token coaches
Feature activation+0.000
.
Token.
Feature activation+1.119
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.151 - 3.226
CONTAINS 0.008%

you
Token you
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+2.385
a
Token a
Feature activation+1.825
car
Token car
Feature activation+1.328
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Member
Token Member
Feature activation+0.000
Activity
TokenActivity
Feature activation+0.000
:
Token:
Feature activation+0.464
448
Token 448
Feature activation+0.000
Merit
TokenMerit
Feature activation+0.000
:
Token:
Feature activation+2.714
250
Token 250
Feature activation+0.000
Re
Token Re
Feature activation+0.000
:
Token:
Feature activation+0.000
[
Token [
Feature activation+0.000
ANN
TokenANN
Feature activation+0.000
FBI
Token FBI
Feature activation+0.045
surveillance
Token surveillance
Feature activation+0.000
.
Token.
Feature activation+1.877
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.970
The
TokenThe
Feature activation+2.748
news
Token news
Feature activation+0.000
comes
Token comes
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
heels
Token heels
Feature activation+0.000
and
Token and
Feature activation+0.000
having
Token having
Feature activation+0.000
two
Token two
Feature activation+1.384
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.848
top
Token top
Feature activation+2.290
11
Token 11
Feature activation+3.468
picks
Token picks
Feature activation+0.000
in
Token in
Feature activation+0.940
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
it
Token it
Feature activation+0.000
touches
Token touches
Feature activation+0.000
the
Token the
Feature activation+0.017
ground
Token ground
Feature activation+0.000
.
Token.
Feature activation+1.810
The
Token The
Feature activation+2.515
play
Token play
Feature activation+0.000
stops
Token stops
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+3.113
player
Token player
Feature activation+0.000

INTERVAL 1.075 - 2.151
CONTAINS 0.024%

moved
Token moved
Feature activation+0.000
back
Token back
Feature activation+0.100
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
plate
Token plate
Feature activation+0.000
and
Token and
Feature activation+1.596
stayed
Token stayed
Feature activation+0.275
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
strike
Token strike
Feature activation+0.000
zone
Token zone
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
come
Token come
Feature activation+0.000
up
Token up
Feature activation+0.000
again
Token again
Feature activation+0.000
and
Token and
Feature activation+1.172
again
Token again
Feature activation+0.000
in
Token in
Feature activation+0.000
human
Token human
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.533
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.873
top
Token top
Feature activation+1.033
prospects
Token prospects
Feature activation+0.000
in
Token in
Feature activation+1.703
the
Token the
Feature activation+2.896
organization
Token organization
Feature activation+0.000
,
Token,
Feature activation+0.485
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
MAN
TokenMAN
Feature activation+0.000
Ap
Token Ap
Feature activation+0.000
es
Tokenes
Feature activation+0.000
(
Token (
Feature activation+0.000
2001
Token2001
Feature activation+0.000
),
Token),
Feature activation+0.326
and
Token and
Feature activation+1.174
Firefly
Token Firefly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.072
Most
TokenMost
Feature activation+1.725
of
Token of
Feature activation+3.746
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.658
what
Token what
Feature activation+0.000
tank
Token tank
Feature activation+0.000
he
Token he
Feature activation+1.686
's
Token's
Feature activation+1.623
in
Token in
Feature activation+0.000
,
Token,
Feature activation+2.187
he
Token he
Feature activation+0.762
got
Token got
Feature activation+0.000
to
Token to
Feature activation+2.843

INTERVAL 0.000 - 1.075
CONTAINS 99.959%

to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
like
Token like
Feature activation+0.000
their
Token their
Feature activation+0.000
Mi
Token Mi
Feature activation+0.000
is
Tokenis
Feature activation+0.000
.
Token.
Feature activation+0.000
Mi
Token Mi
Feature activation+0.000
is
Tokenis
Feature activation+0.000
allow
Token allow
Feature activation+0.000
players
Token players
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
was
Token was
Feature activation+0.000
appealed
Token appealed
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
upl
Token upl
Feature activation+0.000
ifted
Tokenifted
Feature activation+0.000
and
Token and
Feature activation+0.000
enabled
Token enabled
Feature activation+0.000
on
Token on
Feature activation+0.000
Y
TokenY
Feature activation+0.205
FF
TokenFF
Feature activation+0.000
News
Token News
Feature activation+0.000
4
Token 4
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Don
Token Don
Feature activation+0.000
nie
Tokennie
Feature activation+0.000
Walsh
Token Walsh
Feature activation+0.000
-
Token -
Feature activation+0.000
Looks
Token Looks
Feature activation+0.000
like
Token like
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
town
Token town
Feature activation+0.000
to
Token to
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H10.1: (feature 13195)

TOP ACTIVATIONS
MAX = 9.189

Ċ
TokenĊ
Feature activation+1.989
Do
TokenDo
Feature activation+1.280
you
Token you
Feature activation+0.000
feel
Token feel
Feature activation+0.698
confident
Token confident
Feature activation+1.043
on
Token on
Feature activation+9.189
all
Token all
Feature activation+3.280
maps
Token maps
Feature activation+0.412
,
Token,
Feature activation+1.172
or
Token or
Feature activation+0.276
are
Token are
Feature activation+1.605
though
Token though
Feature activation+6.873
we
Token we
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
on
Token on
Feature activation+8.477
the
Token the
Feature activation+5.773
CT
Token CT
Feature activation+0.000
side
Token side
Feature activation+1.087
,
Token,
Feature activation+5.343
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
if
Token if
Feature activation+8.260
they
Token they
Feature activation+0.000
put
Token put
Feature activation+3.614
N
Token N
Feature activation+0.000
uke
Tokenuke
Feature activation+0.000
or
Token or
Feature activation+2.547
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+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+7.975
over
Token over
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+2.383
and
Token and
Feature activation+3.406
expecting
Token expecting
Feature activation+0.000
admitted
Token admitted
Feature activation+0.016
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
percent
Token percent
Feature activation+1.008
of
Token of
Feature activation+7.844
their
Token their
Feature activation+6.264
nearly
Token nearly
Feature activation+0.402
39
Token 39
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+3.429
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+3.019
So
Token So
Feature activation+0.954
when
Token when
Feature activation+5.990
they
Token they
Feature activation+0.000
picked
Token picked
Feature activation+7.796
Over
Token Over
Feature activation+0.000
pass
Tokenpass
Feature activation+0.029
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
currently
Token currently
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.996
an
Token an
Feature activation+1.257
update
Token update
Feature activation+0.000
to
Token to
Feature activation+7.567
improve
Token improve
Feature activation+0.029
the
Token the
Feature activation+0.376
frame
Token frame
Feature activation+0.000
rate
Token rate
Feature activation+0.000
issues
Token issues
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
needle
Token needle
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+7.192
over
Token over
Feature activation+0.000
again
Token again
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
rate
Token rate
Feature activation+0.000
and
Token and
Feature activation+0.000
rum
Token rum
Feature activation+0.000
ble
Tokenble
Feature activation+0.000
issues
Token issues
Feature activation+0.000
in
Token in
Feature activation+7.187
Over
Token Over
Feature activation+0.197
cooked
Tokencooked
Feature activation+0.000
:
Token:
Feature activation+0.000
Special
Token Special
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
so
Token so
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.052
even
Token even
Feature activation+0.000
though
Token though
Feature activation+6.873
we
Token we
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
on
Token on
Feature activation+8.477
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.801
to
Token to
Feature activation+1.947
my
Token my
Feature activation+0.000
team
Token team
Feature activation+0.000
that
Token that
Feature activation+6.828
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
it
Token it
Feature activation+4.543
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
subway
Token subway
Feature activation+0.000
extension
Token extension
Feature activation+0.858
is
Token is
Feature activation+6.781
further
Token further
Feature activation+5.437
ahead
Token ahead
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
relief
Token relief
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
percent
Token percent
Feature activation+1.008
of
Token of
Feature activation+7.844
their
Token their
Feature activation+6.264
nearly
Token nearly
Feature activation+0.402
39
Token 39
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+3.429
applicants
Token applicants
Feature activation+0.000
got
Token got
Feature activation+0.000
six
Token six
Feature activation+0.852
rounds
Token rounds
Feature activation+0.000
as
Token as
Feature activation+0.799
CT
Token CT
Feature activation+0.507
and
Token and
Feature activation+6.158
then
Token then
Feature activation+5.160
we
Token we
Feature activation+0.000
managed
Token managed
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
Feature activation+0.000
shoes
Token shoes
Feature activation+0.000
.
Token.
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
Grey
Token Grey
Feature activation+2.353
:
Token:
Feature activation+0.000
Black
Token Black
Feature activation+6.039
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
There
TokenThere
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+4.448
the
Token the
Feature activation+3.184
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+3.019
So
Token So
Feature activation+0.954
when
Token when
Feature activation+5.990
they
Token they
Feature activation+0.000
picked
Token picked
Feature activation+7.796
Over
Token Over
Feature activation+0.000
pass
Tokenpass
Feature activation+0.029
I
Token I
Feature activation+0.000
200
Token200
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
and
Token and
Feature activation+1.439
couples
Token couples
Feature activation+5.484
earning
Token earning
Feature activation+5.890
over
Token over
Feature activation+0.445
$
Token $
Feature activation+0.000
250
Token250
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
we
Token we
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
on
Token on
Feature activation+8.477
the
Token the
Feature activation+5.773
CT
Token CT
Feature activation+0.000
side
Token side
Feature activation+1.087
,
Token,
Feature activation+5.343
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
to
Token to
Feature activation+0.073
IGN
Token IGN
Feature activation+0.000
.
Token.
Feature activation+2.490
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.578
Exit
TokenExit
Feature activation+0.000
Theatre
Token Theatre
Feature activation+0.000
Mode
Token Mode
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.132
$
Token $
Feature activation+0.000
200
Token200
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
and
Token and
Feature activation+1.439
couples
Token couples
Feature activation+5.484
earning
Token earning
Feature activation+5.890
over
Token over
Feature activation+0.445
$
Token $
Feature activation+0.000
250
Token250
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 9.262

<|endoftext|>
Token<|endoftext|>
Feature activation+0.050
Top resid features:
confident
Token confident
Feature activation-0.016
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
Over
Token Over
Feature activation+9.262
Top resid features:
pass
Tokenpass
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
We
Token We
Feature activation+0.004
Top resid features:
talked
Token talked
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.058
Top resid features:
confident
Token confident
Feature activation-0.004
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
Over
Token Over
Feature activation+5.742
Top resid features:
pass
Tokenpass
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
We
Token We
Feature activation+0.003
Top resid features:
talked
Token talked
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.073
Top resid features:
confident
Token confident
Feature activation-0.009
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
Over
Token Over
Feature activation+8.949
Top resid features:
pass
Tokenpass
Feature activation-0.095
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
We
Token We
Feature activation+0.009
Top resid features:
talked
Token talked
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
doing
Token doing
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
same
Token same
Feature activation-0.016
Top resid features:
thing
Token thing
Feature activation-0.002
Top resid features:
over
Token over
Feature activation+8.693
Top resid features:
and
Token and
Feature activation+0.096
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
5
Token 5
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
8
Token8
Feature activation-0.001
Top resid features:
percent
Token percent
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
over
Token over
Feature activation+8.056
Top resid features:
35
Token 35
Feature activation+0.084
Top resid features:
,
Token,
Feature activation-0.037
Top resid features:
000
Token000
Feature activation+0.036
Top resid features:
applicants
Token applicants
Feature activation+0.282
Top resid features:
this
Token this
Feature activation+0.019
Top resid features:
they
Token they
Feature activation+0.007
Top resid features:
put
Token put
Feature activation-0.002
Top resid features:
N
Token N
Feature activation-0.006
Top resid features:
uke
Tokenuke
Feature activation+0.029
Top resid features:
or
Token or
Feature activation-0.024
Top resid features:
Over
Token Over
Feature activation+5.098
Top resid features:
pass
Tokenpass
Feature activation-0.022
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
pool
Token pool
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
Nintendo
Token Nintendo
Feature activation+0.003
Top resid features:
Switch
Token Switch
Feature activation-0.004
Top resid features:
version
Token version
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
Over
Token Over
Feature activation+8.170
Top resid features:
cooked
Tokencooked
Feature activation-0.145
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
working
Token working
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
will
Token will
Feature activation+0.013
Top resid features:
use
Token use
Feature activation-0.023
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
same
Token same
Feature activation-0.009
Top resid features:
needle
Token needle
Feature activation+0.027
Top resid features:
over
Token over
Feature activation+7.856
Top resid features:
and
Token and
Feature activation+0.068
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
Nintendo
Token Nintendo
Feature activation+0.008
Top resid features:
Switch
Token Switch
Feature activation-0.011
Top resid features:
version
Token version
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
Over
Token Over
Feature activation+7.846
Top resid features:
cooked
Tokencooked
Feature activation-0.197
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
working
Token working
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.041
Top resid features:
confident
Token confident
Feature activation-0.122
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
Over
Token Over
Feature activation+4.119
Top resid features:
pass
Tokenpass
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
We
Token We
Feature activation+0.016
Top resid features:
talked
Token talked
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.048
Top resid features:
confident
Token confident
Feature activation-0.073
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
Over
Token Over
Feature activation+7.411
Top resid features:
pass
Tokenpass
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
We
Token We
Feature activation+0.025
Top resid features:
talked
Token talked
Feature activation+0.001
Top resid features:
about
Token about
Feature activation+0.016
Top resid features:
onge
Tokenonge
Feature activation-0.000
Top resid features:
subway
Token subway
Feature activation+0.004
Top resid features:
line
Token line
Feature activation+0.007
Top resid features:
will
Token will
Feature activation+0.007
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
over
Token over
Feature activation+7.013
Top resid features:
capacity
Tokencapacity
Feature activation+0.287
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
20
Token 20
Feature activation-0.010
Top resid features:
31
Token31
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
5
Token 5
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
8
Token8
Feature activation-0.000
Top resid features:
percent
Token percent
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.036
Top resid features:
over
Token over
Feature activation+6.567
Top resid features:
35
Token 35
Feature activation+0.068
Top resid features:
,
Token,
Feature activation-0.039
Top resid features:
000
Token000
Feature activation+0.030
Top resid features:
applicants
Token applicants
Feature activation+0.160
Top resid features:
this
Token this
Feature activation+0.010
Top resid features:
they
Token they
Feature activation+0.008
Top resid features:
put
Token put
Feature activation-0.001
Top resid features:
N
Token N
Feature activation+0.013
Top resid features:
uke
Tokenuke
Feature activation+0.026
Top resid features:
or
Token or
Feature activation+0.006
Top resid features:
Over
Token Over
Feature activation+3.376
Top resid features:
pass
Tokenpass
Feature activation-0.010
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
pool
Token pool
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
:
Token:
Feature activation-0.048
Top resid features:
We
Token We
Feature activation+0.001
Top resid features:
suggest
Token suggest
Feature activation+0.002
Top resid features:
black
Token black
Feature activation-0.011
Top resid features:
over
Token over
Feature activation+6.751
Top resid features:
any
Token any
Feature activation+0.004
Top resid features:
form
Token form
Feature activation+0.035
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
brown
Token brown
Feature activation-0.028
Top resid features:
leather
Token leather
Feature activation+0.046
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.065
Top resid features:
confident
Token confident
Feature activation-0.047
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
Over
Token Over
Feature activation+5.005
Top resid features:
pass
Tokenpass
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
We
Token We
Feature activation+0.017
Top resid features:
talked
Token talked
Feature activation-0.000
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
tax
Token tax
Feature activation+0.001
Top resid features:
applied
Token applied
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
singles
Token singles
Feature activation-0.002
Top resid features:
earning
Token earning
Feature activation+0.012
Top resid features:
over
Token over
Feature activation+3.127
Top resid features:
$
Token $
Feature activation-0.016
Top resid features:
200
Token200
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
000
Token000
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.033
Top resid features:
confident
Token confident
Feature activation-0.051
Top resid features:
on
Token on
Feature activation+0.013
Top resid features:
Over
Token Over
Feature activation+4.408
Top resid features:
pass
Tokenpass
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
We
Token We
Feature activation+0.002
Top resid features:
talked
Token talked
Feature activation+0.001
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Nintendo
Token Nintendo
Feature activation+0.017
Top resid features:
Switch
Token Switch
Feature activation-0.001
Top resid features:
version
Token version
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Over
Token Over
Feature activation+6.536
Top resid features:
cooked
Tokencooked
Feature activation-0.078
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
working
Token working
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
000
Token000
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
couples
Token couples
Feature activation-0.036
Top resid features:
earnings
Token earnings
Feature activation-0.011
Top resid features:
over
Token over
Feature activation+2.835
Top resid features:
$
Token $
Feature activation-0.042
Top resid features:
450
Token450
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
000
Token000
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.49

Head 2: 0.05

Head 3: 0.05

Head 4: 0.04

Head 5: 0.04

Head 6: 0.03

Head 7: 0.09

Head 8: 0.07

Head 9: 0.04

Head 10: 0.04

Head 11: 0.03

Positive logits

over7.22

Over7.18

over6.81

OVER6.71

Over6.68

overs5.57

OVER5.01

overs4.68

Overs4.55

ove3.76

overc3.67

overd3.57

under3.34

Under3.29

underestimate3.16

overl3.11

overloaded3.04

UNDER3.03

overhe3.02

unders3.00

Negative logits

Truth-2.39

sure-2.36

-2.33

pur-2.27

Assembly-2.25

pressed-2.14

Pur-2.13

eny-2.12

Dig-2.11

heres-2.06

Lak-2.05

clair-2.03

Brave-2.03

Kind-2.02

Truth-2.01

Pur-1.98

Ground-1.96

Direct-1.96

nont-1.96

etter-1.94

INTERVAL 8.270 - 9.189
CONTAINS 0.000%

though
Token though
Feature activation+6.873
we
Token we
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
on
Token on
Feature activation+8.477
the
Token the
Feature activation+5.773
CT
Token CT
Feature activation+0.000
side
Token side
Feature activation+1.087
,
Token,
Feature activation+5.343
I
Token I
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.989
Do
TokenDo
Feature activation+1.280
you
Token you
Feature activation+0.000
feel
Token feel
Feature activation+0.698
confident
Token confident
Feature activation+1.043
on
Token on
Feature activation+9.189
all
Token all
Feature activation+3.280
maps
Token maps
Feature activation+0.412
,
Token,
Feature activation+1.172
or
Token or
Feature activation+0.276
are
Token are
Feature activation+1.605

INTERVAL 7.351 - 8.270
CONTAINS 0.001%

would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
if
Token if
Feature activation+8.260
they
Token they
Feature activation+0.000
put
Token put
Feature activation+3.614
N
Token N
Feature activation+0.000
uke
Tokenuke
Feature activation+0.000
or
Token or
Feature activation+2.547
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+3.019
So
Token So
Feature activation+0.954
when
Token when
Feature activation+5.990
they
Token they
Feature activation+0.000
picked
Token picked
Feature activation+7.796
Over
Token Over
Feature activation+0.000
pass
Tokenpass
Feature activation+0.029
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
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+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+7.975
over
Token over
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+2.383
and
Token and
Feature activation+3.406
expecting
Token expecting
Feature activation+0.000
admitted
Token admitted
Feature activation+0.016
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
percent
Token percent
Feature activation+1.008
of
Token of
Feature activation+7.844
their
Token their
Feature activation+6.264
nearly
Token nearly
Feature activation+0.402
39
Token 39
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+3.429
currently
Token currently
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.996
an
Token an
Feature activation+1.257
update
Token update
Feature activation+0.000
to
Token to
Feature activation+7.567
improve
Token improve
Feature activation+0.029
the
Token the
Feature activation+0.376
frame
Token frame
Feature activation+0.000
rate
Token rate
Feature activation+0.000
issues
Token issues
Feature activation+0.000

INTERVAL 6.432 - 7.351
CONTAINS 0.001%

it
Token it
Feature activation+4.543
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
subway
Token subway
Feature activation+0.000
extension
Token extension
Feature activation+0.858
is
Token is
Feature activation+6.781
further
Token further
Feature activation+5.437
ahead
Token ahead
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
relief
Token relief
Feature activation+0.000
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.801
to
Token to
Feature activation+1.947
my
Token my
Feature activation+0.000
team
Token team
Feature activation+0.000
that
Token that
Feature activation+6.828
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
so
Token so
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.052
even
Token even
Feature activation+0.000
though
Token though
Feature activation+6.873
we
Token we
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
on
Token on
Feature activation+8.477
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
needle
Token needle
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+7.192
over
Token over
Feature activation+0.000
again
Token again
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
rate
Token rate
Feature activation+0.000
and
Token and
Feature activation+0.000
rum
Token rum
Feature activation+0.000
ble
Tokenble
Feature activation+0.000
issues
Token issues
Feature activation+0.000
in
Token in
Feature activation+7.187
Over
Token Over
Feature activation+0.197
cooked
Tokencooked
Feature activation+0.000
:
Token:
Feature activation+0.000
Special
Token Special
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000

INTERVAL 5.513 - 6.432
CONTAINS 0.001%

200
Token200
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
and
Token and
Feature activation+1.439
couples
Token couples
Feature activation+5.484
earning
Token earning
Feature activation+5.890
over
Token over
Feature activation+0.445
$
Token $
Feature activation+0.000
250
Token250
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
shoes
Token shoes
Feature activation+0.000
.
Token.
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
Grey
Token Grey
Feature activation+2.353
:
Token:
Feature activation+0.000
Black
Token Black
Feature activation+6.039
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
There
TokenThere
Feature activation+0.000
's
Token's
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
to
Token to
Feature activation+0.073
IGN
Token IGN
Feature activation+0.000
.
Token.
Feature activation+2.490
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.578
Exit
TokenExit
Feature activation+0.000
Theatre
Token Theatre
Feature activation+0.000
Mode
Token Mode
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.132
got
Token got
Feature activation+0.000
six
Token six
Feature activation+0.852
rounds
Token rounds
Feature activation+0.000
as
Token as
Feature activation+0.799
CT
Token CT
Feature activation+0.507
and
Token and
Feature activation+6.158
then
Token then
Feature activation+5.160
we
Token we
Feature activation+0.000
managed
Token managed
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
Feature activation+0.000
in
Token in
Feature activation+4.448
the
Token the
Feature activation+3.184
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+3.019
So
Token So
Feature activation+0.954
when
Token when
Feature activation+5.990
they
Token they
Feature activation+0.000
picked
Token picked
Feature activation+7.796
Over
Token Over
Feature activation+0.000
pass
Tokenpass
Feature activation+0.029
I
Token I
Feature activation+0.000

INTERVAL 4.594 - 5.513
CONTAINS 0.002%

that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
subway
Token subway
Feature activation+0.000
extension
Token extension
Feature activation+0.858
is
Token is
Feature activation+6.781
further
Token further
Feature activation+5.437
ahead
Token ahead
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
relief
Token relief
Feature activation+0.000
line
Token line
Feature activation+0.009
had
Token had
Feature activation+0.000
your
Token your
Feature activation+0.000
character
Token character
Feature activation+0.000
assassinated
Token assassinated
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+5.440
over
Token over
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.404
and
Tokenand
Feature activation+3.072
in
Token in
Feature activation+0.000
response
Token response
Feature activation+0.487
again
Token again
Feature activation+0.000
:
Token:
Feature activation+1.059
these
Token these
Feature activation+0.066
companies
Token companies
Feature activation+0.000
are
Token are
Feature activation+0.000
making
Token making
Feature activation+4.997
10
Token 10
Feature activation+0.000
billion
Token billion
Feature activation+0.000
(
Token (
Feature activation+0.000
with
Tokenwith
Feature activation+1.194
a
Token a
Feature activation+0.000
launch
Token launch
Feature activation+0.000
over
Token over
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+5.240
its
Token its
Feature activation+0.000
recent
Token recent
Feature activation+0.000
actions
Token actions
Feature activation+4.403
and
Token and
Feature activation+0.000
public
Token public
Feature activation+0.000
who
Token who
Feature activation+0.000
thanked
Token thanked
Feature activation+0.000
his
Token his
Feature activation+0.000
crew
Token crew
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+5.126
over
Token over
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
crossed
Token crossed
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.676 - 4.594
CONTAINS 0.002%

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.000
I
Token I
Feature activation+0.000
came
Token came
Feature activation+4.108
over
Token over
Feature activation+0.028
he
Token he
Feature activation+0.000
actually
Token actually
Feature activation+0.000
gave
Token gave
Feature activation+0.000
me
Token me
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
consistent
Token consistent
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+4.323
contraception
Token contraception
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.972
many
Token many
Feature activation+0.196
women
Token women
Feature activation+0.000
.
Token.
Feature activation+0.000
yogurt
Token yogurt
Feature activation+0.000
market
Token market
Feature activation+0.000
,
Token,
Feature activation+0.000
up
Token up
Feature activation+0.000
from
Token from
Feature activation+3.930
about
Token about
Feature activation+0.000
4
Token 4
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
and
Token and
Feature activation+0.000
local
Token local
Feature activation+0.000
governments
Token governments
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
those
Token those
Feature activation+3.754
are
Token are
Feature activation+0.000
largely
Token largely
Feature activation+0.000
internal
Token internal
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+0.000
;
Token;
Feature activation+1.238
no
Token no
Feature activation+0.000
,
Token,
Feature activation+4.045
I
Token I
Feature activation+0.000
take
Token take
Feature activation+0.000
that
Token that
Feature activation+0.000
back
Token back
Feature activation+0.000
:
Token:
Feature activation+2.033

INTERVAL 2.757 - 3.676
CONTAINS 0.005%

,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
will
Token will
Feature activation+0.000
help
Token help
Feature activation+0.000
reduce
Token reduce
Feature activation+2.245
the
Token the
Feature activation+3.226
economic
Token economic
Feature activation+0.312
competitiveness
Token competitiveness
Feature activation+0.000
of
Token of
Feature activation+0.000
coal
Token coal
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.902
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.087
one
Token one
Feature activation+0.004
permanent
Token permanent
Feature activation+3.341
ban
Token ban
Feature activation+0.000
,
Token,
Feature activation+0.762
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
ID
Token ID
Feature activation+0.000
:
Token:
Feature activation+1.444
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.117
Package
TokenPackage
Feature activation+0.663
:
Token:
Feature activation+3.316
io
Token io
Feature activation+0.000
.
Token.
Feature activation+0.000
v
Tokenv
Feature activation+0.000
oodoo
Tokenoodoo
Feature activation+0.000
.
Token.
Feature activation+0.005
.
Token.
Feature activation+0.127
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.295
{
Token{
Feature activation+0.000
default
Tokendefault
Feature activation+0.000
}
Token}
Feature activation+3.144
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.430
Unlike
TokenUnlike
Feature activation+0.189
today
Token today
Feature activation+0.000
when
Token when
Feature activation+0.291
in
Token in
Feature activation+0.000
EU
Token EU
Feature activation+0.000
scores
Token scores
Feature activation+0.000
over
Token over
Feature activation+0.000
,
Token,
Feature activation+0.465
another
Token another
Feature activation+3.469
team
Token team
Feature activation+3.668
will
Token will
Feature activation+0.000
score
Token score
Feature activation+5.098
just
Token just
Feature activation+2.015
as
Token as
Feature activation+2.107

INTERVAL 1.838 - 2.757
CONTAINS 0.008%

Ċ
TokenĊ
Feature activation+0.790
Here
TokenHere
Feature activation+0.000
are
Token are
Feature activation+0.000
some
Token some
Feature activation+0.026
tips
Token tips
Feature activation+0.000
on
Token on
Feature activation+2.048
how
Token how
Feature activation+0.901
to
Token to
Feature activation+1.177
slow
Token slow
Feature activation+1.801
down
Token down
Feature activation+2.886
and
Token and
Feature activation+0.353
patient
Token patient
Feature activation+0.000
who
Token who
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+1.137
undergoing
Token undergoing
Feature activation+1.792
an
Token an
Feature activation+2.105
un
Token un
Feature activation+0.000
event
Tokenevent
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
u
Token u
Feature activation+0.000
v
Tokenv
Feature activation+0.000
Sweet
Token Sweet
Feature activation+0.000
man
Tokenman
Feature activation+0.000
has
Token has
Feature activation+0.000
posted
Token posted
Feature activation+0.000
photos
Token photos
Feature activation+0.636
taken
Token taken
Feature activation+2.125
March
Token March
Feature activation+0.000
10
Token 10
Feature activation+3.659
by
Token by
Feature activation+0.000
two
Token two
Feature activation+0.000
veteran
Token veteran
Feature activation+0.000
thing
Token thing
Feature activation+0.000
over
Token over
Feature activation+0.000
and
Token and
Feature activation+7.975
over
Token over
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+2.383
and
Token and
Feature activation+3.406
expecting
Token expecting
Feature activation+0.000
a
Token a
Feature activation+0.000
different
Token different
Feature activation+0.000
result
Token result
Feature activation+0.000
avoid
Token avoid
Feature activation+0.608
tan
Token tan
Feature activation+3.226
shoes
Token shoes
Feature activation+0.000
.
Token.
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
Grey
Token Grey
Feature activation+2.353
:
Token:
Feature activation+0.000
Black
Token Black
Feature activation+6.039
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000

INTERVAL 0.919 - 1.838
CONTAINS 0.026%

over
Token over
Feature activation+0.096
$
Token $
Feature activation+0.000
200
Token200
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
and
Token and
Feature activation+1.439
couples
Token couples
Feature activation+5.484
earning
Token earning
Feature activation+5.890
over
Token over
Feature activation+0.445
$
Token $
Feature activation+0.000
250
Token250
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
videos
Token videos
Feature activation+0.000
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
recorded
Token recorded
Feature activation+1.775
in
Token in
Feature activation+0.000
720
Token 720
Feature activation+0.000
p
Tokenp
Feature activation+0.000
so
Token so
Feature activation+0.000
feel
Token feel
Feature activation+0.000
at
Token at
Feature activation+0.000
age
Token age
Feature activation+0.000
five
Token five
Feature activation+0.550
do
Token do
Feature activation+0.749
better
Token better
Feature activation+1.091
in
Token in
Feature activation+1.098
the
Token the
Feature activation+1.118
long
Token long
Feature activation+0.000
run
Token run
Feature activation+0.000
than
Token than
Feature activation+0.000
children
Token children
Feature activation+0.000
by
Token by
Feature activation+0.000
punching
Token punching
Feature activation+0.000
and
Token and
Feature activation+0.000
kicking
Token kicking
Feature activation+0.000
him
Token him
Feature activation+0.541
and
Token and
Feature activation+0.949
stamp
Token stamp
Feature activation+0.000
ing
Tokening
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
head
Token head
Feature activation+0.000
the
Token the
Feature activation+0.000
weak
Token weak
Feature activation+0.000
side
Tokenside
Feature activation+0.000
guard
Token guard
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.971
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
tackles
Token tackles
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 0.000 - 0.919
CONTAINS 99.956%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
walk
Token walk
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
shower
Token shower
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
NA
TokenNA
Feature activation+0.000
reported
Token reported
Feature activation+0.000
Sheikh
Token Sheikh
Feature activation+0.000
Sa
Token Sa
Feature activation+0.000
if
Tokenif
Feature activation+0.000
Bin
Token Bin
Feature activation+0.000
Ahmed
Token Ahmed
Feature activation+0.000
Al
Token Al
Feature activation+0.000
-
Token-
Feature activation+0.000
several
Token several
Feature activation+0.000
integrated
Token integrated
Feature activation+0.000
students
Token students
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
disabled
Token disabled
Feature activation+0.000
children
Token children
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
passed
Token passed
Feature activation+0.000
their
Token their
Feature activation+0.000
Grade
Token Grade
Feature activation+0.000
Solomon
Token Solomon
Feature activation+0.000
responded
Token responded
Feature activation+0.000
by
Token by
Feature activation+0.000
suggesting
Token suggesting
Feature activation+0.000
that
Token that
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
who
Token who
Feature activation+0.000
support
Token support
Feature activation+0.000
gun
Token gun
Feature activation+0.000
laws
Token laws
Feature activation+0.000
should
Token should
Feature activation+0.000
period
Token period
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Figure
TokenFigure
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
ICE
Token ICE
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 H10.1: (feature 19615)

TOP ACTIVATIONS
MAX = 10.377

the
Token the
Feature activation+3.318
city
Token city
Feature activation+0.000
.
Token.
Feature activation+4.689
A
Token A
Feature activation+1.791
spokeswoman
Token spokeswoman
Feature activation+0.000
for
Token for
Feature activation+10.377
the
Token the
Feature activation+4.784
FBI
Token FBI
Feature activation+0.000
's
Token's
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.598
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+1.719
season
Token season
Feature activation+0.000
of
Token of
Feature activation+8.211
"
Token "
Feature activation+9.122
D
TokenD
Feature activation+0.000
ancing
Tokenancing
Feature activation+0.000
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
Stars
Token Stars
Feature activation+0.000
7
Token7
Feature activation+1.033
years
Token years
Feature activation+0.000
.
Token.
Feature activation+1.231
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.813
first
Token first
Feature activation+8.309
full
Token full
Feature activation+0.913
moon
Token moon
Feature activation+1.817
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.115
took
Token took
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.598
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+1.719
season
Token season
Feature activation+0.000
of
Token of
Feature activation+8.211
"
Token "
Feature activation+9.122
D
TokenD
Feature activation+0.000
ancing
Tokenancing
Feature activation+0.000
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
,
Token,
Feature activation+0.000
user
Token user
Feature activation+0.000
2
Token2
Feature activation+4.209
will
Token will
Feature activation+0.000
have
Token have
Feature activation+7.886
internet
Token internet
Feature activation+0.000
access
Token access
Feature activation+0.000
only
Token only
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
has
Token has
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
legal
Token legal
Feature activation+0.000
claim
Token claim
Feature activation+0.000
against
Token against
Feature activation+7.860
the
Token the
Feature activation+3.318
city
Token city
Feature activation+0.000
.
Token.
Feature activation+4.689
A
Token A
Feature activation+1.791
spokeswoman
Token spokeswoman
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
.)
Token.)
Feature activation+3.060
The
Token The
Feature activation+3.148
next
Token next
Feature activation+7.680
blue
Token blue
Feature activation+5.111
moon
Token moon
Feature activation+1.951
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.635
happen
Token happen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
when
Token when
Feature activation+0.000
Milo
Token Milo
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+7.338
CS
Token CS
Feature activation+0.000
UF
TokenUF
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
favorable
Token favorable
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
with
Token with
Feature activation+7.122
the
Token the
Feature activation+1.614
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+4.882
I
Token I
Feature activation+0.000
never
Token never
Feature activation+0.000
noticed
Token noticed
Feature activation+2.974
how
Token how
Feature activation+0.000
many
Token many
Feature activation+6.381
people
Token people
Feature activation+0.000
cross
Token cross
Feature activation+0.000
play
Tokenplay
Feature activation+2.125
.
Token.
Feature activation+0.073
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.285
nice
Token nice
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+6.354
widely
Token widely
Feature activation+0.000
popular
Token popular
Feature activation+4.241
characters
Token characters
Feature activation+0.000
that
Token that
Feature activation+0.000
no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
to
Token to
Feature activation+0.000
grant
Token grant
Feature activation+6.141
pard
Token pard
Feature activation+0.000
ons
Tokenons
Feature activation+0.075
in
Token in
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
contempt
Token contempt
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
.
Token.
Feature activation+4.579
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.720
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.100
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.127
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
considerable
Token considerable
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
buzz
Token buzz
Feature activation+0.000
about
Token about
Feature activation+6.088
the
Token the
Feature activation+2.644
possibility
Token possibility
Feature activation+0.000
of
Token of
Feature activation+4.199
a
Token a
Feature activation+2.875
Pent
Token Pent
Feature activation+0.000
search
Token search
Feature activation+0.000
warrants
Token warrants
Feature activation+0.000
,
Token,
Feature activation+0.545
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.956
it
Token it
Feature activation+6.008
fully
Token fully
Feature activation+1.167
complied
Token complied
Feature activation+0.000
with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+2.644
possibility
Token possibility
Feature activation+0.000
of
Token of
Feature activation+4.199
a
Token a
Feature activation+2.875
Pent
Token Pent
Feature activation+0.000
ax
Tokenax
Feature activation+5.934
full
Token full
Feature activation+0.000
frame
Token frame
Feature activation+1.379
DSL
Token DSL
Feature activation+0.000
R
TokenR
Feature activation+0.000
.
Token.
Feature activation+1.087
involve
Token involve
Feature activation+3.662
rep
Token rep
Feature activation+0.000
aying
Tokenaying
Feature activation+2.749
all
Token all
Feature activation+0.000
players
Token players
Feature activation+0.000
in
Token in
Feature activation+5.886
full
Token full
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.893
is
Token is
Feature activation+0.000
conditional
Token conditional
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
definition
Token definition
Feature activation+0.000
of
Token of
Feature activation+4.708
a
Token a
Feature activation+5.761
blue
Token blue
Feature activation+0.713
moon
Token moon
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
quite
Token quite
Feature activation+0.000
the
Token the
Feature activation+0.658
wild
Token wild
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.947
Lydia
Token Lydia
Feature activation+0.000
from
Token from
Feature activation+5.716
Beetle
Token Beetle
Feature activation+0.000
ju
Tokenju
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
or
Token or
Feature activation+0.000
Dar
Token Dar
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.127
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
that
Token that
Feature activation+5.487
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
funds
Token funds
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000

Top DFA by src position
MAX = 10.595

support
Token support
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Six
TokenSix
Feature activation+0.057
Top resid features:
Full
Token Full
Feature activation+10.595
Top resid features:
erton
Tokenerton
Feature activation+0.380
Top resid features:
police
Token police
Feature activation+0.087
Top resid features:
officers
Token officers
Feature activation+0.024
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
rel
Token rel
Feature activation-0.016
Top resid features:
aunch
Tokenaunch
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
"
Token "
Feature activation+0.033
Top resid features:
Full
TokenFull
Feature activation+10.354
Top resid features:
House
Token House
Feature activation+0.067
Top resid features:
"
Token"
Feature activation+0.039
Top resid features:
on
Token on
Feature activation+0.017
Top resid features:
Netflix
Token Netflix
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.114
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
two
Token two
Feature activation+0.023
Top resid features:
full
Token full
Feature activation+8.911
Top resid features:
moons
Token moons
Feature activation+0.083
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.025
Top resid features:
single
Token single
Feature activation-0.091
Top resid features:
month
Token month
Feature activation+0.171
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
rel
Token rel
Feature activation-0.037
Top resid features:
aunch
Tokenaunch
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
"
Token "
Feature activation-0.013
Top resid features:
Full
TokenFull
Feature activation+9.259
Top resid features:
House
Token House
Feature activation+0.035
Top resid features:
"
Token"
Feature activation+0.222
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
Netflix
Token Netflix
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.006
Top resid features:
Now
TokenNow
Feature activation-0.009
Top resid features:
user
Token user
Feature activation-0.012
Top resid features:
1
Token1
Feature activation-0.003
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
have
Token have
Feature activation-0.005
Top resid features:
full
Token full
Feature activation+8.461
Top resid features:
access
Token access
Feature activation+0.082
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
LAN
Token LAN
Feature activation+0.015
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
internet
Token internet
Feature activation-0.034
Top resid features:
support
Token support
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Six
TokenSix
Feature activation+0.082
Top resid features:
Full
Token Full
Feature activation+8.292
Top resid features:
erton
Tokenerton
Feature activation+0.096
Top resid features:
police
Token police
Feature activation+0.097
Top resid features:
officers
Token officers
Feature activation+0.073
Top resid features:
have
Token have
Feature activation+0.001
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
years
Token years
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
(
Token (
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.014
Top resid features:
first
Token first
Feature activation-0.037
Top resid features:
full
Token full
Feature activation+7.397
Top resid features:
moon
Token moon
Feature activation-0.023
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
August
Token August
Feature activation+0.010
Top resid features:
took
Token took
Feature activation+0.001
Top resid features:
place
Token place
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.002
Top resid features:
California
Token California
Feature activation+0.165
Top resid features:
State
Token State
Feature activation+0.025
Top resid features:
University
Token University
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Full
Token Full
Feature activation+8.208
Top resid features:
erton
Tokenerton
Feature activation+0.049
Top resid features:
student
Token student
Feature activation-0.008
Top resid features:
government
Token government
Feature activation+0.050
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
considering
Token considering
Feature activation+0.000
Top resid features:
financially
Token financially
Feature activation-0.003
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
rou
Tokenrou
Feature activation-0.000
Top resid features:
bled
Tokenbled
Feature activation-0.009
Top resid features:
Full
Token Full
Feature activation+8.254
Top resid features:
T
Token T
Feature activation-0.013
Top resid features:
ilt
Tokenilt
Feature activation+0.007
Top resid features:
Poker
Token Poker
Feature activation-0.143
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
We
TokenWe
Feature activation-0.000
Top resid features:
need
Token need
Feature activation-0.006
Top resid features:
more
Token more
Feature activation-0.004
Top resid features:
Full
Token Full
Feature activation+7.578
Top resid features:
metal
Tokenmetal
Feature activation+0.126
Top resid features:
Alchemist
Token Alchemist
Feature activation-0.000
Top resid features:
cos
Token cos
Feature activation-0.012
Top resid features:
players
Tokenplayers
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
We
TokenWe
Feature activation+0.002
Top resid features:
need
Token need
Feature activation-0.005
Top resid features:
more
Token more
Feature activation+0.012
Top resid features:
Full
Token Full
Feature activation+7.051
Top resid features:
metal
Tokenmetal
Feature activation+0.108
Top resid features:
Alchemist
Token Alchemist
Feature activation+0.010
Top resid features:
cos
Token cos
Feature activation+0.010
Top resid features:
players
Tokenplayers
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
sentence
Token sentence
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
or
Token or
Feature activation+0.008
Top resid features:
grant
Token grant
Feature activation+0.031
Top resid features:
full
Token full
Feature activation+7.413
Top resid features:
rep
Token rep
Feature activation-0.476
Top resid features:
rieve
Tokenrieve
Feature activation-0.062
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
treason
Token treason
Feature activation-0.007
Top resid features:
financially
Token financially
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
rou
Tokenrou
Feature activation-0.000
Top resid features:
bled
Tokenbled
Feature activation-0.002
Top resid features:
Full
Token Full
Feature activation+7.388
Top resid features:
T
Token T
Feature activation-0.009
Top resid features:
ilt
Tokenilt
Feature activation+0.004
Top resid features:
Poker
Token Poker
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
The
Token The
Feature activation+0.011
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.038
Top resid features:
Is
TokenIs
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Pent
Token Pent
Feature activation-0.346
Top resid features:
ax
Tokenax
Feature activation+0.012
Top resid features:
Full
Token Full
Feature activation+6.693
Top resid features:
Frame
Token Frame
Feature activation+0.011
Top resid features:
Just
Token Just
Feature activation-0.006
Top resid features:
Around
Token Around
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Corner
Token Corner
Feature activation-0.011
Top resid features:
as
Tokenas
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
which
Token which
Feature activation-0.006
Top resid features:
it
Token it
Feature activation-0.017
Top resid features:
fully
Token fully
Feature activation+7.056
Top resid features:
complied
Token complied
Feature activation-0.028
Top resid features:
with
Token with
Feature activation+0.172
Top resid features:
66
Token 66
Feature activation+0.006
Top resid features:
percent
Token percent
Feature activation-0.002
Top resid features:
;
Token;
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.037
Top resid features:
Is
TokenIs
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Pent
Token Pent
Feature activation-0.041
Top resid features:
ax
Tokenax
Feature activation+0.002
Top resid features:
Full
Token Full
Feature activation+6.366
Top resid features:
Frame
Token Frame
Feature activation+0.019
Top resid features:
Just
Token Just
Feature activation-0.003
Top resid features:
Around
Token Around
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Corner
Token Corner
Feature activation-0.007
Top resid features:
financially
Token financially
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
rou
Tokenrou
Feature activation-0.001
Top resid features:
bled
Tokenbled
Feature activation-0.014
Top resid features:
Full
Token Full
Feature activation+7.040
Top resid features:
T
Token T
Feature activation-0.025
Top resid features:
ilt
Tokenilt
Feature activation+0.010
Top resid features:
Poker
Token Poker
Feature activation-0.073
Top resid features:
.
Token.
Feature activation-0.050
Top resid features:
The
Token The
Feature activation+0.009
Top resid features:
years
Token years
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
first
Token first
Feature activation-0.031
Top resid features:
full
Token full
Feature activation+4.815
Top resid features:
moon
Token moon
Feature activation-0.020
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
August
Token August
Feature activation+0.003
Top resid features:
took
Token took
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
We
TokenWe
Feature activation-0.000
Top resid features:
need
Token need
Feature activation-0.002
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Full
Token Full
Feature activation+6.709
Top resid features:
metal
Tokenmetal
Feature activation+0.161
Top resid features:
Alchemist
Token Alchemist
Feature activation+0.080
Top resid features:
cos
Token cos
Feature activation-0.006
Top resid features:
players
Tokenplayers
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
financially
Token financially
Feature activation-0.011
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
t
Tokent
Feature activation-0.000
Top resid features:
rou
Tokenrou
Feature activation-0.001
Top resid features:
bled
Tokenbled
Feature activation-0.013
Top resid features:
Full
Token Full
Feature activation+6.745
Top resid features:
T
Token T
Feature activation-0.013
Top resid features:
ilt
Tokenilt
Feature activation+0.014
Top resid features:
Poker
Token Poker
Feature activation-0.121
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.016
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.49

Head 2: 0.05

Head 3: 0.04

Head 4: 0.03

Head 5: 0.02

Head 6: 0.05

Head 7: 0.07

Head 8: 0.06

Head 9: 0.04

Head 10: 0.05

Head 11: 0.05

Positive logits

Full7.80

Full7.38

full7.10

full6.96

FULL6.11

fuller5.12

partial4.62

fullest4.49

Fuller4.44

Partial4.31

partial4.16

complete3.90

Fully3.85

fully3.69

Half3.42

complete3.36

filled3.32

Half3.28

ful2.99

half2.98

Negative logits

eele-2.52

otor-2.45

inav-2.38

indo-2.30

alities-2.29

bourg-2.27

Air-2.17

Conrad-2.14

excise-2.14

guiName-2.13

hesion-2.12

endi-2.06

Polar-2.05

Rad-2.01

disadvant-2.00

trap-1.99

Rad-1.98

strang-1.98

UGH-1.98

SpaceEngineers-1.98

INTERVAL 9.339 - 10.377
CONTAINS 0.000%

the
Token the
Feature activation+3.318
city
Token city
Feature activation+0.000
.
Token.
Feature activation+4.689
A
Token A
Feature activation+1.791
spokeswoman
Token spokeswoman
Feature activation+0.000
for
Token for
Feature activation+10.377
the
Token the
Feature activation+4.784
FBI
Token FBI
Feature activation+0.000
's
Token's
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000

INTERVAL 8.302 - 9.339
CONTAINS 0.000%

7
Token7
Feature activation+1.033
years
Token years
Feature activation+0.000
.
Token.
Feature activation+1.231
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.813
first
Token first
Feature activation+8.309
full
Token full
Feature activation+0.913
moon
Token moon
Feature activation+1.817
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.115
took
Token took
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.598
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+1.719
season
Token season
Feature activation+0.000
of
Token of
Feature activation+8.211
"
Token "
Feature activation+9.122
D
TokenD
Feature activation+0.000
ancing
Tokenancing
Feature activation+0.000
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
Stars
Token Stars
Feature activation+0.000

INTERVAL 7.264 - 8.302
CONTAINS 0.001%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
.)
Token.)
Feature activation+3.060
The
Token The
Feature activation+3.148
next
Token next
Feature activation+7.680
blue
Token blue
Feature activation+5.111
moon
Token moon
Feature activation+1.951
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.635
happen
Token happen
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.598
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+1.719
season
Token season
Feature activation+0.000
of
Token of
Feature activation+8.211
"
Token "
Feature activation+9.122
D
TokenD
Feature activation+0.000
ancing
Tokenancing
Feature activation+0.000
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
,
Token,
Feature activation+0.000
user
Token user
Feature activation+0.000
2
Token2
Feature activation+4.209
will
Token will
Feature activation+0.000
have
Token have
Feature activation+7.886
internet
Token internet
Feature activation+0.000
access
Token access
Feature activation+0.000
only
Token only
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
has
Token has
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
legal
Token legal
Feature activation+0.000
claim
Token claim
Feature activation+0.000
against
Token against
Feature activation+7.860
the
Token the
Feature activation+3.318
city
Token city
Feature activation+0.000
.
Token.
Feature activation+4.689
A
Token A
Feature activation+1.791
spokeswoman
Token spokeswoman
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
when
Token when
Feature activation+0.000
Milo
Token Milo
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+7.338
CS
Token CS
Feature activation+0.000
UF
TokenUF
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 6.226 - 7.264
CONTAINS 0.000%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.285
nice
Token nice
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+6.354
widely
Token widely
Feature activation+0.000
popular
Token popular
Feature activation+4.241
characters
Token characters
Feature activation+0.000
that
Token that
Feature activation+0.000
no
Token no
Feature activation+0.000
,
Token,
Feature activation+4.882
I
Token I
Feature activation+0.000
never
Token never
Feature activation+0.000
noticed
Token noticed
Feature activation+2.974
how
Token how
Feature activation+0.000
many
Token many
Feature activation+6.381
people
Token people
Feature activation+0.000
cross
Token cross
Feature activation+0.000
play
Tokenplay
Feature activation+2.125
.
Token.
Feature activation+0.073
Ċ
TokenĊ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
favorable
Token favorable
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
with
Token with
Feature activation+7.122
the
Token the
Feature activation+1.614
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 5.189 - 6.226
CONTAINS 0.001%

hospital
Token hospital
Feature activation+0.000
this
Token this
Feature activation+0.000
morning
Token morning
Feature activation+0.000
every
Token every
Feature activation+0.000
ward
Token ward
Feature activation+4.925
was
Token was
Feature activation+5.286
full
Token full
Feature activation+0.096
,
Token,
Feature activation+1.395
every
Token every
Feature activation+0.000
escalation
Token escalation
Feature activation+0.000
area
Token area
Feature activation+4.484
Justice
Token Justice
Feature activation+0.000
.
Token.
Feature activation+4.579
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.720
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.100
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.127
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.429
2011
Token 2011
Feature activation+0.000
call
Token call
Feature activation+0.000
for
Token for
Feature activation+5.396
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
third
Tokenthird
Feature activation+1.614
oil
Token oil
Feature activation+0.000
independence
Token independence
Feature activation+0.000
search
Token search
Feature activation+0.000
warrants
Token warrants
Feature activation+0.000
,
Token,
Feature activation+0.545
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.956
it
Token it
Feature activation+6.008
fully
Token fully
Feature activation+1.167
complied
Token complied
Feature activation+0.000
with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+2.644
possibility
Token possibility
Feature activation+0.000
of
Token of
Feature activation+4.199
a
Token a
Feature activation+2.875
Pent
Token Pent
Feature activation+0.000
ax
Tokenax
Feature activation+5.934
full
Token full
Feature activation+0.000
frame
Token frame
Feature activation+1.379
DSL
Token DSL
Feature activation+0.000
R
TokenR
Feature activation+0.000
.
Token.
Feature activation+1.087

INTERVAL 4.151 - 5.189
CONTAINS 0.003%

Hulu
Token Hulu
Feature activation+0.000
demonstrates
Token demonstrates
Feature activation+0.000
that
Token that
Feature activation+1.821
people
Token people
Feature activation+0.000
will
Token will
Feature activation+0.000
watch
Token watch
Feature activation+4.302
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.097
te
Tokente
Feature activation+0.000
levision
Tokenlevision
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
buzz
Token buzz
Feature activation+0.000
about
Token about
Feature activation+6.088
the
Token the
Feature activation+2.644
possibility
Token possibility
Feature activation+0.000
of
Token of
Feature activation+4.199
a
Token a
Feature activation+2.875
Pent
Token Pent
Feature activation+0.000
ax
Tokenax
Feature activation+5.934
full
Token full
Feature activation+0.000
frame
Token frame
Feature activation+1.379
bled
Tokenbled
Feature activation+0.000
Full
Token Full
Feature activation+0.000
T
Token T
Feature activation+0.000
ilt
Tokenilt
Feature activation+0.692
Poker
Token Poker
Feature activation+0.000
.
Token.
Feature activation+4.920
The
Token The
Feature activation+2.670
deal
Token deal
Feature activation+0.000
would
Token would
Feature activation+0.000
involve
Token involve
Feature activation+3.662
rep
Token rep
Feature activation+0.000
LAN
Token LAN
Feature activation+0.000
and
Token and
Feature activation+0.000
internet
Token internet
Feature activation+0.000
,
Token,
Feature activation+0.000
user
Token user
Feature activation+0.000
2
Token2
Feature activation+4.209
will
Token will
Feature activation+0.000
have
Token have
Feature activation+7.886
internet
Token internet
Feature activation+0.000
access
Token access
Feature activation+0.000
only
Token only
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
growing
Token growing
Feature activation+0.085
success
Token success
Feature activation+0.000
of
Token of
Feature activation+4.959
services
Token services
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.580
Hulu
Token Hulu
Feature activation+0.000
demonstrates
Token demonstrates
Feature activation+0.000

INTERVAL 3.113 - 4.151
CONTAINS 0.003%

by
Token by
Feature activation+3.081
Band
Token Band
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
release
Token release
Feature activation+3.357
one
Token one
Feature activation+0.000
episode
Token episode
Feature activation+0.000
every
Token every
Feature activation+0.000
full
Token full
Feature activation+0.020
moon
Token moon
Feature activation+0.082
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
March
Token March
Feature activation+0.000
21
Token 21
Feature activation+0.000
on
Token on
Feature activation+3.801
ABC
Token ABC
Feature activation+0.000
.
Token.
Feature activation+0.263
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.832
Click
TokenClick
Feature activation+0.000
buy
Token buy
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
phone
Token phone
Feature activation+0.000
and
Token and
Feature activation+0.000
pay
Token pay
Feature activation+3.199
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.000
at
Token at
Feature activation+0.972
once
Token once
Feature activation+0.000
find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
complete
Token complete
Feature activation+0.000
release
Token release
Feature activation+0.000
notes
Token notes
Feature activation+0.000
>
Token >
Feature activation+4.048
here
Tokenhere
Feature activation+0.000
<
Token<
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.529
and
Tokenand
Feature activation+0.000
less
Token less
Feature activation+0.000
intrusive
Token intrusive
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+3.170
programs
Token programs
Feature activation+0.000
and
Token and
Feature activation+0.000
movies
Token movies
Feature activation+0.000
on
Token on
Feature activation+0.122
the
Token the
Feature activation+0.000

INTERVAL 2.075 - 3.113
CONTAINS 0.004%

Ļ
TokenĻ
Feature activation+0.000
mon
Tokenmon
Feature activation+0.000
people
Token people
Feature activation+0.000
!
Token!
Feature activation+1.876
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.767
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.285
,
Token,
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
.)
Token.)
Feature activation+3.060
The
Token The
Feature activation+3.148
next
Token next
Feature activation+7.680
blue
Token blue
Feature activation+5.111
moon
Token moon
Feature activation+1.951
won
Token won
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
go
Token go
Feature activation+0.000
full
Token full
Feature activation+0.000
speed
Token speed
Feature activation+0.000
,
Token,
Feature activation+2.841
Nick
Token Nick
Feature activation+0.000
's
Token's
Feature activation+0.522
finding
Token finding
Feature activation+0.000
me
Token me
Feature activation+0.000
in
Token in
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
without
Token without
Feature activation+0.000
a
Token a
Feature activation+3.082
full
Token full
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
says
Token says
Feature activation+2.358
agents
Token agents
Feature activation+0.000
are
Token are
Feature activation+0.000
investigating
Token investigating
Feature activation+0.472
"
Token "
Feature activation+0.000
whether
Tokenwhether
Feature activation+2.324
Kelly
Token Kelly
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
'
Token'
Feature activation+0.000
civil
Token civil
Feature activation+0.000
rights
Token rights
Feature activation+0.000

INTERVAL 1.038 - 2.075
CONTAINS 0.011%

more
Token more
Feature activation+0.000
adventurous
Token adventurous
Feature activation+0.000
and
Token and
Feature activation+0.000
did
Token did
Feature activation+0.000
go
Token go
Feature activation+0.000
for
Token for
Feature activation+1.254
the
Token the
Feature activation+3.787
full
Token full
Feature activation+0.266
Scottish
Token Scottish
Feature activation+0.000
version
Token version
Feature activation+0.000
.
Token.
Feature activation+0.000
said
Token said
Feature activation+0.000
through
Token through
Feature activation+0.000
tears
Token tears
Feature activation+0.000
.
Token.
Feature activation+0.826
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.059
True
TokenTrue
Feature activation+0.000
x
Tokenx
Feature activation+0.000
told
Token told
Feature activation+0.660
Fox
Token Fox
Feature activation+0.000
5
Token 5
Feature activation+0.000
one
Token one
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
cos
Token cos
Feature activation+0.000
plays
Tokenplays
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+1.559
the
Token the
Feature activation+0.658
wild
Token wild
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.947
Lydia
Token Lydia
Feature activation+0.000
full
Token full
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.893
is
Token is
Feature activation+0.000
conditional
Token conditional
Feature activation+0.000
upon
Token upon
Feature activation+2.024
several
Token several
Feature activation+0.000
factors
Token factors
Feature activation+0.000
including
Token including
Feature activation+0.283
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
't
Token't
Feature activation+0.635
happen
Token happen
Feature activation+0.000
until
Token until
Feature activation+0.000
July
Token July
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
.
Token.
Feature activation+1.100
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.025
The
TokenThe
Feature activation+2.255
origin
Token origin
Feature activation+0.000
of
Token of
Feature activation+5.276

INTERVAL 0.000 - 1.038
CONTAINS 99.977%

who
Token who
Feature activation+0.000
kidnapped
Token kidnapped
Feature activation+0.000
and
Token and
Feature activation+0.000
raped
Token raped
Feature activation+0.000
five
Token five
Feature activation+0.000
children
Token children
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
was
Token was
Feature activation+0.000
part
Token part
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
making
Token making
Feature activation+0.000
an
Token an
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
,
Token,
Feature activation+0.000
H
Token H
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ix
Tokenix
Feature activation+0.000
must
Token must
Feature activation+0.000
The
TokenThe
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
number
Token number
Feature activation+0.000
puzzle
Token puzzle
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
in
Token in
Feature activation+0.000
between
Token between
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
rooftop
Token rooftop
Feature activation+0.000
after
Token after
Feature activation+0.000
-
Token-
Feature activation+0.000
part
Tokenpart
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
I
Token I
Feature activation+0.000
and
Token and
Feature activation+0.000
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
examine
Token examine
Feature activation+0.000
and
Token and
Feature activation+0.000
per
Token per
Feature activation+0.000
sec
Tokensec
Feature activation+0.000
ute
Tokenute
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 H10.1: (feature 14701)

TOP ACTIVATIONS
MAX = 7.905

the
Token the
Feature activation+1.705
particular
Token particular
Feature activation+5.991
machine
Token machine
Feature activation+0.000
with
Token with
Feature activation+1.865
which
Token which
Feature activation+4.932
the
Token the
Feature activation+7.905
hard
Token hard
Feature activation+1.699
drive
Token drive
Feature activation+0.787
was
Token was
Feature activation+0.000
associated
Token associated
Feature activation+0.000
;
Token;
Feature activation+0.000
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+7.870
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
.
Token.
Feature activation+0.976
He
Token He
Feature activation+0.000
also
Token also
Feature activation+0.000
argues
Token argues
Feature activation+0.000
that
Token that
Feature activation+3.437
because
Token because
Feature activation+6.993
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
Constantinople
Token Constantinople
Feature activation+3.615
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
currently
Token currently
Feature activation+0.000
have
Token have
Feature activation+2.236
a
Token a
Feature activation+6.549
release
Token release
Feature activation+0.000
date
Token date
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
is
Token is
Feature activation+0.000
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
drive
Token drive
Feature activation+0.689
is
Token is
Feature activation+0.291
deg
Token deg
Feature activation+0.000
a
Tokena
Feature activation+0.000
,
Token,
Feature activation+3.568
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
drive
Token drive
Feature activation+0.689
is
Token is
Feature activation+0.291
deg
Token deg
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hard
TokenHard
Feature activation+0.000
Cover
Token Cover
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
message
Token message
Feature activation+0.000
violate
Token violate
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
.
Token.
Feature activation+6.191
(
Token (
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
:
Token:
Feature activation+0.000
Henri
Token Henri
Feature activation+0.000
etta
Tokenetta
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hard
TokenHard
Feature activation+0.000
Cover
Token Cover
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.163
with
Token with
Feature activation+2.192
a
Token a
Feature activation+3.460
faux
Token faux
Feature activation+2.160
Cover
Token Cover
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.163
with
Token with
Feature activation+2.192
employee
Token employee
Feature activation+0.524
's
Token's
Feature activation+4.009
name
Token name
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+1.705
particular
Token particular
Feature activation+5.991
machine
Token machine
Feature activation+0.000
with
Token with
Feature activation+1.865
which
Token which
Feature activation+4.932
the
Token the
Feature activation+7.905
hard
Token hard
Feature activation+1.699
cold
Token cold
Feature activation+0.000
,
Token,
Feature activation+0.000
schedules
Token schedules
Feature activation+0.000
get
Token get
Feature activation+0.000
harder
Token harder
Feature activation+0.000
and
Token and
Feature activation+5.905
easier
Token easier
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
generally
Token generally
Feature activation+0.000
,
Token,
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
hard
Token hard
Feature activation+0.000
drives
Token drives
Feature activation+0.000
,
Token,
Feature activation+3.568
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
the
Token the
Feature activation+2.483
IRS
Token IRS
Feature activation+5.076
's
Token's
Feature activation+2.700
destruction
Token destruction
Feature activation+0.951
policies
Token policies
Feature activation+0.000
concerning
Token concerning
Feature activation+5.491
hard
Token hard
Feature activation+0.908
drives
Token drives
Feature activation+0.000
.
Token.
Feature activation+1.414
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.074
hard
Token hard
Feature activation+0.000
drives
Token drives
Feature activation+0.000
,
Token,
Feature activation+3.568
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
drive
Token drive
Feature activation+0.689
in
Token in
Feature activation+0.000
with
Token with
Feature activation+0.378
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.119
world
Token world
Feature activation+0.000
's
Token's
Feature activation+5.170
great
Token great
Feature activation+0.000
players
Token players
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
vendor
Token vendor
Feature activation+0.000
who
Token who
Feature activation+0.000
can
Token can
Feature activation+0.000
verify
Token verify
Feature activation+3.563
the
Token the
Feature activation+2.483
IRS
Token IRS
Feature activation+5.076
's
Token's
Feature activation+2.700
destruction
Token destruction
Feature activation+0.951
policies
Token policies
Feature activation+0.000
concerning
Token concerning
Feature activation+5.491
hard
Token hard
Feature activation+0.908
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+1.312
that
Token that
Feature activation+0.000
in
Token in
Feature activation+4.980
humanities
Token humanities
Feature activation+0.106
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
or
Token or
Feature activation+0.000
the
Token the
Feature activation+1.705
particular
Token particular
Feature activation+5.991
machine
Token machine
Feature activation+0.000
with
Token with
Feature activation+1.865
which
Token which
Feature activation+4.932
the
Token the
Feature activation+7.905
hard
Token hard
Feature activation+1.699
drive
Token drive
Feature activation+0.787
was
Token was
Feature activation+0.000
associated
Token associated
Feature activation+0.000

Top DFA by src position
MAX = 8.624

whether
Token whether
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
IRS
Token IRS
Feature activation+0.012
Top resid features:
records
Token records
Feature activation+0.018
Top resid features:
whose
Token whose
Feature activation+0.014
Top resid features:
hard
Token hard
Feature activation+4.787
Top resid features:
drive
Token drive
Feature activation+0.058
Top resid features:
is
Token is
Feature activation+0.065
Top resid features:
deg
Token deg
Feature activation-0.401
Top resid features:
a
Tokena
Feature activation+0.003
Top resid features:
ussed
Tokenussed
Feature activation+0.037
Top resid features:
augmented
Token augmented
Feature activation-0.003
Top resid features:
by
Token by
Feature activation+0.009
Top resid features:
doing
Token doing
Feature activation+0.010
Top resid features:
things
Token things
Feature activation-0.018
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
hard
Token hard
Feature activation+8.624
Top resid features:
way
Token way
Feature activation-0.035
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
doing
Token doing
Feature activation+0.039
Top resid features:
everything
Token everything
Feature activation+0.004
Top resid features:
ature
Tokenature
Feature activation-0.249
Top resid features:
decay
Token decay
Feature activation-0.234
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ŀ
TokenĿ
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
hard
Token hard
Feature activation+8.092
Top resid features:
sciences
Token sciences
Feature activation-0.018
Top resid features:
such
Token such
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
physics
Token physics
Feature activation+0.064
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
2018
Token 2018
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
when
Token when
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
further
Token further
Feature activation-0.020
Top resid features:
hard
Token hard
Feature activation+4.696
Top resid features:
fork
Token fork
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Constantinople
Token Constantinople
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
component
Token component
Feature activation-0.069
Top resid features:
parts
Token parts
Feature activation-0.027
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
such
Token such
Feature activation-0.002
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
hard
Token hard
Feature activation+5.463
Top resid features:
drives
Token drives
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
when
Token when
Feature activation+0.011
Top resid features:
being
Token being
Feature activation-0.018
Top resid features:
serv
Token serv
Feature activation-0.085
Top resid features:
policy
Token policy
Feature activation-0.052
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
deg
Token deg
Feature activation-0.171
Top resid features:
a
Tokena
Feature activation+0.001
Top resid features:
uss
Tokenuss
Feature activation+0.017
Top resid features:
hard
Token hard
Feature activation+4.456
Top resid features:
drives
Token drives
Feature activation+0.063
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
including
Token including
Feature activation+0.018
Top resid features:
whether
Token whether
Feature activation+0.098
Top resid features:
the
Token the
Feature activation+0.091
Top resid features:
leaf
Token leaf
Feature activation+0.008
Top resid features:
notes
Token notes
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Hard
TokenHard
Feature activation+6.585
Top resid features:
Cover
Token Cover
Feature activation+0.231
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.104
Top resid features:
Each
TokenEach
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Wal
Token Wal
Feature activation-0.073
Top resid features:
nut
Tokennut
Feature activation-0.019
Top resid features:
Hill
Token Hill
Feature activation-0.018
Top resid features:
Principal
Token Principal
Feature activation-0.185
Top resid features:
Albert
Token Albert
Feature activation-0.116
Top resid features:
Hard
Token Hard
Feature activation+7.083
Top resid features:
ison
Tokenison
Feature activation+0.030
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
religious
Token religious
Feature activation-0.004
Top resid features:
message
Token message
Feature activation+0.011
Top resid features:
violate
Token violate
Feature activation-0.013
Top resid features:
leaf
Token leaf
Feature activation+0.002
Top resid features:
notes
Token notes
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Hard
TokenHard
Feature activation+6.444
Top resid features:
Cover
Token Cover
Feature activation+0.058
Top resid features:
Ċ
TokenĊ
Feature activation+0.130
Top resid features:
Ċ
TokenĊ
Feature activation+0.149
Top resid features:
Each
TokenEach
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
leaf
Token leaf
Feature activation+0.002
Top resid features:
notes
Token notes
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Hard
TokenHard
Feature activation+6.637
Top resid features:
Cover
Token Cover
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Each
TokenEach
Feature activation+0.031
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
leaf
Token leaf
Feature activation+0.009
Top resid features:
notes
Token notes
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Hard
TokenHard
Feature activation+6.585
Top resid features:
Cover
Token Cover
Feature activation+0.124
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Each
TokenEach
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.075
Top resid features:
whether
Token whether
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
IRS
Token IRS
Feature activation+0.007
Top resid features:
records
Token records
Feature activation+0.021
Top resid features:
whose
Token whose
Feature activation+0.018
Top resid features:
hard
Token hard
Feature activation+3.049
Top resid features:
drive
Token drive
Feature activation+0.059
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
deg
Token deg
Feature activation-0.261
Top resid features:
a
Tokena
Feature activation-0.001
Top resid features:
ussed
Tokenussed
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
cold
Token cold
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
schedules
Token schedules
Feature activation-0.067
Top resid features:
get
Token get
Feature activation+0.006
Top resid features:
harder
Token harder
Feature activation+6.317
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
easier
Token easier
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
generally
Token generally
Feature activation+0.000
Top resid features:
policy
Token policy
Feature activation-0.018
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
deg
Token deg
Feature activation-0.833
Top resid features:
a
Tokena
Feature activation-0.001
Top resid features:
uss
Tokenuss
Feature activation+0.027
Top resid features:
hard
Token hard
Feature activation+4.890
Top resid features:
drives
Token drives
Feature activation+0.099
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
including
Token including
Feature activation+0.013
Top resid features:
whether
Token whether
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
policy
Token policy
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
deg
Token deg
Feature activation-0.067
Top resid features:
a
Tokena
Feature activation+0.002
Top resid features:
uss
Tokenuss
Feature activation+0.005
Top resid features:
hard
Token hard
Feature activation+3.526
Top resid features:
drives
Token drives
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
including
Token including
Feature activation-0.001
Top resid features:
whether
Token whether
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
policy
Token policy
Feature activation-0.064
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
deg
Token deg
Feature activation-0.819
Top resid features:
a
Tokena
Feature activation+0.002
Top resid features:
uss
Tokenuss
Feature activation+0.015
Top resid features:
hard
Token hard
Feature activation+4.007
Top resid features:
drives
Token drives
Feature activation+0.118
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
including
Token including
Feature activation+0.007
Top resid features:
whether
Token whether
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
league
Token league
Feature activation+0.021
Top resid features:
regarded
Token regarded
Feature activation+0.008
Top resid features:
as
Token as
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
hardest
Token hardest
Feature activation+5.344
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
play
Token play
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.032
Top resid features:
with
Token with
Feature activation+0.065
Top resid features:
some
Token some
Feature activation+0.055
Top resid features:
policy
Token policy
Feature activation-0.082
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
deg
Token deg
Feature activation-0.056
Top resid features:
a
Tokena
Feature activation+0.004
Top resid features:
uss
Tokenuss
Feature activation+0.008
Top resid features:
hard
Token hard
Feature activation+2.323
Top resid features:
drives
Token drives
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
including
Token including
Feature activation+0.001
Top resid features:
whether
Token whether
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
ature
Tokenature
Feature activation-0.048
Top resid features:
decay
Token decay
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
Ŀ
TokenĿ
Feature activation-0.005
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
hard
Token hard
Feature activation+5.687
Top resid features:
sciences
Token sciences
Feature activation+0.039
Top resid features:
such
Token such
Feature activation-0.017
Top resid features:
as
Token as
Feature activation+0.010
Top resid features:
physics
Token physics
Feature activation+0.097
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
policy
Token policy
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
deg
Token deg
Feature activation-0.625
Top resid features:
a
Tokena
Feature activation-0.000
Top resid features:
uss
Tokenuss
Feature activation+0.012
Top resid features:
hard
Token hard
Feature activation+3.349
Top resid features:
drives
Token drives
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
including
Token including
Feature activation+0.004
Top resid features:
whether
Token whether
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.49

Head 2: 0.06

Head 3: 0.04

Head 4: 0.05

Head 5: 0.02

Head 6: 0.05

Head 7: 0.06

Head 8: 0.02

Head 9: 0.03

Head 10: 0.08

Head 11: 0.05

Positive logits

Hard8.99

Hard8.58

hard7.97

hard7.63

Soft6.38

soft6.24

harder6.22

Soft5.86

hardness5.68

soft5.52

hardest5.23

tough5.01

Easy4.84

softer4.81

Hardy4.49

Hardcore4.46

Easy4.40

easy4.37

easy4.33

hardened4.22

Negative logits

-2.67

rax-2.49

Interstitial-2.43

END-2.41

GEN-2.40

ajo-2.40

iverse-2.38

aired-2.38

aido-2.36

Winged-2.36

contrace-2.34

endered-2.32

fired-2.31

Cth-2.28

qua-2.28

mascul-2.27

Goddess-2.22

Wind-2.22

Trop-2.21

anten-2.17

INTERVAL 7.115 - 7.905
CONTAINS 0.000%

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+7.870
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
the
Token the
Feature activation+1.705
particular
Token particular
Feature activation+5.991
machine
Token machine
Feature activation+0.000
with
Token with
Feature activation+1.865
which
Token which
Feature activation+4.932
the
Token the
Feature activation+7.905
hard
Token hard
Feature activation+1.699
drive
Token drive
Feature activation+0.787
was
Token was
Feature activation+0.000
associated
Token associated
Feature activation+0.000
;
Token;
Feature activation+0.000

INTERVAL 6.324 - 7.115
CONTAINS 0.000%

including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
drive
Token drive
Feature activation+0.689
is
Token is
Feature activation+0.291
deg
Token deg
Feature activation+0.000
a
Tokena
Feature activation+0.000
Constantinople
Token Constantinople
Feature activation+3.615
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
currently
Token currently
Feature activation+0.000
have
Token have
Feature activation+2.236
a
Token a
Feature activation+6.549
release
Token release
Feature activation+0.000
date
Token date
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.976
He
Token He
Feature activation+0.000
also
Token also
Feature activation+0.000
argues
Token argues
Feature activation+0.000
that
Token that
Feature activation+3.437
because
Token because
Feature activation+6.993
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000

INTERVAL 5.534 - 6.324
CONTAINS 0.001%

uss
Tokenuss
Feature activation+0.000
hard
Token hard
Feature activation+0.000
drives
Token drives
Feature activation+0.000
,
Token,
Feature activation+3.568
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.163
with
Token with
Feature activation+2.192
a
Token a
Feature activation+3.460
faux
Token faux
Feature activation+2.160
Ċ
TokenĊ
Feature activation+0.000
Hard
TokenHard
Feature activation+0.000
Cover
Token Cover
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
Cover
Token Cover
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.074
Each
TokenEach
Feature activation+6.233
of
Token of
Feature activation+0.255
our
Token our
Feature activation+6.009
notebooks
Token notebooks
Feature activation+1.316
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.163
with
Token with
Feature activation+2.192
message
Token message
Feature activation+0.000
violate
Token violate
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
.
Token.
Feature activation+6.191
(
Token (
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
:
Token:
Feature activation+0.000
Henri
Token Henri
Feature activation+0.000
etta
Tokenetta
Feature activation+0.000

INTERVAL 4.743 - 5.534
CONTAINS 0.001%

"
Token "
Feature activation+0.188
But
TokenBut
Feature activation+1.355
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
probably
Token probably
Feature activation+0.561
even
Token even
Feature activation+4.892
harder
Token harder
Feature activation+0.000
for
Token for
Feature activation+2.587
a
Token a
Feature activation+1.117
parent
Token parent
Feature activation+0.000
.
Token.
Feature activation+0.655
hard
Token hard
Feature activation+0.000
drives
Token drives
Feature activation+0.000
,
Token,
Feature activation+3.568
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
whose
Token whose
Feature activation+6.399
hard
Token hard
Feature activation+0.125
drive
Token drive
Feature activation+0.689
in
Token in
Feature activation+0.000
with
Token with
Feature activation+0.378
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.119
world
Token world
Feature activation+0.000
's
Token's
Feature activation+5.170
great
Token great
Feature activation+0.000
players
Token players
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ussed
Tokenussed
Feature activation+1.001
,
Token,
Feature activation+0.000
either
Token either
Feature activation+1.002
by
Token by
Feature activation+0.000
tracking
Token tracking
Feature activation+2.289
the
Token the
Feature activation+4.823
employee
Token employee
Feature activation+0.524
's
Token's
Feature activation+4.009
name
Token name
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+1.705
choice
Tokenchoice
Feature activation+0.000
of
Token of
Feature activation+0.298
black
Token black
Feature activation+0.000
or
Token or
Feature activation+0.000
white
Token white
Feature activation+0.000
).
Token).
Feature activation+4.874
An
Token An
Feature activation+0.971
elastic
Token elastic
Feature activation+0.541
band
Token band
Feature activation+0.000
holds
Token holds
Feature activation+0.000
the
Token the
Feature activation+2.486

INTERVAL 3.953 - 4.743
CONTAINS 0.001%

in
Token in
Feature activation+0.000
being
Token being
Feature activation+0.000
led
Token led
Feature activation+0.000
around
Token around
Feature activation+0.000
by
Token by
Feature activation+3.193
the
Token the
Feature activation+4.640
Greens
Token Greens
Feature activation+0.000
,''
Token,''
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
either
Token either
Feature activation+1.002
by
Token by
Feature activation+0.000
tracking
Token tracking
Feature activation+2.289
the
Token the
Feature activation+4.823
employee
Token employee
Feature activation+0.524
's
Token's
Feature activation+4.009
name
Token name
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+1.705
particular
Token particular
Feature activation+5.991
machine
Token machine
Feature activation+0.000
hard
Token hard
Feature activation+0.000
choices
Token choices
Feature activation+0.000
.
Token.
Feature activation+0.000
Oh
Token Oh
Feature activation+0.000
and
Token and
Feature activation+0.000
by
Token by
Feature activation+4.573
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
fluor
Token fluor
Feature activation+0.000
or
Token or
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
receive
Token receive
Feature activation+0.430
two
Token two
Feature activation+4.582
copies
Token copies
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+3.240
.
Token.
Feature activation+0.063
Goods
Token Goods
Feature activation+0.000
:
Token:
Feature activation+0.000
Live
Token Live
Feature activation+0.000
Hard
Token Hard
Feature activation+0.000
,
Token,
Feature activation+1.177
Sell
Token Sell
Feature activation+4.027
Hard
Token Hard
Feature activation+1.599
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
How
Token How
Feature activation+0.000

INTERVAL 3.162 - 3.953
CONTAINS 0.002%

prices
Token prices
Feature activation+0.000
.
Token.
Feature activation+1.408
Instead
Token Instead
Feature activation+2.750
of
Token of
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
,
Token,
Feature activation+3.363
a
Token a
Feature activation+1.174
third
Token third
Feature activation+3.369
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.798
show
Token show
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
by
Token by
Feature activation+0.511
Krist
Token Krist
Feature activation+0.000
ine
Tokenine
Feature activation+0.046
Lars
Token Lars
Feature activation+0.000
en
Tokenen
Feature activation+3.169
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
redict
Tokenredict
Feature activation+0.000
ing
Tokening
Feature activation+0.000
deg
Token deg
Feature activation+0.000
a
Tokena
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
hard
Token hard
Feature activation+0.000
drives
Token drives
Feature activation+0.000
,
Token,
Feature activation+3.568
including
Token including
Feature activation+2.897
whether
Token whether
Feature activation+5.589
the
Token the
Feature activation+5.246
IRS
Token IRS
Feature activation+0.000
records
Token records
Feature activation+6.302
Ford
Token Ford
Feature activation+0.000
Motor
Token Motor
Feature activation+0.000
Company
Token Company
Feature activation+0.000
,
Token,
Feature activation+0.051
the
Token the
Feature activation+0.918
first
Token first
Feature activation+3.898
production
Token production
Feature activation+0.394
Mustang
Token Mustang
Feature activation+0.000
was
Token was
Feature activation+0.000
formally
Token formally
Feature activation+0.000
rolled
Token rolled
Feature activation+0.000
act
Token act
Feature activation+0.000
on
Token on
Feature activation+0.621
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.013
s
Tokens
Feature activation+3.710
perceptions
Token perceptions
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.037
The
TokenThe
Feature activation+0.512
auditor
Token auditor
Feature activation+0.000

INTERVAL 2.372 - 3.162
CONTAINS 0.004%

hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.163
with
Token with
Feature activation+2.192
a
Token a
Feature activation+3.460
faux
Token faux
Feature activation+2.160
leather
Token leather
Feature activation+2.763
finish
Token finish
Feature activation+0.000
(
Token (
Feature activation+0.263
choice
Tokenchoice
Feature activation+0.000
of
Token of
Feature activation+0.298
black
Token black
Feature activation+0.000
any
Token any
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
bacteria
Token bacteria
Feature activation+0.000
or
Token or
Feature activation+0.000
fungus
Token fungus
Feature activation+0.000
,
Token,
Feature activation+3.035
we
Token we
Feature activation+0.000
enter
Token enter
Feature activation+2.046
the
Token the
Feature activation+0.000
Frog
Token Frog
Feature activation+0.000
P
TokenP
Feature activation+0.000
scene
Token scene
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.913
a
Token a
Feature activation+0.459
scene
Token scene
Feature activation+2.020
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+2.283
Ev
Token Ev
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
uation
Tokenuation
Feature activation+0.000
Order
Token Order
Feature activation+0.000
in
Token in
Feature activation+0.000
H
Token H
Feature activation+2.415
uckle
Tokenuckle
Feature activation+0.000
berry
Tokenberry
Feature activation+0.000
fire
Token fire
Feature activation+0.000
completely
Token completely
Feature activation+0.000
lifted
Token lifted
Feature activation+0.000
outside
Token outside
Feature activation+0.364
vendor
Token vendor
Feature activation+0.000
who
Token who
Feature activation+0.000
can
Token can
Feature activation+0.000
verify
Token verify
Feature activation+3.563
the
Token the
Feature activation+2.483
IRS
Token IRS
Feature activation+5.076
's
Token's
Feature activation+2.700
destruction
Token destruction
Feature activation+0.951
policies
Token policies
Feature activation+0.000
concerning
Token concerning
Feature activation+5.491

INTERVAL 1.581 - 2.372
CONTAINS 0.009%

lation
Tokenlation
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.055
sc
Tokensc
Feature activation+0.000
ared
Tokenared
Feature activation+2.313
stiff
Token stiff
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.171
utter
Tokenutter
Feature activation+1.060
think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.957
also
Token also
Feature activation+1.819
very
Token very
Feature activation+1.722
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
the
Token the
Feature activation+0.000
Ev
Token Ev
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
uation
Tokenuation
Feature activation+0.000
order
Token order
Feature activation+0.000
in
Token in
Feature activation+0.000
Port
Token Port
Feature activation+1.848
Hardy
Token Hardy
Feature activation+0.000
lifted
Token lifted
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
TokenK
Feature activation+0.000
think
Token think
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.423
lot
Token lot
Feature activation+2.719
of
Token of
Feature activation+2.063
times
Token times
Feature activation+2.050
when
Token when
Feature activation+0.075
I
Token I
Feature activation+0.000
hear
Token hear
Feature activation+0.194
gamers
Token gamers
Feature activation+0.000
is
Token is
Feature activation+6.058
hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.163
with
Token with
Feature activation+2.192
a
Token a
Feature activation+3.460
faux
Token faux
Feature activation+2.160
leather
Token leather
Feature activation+2.763
finish
Token finish
Feature activation+0.000
(
Token (
Feature activation+0.263
choice
Tokenchoice
Feature activation+0.000
of
Token of
Feature activation+0.298

INTERVAL 0.791 - 1.581
CONTAINS 0.019%

and
Token and
Feature activation+0.553
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
critical
Token critical
Feature activation+0.000
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+0.870
how
Token how
Feature activation+0.281
it
Token it
Feature activation+0.000
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
trade
Token trade
Feature activation+0.000
-
Token-
Feature activation+0.000
offs
Tokenoffs
Feature activation+0.000
were
Token were
Feature activation+1.338
tough
Token tough
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
choices
Token choices
Feature activation+0.000
were
Token were
Feature activation+0.197
rules
Token rules
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
hard
Token hard
Feature activation+0.000
time
Token time
Feature activation+0.000
maintaining
Token maintaining
Feature activation+0.968
a
Token a
Feature activation+1.347
long
Token long
Feature activation+0.000
term
Token term
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.118
I
TokenI
Feature activation+0.000
dropped
Token dropped
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+1.267
publisher
Token publisher
Feature activation+0.000
to
Token to
Feature activation+0.000
sign
Token sign
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
me
Token me
Feature activation+0.000
today
Token today
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.878
many
Token many
Feature activation+2.420
Republicans
Token Republicans
Feature activation+0.000
objected
Token objected
Feature activation+0.000
to
Token to
Feature activation+1.962
the
Token the
Feature activation+1.770

INTERVAL 0.000 - 0.791
CONTAINS 99.963%

SH
TokenSH
Feature activation+0.000
INE
TokenINE
Feature activation+0.000
CO
Token CO
Feature activation+0.000
AST
TokenAST
Feature activation+0.000
:
Token:
Feature activation+0.000
Ev
Token Ev
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
uation
Tokenuation
Feature activation+0.000
alert
Token alert
Feature activation+0.000
issued
Token issued
Feature activation+0.000
due
Token due
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
hopes
Token hopes
Feature activation+0.000
Austrian
Token Austrian
Feature activation+0.000
law
Token law
Feature activation+0.000
is
Token is
Feature activation+0.000
changed
Token changed
Feature activation+0.000
18
Token 18
Feature activation+0.000
87
Token87
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
decade
Token decade
Feature activation+0.000
of
Token of
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
Iraqi
Token Iraqi
Feature activation+0.000
delegation
Token delegation
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
institute
Token institute
Feature activation+0.000
agreed
Token agreed
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Dane
Token Dane
Feature activation+0.000
County
Token County
Feature activation+0.000
Clerk
Token Clerk
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
McD
Token McD
Feature activation+0.000
one
Tokenone
Feature activation+0.000
ll
Tokenll
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 H10.1: (feature 13170)

TOP ACTIVATIONS
MAX = 10.012

games
Token games
Feature activation+0.000
and
Token and
Feature activation+0.000
rule
Token rule
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.407
.
Token.
Feature activation+10.012
(
Token (
Feature activation+0.965
hide
Tokenhide
Feature activation+0.000
)
Token)
Feature activation+2.026
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.912
journey
Token journey
Feature activation+0.000
together
Token together
Feature activation+0.000
,
Token,
Feature activation+0.626
a
Token a
Feature activation+4.118
long
Token long
Feature activation+0.746
,
Token,
Feature activation+5.814
long
Token long
Feature activation+0.246
journey
Token journey
Feature activation+0.000
.
Token.
Feature activation+0.388
May
Token May
Feature activation+0.000
it
Token it
Feature activation+0.000
40
Token 40
Feature activation+0.000
pc
Token pc
Feature activation+0.000
tenants
Token tenants
Feature activation+0.000
.
Token.
Feature activation+4.929
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.807
Speaking
TokenSpeaking
Feature activation+0.000
to
Token to
Feature activation+0.869
Independent
Token Independent
Feature activation+0.000
.
Token.
Feature activation+0.000
ie
Tokenie
Feature activation+0.039
,
Token,
Feature activation+0.872
and
Token and
Feature activation+2.793
they
Token they
Feature activation+0.000
can
Token can
Feature activation+1.020
keep
Token keep
Feature activation+4.128
buying
Token buying
Feature activation+5.790
them
Token them
Feature activation+1.256
and
Token and
Feature activation+1.471
providing
Token providing
Feature activation+1.556
high
Token high
Feature activation+0.320
-
Token-
Feature activation+0.477
Independent
Token Independent
Feature activation+0.000
.
Token.
Feature activation+0.000
ie
Tokenie
Feature activation+0.039
this
Token this
Feature activation+0.000
morning
Token morning
Feature activation+0.597
,
Token,
Feature activation+5.660
local
Token local
Feature activation+0.000
C
Token C
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
r
Tokenr
Feature activation+0.000
D
Token D
Feature activation+0.000
up
Token up
Feature activation+0.000
of
Token of
Feature activation+5.017
noteworthy
Token noteworthy
Feature activation+5.455
g
Token g
Feature activation+0.000
ents
Tokenents
Feature activation+1.625
with
Token with
Feature activation+5.645
long
Token long
Feature activation+1.876
locks
Token locks
Feature activation+0.067
is
Token is
Feature activation+0.000
bound
Token bound
Feature activation+0.000
to
Token to
Feature activation+0.000
:
Token:
Feature activation+1.159
probably
Token probably
Feature activation+0.835
yes
Token yes
Feature activation+0.000
.
Token.
Feature activation+2.429
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.469
Long
TokenLong
Feature activation+0.411
version
Token version
Feature activation+0.000
,
Token,
Feature activation+2.431
showing
Token showing
Feature activation+0.000
my
Token my
Feature activation+0.000
,
Token,
Feature activation+4.176
this
Token this
Feature activation+2.932
round
Token round
Feature activation+0.102
up
Token up
Feature activation+0.000
of
Token of
Feature activation+5.017
noteworthy
Token noteworthy
Feature activation+5.455
g
Token g
Feature activation+0.000
ents
Tokenents
Feature activation+1.625
with
Token with
Feature activation+5.645
long
Token long
Feature activation+1.876
locks
Token locks
Feature activation+0.067
public
Token public
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+5.421
both
Token both
Feature activation+1.167
Dublin
Token Dublin
Feature activation+0.000
City
Token City
Feature activation+0.000
Council
Token Council
Feature activation+0.000
and
Token and
Feature activation+1.692
way
Token way
Feature activation+1.571
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
,
Token,
Feature activation+5.412
when
Token when
Feature activation+2.730
neither
Token neither
Feature activation+0.976
Baghdad
Token Baghdad
Feature activation+0.000
nor
Token nor
Feature activation+0.374
Washington
Token Washington
Feature activation+0.000
focused
Token focused
Feature activation+0.000
on
Token on
Feature activation+0.586
our
Token our
Feature activation+0.000
core
Token core
Feature activation+0.000
products
Token products
Feature activation+0.066
and
Token and
Feature activation+5.374
business
Token business
Feature activation+0.700
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ord
TokenOrd
Feature activation+0.000
.
Token.
Feature activation+0.555
Now
Token Now
Feature activation+1.157
we
Token we
Feature activation+0.647
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+5.251
out
Token out
Feature activation+0.912
of
Token of
Feature activation+0.929
the
Token the
Feature activation+1.149
L
Token L
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.122
The
TokenThe
Feature activation+0.087
Latino
Token Latino
Feature activation+0.000
population
Token population
Feature activation+0.000
of
Token of
Feature activation+5.213
Long
Token Long
Feature activation+0.000
mont
Tokenmont
Feature activation+0.000
is
Token is
Feature activation+0.000
very
Token very
Feature activation+0.000
diverse
Token diverse
Feature activation+0.000
appearance
Token appearance
Feature activation+0.000
,
Token,
Feature activation+4.176
this
Token this
Feature activation+2.932
round
Token round
Feature activation+0.102
up
Token up
Feature activation+0.000
of
Token of
Feature activation+5.017
noteworthy
Token noteworthy
Feature activation+5.455
g
Token g
Feature activation+0.000
ents
Tokenents
Feature activation+1.625
with
Token with
Feature activation+5.645
long
Token long
Feature activation+1.876
wanted
Token wanted
Feature activation+0.033
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+4.943
negotiations
Token negotiations
Feature activation+0.000
broke
Token broke
Feature activation+0.000
down
Token down
Feature activation+0.000
.
Token.
Feature activation+3.664
No
Token No
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
and
Token and
Feature activation+0.000
40
Token 40
Feature activation+0.000
pc
Token pc
Feature activation+0.000
tenants
Token tenants
Feature activation+0.000
.
Token.
Feature activation+4.929
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.807
Speaking
TokenSpeaking
Feature activation+0.000
to
Token to
Feature activation+0.869
Independent
Token Independent
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+3.758
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.915
Christopher
TokenChristopher
Feature activation+2.447
Pre
Token Pre
Feature activation+0.000
ble
Tokenble
Feature activation+0.000
,
Token,
Feature activation+0.304
vice
Token vice
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
hospitalized
Token hospitalized
Feature activation+0.000
.
Token.
Feature activation+4.178
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.864
Additional
TokenAdditional
Feature activation+0.000
details
Token details
Feature activation+0.000
about
Token about
Feature activation+0.770
the
Token the
Feature activation+0.000
incident
Token incident
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.389
T
TokenT
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
acco
Tokenacco
Feature activation+0.000
exception
Token exception
Feature activation+0.000
(
Token (
Feature activation+4.801
Canada
TokenCanada
Feature activation+0.000
reserves
Token reserves
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
was
Token was
Feature activation+0.017
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.124
s
Tokens
Feature activation+4.796
role
Token role
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
bir
Token bir
Feature activation+0.000
ther
Tokenther
Feature activation+0.000

Top DFA by src position
MAX = 10.212

and
Token and
Feature activation-0.001
Top resid features:
rule
Token rule
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Long
Token Long
Feature activation+10.212
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
reliable
Token reliable
Feature activation+0.006
Top resid features:
S
Token S
Feature activation+0.033
Top resid features:
shots
Token shots
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
together
Token together
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
long
Token long
Feature activation+1.699
Top resid features:
,
Token,
Feature activation+0.216
Top resid features:
long
Token long
Feature activation+2.532
Top resid features:
journey
Token journey
Feature activation+0.010
Top resid features:
together
Token together
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
long
Token long
Feature activation+1.528
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
play
Token play
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Long
TokenLong
Feature activation+6.379
Top resid features:
boat
Tokenboat
Feature activation+0.035
Top resid features:
Qu
Token Qu
Feature activation-0.076
Top resid features:
ay
Tokenay
Feature activation-0.011
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
60
Token 60
Feature activation+0.011
Top resid features:
simple
Token simple
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
They
Token They
Feature activation+0.001
Top resid features:
can
Token can
Feature activation-0.013
Top resid features:
buy
Token buy
Feature activation+0.010
Top resid features:
long
Token long
Feature activation+4.265
Top resid features:
-
Token-
Feature activation+0.573
Top resid features:
term
Tokenterm
Feature activation+1.037
Top resid features:
government
Token government
Feature activation+0.299
Top resid features:
securities
Token securities
Feature activation+0.120
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
play
Token play
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Long
TokenLong
Feature activation+6.256
Top resid features:
boat
Tokenboat
Feature activation+0.054
Top resid features:
Qu
Token Qu
Feature activation-0.071
Top resid features:
ay
Tokenay
Feature activation-0.031
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
60
Token 60
Feature activation+0.004
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
l
Tokenl
Feature activation-0.001
Top resid features:
isters
Tokenisters
Feature activation+0.001
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
sport
Token sport
Feature activation+0.008
Top resid features:
longer
Token longer
Feature activation+3.756
Top resid features:
t
Token t
Feature activation-0.053
Top resid features:
resses
Tokenresses
Feature activation+0.038
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
we
Token we
Feature activation-0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
best
Token best
Feature activation-0.015
Top resid features:
?
Token?
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Short
TokenShort
Feature activation+5.809
Top resid features:
version
Token version
Feature activation+0.064
Top resid features:
:
Token:
Feature activation+0.024
Top resid features:
probably
Token probably
Feature activation-0.002
Top resid features:
yes
Token yes
Feature activation-0.027
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
You
TokenYou
Feature activation-0.000
Top resid features:
might
Token might
Feature activation+0.001
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
rocking
Token rocking
Feature activation-0.033
Top resid features:
long
Token long
Feature activation+2.312
Top resid features:
hair
Token hair
Feature activation+0.043
Top resid features:
isn
Token isn
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
play
Token play
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Long
TokenLong
Feature activation+5.855
Top resid features:
boat
Tokenboat
Feature activation+0.118
Top resid features:
Qu
Token Qu
Feature activation-0.067
Top resid features:
ay
Tokenay
Feature activation-0.036
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
60
Token 60
Feature activation+0.004
Top resid features:
crime
Token crime
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Austin
TokenAustin
Feature activation-0.035
Top resid features:
Long
Token Long
Feature activation+5.835
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
Columbia
Token Columbia
Feature activation+0.018
Top resid features:
University
Token University
Feature activation+0.000
Top resid features:
international
Token international
Feature activation+0.002
Top resid features:
important
Token important
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
our
Token our
Feature activation+0.009
Top resid features:
mission
Token mission
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
long
Token long
Feature activation+4.841
Top resid features:
term
Token term
Feature activation+0.679
Top resid features:
strategy
Token strategy
Feature activation+0.038
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
but
Token but
Feature activation+0.004
Top resid features:
we
Token we
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
humans
Token humans
Feature activation-0.008
Top resid features:
became
Token became
Feature activation+0.030
Top resid features:
short
Token short
Feature activation+5.379
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
stock
Token stock
Feature activation+0.003
Top resid features:
y
Tokeny
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
improvement
Token improvement
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
He
Token He
Feature activation-0.001
Top resid features:
moved
Token moved
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
Long
Token Long
Feature activation+5.847
Top resid features:
mont
Tokenmont
Feature activation-0.127
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
1984
Token 1984
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
-
Token-
Feature activation-0.007
Top resid features:
l
Tokenl
Feature activation-0.007
Top resid features:
isters
Tokenisters
Feature activation+0.013
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
sport
Token sport
Feature activation+0.007
Top resid features:
longer
Token longer
Feature activation+2.710
Top resid features:
t
Token t
Feature activation-0.056
Top resid features:
resses
Tokenresses
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
we
Token we
Feature activation-0.001
Top resid features:
think
Token think
Feature activation-0.000
Top resid features:
crime
Token crime
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Austin
TokenAustin
Feature activation-0.035
Top resid features:
Long
Token Long
Feature activation+5.305
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
Columbia
Token Columbia
Feature activation+0.015
Top resid features:
University
Token University
Feature activation-0.001
Top resid features:
international
Token international
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
play
Token play
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Long
TokenLong
Feature activation+5.526
Top resid features:
boat
Tokenboat
Feature activation+0.077
Top resid features:
Qu
Token Qu
Feature activation-0.107
Top resid features:
ay
Tokenay
Feature activation-0.028
Top resid features:
is
Token is
Feature activation+0.015
Top resid features:
60
Token 60
Feature activation+0.014
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
Iraq
Token Iraq
Feature activation+0.030
Top resid features:
,"
Token,"
Feature activation+0.010
Top resid features:
Long
Token Long
Feature activation+5.242
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
"
Token "
Feature activation+0.002
Top resid features:
But
TokenBut
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
occupants
Token occupants
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Short
TokenShort
Feature activation+5.293
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
firefighter
Token firefighter
Feature activation+0.032
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
treated
Token treated
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Climate
TokenClimate
Feature activation+0.034
Top resid features:
change
Token change
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+0.005
Top resid features:
short
Tokenshort
Feature activation+5.462
Top resid features:
en
Tokenen
Feature activation+0.190
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
article
Token article
Feature activation-0.051
Top resid features:
)
Token)
Feature activation+0.004
Top resid features:
Labour
Token Labour
Feature activation+0.041
Top resid features:
finally
Token finally
Feature activation+0.021
Top resid features:
dred
Token dred
Feature activation-0.001
Top resid features:
ged
Tokenged
Feature activation+0.005
Top resid features:
up
Token up
Feature activation+0.014
Top resid features:
his
Token his
Feature activation-0.004
Top resid features:
long
Token long
Feature activation+5.522
Top resid features:
form
Tokenform
Feature activation+0.027
Top resid features:
birth
Token birth
Feature activation-0.222
Top resid features:
certificate
Token certificate
Feature activation+0.118
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
But
Token But
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.49

Head 2: 0.05

Head 3: 0.08

Head 4: 0.03

Head 5: 0.02

Head 6: 0.04

Head 7: 0.07

Head 8: 0.03

Head 9: 0.03

Head 10: 0.05

Head 11: 0.07

Positive logits

Long7.73

Long7.66

long7.30

long7.23

short7.06

short6.86

LONG6.78

Short6.66

Short6.48

longer6.20

longest5.54

shorter5.51

shortest5.19

shorten4.65

leng4.11

prolonged4.03

length4.03

extended4.02

lengthy3.91

shortened3.83

Negative logits

eous-2.75

conscious-2.64

ivari-2.59

insk-2.50

eer-2.49

oteric-2.32

Gunn-2.28

essional-2.27

-2.25

-2.23

Freeman-2.22

nude-2.19

esthes-2.15

Frey-2.13

roph-2.10

ophone-2.10

ieu-2.09

clad-2.08

othermal-2.08

rock-2.08

INTERVAL 9.011 - 10.012
CONTAINS 0.000%

games
Token games
Feature activation+0.000
and
Token and
Feature activation+0.000
rule
Token rule
Feature activation+0.000
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.407
.
Token.
Feature activation+10.012
(
Token (
Feature activation+0.965
hide
Tokenhide
Feature activation+0.000
)
Token)
Feature activation+2.026
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.912

INTERVAL 8.010 - 9.011
CONTAINS 0.000%

INTERVAL 7.009 - 8.010
CONTAINS 0.000%

INTERVAL 6.007 - 7.009
CONTAINS 0.000%

INTERVAL 5.006 - 6.007
CONTAINS 0.002%

,
Token,
Feature activation+0.872
and
Token and
Feature activation+2.793
they
Token they
Feature activation+0.000
can
Token can
Feature activation+1.020
keep
Token keep
Feature activation+4.128
buying
Token buying
Feature activation+5.790
them
Token them
Feature activation+1.256
and
Token and
Feature activation+1.471
providing
Token providing
Feature activation+1.556
high
Token high
Feature activation+0.320
-
Token-
Feature activation+0.477
40
Token 40
Feature activation+0.000
pc
Token pc
Feature activation+0.000
tenants
Token tenants
Feature activation+0.000
.
Token.
Feature activation+4.929
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.807
Speaking
TokenSpeaking
Feature activation+0.000
to
Token to
Feature activation+0.869
Independent
Token Independent
Feature activation+0.000
.
Token.
Feature activation+0.000
ie
Tokenie
Feature activation+0.039
,
Token,
Feature activation+4.176
this
Token this
Feature activation+2.932
round
Token round
Feature activation+0.102
up
Token up
Feature activation+0.000
of
Token of
Feature activation+5.017
noteworthy
Token noteworthy
Feature activation+5.455
g
Token g
Feature activation+0.000
ents
Tokenents
Feature activation+1.625
with
Token with
Feature activation+5.645
long
Token long
Feature activation+1.876
locks
Token locks
Feature activation+0.067
way
Token way
Feature activation+1.571
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
,
Token,
Feature activation+5.412
when
Token when
Feature activation+2.730
neither
Token neither
Feature activation+0.976
Baghdad
Token Baghdad
Feature activation+0.000
nor
Token nor
Feature activation+0.374
Washington
Token Washington
Feature activation+0.000
public
Token public
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+5.421
both
Token both
Feature activation+1.167
Dublin
Token Dublin
Feature activation+0.000
City
Token City
Feature activation+0.000
Council
Token Council
Feature activation+0.000
and
Token and
Feature activation+1.692

INTERVAL 4.005 - 5.006
CONTAINS 0.003%

are
Token are
Feature activation+0.000
fundamentally
Token fundamentally
Feature activation+0.000
political
Token political
Feature activation+0.000
."
Token."
Feature activation+4.130
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.420
Remember
TokenRemember
Feature activation+0.338
that
Token that
Feature activation+1.615
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
was
Token was
Feature activation+0.000
wanted
Token wanted
Feature activation+0.033
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+4.943
negotiations
Token negotiations
Feature activation+0.000
broke
Token broke
Feature activation+0.000
down
Token down
Feature activation+0.000
.
Token.
Feature activation+3.664
No
Token No
Feature activation+0.000
the
Token the
Feature activation+0.000
scene
Token scene
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
hospitalized
Token hospitalized
Feature activation+0.000
.
Token.
Feature activation+4.178
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.864
Additional
TokenAdditional
Feature activation+0.000
details
Token details
Feature activation+0.000
about
Token about
Feature activation+0.770
making
Token making
Feature activation+0.823
a
Token a
Feature activation+0.083
red
Token red
Feature activation+0.000
carpet
Token carpet
Feature activation+0.000
appearance
Token appearance
Feature activation+0.000
,
Token,
Feature activation+4.176
this
Token this
Feature activation+2.932
round
Token round
Feature activation+0.102
up
Token up
Feature activation+0.000
of
Token of
Feature activation+5.017
noteworthy
Token noteworthy
Feature activation+5.455
successful
Token successful
Feature activation+0.849
lay
Token lay
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
off
Token off
Feature activation+0.071
"
Token "
Feature activation+4.545
Short
TokenShort
Feature activation+0.000
"
Token"
Feature activation+0.000
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.014
the
Token the
Feature activation+0.000

INTERVAL 3.004 - 4.005
CONTAINS 0.004%

!
Token!
Feature activation+1.602
After
Token After
Feature activation+0.000
all
Token all
Feature activation+1.878
,
Token,
Feature activation+4.690
if
Token if
Feature activation+3.963
these
Token these
Feature activation+3.918
inspirational
Token inspirational
Feature activation+3.753
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
l
Tokenl
Feature activation+0.000
isters
Tokenisters
Feature activation+0.000
The
TokenThe
Feature activation+2.136
Liberal
Token Liberal
Feature activation+0.000
government
Token government
Feature activation+0.000
opted
Token opted
Feature activation+0.000
to
Token to
Feature activation+0.000
publish
Token publish
Feature activation+3.053
them
Token them
Feature activation+0.000
quietly
Token quietly
Feature activation+0.000
online
Token online
Feature activation+0.000
without
Token without
Feature activation+0.000
a
Token a
Feature activation+0.000
(
Token (
Feature activation+0.000
Labour
TokenLabour
Feature activation+0.000
),
Token),
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
at
Token at
Feature activation+3.644
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
is
Token is
Feature activation+0.160
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
exciting
Token exciting
Feature activation+0.000
project
Token project
Feature activation+0.000
for
Token for
Feature activation+3.898
the
Token the
Feature activation+1.780
city
Token city
Feature activation+0.000
and
Token and
Feature activation+1.355
community
Token community
Feature activation+0.000
of
Token of
Feature activation+4.657
pass
Token pass
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
silicon
Token silicon
Feature activation+0.000
.
Token.
Feature activation+2.074
These
Token These
Feature activation+3.952
wavelengths
Token wavelengths
Feature activation+0.000
of
Token of
Feature activation+0.000
light
Token light
Feature activation+0.000
pass
Token pass
Feature activation+0.000
right
Token right
Feature activation+0.000

INTERVAL 2.002 - 3.004
CONTAINS 0.008%

confirmed
Token confirmed
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
Globe
Token Globe
Feature activation+0.000
that
Token that
Feature activation+1.004
the
Token the
Feature activation+2.665
government
Token government
Feature activation+0.000
is
Token is
Feature activation+0.000
planning
Token planning
Feature activation+0.000
to
Token to
Feature activation+0.000
release
Token release
Feature activation+1.991
not
Token not
Feature activation+0.000
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.087
difference
Token difference
Feature activation+0.000
between
Token between
Feature activation+3.000
a
Token a
Feature activation+3.368
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
least
Token least
Feature activation+0.000
until
Token until
Feature activation+0.826
they
Token they
Feature activation+0.405
google
Token google
Feature activation+2.685
you
Token you
Feature activation+0.222
.
Token.
Feature activation+2.790
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
goal
Token goal
Feature activation+0.000
is
Token is
Feature activation+0.000
without
Token without
Feature activation+0.000
should
Token should
Feature activation+0.000
serve
Token serve
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
impetus
Token impetus
Feature activation+0.000
for
Token for
Feature activation+2.775
greater
Token greater
Feature activation+0.381
cooperation
Token cooperation
Feature activation+0.000
in
Token in
Feature activation+0.000
several
Token several
Feature activation+0.000
areas
Token areas
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
super
Token super
Feature activation+0.674
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.411
you
Token you
Feature activation+2.503
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.368
the
Token the
Feature activation+0.000
migration
Token migration
Feature activation+0.000
figures
Token figures
Feature activation+0.000

INTERVAL 1.001 - 2.002
CONTAINS 0.029%

Getty
Token Getty
Feature activation+0.000
1
Token 1
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
I
Token I
Feature activation+0.000
ker
Tokenker
Feature activation+1.007
Cas
Token Cas
Feature activation+0.000
illas
Tokenillas
Feature activation+0.000
Getty
Token Getty
Feature activation+0.000
2
Token 2
Feature activation+0.000
/
Token/
Feature activation+0.000
.
Token.
Feature activation+0.444
Stay
Token Stay
Feature activation+0.000
tuned
Token tuned
Feature activation+0.000
!
Token!
Feature activation+0.183
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.407
Advertisements
TokenAdvertisements
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Social
TokenSocial
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
:
Token:
Feature activation+0.000
re
Tokenre
Feature activation+0.000
gex
Tokengex
Feature activation+0.000
_
Token_
Feature activation+0.134
tra
Tokentra
Feature activation+0.000
its
Tokenits
Feature activation+0.000
<
Token<
Feature activation+1.093
char
Tokenchar
Feature activation+0.000
,
Token,
Feature activation+0.028
boost
Token boost
Feature activation+0.000
::
Token::
Feature activation+0.000
cpp
Tokencpp
Feature activation+0.000
C
Token C
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
costs
Token costs
Feature activation+0.000
.
Token.
Feature activation+1.269
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.401
Ċ
TokenĊ
Feature activation+0.072
Ċ
TokenĊ
Feature activation+2.082
So
TokenSo
Feature activation+0.657
that
Token that
Feature activation+0.310
could
Token could
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
contingency
Token contingency
Feature activation+0.000
.
Token.
Feature activation+1.230
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.084
The
TokenThe
Feature activation+0.765
threat
Token threat
Feature activation+0.000
to
Token to
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 1.001
CONTAINS 99.954%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Officers
TokenOfficers
Feature activation+0.000
also
Token also
Feature activation+0.000
seized
Token seized
Feature activation+0.000
three
Token three
Feature activation+0.000
handguns
Token handguns
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
small
Token small
Feature activation+0.000
Killed
Token Killed
Feature activation+0.000
Don
Token Don
Feature activation+0.000
Qu
Token Qu
Feature activation+0.000
ix
Tokenix
Feature activation+0.000
ote
Tokenote
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
director
Token director
Feature activation+0.000
has
Token has
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
past
Token past
Feature activation+0.000
financial
Token financial
Feature activation+0.000
performance
Token performance
Feature activation+0.000
are
Token are
Feature activation+0.000
no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
adequate
Token adequate
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
trade
Token trade
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
6
Token 6
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
population
Token population
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
further
Token further
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
phones
Token phones
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
leader
Token leader
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H10.1: (feature 14463)

TOP ACTIVATIONS
MAX = 7.358

ral
Tokenral
Feature activation+0.000
neurons
Token neurons
Feature activation+0.000
(
Token (
Feature activation+5.292
yellow
Tokenyellow
Feature activation+0.249
arrows
Token arrows
Feature activation+0.041
,
Token,
Feature activation+6.223
lower
Token lower
Feature activation+0.469
panels
Token panels
Feature activation+0.000
).
Token).
Feature activation+0.000
(
Token (
Feature activation+0.411
d
Tokend
Feature activation+0.000
groups
Token groups
Feature activation+0.000
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+5.862
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.920
carbon
Tokencarbon
Feature activation+0.192
bubble
Token bubble
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
groups
Token groups
Feature activation+0.000
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+5.862
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
in
Token in
Feature activation+2.662
its
Token its
Feature activation+4.988
designated
Token designated
Feature activation+5.842
orbit
Token orbit
Feature activation+0.341
-
Token -
Feature activation+0.163
this
Token this
Feature activation+2.458
is
Token is
Feature activation+0.000
called
Token called
Feature activation+3.674
ations
Tokenations
Feature activation+0.000
[
Token [
Feature activation+0.000
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.489
Type
TokenType
Feature activation+0.524
of
Token of
Feature activation+3.682
amput
Token amput
Feature activation+0.000
ation
Tokenation
Feature activation+0.749
for
Token for
Feature activation+3.478
sentences
Token sentences
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
High
TokenHigh
Feature activation+0.231
status
Token status
Feature activation+5.465
people
Token people
Feature activation+0.234
always
Token always
Feature activation+0.000
'
Token '
Feature activation+0.000
keep
Tokenkeep
Feature activation+0.000
their
Token their
Feature activation+0.235
stri
Token stri
Feature activation+0.000
aton
Tokenaton
Feature activation+0.000
ig
Tokenig
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
neurons
Token neurons
Feature activation+0.000
(
Token (
Feature activation+5.292
yellow
Tokenyellow
Feature activation+0.249
arrows
Token arrows
Feature activation+0.041
,
Token,
Feature activation+6.223
lower
Token lower
Feature activation+0.469
panels
Token panels
Feature activation+0.000
gestures
Token gestures
Feature activation+0.000
for
Token for
Feature activation+0.423
words
Token words
Feature activation+0.000
.
Token.
Feature activation+2.175
As
Token As
Feature activation+0.858
a
Token a
Feature activation+5.089
general
Token general
Feature activation+0.236
rule
Token rule
Feature activation+4.736
,
Token,
Feature activation+3.458
the
Token the
Feature activation+3.062
higher
Token higher
Feature activation+1.998
orbit
Token orbit
Feature activation+0.000
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
in
Token in
Feature activation+2.662
its
Token its
Feature activation+4.988
designated
Token designated
Feature activation+5.842
orbit
Token orbit
Feature activation+0.341
-
Token -
Feature activation+0.163
this
Token this
Feature activation+2.458
is
Token is
Feature activation+0.000
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.920
carbon
Tokencarbon
Feature activation+0.192
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.264
Our
Token Our
Feature activation+0.000
funds
Token funds
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.897
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.746
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
player
Token player
Feature activation+0.000
characters
Token characters
Feature activation+0.000
\'
Token\'
Feature activation+0.000
water
Token water
Feature activation+0.000
consumption
Token consumption
Feature activation+0.000
.
Token.
Feature activation+4.819
Higher
Token Higher
Feature activation+0.299
values
Token values
Feature activation+0.000
increase
Token increase
Feature activation+0.000
water
Token water
Feature activation+0.000
consumption
Token consumption
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.897
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.746
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
words
Token words
Feature activation+0.000
.
Token.
Feature activation+2.175
As
Token As
Feature activation+0.858
a
Token a
Feature activation+5.089
general
Token general
Feature activation+0.236
rule
Token rule
Feature activation+4.736
,
Token,
Feature activation+3.458
the
Token the
Feature activation+3.062
higher
Token higher
Feature activation+1.998
up
Token up
Feature activation+2.224
the
Token the
Feature activation+1.143
new
Token new
Feature activation+0.000
lower
Token lower
Feature activation+0.000
level
Token level
Feature activation+0.000
,
Token,
Feature activation+1.528
because
Token because
Feature activation+0.611
that
Token that
Feature activation+4.640
is
Token is
Feature activation+0.804
really
Token really
Feature activation+0.441
outside
Token outside
Feature activation+0.000
our
Token our
Feature activation+0.000
control
Token control
Feature activation+0.000
He
Token He
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
colleagues
Token colleagues
Feature activation+0.000
posit
Token posit
Feature activation+0.611
that
Token that
Feature activation+4.416
investors
Token investors
Feature activation+0.000
in
Token in
Feature activation+1.237
oil
Token oil
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
higher
Token higher
Feature activation+0.000
rank
Token rank
Feature activation+0.000
was
Token was
Feature activation+0.000
more
Token more
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
than
Token than
Feature activation+4.392
the
Token the
Feature activation+2.441
last
Token last
Feature activation+2.846
,
Token,
Feature activation+0.305
only
Token only
Feature activation+0.000
the
Token the
Feature activation+0.961
players
Token players
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
.
Token.
Feature activation+3.926
The
Token The
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ed
TokenEd
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.000
back
Token back
Feature activation+0.000
into
Token into
Feature activation+0.041
a
Token a
Feature activation+3.846
higher
Token higher
Feature activation+0.000
orbit
Token orbit
Feature activation+0.000
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+5.862
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.920
carbon
Tokencarbon
Feature activation+0.192
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 6.858

neurons
Token neurons
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
white
Tokenwhite
Feature activation-0.009
Top resid features:
arrows
Token arrows
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
upper
Token upper
Feature activation+6.858
Top resid features:
panels
Token panels
Feature activation+0.050
Top resid features:
)
Token)
Feature activation+0.009
Top resid features:
but
Token but
Feature activation+0.017
Top resid features:
not
Token not
Feature activation+0.014
Top resid features:
SP
Token SP
Feature activation+0.039
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.143
Top resid features:
-
Token-
Feature activation-0.020
Top resid features:
lower
Tokenlower
Feature activation+6.396
Top resid features:
renewables
Token renewables
Feature activation+0.243
Top resid features:
costs
Token costs
Feature activation+0.083
Top resid features:
has
Token has
Feature activation+0.010
Top resid features:
kept
Token kept
Feature activation-0.034
Top resid features:
coal
Token coal
Feature activation+0.057
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.146
Top resid features:
-
Token-
Feature activation-0.025
Top resid features:
lower
Tokenlower
Feature activation+6.130
Top resid features:
renewables
Token renewables
Feature activation+0.304
Top resid features:
costs
Token costs
Feature activation+0.058
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
kept
Token kept
Feature activation-0.006
Top resid features:
coal
Token coal
Feature activation+0.071
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.040
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
lower
Token lower
Feature activation+3.269
Top resid features:
orbit
Token orbit
Feature activation+0.129
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
The
Token The
Feature activation+0.015
Top resid features:
G
Token G
Feature activation-0.095
Top resid features:
OC
TokenOC
Feature activation-0.004
Top resid features:
.[
Token.[
Feature activation+0.028
Top resid features:
11
Token11
Feature activation+0.002
Top resid features:
]
Token]
Feature activation+0.085
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Lower
TokenLower
Feature activation+5.901
Top resid features:
body
Token body
Feature activation+0.285
Top resid features:
amput
Token amput
Feature activation-0.070
Top resid features:
ations
Tokenations
Feature activation+0.019
Top resid features:
[
Token [
Feature activation+0.050
Top resid features:
edit
Token edit
Feature activation-0.024
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.080
Top resid features:
,
Token,
Feature activation-0.048
Top resid features:
less
Token less
Feature activation-0.007
Top resid features:
skilled
Token skilled
Feature activation+0.018
Top resid features:
lower
Token lower
Feature activation+5.108
Top resid features:
-
Token-
Feature activation+0.318
Top resid features:
status
Tokenstatus
Feature activation+0.254
Top resid features:
person
Token person
Feature activation+0.029
Top resid features:
will
Token will
Feature activation+0.011
Top resid features:
rely
Token rely
Feature activation+0.005
Top resid features:
neurons
Token neurons
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
white
Tokenwhite
Feature activation-0.426
Top resid features:
arrows
Token arrows
Feature activation+0.062
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
upper
Token upper
Feature activation+6.318
Top resid features:
panels
Token panels
Feature activation+0.006
Top resid features:
)
Token)
Feature activation+0.011
Top resid features:
but
Token but
Feature activation+0.007
Top resid features:
not
Token not
Feature activation+0.005
Top resid features:
SP
Token SP
Feature activation+0.027
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.157
Top resid features:
,
Token,
Feature activation-0.023
Top resid features:
less
Token less
Feature activation-0.014
Top resid features:
skilled
Token skilled
Feature activation+0.017
Top resid features:
lower
Token lower
Feature activation+4.834
Top resid features:
-
Token-
Feature activation+0.351
Top resid features:
status
Tokenstatus
Feature activation+0.235
Top resid features:
person
Token person
Feature activation+0.030
Top resid features:
will
Token will
Feature activation+0.027
Top resid features:
rely
Token rely
Feature activation+0.014
Top resid features:
bring
Token bring
Feature activation-0.004
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
back
Token back
Feature activation-0.009
Top resid features:
into
Token into
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.030
Top resid features:
higher
Token higher
Feature activation+3.517
Top resid features:
orbit
Token orbit
Feature activation+0.182
Top resid features:
or
Token or
Feature activation+0.005
Top resid features:
keep
Token keep
Feature activation+0.033
Top resid features:
it
Token it
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.134
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.096
Top resid features:
-
Token-
Feature activation-0.010
Top resid features:
lower
Tokenlower
Feature activation+5.409
Top resid features:
renewables
Token renewables
Feature activation+0.118
Top resid features:
costs
Token costs
Feature activation+0.049
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
kept
Token kept
Feature activation-0.017
Top resid features:
coal
Token coal
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
Our
Token Our
Feature activation+0.124
Top resid features:
funds
Token funds
Feature activation-0.006
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
getting
Token getting
Feature activation-0.004
Top resid features:
lower
Token lower
Feature activation+5.436
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
lower
Token lower
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
characters
Token characters
Feature activation+0.000
Top resid features:
\'
Token\'
Feature activation+0.011
Top resid features:
stamina
Token stamina
Feature activation+0.003
Top resid features:
consumption
Token consumption
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Higher
Token Higher
Feature activation+5.403
Top resid features:
values
Token values
Feature activation+0.120
Top resid features:
increase
Token increase
Feature activation+0.008
Top resid features:
stamina
Token stamina
Feature activation+0.001
Top resid features:
consumption
Token consumption
Feature activation+0.002
Top resid features:
(
Token (
Feature activation-0.018
Top resid features:
.
Token.
Feature activation+0.082
Top resid features:
Our
Token Our
Feature activation+0.089
Top resid features:
funds
Token funds
Feature activation-0.009
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
getting
Token getting
Feature activation-0.010
Top resid features:
lower
Token lower
Feature activation+3.629
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
lower
Token lower
Feature activation+1.585
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.086
Top resid features:
,
Token,
Feature activation-0.036
Top resid features:
less
Token less
Feature activation-0.019
Top resid features:
skilled
Token skilled
Feature activation+0.049
Top resid features:
lower
Token lower
Feature activation+4.478
Top resid features:
-
Token-
Feature activation+0.281
Top resid features:
status
Tokenstatus
Feature activation+0.123
Top resid features:
person
Token person
Feature activation-0.011
Top resid features:
will
Token will
Feature activation+0.020
Top resid features:
rely
Token rely
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
company
Token company
Feature activation-0.011
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
new
Token new
Feature activation-0.023
Top resid features:
lower
Token lower
Feature activation+4.701
Top resid features:
level
Token level
Feature activation+0.673
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
because
Token because
Feature activation+0.058
Top resid features:
that
Token that
Feature activation+0.045
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.142
Top resid features:
-
Token-
Feature activation-0.028
Top resid features:
lower
Tokenlower
Feature activation+4.502
Top resid features:
renewables
Token renewables
Feature activation+0.322
Top resid features:
costs
Token costs
Feature activation+0.106
Top resid features:
has
Token has
Feature activation+0.007
Top resid features:
kept
Token kept
Feature activation-0.012
Top resid features:
coal
Token coal
Feature activation+0.145
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.221
Top resid features:
higher
Token higher
Feature activation+4.243
Top resid features:
rank
Token rank
Feature activation+0.796
Top resid features:
was
Token was
Feature activation+0.015
Top resid features:
more
Token more
Feature activation-0.004
Top resid features:
expensive
Token expensive
Feature activation+0.101
Top resid features:
than
Token than
Feature activation+0.042
Top resid features:
characters
Token characters
Feature activation+0.000
Top resid features:
\'
Token\'
Feature activation+0.009
Top resid features:
stamina
Token stamina
Feature activation+0.003
Top resid features:
consumption
Token consumption
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Higher
Token Higher
Feature activation+3.749
Top resid features:
values
Token values
Feature activation+0.073
Top resid features:
increase
Token increase
Feature activation-0.003
Top resid features:
stamina
Token stamina
Feature activation+0.001
Top resid features:
consumption
Token consumption
Feature activation+0.001
Top resid features:
(
Token (
Feature activation-0.015
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.103
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
lower
Token lower
Feature activation+4.332
Top resid features:
orbit
Token orbit
Feature activation+0.132
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
G
Token G
Feature activation-0.090
Top resid features:
OC
TokenOC
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.122
Top resid features:
-
Token-
Feature activation-0.047
Top resid features:
lower
Tokenlower
Feature activation+4.198
Top resid features:
renewables
Token renewables
Feature activation+0.220
Top resid features:
costs
Token costs
Feature activation+0.049
Top resid features:
has
Token has
Feature activation-0.003
Top resid features:
kept
Token kept
Feature activation-0.041
Top resid features:
coal
Token coal
Feature activation+0.058
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.49

Head 2: 0.05

Head 3: 0.06

Head 4: 0.04

Head 5: 0.03

Head 6: 0.04

Head 7: 0.09

Head 8: 0.04

Head 9: 0.03

Head 10: 0.04

Head 11: 0.05

Positive logits

Lower8.47

Lower8.32

lower7.89

lower7.76

Higher7.17

Upper7.09

upper7.05

Higher6.51

upper6.30

higher6.25

higher6.00

lowered5.35

lowers5.24

lowering4.79

lowest4.14

Hig3.62

Low3.54

low3.53

poorer3.48

Low3.43

Negative logits

turn-2.53

sterdam-2.44

Sick-2.43

Beaut-2.42

Turns-2.37

Blind-2.32

Op-2.30

essions-2.28

seize-2.28

blindness-2.28

turns-2.27

Fasc-2.24

imble-2.23

lete-2.20

metic-2.19

abases-2.17

blind-2.11

opian-2.08

enaries-2.07

Blink-2.07

INTERVAL 6.623 - 7.358
CONTAINS 0.000%

INTERVAL 5.887 - 6.623
CONTAINS 0.000%

groups
Token groups
Feature activation+0.000
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+5.862
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.920
carbon
Tokencarbon
Feature activation+0.192
bubble
Token bubble
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
neurons
Token neurons
Feature activation+0.000
(
Token (
Feature activation+5.292
yellow
Tokenyellow
Feature activation+0.249
arrows
Token arrows
Feature activation+0.041
,
Token,
Feature activation+6.223
lower
Token lower
Feature activation+0.469
panels
Token panels
Feature activation+0.000
).
Token).
Feature activation+0.000
(
Token (
Feature activation+0.411
d
Tokend
Feature activation+0.000

INTERVAL 5.151 - 5.887
CONTAINS 0.001%

sentences
Token sentences
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
High
TokenHigh
Feature activation+0.231
status
Token status
Feature activation+5.465
people
Token people
Feature activation+0.234
always
Token always
Feature activation+0.000
'
Token '
Feature activation+0.000
keep
Tokenkeep
Feature activation+0.000
their
Token their
Feature activation+0.235
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
in
Token in
Feature activation+2.662
its
Token its
Feature activation+4.988
designated
Token designated
Feature activation+5.842
orbit
Token orbit
Feature activation+0.341
-
Token -
Feature activation+0.163
this
Token this
Feature activation+2.458
is
Token is
Feature activation+0.000
called
Token called
Feature activation+3.674
ations
Tokenations
Feature activation+0.000
[
Token [
Feature activation+0.000
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.489
Type
TokenType
Feature activation+0.524
of
Token of
Feature activation+3.682
amput
Token amput
Feature activation+0.000
ation
Tokenation
Feature activation+0.749
for
Token for
Feature activation+3.478
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
groups
Token groups
Feature activation+0.000
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+5.862
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
stri
Token stri
Feature activation+0.000
aton
Tokenaton
Feature activation+0.000
ig
Tokenig
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
neurons
Token neurons
Feature activation+0.000
(
Token (
Feature activation+5.292
yellow
Tokenyellow
Feature activation+0.249
arrows
Token arrows
Feature activation+0.041
,
Token,
Feature activation+6.223
lower
Token lower
Feature activation+0.469
panels
Token panels
Feature activation+0.000

INTERVAL 4.415 - 5.151
CONTAINS 0.001%

Our
Token Our
Feature activation+0.000
funds
Token funds
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.897
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.746
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.897
lower
Token lower
Feature activation+0.000
and
Token and
Feature activation+4.746
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
He
Token He
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
colleagues
Token colleagues
Feature activation+0.000
posit
Token posit
Feature activation+0.611
that
Token that
Feature activation+4.416
investors
Token investors
Feature activation+0.000
in
Token in
Feature activation+1.237
oil
Token oil
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.920
carbon
Tokencarbon
Feature activation+0.192
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.264
orbit
Token orbit
Feature activation+0.000
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
in
Token in
Feature activation+2.662
its
Token its
Feature activation+4.988
designated
Token designated
Feature activation+5.842
orbit
Token orbit
Feature activation+0.341
-
Token -
Feature activation+0.163
this
Token this
Feature activation+2.458
is
Token is
Feature activation+0.000

INTERVAL 3.679 - 4.415
CONTAINS 0.001%

higher
Token higher
Feature activation+0.000
rank
Token rank
Feature activation+0.000
was
Token was
Feature activation+0.000
more
Token more
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
than
Token than
Feature activation+4.392
the
Token the
Feature activation+2.441
last
Token last
Feature activation+2.846
,
Token,
Feature activation+0.305
only
Token only
Feature activation+0.000
the
Token the
Feature activation+0.961
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.000
back
Token back
Feature activation+0.000
into
Token into
Feature activation+0.041
a
Token a
Feature activation+3.846
higher
Token higher
Feature activation+0.000
orbit
Token orbit
Feature activation+0.000
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.489
Type
TokenType
Feature activation+0.524
of
Token of
Feature activation+3.682
amput
Token amput
Feature activation+0.000
ation
Tokenation
Feature activation+0.749
for
Token for
Feature activation+3.478
an
Token an
Feature activation+2.132
A
Token A
Feature activation+0.000
players
Token players
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
.
Token.
Feature activation+3.926
The
Token The
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ed
TokenEd
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+5.862
the
Token the
Feature activation+1.344
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+6.101
a
Token a
Feature activation+3.771
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.920
carbon
Tokencarbon
Feature activation+0.192
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.943 - 3.679
CONTAINS 0.001%

request
Token request
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
or
Token or
Feature activation+0.000
suspend
Token suspend
Feature activation+0.000
the
Token the
Feature activation+3.162
medical
Token medical
Feature activation+0.000
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
designated
Token designated
Feature activation+5.842
orbit
Token orbit
Feature activation+0.341
-
Token -
Feature activation+0.163
this
Token this
Feature activation+2.458
is
Token is
Feature activation+0.000
called
Token called
Feature activation+3.674
orbit
Token orbit
Feature activation+1.052
control
Token control
Feature activation+0.000
.
Token.
Feature activation+0.651
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.383
Ċ
TokenĊ
Feature activation+5.489
Type
TokenType
Feature activation+0.524
of
Token of
Feature activation+3.682
amput
Token amput
Feature activation+0.000
ation
Tokenation
Feature activation+0.749
for
Token for
Feature activation+3.478
an
Token an
Feature activation+2.132
A
Token A
Feature activation+0.000
1
Token1
Feature activation+0.176
classified
Token classified
Feature activation+0.000
sports
Token sports
Feature activation+0.000
.
Token.
Feature activation+2.175
As
Token As
Feature activation+0.858
a
Token a
Feature activation+5.089
general
Token general
Feature activation+0.236
rule
Token rule
Feature activation+4.736
,
Token,
Feature activation+3.458
the
Token the
Feature activation+3.062
higher
Token higher
Feature activation+1.998
up
Token up
Feature activation+2.224
the
Token the
Feature activation+1.143
person
Token person
Feature activation+0.521
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
little
Token little
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
that
Token that
Feature activation+3.661
modest
Token modest
Feature activation+2.084
ly
Tokenly
Feature activation+1.531
higher
Token higher
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 2.208 - 2.943
CONTAINS 0.003%

being
Token being
Feature activation+0.000
caused
Token caused
Feature activation+0.000
by
Token by
Feature activation+0.000
funding
Token funding
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
,
Token,
Feature activation+2.508
the
Token the
Feature activation+0.000
astonishing
Token astonishing
Feature activation+0.000
rise
Token rise
Feature activation+0.000
in
Token in
Feature activation+0.747
college
Token college
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
a
Token a
Feature activation+0.000
lower
Token lower
Feature activation+0.000
orbit
Token orbit
Feature activation+0.000
.
Token.
Feature activation+0.677
The
Token The
Feature activation+2.826
G
Token G
Feature activation+0.000
OC
TokenOC
Feature activation+0.000
E
TokenE
Feature activation+1.233
satellite
Token satellite
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
GE
TokenGE
Feature activation+0.000
wants
Token wants
Feature activation+0.177
to
Token to
Feature activation+2.309
tap
Token tap
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
branding
Token branding
Feature activation+0.000
element
Token element
Feature activation+0.000
tax
Token tax
Feature activation+0.000
is
Token is
Feature activation+0.000
basically
Token basically
Feature activation+0.000
a
Token a
Feature activation+0.000
solution
Token solution
Feature activation+0.000
to
Token to
Feature activation+2.881
a
Token a
Feature activation+0.631
problem
Token problem
Feature activation+0.000
that
Token that
Feature activation+1.037
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
be
Token be
Feature activation+0.000
just
Token just
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
100
Token100
Feature activation+2.237
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.472 - 2.208
CONTAINS 0.007%

Michael
Token Michael
Feature activation+0.000
Gordon
Token Gordon
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
grant
Token grant
Feature activation+0.000
the
Token the
Feature activation+1.686
county
Token county
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.698
unin
Token unin
Feature activation+0.000
hibited
Tokenhibited
Feature activation+0.000
expression
Token expression
Feature activation+0.000
of
Token of
Feature activation+0.000
sexuality
Token sexuality
Feature activation+0.000
.
Token.
Feature activation+1.532
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.513
Q
TokenQ
Feature activation+0.000
)
Token)
Feature activation+0.329
When
Token When
Feature activation+1.135
were
Token were
Feature activation+0.000
scarce
Token scarce
Feature activation+0.000
in
Token in
Feature activation+0.329
the
Token the
Feature activation+1.742
western
Token western
Feature activation+0.091
and
Token and
Feature activation+1.567
south
Token south
Feature activation+0.000
-
Token-
Feature activation+0.000
western
Tokenwestern
Feature activation+0.000
suburbs
Token suburbs
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.012
This
TokenThis
Feature activation+0.000
week
Token week
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.982
s
Tokens
Feature activation+0.260
Carbon
Token Carbon
Feature activation+0.000
Tracker
Token Tracker
Feature activation+0.000
report
Token report
Feature activation+0.000
comes
Token comes
Feature activation+0.000
without
Token without
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
any
Token any
Feature activation+0.000
real
Token real
Feature activation+0.000
warfare
Token warfare
Feature activation+0.000
.
Token.
Feature activation+2.121
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.589
This
TokenThis
Feature activation+0.552
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.736 - 1.472
CONTAINS 0.017%

said
Token said
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
That
TokenThat
Feature activation+1.135
,
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
[
Token [
Feature activation+0.000
generated
Token generated
Feature activation+0.000
at
Token at
Feature activation+0.000
$
Token $
Feature activation+0.000
9
Token9
Feature activation+0.000
.
Token.
Feature activation+0.000
99
Token99
Feature activation+0.878
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
good
Token good
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Tokens
Feature activation+0.000
at
Token at
Feature activation+0.000
$
Token $
Feature activation+0.000
22
Token22
Feature activation+0.000
,
Token,
Feature activation+0.000
647
Token647
Feature activation+0.852
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
clearly
Token clearly
Feature activation+0.078
sloppy
Token sloppy
Feature activation+0.000
about
Token about
Feature activation+0.000
their
Token their
Feature activation+0.000
engagement
Token engagement
Feature activation+0.000
with
Token with
Feature activation+0.850
the
Token the
Feature activation+0.000
audience
Token audience
Feature activation+0.000
(
Token (
Feature activation+0.000
c
Tokenc
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000
a
Token a
Feature activation+3.846
higher
Token higher
Feature activation+0.000
orbit
Token orbit
Feature activation+0.000
or
Token or
Feature activation+1.897
keep
Token keep
Feature activation+0.000
it
Token it
Feature activation+1.387
in
Token in
Feature activation+2.662
its
Token its
Feature activation+4.988
designated
Token designated
Feature activation+5.842
orbit
Token orbit
Feature activation+0.341
-
Token -
Feature activation+0.163

INTERVAL 0.000 - 0.736
CONTAINS 99.971%

fluct
Token fluct
Feature activation+0.000
uation
Tokenuation
Feature activation+0.000
deals
Token deals
Feature activation+0.000
a
Token a
Feature activation+0.000
death
Token death
Feature activation+0.000
blow
Token blow
Feature activation+0.000
to
Token to
Feature activation+0.000
fisheries
Token fisheries
Feature activation+0.000
,
Token,
Feature activation+0.000
drift
Token drift
Feature activation+0.000
wood
Tokenwood
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
ready
Token ready
Feature activation+0.000
for
Token for
Feature activation+0.000
retirement
Token retirement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
án
Tokenán
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
travel
Token travel
Feature activation+0.000
turns
Token turns
Feature activation+0.000
out
Token out
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
lighter
Token lighter
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.000
expected
Token expected
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
app
Token app
Feature activation+0.000
called
Token called
Feature activation+0.000
Stealth
Token Stealth
Feature activation+0.000
Gen
TokenGen
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
meant
Token meant
Feature activation+0.000
to
Token to
Feature activation+0.000
target
Token target
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 H10.1: (feature 13344)

TOP ACTIVATIONS
MAX = 8.102

H
TokenH
Feature activation+0.000
indu
Tokenindu
Feature activation+6.155
âĢ¦
TokenâĢ¦
Feature activation+1.820
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Indian
TokenIndian
Feature activation+8.102
âĢ¦
TokenâĢ¦
Feature activation+0.261
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pak
TokenPak
Feature activation+0.000
istani
Tokenistani
Feature activation+0.178
third
Token third
Feature activation+0.366
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
row
Token row
Feature activation+4.087
the
Token the
Feature activation+7.968
Lamar
Token Lamar
Feature activation+0.000
Hunt
Token Hunt
Feature activation+0.000
US
Token US
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
does
Token does
Feature activation+0.000
better
Token better
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
than
Token than
Feature activation+7.794
the
Token the
Feature activation+0.000
Republicans
Token Republicans
Feature activation+4.320
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Marg
Token Marg
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
James
Token James
Feature activation+0.000
MP
Token MP
Feature activation+0.000
,
Token,
Feature activation+1.045
Parliamentary
Token Parliamentary
Feature activation+7.620
Under
Token Under
Feature activation+0.270
-
Token-
Feature activation+0.000
Secretary
TokenSecretary
Feature activation+0.000
(
Token (
Feature activation+0.000
Department
TokenDepartment
Feature activation+0.000
books
Tokenbooks
Feature activation+0.480
are
Token are
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
H
TokenH
Feature activation+0.000
indu
Tokenindu
Feature activation+6.155
âĢ¦
TokenâĢ¦
Feature activation+1.820
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Indian
TokenIndian
Feature activation+8.102
âĢ¦
TokenâĢ¦
Feature activation+0.261
can
Token can
Feature activation+0.000
only
Token only
Feature activation+1.321
add
Token add
Feature activation+1.540
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.000
app
Token app
Feature activation+6.073
,
Token,
Feature activation+0.641
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.369
any
Token any
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
administration
Token administration
Feature activation+0.836
,
Token,
Feature activation+0.269
and
Token and
Feature activation+3.736
not
Token not
Feature activation+2.216
just
Token just
Feature activation+5.627
the
Token the
Feature activation+0.038
Obama
Token Obama
Feature activation+0.000
regime
Token regime
Feature activation+1.829
,
Token,
Feature activation+0.202
I
Token I
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
have
Token have
Feature activation+0.000
occurred
Token occurred
Feature activation+0.000
under
Token under
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
than
Token than
Feature activation+5.456
under
Token under
Feature activation+0.000
George
Token George
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
add
Token add
Feature activation+0.243
entry
Token entry
Feature activation+1.759
of
Token of
Feature activation+0.000
it
Token it
Feature activation+5.379
in
Token in
Feature activation+0.060
main
Token main
Feature activation+0.000
ur
Token ur
Feature activation+0.000
ls
Tokenls
Feature activation+0.496
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
one
Token one
Feature activation+0.000
at
Token at
Feature activation+0.000
D
Token D
Feature activation+4.991
under
Tokenunder
Feature activation+0.000
-
Token-
Feature activation+0.428
M
TokenM
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
software
Token software
Feature activation+0.000
is
Token is
Feature activation+0.000
used
Token used
Feature activation+0.000
.
Token.
Feature activation+0.278
This
Token This
Feature activation+0.000
flaw
Token flaw
Feature activation+4.770
dispar
Token dispar
Feature activation+0.000
ately
Tokenately
Feature activation+0.000
affected
Token affected
Feature activation+0.000
AT
Token AT
Feature activation+0.000
&
Token&
Feature activation+0.000
and
Token and
Feature activation+0.000
twice
Token twice
Feature activation+0.000
as
Token as
Feature activation+0.000
many
Token many
Feature activation+0.000
civilians
Token civilians
Feature activation+0.761
as
Token as
Feature activation+4.630
Bush
Token Bush
Feature activation+0.460
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.167
s
Tokens
Feature activation+0.886
.
Token.
Feature activation+0.236
Democrats
Token Democrats
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
House
TokenHouse
Feature activation+0.000
Republicans
Token Republicans
Feature activation+4.338
are
Token are
Feature activation+0.399
calling
Token calling
Feature activation+0.000
their
Token their
Feature activation+0.045
bill
Token bill
Feature activation+0.000
The
Token The
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
than
Token than
Feature activation+7.794
the
Token the
Feature activation+0.000
Republicans
Token Republicans
Feature activation+4.320
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
another
Token another
Feature activation+0.000
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
ratio
Token ratio
Feature activation+1.220
employed
Token employed
Feature activation+4.298
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+2.596
,
Token,
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.369
any
Token any
Feature activation+0.000
3
Token 3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
party
Token party
Feature activation+0.000
app
Token app
Feature activation+4.283
within
Token within
Feature activation+0.000
your
Token your
Feature activation+0.000
project
Token project
Feature activation+0.800
and
Token and
Feature activation+0.907
use
Token use
Feature activation+0.502
best
Token best
Feature activation+0.000
under
Token under
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
,
Token,
Feature activation+0.502
although
Token although
Feature activation+1.509
ideally
Token ideally
Feature activation+4.247
less
Token less
Feature activation+2.389
than
Token than
Feature activation+2.261
two
Token two
Feature activation+0.362
tons
Token tons
Feature activation+0.000
per
Token per
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
P
Token P
Feature activation+0.000
AM
TokenAM
Feature activation+0.000
sequence
Token sequence
Feature activation+0.445
(
Token (
Feature activation+4.236
Fig
TokenFig
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
).
Token ).
Feature activation+0.000
It
Token It
Feature activation+0.000
the
Token the
Feature activation+2.384
third
Token third
Feature activation+0.366
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
row
Token row
Feature activation+4.087
the
Token the
Feature activation+7.968
Lamar
Token Lamar
Feature activation+0.000
Hunt
Token Hunt
Feature activation+0.000
US
Token US
Feature activation+0.000
Open
Token Open
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
Boulder
Token Boulder
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+3.958
Har
Token Har
Feature activation+0.000
po
Tokenpo
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.483

Top DFA by src position
MAX = 8.099

indu
Tokenindu
Feature activation-0.000
Top resid features:
&
Token &
Feature activation-0.095
Top resid features:
anti
Token anti
Feature activation-0.013
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
Indian
TokenIndian
Feature activation+0.005
Top resid features:
under
Token under
Feature activation+8.089
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
influence
Token influence
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
Qur
Token Qur
Feature activation+0.006
Top resid features:
anic
Tokenanic
Feature activation-0.006
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.177
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
Meet
TokenMeet
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
Under
Token Under
Feature activation+8.099
Top resid features:
dogs
Tokendogs
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
economy
Token economy
Feature activation+0.034
Top resid features:
does
Token does
Feature activation-0.009
Top resid features:
better
Token better
Feature activation+0.005
Top resid features:
under
Token under
Feature activation+7.931
Top resid features:
the
Token the
Feature activation+0.338
Top resid features:
Democrats
Token Democrats
Feature activation+0.014
Top resid features:
than
Token than
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Republicans
Token Republicans
Feature activation+0.000
Top resid features:
ot
Tokenot
Feature activation-0.001
Top resid features:
James
Token James
Feature activation+0.001
Top resid features:
MP
Token MP
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
Parliamentary
Token Parliamentary
Feature activation-0.019
Top resid features:
Under
Token Under
Feature activation+7.741
Top resid features:
-
Token-
Feature activation+0.332
Top resid features:
Secretary
TokenSecretary
Feature activation+0.155
Top resid features:
(
Token (
Feature activation-0.039
Top resid features:
Department
TokenDepartment
Feature activation-0.000
Top resid features:
for
Token for
Feature activation-0.034
Top resid features:
indu
Tokenindu
Feature activation-0.015
Top resid features:
&
Token &
Feature activation-0.259
Top resid features:
anti
Token anti
Feature activation-0.023
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Indian
TokenIndian
Feature activation+0.002
Top resid features:
under
Token under
Feature activation+6.774
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
influence
Token influence
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
Qur
Token Qur
Feature activation+0.002
Top resid features:
anic
Tokenanic
Feature activation-0.008
Top resid features:
many
Token many
Feature activation+0.002
Top resid features:
apps
Token apps
Feature activation+0.011
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
I
Token I
Feature activation-0.000
Top resid features:
want
Token want
Feature activation+0.001
Top resid features:
under
Token under
Feature activation+4.032
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
single
Token single
Feature activation-0.001
Top resid features:
Project
Token Project
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.035
Top resid features:
e
Tokene
Feature activation-0.006
Top resid features:
conduct
Token conduct
Feature activation+0.013
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
American
Token American
Feature activation+0.011
Top resid features:
foreign
Token foreign
Feature activation+0.006
Top resid features:
policy
Token policy
Feature activation+0.041
Top resid features:
under
Token under
Feature activation+6.157
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
Bush
Token Bush
Feature activation+0.060
Top resid features:
administration
Token administration
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
times
Token times
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
strikes
Token strikes
Feature activation+0.030
Top resid features:
have
Token have
Feature activation+0.008
Top resid features:
occurred
Token occurred
Feature activation+0.025
Top resid features:
under
Token under
Feature activation+5.932
Top resid features:
Obama
Token Obama
Feature activation+0.020
Top resid features:
than
Token than
Feature activation+0.039
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
George
Token George
Feature activation+0.000
Top resid features:
W
Token W
Feature activation+0.000
Top resid features:
create
Token create
Feature activation-0.003
Top resid features:
ur
Token ur
Feature activation-0.035
Top resid features:
ls
Tokenls
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
py
Tokenpy
Feature activation-0.021
Top resid features:
under
Token under
Feature activation+5.440
Top resid features:
tracker
Token tracker
Feature activation+0.016
Top resid features:
folder
Token folder
Feature activation+0.011
Top resid features:
but
Token but
Feature activation+0.073
Top resid features:
I
Token I
Feature activation+0.014
Top resid features:
did
Token did
Feature activation+0.008
Top resid features:
co
Token co
Feature activation-0.000
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
workers
Tokenworkers
Feature activation-0.002
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
D
Token D
Feature activation+0.001
Top resid features:
under
Tokenunder
Feature activation+5.334
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
M
TokenM
Feature activation+0.085
Top resid features:
iff
Tokeniff
Feature activation-0.001
Top resid features:
lin
Tokenlin
Feature activation+0.011
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
has
Token has
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
technical
Token technical
Feature activation-0.020
Top resid features:
flaw
Token flaw
Feature activation-0.096
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
under
Token under
Feature activation+5.347
Top resid features:
states
Tokenstates
Feature activation-0.011
Top resid features:
our
Token our
Feature activation+0.001
Top resid features:
4
Token 4
Feature activation+0.000
Top resid features:
G
TokenG
Feature activation+0.002
Top resid features:
LTE
Token LTE
Feature activation+0.001
Top resid features:
have
Token have
Feature activation+0.001
Top resid features:
occurred
Token occurred
Feature activation+0.002
Top resid features:
under
Token under
Feature activation+1.250
Top resid features:
Obama
Token Obama
Feature activation+0.017
Top resid features:
than
Token than
Feature activation+0.011
Top resid features:
under
Token under
Feature activation+3.624
Top resid features:
George
Token George
Feature activation+0.086
Top resid features:
W
Token W
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Bush
Token Bush
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Pub
TokenPub
Feature activation-0.006
Top resid features:
lishing
Tokenlishing
Feature activation+0.010
Top resid features:
:
Token:
Feature activation+0.002
Top resid features:
Republicans
Token Republicans
Feature activation+0.001
Top resid features:
under
Token under
Feature activation+4.566
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
leadership
Token leadership
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
Speaker
Token Speaker
Feature activation+0.007
Top resid features:
Paul
Token Paul
Feature activation-0.009
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
economy
Token economy
Feature activation-0.015
Top resid features:
does
Token does
Feature activation+0.009
Top resid features:
better
Token better
Feature activation+0.099
Top resid features:
under
Token under
Feature activation+4.568
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
Democrats
Token Democrats
Feature activation+0.003
Top resid features:
than
Token than
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
Republicans
Token Republicans
Feature activation+0.007
Top resid features:
U
Token U
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
exports
Token exports
Feature activation+0.004
Top resid features:
under
Token under
Feature activation+4.291
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
FTA
Token FTA
Feature activation-0.007
Top resid features:
brought
Token brought
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
21
Token 21
Feature activation-0.002
Top resid features:
many
Token many
Feature activation+0.002
Top resid features:
apps
Token apps
Feature activation+0.005
Top resid features:
as
Token as
Feature activation+0.004
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
want
Token want
Feature activation+0.001
Top resid features:
under
Token under
Feature activation+3.139
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
single
Token single
Feature activation-0.001
Top resid features:
Project
Token Project
Feature activation+0.001
Top resid features:
(
Token (
Feature activation+0.020
Top resid features:
e
Tokene
Feature activation-0.005
Top resid features:
worry
Token worry
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
I
Token I
Feature activation+0.049
Top resid features:
work
Token work
Feature activation+0.012
Top resid features:
best
Token best
Feature activation-0.023
Top resid features:
under
Token under
Feature activation+3.879
Top resid features:
pressure
Token pressure
Feature activation+0.380
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
although
Token although
Feature activation+0.176
Top resid features:
ideally
Token ideally
Feature activation+0.061
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
C
Token C
Feature activation+0.006
Top resid features:
CC
TokenCC
Feature activation+0.013
Top resid features:
GG
TokenGG
Feature activation+0.004
Top resid features:
G
TokenG
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+0.016
Top resid features:
under
Tokenunder
Feature activation+4.689
Top resid features:
lined
Tokenlined
Feature activation+0.048
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
Table
Token Table
Feature activation+0.032
Top resid features:
III
Token III
Feature activation+0.029
Top resid features:
B
Token B
Feature activation-0.084
Top resid features:
you
Token you
Feature activation+0.006
Top resid features:
âĢ
Token âĢ
Feature activation+0.205
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
Meet
TokenMeet
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
Under
Token Under
Feature activation+4.255
Top resid features:
dogs
Tokendogs
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ŀ
TokenĿ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
you
Token you
Feature activation-0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.122
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Meet
TokenMeet
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
Under
Token Under
Feature activation+4.383
Top resid features:
dogs
Tokendogs
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ŀ
TokenĿ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.49

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.04

Head 6: 0.04

Head 7: 0.07

Head 8: 0.08

Head 9: 0.04

Head 10: 0.04

Head 11: 0.04

Positive logits

Under8.12

under7.53

under7.49

Under7.05

UNDER6.97

underneath4.20

undert4.16

unders4.06

beneath3.98

DER3.77

Underground3.64

underground3.46

unders3.45

underwater2.87

underside2.78

Over2.77

secret2.71

underage2.69

OVER2.63

below2.57

Negative logits

constitu-2.92

Glad-2.69

hello-2.55

iation-2.52

than-2.50

hom-2.43

subsequ-2.32

plur-2.32

hello-2.30

א-2.27

Hi-2.25

eness-2.25

Bows-2.21

isoft-2.21

Multi-2.19

aign-2.18

RAD-2.17

Osw-2.16

cass-2.15

nicer-2.14

INTERVAL 7.292 - 8.102
CONTAINS 0.000%

third
Token third
Feature activation+0.366
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
row
Token row
Feature activation+4.087
the
Token the
Feature activation+7.968
Lamar
Token Lamar
Feature activation+0.000
Hunt
Token Hunt
Feature activation+0.000
US
Token US
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
does
Token does
Feature activation+0.000
better
Token better
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
than
Token than
Feature activation+7.794
the
Token the
Feature activation+0.000
Republicans
Token Republicans
Feature activation+4.320
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
indu
Tokenindu
Feature activation+6.155
âĢ¦
TokenâĢ¦
Feature activation+1.820
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Indian
TokenIndian
Feature activation+8.102
âĢ¦
TokenâĢ¦
Feature activation+0.261
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pak
TokenPak
Feature activation+0.000
istani
Tokenistani
Feature activation+0.178
Marg
Token Marg
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
James
Token James
Feature activation+0.000
MP
Token MP
Feature activation+0.000
,
Token,
Feature activation+1.045
Parliamentary
Token Parliamentary
Feature activation+7.620
Under
Token Under
Feature activation+0.270
-
Token-
Feature activation+0.000
Secretary
TokenSecretary
Feature activation+0.000
(
Token (
Feature activation+0.000
Department
TokenDepartment
Feature activation+0.000

INTERVAL 6.482 - 7.292
CONTAINS 0.000%

INTERVAL 5.672 - 6.482
CONTAINS 0.000%

books
Tokenbooks
Feature activation+0.480
are
Token are
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
H
TokenH
Feature activation+0.000
indu
Tokenindu
Feature activation+6.155
âĢ¦
TokenâĢ¦
Feature activation+1.820
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Indian
TokenIndian
Feature activation+8.102
âĢ¦
TokenâĢ¦
Feature activation+0.261
can
Token can
Feature activation+0.000
only
Token only
Feature activation+1.321
add
Token add
Feature activation+1.540
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.000
app
Token app
Feature activation+6.073
,
Token,
Feature activation+0.641
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.369
any
Token any
Feature activation+0.000

INTERVAL 4.861 - 5.672
CONTAINS 0.000%

did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
add
Token add
Feature activation+0.243
entry
Token entry
Feature activation+1.759
of
Token of
Feature activation+0.000
it
Token it
Feature activation+5.379
in
Token in
Feature activation+0.060
main
Token main
Feature activation+0.000
ur
Token ur
Feature activation+0.000
ls
Tokenls
Feature activation+0.496
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
one
Token one
Feature activation+0.000
at
Token at
Feature activation+0.000
D
Token D
Feature activation+4.991
under
Tokenunder
Feature activation+0.000
-
Token-
Feature activation+0.428
M
TokenM
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
have
Token have
Feature activation+0.000
occurred
Token occurred
Feature activation+0.000
under
Token under
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
than
Token than
Feature activation+5.456
under
Token under
Feature activation+0.000
George
Token George
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
administration
Token administration
Feature activation+0.836
,
Token,
Feature activation+0.269
and
Token and
Feature activation+3.736
not
Token not
Feature activation+2.216
just
Token just
Feature activation+5.627
the
Token the
Feature activation+0.038
Obama
Token Obama
Feature activation+0.000
regime
Token regime
Feature activation+1.829
,
Token,
Feature activation+0.202
I
Token I
Feature activation+0.000

INTERVAL 4.051 - 4.861
CONTAINS 0.001%

the
Token the
Feature activation+2.384
third
Token third
Feature activation+0.366
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
row
Token row
Feature activation+4.087
the
Token the
Feature activation+7.968
Lamar
Token Lamar
Feature activation+0.000
Hunt
Token Hunt
Feature activation+0.000
US
Token US
Feature activation+0.000
Open
Token Open
Feature activation+0.000
best
Token best
Feature activation+0.000
under
Token under
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
,
Token,
Feature activation+0.502
although
Token although
Feature activation+1.509
ideally
Token ideally
Feature activation+4.247
less
Token less
Feature activation+2.389
than
Token than
Feature activation+2.261
two
Token two
Feature activation+0.362
tons
Token tons
Feature activation+0.000
per
Token per
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
P
Token P
Feature activation+0.000
AM
TokenAM
Feature activation+0.000
sequence
Token sequence
Feature activation+0.445
(
Token (
Feature activation+4.236
Fig
TokenFig
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
).
Token ).
Feature activation+0.000
It
Token It
Feature activation+0.000
and
Token and
Feature activation+0.000
twice
Token twice
Feature activation+0.000
as
Token as
Feature activation+0.000
many
Token many
Feature activation+0.000
civilians
Token civilians
Feature activation+0.761
as
Token as
Feature activation+4.630
Bush
Token Bush
Feature activation+0.460
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.167
s
Tokens
Feature activation+0.886
.
Token.
Feature activation+0.236
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
ratio
Token ratio
Feature activation+1.220
employed
Token employed
Feature activation+4.298
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+2.596
,
Token,
Feature activation+0.000

INTERVAL 3.241 - 4.051
CONTAINS 0.001%

dogs
Tokendogs
Feature activation+0.626
.
Token.
Feature activation+2.584
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.976
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.826
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+2.384
third
Token third
Feature activation+0.366
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
Boulder
Token Boulder
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+3.958
Har
Token Har
Feature activation+0.000
po
Tokenpo
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.483
of
Token of
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.000
.
Token.
Feature activation+0.625
This
Token This
Feature activation+0.072
year
Token year
Feature activation+1.908
,
Token,
Feature activation+3.773
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
Boulder
Token Boulder
Feature activation+0.000
-
Token-
Feature activation+0.000
voters
Token voters
Feature activation+0.000
under
Token under
Feature activation+0.000
30
Token 30
Feature activation+0.000
;
Token;
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
voters
Token voters
Feature activation+3.633
who
Token who
Feature activation+0.275
remember
Token remember
Feature activation+0.000
2000
Token 2000
Feature activation+0.000
are
Token are
Feature activation+0.036
likely
Token likely
Feature activation+0.456
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
@
Token @
Feature activation+0.000
4
Token4
Feature activation+0.000
social
Tokensocial
Feature activation+0.000
housing
Tokenhousing
Feature activation+3.612
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
police
Token police
Feature activation+0.000
officer
Token officer
Feature activation+0.000
shows
Token shows
Feature activation+0.000

INTERVAL 2.431 - 3.241
CONTAINS 0.003%

to
Token to
Feature activation+0.000
wear
Token wear
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.488
of
Token of
Feature activation+0.000
padding
Token padding
Feature activation+3.177
underneath
Token underneath
Feature activation+1.062
your
Token your
Feature activation+0.000
colorful
Token colorful
Feature activation+0.000
suit
Token suit
Feature activation+0.678
.
Token.
Feature activation+0.000
their
Token their
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
.
Token.
Feature activation+0.119
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.265
These
TokenThese
Feature activation+2.542
players
Token players
Feature activation+0.000
have
Token have
Feature activation+0.000
plenty
Token plenty
Feature activation+0.000
of
Token of
Feature activation+0.000
function
Token function
Feature activation+0.000
ratio
Token ratio
Feature activation+1.220
employed
Token employed
Feature activation+4.298
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+2.596
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
trade
Token trade
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000
expansion
Token expansion
Feature activation+1.651
revised
Token revised
Feature activation+0.000
cooling
Token cooling
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
brake
Token brake
Feature activation+0.000
fade
Token fade
Feature activation+2.448
at
Token at
Feature activation+0.000
bay
Token bay
Feature activation+0.000
.
Token.
Feature activation+0.000
Bra
Token Bra
Feature activation+0.000
king
Tokenking
Feature activation+0.000
with
Token with
Feature activation+0.000
characteristics
Token characteristics
Feature activation+0.039
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
also
Token also
Feature activation+0.000
protected
Token protected
Feature activation+2.747
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000

INTERVAL 1.620 - 2.431
CONTAINS 0.008%

under
Token under
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
,
Token,
Feature activation+0.502
although
Token although
Feature activation+1.509
ideally
Token ideally
Feature activation+4.247
less
Token less
Feature activation+2.389
than
Token than
Feature activation+2.261
two
Token two
Feature activation+0.362
tons
Token tons
Feature activation+0.000
per
Token per
Feature activation+0.000
square
Token square
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000
expansion
Token expansion
Feature activation+1.651
implies
Token implies
Feature activation+0.000
the
Token the
Feature activation+0.000
net
Token net
Feature activation+0.000
loss
Token loss
Feature activation+1.709
of
Token of
Feature activation+0.000
over
Token over
Feature activation+0.000
16
Token 16
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
a
Token a
Feature activation+0.000
score
Token score
Feature activation+0.000
line
Token line
Feature activation+0.000
like
Token like
Feature activation+0.000
that
Token that
Feature activation+0.000
happen
Token happen
Feature activation+2.296
again
Token again
Feature activation+0.719
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
CLE
TokenCLE
Feature activation+0.000
VEL
TokenVEL
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
,
Token,
Feature activation+0.502
although
Token although
Feature activation+1.509
ideally
Token ideally
Feature activation+4.247
less
Token less
Feature activation+2.389
than
Token than
Feature activation+2.261
two
Token two
Feature activation+0.362
tons
Token tons
Feature activation+0.000
per
Token per
Feature activation+0.000
square
Token square
Feature activation+0.000
inch
Token inch
Feature activation+0.000
to
Token to
Feature activation+0.000
main
Token main
Feature activation+0.000
ur
Token ur
Feature activation+0.000
ls
Tokenls
Feature activation+0.447
.
Token.
Feature activation+0.000
py
Tokenpy
Feature activation+2.061
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
case
Token case
Feature activation+0.492
in
Token in
Feature activation+0.000

INTERVAL 0.810 - 1.620
CONTAINS 0.019%

would
Token would
Feature activation+0.000
choose
Token choose
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
denied
Token denied
Feature activation+0.000
coverage
Token coverage
Feature activation+1.342
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
existing
Tokenexisting
Feature activation+0.000
bail
Token bail
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
released
Token released
Feature activation+0.855
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
more
Token more
Feature activation+0.000
hours
Token hours
Feature activation+0.075
.
Token.
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
that
Token that
Feature activation+0.419
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
only
Token only
Feature activation+1.321
add
Token add
Feature activation+1.540
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.000
app
Token app
Feature activation+6.073
,
Token,
Feature activation+0.641
you
Token you
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.074
amend
Token amend
Feature activation+0.951
the
Token the
Feature activation+1.464
1964
Token 1964
Feature activation+0.933
Civil
Token Civil
Feature activation+1.460
Rights
Token Rights
Feature activation+0.274
Act
Token Act
Feature activation+0.000
to
Token to
Feature activation+0.000
ban
Token ban
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
under
Token under
Feature activation+0.000
10
Token 10
Feature activation+0.000
$
Token$
Feature activation+0.000
for
Token for
Feature activation+0.840
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
bottle
Token bottle
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.000 - 0.810
CONTAINS 99.967%

400
Token 400
Feature activation+0.000
+
Token+
Feature activation+0.000
cities
Token cities
Feature activation+0.000
where
Token where
Feature activation+0.000
Uber
Token Uber
Feature activation+0.000
operates
Token operates
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
education
Token education
Feature activation+0.000
director
Token director
Feature activation+0.000
Chris
Token Chris
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
contacted
Token contacted
Feature activation+0.000
the
Token the
Feature activation+0.000
Star
Token Star
Feature activation+0.000
late
Token late
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
to
Token to
Feature activation+0.000
judges
Token judges
Feature activation+0.000
and
Token and
Feature activation+0.000
bar
Token bar
Feature activation+0.000
ris
Tokenris
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
alien
Token alien
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
many
Token many
Feature activation+0.000
court
Token court
Feature activation+0.000
users
Token users
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
ge
Token ge
Feature activation+0.000
omet
Tokenomet
Feature activation+0.000
rical
Tokenrical
Feature activation+0.000
foundations
Token foundations
Feature activation+0.000
of
Token of
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
S
TokenS
Feature activation+0.000
2
Token 2
Feature activation+0.000
p
Token p
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
suitable
Token suitable
Feature activation+0.000
length
Token length
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
p
Token p
Feature activation+0.000
the
Token the
Feature activation+0.000
probability
Token probability
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 H10.1: (feature 23995)

TOP ACTIVATIONS
MAX = 10.347

Ċ
TokenĊ
Feature activation+3.926
After
TokenAfter
Feature activation+1.788
V
Token V
Feature activation+0.000
SS
TokenSS
Feature activation+0.167
Enterprise
Token Enterprise
Feature activation+0.352
and
Token and
Feature activation+10.347
V
Token V
Feature activation+0.000
MS
TokenMS
Feature activation+2.254
Eve
Token Eve
Feature activation+0.000
test
Token test
Feature activation+0.000
flights
Token flights
Feature activation+0.651
Eve
Token Eve
Feature activation+0.000
test
Token test
Feature activation+0.000
flights
Token flights
Feature activation+0.651
are
Token are
Feature activation+0.000
completed
Token completed
Feature activation+0.317
,
Token,
Feature activation+8.903
Virgin
Token Virgin
Feature activation+0.000
Galactic
Token Galactic
Feature activation+0.693
will
Token will
Feature activation+0.000
begin
Token begin
Feature activation+0.000
commercial
Token commercial
Feature activation+0.000
State
Token State
Feature activation+0.000
Athletic
Token Athletic
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.000
allow
Token allow
Feature activation+8.460
the
Token the
Feature activation+1.677
straw
Token straw
Feature activation+0.000
weight
Tokenweight
Feature activation+0.000
champion
Token champion
Feature activation+0.195
to
Token to
Feature activation+0.000
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.863
myriad
Token myriad
Feature activation+0.000
re
Tokenre
Feature activation+0.000
asons
Tokenasons
Feature activation+4.544
why
Token why
Feature activation+8.192
the
Token the
Feature activation+1.108
Nevada
Token Nevada
Feature activation+0.000
State
Token State
Feature activation+0.000
Athletic
Token Athletic
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
legislative
Token legislative
Feature activation+0.000
typo
Token typo
Feature activation+0.000
in
Token in
Feature activation+0.220
American
Token American
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+7.975
we
Token we
Feature activation+0.000
dug
Token dug
Feature activation+0.000
into
Token into
Feature activation+6.839
the
Token the
Feature activation+0.343
matter
Token matter
Feature activation+0.000
-
Token-
Feature activation+0.000
car
Tokencar
Feature activation+0.000
-
Token-
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
ipping
Tokenipping
Feature activation+0.420
to
Token to
Feature activation+7.681
White
Token White
Feature activation+0.103
horse
Tokenhorse
Feature activation+0.028
Motors
Token Motors
Feature activation+0.400
was
Token was
Feature activation+0.000
by
Token by
Feature activation+2.087
UFC
Token UFC
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
175
Token 175
Feature activation+0.000
.
Token.
Feature activation+7.511
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.100
On
TokenOn
Feature activation+0.540
paper
Token paper
Feature activation+0.034
,
Token,
Feature activation+3.539
government
Token government
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
share
Token share
Feature activation+7.315
the
Token the
Feature activation+0.014
magazine
Token magazine
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
RB
Token RB
Feature activation+0.000
,
Token,
Feature activation+0.000
North
Token North
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+7.309
Whatever
Token Whatever
Feature activation+1.829
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
a
Token a
Feature activation+0.000
running
Token running
Feature activation+0.000
routine
Token routine
Feature activation+0.000
.
Token.
Feature activation+5.799
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.194
Unfortunately
TokenUnfortunately
Feature activation+3.402
,
Token,
Feature activation+7.221
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
government
Token government
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
operating
Token operating
Feature activation+0.000
at
Token at
Feature activation+0.000
its
Token its
Feature activation+0.000
slick
Token slick
Feature activation+0.000
est
Tokenest
Feature activation+0.000
.
Token.
Feature activation+7.203
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.863
myriad
Token myriad
Feature activation+0.000
re
Tokenre
Feature activation+0.000
asons
Tokenasons
Feature activation+4.544
An
Token An
Feature activation+0.000
avid
Token avid
Feature activation+0.000
gram
Token gram
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arian
Tokenarian
Feature activation+0.000
,
Token,
Feature activation+7.115
the
Token the
Feature activation+0.064
Charlotte
Token Charlotte
Feature activation+0.059
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.020
s
Tokens
Feature activation+0.000
at
Token at
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
175
Token 175
Feature activation+0.000
.
Token.
Feature activation+7.511
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.100
On
TokenOn
Feature activation+0.540
paper
Token paper
Feature activation+0.034
,
Token,
Feature activation+3.539
it
Token it
Feature activation+0.000
Rouse
Token Rouse
Feature activation+0.000
forefront
Token forefront
Feature activation+0.000
of
Token of
Feature activation+3.296
the
Token the
Feature activation+2.069
efforts
Token efforts
Feature activation+0.000
to
Token to
Feature activation+0.000
debunk
Token debunk
Feature activation+7.073
factual
Token factual
Feature activation+0.705
anti
Token anti
Feature activation+0.627
-
Token-
Feature activation+5.850
commun
Tokencommun
Feature activation+0.000
ist
Tokenist
Feature activation+0.076
,
Token,
Feature activation+0.000
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+6.984
assuming
Token assuming
Feature activation+0.635
she
Token she
Feature activation+0.000
gets
Token gets
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+7.975
we
Token we
Feature activation+0.000
dug
Token dug
Feature activation+0.000
into
Token into
Feature activation+6.839
the
Token the
Feature activation+0.343
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+1.264
If
Token If
Feature activation+3.346
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
back
Token back
Feature activation+0.000
with
Token with
Feature activation+0.000
speed
Token speed
Feature activation+0.000
,
Token,
Feature activation+6.817
White
Token White
Feature activation+0.000
has
Token has
Feature activation+0.000
20
Token 20
Feature activation+0.000
offers
Token offers
Feature activation+0.000
but
Token but
Feature activation+0.000
one
Tokenone
Feature activation+0.000
noticing
Token noticing
Feature activation+0.000
.
Token.
Feature activation+3.628
By
Token By
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+6.748
the
Token the
Feature activation+0.658
Evening
Token Evening
Feature activation+0.000
Standard
Token Standard
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+6.607
When
Token When
Feature activation+5.496
they
Token they
Feature activation+0.000
went
Token went
Feature activation+0.000
inside
Token inside
Feature activation+1.714
,
Token,
Feature activation+6.735
deputies
Token deputies
Feature activation+0.000
met
Token met
Feature activation+4.735
Par
Token Par
Feature activation+0.000
rot
Tokenrot
Feature activation+0.000
te
Tokente
Feature activation+0.000
a
Token a
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+6.679
this
Token this
Feature activation+0.000
kid
Token kid
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
it
Token it
Feature activation+0.000

Top DFA by src position
MAX = 10.865

SS
TokenSS
Feature activation-0.000
Top resid features:
Enterprise
Token Enterprise
Feature activation-0.019
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
carrier
Token carrier
Feature activation-0.223
Top resid features:
White
Token White
Feature activation+10.865
Top resid features:
Knight
TokenKnight
Feature activation-0.005
Top resid features:
Two
TokenTwo
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
christ
Token christ
Feature activation-0.002
Top resid features:
ened
Tokenened
Feature activation+0.000
Top resid features:
SS
TokenSS
Feature activation+0.000
Top resid features:
Enterprise
Token Enterprise
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
carrier
Token carrier
Feature activation-0.064
Top resid features:
White
Token White
Feature activation+9.373
Top resid features:
Knight
TokenKnight
Feature activation+0.001
Top resid features:
Two
TokenTwo
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
christ
Token christ
Feature activation-0.002
Top resid features:
ened
Tokenened
Feature activation-0.000
Top resid features:
antasy
Tokenantasy
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
The
TokenThe
Feature activation+0.018
Top resid features:
tweets
Token tweets
Feature activation+0.011
Top resid features:
by
Token by
Feature activation-0.002
Top resid features:
White
Token White
Feature activation+8.994
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
Jed
Token Jed
Feature activation+0.059
Top resid features:
r
Tokenr
Feature activation+0.009
Top resid features:
ze
Tokenze
Feature activation-0.014
Top resid features:
jc
Tokenjc
Feature activation+0.016
Top resid features:
antasy
Tokenantasy
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
The
TokenThe
Feature activation+0.021
Top resid features:
tweets
Token tweets
Feature activation+0.010
Top resid features:
by
Token by
Feature activation-0.002
Top resid features:
White
Token White
Feature activation+8.958
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
Jed
Token Jed
Feature activation-0.075
Top resid features:
r
Tokenr
Feature activation-0.009
Top resid features:
ze
Tokenze
Feature activation-0.008
Top resid features:
jc
Tokenjc
Feature activation+0.018
Top resid features:
writer
Token writer
Feature activation+0.003
Top resid features:
E
Token E
Feature activation-0.101
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
B
TokenB
Feature activation-0.060
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
White
Token White
Feature activation+8.542
Top resid features:
paused
Token paused
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
smiled
Token smiled
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
leave
Token leave
Feature activation-0.016
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
car
Token car
Feature activation-0.006
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
White
Token White
Feature activation+5.737
Top resid features:
horse
Tokenhorse
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
sale
Token sale
Feature activation-0.019
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
White
Token White
Feature activation+2.716
Top resid features:
deal
Token deal
Feature activation-0.004
Top resid features:
done
Token done
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.151
Top resid features:
Ŀ
TokenĿ
Feature activation-0.032
Top resid features:
White
Token White
Feature activation+8.649
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
UFC
TokenUFC
Feature activation+0.008
Top resid features:
writer
Token writer
Feature activation+0.003
Top resid features:
E
Token E
Feature activation-0.105
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
B
TokenB
Feature activation-0.023
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
White
Token White
Feature activation+7.945
Top resid features:
paused
Token paused
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
smiled
Token smiled
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
3
Token3
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Zam
Token Zam
Feature activation+0.565
Top resid features:
ir
Tokenir
Feature activation-0.060
Top resid features:
White
Token White
Feature activation+7.551
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
RB
Token RB
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
North
Token North
Feature activation-0.072
Top resid features:
Carolina
Token Carolina
Feature activation+0.045
Top resid features:
writer
Token writer
Feature activation+0.006
Top resid features:
E
Token E
Feature activation-0.075
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
B
TokenB
Feature activation-0.040
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
White
Token White
Feature activation+7.827
Top resid features:
paused
Token paused
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
smiled
Token smiled
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
antasy
Tokenantasy
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
The
TokenThe
Feature activation+0.012
Top resid features:
tweets
Token tweets
Feature activation+0.001
Top resid features:
by
Token by
Feature activation-0.006
Top resid features:
White
Token White
Feature activation+8.042
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
Jed
Token Jed
Feature activation-0.222
Top resid features:
r
Tokenr
Feature activation-0.008
Top resid features:
ze
Tokenze
Feature activation-0.006
Top resid features:
jc
Tokenjc
Feature activation-0.005
Top resid features:
writer
Token writer
Feature activation-0.002
Top resid features:
E
Token E
Feature activation-0.067
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
B
TokenB
Feature activation-0.051
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
White
Token White
Feature activation+7.882
Top resid features:
paused
Token paused
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
smiled
Token smiled
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
deal
Token deal
Feature activation-0.002
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ŀ
TokenĿ
Feature activation-0.011
Top resid features:
White
Token White
Feature activation+8.160
Top resid features:
said
Token said
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
UFC
TokenUFC
Feature activation+0.056
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.108
Top resid features:
most
Token most
Feature activation+0.003
Top resid features:
recent
Token recent
Feature activation-0.002
Top resid features:
admissions
Token admissions
Feature activation+0.019
Top resid features:
concerning
Token concerning
Feature activation-0.006
Top resid features:
White
Token White
Feature activation+7.571
Top resid features:
âĢ
TokenâĢ
Feature activation+0.043
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
crucial
Token crucial
Feature activation-0.114
Top resid features:
role
Token role
Feature activation+0.003
Top resid features:
deal
Token deal
Feature activation-0.001
Top resid features:
done
Token done
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ŀ
TokenĿ
Feature activation-0.070
Top resid features:
White
Token White
Feature activation+7.948
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
UFC
TokenUFC
Feature activation+0.028
Top resid features:
writer
Token writer
Feature activation-0.002
Top resid features:
E
Token E
Feature activation-0.075
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
B
TokenB
Feature activation-0.022
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
White
Token White
Feature activation+7.351
Top resid features:
paused
Token paused
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
smiled
Token smiled
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
3
Token3
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Zam
Token Zam
Feature activation+0.377
Top resid features:
ir
Tokenir
Feature activation-0.042
Top resid features:
White
Token White
Feature activation+7.519
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
RB
Token RB
Feature activation-0.021
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
North
Token North
Feature activation-0.001
Top resid features:
Carolina
Token Carolina
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
As
TokenAs
Feature activation-0.003
Top resid features:
both
Token both
Feature activation-0.016
Top resid features:
White
Token White
Feature activation+7.254
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
Marriott
Token Marriott
Feature activation-0.058
Top resid features:
explain
Token explain
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
Office
Token Office
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
White
TokenWhite
Feature activation+7.477
Top resid features:
met
Token met
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
three
Token three
Feature activation+0.024
Top resid features:
deputies
Token deputies
Feature activation+0.047
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
3
Token3
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Zam
Token Zam
Feature activation+0.728
Top resid features:
ir
Tokenir
Feature activation-0.104
Top resid features:
White
Token White
Feature activation+6.969
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
RB
Token RB
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
North
Token North
Feature activation-0.089
Top resid features:
Carolina
Token Carolina
Feature activation+0.038
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.48

Head 2: 0.05

Head 3: 0.07

Head 4: 0.03

Head 5: 0.02

Head 6: 0.05

Head 7: 0.08

Head 8: 0.03

Head 9: 0.04

Head 10: 0.08

Head 11: 0.04

Positive logits

White8.92

White8.38

white8.33

WHITE8.20

white8.03

Whites6.49

whites6.03

black5.61

whit5.58

black5.47

Black5.07

Black5.02

colored4.50

Whit4.42

BLACK4.41

brown4.38

Yellow4.34

yellow4.33

gray4.18

blacks4.16

Negative logits

imentary-2.83

lik-2.68

ombo-2.53

imental-2.45

Lim-2.34

Reviewed-2.34

Lib-2.28

atron-2.25

cair-2.25

cientious-2.23

Libre-2.21

verse-2.19

iments-2.13

Var-2.13

Cyprus-2.13

osal-2.12

Hyper-2.11

Samar-2.11

Lim-2.10

osure-2.07

INTERVAL 9.312 - 10.347
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+3.926
After
TokenAfter
Feature activation+1.788
V
Token V
Feature activation+0.000
SS
TokenSS
Feature activation+0.167
Enterprise
Token Enterprise
Feature activation+0.352
and
Token and
Feature activation+10.347
V
Token V
Feature activation+0.000
MS
TokenMS
Feature activation+2.254
Eve
Token Eve
Feature activation+0.000
test
Token test
Feature activation+0.000
flights
Token flights
Feature activation+0.651

INTERVAL 8.277 - 9.312
CONTAINS 0.000%

Eve
Token Eve
Feature activation+0.000
test
Token test
Feature activation+0.000
flights
Token flights
Feature activation+0.651
are
Token are
Feature activation+0.000
completed
Token completed
Feature activation+0.317
,
Token,
Feature activation+8.903
Virgin
Token Virgin
Feature activation+0.000
Galactic
Token Galactic
Feature activation+0.693
will
Token will
Feature activation+0.000
begin
Token begin
Feature activation+0.000
commercial
Token commercial
Feature activation+0.000
State
Token State
Feature activation+0.000
Athletic
Token Athletic
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.000
allow
Token allow
Feature activation+8.460
the
Token the
Feature activation+1.677
straw
Token straw
Feature activation+0.000
weight
Tokenweight
Feature activation+0.000
champion
Token champion
Feature activation+0.195
to
Token to
Feature activation+0.000

INTERVAL 7.243 - 8.277
CONTAINS 0.001%

government
Token government
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
share
Token share
Feature activation+7.315
the
Token the
Feature activation+0.014
magazine
Token magazine
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.863
myriad
Token myriad
Feature activation+0.000
re
Tokenre
Feature activation+0.000
asons
Tokenasons
Feature activation+4.544
why
Token why
Feature activation+8.192
the
Token the
Feature activation+1.108
Nevada
Token Nevada
Feature activation+0.000
State
Token State
Feature activation+0.000
Athletic
Token Athletic
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
legislative
Token legislative
Feature activation+0.000
typo
Token typo
Feature activation+0.000
in
Token in
Feature activation+0.220
American
Token American
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+7.975
we
Token we
Feature activation+0.000
dug
Token dug
Feature activation+0.000
into
Token into
Feature activation+6.839
the
Token the
Feature activation+0.343
matter
Token matter
Feature activation+0.000
,
Token,
Feature activation+0.000
RB
Token RB
Feature activation+0.000
,
Token,
Feature activation+0.000
North
Token North
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+7.309
Whatever
Token Whatever
Feature activation+1.829
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
a
Token a
Feature activation+0.000
running
Token running
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
175
Token 175
Feature activation+0.000
.
Token.
Feature activation+7.511
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.100
On
TokenOn
Feature activation+0.540
paper
Token paper
Feature activation+0.034
,
Token,
Feature activation+3.539

INTERVAL 6.208 - 7.243
CONTAINS 0.002%

American
Token American
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+7.975
we
Token we
Feature activation+0.000
dug
Token dug
Feature activation+0.000
into
Token into
Feature activation+6.839
the
Token the
Feature activation+0.343
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+1.264
If
Token If
Feature activation+3.346
you
Token you
Feature activation+0.000
husband
Token husband
Feature activation+0.000
elected
Token elected
Feature activation+0.088
?
Token?
Feature activation+1.853
What
Token What
Feature activation+1.647
of
Token of
Feature activation+3.926
those
Token those
Feature activation+6.398
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.241
white
Tokenwhite
Feature activation+0.736
men
Token men
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
operating
Token operating
Feature activation+0.000
at
Token at
Feature activation+0.000
its
Token its
Feature activation+0.000
slick
Token slick
Feature activation+0.000
est
Tokenest
Feature activation+0.000
.
Token.
Feature activation+7.203
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.863
myriad
Token myriad
Feature activation+0.000
re
Tokenre
Feature activation+0.000
asons
Tokenasons
Feature activation+4.544
say
Token say
Feature activation+0.000
no
Token no
Feature activation+0.000
,
Token,
Feature activation+0.134
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.312
said
Token said
Feature activation+6.298
Ph
Token Ph
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
uf
Tokenuf
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
,
Token,
Feature activation+0.000
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+6.984
assuming
Token assuming
Feature activation+0.635
she
Token she
Feature activation+0.000
gets
Token gets
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 5.173 - 6.208
CONTAINS 0.002%

author
Token author
Feature activation+0.000
thoroughly
Token thoroughly
Feature activation+0.000
enjoyed
Token enjoyed
Feature activation+6.401
this
Token this
Feature activation+0.000
routine
Token routine
Feature activation+0.000
.
Token.
Feature activation+5.799
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.194
Unfortunately
TokenUnfortunately
Feature activation+3.402
,
Token,
Feature activation+7.221
the
Token the
Feature activation+0.000
white
Token white
Feature activation+0.274
comedian
Token comedian
Feature activation+0.000
was
Token was
Feature activation+0.082
saying
Token saying
Feature activation+1.564
he
Token he
Feature activation+0.000
hates
Token hates
Feature activation+5.260
black
Token black
Feature activation+0.173
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+1.414
them
Token them
Feature activation+0.000
outlining
Token outlining
Feature activation+0.000
the
Token the
Feature activation+0.000
victim
Token victim
Feature activation+0.000
.
Token.
Feature activation+5.684
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+5.743
An
Token An
Feature activation+0.000
avid
Token avid
Feature activation+0.000
gram
Token gram
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arian
Tokenarian
Feature activation+0.000
North
Token North
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
moment
Token moment
Feature activation+0.000
.
Token.
Feature activation+5.258
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.240
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
Xavier
Token Xavier
Feature activation+0.000
based
Tokenbased
Feature activation+1.574
Sc
Token Sc
Feature activation+0.000
aled
Tokenaled
Feature activation+0.000
Compos
Token Compos
Feature activation+0.000
ites
Tokenites
Feature activation+0.000
.
Token.
Feature activation+5.227
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.988
This
TokenThis
Feature activation+0.000
launch
Token launch
Feature activation+0.000
system
Token system
Feature activation+0.000

INTERVAL 4.139 - 5.173
CONTAINS 0.003%

down
Token down
Feature activation+0.000
gave
Token gave
Feature activation+3.410
us
Token us
Feature activation+0.000
a
Token a
Feature activation+0.000
glimpse
Token glimpse
Feature activation+0.000
of
Token of
Feature activation+4.694
the
Token the
Feature activation+0.005
promotional
Token promotional
Feature activation+0.000
game
Token game
Feature activation+0.000
operating
Token operating
Feature activation+0.000
at
Token at
Feature activation+0.000
.
Token.
Feature activation+2.794
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.177
One
TokenOne
Feature activation+2.529
would
Token would
Feature activation+0.000
think
Token think
Feature activation+4.309
her
Token her
Feature activation+1.880
fear
Token fear
Feature activation+0.000
of
Token of
Feature activation+3.624
white
Token white
Feature activation+0.855
men
Token men
Feature activation+0.000
zeal
Token zeal
Feature activation+0.000
for
Token for
Feature activation+0.000
punct
Token punct
Feature activation+0.000
uation
Tokenuation
Feature activation+0.000
--
Token --
Feature activation+0.820
and
Token and
Feature activation+4.532
sometimes
Token sometimes
Feature activation+0.000
,
Token,
Feature activation+2.399
it
Token it
Feature activation+0.000
costs
Token costs
Feature activation+0.641
taxpayers
Token taxpayers
Feature activation+0.000
and
Token and
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
pine
Token pine
Feature activation+0.000
beetle
Token beetle
Feature activation+0.000
outbreaks
Token outbreaks
Feature activation+0.000
.
Token.
Feature activation+4.956
Nut
Token Nut
Feature activation+0.000
cr
Tokencr
Feature activation+0.000
acker
Tokenacker
Feature activation+0.000
populations
Token populations
Feature activation+0.000
have
Token have
Feature activation+0.000
aled
Tokenaled
Feature activation+0.000
Compos
Token Compos
Feature activation+0.000
ites
Tokenites
Feature activation+0.000
.
Token.
Feature activation+5.227
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.988
This
TokenThis
Feature activation+0.000
launch
Token launch
Feature activation+0.000
system
Token system
Feature activation+0.000
is
Token is
Feature activation+0.000
designed
Token designed
Feature activation+0.000

INTERVAL 3.104 - 4.139
CONTAINS 0.008%

players
Token players
Feature activation+0.000
can
Token can
Feature activation+0.000
wear
Token wear
Feature activation+0.000
to
Token to
Feature activation+0.304
look
Token look
Feature activation+1.550
like
Token like
Feature activation+3.310
their
Token their
Feature activation+2.467
Mi
Token Mi
Feature activation+0.000
is
Tokenis
Feature activation+0.000
.
Token.
Feature activation+0.667
Mi
Token Mi
Feature activation+0.000
owe
Token owe
Feature activation+0.244
it
Token it
Feature activation+0.000
quite
Token quite
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
to
Token to
Feature activation+3.173
themselves
Token themselves
Feature activation+0.000
as
Token as
Feature activation+4.065
to
Token to
Feature activation+2.751
the
Token the
Feature activation+1.207
colored
Token colored
Feature activation+0.193
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
tweets
Token tweets
Feature activation+0.000
by
Token by
Feature activation+0.000
White
Token White
Feature activation+0.000
and
Token and
Feature activation+3.320
Jed
Token Jed
Feature activation+0.883
r
Tokenr
Feature activation+0.000
ze
Tokenze
Feature activation+0.000
jc
Tokenjc
Feature activation+0.000
zyk
Tokenzyk
Feature activation+0.000
room
Token room
Feature activation+1.142
what
Token what
Feature activation+0.623
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
see
Token see
Feature activation+0.027
is
Token is
Feature activation+4.037
this
Token this
Feature activation+2.048
real
Token real
Feature activation+2.301
dich
Token dich
Feature activation+0.000
otomy
Tokenotomy
Feature activation+0.000
.
Token.
Feature activation+3.154
black
Token black
Feature activation+0.000
firefighter
Token firefighter
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
fourth
Token fourth
Feature activation+3.306
firefighter
Token firefighter
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.472
a
Token a
Feature activation+0.000
Cuban
Token Cuban
Feature activation+0.000

INTERVAL 2.069 - 3.104
CONTAINS 0.014%

as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
to
Token to
Feature activation+3.173
themselves
Token themselves
Feature activation+0.000
as
Token as
Feature activation+4.065
to
Token to
Feature activation+2.751
the
Token the
Feature activation+1.207
colored
Token colored
Feature activation+0.193
race
Token race
Feature activation+0.000
to
Token to
Feature activation+0.000
treat
Token treat
Feature activation+2.652
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
made
Token made
Feature activation+0.267
the
Token the
Feature activation+0.000
hit
Token hit
Feature activation+0.000
and
Token and
Feature activation+2.305
(
Token (
Feature activation+6.115
White
TokenWhite
Feature activation+0.000
)
Token)
Feature activation+0.000
came
Token came
Feature activation+0.000
over
Token over
Feature activation+0.000
our
Token our
Feature activation+0.000
religious
Token religious
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
oath
Token oath
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+2.200
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
one
Token one
Feature activation+0.000
since
Token since
Feature activation+2.196
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
II
Token II
Feature activation+2.830
,
Token,
Feature activation+4.013
the
Token the
Feature activation+2.206
CFR
Token CFR
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.035
very
Token very
Feature activation+0.000
s
Tokens
Feature activation+0.000
fur
Token fur
Feature activation+0.000
as
Token as
Feature activation+0.346
she
Token she
Feature activation+0.000
ages
Token ages
Feature activation+0.000
:
Token:
Feature activation+3.039
Cats
Token Cats
Feature activation+0.000
do
Token do
Feature activation+0.000
start
Token start
Feature activation+0.256
going
Token going
Feature activation+1.178
gray
Token gray
Feature activation+0.000

INTERVAL 1.035 - 2.069
CONTAINS 0.034%

have
Token have
Feature activation+0.000
demanded
Token demanded
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+1.137
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.436
Nonetheless
TokenNonetheless
Feature activation+1.509
,
Token,
Feature activation+1.643
many
Token many
Feature activation+4.106
white
Token white
Feature activation+0.616
feminists
Token feminists
Feature activation+0.000
AP
Token AP
Feature activation+0.000
A
TokenA
Feature activation+0.000
,
Token,
Feature activation+0.270
all
Token all
Feature activation+0.000
rights
Token rights
Feature activation+0.000
reserved
Token reserved
Feature activation+1.214
).
Token).
Feature activation+0.843
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Looking
TokenLooking
Feature activation+0.000
for
Token for
Feature activation+0.000
news
Token news
Feature activation+0.000
is
Token is
Feature activation+0.000
John
Token John
Feature activation+0.000
Kasich
Token Kasich
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.298
only
Token only
Feature activation+1.163
other
Token other
Feature activation+1.209
candidate
Token candidate
Feature activation+0.000
still
Token still
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Tell
TokenTell
Feature activation+0.000
us
Token us
Feature activation+0.000
:
Token:
Feature activation+0.413
Do
Token Do
Feature activation+3.012
you
Token you
Feature activation+0.288
know
Token know
Feature activation+1.049
any
Token any
Feature activation+2.701
other
Token other
Feature activation+2.207
facts
Token facts
Feature activation+0.000
about
Token about
Feature activation+2.121
cat
Token cat
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
since
Tokensince
Feature activation+0.000
debunked
Token debunked
Feature activation+0.463
story
Token story
Feature activation+0.000
that
Token that
Feature activation+1.375
the
Token the
Feature activation+2.048
outgoing
Token outgoing
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
istas
Tokenistas
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 1.035
CONTAINS 99.936%

illas
Tokenillas
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Fat
Token Fat
Feature activation+0.000
aki
Tokenaki
Feature activation+0.000
,
Token,
Feature activation+0.000
F
Token F
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
u
Tokenu
Feature activation+0.000
and
Token and
Feature activation+0.000
Mah
Token Mah
Feature activation+0.000
ali
Tokenali
Feature activation+0.000
documentary
Token documentary
Feature activation+0.000
'
Token '
Feature activation+0.000
Black
TokenBlack
Feature activation+0.000
Sabbath
Token Sabbath
Feature activation+0.000
-
Token -
Feature activation+0.000
The
Token The
Feature activation+0.000
Re
Token Re
Feature activation+0.000
-
Token-
Feature activation+0.000
union
Tokenunion
Feature activation+0.000
,'
Token,'
Feature activation+0.000
plus
Token plus
Feature activation+0.000
s
Tokens
Feature activation+0.000
American
Token American
Feature activation+0.000
Kitchen
Token Kitchen
Feature activation+0.000
or
Token or
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
T
TokenT
Feature activation+0.000
us
Tokenus
Feature activation+0.000
can
Tokencan
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Oil
TokenOil
Feature activation+0.000
futures
Token futures
Feature activation+0.000
finished
Token finished
Feature activation+0.000
modest
Token modest
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
lower
Token lower
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
after
Token after
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
yet
Token yet
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
having
Token having
Feature activation+0.000
someone
Token someone
Feature activation+0.000
that
Token that
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 H10.1: (feature 380)

TOP ACTIVATIONS
MAX = 8.116

keep
Token keep
Feature activation+1.426
saying
Token saying
Feature activation+0.165
us
Token us
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
guys
Token guys
Feature activation+1.184
have
Token have
Feature activation+8.116
small
Token small
Feature activation+0.000
penis
Token penis
Feature activation+0.346
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
our
Token our
Feature activation+0.150
ful
Tokenful
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.531
needs
Token needs
Feature activation+0.000
of
Token of
Feature activation+5.496
the
Token the
Feature activation+5.448
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
,
Token,
Feature activation+0.000
quality
Token quality
Feature activation+7.291
Ċ
TokenĊ
Feature activation+7.075
As
TokenAs
Feature activation+3.143
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.433
,
Token,
Feature activation+7.707
Tim
Token Tim
Feature activation+0.000
and
Token and
Feature activation+4.486
I
Token I
Feature activation+0.000
are
Token are
Feature activation+0.000
prone
Token prone
Feature activation+0.000
supporting
Token supporting
Feature activation+5.344
and
Token and
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
spons
Tokenspons
Feature activation+0.000
oring
Tokenoring
Feature activation+7.292
this
Token this
Feature activation+0.674
important
Token important
Feature activation+0.735
legislation
Token legislation
Feature activation+0.000
.
Token.
Feature activation+1.817
âĢ
TokenâĢ
Feature activation+0.000
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
,
Token,
Feature activation+0.000
quality
Token quality
Feature activation+7.291
small
Token small
Feature activation+0.049
arms
Token arms
Feature activation+0.000
in
Token in
Feature activation+0.249
the
Token the
Feature activation+0.284
wake
Token wake
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
in
Token in
Feature activation+0.000
length
Token length
Feature activation+0.000
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
).
Token).
Feature activation+7.075
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.075
As
TokenAs
Feature activation+3.143
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
length
Token length
Feature activation+0.000
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
).
Token).
Feature activation+7.075
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.075
As
TokenAs
Feature activation+3.143
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.433
,
Token,
Feature activation+7.707
maintaining
Token maintaining
Feature activation+0.820
the
Token the
Feature activation+0.942
status
Token status
Feature activation+0.000
quo
Token quo
Feature activation+0.095
.
Token.
Feature activation+5.480
But
Token But
Feature activation+7.008
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
not
Token not
Feature activation+0.487
world
Token world
Feature activation+0.000
who
Token who
Feature activation+0.000
keep
Token keep
Feature activation+0.000
boasting
Token boasting
Feature activation+1.243
about
Token about
Feature activation+5.120
their
Token their
Feature activation+6.941
penis
Token penis
Feature activation+2.392
size
Token size
Feature activation+0.604
while
Token while
Feature activation+0.000
saying
Token saying
Feature activation+0.105
other
Token other
Feature activation+0.000
Now
Token Now
Feature activation+0.441
,
Token,
Feature activation+0.625
however
Token however
Feature activation+0.000
,
Token,
Feature activation+1.033
the
Token the
Feature activation+2.229
Indian
Token Indian
Feature activation+6.759
engineering
Token engineering
Feature activation+0.261
group
Token group
Feature activation+0.000
Pun
Token Pun
Feature activation+0.000
ji
Tokenji
Feature activation+0.000
Lloyd
Token Lloyd
Feature activation+0.000
s
Tokens
Feature activation+0.000
limbs
Token limbs
Feature activation+0.000
.
Token.
Feature activation+0.000
Per
Token Per
Feature activation+0.000
ipher
Tokenipher
Feature activation+0.000
al
Tokenal
Feature activation+6.195
circulation
Token circulation
Feature activation+0.000
is
Token is
Feature activation+0.000
great
Token great
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
this
Tokenthis
Feature activation+0.060
bacteria
Token bacteria
Feature activation+0.000
is
Token is
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+6.147
large
Token large
Feature activation+0.246
quantities
Token quantities
Feature activation+0.000
in
Token in
Feature activation+0.000
yogurt
Token yogurt
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.808
s
Tokens
Feature activation+3.186
first
Token first
Feature activation+1.729
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+5.752
affiliate
Token affiliate
Feature activation+1.105
academy
Token academy
Feature activation+0.000
(
Token (
Feature activation+0.147
which
Tokenwhich
Feature activation+0.002
Tim
Token Tim
Feature activation+0.000
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.531
needs
Token needs
Feature activation+0.000
of
Token of
Feature activation+5.496
the
Token the
Feature activation+5.448
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
is
Token is
Feature activation+1.203
maintaining
Token maintaining
Feature activation+0.820
the
Token the
Feature activation+0.942
status
Token status
Feature activation+0.000
quo
Token quo
Feature activation+0.095
.
Token.
Feature activation+5.480
But
Token But
Feature activation+7.008
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
un
Tokenun
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.531
needs
Token needs
Feature activation+0.000
of
Token of
Feature activation+5.496
the
Token the
Feature activation+5.448
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
,
Token,
Feature activation+0.000
of
Token of
Feature activation+5.496
the
Token the
Feature activation+5.448
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
,
Token,
Feature activation+0.000
quality
Token quality
Feature activation+7.291
small
Token small
Feature activation+0.049
arms
Token arms
Feature activation+0.000
in
Token in
Feature activation+0.249
for
Token for
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
government
Token government
Feature activation+0.009
.
Token.
Feature activation+2.798
We
Token We
Feature activation+0.000
believe
Token believe
Feature activation+5.421
public
Token public
Feature activation+0.064
sector
Token sector
Feature activation+0.546
bureaucrats
Token bureaucrats
Feature activation+0.000
are
Token are
Feature activation+0.000
w
Token w
Feature activation+0.000
processes
Token processes
Feature activation+0.564
,
Token,
Feature activation+1.789
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
think
Token think
Feature activation+1.100
of
Token of
Feature activation+5.413
this
Token this
Feature activation+0.745
as
Token as
Feature activation+3.947
a
Token a
Feature activation+2.824
truly
Token truly
Feature activation+1.586
incremental
Token incremental
Feature activation+0.929
Congress
Token Congress
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
hesitation
Token hesitation
Feature activation+0.000
supporting
Token supporting
Feature activation+5.344
and
Token and
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
spons
Tokenspons
Feature activation+0.000
oring
Tokenoring
Feature activation+7.292

Top DFA by src position
MAX = 8.718

saying
Token saying
Feature activation-0.003
Top resid features:
us
Token us
Feature activation-0.003
Top resid features:
Asian
Token Asian
Feature activation-0.024
Top resid features:
guys
Token guys
Feature activation-0.001
Top resid features:
have
Token have
Feature activation-0.012
Top resid features:
small
Token small
Feature activation+8.718
Top resid features:
penis
Token penis
Feature activation+0.020
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
because
Token because
Feature activation-0.016
Top resid features:
:
Token :
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.170
Top resid features:
Previously
Token Previously
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Indian
Token Indian
Feature activation+0.006
Top resid features:
small
Token small
Feature activation+5.812
Top resid features:
arms
Token arms
Feature activation+0.136
Top resid features:
industry
Token industry
Feature activation+0.027
Top resid features:
has
Token has
Feature activation+0.004
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
entirely
Token entirely
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Tim
TokenTim
Feature activation-0.011
Top resid features:
owns
Token owns
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
operates
Token operates
Feature activation+0.009
Top resid features:
Small
Token Small
Feature activation+8.549
Top resid features:
Axe
Token Axe
Feature activation+0.003
Top resid features:
Jiu
Token Jiu
Feature activation+0.004
Top resid features:
J
Token J
Feature activation-0.001
Top resid features:
itsu
Tokenitsu
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
Pass
TokenPass
Feature activation+0.014
Top resid features:
age
Tokenage
Feature activation-0.039
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
Small
Token Small
Feature activation+7.260
Top resid features:
Business
Token Business
Feature activation+0.107
Top resid features:
Tax
Token Tax
Feature activation+0.034
Top resid features:
Equity
Token Equity
Feature activation+0.063
Top resid features:
Act
Token Act
Feature activation-0.006
Top resid features:
will
Token will
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
very
Token very
Feature activation+0.001
Top resid features:
first
Token first
Feature activation+0.002
Top resid features:
private
Token private
Feature activation+0.008
Top resid features:
sector
Token sector
Feature activation+0.001
Top resid features:
small
Token small
Feature activation+5.038
Top resid features:
arms
Token arms
Feature activation+0.089
Top resid features:
factory
Token factory
Feature activation+0.014
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
nation
Token nation
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Tim
TokenTim
Feature activation-0.030
Top resid features:
owns
Token owns
Feature activation+0.011
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
operates
Token operates
Feature activation+0.014
Top resid features:
Small
Token Small
Feature activation+7.849
Top resid features:
Axe
Token Axe
Feature activation+0.002
Top resid features:
Jiu
Token Jiu
Feature activation+0.008
Top resid features:
J
Token J
Feature activation-0.000
Top resid features:
itsu
Tokenitsu
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Tim
TokenTim
Feature activation-0.048
Top resid features:
owns
Token owns
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
operates
Token operates
Feature activation+0.009
Top resid features:
Small
Token Small
Feature activation+7.856
Top resid features:
Axe
Token Axe
Feature activation-0.003
Top resid features:
Jiu
Token Jiu
Feature activation+0.026
Top resid features:
J
Token J
Feature activation-0.001
Top resid features:
itsu
Tokenitsu
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
s
Tokens
Feature activation+0.025
Top resid features:
campaign
Token campaign
Feature activation+0.000
Top resid features:
relied
Token relied
Feature activation-0.001
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
small
Token small
Feature activation+4.212
Top resid features:
organizing
Token organizing
Feature activation+0.046
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
which
Token which
Feature activation-0.001
Top resid features:
Bond
Token Bond
Feature activation+0.253
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
saying
Token saying
Feature activation-0.002
Top resid features:
us
Token us
Feature activation-0.007
Top resid features:
Asian
Token Asian
Feature activation-0.008
Top resid features:
guys
Token guys
Feature activation+0.003
Top resid features:
have
Token have
Feature activation+0.013
Top resid features:
small
Token small
Feature activation+5.342
Top resid features:
penis
Token penis
Feature activation+0.022
Top resid features:
will
Token will
Feature activation-0.000
Top resid features:
make
Token make
Feature activation-0.001
Top resid features:
our
Token our
Feature activation+0.006
Top resid features:
Asian
Token Asian
Feature activation-0.024
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.159
Top resid features:
Previously
Token Previously
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
Indian
Token Indian
Feature activation+0.010
Top resid features:
small
Token small
Feature activation+6.886
Top resid features:
arms
Token arms
Feature activation+0.218
Top resid features:
industry
Token industry
Feature activation+0.088
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
entirely
Token entirely
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
associated
Tokenassociated
Feature activation-0.000
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
poorer
Token poorer
Feature activation-0.023
Top resid features:
peripheral
Token peripheral
Feature activation-0.084
Top resid features:
small
Token small
Feature activation+6.611
Top resid features:
artery
Token artery
Feature activation+0.321
Top resid features:
function
Token function
Feature activation-0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.006
Top resid features:
this
Tokenthis
Feature activation+0.088
Top resid features:
bacteria
Token bacteria
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
found
Token found
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
large
Token large
Feature activation+6.324
Top resid features:
quantities
Token quantities
Feature activation+0.139
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
yogurt
Token yogurt
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Tim
TokenTim
Feature activation+0.000
Top resid features:
owns
Token owns
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
operates
Token operates
Feature activation+0.026
Top resid features:
Small
Token Small
Feature activation+6.321
Top resid features:
Axe
Token Axe
Feature activation+0.004
Top resid features:
Jiu
Token Jiu
Feature activation-0.011
Top resid features:
J
Token J
Feature activation+0.001
Top resid features:
itsu
Tokenitsu
Feature activation-0.084
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
very
Token very
Feature activation-0.002
Top resid features:
first
Token first
Feature activation+0.007
Top resid features:
private
Token private
Feature activation+0.037
Top resid features:
sector
Token sector
Feature activation+0.008
Top resid features:
small
Token small
Feature activation+3.537
Top resid features:
arms
Token arms
Feature activation+0.069
Top resid features:
factory
Token factory
Feature activation+0.024
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
nation
Token nation
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation-0.009
Top resid features:
s
Tokens
Feature activation+0.033
Top resid features:
campaign
Token campaign
Feature activation-0.003
Top resid features:
relied
Token relied
Feature activation-0.008
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
small
Token small
Feature activation+2.921
Top resid features:
organizing
Token organizing
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
which
Token which
Feature activation-0.006
Top resid features:
Bond
Token Bond
Feature activation+0.209
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.115
Top resid features:
Previously
Token Previously
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
Indian
Token Indian
Feature activation+0.093
Top resid features:
small
Token small
Feature activation+3.247
Top resid features:
arms
Token arms
Feature activation+0.100
Top resid features:
industry
Token industry
Feature activation+0.082
Top resid features:
has
Token has
Feature activation+0.010
Top resid features:
been
Token been
Feature activation+0.003
Top resid features:
entirely
Token entirely
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.125
Top resid features:
Previously
Token Previously
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Indian
Token Indian
Feature activation+0.003
Top resid features:
small
Token small
Feature activation+2.947
Top resid features:
arms
Token arms
Feature activation+0.068
Top resid features:
industry
Token industry
Feature activation+0.007
Top resid features:
has
Token has
Feature activation+0.003
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
entirely
Token entirely
Feature activation-0.002
Top resid features:
ourselves
Token ourselves
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.010
Top resid features:
being
Token being
Feature activation+0.004
Top resid features:
advocates
Token advocates
Feature activation-0.015
Top resid features:
for
Token for
Feature activation+0.005
Top resid features:
smaller
Token smaller
Feature activation+5.693
Top resid features:
government
Token government
Feature activation+0.263
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
We
Token We
Feature activation+0.004
Top resid features:
believe
Token believe
Feature activation+0.014
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.073
Top resid features:
small
Token small
Feature activation+5.209
Top resid features:
processes
Token processes
Feature activation+0.636
Top resid features:
,
Token,
Feature activation+0.286
Top resid features:
you
Token you
Feature activation+0.033
Top resid features:
can
Token can
Feature activation+0.034
Top resid features:
think
Token think
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
Pass
TokenPass
Feature activation+0.006
Top resid features:
age
Tokenage
Feature activation-0.038
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
Small
Token Small
Feature activation+5.266
Top resid features:
Business
Token Business
Feature activation+0.131
Top resid features:
Tax
Token Tax
Feature activation+0.055
Top resid features:
Equity
Token Equity
Feature activation+0.077
Top resid features:
Act
Token Act
Feature activation-0.004
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.48

Head 2: 0.06

Head 3: 0.04

Head 4: 0.03

Head 5: 0.02

Head 6: 0.05

Head 7: 0.09

Head 8: 0.03

Head 9: 0.04

Head 10: 0.06

Head 11: 0.06

Positive logits

Small8.14

Small8.09

small7.49

small6.94

smaller6.30

Large5.93

smallest5.71

Large5.57

large5.36

tiny5.31

Tiny5.14

larger4.88

sized4.76

sized4.69

Medium4.58

tiny4.51

Medium4.49

larg4.48

large4.45

bigger4.36

Negative logits

osite-2.60

oglu-2.44

ace-2.43

Aven-2.41

alky-2.39

ocry-2.37

straight-2.37

ophen-2.27

Riders-2.25

ear-2.24

stranded-2.15

limbo-2.12

hon-2.11

straight-2.11

osed-2.10

bast-2.10

que-2.07

osuke-2.07

Brom-2.05

hottest-2.05

INTERVAL 7.304 - 8.116
CONTAINS 0.000%

ful
Tokenful
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.531
needs
Token needs
Feature activation+0.000
of
Token of
Feature activation+5.496
the
Token the
Feature activation+5.448
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
,
Token,
Feature activation+0.000
quality
Token quality
Feature activation+7.291
keep
Token keep
Feature activation+1.426
saying
Token saying
Feature activation+0.165
us
Token us
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
guys
Token guys
Feature activation+1.184
have
Token have
Feature activation+8.116
small
Token small
Feature activation+0.000
penis
Token penis
Feature activation+0.346
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
our
Token our
Feature activation+0.150
Ċ
TokenĊ
Feature activation+7.075
As
TokenAs
Feature activation+3.143
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.433
,
Token,
Feature activation+7.707
Tim
Token Tim
Feature activation+0.000
and
Token and
Feature activation+4.486
I
Token I
Feature activation+0.000
are
Token are
Feature activation+0.000
prone
Token prone
Feature activation+0.000

INTERVAL 6.492 - 7.304
CONTAINS 0.001%

length
Token length
Feature activation+0.000
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
).
Token).
Feature activation+7.075
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.075
As
TokenAs
Feature activation+3.143
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.433
,
Token,
Feature activation+7.707
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
,
Token,
Feature activation+0.000
quality
Token quality
Feature activation+7.291
small
Token small
Feature activation+0.049
arms
Token arms
Feature activation+0.000
in
Token in
Feature activation+0.249
the
Token the
Feature activation+0.284
wake
Token wake
Feature activation+0.000
maintaining
Token maintaining
Feature activation+0.820
the
Token the
Feature activation+0.942
status
Token status
Feature activation+0.000
quo
Token quo
Feature activation+0.095
.
Token.
Feature activation+5.480
But
Token But
Feature activation+7.008
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
not
Token not
Feature activation+0.487
spoke
Token spoke
Feature activation+0.000
in
Token in
Feature activation+0.000
length
Token length
Feature activation+0.000
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
).
Token).
Feature activation+7.075
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.075
As
TokenAs
Feature activation+3.143
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
Now
Token Now
Feature activation+0.441
,
Token,
Feature activation+0.625
however
Token however
Feature activation+0.000
,
Token,
Feature activation+1.033
the
Token the
Feature activation+2.229
Indian
Token Indian
Feature activation+6.759
engineering
Token engineering
Feature activation+0.261
group
Token group
Feature activation+0.000
Pun
Token Pun
Feature activation+0.000
ji
Tokenji
Feature activation+0.000
Lloyd
Token Lloyd
Feature activation+0.000

INTERVAL 5.681 - 6.492
CONTAINS 0.000%

s
Tokens
Feature activation+0.000
limbs
Token limbs
Feature activation+0.000
.
Token.
Feature activation+0.000
Per
Token Per
Feature activation+0.000
ipher
Tokenipher
Feature activation+0.000
al
Tokenal
Feature activation+6.195
circulation
Token circulation
Feature activation+0.000
is
Token is
Feature activation+0.000
great
Token great
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
this
Tokenthis
Feature activation+0.060
bacteria
Token bacteria
Feature activation+0.000
is
Token is
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+6.147
large
Token large
Feature activation+0.246
quantities
Token quantities
Feature activation+0.000
in
Token in
Feature activation+0.000
yogurt
Token yogurt
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.808
s
Tokens
Feature activation+3.186
first
Token first
Feature activation+1.729
-
Token-
Feature activation+0.000
ever
Tokenever
Feature activation+5.752
affiliate
Token affiliate
Feature activation+1.105
academy
Token academy
Feature activation+0.000
(
Token (
Feature activation+0.147
which
Tokenwhich
Feature activation+0.002
Tim
Token Tim
Feature activation+0.000

INTERVAL 4.869 - 5.681
CONTAINS 0.001%

People
TokenPeople
Feature activation+0.417
are
Token are
Feature activation+0.449
beginning
Token beginning
Feature activation+0.183
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+3.372
that
Token that
Feature activation+5.220
the
Token the
Feature activation+1.864
problems
Token problems
Feature activation+0.595
we
Token we
Feature activation+0.000
face
Token face
Feature activation+0.000
now
Token now
Feature activation+0.000
processes
Token processes
Feature activation+0.564
,
Token,
Feature activation+1.789
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
think
Token think
Feature activation+1.100
of
Token of
Feature activation+5.413
this
Token this
Feature activation+0.745
as
Token as
Feature activation+3.947
a
Token a
Feature activation+2.824
truly
Token truly
Feature activation+1.586
incremental
Token incremental
Feature activation+0.929
for
Token for
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
government
Token government
Feature activation+0.009
.
Token.
Feature activation+2.798
We
Token We
Feature activation+0.000
believe
Token believe
Feature activation+5.421
public
Token public
Feature activation+0.064
sector
Token sector
Feature activation+0.546
bureaucrats
Token bureaucrats
Feature activation+0.000
are
Token are
Feature activation+0.000
w
Token w
Feature activation+0.000
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.531
needs
Token needs
Feature activation+0.000
of
Token of
Feature activation+5.496
the
Token the
Feature activation+5.448
Indian
Token Indian
Feature activation+7.946
military
Token military
Feature activation+0.519
for
Token for
Feature activation+2.596
modern
Token modern
Feature activation+5.442
is
Token is
Feature activation+1.203
maintaining
Token maintaining
Feature activation+0.820
the
Token the
Feature activation+0.942
status
Token status
Feature activation+0.000
quo
Token quo
Feature activation+0.095
.
Token.
Feature activation+5.480
But
Token But
Feature activation+7.008
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 4.058 - 4.869
CONTAINS 0.002%

small
Token small
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
necessarily
Token necessarily
Feature activation+0.000
equate
Token equate
Feature activation+1.900
to
Token to
Feature activation+4.141
weakness
Token weakness
Feature activation+0.000
...
Token...
Feature activation+0.687
a
Tokena
Feature activation+0.957
lot
Token lot
Feature activation+2.418
of
Token of
Feature activation+3.411
Ŀ
TokenĿ
Feature activation+0.891
they
Token they
Feature activation+0.000
write
Token write
Feature activation+0.000
.
Token.
Feature activation+4.148
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.414
Clinton
TokenClinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.153
s
Tokens
Feature activation+0.743
campaign
Token campaign
Feature activation+0.000
.
Token.
Feature activation+1.817
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.752
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.839
The
TokenThe
Feature activation+4.447
anti
Token anti
Feature activation+0.331
-
Token-
Feature activation+2.221
tax
Tokentax
Feature activation+0.226
crus
Token crus
Feature activation+0.000
ader
Tokenader
Feature activation+0.238
internal
Token internal
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
politics
Token politics
Feature activation+0.000
would
Token would
Feature activation+0.000
likely
Token likely
Feature activation+0.000
prohibit
Token prohibit
Feature activation+4.347
that
Token that
Feature activation+0.265
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.727
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.627
enough
Token enough
Feature activation+0.073
to
Token to
Feature activation+0.000
challenge
Token challenge
Feature activation+0.520
the
Token the
Feature activation+0.688
establishment
Token establishment
Feature activation+0.000
.
Token.
Feature activation+4.493
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.971
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.915
People
TokenPeople
Feature activation+0.417

INTERVAL 3.246 - 4.058
CONTAINS 0.002%

paperwork
Token paperwork
Feature activation+0.000
requirement
Token requirement
Feature activation+0.000
for
Token for
Feature activation+1.716
job
Token job
Feature activation+0.000
creators
Token creators
Feature activation+0.000
.
Token.
Feature activation+3.781
The
Token The
Feature activation+1.093
continued
Token continued
Feature activation+0.000
delays
Token delays
Feature activation+0.000
add
Token add
Feature activation+0.000
to
Token to
Feature activation+0.442
ľ
Tokenľ
Feature activation+3.915
People
TokenPeople
Feature activation+0.417
are
Token are
Feature activation+0.449
beginning
Token beginning
Feature activation+0.183
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+3.372
that
Token that
Feature activation+5.220
the
Token the
Feature activation+1.864
problems
Token problems
Feature activation+0.595
we
Token we
Feature activation+0.000
face
Token face
Feature activation+0.000
Don
Token Don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
tell
Token tell
Feature activation+0.000
me
Token me
Feature activation+3.291
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
shocked
Token shocked
Feature activation+0.000
and
Token and
Feature activation+0.993
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
12
Token12
Feature activation+0.000
for
Token for
Feature activation+0.921
the
Token the
Feature activation+3.265
larger
Token larger
Feature activation+0.235
ones
Token ones
Feature activation+0.000
.
Token.
Feature activation+0.000
Die
Token Die
Feature activation+0.000
u
Tokenu
Feature activation+0.000
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
Two
Token Two
Feature activation+0.000
battle
Token battle
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+3.874
tiny
Token tiny
Feature activation+0.336
Mediterranean
Token Mediterranean
Feature activation+0.000
island
Token island
Feature activation+0.000
of
Token of
Feature activation+0.000
Malta
Token Malta
Feature activation+0.000

INTERVAL 2.435 - 3.246
CONTAINS 0.005%

capital
Token capital
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
risk
Token risk
Feature activation+0.000
.
Token.
Feature activation+2.925
That
Token That
Feature activation+0.497
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
why
Token why
Feature activation+3.137
too
Token too
Feature activation+0.409
many
Token many
Feature activation+2.496
laws
Token laws
Feature activation+0.486
and
Token and
Feature activation+0.030
regulations
Token regulations
Feature activation+0.968
.
Token.
Feature activation+2.613
Something
Token Something
Feature activation+0.097
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.209
done
Token done
Feature activation+0.359
.
Token.
Feature activation+0.915
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.834
"
Token"
Feature activation+1.582
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+2.519
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.582
,
Token,
Feature activation+4.235
value
Token value
Feature activation+0.000
in
Token in
Feature activation+0.000
each
Token each
Feature activation+0.000
row
Token row
Feature activation+0.000
from
Token from
Feature activation+1.034
the
Token the
Feature activation+2.684
entire
Token entire
Feature activation+0.285
row
Token row
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
E
Token E
Feature activation+0.000
made
Token made
Feature activation+0.000
up
Token up
Feature activation+0.000
of
Token of
Feature activation+1.262
small
Token small
Feature activation+0.391
Vs
Token Vs
Feature activation+2.782
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000

INTERVAL 1.623 - 2.435
CONTAINS 0.012%

another
Token another
Feature activation+0.000
on
Token on
Feature activation+0.000
erous
Tokenerous
Feature activation+0.000
paperwork
Token paperwork
Feature activation+0.000
requirement
Token requirement
Feature activation+0.000
for
Token for
Feature activation+1.716
job
Token job
Feature activation+0.000
creators
Token creators
Feature activation+0.000
.
Token.
Feature activation+3.781
The
Token The
Feature activation+1.093
continued
Token continued
Feature activation+0.000
losers
Token losers
Feature activation+0.000
retarded
Token retarded
Feature activation+0.000
ly
Tokenly
Feature activation+0.311
believe
Token believe
Feature activation+0.285
that
Token that
Feature activation+0.029
by
Token by
Feature activation+1.889
keep
Token keep
Feature activation+1.426
saying
Token saying
Feature activation+0.165
us
Token us
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
guys
Token guys
Feature activation+1.184
parties
Token parties
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
look
Token look
Feature activation+0.000
promising
Token promising
Feature activation+0.000
.
Token.
Feature activation+2.226
Ram
Token Ram
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
andra
Tokenandra
Feature activation+0.000
Gu
Token Gu
Feature activation+0.000
ha
Tokenha
Feature activation+0.000
iteration
Token iteration
Feature activation+0.000
,
Token,
Feature activation+0.058
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
turn
Token turn
Feature activation+1.773
stretched
Token stretched
Feature activation+0.000
out
Token out
Feature activation+1.082
and
Token and
Feature activation+2.330
folded
Token folded
Feature activation+0.000
to
Token to
Feature activation+0.898
Le
Token Le
Feature activation+0.000
Rou
Token Rou
Feature activation+0.000
x
Tokenx
Feature activation+0.000
.
Token.
Feature activation+0.539
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.800
"
Token"
Feature activation+2.212
Many
TokenMany
Feature activation+2.468
of
Token of
Feature activation+0.493
these
Token these
Feature activation+2.473
contractors
Token contractors
Feature activation+0.000

INTERVAL 0.812 - 1.623
CONTAINS 0.033%

stick
Token stick
Feature activation+0.000
of
Token of
Feature activation+0.000
dynam
Token dynam
Feature activation+0.000
ite
Tokenite
Feature activation+0.000
!
Token!
Feature activation+0.000
These
Token These
Feature activation+1.270
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
banned
Token banned
Feature activation+0.000
from
Token from
Feature activation+0.000
sale
Token sale
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.093
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
too
Token too
Feature activation+0.908
small
Token small
Feature activation+0.000
to
Token to
Feature activation+0.000
worry
Token worry
Feature activation+0.000
about
Token about
Feature activation+0.000
and
Token and
Feature activation+0.395
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
command
Token command
Feature activation+0.894
key
Token key
Feature activation+0.000
sectors
Token sectors
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
humans
Token humans
Feature activation+0.000
dropping
Token dropping
Feature activation+0.000
balls
Token balls
Feature activation+0.253
of
Token of
Feature activation+0.034
markedly
Token markedly
Feature activation+1.199
different
Token different
Feature activation+0.832
weights
Token weights
Feature activation+0.000
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
caffeine
Token caffeine
Feature activation+0.000
cause
Token cause
Feature activation+0.000
light
Token light
Feature activation+0.000
-
Token-
Feature activation+0.000
headed
Tokenheaded
Feature activation+0.000
ness
Tokenness
Feature activation+1.438
and
Token and
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
f
Token f
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
ting
Tokenting
Feature activation+0.465

INTERVAL 0.000 - 0.812
CONTAINS 99.942%

âĢĶ
Token âĢĶ
Feature activation+0.000
but
Token but
Feature activation+0.000
its
Token its
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
solar
Token solar
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
long
Token long
Feature activation+0.000
collection
Token collection
Feature activation+0.000
agents
Token agents
Feature activation+0.000
were
Token were
Feature activation+0.000
also
Token also
Feature activation+0.000
not
Token not
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
checked
Token checked
Feature activation+0.000
for
Token for
Feature activation+0.000
up
Token up
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
the
Token the
Feature activation+0.000
Executive
Token Executive
Feature activation+0.000
Branch
Token Branch
Feature activation+0.000
and
Token and
Feature activation+0.000
place
Token place
Feature activation+0.000
this
Token this
Feature activation+0.000
information
Token information
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
website
Token website
Feature activation+0.000
,
Token,
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
captive
Token captive
Feature activation+0.000
killer
Token killer
Feature activation+0.000
whales
Token whales
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
venture
Token venture
Feature activation+0.000
question
Token question
Feature activation+0.000
)
Token)
Feature activation+0.000
Sam
Token Sam
Feature activation+0.000
M
Token M
Feature activation+0.000
D
Token D
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000
Answer
Token Answer
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

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