H8.4 top features

Top feature 0 in H8.4: (feature 13211)

TOP ACTIVATIONS
MAX = 5.956

Constitution
Token Constitution
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
ad
Token ad
Feature activation+0.000
her
Tokenher
Feature activation+0.000
ing
Tokening
Feature activation+5.956
to
Token to
Feature activation+0.000
principle
Token principle
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
minimum
Token minimum
Feature activation+0.000
wages
Token wages
Feature activation+0.000
(
Token (
Feature activation+0.000
not
Tokennot
Feature activation+0.000
relating
Token relating
Feature activation+0.000
specifically
Token specifically
Feature activation+5.307
to
Token to
Feature activation+0.000
LGBT
Token LGBT
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.693
cos
Token cos
Feature activation+0.000
mology
Tokenmology
Feature activation+0.000
which
Token which
Feature activation+0.000
she
Token she
Feature activation+0.000
then
Token then
Feature activation+0.000
attributed
Token attributed
Feature activation+3.983
to
Token to
Feature activation+0.112
divine
Token divine
Feature activation+0.000
inspiration
Token inspiration
Feature activation+0.000
(
Token (
Feature activation+0.000
what
Tokenwhat
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
movies
Token movies
Feature activation+0.000
that
Token that
Feature activation+0.000
subscrib
Token subscrib
Feature activation+0.000
es
Tokenes
Feature activation+3.933
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
dubious
Token dubious
Feature activation+0.009
home
Token home
Feature activation+0.000
opathic
Tokenopathic
Feature activation+0.000
indignation
Token indignation
Feature activation+3.675
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
acts
Token acts
Feature activation+1.267
,
Token,
Feature activation+3.912
to
Token to
Feature activation+2.401
the
Token the
Feature activation+0.000
degener
Token degener
Feature activation+0.000
ating
Tokenating
Feature activation+0.222
influence
Token influence
Feature activation+0.000
to
Token to
Feature activation+0.000
subordinate
Token subordinate
Feature activation+0.037
their
Token their
Feature activation+1.781
own
Token own
Feature activation+1.276
nationalist
Token nationalist
Feature activation+0.683
objectives
Token objectives
Feature activation+3.803
in
Token in
Feature activation+1.841
order
Token order
Feature activation+0.060
to
Token to
Feature activation+0.035
help
Token help
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
,
Token,
Feature activation+0.000
due
Token due
Feature activation+0.000
in
Token in
Feature activation+0.597
no
Token no
Feature activation+0.000
small
Token small
Feature activation+0.205
part
Token part
Feature activation+3.717
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
esteem
Token esteem
Feature activation+0.000
his
Token his
Feature activation+0.000
work
Token work
Feature activation+0.000
attributed
Token attributed
Feature activation+1.061
all
Token all
Feature activation+0.000
violent
Token violent
Feature activation+0.000
demonstrations
Token demonstrations
Feature activation+3.064
of
Token of
Feature activation+0.000
indignation
Token indignation
Feature activation+3.675
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
acts
Token acts
Feature activation+1.267
,
Token,
Feature activation+3.912
of
Token of
Feature activation+0.000
built
Token built
Feature activation+0.000
forms
Token forms
Feature activation+0.000
correspond
Token correspond
Feature activation+0.000
more
Token more
Feature activation+3.173
closely
Token closely
Feature activation+3.647
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+0.000
prototypes
Token prototypes
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
referred
Token referred
Feature activation+0.000
only
Token only
Feature activation+1.876
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
footnote
Token footnote
Feature activation+3.573
to
Token to
Feature activation+1.181
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
effect
Token effect
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
likened
Token likened
Feature activation+2.229
it
Token it
Feature activation+3.521
to
Token to
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
effect
Token effect
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
would
Token would
Feature activation+0.000
subject
Token subject
Feature activation+0.000
him
Token him
Feature activation+3.427
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
fine
Token fine
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
said
Token said
Feature activation+0.000
referred
Token referred
Feature activation+0.059
U
Token U
Feature activation+0.000
rets
Tokenrets
Feature activation+2.595
ky
Tokenky
Feature activation+3.399
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
Seth
Token Seth
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
linked
Token linked
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
ins
Tokenins
Feature activation+3.377
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
crime
Token crime
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
requested
Token requested
Feature activation+0.000
$
Token $
Feature activation+0.000
25
Token25
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
billion
Token billion
Feature activation+3.346
to
Token to
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
and
Token and
Feature activation+0.000
prevention
Token prevention
Feature activation+0.000
.
Token.
Feature activation+0.000
president
Token president
Feature activation+1.794
's
Token's
Feature activation+0.000
health
Token health
Feature activation+0.000
-
Token-
Feature activation+0.000
care
Tokencare
Feature activation+0.000
fight
Token fight
Feature activation+3.307
to
Token to
Feature activation+0.000
Napoleon
Token Napoleon
Feature activation+0.000
Bon
Token Bon
Feature activation+0.000
ap
Tokenap
Feature activation+0.000
arte
Tokenarte
Feature activation+0.000
,
Token,
Feature activation+0.000
adding
Token adding
Feature activation+0.000
he
Token he
Feature activation+0.000
attributed
Token attributed
Feature activation+0.000
the
Token the
Feature activation+0.387
disagreement
Token disagreement
Feature activation+3.307
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
being
Token being
Feature activation+0.000
drunk
Token drunk
Feature activation+0.000
.
Token.
Feature activation+0.000
potential
Token potential
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
close
Token close
Feature activation+0.000
that
Token that
Feature activation+1.294
potential
Token potential
Feature activation+3.246
was
Token was
Feature activation+3.472
to
Token to
Feature activation+0.253
being
Token being
Feature activation+0.000
realized
Token realized
Feature activation+0.000
.
Token.
Feature activation+0.000
arn
Tokenarn
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
.
Token.
Feature activation+0.000
Due
Token Due
Feature activation+0.000
in
Token in
Feature activation+0.522
part
Token part
Feature activation+3.242
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
early
Token early
Feature activation+0.000
season
Token season
Feature activation+0.000
struggles
Token struggles
Feature activation+0.000
types
Token types
Feature activation+0.000
of
Token of
Feature activation+0.000
built
Token built
Feature activation+0.000
forms
Token forms
Feature activation+0.000
correspond
Token correspond
Feature activation+0.000
more
Token more
Feature activation+3.173
closely
Token closely
Feature activation+3.647
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+0.000
prototypes
Token prototypes
Feature activation+0.000
?
Token?
Feature activation+0.000

Top DFA by src position
MAX = 6.443

the
Token the
Feature activation+0.007
Top resid features:
Constitution
Token Constitution
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
just
Token just
Feature activation+0.015
Top resid features:
ad
Token ad
Feature activation+0.023
Top resid features:
her
Tokenher
Feature activation+6.443
Top resid features:
ing
Tokening
Feature activation+0.032
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
principle
Token principle
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:
higher
Token higher
Feature activation-0.003
Top resid features:
minimum
Token minimum
Feature activation+0.000
Top resid features:
wages
Token wages
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.035
Top resid features:
not
Tokennot
Feature activation+0.056
Top resid features:
relating
Token relating
Feature activation+5.771
Top resid features:
specifically
Token specifically
Feature activation+0.047
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
LGBT
Token LGBT
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
cos
Token cos
Feature activation+0.001
Top resid features:
mology
Tokenmology
Feature activation-0.007
Top resid features:
which
Token which
Feature activation+0.065
Top resid features:
she
Token she
Feature activation-0.001
Top resid features:
then
Token then
Feature activation+0.024
Top resid features:
attributed
Token attributed
Feature activation+4.462
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
divine
Token divine
Feature activation+0.000
Top resid features:
inspiration
Token inspiration
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
what
Tokenwhat
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
those
Token those
Feature activation+0.013
Top resid features:
movies
Token movies
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.067
Top resid features:
subscrib
Token subscrib
Feature activation+4.414
Top resid features:
es
Tokenes
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
dubious
Token dubious
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
bourgeoisie
Token bourgeoisie
Feature activation+0.015
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
all
Token all
Feature activation-0.001
Top resid features:
times
Token times
Feature activation+0.008
Top resid features:
attributed
Token attributed
Feature activation+4.318
Top resid features:
all
Token all
Feature activation+0.015
Top resid features:
violent
Token violent
Feature activation+0.001
Top resid features:
demonstrations
Token demonstrations
Feature activation+0.091
Top resid features:
of
Token of
Feature activation-0.017
Top resid features:
indignation
Token indignation
Feature activation+0.064
Top resid features:
Islamic
Token Islamic
Feature activation-0.002
Top resid features:
government
Token government
Feature activation+0.004
Top resid features:
leaders
Token leaders
Feature activation-0.000
Top resid features:
[...]
Token [...]
Feature activation+0.052
Top resid features:
to
Token to
Feature activation+0.059
Top resid features:
subordinate
Token subordinate
Feature activation+4.182
Top resid features:
their
Token their
Feature activation+0.037
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
nationalist
Token nationalist
Feature activation-0.044
Top resid features:
objectives
Token objectives
Feature activation+0.027
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Royal
Token Royal
Feature activation+0.002
Top resid features:
Institution
Token Institution
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
London
Token London
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
due
Token due
Feature activation+4.315
Top resid features:
in
Token in
Feature activation-0.041
Top resid features:
no
Token no
Feature activation-0.005
Top resid features:
small
Token small
Feature activation-0.049
Top resid features:
part
Token part
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
bourgeoisie
Token bourgeoisie
Feature activation+0.010
Top resid features:
has
Token has
Feature activation+0.008
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
all
Token all
Feature activation-0.000
Top resid features:
times
Token times
Feature activation+0.013
Top resid features:
attributed
Token attributed
Feature activation+4.155
Top resid features:
all
Token all
Feature activation+0.042
Top resid features:
violent
Token violent
Feature activation-0.001
Top resid features:
demonstrations
Token demonstrations
Feature activation+0.067
Top resid features:
of
Token of
Feature activation-0.041
Top resid features:
indignation
Token indignation
Feature activation+0.039
Top resid features:
What
Token What
Feature activation+0.009
Top resid features:
types
Token types
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
built
Token built
Feature activation-0.001
Top resid features:
forms
Token forms
Feature activation+0.027
Top resid features:
correspond
Token correspond
Feature activation+4.110
Top resid features:
more
Token more
Feature activation+0.043
Top resid features:
closely
Token closely
Feature activation+0.075
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
biological
Token biological
Feature activation+0.000
Top resid features:
prototypes
Token prototypes
Feature activation+0.000
Top resid features:
talks
Token talks
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
compromise
Token compromise
Feature activation+0.006
Top resid features:
proposal
Token proposal
Feature activation+0.020
Top resid features:
referred
Token referred
Feature activation+4.082
Top resid features:
only
Token only
Feature activation+0.061
Top resid features:
in
Token in
Feature activation-0.010
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
footnote
Token footnote
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+0.002
Top resid features:
effect
Token effect
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
one
Token one
Feature activation-0.006
Top resid features:
researcher
Token researcher
Feature activation+0.055
Top resid features:
likened
Token likened
Feature activation+3.997
Top resid features:
it
Token it
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
discussion
Token discussion
Feature activation+0.015
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
matter
Token matter
Feature activation+0.022
Top resid features:
would
Token would
Feature activation+0.066
Top resid features:
subject
Token subject
Feature activation+3.887
Top resid features:
him
Token him
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
fine
Token fine
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Director
Token Director
Feature activation+0.007
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.025
Top resid features:
who
Token who
Feature activation+0.011
Top resid features:
Bernie
Token Bernie
Feature activation+0.012
Top resid features:
said
Token said
Feature activation-0.035
Top resid features:
referred
Token referred
Feature activation+3.938
Top resid features:
U
Token U
Feature activation+0.037
Top resid features:
rets
Tokenrets
Feature activation+0.016
Top resid features:
ky
Tokenky
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
FBI
Token FBI
Feature activation-0.006
Top resid features:
linked
Token linked
Feature activation+3.995
Top resid features:
Iv
Token Iv
Feature activation+0.009
Top resid features:
ins
Tokenins
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
crime
Token crime
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
fiscal
Token fiscal
Feature activation+0.008
Top resid features:
year
Token year
Feature activation-0.001
Top resid features:
2013
Token 2013
Feature activation+0.020
Top resid features:
dev
Token dev
Feature activation-0.002
Top resid features:
otes
Tokenotes
Feature activation+3.626
Top resid features:
just
Token just
Feature activation+0.018
Top resid features:
over
Token over
Feature activation+0.011
Top resid features:
40
Token 40
Feature activation+0.002
Top resid features:
percent
Token percent
Feature activation+0.129
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
Obama
Token Obama
Feature activation-0.002
Top resid features:
allies
Token allies
Feature activation+0.001
Top resid features:
after
Token after
Feature activation+0.012
Top resid features:
he
Token he
Feature activation+0.001
Top resid features:
likened
Token likened
Feature activation+3.931
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
president
Token president
Feature activation+0.008
Top resid features:
's
Token's
Feature activation-0.068
Top resid features:
health
Token health
Feature activation+0.005
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
affidavit
Token affidavit
Feature activation+0.005
Top resid features:
said
Token said
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
adding
Token adding
Feature activation+0.010
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
attributed
Token attributed
Feature activation+3.948
Top resid features:
the
Token the
Feature activation-0.033
Top resid features:
disagreement
Token disagreement
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
potential
Token potential
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
how
Token how
Feature activation+0.017
Top resid features:
close
Token close
Feature activation+3.868
Top resid features:
that
Token that
Feature activation-0.097
Top resid features:
potential
Token potential
Feature activation+0.042
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
Chandler
Token Chandler
Feature activation-0.003
Top resid features:
H
Token H
Feature activation+0.002
Top resid features:
arn
Tokenarn
Feature activation+0.006
Top resid features:
ish
Tokenish
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Due
Token Due
Feature activation+3.739
Top resid features:
in
Token in
Feature activation+0.046
Top resid features:
part
Token part
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
early
Token early
Feature activation+0.000
Top resid features:
What
Token What
Feature activation+0.004
Top resid features:
types
Token types
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
built
Token built
Feature activation-0.001
Top resid features:
forms
Token forms
Feature activation+0.036
Top resid features:
correspond
Token correspond
Feature activation+3.753
Top resid features:
more
Token more
Feature activation+0.015
Top resid features:
closely
Token closely
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
biological
Token biological
Feature activation+0.000
Top resid features:
prototypes
Token prototypes
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.61

Head 5: 0.05

Head 6: 0.02

Head 7: 0.06

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

to3.51

unto3.04

thereto2.99

to2.86

TO2.61

onto2.44

To2.39

To2.37

TO2.35

towards2.17

MpServer2.07

toward1.97

onwards1.95

assetsadobe1.92

Cosponsors1.85

Thumbnails1.81

onward1.76

downwards1.75

href1.69

ItemTracker1.64

Negative logits

-2.12

iven-2.02

ウス-1.95

ubric-1.82

uren-1.68

toggle-1.65

pared-1.63

disregard-1.61

с-1.61

裏�-1.60

autions-1.60

-1.59

-1.58

refuse-1.57

enson-1.55

open-1.54

kay-1.54

submit-1.53

inth-1.53

destroy-1.53

INTERVAL 5.360 - 5.956
CONTAINS 0.000%

Constitution
Token Constitution
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
ad
Token ad
Feature activation+0.000
her
Tokenher
Feature activation+0.000
ing
Tokening
Feature activation+5.956
to
Token to
Feature activation+0.000
principle
Token principle
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 4.765 - 5.360
CONTAINS 0.000%

minimum
Token minimum
Feature activation+0.000
wages
Token wages
Feature activation+0.000
(
Token (
Feature activation+0.000
not
Tokennot
Feature activation+0.000
relating
Token relating
Feature activation+0.000
specifically
Token specifically
Feature activation+5.307
to
Token to
Feature activation+0.000
LGBT
Token LGBT
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.693

INTERVAL 4.169 - 4.765
CONTAINS 0.000%

INTERVAL 3.574 - 4.169
CONTAINS 0.001%

of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
movies
Token movies
Feature activation+0.000
that
Token that
Feature activation+0.000
subscrib
Token subscrib
Feature activation+0.000
es
Tokenes
Feature activation+3.933
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
dubious
Token dubious
Feature activation+0.009
home
Token home
Feature activation+0.000
opathic
Tokenopathic
Feature activation+0.000
of
Token of
Feature activation+0.000
built
Token built
Feature activation+0.000
forms
Token forms
Feature activation+0.000
correspond
Token correspond
Feature activation+0.000
more
Token more
Feature activation+3.173
closely
Token closely
Feature activation+3.647
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+0.000
prototypes
Token prototypes
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
indignation
Token indignation
Feature activation+3.675
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
acts
Token acts
Feature activation+1.267
,
Token,
Feature activation+3.912
to
Token to
Feature activation+2.401
the
Token the
Feature activation+0.000
degener
Token degener
Feature activation+0.000
ating
Tokenating
Feature activation+0.222
influence
Token influence
Feature activation+0.000
to
Token to
Feature activation+0.000
subordinate
Token subordinate
Feature activation+0.037
their
Token their
Feature activation+1.781
own
Token own
Feature activation+1.276
nationalist
Token nationalist
Feature activation+0.683
objectives
Token objectives
Feature activation+3.803
in
Token in
Feature activation+1.841
order
Token order
Feature activation+0.060
to
Token to
Feature activation+0.035
help
Token help
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
,
Token,
Feature activation+0.000
due
Token due
Feature activation+0.000
in
Token in
Feature activation+0.597
no
Token no
Feature activation+0.000
small
Token small
Feature activation+0.205
part
Token part
Feature activation+3.717
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
esteem
Token esteem
Feature activation+0.000
his
Token his
Feature activation+0.000
work
Token work
Feature activation+0.000

INTERVAL 2.978 - 3.574
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
linked
Token linked
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
ins
Tokenins
Feature activation+3.377
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
crime
Token crime
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
effect
Token effect
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
likened
Token likened
Feature activation+2.229
it
Token it
Feature activation+3.521
to
Token to
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
effect
Token effect
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
that
Token that
Feature activation+0.000
expose
Token expose
Feature activation+0.000
them
Token them
Feature activation+3.023
to
Token to
Feature activation+0.234
new
Token new
Feature activation+0.000
selection
Token selection
Feature activation+0.000
pressures
Token pressures
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
no
Token no
Feature activation+0.000
similarity
Token similarity
Feature activation+2.272
at
Token at
Feature activation+0.508
all
Token all
Feature activation+3.129
to
Token to
Feature activation+0.405
Hook
Token Hook
Feature activation+0.000
&
Token &
Feature activation+0.000
S
Token S
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
said
Token said
Feature activation+0.000
referred
Token referred
Feature activation+0.059
U
Token U
Feature activation+0.000
rets
Tokenrets
Feature activation+2.595
ky
Tokenky
Feature activation+3.399
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
Seth
Token Seth
Feature activation+0.000

INTERVAL 2.382 - 2.978
CONTAINS 0.003%

must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
XML
Token XML
Feature activation+0.000
which
Token which
Feature activation+0.000
conform
Token conform
Feature activation+0.000
s
Tokens
Feature activation+2.722
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
provided
Token provided
Feature activation+0.000
schema
Token schema
Feature activation+0.000
(
Token (
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
attach
Token attach
Feature activation+0.000
too
Token too
Feature activation+2.885
much
Token much
Feature activation+2.772
personality
Token personality
Feature activation+1.916
to
Token to
Feature activation+0.000
these
Token these
Feature activation+0.000
animals
Token animals
Feature activation+0.000
rights
Token rights
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.000
over
Token over
Feature activation+0.000
their
Token their
Feature activation+1.266
children
Token children
Feature activation+2.671
to
Token to
Feature activation+0.042
the
Token the
Feature activation+0.000
whims
Token whims
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token-
Feature activation+0.000
half
Tokenhalf
Feature activation+0.000
year
Token year
Feature activation+0.000
deal
Token deal
Feature activation+0.000
tying
Token tying
Feature activation+0.000
him
Token him
Feature activation+2.959
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
club
Token club
Feature activation+0.000
until
Token until
Feature activation+0.000
the
Token the
Feature activation+0.000
AR
Token AR
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
closer
Token closer
Feature activation+0.532
you
Token you
Feature activation+2.387
get
Token get
Feature activation+2.527
to
Token to
Feature activation+0.055
the
Token the
Feature activation+0.000
wearable
Token wearable
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 1.787 - 2.382
CONTAINS 0.010%

i
Tokeni
Feature activation+0.000
*,
Token*,
Feature activation+0.000
and
Token and
Feature activation+0.064
establishments
Token establishments
Feature activation+0.000
catering
Token catering
Feature activation+0.000
exclusively
Token exclusively
Feature activation+2.231
to
Token to
Feature activation+0.206
nobles
Token nobles
Feature activation+0.000
.
Token.
Feature activation+0.000
(*
Token (*
Feature activation+0.000
F
TokenF
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
"
Token "
Feature activation+0.000
not
Tokennot
Feature activation+0.000
indifferent
Token indifferent
Feature activation+0.000
"
Token"
Feature activation+1.831
to
Token to
Feature activation+0.320
the
Token the
Feature activation+0.000
f
Token f
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
of
Token of
Feature activation+0.000
agency
Token agency
Feature activation+0.000
would
Token would
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Token over
Feature activation+0.000
these
Token these
Feature activation+0.000
duties
Token duties
Feature activation+1.839
to
Token to
Feature activation+0.167
poultry
Token poultry
Feature activation+0.000
plant
Token plant
Feature activation+0.000
employees
Token employees
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
tying
Token tying
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+2.038
prices
Token prices
Feature activation+2.122
to
Token to
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
is
Token is
Feature activation+0.000
anecdotal
Token anecdotal
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
compromise
Token compromise
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
referred
Token referred
Feature activation+0.000
only
Token only
Feature activation+1.876
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
footnote
Token footnote
Feature activation+3.573
to
Token to
Feature activation+1.181
the
Token the
Feature activation+0.000

INTERVAL 1.191 - 1.787
CONTAINS 0.026%

in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
visits
Token visits
Feature activation+0.000
were
Token were
Feature activation+1.259
recorded
Token recorded
Feature activation+0.000
as
Token as
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.068
unconditional
Token unconditional
Feature activation+0.000
love
Token love
Feature activation+0.000
leads
Token leads
Feature activation+0.000
him
Token him
Feature activation+1.216
down
Token down
Feature activation+0.000
dark
Token dark
Feature activation+0.000
paths
Token paths
Feature activation+0.000
.
Token.
Feature activation+0.000
Still
Token Still
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
export
Token export
Feature activation+0.000
the
Token the
Feature activation+0.000
test
Token test
Feature activation+0.280
database
Token database
Feature activation+1.340
that
Token that
Feature activation+0.000
contains
Token contains
Feature activation+0.000
our
Token our
Feature activation+0.000
test
Token test
Feature activation+0.000
Data
TokenData
Feature activation+1.429
same
Token same
Feature activation+0.000
-
Token-
Feature activation+0.000
sex
Tokensex
Feature activation+0.000
marriage
Token marriage
Feature activation+1.648
in
Token in
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+1.546
and
Token and
Feature activation+0.167
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.044
is
Token is
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
Cong
Token Cong
Feature activation+0.000
rats
Tokenrats
Feature activation+0.000
,
Token,
Feature activation+0.000
U
Token U
Feature activation+0.000
MG
TokenMG
Feature activation+0.101
,
Token,
Feature activation+1.333
you
Token you
Feature activation+0.000
just
Token just
Feature activation+0.000
spent
Token spent
Feature activation+0.000
your
Token your
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000

INTERVAL 0.596 - 1.191
CONTAINS 0.092%

installed
Token installed
Feature activation+0.000
and
Token and
Feature activation+0.000
added
Token added
Feature activation+0.022
the
Token the
Feature activation+0.182
binaries
Token binaries
Feature activation+1.078
to
Token to
Feature activation+1.070
your
Token your
Feature activation+0.000
path
Token path
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
simply
Token simply
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
port
Token port
Feature activation+0.000
ing
Tokening
Feature activation+0.902
an
Token an
Feature activation+0.000
app
Token app
Feature activation+1.589
made
Token made
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
almost
Token almost
Feature activation+0.000
unrecogn
Token unrecogn
Feature activation+0.000
izable
Tokenizable
Feature activation+0.000
face
Token face
Feature activation+0.000
hooked
Token hooked
Feature activation+0.223
up
Token up
Feature activation+0.904
to
Token to
Feature activation+0.208
all
Token all
Feature activation+0.000
sorts
Token sorts
Feature activation+0.000
of
Token of
Feature activation+0.000
machines
Token machines
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
WHAT
TokenWHAT
Feature activation+0.000
lead
Token lead
Feature activation+0.000
you
Token you
Feature activation+1.043
to
Token to
Feature activation+0.000
believe
Token believe
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
alternative
Token alternative
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
I
Token I
Feature activation+0.000
address
Token address
Feature activation+0.000
anybody
Token anybody
Feature activation+0.928
else
Token else
Feature activation+0.916
's
Token's
Feature activation+0.660
red
Token red
Feature activation+0.000
lines
Token lines
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 0.000 - 0.596
CONTAINS 99.866%

generally
Token generally
Feature activation+0.000
are
Token are
Feature activation+0.000
organized
Token organized
Feature activation+0.000
at
Token at
Feature activation+0.000
individual
Token individual
Feature activation+0.000
companies
Token companies
Feature activation+0.000
,
Token,
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
across
Token across
Feature activation+0.000
industries
Token industries
Feature activation+0.000
-
Token-
Feature activation+0.000
A
TokenA
Feature activation+0.000
ce
Tokence
Feature activation+0.000
rear
Token rear
Feature activation+0.000
derail
Token derail
Feature activation+0.000
le
Tokenle
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
cage
Token cage
Feature activation+0.000
plates
Token plates
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.000
complete
Token complete
Feature activation+0.000
arrogance
Token arrogance
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
horrific
Token horrific
Feature activation+0.000
mis
Token mis
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
best
Token best
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
urban
Token urban
Feature activation+0.000
ruins
Token ruins
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
abolition
Token abolition
Feature activation+0.000
of
Token of
Feature activation+0.000
slavery
Token slavery
Feature activation+0.000
,
Token,
Feature activation+0.000
Darwin
Token Darwin
Feature activation+0.000
attracted
Token attracted
Feature activation+0.000
hostility
Token hostility
Feature activation+0.000
from
Token from
Feature activation+0.000
British
Token British
Feature activation+0.000
ant
Token ant
Feature activation+0.000
ire
Tokenire
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 H8.4: (feature 1197)

TOP ACTIVATIONS
MAX = 4.338

restored
Token restored
Feature activation+0.417
DNA
Token DNA
Feature activation+3.973
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.006
cave
Token cave
Feature activation+0.493
lion
Token lion
Feature activation+4.338
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
DNA
Token DNA
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.000
the
Token the
Feature activation+0.618
restored
Token restored
Feature activation+0.417
DNA
Token DNA
Feature activation+3.973
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.006
cave
Token cave
Feature activation+0.493
lion
Token lion
Feature activation+4.338
into
Token into
Feature activation+0.000
be
Token be
Feature activation+0.000
around
Token around
Feature activation+0.000
to
Token to
Feature activation+0.000
inject
Token inject
Feature activation+0.532
some
Token some
Feature activation+2.529
fire
Token fire
Feature activation+3.568
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
when
Token when
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
writers
Token writers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.000
science
Token science
Feature activation+3.524
into
Token into
Feature activation+0.000
their
Token their
Feature activation+0.000
work
Token work
Feature activation+0.028
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
song
Token song
Feature activation+0.000
,
Token,
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
being
Token being
Feature activation+0.000
induct
Token induct
Feature activation+0.207
ed
Tokened
Feature activation+3.510
into
Token into
Feature activation+0.639
the
Token the
Feature activation+1.232
Library
Token Library
Feature activation+0.639
of
Token of
Feature activation+0.274
Congress
Token Congress
Feature activation+1.050
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
integrated
Token integrated
Feature activation+0.000
a
Token a
Feature activation+0.401
Bitcoin
Token Bitcoin
Feature activation+1.570
wallet
Token wallet
Feature activation+3.351
into
Token into
Feature activation+0.064
our
Token our
Feature activation+0.000
system
Token system
Feature activation+0.095
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
rescent
Tokenrescent
Feature activation+0.000
shield
Token shield
Feature activation+0.000
,
Token,
Feature activation+0.000
insert
Token insert
Feature activation+0.634
it
Token it
Feature activation+3.339
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
PVC
Token PVC
Feature activation+0.000
pipe
Token pipe
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
brain
Token brain
Feature activation+0.000
integrates
Token integrates
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
sensory
Token sensory
Feature activation+0.526
cues
Token cues
Feature activation+3.326
to
Token to
Feature activation+0.297
influence
Token influence
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
induct
Token induct
Feature activation+0.000
ed
Tokened
Feature activation+3.261
as
Token as
Feature activation+2.508
members
Token members
Feature activation+1.055
of
Token of
Feature activation+0.213
a
Token a
Feature activation+0.108
team
Token team
Feature activation+1.749
simple
Token simple
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
integrate
Token integrate
Feature activation+0.168
clean
Token clean
Feature activation+0.442
ly
Tokenly
Feature activation+3.259
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
existing
Token existing
Feature activation+0.000
ways
Token ways
Feature activation+0.000
I
Token I
Feature activation+0.000
athe
Tokenathe
Feature activation+0.000
when
Token when
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
plug
Token plug
Feature activation+0.000
it
Token it
Feature activation+3.139
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.334
wrong
Token wrong
Feature activation+0.079
way
Token way
Feature activation+0.000
).
Token).
Feature activation+0.000
about
Token about
Feature activation+0.158
Powered
Token Powered
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Apocalypse
Token Apocalypse
Feature activation+1.447
games
Token games
Feature activation+3.094
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
integrate
Token integrate
Feature activation+0.000
an
Token an
Feature activation+0.000
aer
Tokenaer
Feature activation+0.000
obic
Tokenobic
Feature activation+0.000
digestion
Token digestion
Feature activation+2.990
into
Token into
Feature activation+0.000
its
Token its
Feature activation+0.000
compost
Token compost
Feature activation+0.000
ing
Tokening
Feature activation+0.000
process
Token process
Feature activation+0.272
Storm
TokenStorm
Feature activation+2.369
and
Token and
Feature activation+0.000
Vert
Token Vert
Feature activation+0.000
igo
Tokenigo
Feature activation+2.140
superhero
Token superhero
Feature activation+0.742
properties
Token properties
Feature activation+2.979
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
induct
Token induct
Feature activation+0.000
ed
Tokened
Feature activation+1.721
Kir
Token Kir
Feature activation+0.000
an
Tokenan
Feature activation+1.628
B
Token B
Feature activation+0.000
edi
Tokenedi
Feature activation+2.979
and
Token and
Feature activation+0.000
projected
Token projected
Feature activation+0.000
her
Token her
Feature activation+0.743
as
Token as
Feature activation+0.079
BJP
Token BJP
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
fit
Token fit
Feature activation+0.000
67
Token 67
Feature activation+0.000
characters
Token characters
Feature activation+2.913
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
films
Token films
Feature activation+0.000
would
Token would
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
trick
Token trick
Feature activation+0.000
the
Token the
Feature activation+0.712
immune
Token immune
Feature activation+1.141
system
Token system
Feature activation+2.881
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
approved
Token approved
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
incorporating
Token incorporating
Feature activation+0.000
live
Token live
Feature activation+0.340
visual
Token visual
Feature activation+0.482
elements
Token elements
Feature activation+2.825
into
Token into
Feature activation+0.000
my
Token my
Feature activation+0.000
sets
Token sets
Feature activation+0.000
to
Token to
Feature activation+0.000
enhance
Token enhance
Feature activation+0.000
merchants
Token merchants
Feature activation+0.000
to
Token to
Feature activation+0.000
integrate
Token integrate
Feature activation+0.018
a
Token a
Feature activation+1.268
Bitcoin
Token Bitcoin
Feature activation+1.521
wallet
Token wallet
Feature activation+2.792
into
Token into
Feature activation+0.000
their
Token their
Feature activation+0.000
shops
Token shops
Feature activation+0.061
easily
Token easily
Feature activation+0.554
.
Token.
Feature activation+0.000
around
Token around
Feature activation+0.000
and
Token and
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
transform
Token transform
Feature activation+0.000
him
Token him
Feature activation+2.746
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
linebacker
Token linebacker
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000

Top DFA by src position
MAX = 4.522

and
Token and
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+0.023
Top resid features:
may
Token may
Feature activation+0.027
Top resid features:
try
Token try
Feature activation+0.052
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
incorporate
Token incorporate
Feature activation+4.443
Top resid features:
the
Token the
Feature activation+0.084
Top resid features:
restored
Token restored
Feature activation+0.005
Top resid features:
DNA
Token DNA
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.163
Top resid features:
the
Token the
Feature activation+0.163
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
one
Token one
Feature activation+0.026
Top resid features:
may
Token may
Feature activation+0.028
Top resid features:
try
Token try
Feature activation+0.057
Top resid features:
to
Token to
Feature activation+0.061
Top resid features:
incorporate
Token incorporate
Feature activation+4.522
Top resid features:
the
Token the
Feature activation+0.071
Top resid features:
restored
Token restored
Feature activation+0.008
Top resid features:
DNA
Token DNA
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.048
Top resid features:
still
Token still
Feature activation+0.052
Top resid features:
be
Token be
Feature activation+0.019
Top resid features:
around
Token around
Feature activation-0.007
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
inject
Token inject
Feature activation+3.980
Top resid features:
some
Token some
Feature activation+0.159
Top resid features:
fire
Token fire
Feature activation+0.015
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
writers
Token writers
Feature activation-0.010
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
filmmakers
Token filmmakers
Feature activation+0.022
Top resid features:
incorporate
Token incorporate
Feature activation+4.302
Top resid features:
science
Token science
Feature activation-0.004
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
song
Token song
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
eventually
Token eventually
Feature activation+0.121
Top resid features:
being
Token being
Feature activation+0.059
Top resid features:
induct
Token induct
Feature activation+3.966
Top resid features:
ed
Tokened
Feature activation+0.020
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Library
Token Library
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
marketplace
Token marketplace
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
Malaysia
Token Malaysia
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
have
Token have
Feature activation+0.034
Top resid features:
integrated
Token integrated
Feature activation+3.597
Top resid features:
a
Token a
Feature activation+0.097
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.061
Top resid features:
wallet
Token wallet
Feature activation+0.029
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
fl
Token fl
Feature activation+0.001
Top resid features:
ou
Tokenou
Feature activation+0.007
Top resid features:
rescent
Tokenrescent
Feature activation-0.000
Top resid features:
shield
Token shield
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
insert
Token insert
Feature activation+3.981
Top resid features:
it
Token it
Feature activation+0.040
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
PVC
Token PVC
Feature activation+0.000
Top resid features:
pipe
Token pipe
Feature activation+0.000
Top resid features:
understanding
Token understanding
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
how
Token how
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
brain
Token brain
Feature activation+0.015
Top resid features:
integrates
Token integrates
Feature activation+3.611
Top resid features:
multiple
Token multiple
Feature activation+0.091
Top resid features:
sensory
Token sensory
Feature activation+0.098
Top resid features:
cues
Token cues
Feature activation+0.125
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.014
Top resid features:
aren
Token aren
Feature activation+0.058
Top resid features:
âĢ
TokenâĢ
Feature activation+0.033
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
t
Tokent
Feature activation+0.067
Top resid features:
induct
Token induct
Feature activation+3.539
Top resid features:
ed
Tokened
Feature activation+0.082
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.019
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
simple
Token simple
Feature activation-0.009
Top resid features:
enough
Token enough
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.074
Top resid features:
integrate
Token integrate
Feature activation+3.784
Top resid features:
clean
Token clean
Feature activation-0.002
Top resid features:
ly
Tokenly
Feature activation+0.025
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
existing
Token existing
Feature activation+0.000
Top resid features:
lo
Token lo
Feature activation+0.008
Top resid features:
athe
Tokenathe
Feature activation-0.023
Top resid features:
when
Token when
Feature activation+0.049
Top resid features:
trying
Token trying
Feature activation-0.017
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
plug
Token plug
Feature activation+3.754
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wrong
Token wrong
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
ground
Token ground
Feature activation+0.001
Top resid features:
up
Token up
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.031
Top resid features:
incorporate
Token incorporate
Feature activation+3.290
Top resid features:
everything
Token everything
Feature activation+0.124
Top resid features:
I
Token I
Feature activation+0.031
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
ve
Tokenve
Feature activation+0.021
Top resid features:
ess
Tokeness
Feature activation+0.001
Top resid features:
mann
Tokenmann
Feature activation+0.002
Top resid features:
Group
Token Group
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
integrate
Token integrate
Feature activation+3.640
Top resid features:
an
Token an
Feature activation+0.070
Top resid features:
aer
Tokenaer
Feature activation+0.026
Top resid features:
obic
Tokenobic
Feature activation+0.011
Top resid features:
digestion
Token digestion
Feature activation+0.005
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.008
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
its
Token its
Feature activation+0.010
Top resid features:
franchises
Token franchises
Feature activation+0.012
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
integrate
Token integrate
Feature activation+3.212
Top resid features:
its
Token its
Feature activation+0.073
Top resid features:
Wild
Token Wild
Feature activation+0.002
Top resid features:
Storm
TokenStorm
Feature activation+0.026
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
Vert
Token Vert
Feature activation+0.009
Top resid features:
against
Token against
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Delhi
Token Delhi
Feature activation-0.005
Top resid features:
BJP
Token BJP
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.091
Top resid features:
induct
Token induct
Feature activation+3.158
Top resid features:
ed
Tokened
Feature activation+0.394
Top resid features:
Kir
Token Kir
Feature activation+0.017
Top resid features:
an
Tokenan
Feature activation+0.013
Top resid features:
B
Token B
Feature activation+0.025
Top resid features:
edi
Tokenedi
Feature activation+0.012
Top resid features:
But
Token But
Feature activation+0.006
Top resid features:
finding
Token finding
Feature activation+0.068
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
way
Token way
Feature activation+0.072
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
fit
Token fit
Feature activation+3.311
Top resid features:
67
Token 67
Feature activation+0.061
Top resid features:
characters
Token characters
Feature activation+0.056
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation+0.009
Top resid features:
ability
Token ability
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
trick
Token trick
Feature activation+3.442
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
immune
Token immune
Feature activation+0.005
Top resid features:
system
Token system
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
In
TokenIn
Feature activation+0.012
Top resid features:
2010
Token 2010
Feature activation+0.011
Top resid features:
I
Token I
Feature activation+0.037
Top resid features:
started
Token started
Feature activation+0.047
Top resid features:
incorporating
Token incorporating
Feature activation+3.327
Top resid features:
live
Token live
Feature activation+0.096
Top resid features:
visual
Token visual
Feature activation+0.004
Top resid features:
elements
Token elements
Feature activation+0.069
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
enabling
Token enabling
Feature activation+0.012
Top resid features:
its
Token its
Feature activation+0.017
Top resid features:
merchants
Token merchants
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
integrate
Token integrate
Feature activation+3.334
Top resid features:
a
Token a
Feature activation+0.115
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.009
Top resid features:
wallet
Token wallet
Feature activation+0.010
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.001
Top resid features:
around
Token around
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
tried
Token tried
Feature activation+0.042
Top resid features:
to
Token to
Feature activation+0.075
Top resid features:
transform
Token transform
Feature activation+3.399
Top resid features:
him
Token him
Feature activation+0.032
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
linebacker
Token linebacker
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.03

Head 3: 0.03

Head 4: 0.59

Head 5: 0.06

Head 6: 0.01

Head 7: 0.07

Head 8: 0.05

Head 9: 0.03

Head 10: 0.07

Head 11: 0.02

Positive logits

into7.02

into5.89

Into5.75

INTO5.61

onto4.58

overboard2.44

aneously2.34

seamlessly2.26

deeper2.23

ression2.14

prise2.06

tion2.00

unto1.98

onto1.94

untarily1.90

shit1.90

inement1.87

therein1.85

away1.85

toward1.84

Negative logits

rall-2.16

Examiner-1.88

ranged-1.72

pport-1.71

vertisement-1.67

Featured-1.58

asin-1.53

expected-1.52

conduc-1.52

persecuted-1.52

icult-1.50

ghazi-1.50

iannopoulos-1.48

Appeal-1.48

baugh-1.47

prevailed-1.47

Uncommon-1.46

Tanz-1.46

praying-1.45

aird-1.43

INTERVAL 3.904 - 4.338
CONTAINS 0.000%

try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.000
the
Token the
Feature activation+0.618
restored
Token restored
Feature activation+0.417
DNA
Token DNA
Feature activation+3.973
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.006
cave
Token cave
Feature activation+0.493
lion
Token lion
Feature activation+4.338
into
Token into
Feature activation+0.000
restored
Token restored
Feature activation+0.417
DNA
Token DNA
Feature activation+3.973
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.006
cave
Token cave
Feature activation+0.493
lion
Token lion
Feature activation+4.338
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
DNA
Token DNA
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.470 - 3.904
CONTAINS 0.000%

writers
Token writers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.000
science
Token science
Feature activation+3.524
into
Token into
Feature activation+0.000
their
Token their
Feature activation+0.000
work
Token work
Feature activation+0.028
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
around
Token around
Feature activation+0.000
to
Token to
Feature activation+0.000
inject
Token inject
Feature activation+0.532
some
Token some
Feature activation+2.529
fire
Token fire
Feature activation+3.568
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
when
Token when
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
song
Token song
Feature activation+0.000
,
Token,
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
being
Token being
Feature activation+0.000
induct
Token induct
Feature activation+0.207
ed
Tokened
Feature activation+3.510
into
Token into
Feature activation+0.639
the
Token the
Feature activation+1.232
Library
Token Library
Feature activation+0.639
of
Token of
Feature activation+0.274
Congress
Token Congress
Feature activation+1.050

INTERVAL 3.037 - 3.470
CONTAINS 0.001%

about
Token about
Feature activation+0.158
Powered
Token Powered
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Apocalypse
Token Apocalypse
Feature activation+1.447
games
Token games
Feature activation+3.094
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
you
Token you
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
induct
Token induct
Feature activation+0.000
ed
Tokened
Feature activation+3.261
as
Token as
Feature activation+2.508
members
Token members
Feature activation+1.055
of
Token of
Feature activation+0.213
a
Token a
Feature activation+0.108
team
Token team
Feature activation+1.749
the
Token the
Feature activation+0.000
brain
Token brain
Feature activation+0.000
integrates
Token integrates
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
sensory
Token sensory
Feature activation+0.526
cues
Token cues
Feature activation+3.326
to
Token to
Feature activation+0.297
influence
Token influence
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
athe
Tokenathe
Feature activation+0.000
when
Token when
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
plug
Token plug
Feature activation+0.000
it
Token it
Feature activation+3.139
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.334
wrong
Token wrong
Feature activation+0.079
way
Token way
Feature activation+0.000
).
Token).
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
integrated
Token integrated
Feature activation+0.000
a
Token a
Feature activation+0.401
Bitcoin
Token Bitcoin
Feature activation+1.570
wallet
Token wallet
Feature activation+3.351
into
Token into
Feature activation+0.064
our
Token our
Feature activation+0.000
system
Token system
Feature activation+0.095
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 2.603 - 3.037
CONTAINS 0.002%

a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
fit
Token fit
Feature activation+0.000
67
Token 67
Feature activation+0.000
characters
Token characters
Feature activation+2.913
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
films
Token films
Feature activation+0.000
would
Token would
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
trick
Token trick
Feature activation+0.000
the
Token the
Feature activation+0.712
immune
Token immune
Feature activation+1.141
system
Token system
Feature activation+2.881
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
approved
Token approved
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
incorporating
Token incorporating
Feature activation+0.000
live
Token live
Feature activation+0.340
visual
Token visual
Feature activation+0.482
elements
Token elements
Feature activation+2.825
into
Token into
Feature activation+0.000
my
Token my
Feature activation+0.000
sets
Token sets
Feature activation+0.000
to
Token to
Feature activation+0.000
enhance
Token enhance
Feature activation+0.000
to
Token to
Feature activation+0.000
integrate
Token integrate
Feature activation+0.000
an
Token an
Feature activation+0.000
aer
Tokenaer
Feature activation+0.000
obic
Tokenobic
Feature activation+0.000
digestion
Token digestion
Feature activation+2.990
into
Token into
Feature activation+0.000
its
Token its
Feature activation+0.000
compost
Token compost
Feature activation+0.000
ing
Tokening
Feature activation+0.000
process
Token process
Feature activation+0.272
induct
Token induct
Feature activation+0.000
ed
Tokened
Feature activation+1.721
Kir
Token Kir
Feature activation+0.000
an
Tokenan
Feature activation+1.628
B
Token B
Feature activation+0.000
edi
Tokenedi
Feature activation+2.979
and
Token and
Feature activation+0.000
projected
Token projected
Feature activation+0.000
her
Token her
Feature activation+0.743
as
Token as
Feature activation+0.079
BJP
Token BJP
Feature activation+0.000

INTERVAL 2.169 - 2.603
CONTAINS 0.003%

-
Token-
Feature activation+0.000
designed
Tokendesigned
Feature activation+0.000
buildings
Token buildings
Feature activation+1.851
in
Token in
Feature activation+0.047
the
Token the
Feature activation+0.000
District
Token District
Feature activation+2.288
to
Token to
Feature activation+0.946
net
Token net
Feature activation+0.000
zero
Token zero
Feature activation+0.000
energy
Token energy
Feature activation+0.000
,
Token,
Feature activation+0.000
franchises
Token franchises
Feature activation+0.417
,
Token,
Feature activation+0.000
integrate
Token integrate
Feature activation+0.021
its
Token its
Feature activation+1.713
Wild
Token Wild
Feature activation+0.000
Storm
TokenStorm
Feature activation+2.369
and
Token and
Feature activation+0.000
Vert
Token Vert
Feature activation+0.000
igo
Tokenigo
Feature activation+2.140
superhero
Token superhero
Feature activation+0.742
properties
Token properties
Feature activation+2.979
reading
Token reading
Feature activation+0.000
,
Token,
Feature activation+0.000
lets
Token lets
Feature activation+0.000
trans
Token trans
Feature activation+0.000
pose
Tokenpose
Feature activation+0.408
this
Token this
Feature activation+2.438
whole
Token whole
Feature activation+0.036
chat
Token chat
Feature activation+1.654
into
Token into
Feature activation+0.056
books
Token books
Feature activation+0.000
.
Token.
Feature activation+0.000
still
Token still
Feature activation+0.000
be
Token be
Feature activation+0.000
around
Token around
Feature activation+0.000
to
Token to
Feature activation+0.000
inject
Token inject
Feature activation+0.532
some
Token some
Feature activation+2.529
fire
Token fire
Feature activation+3.568
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
when
Token when
Feature activation+0.000
argued
Token argued
Feature activation+0.000
in
Token in
Feature activation+0.000
favour
Token favour
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
integration
Token integration
Feature activation+2.209
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
LGBTQ
Token LGBTQ
Feature activation+0.000
community
Token community
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.735 - 2.169
CONTAINS 0.004%

transformation
Token transformation
Feature activation+0.000
of
Token of
Feature activation+0.241
her
Token her
Feature activation+0.673
daughter
Token daughter
Feature activation+1.692
Princess
Token Princess
Feature activation+0.129
Elizabeth
Token Elizabeth
Feature activation+1.972
from
Token from
Feature activation+0.000
girl
Token girl
Feature activation+0.000
to
Token to
Feature activation+0.000
young
Token young
Feature activation+0.000
woman
Token woman
Feature activation+0.135
ing
Tokening
Feature activation+0.869
his
Token his
Feature activation+0.237
center
Token center
Feature activation+0.247
-
Token-
Feature activation+0.000
right
Tokenright
Feature activation+0.892
party
Token party
Feature activation+1.968
back
Token back
Feature activation+0.575
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
spotlight
Token spotlight
Feature activation+0.000
amid
Token amid
Feature activation+0.000
incorporate
Token incorporate
Feature activation+0.000
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+1.949
within
Token within
Feature activation+0.000
your
Token your
Feature activation+0.000
project
Token project
Feature activation+0.000
and
Token and
Feature activation+0.000
use
Token use
Feature activation+0.000
to
Token to
Feature activation+0.000
import
Token import
Feature activation+0.000
products
Token products
Feature activation+1.372
duty
Token duty
Feature activation+0.000
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+1.751
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
now
Token now
Feature activation+0.000
it
Token it
Feature activation+0.000
appears
Token appears
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
escalation
Token escalation
Feature activation+0.000
could
Token could
Feature activation+0.000
morph
Token morph
Feature activation+0.913
by
Token by
Feature activation+0.000
design
Token design
Feature activation+1.929
or
Token or
Feature activation+0.000
inadvert
Token inadvert
Feature activation+0.000
ence
Tokenence
Feature activation+2.541
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.301 - 1.735
CONTAINS 0.009%

Sl
Token Sl
Feature activation+0.000
ipping
Tokenipping
Feature activation+0.349
a
Token a
Feature activation+0.510
DRM
Token DRM
Feature activation+0.557
delivery
Token delivery
Feature activation+0.339
mechanism
Token mechanism
Feature activation+1.336
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
HTML
Token HTML
Feature activation+0.000
5
Token5
Feature activation+0.000
standard
Token standard
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
,
Token,
Feature activation+0.000
yard
Token yard
Feature activation+0.000
tr
Token tr
Feature activation+0.000
imm
Tokenimm
Feature activation+0.000
ings
Tokenings
Feature activation+1.667
,
Token,
Feature activation+0.000
food
Token food
Feature activation+0.000
waste
Token waste
Feature activation+1.581
and
Token and
Feature activation+0.000
wood
Token wood
Feature activation+0.942
learned
Token learned
Feature activation+1.396
about
Token about
Feature activation+0.158
Powered
Token Powered
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Apocalypse
Token Apocalypse
Feature activation+1.447
games
Token games
Feature activation+3.094
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
lets
Token lets
Feature activation+0.000
trans
Token trans
Feature activation+0.000
pose
Tokenpose
Feature activation+0.408
this
Token this
Feature activation+2.438
whole
Token whole
Feature activation+0.036
chat
Token chat
Feature activation+1.654
into
Token into
Feature activation+0.056
books
Token books
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
The
TokenThe
Feature activation+0.000
other
Token other
Feature activation+0.000
option
Token option
Feature activation+0.000
translated
Token translated
Feature activation+0.000
in
Token in
Feature activation+0.000
English
Token English
Feature activation+1.379
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
land
Token land
Feature activation+0.000

INTERVAL 0.868 - 1.301
CONTAINS 0.021%

cing
Tokencing
Feature activation+0.057
tam
Token tam
Feature activation+0.000
per
Tokenper
Feature activation+0.000
-
Token-
Feature activation+0.000
proof
Tokenproof
Feature activation+0.099
ing
Tokening
Feature activation+0.995
was
Token was
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
considered
Token considered
Feature activation+0.000
still
Token still
Feature activation+0.000
pumping
Token pumping
Feature activation+0.000
all
Token all
Feature activation+0.008
donation
Token donation
Feature activation+0.156
/
Token /
Feature activation+0.000
subscriber
Token subscriber
Feature activation+0.931
income
Token income
Feature activation+0.769
into
Token into
Feature activation+0.000
putting
Token putting
Feature activation+0.000
on
Token on
Feature activation+0.000
more
Token more
Feature activation+0.000
how
Token how
Feature activation+0.000
accepting
Token accepting
Feature activation+0.000
people
Token people
Feature activation+0.342
have
Token have
Feature activation+0.773
generally
Token generally
Feature activation+0.584
been
Token been
Feature activation+1.067
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
this
Token this
Feature activation+0.000
odd
Token odd
Feature activation+0.000
use
Token use
Feature activation+0.000
in
Token in
Feature activation+0.000
embed
Token embed
Feature activation+0.000
ding
Tokending
Feature activation+0.994
PowerShell
Token PowerShell
Feature activation+0.876
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
registry
Token registry
Feature activation+0.000
in
Token in
Feature activation+0.000
spl
Token spl
Feature activation+0.000
inter
Tokeninter
Feature activation+0.000
ing
Tokening
Feature activation+1.153
of
Token of
Feature activation+1.013
family
Token family
Feature activation+0.824
residences
Token residences
Feature activation+1.059
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
hope
Token hope
Feature activation+0.000

INTERVAL 0.434 - 0.868
CONTAINS 0.068%

used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
force
Token force
Feature activation+0.000
-
Token-
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
us
Token us
Feature activation+0.563
global
Token global
Feature activation+0.000
warming
Token warming
Feature activation+0.000
.
Token.
Feature activation+0.000
Carbon
Token Carbon
Feature activation+0.000
D
Token D
Feature activation+0.000
seems
Token seems
Feature activation+0.000
criminals
Token criminals
Feature activation+0.000
have
Token have
Feature activation+0.000
managed
Token managed
Feature activation+0.000
to
Token to
Feature activation+0.000
slip
Token slip
Feature activation+0.806
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
net
Token net
Feature activation+0.000
as
Token as
Feature activation+0.000
since
Token since
Feature activation+0.000
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
6
Token6
Feature activation+0.000
$.
Token$.
Feature activation+0.000
Feed
Token Feed
Feature activation+0.000
this
Token this
Feature activation+0.703
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
Eval
Token Eval
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
DRM
Token DRM
Feature activation+0.000
.
Token.
Feature activation+0.000
Sl
Token Sl
Feature activation+0.000
ipping
Tokenipping
Feature activation+0.349
a
Token a
Feature activation+0.510
DRM
Token DRM
Feature activation+0.557
delivery
Token delivery
Feature activation+0.339
mechanism
Token mechanism
Feature activation+1.336
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
HTML
Token HTML
Feature activation+0.000
ired
Tokenired
Feature activation+0.000
fans
Token fans
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
forced
Token forced
Feature activation+0.000
him
Token him
Feature activation+0.447
to
Token to
Feature activation+0.000
post
Token post
Feature activation+0.000
this
Token this
Feature activation+0.000
on
Token on
Feature activation+0.000
Instagram
Token Instagram
Feature activation+0.000

INTERVAL 0.000 - 0.434
CONTAINS 99.893%

James
Token James
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
script
Token script
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Battle
Token Battle
Feature activation+0.000
of
Token of
Feature activation+0.000
Al
Token Al
Feature activation+0.000
cat
Tokencat
Feature activation+0.000
monster
Tokenmonster
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
had
Token had
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
y
Tokeny
Feature activation+0.000
l
Token l
Feature activation+0.000
party
Token party
Feature activation+0.000
documents
Token documents
Feature activation+0.000
single
Token single
Feature activation+0.000
out
Token out
Feature activation+0.000
churches
Token churches
Feature activation+0.000
and
Token and
Feature activation+0.000
folk
Token folk
Feature activation+0.000
religious
Token religious
Feature activation+0.000
sites
Token sites
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
planning
Token planning
Feature activation+0.000
on
Token on
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
either
Token either
Feature activation+0.000
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
woman
Token woman
Feature activation+0.000
to
Token to
Feature activation+0.000
win
Token win
Feature activation+0.000
the
Token the
Feature activation+0.000
convention
Token convention
Feature activation+0.000
votes
Token votes
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
claim
Token claim
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 H8.4: (feature 20055)

TOP ACTIVATIONS
MAX = 7.193

lawmakers
Token lawmakers
Feature activation+0.000
for
Token for
Feature activation+0.000
failing
Token failing
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
banks
Token banks
Feature activation+7.193
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
discipl
Token discipl
Feature activation+0.000
in
Tokenin
Feature activation+0.000
arian
Tokenarian
Feature activation+0.000
or
Token or
Feature activation+0.000
hold
Token hold
Feature activation+0.000
them
Token them
Feature activation+7.094
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
That
Token That
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
I
Token I
Feature activation+0.000
hold
Token hold
Feature activation+0.000
them
Token them
Feature activation+6.536
accountable
Token accountable
Feature activation+0.000
.
Token.
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
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
involved
Token involved
Feature activation+0.000
is
Token is
Feature activation+0.000
held
Token held
Feature activation+4.008
fully
Token fully
Feature activation+6.387
accountable
Token accountable
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
force
Token force
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+3.121
stories
Token stories
Feature activation+3.549
and
Token and
Feature activation+0.681
the
Token the
Feature activation+0.922
suffering
Token suffering
Feature activation+6.360
and
Token and
Feature activation+1.397
the
Token the
Feature activation+0.373
sorry
Token sorry
Feature activation+0.000
of
Token of
Feature activation+0.000
children
Token children
Feature activation+4.932
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
men
Token men
Feature activation+0.000
had
Token had
Feature activation+0.000
held
Token held
Feature activation+0.000
her
Token her
Feature activation+6.355
hands
Token hands
Feature activation+1.513
and
Token and
Feature activation+0.000
pulled
Token pulled
Feature activation+0.000
her
Token her
Feature activation+0.000
hair
Token hair
Feature activation+0.000
God
Token God
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
will
Tokenwill
Feature activation+0.000
hold
Token hold
Feature activation+0.000
us
Token us
Feature activation+6.313
accountable
Token accountable
Feature activation+0.000
to
Token to
Feature activation+0.000
think
Token think
Feature activation+0.000
deeply
Token deeply
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Hick
Token Hick
Feature activation+0.000
man
Tokenman
Feature activation+0.000
held
Token held
Feature activation+0.000
the
Token the
Feature activation+0.614
officer
Token officer
Feature activation+6.312
down
Token down
Feature activation+0.199
while
Token while
Feature activation+0.000
Casey
Token Casey
Feature activation+0.000
kicked
Token kicked
Feature activation+0.000
him
Token him
Feature activation+0.000
were
Token were
Feature activation+0.000
sexually
Token sexually
Feature activation+0.000
abused
Token abused
Feature activation+5.021
by
Token by
Feature activation+0.000
priests
Token priests
Feature activation+0.246
deep
Token deep
Feature activation+6.229
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
heart
Token heart
Feature activation+1.841
,
Token,
Feature activation+4.326
âĢ
TokenâĢ
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
people
Token people
Feature activation+6.066
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
idea
Token idea
Feature activation+0.000
is
Token is
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
them
Token them
Feature activation+6.015
accountable
Token accountable
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
strong
Token strong
Feature activation+0.000
forces
Token forces
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
Australian
Token Australian
Feature activation+0.776
dollar
Token dollar
Feature activation+5.632
in
Token in
Feature activation+3.544
the
Token the
Feature activation+0.553
range
Token range
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.170
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
faces
Token faces
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
driver
Token driver
Feature activation+5.414
's
Token's
Feature activation+1.332
door
Token door
Feature activation+4.963
open
Token open
Feature activation+0.482
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
held
Token held
Feature activation+0.000
himself
Token himself
Feature activation+5.370
up
Token up
Feature activation+0.000
on
Token on
Feature activation+0.000
cr
Token cr
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
ches
Tokenches
Feature activation+0.000
of
Token of
Feature activation+0.000
children
Token children
Feature activation+4.932
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
sexually
Token sexually
Feature activation+0.000
abused
Token abused
Feature activation+5.021
by
Token by
Feature activation+0.000
priests
Token priests
Feature activation+0.246
deep
Token deep
Feature activation+6.229
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
faces
Token faces
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
driver
Token driver
Feature activation+5.414
's
Token's
Feature activation+1.332
door
Token door
Feature activation+4.963
open
Token open
Feature activation+0.482
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Little
TokenLittle
Feature activation+0.000
suffering
Token suffering
Feature activation+6.360
and
Token and
Feature activation+1.397
the
Token the
Feature activation+0.373
sorry
Token sorry
Feature activation+0.000
of
Token of
Feature activation+0.000
children
Token children
Feature activation+4.932
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
sexually
Token sexually
Feature activation+0.000
abused
Token abused
Feature activation+5.021
by
Token by
Feature activation+0.000
our
Token our
Feature activation+0.000
committee
Token committee
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+4.913
accountable
Token accountable
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
actions
Token actions
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fabric
Token fabric
Feature activation+0.000
that
Token that
Feature activation+0.000
holds
Token holds
Feature activation+0.000
this
Token this
Feature activation+2.228
community
Token community
Feature activation+4.852
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
governments
Token governments
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
held
Token held
Feature activation+3.923
more
Token more
Feature activation+4.835
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
El
TokenEl
Feature activation+0.000

Top DFA by src position
MAX = 8.419

.
Token.
Feature activation+0.002
Top resid features:
lawmakers
Token lawmakers
Feature activation+0.016
Top resid features:
for
Token for
Feature activation+0.048
Top resid features:
failing
Token failing
Feature activation+0.042
Top resid features:
to
Token to
Feature activation+0.170
Top resid features:
hold
Token hold
Feature activation+8.419
Top resid features:
banks
Token banks
Feature activation+0.061
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
discipl
Token discipl
Feature activation-0.004
Top resid features:
in
Tokenin
Feature activation-0.007
Top resid features:
arian
Tokenarian
Feature activation-0.026
Top resid features:
or
Token or
Feature activation+0.099
Top resid features:
hold
Token hold
Feature activation+8.360
Top resid features:
them
Token them
Feature activation+0.043
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
At
Token At
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
same
Token same
Feature activation+0.005
Top resid features:
time
Token time
Feature activation+0.055
Top resid features:
I
Token I
Feature activation+0.063
Top resid features:
hold
Token hold
Feature activation+7.859
Top resid features:
them
Token them
Feature activation+0.100
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
.
Token.
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:
anybody
Token anybody
Feature activation-0.017
Top resid features:
who
Token who
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
involved
Token involved
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.051
Top resid features:
held
Token held
Feature activation+7.530
Top resid features:
fully
Token fully
Feature activation+0.180
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
full
Token full
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.216
Top resid features:
âĢ
TokenâĢ
Feature activation+0.066
Top resid features:
ľ
Tokenľ
Feature activation-0.017
Top resid features:
I
TokenI
Feature activation-0.004
Top resid features:
hold
Token hold
Feature activation+7.002
Top resid features:
the
Token the
Feature activation+0.588
Top resid features:
stories
Token stories
Feature activation+0.153
Top resid features:
and
Token and
Feature activation+0.120
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
suffering
Token suffering
Feature activation-0.070
Top resid features:
some
Token some
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
men
Token men
Feature activation+0.014
Top resid features:
had
Token had
Feature activation+0.046
Top resid features:
held
Token held
Feature activation+7.444
Top resid features:
her
Token her
Feature activation+0.080
Top resid features:
hands
Token hands
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
pulled
Token pulled
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.071
Top resid features:
God
Token God
Feature activation+0.013
Top resid features:
âĢ
Token âĢ
Feature activation+0.029
Top resid features:
ľ
Tokenľ
Feature activation+0.006
Top resid features:
will
Tokenwill
Feature activation+0.006
Top resid features:
hold
Token hold
Feature activation+7.723
Top resid features:
us
Token us
Feature activation+0.045
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
deeply
Token deeply
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.028
Top resid features:
him
Token him
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
Hick
Token Hick
Feature activation+0.004
Top resid features:
man
Tokenman
Feature activation+0.001
Top resid features:
held
Token held
Feature activation+7.506
Top resid features:
the
Token the
Feature activation+0.168
Top resid features:
officer
Token officer
Feature activation+0.103
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
Casey
Token Casey
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.389
Top resid features:
âĢ
TokenâĢ
Feature activation+0.038
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
I
TokenI
Feature activation+0.026
Top resid features:
hold
Token hold
Feature activation+7.197
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
stories
Token stories
Feature activation+0.127
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
suffering
Token suffering
Feature activation-0.023
Top resid features:
tutorial
Token tutorial
Feature activation-0.137
Top resid features:
will
Token will
Feature activation+0.010
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
enough
Token enough
Feature activation-0.025
Top resid features:
to
Token to
Feature activation+0.056
Top resid features:
hold
Token hold
Feature activation+7.783
Top resid features:
people
Token people
Feature activation+0.043
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
m
Tokenm
Feature activation-0.001
Top resid features:
going
Token going
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
hold
Token hold
Feature activation+7.459
Top resid features:
them
Token them
Feature activation+0.089
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
few
Token few
Feature activation+0.019
Top resid features:
strong
Token strong
Feature activation+0.027
Top resid features:
forces
Token forces
Feature activation+0.029
Top resid features:
holding
Token holding
Feature activation+6.526
Top resid features:
the
Token the
Feature activation+0.161
Top resid features:
Australian
Token Australian
Feature activation+0.035
Top resid features:
dollar
Token dollar
Feature activation+0.163
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
get
Token get
Feature activation-0.038
Top resid features:
out
Token out
Feature activation-0.025
Top resid features:
of
Token of
Feature activation-0.023
Top resid features:
their
Token their
Feature activation+0.006
Top resid features:
faces
Token faces
Feature activation+0.070
Top resid features:
holding
Token holding
Feature activation+6.765
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
driver
Token driver
Feature activation+0.063
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
door
Token door
Feature activation+0.000
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
relationship
Token relationship
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.018
Top resid features:
Even
TokenEven
Feature activation+0.012
Top resid features:
as
Token as
Feature activation+0.105
Top resid features:
he
Token he
Feature activation+0.018
Top resid features:
held
Token held
Feature activation+6.423
Top resid features:
himself
Token himself
Feature activation+0.232
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
cr
Token cr
Feature activation+0.000
Top resid features:
ut
Tokenut
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.373
Top resid features:
âĢ
TokenâĢ
Feature activation+0.027
Top resid features:
ľ
Tokenľ
Feature activation-0.018
Top resid features:
I
TokenI
Feature activation-0.012
Top resid features:
hold
Token hold
Feature activation+5.667
Top resid features:
the
Token the
Feature activation+0.232
Top resid features:
stories
Token stories
Feature activation+0.126
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
suffering
Token suffering
Feature activation+0.013
Top resid features:
get
Token get
Feature activation-0.021
Top resid features:
out
Token out
Feature activation-0.008
Top resid features:
of
Token of
Feature activation-0.008
Top resid features:
their
Token their
Feature activation-0.001
Top resid features:
faces
Token faces
Feature activation+0.044
Top resid features:
holding
Token holding
Feature activation+5.966
Top resid features:
the
Token the
Feature activation+0.229
Top resid features:
driver
Token driver
Feature activation+0.084
Top resid features:
's
Token's
Feature activation+0.112
Top resid features:
door
Token door
Feature activation+0.081
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.331
Top resid features:
âĢ
TokenâĢ
Feature activation+0.036
Top resid features:
ľ
Tokenľ
Feature activation-0.009
Top resid features:
I
TokenI
Feature activation-0.008
Top resid features:
hold
Token hold
Feature activation+5.722
Top resid features:
the
Token the
Feature activation+0.457
Top resid features:
stories
Token stories
Feature activation+0.098
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
suffering
Token suffering
Feature activation+0.017
Top resid features:
emergency
Token emergency
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
our
Token our
Feature activation+0.031
Top resid features:
committee
Token committee
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.062
Top resid features:
hold
Token hold
Feature activation+5.902
Top resid features:
the
Token the
Feature activation+0.169
Top resid features:
president
Token president
Feature activation+0.093
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
tear
Token tear
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.027
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
fabric
Token fabric
Feature activation+0.026
Top resid features:
that
Token that
Feature activation+0.031
Top resid features:
holds
Token holds
Feature activation+6.203
Top resid features:
this
Token this
Feature activation+0.111
Top resid features:
community
Token community
Feature activation+0.060
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Nations
Token Nations
Feature activation-0.000
Top resid features:
governments
Token governments
Feature activation-0.006
Top resid features:
need
Token need
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation-0.012
Top resid features:
held
Token held
Feature activation+6.159
Top resid features:
more
Token more
Feature activation+0.101
Top resid features:
accountable
Token accountable
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.03

Head 3: 0.02

Head 4: 0.58

Head 5: 0.06

Head 6: 0.02

Head 7: 0.10

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

accountable3.55

hostage2.82

ransom2.55

responsible2.37

respons2.28

liable2.16

ependent2.07

captive2.00

sacred1.96

together1.92

culp1.92

LIA1.91

responsible1.91

alone1.86

judgement1.81

amped1.80

cogn1.80

hostages1.77

Narr1.76

guilty1.73

Negative logits

clus-2.15

reach-2.15

Finish-1.96

become-1.95

hya-1.90

populate-1.87

pta-1.86

arrive-1.84

procure-1.81

dos-1.81

reach-1.81

abbre-1.81

fters-1.79

come-1.79

traverse-1.75

soon-1.74

write-1.73

gans-1.73

Finish-1.72

failed-1.71

INTERVAL 6.474 - 7.193
CONTAINS 0.000%

discipl
Token discipl
Feature activation+0.000
in
Tokenin
Feature activation+0.000
arian
Tokenarian
Feature activation+0.000
or
Token or
Feature activation+0.000
hold
Token hold
Feature activation+0.000
them
Token them
Feature activation+7.094
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
That
Token That
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
I
Token I
Feature activation+0.000
hold
Token hold
Feature activation+0.000
them
Token them
Feature activation+6.536
accountable
Token accountable
Feature activation+0.000
.
Token.
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
lawmakers
Token lawmakers
Feature activation+0.000
for
Token for
Feature activation+0.000
failing
Token failing
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
banks
Token banks
Feature activation+7.193
accountable
Token accountable
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000

INTERVAL 5.755 - 6.474
CONTAINS 0.001%

will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
people
Token people
Feature activation+6.066
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
idea
Token idea
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
Hick
Token Hick
Feature activation+0.000
man
Tokenman
Feature activation+0.000
held
Token held
Feature activation+0.000
the
Token the
Feature activation+0.614
officer
Token officer
Feature activation+6.312
down
Token down
Feature activation+0.199
while
Token while
Feature activation+0.000
Casey
Token Casey
Feature activation+0.000
kicked
Token kicked
Feature activation+0.000
him
Token him
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
involved
Token involved
Feature activation+0.000
is
Token is
Feature activation+0.000
held
Token held
Feature activation+4.008
fully
Token fully
Feature activation+6.387
accountable
Token accountable
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
force
Token force
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+3.121
stories
Token stories
Feature activation+3.549
and
Token and
Feature activation+0.681
the
Token the
Feature activation+0.922
suffering
Token suffering
Feature activation+6.360
and
Token and
Feature activation+1.397
the
Token the
Feature activation+0.373
sorry
Token sorry
Feature activation+0.000
of
Token of
Feature activation+0.000
children
Token children
Feature activation+4.932
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
them
Token them
Feature activation+6.015
accountable
Token accountable
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 5.035 - 5.755
CONTAINS 0.001%

strong
Token strong
Feature activation+0.000
forces
Token forces
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
Australian
Token Australian
Feature activation+0.776
dollar
Token dollar
Feature activation+5.632
in
Token in
Feature activation+3.544
the
Token the
Feature activation+0.553
range
Token range
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.170
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
faces
Token faces
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
driver
Token driver
Feature activation+5.414
's
Token's
Feature activation+1.332
door
Token door
Feature activation+4.963
open
Token open
Feature activation+0.482
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
held
Token held
Feature activation+0.000
himself
Token himself
Feature activation+5.370
up
Token up
Feature activation+0.000
on
Token on
Feature activation+0.000
cr
Token cr
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
ches
Tokenches
Feature activation+0.000

INTERVAL 4.316 - 5.035
CONTAINS 0.001%

our
Token our
Feature activation+0.000
committee
Token committee
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+4.913
accountable
Token accountable
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
actions
Token actions
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
Fres
Token Fres
Feature activation+0.000
cas
Tokencas
Feature activation+0.000
held
Token held
Feature activation+0.000
the
Token the
Feature activation+1.074
gun
Token gun
Feature activation+4.317
at
Token at
Feature activation+1.824
one
Token one
Feature activation+0.725
point
Token point
Feature activation+1.346
,
Token,
Feature activation+0.405
but
Token but
Feature activation+0.000
priests
Token priests
Feature activation+0.246
deep
Token deep
Feature activation+6.229
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
heart
Token heart
Feature activation+1.841
,
Token,
Feature activation+4.326
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Francis
Token Francis
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fabric
Token fabric
Feature activation+0.000
that
Token that
Feature activation+0.000
holds
Token holds
Feature activation+0.000
this
Token this
Feature activation+2.228
community
Token community
Feature activation+4.852
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sheep
Token sheep
Feature activation+0.000
's
Token's
Feature activation+0.000
head
Token head
Feature activation+0.000
and
Token and
Feature activation+0.000
held
Token held
Feature activation+0.000
it
Token it
Feature activation+4.317
in
Token in
Feature activation+1.234
the
Token the
Feature activation+0.202
air
Token air
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 3.597 - 4.316
CONTAINS 0.002%

currently
Token currently
Feature activation+0.000
holding
Token holding
Feature activation+0.000
about
Token about
Feature activation+0.000
130
Token 130
Feature activation+0.000
crew
Token crew
Feature activation+0.654
members
Token members
Feature activation+4.312
hostage
Token hostage
Feature activation+0.000
on
Token on
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
seven
Token seven
Feature activation+0.000
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
former
Token former
Feature activation+0.000
officials
Token officials
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+3.850
accountable
Token accountable
Feature activation+0.000
for
Token for
Feature activation+0.000
past
Token past
Feature activation+0.000
failures
Token failures
Feature activation+0.000
,
Token,
Feature activation+0.000
pa
Tokenpa
Feature activation+0.000
Sales
Token Sales
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
been
Token been
Feature activation+0.000
held
Token held
Feature activation+3.966
responsible
Token responsible
Feature activation+0.000
for
Token for
Feature activation+0.000
disrupting
Token disrupting
Feature activation+0.000
deliveries
Token deliveries
Feature activation+0.000
over
Token over
Feature activation+0.000
anybody
Token anybody
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
involved
Token involved
Feature activation+0.000
is
Token is
Feature activation+0.000
held
Token held
Feature activation+4.008
fully
Token fully
Feature activation+6.387
accountable
Token accountable
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
are
Token are
Feature activation+0.000
holding
Token holding
Feature activation+0.000
thousands
Token thousands
Feature activation+1.554
of
Token of
Feature activation+0.299
political
Token political
Feature activation+0.160
separatists
Token separatists
Feature activation+4.286
without
Token without
Feature activation+0.000
charge
Token charge
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
New
Token New
Feature activation+0.000

INTERVAL 2.877 - 3.597
CONTAINS 0.002%

.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.106
Senate
Token Senate
Feature activation+3.089
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
better
Token better
Feature activation+0.000
win
Token win
Feature activation+0.000
Missouri
Token Missouri
Feature activation+0.000
remain
Token remain
Feature activation+0.000
committed
Token committed
Feature activation+0.000
to
Token to
Feature activation+0.000
holding
Token holding
Feature activation+0.000
this
Token this
Feature activation+1.840
dialogue
Token dialogue
Feature activation+3.544
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
'll
Token'll
Feature activation+0.000
look
Token look
Feature activation+0.000
for
Token for
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
held
Token held
Feature activation+0.000
my
Token my
Feature activation+3.388
attention
Token attention
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
better
Token better
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.481
Senate
Token Senate
Feature activation+3.174
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.106
is
Token is
Feature activation+0.000
jumping
Token jumping
Feature activation+0.000
and
Token and
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
is
Token is
Feature activation+0.000
held
Token held
Feature activation+2.898
up
Token up
Feature activation+0.000
by
Token by
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ped
Tokenped
Feature activation+0.000

INTERVAL 2.158 - 2.877
CONTAINS 0.002%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fabric
Token fabric
Feature activation+0.000
that
Token that
Feature activation+0.000
holds
Token holds
Feature activation+0.000
this
Token this
Feature activation+2.228
community
Token community
Feature activation+4.852
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
hang
Token hang
Feature activation+0.000
men
Tokenmen
Feature activation+0.000
were
Token were
Feature activation+0.000
held
Token held
Feature activation+2.805
to
Token to
Feature activation+2.757
implicitly
Token implicitly
Feature activation+0.000
forb
Token forb
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
held
Token held
Feature activation+2.202
responsible
Token responsible
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
because
Token because
Feature activation+0.000
or
Token or
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
Walker
Token Walker
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+2.634
accountable
Token accountable
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
death
Token death
Feature activation+0.000
he
Token he
Feature activation+0.000
move
Token move
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+2.186
against
Token against
Feature activation+0.000
their
Token their
Feature activation+0.000
will
Token will
Feature activation+2.390
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.439 - 2.158
CONTAINS 0.002%

prison
Token prison
Feature activation+0.000
companies
Token companies
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
held
Token held
Feature activation+0.000
shares
Token shares
Feature activation+1.717
in
Token in
Feature activation+0.000
or
Token or
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+0.000
group
Token group
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
holding
Token holding
Feature activation+0.000
Shal
Token Shal
Feature activation+0.000
it
Tokenit
Feature activation+1.578
hostage
Token hostage
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
reass
Token reass
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
cops
Token cops
Feature activation+0.000
not
Token not
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+1.952
accountable
Token accountable
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
s
Tokens
Feature activation+0.000
security
Token security
Feature activation+0.000
forces
Token forces
Feature activation+0.000
are
Token are
Feature activation+0.000
holding
Token holding
Feature activation+0.000
thousands
Token thousands
Feature activation+1.554
of
Token of
Feature activation+0.299
political
Token political
Feature activation+0.160
separatists
Token separatists
Feature activation+4.286
without
Token without
Feature activation+0.000
charge
Token charge
Feature activation+0.000
Fres
Token Fres
Feature activation+0.000
cas
Tokencas
Feature activation+0.000
held
Token held
Feature activation+0.000
the
Token the
Feature activation+1.074
gun
Token gun
Feature activation+4.317
at
Token at
Feature activation+1.824
one
Token one
Feature activation+0.725
point
Token point
Feature activation+1.346
,
Token,
Feature activation+0.405
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.719 - 1.439
CONTAINS 0.006%

papers
Token papers
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.931
conference
Token conference
Feature activation+0.796
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
began
Token began
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
passenger
Token passenger
Feature activation+0.000
door
Token door
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
Longh
Token Longh
Feature activation+0.000
orn
Tokenorn
Feature activation+1.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.375
s
Tokens
Feature activation+1.134
pen
Token pen
Feature activation+0.355
together
Token together
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
Longh
Token Longh
Feature activation+0.000
orn
Tokenorn
Feature activation+1.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.375
s
Tokens
Feature activation+1.134
pen
Token pen
Feature activation+0.355
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
no
Token no
Feature activation+0.000
practical
Token practical
Feature activation+0.000
basis
Token basis
Feature activation+0.000
for
Token for
Feature activation+0.000
holding
Token holding
Feature activation+0.108
that
Token that
Feature activation+1.352
there
Token there
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
property
Token property
Feature activation+0.000
in
Token in
Feature activation+0.000
of
Token of
Feature activation+0.000
Matt
Token Matt
Feature activation+0.000
and
Token and
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
enc
Tokenenc
Feature activation+0.000
io
Tokenio
Feature activation+0.803
are
Token are
Feature activation+0.000
related
Token related
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.000 - 0.719
CONTAINS 99.984%

all
Token all
Feature activation+0.000
time
Token time
Feature activation+0.000
:
Token:
Feature activation+0.000
Out
Token Out
Feature activation+0.000
k
Tokenk
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
without
Token without
Feature activation+0.000
her
Token her
Feature activation+0.000
consent
Token consent
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
rape
Token rape
Feature activation+0.000
culture
Token culture
Feature activation+0.000
that
Token that
Feature activation+0.000
views
Token views
Feature activation+0.000
the
Token the
Feature activation+0.000
often
Token often
Feature activation+0.000
mistake
Token mistake
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
protective
Token protective
Feature activation+0.000
component
Token component
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
normally
Token normally
Feature activation+0.000
also
Token also
Feature activation+0.000
provides
Token provides
Feature activation+0.000
waging
Token waging
Feature activation+0.000
air
Token air
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
enemies
Token enemies
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
S
TokenS
Feature activation+0.000
ANA
TokenANA
Feature activation+0.000
/
Token /
Feature activation+0.000
bathing
Token bathing
Feature activation+0.000
causes
Token causes
Feature activation+0.000
a
Token a
Feature activation+0.000
condition
Token condition
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
Barrett
Token Barrett
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
es
Token es
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 H8.4: (feature 1649)

TOP ACTIVATIONS
MAX = 4.811

T
Token T
Feature activation+0.000
ure
Tokenure
Feature activation+0.725
tsky
Tokentsky
Feature activation+4.101
and
Token and
Feature activation+0.276
her
Token her
Feature activation+0.720
team
Token team
Feature activation+4.811
have
Token have
Feature activation+4.572
,
Token,
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
can
Token can
Feature activation+0.000
gain
Token gain
Feature activation+0.000
conduct
Token conduct
Feature activation+0.000
raids
Token raids
Feature activation+0.000
in
Token in
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+4.688
work
Token work
Feature activation+0.455
to
Token to
Feature activation+0.000
identify
Token identify
Feature activation+0.000
and
Token and
Feature activation+0.000
take
Token take
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
crucial
Token crucial
Feature activation+0.000
states
Token states
Feature activation+0.000
as
Token as
Feature activation+0.000
others
Token others
Feature activation+4.669
are
Token are
Feature activation+4.424
actively
Token actively
Feature activation+2.340
doing
Token doing
Feature activation+0.387
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
with
Token with
Feature activation+0.000
Google
Token Google
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.834
internet
Token internet
Feature activation+1.683
giant
Token giant
Feature activation+4.651
apologised
Token apologised
Feature activation+0.000
for
Token for
Feature activation+0.000
failing
Token failing
Feature activation+0.000
to
Token to
Feature activation+0.000
crack
Token crack
Feature activation+0.000
ure
Tokenure
Feature activation+0.725
tsky
Tokentsky
Feature activation+4.101
and
Token and
Feature activation+0.276
her
Token her
Feature activation+0.720
team
Token team
Feature activation+4.811
have
Token have
Feature activation+4.572
,
Token,
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
can
Token can
Feature activation+0.000
gain
Token gain
Feature activation+0.000
a
Token a
Feature activation+0.000
put
Token put
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Academy
Token Academy
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+4.468
learn
Token learn
Feature activation+0.020
their
Token their
Feature activation+0.000
trade
Token trade
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.003
leaders
Token leaders
Feature activation+2.902
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.058
two
Token two
Feature activation+0.235
countries
Token countries
Feature activation+4.463
met
Token met
Feature activation+0.000
for
Token for
Feature activation+0.000
talks
Token talks
Feature activation+0.000
in
Token in
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
those
Token those
Feature activation+0.000
crucial
Token crucial
Feature activation+0.000
states
Token states
Feature activation+0.000
as
Token as
Feature activation+0.000
others
Token others
Feature activation+4.669
are
Token are
Feature activation+4.424
actively
Token actively
Feature activation+2.340
doing
Token doing
Feature activation+0.387
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
has
Token has
Feature activation+0.000
will
Token will
Feature activation+0.000
add
Token add
Feature activation+0.000
new
Token new
Feature activation+0.000
functionality
Token functionality
Feature activation+0.000
as
Token as
Feature activation+0.000
developers
Token developers
Feature activation+4.285
create
Token create
Feature activation+0.182
more
Token more
Feature activation+0.000
applications
Token applications
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
careless
Token careless
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
negligent
Token negligent
Feature activation+0.000
"
Token"
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+4.271
demolished
Token demolished
Feature activation+0.000
her
Token her
Feature activation+0.000
oft
Token oft
Feature activation+0.000
-
Token-
Feature activation+0.000
stated
Tokenstated
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.775
s
Tokens
Feature activation+0.000
big
Token big
Feature activation+0.000
L
Token L
Feature activation+0.000
NG
TokenNG
Feature activation+0.000
consumers
Token consumers
Feature activation+4.269
make
Token make
Feature activation+0.514
it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
sourced
Token sourced
Feature activation+0.000
from
Token from
Feature activation+0.000
regions
Token regions
Feature activation+0.000
as
Token as
Feature activation+0.000
far
Token far
Feature activation+0.000
flung
Token flung
Feature activation+4.208
as
Token as
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
present
Token present
Feature activation+0.000
the
Token the
Feature activation+0.000
globe
Token globe
Feature activation+0.000
as
Token as
Feature activation+0.000
T
Token T
Feature activation+0.000
ure
Tokenure
Feature activation+0.725
tsky
Tokentsky
Feature activation+4.101
and
Token and
Feature activation+0.276
her
Token her
Feature activation+0.720
team
Token team
Feature activation+4.811
have
Token have
Feature activation+4.572
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.154
Exit
Token Exit
Feature activation+0.000
negotiations
Token negotiations
Feature activation+4.017
now
Token now
Feature activation+1.806
get
Token get
Feature activation+0.872
under
Token under
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
air
Token air
Feature activation+0.000
flows
Tokenflows
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.236
animals
Token animals
Feature activation+3.995
breathed
Token breathed
Feature activation+0.312
normally
Token normally
Feature activation+0.832
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
short
Token short
Feature activation+0.000
other
Token other
Feature activation+0.000
orders
Token orders
Feature activation+0.000
)
Token)
Feature activation+0.000
out
Token out
Feature activation+0.000
as
Token as
Feature activation+0.000
quickly
Token quickly
Feature activation+3.963
as
Token as
Feature activation+0.325
we
Token we
Feature activation+0.099
can
Token can
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
Ser
Token Ser
Feature activation+0.000
zh
Tokenzh
Feature activation+0.000
S
Token S
Feature activation+0.000
arg
Tokenarg
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
an
Tokenan
Feature activation+3.959
acknowledged
Token acknowledged
Feature activation+0.625
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
rules
Token rules
Feature activation+0.000
up
Token up
Feature activation+0.000
as
Token as
Feature activation+0.024
they
Token they
Feature activation+3.937
go
Token go
Feature activation+2.653
along
Token along
Feature activation+0.834
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
forthcoming
Token forthcoming
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
investigation
Token investigation
Feature activation+3.906
continues
Token continues
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
burn
Token burn
Feature activation+0.000
up
Token up
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+3.886
falls
Token falls
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 5.594

land
Tokenland
Feature activation+0.008
Top resid features:
sites
Token sites
Feature activation+0.025
Top resid features:
across
Token across
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
globe
Token globe
Feature activation-0.002
Top resid features:
as
Token as
Feature activation+5.594
Top resid features:
T
Token T
Feature activation+0.009
Top resid features:
ure
Tokenure
Feature activation+0.012
Top resid features:
tsky
Tokentsky
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
her
Token her
Feature activation+0.037
Top resid features:
Paris
Token Paris
Feature activation+0.040
Top resid features:
conduct
Token conduct
Feature activation+0.108
Top resid features:
raids
Token raids
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
Belgium
Token Belgium
Feature activation+0.077
Top resid features:
as
Token as
Feature activation+4.814
Top resid features:
they
Token they
Feature activation+0.269
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
identify
Token identify
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
consultants
Token consultants
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.033
Top resid features:
crucial
Token crucial
Feature activation+0.002
Top resid features:
states
Token states
Feature activation+0.040
Top resid features:
as
Token as
Feature activation+5.238
Top resid features:
others
Token others
Feature activation+0.213
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
actively
Token actively
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
suspended
Token suspended
Feature activation+0.001
Top resid features:
advertising
Token advertising
Feature activation+0.007
Top resid features:
deals
Token deals
Feature activation+0.007
Top resid features:
with
Token with
Feature activation-0.005
Top resid features:
Google
Token Google
Feature activation+0.013
Top resid features:
as
Token as
Feature activation+4.759
Top resid features:
the
Token the
Feature activation+0.607
Top resid features:
internet
Token internet
Feature activation+0.012
Top resid features:
giant
Token giant
Feature activation+0.052
Top resid features:
apologised
Token apologised
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
land
Tokenland
Feature activation+0.011
Top resid features:
sites
Token sites
Feature activation+0.042
Top resid features:
across
Token across
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
globe
Token globe
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+5.210
Top resid features:
T
Token T
Feature activation+0.004
Top resid features:
ure
Tokenure
Feature activation+0.017
Top resid features:
tsky
Tokentsky
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
her
Token her
Feature activation+0.034
Top resid features:
stay
Token stay
Feature activation-0.028
Top resid features:
put
Token put
Feature activation-0.004
Top resid features:
at
Token at
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Academy
Token Academy
Feature activation+0.026
Top resid features:
as
Token as
Feature activation+4.959
Top resid features:
they
Token they
Feature activation+0.133
Top resid features:
learn
Token learn
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
trade
Token trade
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
greenhouse
Token greenhouse
Feature activation-0.001
Top resid features:
gas
Token gas
Feature activation-0.001
Top resid features:
emissions
Token emissions
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
as
Token as
Feature activation+4.707
Top resid features:
the
Token the
Feature activation+0.223
Top resid features:
leaders
Token leaders
Feature activation+0.118
Top resid features:
of
Token of
Feature activation+0.160
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
two
Token two
Feature activation+0.008
Top resid features:
consultants
Token consultants
Feature activation+0.017
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
those
Token those
Feature activation+0.021
Top resid features:
crucial
Token crucial
Feature activation-0.005
Top resid features:
states
Token states
Feature activation+0.036
Top resid features:
as
Token as
Feature activation+4.828
Top resid features:
others
Token others
Feature activation+0.354
Top resid features:
are
Token are
Feature activation+0.121
Top resid features:
actively
Token actively
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
which
Token which
Feature activation-0.007
Top resid features:
will
Token will
Feature activation+0.021
Top resid features:
add
Token add
Feature activation+0.023
Top resid features:
new
Token new
Feature activation-0.007
Top resid features:
functionality
Token functionality
Feature activation-0.045
Top resid features:
as
Token as
Feature activation+5.139
Top resid features:
developers
Token developers
Feature activation+0.088
Top resid features:
create
Token create
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
applications
Token applications
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
extremely
Tokenextremely
Feature activation+0.000
Top resid features:
careless
Token careless
Feature activation+0.013
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.025
Top resid features:
negligent
Token negligent
Feature activation+0.011
Top resid features:
"
Token"
Feature activation+0.029
Top resid features:
as
Token as
Feature activation+4.763
Top resid features:
he
Token he
Feature activation+0.114
Top resid features:
demolished
Token demolished
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
oft
Token oft
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Papua
Token Papua
Feature activation-0.003
Top resid features:
New
Token New
Feature activation+0.001
Top resid features:
Guinea
Token Guinea
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
growth
Token growth
Feature activation+0.001
Top resid features:
as
Token as
Feature activation+4.132
Top resid features:
the
Token the
Feature activation+0.442
Top resid features:
quality
Token quality
Feature activation+0.022
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
its
Token its
Feature activation+0.002
Top resid features:
gas
Token gas
Feature activation+0.004
Top resid features:
with
Token with
Feature activation-0.009
Top resid features:
coal
Token coal
Feature activation-0.002
Top resid features:
sourced
Token sourced
Feature activation+0.009
Top resid features:
from
Token from
Feature activation-0.008
Top resid features:
regions
Token regions
Feature activation+0.030
Top resid features:
as
Token as
Feature activation+5.036
Top resid features:
far
Token far
Feature activation+0.060
Top resid features:
flung
Token flung
Feature activation-0.006
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Russia
Token Russia
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
land
Tokenland
Feature activation+0.009
Top resid features:
sites
Token sites
Feature activation+0.023
Top resid features:
across
Token across
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
globe
Token globe
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+4.904
Top resid features:
T
Token T
Feature activation+0.060
Top resid features:
ure
Tokenure
Feature activation+0.056
Top resid features:
tsky
Tokentsky
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
industrial
Token industrial
Feature activation+0.001
Top resid features:
strategy
Token strategy
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
Brexit
Token Brexit
Feature activation-0.003
Top resid features:
as
Token as
Feature activation+4.281
Top resid features:
the
Token the
Feature activation+0.625
Top resid features:
Exit
Token Exit
Feature activation+0.047
Top resid features:
negotiations
Token negotiations
Feature activation+0.088
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
way
Tokenway
Feature activation+0.016
Top resid features:
pressures
Token pressures
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
air
Token air
Feature activation+0.003
Top resid features:
flows
Tokenflows
Feature activation+0.077
Top resid features:
as
Token as
Feature activation+4.385
Top resid features:
the
Token the
Feature activation+0.285
Top resid features:
animals
Token animals
Feature activation+0.026
Top resid features:
breathed
Token breathed
Feature activation+0.000
Top resid features:
normally
Token normally
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
other
Token other
Feature activation-0.002
Top resid features:
orders
Token orders
Feature activation+0.017
Top resid features:
)
Token)
Feature activation+0.033
Top resid features:
out
Token out
Feature activation+0.020
Top resid features:
as
Token as
Feature activation+4.583
Top resid features:
quickly
Token quickly
Feature activation+0.051
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.002
Top resid features:
already
Token already
Feature activation-0.015
Top resid features:
been
Token been
Feature activation-0.001
Top resid features:
broken
Token broken
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.059
Top resid features:
As
Token As
Feature activation+5.019
Top resid features:
Armenian
Token Armenian
Feature activation-0.005
Top resid features:
President
Token President
Feature activation+0.096
Top resid features:
Ser
Token Ser
Feature activation-0.022
Top resid features:
zh
Tokenzh
Feature activation-0.004
Top resid features:
S
Token S
Feature activation+0.004
Top resid features:
just
Token just
Feature activation+0.014
Top resid features:
make
Token make
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
rules
Token rules
Feature activation-0.013
Top resid features:
up
Token up
Feature activation-0.072
Top resid features:
as
Token as
Feature activation+4.844
Top resid features:
they
Token they
Feature activation+0.063
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
more
Token more
Feature activation-0.002
Top resid features:
charges
Token charges
Feature activation-0.001
Top resid features:
may
Token may
Feature activation-0.003
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
forthcoming
Token forthcoming
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+4.224
Top resid features:
the
Token the
Feature activation+0.411
Top resid features:
investigation
Token investigation
Feature activation+0.095
Top resid features:
continues
Token continues
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.070
Top resid features:
allowed
Token allowed
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
burn
Token burn
Feature activation-0.018
Top resid features:
up
Token up
Feature activation+0.003
Top resid features:
as
Token as
Feature activation+4.578
Top resid features:
it
Token it
Feature activation+0.067
Top resid features:
falls
Token falls
Feature activation+0.000
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Earth
Token Earth
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.03

Head 3: 0.02

Head 4: 0.58

Head 5: 0.08

Head 6: 0.03

Head 7: 0.10

Head 8: 0.02

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

progresses3.15

progressed2.94

approached2.58

unfolds2.58

grows2.56

attest2.53

evolves2.49

prepares2.42

approaches2.41

continues2.36

struggled2.35

unfolded2.33

unravel2.30

matured2.21

expands2.21

develops2.10

transitioned2.09

drifted2.07

transitions2.07

struggles2.06

Negative logits

GOODMAN-1.97

altogether-1.73

liking-1.70

rig-1.59

______-1.58

coincidence-1.58

-1.55

Logged-1.54

ono-1.53

osc-1.52

Ctrl-1.51

mir-1.51

-1.51

░░-1.49

Drinking-1.48

Interested-1.47

tab-1.46

understatement-1.46

Sight-1.46

save-1.43

INTERVAL 4.330 - 4.811
CONTAINS 0.001%

conduct
Token conduct
Feature activation+0.000
raids
Token raids
Feature activation+0.000
in
Token in
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+4.688
work
Token work
Feature activation+0.455
to
Token to
Feature activation+0.000
identify
Token identify
Feature activation+0.000
and
Token and
Feature activation+0.000
take
Token take
Feature activation+0.000
ure
Tokenure
Feature activation+0.725
tsky
Tokentsky
Feature activation+4.101
and
Token and
Feature activation+0.276
her
Token her
Feature activation+0.720
team
Token team
Feature activation+4.811
have
Token have
Feature activation+4.572
,
Token,
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
can
Token can
Feature activation+0.000
gain
Token gain
Feature activation+0.000
a
Token a
Feature activation+0.000
with
Token with
Feature activation+0.000
Google
Token Google
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.834
internet
Token internet
Feature activation+1.683
giant
Token giant
Feature activation+4.651
apologised
Token apologised
Feature activation+0.000
for
Token for
Feature activation+0.000
failing
Token failing
Feature activation+0.000
to
Token to
Feature activation+0.000
crack
Token crack
Feature activation+0.000
those
Token those
Feature activation+0.000
crucial
Token crucial
Feature activation+0.000
states
Token states
Feature activation+0.000
as
Token as
Feature activation+0.000
others
Token others
Feature activation+4.669
are
Token are
Feature activation+4.424
actively
Token actively
Feature activation+2.340
doing
Token doing
Feature activation+0.387
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
has
Token has
Feature activation+0.000
T
Token T
Feature activation+0.000
ure
Tokenure
Feature activation+0.725
tsky
Tokentsky
Feature activation+4.101
and
Token and
Feature activation+0.276
her
Token her
Feature activation+0.720
team
Token team
Feature activation+4.811
have
Token have
Feature activation+4.572
,
Token,
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
can
Token can
Feature activation+0.000
gain
Token gain
Feature activation+0.000

INTERVAL 3.849 - 4.330
CONTAINS 0.002%

bringing
Token bringing
Feature activation+0.000
together
Token together
Feature activation+0.000
their
Token their
Feature activation+0.000
communities
Token communities
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+3.861
set
Token set
Feature activation+0.000
out
Token out
Feature activation+0.000
why
Token why
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
other
Token other
Feature activation+0.000
orders
Token orders
Feature activation+0.000
)
Token)
Feature activation+0.000
out
Token out
Feature activation+0.000
as
Token as
Feature activation+0.000
quickly
Token quickly
Feature activation+3.963
as
Token as
Feature activation+0.325
we
Token we
Feature activation+0.099
can
Token can
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
careless
Token careless
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
negligent
Token negligent
Feature activation+0.000
"
Token"
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+4.271
demolished
Token demolished
Feature activation+0.000
her
Token her
Feature activation+0.000
oft
Token oft
Feature activation+0.000
-
Token-
Feature activation+0.000
stated
Tokenstated
Feature activation+0.000
relations
Token relations
Feature activation+0.000
with
Token with
Feature activation+0.000
major
Token major
Feature activation+0.000
powers
Token powers
Feature activation+0.000
as
Token as
Feature activation+0.000
she
Token she
Feature activation+3.873
negoti
Token negoti
Feature activation+0.000
ates
Tokenates
Feature activation+0.023
Britain
Token Britain
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
and
Token and
Feature activation+0.000
air
Token air
Feature activation+0.000
flows
Tokenflows
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.236
animals
Token animals
Feature activation+3.995
breathed
Token breathed
Feature activation+0.312
normally
Token normally
Feature activation+0.832
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
short
Token short
Feature activation+0.000

INTERVAL 3.368 - 3.849
CONTAINS 0.005%

against
Token against
Feature activation+0.000
Daesh
Token Daesh
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.060
Turkish
Token Turkish
Feature activation+1.126
leader
Token leader
Feature activation+3.769
shares
Token shares
Feature activation+0.084
that
Token that
Feature activation+0.000
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
the
Token the
Feature activation+0.374
phenomenon
Token phenomenon
Feature activation+2.519
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
economy
Token economy
Feature activation+3.490
grows
Token grows
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
good
Token good
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
the
Token the
Feature activation+0.472
Syrian
Token Syrian
Feature activation+0.000
crisis
Token crisis
Feature activation+3.531
enters
Token enters
Feature activation+0.097
its
Token its
Feature activation+0.000
sixth
Token sixth
Feature activation+0.000
year
Token year
Feature activation+1.331
,
Token,
Feature activation+0.000
struck
Token struck
Feature activation+0.000
by
Token by
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+3.458
was
Token was
Feature activation+3.267
being
Token being
Feature activation+1.748
filmed
Token filmed
Feature activation+0.000
,
Token,
Feature activation+0.000
reports
Token reports
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+3.239
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+3.790
travel
Token travel
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Et
Token Et
Feature activation+0.000
ihad
Tokenihad
Feature activation+0.934

INTERVAL 2.887 - 3.368
CONTAINS 0.008%

:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
track
Token track
Feature activation+0.088
work
Token work
Feature activation+3.037
continues
Token continues
Feature activation+0.287
to
Token to
Feature activation+0.446
progress
Token progress
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
the
Token the
Feature activation+0.303
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+3.341
announces
Token announces
Feature activation+0.607
a
Token a
Feature activation+0.000
task
Token task
Feature activation+0.000
force
Tokenforce
Feature activation+0.000
to
Token to
Feature activation+0.000
gas
Token gas
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.003
leaders
Token leaders
Feature activation+2.902
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.058
two
Token two
Feature activation+0.235
countries
Token countries
Feature activation+4.463
met
Token met
Feature activation+0.000
support
Token support
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
as
Token as
Feature activation+0.000
she
Token she
Feature activation+3.321
and
Token and
Feature activation+0.000
Coach
Token Coach
Feature activation+0.538
always
Token always
Feature activation+0.000
did
Token did
Feature activation+0.000
for
Token for
Feature activation+0.000
people
Token people
Feature activation+0.000
and
Token and
Feature activation+0.000
injured
Token injured
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+3.309
flattened
Token flattened
Feature activation+0.000
three
Token three
Feature activation+0.000
medieval
Token medieval
Feature activation+0.000
towns
Token towns
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.406 - 2.887
CONTAINS 0.014%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
these
Token these
Feature activation+0.000
other
Token other
Feature activation+0.000
candidates
Token candidates
Feature activation+2.790
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
mere
Token mere
Feature activation+0.000
novelty
Token novelty
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+2.565
replaces
Token replaces
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
library
Token library
Feature activation+0.000
,
Token,
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
trail
Token trail
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+2.659
has
Token has
Feature activation+0.727
done
Token done
Feature activation+0.000
to
Token to
Feature activation+0.000
former
Token former
Feature activation+0.000
rail
Token rail
Feature activation+0.000
when
Token when
Feature activation+0.000
others
Token others
Feature activation+0.000
step
Token step
Feature activation+0.000
up
Token up
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+2.521
step
Token step
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
children
Token children
Feature activation+0.000
or
Token or
Feature activation+0.000
adults
Token adults
Feature activation+0.385
has
Token has
Feature activation+2.678
declined
Token declined
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
chart
Token chart
Feature activation+0.000
only
Token only
Feature activation+0.000

INTERVAL 1.924 - 2.406
CONTAINS 0.023%

consistency
Token consistency
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
site
Token site
Feature activation+0.000
as
Token as
Feature activation+0.000
sprawling
Token sprawling
Feature activation+1.936
as
Token as
Feature activation+0.000
ours
Token ours
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
from
Token from
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+1.997
ran
Token ran
Feature activation+0.000
away
Token away
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
The
Token The
Feature activation+0.000
crash
Token crash
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+2.006
was
Token was
Feature activation+1.715
,
Token,
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
way
Token way
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
woods
Token woods
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+1.939
as
Token as
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
and
Token and
Feature activation+0.000
agreed
Token agreed
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Unfortunately
Token Unfortunately
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
modeling
Token modeling
Feature activation+1.447
has
Token has
Feature activation+2.129
improved
Token improved
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 1.443 - 1.924
CONTAINS 0.026%

ins
Tokenins
Feature activation+0.000
for
Token for
Feature activation+0.000
passengers
Token passengers
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
airplane
Token airplane
Feature activation+1.803
."
Token."
Feature activation+0.000
Austria
Token Austria
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
as
Token as
Feature activation+0.000
relations
Token relations
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.488
sides
Token sides
Feature activation+1.643
were
Token were
Feature activation+1.482
wrestling
Token wrestling
Feature activation+0.076
with
Token with
Feature activation+0.036
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
another
Token another
Feature activation+0.000
leaked
Token leaked
Feature activation+0.000
chapter
Token chapter
Feature activation+1.582
makes
Token makes
Feature activation+0.838
clear
Token clear
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
he
Token he
Feature activation+0.000
boil
Token boil
Feature activation+0.000
the
Token the
Feature activation+0.000
offender
Token offender
Feature activation+0.000
as
Token as
Feature activation+0.000
soon
Token soon
Feature activation+1.512
as
Token as
Feature activation+0.267
possible
Token possible
Feature activation+0.000
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
post
Token post
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
I
Token I
Feature activation+1.751
cautiously
Token cautiously
Feature activation+1.630
walked
Token walked
Feature activation+0.319
down
Token down
Feature activation+0.000
a
Token a
Feature activation+0.000
narrow
Token narrow
Feature activation+0.000

INTERVAL 0.962 - 1.443
CONTAINS 0.035%

a
Token a
Feature activation+0.000
decent
Token decent
Feature activation+0.000
sized
Token sized
Feature activation+0.000
wave
Token wave
Feature activation+0.293
of
Token of
Feature activation+0.000
opposition
Token opposition
Feature activation+1.257
to
Token to
Feature activation+0.000
new
Token new
Feature activation+0.000
Form
Token Form
Feature activation+0.000
10
Token 10
Feature activation+0.000
99
Token99
Feature activation+0.000
the
Token the
Feature activation+0.000
vicinity
Token vicinity
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+1.107
illustrates
Token illustrates
Feature activation+0.280
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
implementation
Token implementation
Feature activation+0.000
of
Token of
Feature activation+0.000
close
Token close
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+1.025
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
stand
Token stand
Feature activation+0.000
it
Token it
Feature activation+0.000
per
Token per
Feature activation+0.000
gallon
Token gallon
Feature activation+1.117
out
Token out
Feature activation+0.529
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
cars
Token cars
Feature activation+1.185
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
economic
Token economic
Feature activation+0.000
disappoint
Token disappoint
Feature activation+0.000
ments
Tokenments
Feature activation+0.952
in
Token in
Feature activation+0.000
emerging
Token emerging
Feature activation+0.000
markets
Token markets
Feature activation+1.080
sent
Token sent
Feature activation+0.000
equity
Token equity
Feature activation+0.000
markets
Token markets
Feature activation+0.000
t
Token t
Feature activation+0.000
umbling
Tokenumbling
Feature activation+0.000

INTERVAL 0.481 - 0.962
CONTAINS 0.057%

ept
Tokenept
Feature activation+0.000
o
Tokeno
Feature activation+0.233
and
Token and
Feature activation+0.000
.
Token .
Feature activation+0.000
O
TokenO
Feature activation+0.000
din
Tokendin
Feature activation+0.532
,
Token,
Feature activation+0.000
.
Token .
Feature activation+0.000
Sh
TokenSh
Feature activation+0.000
it
Tokenit
Feature activation+0.000
R
Token R
Feature activation+0.000
K
TokenK
Feature activation+0.000
een
Tokeneen
Feature activation+0.000
as
Token as
Feature activation+0.000
Starr
Token Starr
Feature activation+2.603
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.491
compile
Token compile
Feature activation+0.000
a
Token a
Feature activation+0.000
thoroughly
Token thoroughly
Feature activation+0.000
damning
Token damning
Feature activation+0.000
impeachment
Token impeachment
Feature activation+0.000
press
Token press
Feature activation+0.090
release
Token release
Feature activation+1.792
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
examination
Token examination
Feature activation+0.828
guidelines
Token guidelines
Feature activation+2.980
indicate
Token indicate
Feature activation+0.972
,
Token,
Feature activation+0.000
China
Token China
Feature activation+0.000
has
Token has
Feature activation+0.000
expert
Token expert
Feature activation+0.000
social
Token social
Feature activation+0.000
engineering
Token engineering
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.748
approach
Token approach
Feature activation+0.000
for
Token for
Feature activation+0.000
solving
Token solving
Feature activation+0.000
problems
Token problems
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
whenever
Token whenever
Feature activation+0.000
I
Token I
Feature activation+0.507
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.534
m
Tokenm
Feature activation+0.660
needed
Token needed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000

INTERVAL 0.000 - 0.481
CONTAINS 99.830%

're
Token're
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
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
We
TokenWe
Feature activation+0.000
're
Token're
Feature activation+0.000
here
Token here
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
University
Token University
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Faculty
Token Faculty
Feature activation+0.000
of
Token of
Feature activation+0.000
Medicine
Token Medicine
Feature activation+0.000
,
Token,
Feature activation+0.000
denied
Token denied
Feature activation+0.000
reports
Token reports
Feature activation+0.000
of
Token of
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
causes
Token causes
Feature activation+0.000
of
Token of
Feature activation+0.000
Hurricane
Token Hurricane
Feature activation+0.000
Katrina
Token Katrina
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
your
Token your
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+0.000
unusual
Token unusual
Feature activation+0.000
animal
Token animal
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
shop
Token shop
Feature activation+0.000
also
Token also
Feature activation+0.000
con
Tokencon
Feature activation+0.000
clusively
Tokenclusively
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
debris
Token debris
Feature activation+0.000
found
Token found
Feature activation+0.000
on
Token on
Feature activation+0.000
Re
Token Re
Feature activation+0.000
union
Tokenunion
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 H8.4: (feature 16002)

TOP ACTIVATIONS
MAX = 7.467

ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ement
Tokenement
Feature activation+6.110
program
Token program
Feature activation+7.095
âĢ
TokenâĢ
Feature activation+5.108
Ŀ
TokenĿ
Feature activation+7.467
to
Token to
Feature activation+1.366
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
the
Token the
Feature activation+0.000
nuisance
Token nuisance
Feature activation+0.000
ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ement
Tokenement
Feature activation+6.110
program
Token program
Feature activation+7.095
âĢ
TokenâĢ
Feature activation+5.108
Ŀ
TokenĿ
Feature activation+7.467
to
Token to
Feature activation+1.366
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.000
/
Token /
Feature activation+0.000
r
Tokenr
Feature activation+0.000
/
Token/
Feature activation+0.000
Fall
TokenFall
Feature activation+0.000
out
Tokenout
Feature activation+2.080
community
Token community
Feature activation+7.014
together
Token together
Feature activation+0.000
(
Token (
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.512
benefits
Token benefits
Feature activation+0.656
of
Token of
Feature activation+0.000
decentral
Token decentral
Feature activation+0.000
ization
Tokenization
Feature activation+6.968
to
Token to
Feature activation+0.726
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
financial
Token financial
Feature activation+0.000
system
Token system
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
any
Token any
Feature activation+3.169
of
Token of
Feature activation+0.565
them
Token them
Feature activation+6.831
to
Token to
Feature activation+1.795
fruition
Token fruition
Feature activation+0.000
.
Token.
Feature activation+0.000
Right
Token Right
Feature activation+0.000
now
Token now
Feature activation+0.000
spending
Token spending
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
brought
Token brought
Feature activation+0.000
the
Token the
Feature activation+0.789
United
Token United
Feature activation+0.371
States
Token States
Feature activation+6.541
close
Token close
Feature activation+0.431
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
brink
Token brink
Feature activation+0.000
of
Token of
Feature activation+0.000
stars
Token stars
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
Captain
Token Captain
Feature activation+0.000
Britain
Token Britain
Feature activation+6.531
to
Token to
Feature activation+2.236
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
producer
Token producer
Feature activation+0.000
is
Token is
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.556
job
Token job
Feature activation+0.053
lessness
Tokenlessness
Feature activation+6.492
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
above
Token above
Feature activation+0.000
10
Token 10
Feature activation+0.000
percent
Token percent
Feature activation+0.000
ights
Tokenights
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
bring
Token bring
Feature activation+0.651
WWII
Token WWII
Feature activation+1.216
veterans
Token veterans
Feature activation+6.411
to
Token to
Feature activation+1.115
the
Token the
Feature activation+0.010
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+2.189
collect
Token collect
Feature activation+0.000
these
Token these
Feature activation+0.000
samples
Token samples
Feature activation+0.277
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+1.270
them
Token them
Feature activation+6.407
back
Token back
Feature activation+0.851
to
Token to
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
discontent
Token discontent
Feature activation+0.000
by
Token by
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
its
Token its
Feature activation+0.822
beautiful
Token beautiful
Feature activation+0.030
qualities
Token qualities
Feature activation+6.372
like
Token like
Feature activation+0.000
an
Token an
Feature activation+0.000
actual
Token actual
Feature activation+0.000
season
Token season
Feature activation+1.464
with
Token with
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token 3
Feature activation+2.217
and
Token and
Feature activation+0.000
4
Token 4
Feature activation+2.609
train
Token train
Feature activation+1.445
service
Token service
Feature activation+6.310
down
Token down
Feature activation+0.606
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Parkway
Token Parkway
Feature activation+0.000
this
Token this
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
bring
Token bring
Feature activation+1.029
them
Token them
Feature activation+6.140
to
Token to
Feature activation+1.836
justice
Token justice
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
nuisance
Token nuisance
Feature activation+0.000
ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ement
Tokenement
Feature activation+6.110
program
Token program
Feature activation+7.095
âĢ
TokenâĢ
Feature activation+5.108
Ŀ
TokenĿ
Feature activation+7.467
to
Token to
Feature activation+1.366
the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.000
who
Token who
Feature activation+0.000
bring
Token bring
Feature activation+0.000
incidents
Token incidents
Feature activation+2.165
of
Token of
Feature activation+0.580
misconduct
Token misconduct
Feature activation+6.063
to
Token to
Feature activation+1.240
the
Token the
Feature activation+0.000
attention
Token attention
Feature activation+0.000
of
Token of
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
looks
Token looks
Feature activation+0.000
forward
Token forward
Feature activation+0.000
to
Token to
Feature activation+0.000
bringing
Token bringing
Feature activation+0.214
this
Token this
Feature activation+3.083
matter
Token matter
Feature activation+5.958
to
Token to
Feature activation+0.278
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000
soon
Token soon
Feature activation+0.000
."
Token."
Feature activation+0.000
entire
Token entire
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
for
Token for
Feature activation+0.000
bringing
Token bringing
Feature activation+0.364
the
Token the
Feature activation+0.703
Act
Token Act
Feature activation+5.843
into
Token into
Feature activation+0.474
force
Token force
Feature activation+0.000
has
Token has
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
which
Token which
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.400
the
Token the
Feature activation+2.118
mobile
Token mobile
Feature activation+1.535
OS
Token OS
Feature activation+5.817
to
Token to
Feature activation+2.562
inf
Token inf
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
ainment
Tokenainment
Feature activation+0.000
system
Token system
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
an
Token an
Feature activation+1.333
NHL
Token NHL
Feature activation+0.915
franchise
Token franchise
Feature activation+5.737
to
Token to
Feature activation+0.397
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
larger
Token larger
Feature activation+0.000
societal
Token societal
Feature activation+0.000
impact
Token impact
Feature activation+2.269
of
Token of
Feature activation+0.000
proposed
Token proposed
Feature activation+0.000
research
Token research
Feature activation+5.646
into
Token into
Feature activation+0.152
the
Token the
Feature activation+0.000
peer
Token peer
Feature activation+0.000
review
Token review
Feature activation+0.000
process
Token process
Feature activation+0.000

Top DFA by src position
MAX = 8.586

targeted
Token targeted
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
he
Token he
Feature activation-0.006
Top resid features:
plans
Token plans
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
bring
Token bring
Feature activation+8.586
Top resid features:
âĢ
Token âĢ
Feature activation+0.018
Top resid features:
ľ
Tokenľ
Feature activation+0.010
Top resid features:
con
Tokencon
Feature activation+0.003
Top resid features:
cern
Tokencern
Feature activation+0.102
Top resid features:
s
Tokens
Feature activation+0.112
Top resid features:
targeted
Token targeted
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
he
Token he
Feature activation-0.003
Top resid features:
plans
Token plans
Feature activation-0.012
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
bring
Token bring
Feature activation+8.025
Top resid features:
âĢ
Token âĢ
Feature activation+0.029
Top resid features:
ľ
Tokenľ
Feature activation+0.059
Top resid features:
con
Tokencon
Feature activation+0.006
Top resid features:
cern
Tokencern
Feature activation+0.058
Top resid features:
s
Tokens
Feature activation+0.026
Top resid features:
12
Token 12
Feature activation+0.010
Top resid features:
/
Token/
Feature activation+0.002
Top resid features:
11
Token11
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
bring
Token bring
Feature activation+7.913
Top resid features:
the
Token the
Feature activation+0.381
Top resid features:
/
Token /
Feature activation-0.062
Top resid features:
r
Tokenr
Feature activation+0.005
Top resid features:
/
Token/
Feature activation+0.129
Top resid features:
Fall
TokenFall
Feature activation+0.012
Top resid features:
developing
Token developing
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
infrastructure
Token infrastructure
Feature activation+0.003
Top resid features:
needed
Token needed
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.046
Top resid features:
bring
Token bring
Feature activation+7.661
Top resid features:
the
Token the
Feature activation+0.181
Top resid features:
benefits
Token benefits
Feature activation+0.168
Top resid features:
of
Token of
Feature activation+0.165
Top resid features:
decentral
Token decentral
Feature activation+0.091
Top resid features:
ization
Tokenization
Feature activation+0.120
Top resid features:
too
Token too
Feature activation+0.001
Top resid features:
many
Token many
Feature activation+0.020
Top resid features:
projects
Token projects
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
not
Token not
Feature activation+0.018
Top resid features:
bringing
Token bringing
Feature activation+8.002
Top resid features:
any
Token any
Feature activation+0.102
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
them
Token them
Feature activation+0.050
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
fruition
Token fruition
Feature activation+0.000
Top resid features:
agreed
Token agreed
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
large
Token large
Feature activation+0.013
Top resid features:
spending
Token spending
Feature activation+0.027
Top resid features:
cuts
Token cuts
Feature activation+0.004
Top resid features:
brought
Token brought
Feature activation+7.793
Top resid features:
the
Token the
Feature activation+0.189
Top resid features:
United
Token United
Feature activation+0.008
Top resid features:
States
Token States
Feature activation+0.034
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.015
Top resid features:
already
Token already
Feature activation-0.007
Top resid features:
stars
Token stars
Feature activation-0.016
Top resid features:
interested
Token interested
Feature activation-0.010
Top resid features:
in
Token in
Feature activation+0.031
Top resid features:
bringing
Token bringing
Feature activation+7.906
Top resid features:
Captain
Token Captain
Feature activation+0.054
Top resid features:
Britain
Token Britain
Feature activation+0.158
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
who
Token who
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
fighting
Token fighting
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.116
Top resid features:
bring
Token bring
Feature activation+7.507
Top resid features:
job
Token job
Feature activation+0.046
Top resid features:
lessness
Tokenlessness
Feature activation+0.128
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
above
Token above
Feature activation+0.000
Top resid features:
Honor
Token Honor
Feature activation-0.011
Top resid features:
Fl
Token Fl
Feature activation-0.006
Top resid features:
ights
Tokenights
Feature activation-0.063
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
which
Token which
Feature activation+0.034
Top resid features:
bring
Token bring
Feature activation+7.585
Top resid features:
WWII
Token WWII
Feature activation+0.176
Top resid features:
veterans
Token veterans
Feature activation+0.169
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
nation
Token nation
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
collect
Token collect
Feature activation+0.065
Top resid features:
these
Token these
Feature activation+0.020
Top resid features:
samples
Token samples
Feature activation+0.052
Top resid features:
and
Token and
Feature activation+0.184
Top resid features:
bring
Token bring
Feature activation+6.993
Top resid features:
them
Token them
Feature activation+0.108
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Earth
Token Earth
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
gy
Tokengy
Feature activation+0.004
Top resid features:
mn
Tokenmn
Feature activation-0.001
Top resid features:
astics
Tokenastics
Feature activation+0.023
Top resid features:
discontent
Token discontent
Feature activation+0.034
Top resid features:
by
Token by
Feature activation+0.062
Top resid features:
bringing
Token bringing
Feature activation+6.626
Top resid features:
its
Token its
Feature activation+0.731
Top resid features:
beautiful
Token beautiful
Feature activation+0.183
Top resid features:
qualities
Token qualities
Feature activation+0.048
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
Metropolitan
Token Metropolitan
Feature activation+0.000
Top resid features:
Transportation
Token Transportation
Feature activation-0.002
Top resid features:
Authority
Token Authority
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
examine
Token examine
Feature activation+0.007
Top resid features:
bringing
Token bringing
Feature activation+7.212
Top resid features:
No
Token No
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
3
Token 3
Feature activation+0.091
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
4
Token 4
Feature activation+0.083
Top resid features:
did
Token did
Feature activation-0.012
Top resid features:
this
Token this
Feature activation-0.038
Top resid features:
so
Token so
Feature activation+0.019
Top resid features:
we
Token we
Feature activation-0.003
Top resid features:
can
Token can
Feature activation+0.056
Top resid features:
bring
Token bring
Feature activation+7.224
Top resid features:
them
Token them
Feature activation+0.217
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
justice
Token justice
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
targeted
Token targeted
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
plans
Token plans
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
bring
Token bring
Feature activation+7.157
Top resid features:
âĢ
Token âĢ
Feature activation+0.012
Top resid features:
ľ
Tokenľ
Feature activation+0.031
Top resid features:
con
Tokencon
Feature activation+0.011
Top resid features:
cern
Tokencern
Feature activation+0.020
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
seek
Token seek
Feature activation-0.021
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
deport
Token deport
Feature activation-0.012
Top resid features:
victims
Token victims
Feature activation-0.009
Top resid features:
who
Token who
Feature activation-0.043
Top resid features:
bring
Token bring
Feature activation+7.609
Top resid features:
incidents
Token incidents
Feature activation+0.083
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
misconduct
Token misconduct
Feature activation-0.041
Top resid features:
to
Token to
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:
FTA
Token FTA
Feature activation-0.002
Top resid features:
looks
Token looks
Feature activation-0.015
Top resid features:
forward
Token forward
Feature activation-0.013
Top resid features:
to
Token to
Feature activation+0.024
Top resid features:
bringing
Token bringing
Feature activation+6.978
Top resid features:
this
Token this
Feature activation+0.243
Top resid features:
matter
Token matter
Feature activation+0.072
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
As
TokenAs
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
entire
Token entire
Feature activation+0.003
Top resid features:
infrastructure
Token infrastructure
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.077
Top resid features:
bringing
Token bringing
Feature activation+6.663
Top resid features:
the
Token the
Feature activation+0.230
Top resid features:
Act
Token Act
Feature activation+0.105
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
force
Token force
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
dash
Token dash
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
which
Token which
Feature activation+0.023
Top resid features:
would
Token would
Feature activation+0.064
Top resid features:
bring
Token bring
Feature activation+5.790
Top resid features:
the
Token the
Feature activation+0.284
Top resid features:
mobile
Token mobile
Feature activation+0.118
Top resid features:
OS
Token OS
Feature activation+0.088
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
inf
Token inf
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.023
Top resid features:
sparking
Token sparking
Feature activation+0.009
Top resid features:
initial
Token initial
Feature activation+0.020
Top resid features:
interest
Token interest
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
bringing
Token bringing
Feature activation+6.149
Top resid features:
an
Token an
Feature activation+0.988
Top resid features:
NHL
Token NHL
Feature activation+0.044
Top resid features:
franchise
Token franchise
Feature activation+0.142
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
world
Token world
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
struggling
Token struggling
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
bring
Token bring
Feature activation+6.851
Top resid features:
assessments
Token assessments
Feature activation+0.061
Top resid features:
of
Token of
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
larger
Token larger
Feature activation+0.018
Top resid features:
societal
Token societal
Feature activation+0.014
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.03

Head 3: 0.02

Head 4: 0.57

Head 5: 0.06

Head 6: 0.01

Head 7: 0.11

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

onto3.18

into3.18

closer2.37

Into2.37

together2.28

INTO2.19

nearer2.18

forth2.17

back2.12

alive2.10

toget2.08

into2.08

unto2.05

up1.95

rawdownloadcloneembedreportprint1.85

ylum1.82

Together1.81

thereto1.80

away1.79

to1.78

Negative logits

ende-1.85

Reasons-1.74

also-1.71

PLIED-1.68

raid-1.67

edi-1.66

preferring-1.61

255-1.60

resist-1.60

whether-1.60

do-1.57

apply-1.57

&&-1.54

Fail-1.54

grave-1.53

tif-1.53

reasons-1.53

gross-1.53

obbies-1.52

anges-1.52

INTERVAL 6.721 - 7.467
CONTAINS 0.001%

and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
any
Token any
Feature activation+3.169
of
Token of
Feature activation+0.565
them
Token them
Feature activation+6.831
to
Token to
Feature activation+1.795
fruition
Token fruition
Feature activation+0.000
.
Token.
Feature activation+0.000
Right
Token Right
Feature activation+0.000
now
Token now
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.512
benefits
Token benefits
Feature activation+0.656
of
Token of
Feature activation+0.000
decentral
Token decentral
Feature activation+0.000
ization
Tokenization
Feature activation+6.968
to
Token to
Feature activation+0.726
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
financial
Token financial
Feature activation+0.000
system
Token system
Feature activation+0.000
/
Token /
Feature activation+0.000
r
Tokenr
Feature activation+0.000
/
Token/
Feature activation+0.000
Fall
TokenFall
Feature activation+0.000
out
Tokenout
Feature activation+2.080
community
Token community
Feature activation+7.014
together
Token together
Feature activation+0.000
(
Token (
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
the
Token the
Feature activation+0.000
nuisance
Token nuisance
Feature activation+0.000
ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ement
Tokenement
Feature activation+6.110
program
Token program
Feature activation+7.095
âĢ
TokenâĢ
Feature activation+5.108
Ŀ
TokenĿ
Feature activation+7.467
to
Token to
Feature activation+1.366
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.000
ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ement
Tokenement
Feature activation+6.110
program
Token program
Feature activation+7.095
âĢ
TokenâĢ
Feature activation+5.108
Ŀ
TokenĿ
Feature activation+7.467
to
Token to
Feature activation+1.366
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000

INTERVAL 5.974 - 6.721
CONTAINS 0.001%

.
Token.
Feature activation+0.000
3
Token 3
Feature activation+2.217
and
Token and
Feature activation+0.000
4
Token 4
Feature activation+2.609
train
Token train
Feature activation+1.445
service
Token service
Feature activation+6.310
down
Token down
Feature activation+0.606
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Parkway
Token Parkway
Feature activation+0.000
discontent
Token discontent
Feature activation+0.000
by
Token by
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
its
Token its
Feature activation+0.822
beautiful
Token beautiful
Feature activation+0.030
qualities
Token qualities
Feature activation+6.372
like
Token like
Feature activation+0.000
an
Token an
Feature activation+0.000
actual
Token actual
Feature activation+0.000
season
Token season
Feature activation+1.464
with
Token with
Feature activation+0.000
is
Token is
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.556
job
Token job
Feature activation+0.053
lessness
Tokenlessness
Feature activation+6.492
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
above
Token above
Feature activation+0.000
10
Token 10
Feature activation+0.000
percent
Token percent
Feature activation+0.000
ights
Tokenights
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
bring
Token bring
Feature activation+0.651
WWII
Token WWII
Feature activation+1.216
veterans
Token veterans
Feature activation+6.411
to
Token to
Feature activation+1.115
the
Token the
Feature activation+0.010
nation
Token nation
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+2.189
this
Token this
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
bring
Token bring
Feature activation+1.029
them
Token them
Feature activation+6.140
to
Token to
Feature activation+1.836
justice
Token justice
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 5.227 - 5.974
CONTAINS 0.002%

the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
it
Token it
Feature activation+5.626
to
Token to
Feature activation+0.726
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
it
Token it
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
FTC
Token FTC
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
it
Token it
Feature activation+5.522
to
Token to
Feature activation+0.213
court
Token court
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
brings
Token brings
Feature activation+0.000
a
Token a
Feature activation+0.212
passion
Token passion
Feature activation+0.716
for
Token for
Feature activation+0.000
efficiency
Token efficiency
Feature activation+5.384
and
Token and
Feature activation+0.000
innovation
Token innovation
Feature activation+5.395
to
Token to
Feature activation+0.155
life
Token life
Feature activation+0.000
with
Token with
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
an
Token an
Feature activation+1.333
NHL
Token NHL
Feature activation+0.915
franchise
Token franchise
Feature activation+5.737
to
Token to
Feature activation+0.397
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.212
passion
Token passion
Feature activation+0.716
for
Token for
Feature activation+0.000
efficiency
Token efficiency
Feature activation+5.384
and
Token and
Feature activation+0.000
innovation
Token innovation
Feature activation+5.395
to
Token to
Feature activation+0.155
life
Token life
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000

INTERVAL 4.480 - 5.227
CONTAINS 0.003%

total
Token total
Feature activation+0.313
captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.000
killed
Token killed
Feature activation+1.902
so
Token so
Feature activation+2.897
far
Token far
Feature activation+4.741
to
Token to
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+0.000
H
Token H
Feature activation+0.000
é
Tokené
Feature activation+0.000
and
Token and
Feature activation+0.000
rock
Token rock
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
bringing
Token bringing
Feature activation+0.500
samples
Token samples
Feature activation+5.007
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.035
Earth
Token Earth
Feature activation+0.000
would
Token would
Feature activation+0.000
allow
Token allow
Feature activation+0.000
says
Token says
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.658
the
Token the
Feature activation+0.753
petition
Token petition
Feature activation+4.532
to
Token to
Feature activation+0.576
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
prohibits
Token prohibits
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
aliens
Token aliens
Feature activation+5.156
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.784
them
Token them
Feature activation+4.647
together
Token together
Feature activation+0.000
directly
Token directly
Feature activation+0.106
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
revolutionary
Token revolutionary
Feature activation+0.000

INTERVAL 3.734 - 4.480
CONTAINS 0.002%

Gaza
Token Gaza
Feature activation+0.000
Strip
Token Strip
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.614
him
Token him
Feature activation+4.351
back
Token back
Feature activation+0.164
to
Token to
Feature activation+0.051
Israel
Token Israel
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
downloadable
Token downloadable
Feature activation+0.000
content
Token content
Feature activation+3.949
packs
Token packs
Feature activation+4.371
to
Token to
Feature activation+1.021
Minecraft
Token Minecraft
Feature activation+0.000
for
Token for
Feature activation+0.000
Xbox
Token Xbox
Feature activation+0.000
,
Token,
Feature activation+0.000
spacing
Token spacing
Feature activation+0.000
us
Token us
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
brings
Token brings
Feature activation+0.111
us
Token us
Feature activation+4.250
more
Token more
Feature activation+1.712
directly
Token directly
Feature activation+2.946
in
Token in
Feature activation+0.723
contact
Token contact
Feature activation+0.000
with
Token with
Feature activation+0.000
teamed
Token teamed
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
downloadable
Token downloadable
Feature activation+0.000
content
Token content
Feature activation+3.949
packs
Token packs
Feature activation+4.371
to
Token to
Feature activation+1.021
Minecraft
Token Minecraft
Feature activation+0.000
for
Token for
Feature activation+0.000
Xbox
Token Xbox
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
people
Token people
Feature activation+3.102
and
Token and
Feature activation+0.000
devices
Token devices
Feature activation+4.209
online
Token online
Feature activation+1.106
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
we
Token we
Feature activation+0.000
've
Token've
Feature activation+0.000

INTERVAL 2.987 - 3.734
CONTAINS 0.003%

legitimately
Token legitimately
Feature activation+0.000
close
Token close
Feature activation+0.000
and
Token and
Feature activation+0.000
exciting
Token exciting
Feature activation+0.000
team
Token team
Feature activation+0.000
competitions
Token competitions
Feature activation+3.529
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+0.000
being
Token being
Feature activation+0.000
barred
Token barred
Feature activation+0.000
from
Token from
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
instruments
Token instruments
Feature activation+3.426
to
Token to
Feature activation+0.822
Saturday
Token Saturday
Feature activation+0.000
's
Token's
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
's
Token's
Feature activation+0.000
.
Token.
Feature activation+0.000
Montreal
Token Montreal
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+3.047
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+2.959
all
Token all
Feature activation+3.705
to
Token to
Feature activation+1.252
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.110
and
Token and
Feature activation+0.366
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
people
Token people
Feature activation+3.102
and
Token and
Feature activation+0.000
devices
Token devices
Feature activation+4.209
online
Token online
Feature activation+1.106
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000

INTERVAL 2.240 - 2.987
CONTAINS 0.005%

bringing
Token bringing
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.512
festive
Token festive
Feature activation+2.537
cheer
Token cheer
Feature activation+2.639
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bring
TokenBring
Feature activation+0.000
ing
Tokening
Feature activation+5.473
the
Token the
Feature activation+2.608
coating
Token coating
Feature activation+3.878
to
Token to
Feature activation+1.699
the
Token the
Feature activation+0.370
market
Token market
Feature activation+0.000
could
Token could
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
No
Token No
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token 3
Feature activation+2.217
and
Token and
Feature activation+0.000
4
Token 4
Feature activation+2.609
train
Token train
Feature activation+1.445
service
Token service
Feature activation+6.310
down
Token down
Feature activation+0.606
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
officially
Token officially
Feature activation+0.000
announced
Token announced
Feature activation+0.000
later
Token later
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000
brings
Token brings
Feature activation+2.508
to
Token to
Feature activation+3.794
a
Token a
Feature activation+0.670
close
Token close
Feature activation+0.000
months
Token months
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
service
Token service
Feature activation+0.000
was
Token was
Feature activation+0.000
brought
Token brought
Feature activation+0.296
to
Token to
Feature activation+2.538
an
Token an
Feature activation+0.515
end
Token end
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.493 - 2.240
CONTAINS 0.006%

interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
Captain
Token Captain
Feature activation+0.000
Britain
Token Britain
Feature activation+6.531
to
Token to
Feature activation+2.236
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
producer
Token producer
Feature activation+0.000
said
Token said
Feature activation+0.000
Six
Token Six
Feature activation+0.000
of
Token of
Feature activation+0.000
One
Token One
Feature activation+0.000
,
Token,
Feature activation+0.000
brought
Token brought
Feature activation+0.026
to
Token to
Feature activation+1.853
you
Token you
Feature activation+0.265
by
Token by
Feature activation+0.000
Mart
Token Mart
Feature activation+0.000
a
Tokena
Feature activation+0.000
Kau
Token Kau
Feature activation+0.000
Livingston
Token Livingston
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
will
Tokenwill
Feature activation+0.000
bring
Token bring
Feature activation+0.533
huge
Token huge
Feature activation+1.620
talent
Token talent
Feature activation+3.143
to
Token to
Feature activation+0.087
a
Token a
Feature activation+0.000
vital
Token vital
Feature activation+0.000
national
Token national
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Jennings
Token Jennings
Feature activation+0.000
,
Token,
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+1.520
comparison
Token comparison
Feature activation+0.423
.
Token.
Feature activation+0.000
Many
Token Many
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
Mae
Token Mae
Feature activation+0.000
brings
Token brings
Feature activation+0.081
the
Token the
Feature activation+0.594
"
Token "
Feature activation+0.000
real
Tokenreal
Feature activation+0.000
world
Token world
Feature activation+2.222
"
Token"
Feature activation+3.639
into
Token into
Feature activation+0.362
The
Token The
Feature activation+0.000
Kid
Token Kid
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 0.747 - 1.493
CONTAINS 0.017%

expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
call
Token call
Feature activation+0.000
more
Token more
Feature activation+0.000
witnesses
Token witnesses
Feature activation+0.000
in
Token in
Feature activation+1.047
the
Token the
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.661
to
Token to
Feature activation+0.959
discuss
Token discuss
Feature activation+0.000
the
Token the
Feature activation+0.000
was
Token was
Feature activation+0.000
founded
Token founded
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+1.201
together
Token together
Feature activation+0.000
neuroscience
Token neuroscience
Feature activation+0.000
and
Token and
Feature activation+0.000
leadership
Token leadership
Feature activation+0.392
experts
Token experts
Feature activation+0.679
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.458
best
Token best
Feature activation+0.000
of
Token of
Feature activation+0.000
Broadway
Token Broadway
Feature activation+3.788
to
Token to
Feature activation+0.814
audiences
Token audiences
Feature activation+0.000
who
Token who
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ball
Token ball
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.247
a
Token a
Feature activation+0.496
player
Token player
Feature activation+4.626
to
Token to
Feature activation+1.082
the
Token the
Feature activation+0.178
ball
Token ball
Feature activation+0.000
and
Token and
Feature activation+0.000
move
Token move
Feature activation+0.000
it
Token it
Feature activation+0.000
important
Token important
Feature activation+0.000
and
Token and
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
projects
Token projects
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.984
fruition
Token fruition
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000

INTERVAL 0.000 - 0.747
CONTAINS 99.961%

consider
Token consider
Feature activation+0.000
something
Token something
Feature activation+0.000
proven
Token proven
Feature activation+0.000
unless
Token unless
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
proven
Token proven
Feature activation+0.000
by
Token by
Feature activation+0.000
deduct
Token deduct
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
reasoning
Token reasoning
Feature activation+0.000
Review
Token Review
Feature activation+0.000
,
Token,
Feature activation+0.000
Winter
Token Winter
Feature activation+0.000
1967
Token 1967
Feature activation+0.000
,
Token,
Feature activation+0.000
p
Token p
Feature activation+0.000
.
Token.
Feature activation+0.000
57
Token 57
Feature activation+0.000
]
Token]
Feature activation+0.000
Susan
Token Susan
Feature activation+0.000
S
Token S
Feature activation+0.000
banks
Tokenbanks
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Fair
Token Fair
Feature activation+0.000
banks
Tokenbanks
Feature activation+0.000
North
Token North
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Borough
Token Borough
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
is
Token is
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
represent
Token represent
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
T
TokenT
Feature activation+0.000
un
Tokenun
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
Tun
Token Tun
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
Tun
Token Tun
Feature activation+0.000
"
Token"
Feature activation+0.000
found
Token found
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 H8.4: (feature 15600)

TOP ACTIVATIONS
MAX = 5.343

have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
election
Tokenelection
Feature activation+0.000
times
Token times
Feature activation+0.000
.
Token.
Feature activation+0.000
Prov
Token Prov
Feature activation+0.000
iding
Tokeniding
Feature activation+0.000
your
Token your
Feature activation+1.087
baby
Token baby
Feature activation+5.039
is
Token is
Feature activation+0.000
content
Token content
Feature activation+0.000
,
Token,
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
and
Token and
Feature activation+0.000
happened
Token happened
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
provides
Token provides
Feature activation+0.000
the
Token the
Feature activation+1.619
reader
Token reader
Feature activation+4.797
with
Token with
Feature activation+0.612
a
Token a
Feature activation+0.101
blueprint
Token blueprint
Feature activation+0.000
to
Token to
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
community
Token community
Feature activation+0.000
competition
Token competition
Feature activation+0.000
will
Token will
Feature activation+0.000
provide
Token provide
Feature activation+0.000
you
Token you
Feature activation+4.288
with
Token with
Feature activation+0.541
the
Token the
Feature activation+0.716
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
is
Token is
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
correlated
Token correlated
Feature activation+0.000
,
Token,
Feature activation+0.000
providing
Token providing
Feature activation+0.000
users
Token users
Feature activation+4.131
with
Token with
Feature activation+0.084
a
Token a
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
provide
Token provide
Feature activation+0.000
them
Token them
Feature activation+4.076
with
Token with
Feature activation+0.484
detailed
Token detailed
Feature activation+0.000
blue
Token blue
Feature activation+0.000
prints
Tokenprints
Feature activation+0.000
of
Token of
Feature activation+0.000
s
Tokens
Feature activation+0.000
arrogance
Token arrogance
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
provide
Token provide
Feature activation+0.000
any
Token any
Feature activation+0.137
child
Token child
Feature activation+2.432
with
Token with
Feature activation+1.795
special
Token special
Feature activation+0.000
needs
Token needs
Feature activation+3.971
equipment
Token equipment
Feature activation+0.303
a
Token a
Feature activation+1.469
unique
Token unique
Feature activation+0.000
and
Token and
Feature activation+0.000
custom
Token custom
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
solution
Token solution
Feature activation+0.000
provides
Token provides
Feature activation+0.000
every
Token every
Feature activation+0.000
nation
Token nation
Feature activation+3.861
with
Token with
Feature activation+0.493
that
Token that
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
whilst
Token whilst
Feature activation+0.000
rewarding
Token rewarding
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Those
TokenThose
Feature activation+0.000
moves
Token moves
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Washington
Token Washington
Feature activation+3.635
help
Token help
Feature activation+0.572
on
Token on
Feature activation+0.000
special
Token special
Feature activation+0.000
teams
Token teams
Feature activation+0.000
,
Token,
Feature activation+0.000
We
Token We
Feature activation+0.000
strive
Token strive
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
our
Token our
Feature activation+0.378
fans
Token fans
Feature activation+3.590
the
Token the
Feature activation+0.984
best
Token best
Feature activation+0.071
Blu
Token Blu
Feature activation+0.000
-
Token-
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
which
Token which
Feature activation+0.000
provides
Token provides
Feature activation+0.000
them
Token them
Feature activation+3.581
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
sense
Token sense
Feature activation+0.000
of
Token of
Feature activation+0.000
self
Token self
Feature activation+0.000
the
Token the
Feature activation+0.000
sovereign
Token sovereign
Feature activation+2.168
's
Token's
Feature activation+0.000
eff
Token eff
Feature activation+0.000
ig
Tokenig
Feature activation+0.000
y
Tokeny
Feature activation+3.540
appeared
Token appeared
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
stamp
Token stamp
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
you
Token you
Feature activation+3.236
with
Token with
Feature activation+0.000
materials
Token materials
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
your
Token your
Feature activation+0.000
his
Token his
Feature activation+0.000
group
Token group
Feature activation+0.000
was
Token was
Feature activation+0.000
providing
Token providing
Feature activation+0.000
the
Token the
Feature activation+0.069
government
Token government
Feature activation+3.023
with
Token with
Feature activation+0.509
additional
Token additional
Feature activation+0.000
details
Token details
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+0.230
network
Token network
Feature activation+2.992
with
Token with
Feature activation+0.000
cheaper
Token cheaper
Feature activation+0.000
transactions
Token transactions
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
not
Token not
Feature activation+0.000
provide
Token provide
Feature activation+0.000
"
Token "
Feature activation+0.000
any
Tokenany
Feature activation+1.076
government
Token government
Feature activation+1.579
agency
Token agency
Feature activation+2.899
"
Token"
Feature activation+2.730
with
Token with
Feature activation+0.000
direct
Token direct
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
"
Token "
Feature activation+0.000
any
Tokenany
Feature activation+1.076
government
Token government
Feature activation+1.579
agency
Token agency
Feature activation+2.899
"
Token"
Feature activation+2.730
with
Token with
Feature activation+0.000
direct
Token direct
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
its
Token its
Feature activation+0.000
in
Token in
Feature activation+0.000
Sutherland
Token Sutherland
Feature activation+0.000
Springs
Token Springs
Feature activation+0.000
may
Token may
Feature activation+0.000
provide
Token provide
Feature activation+0.000
new
Token new
Feature activation+2.592
fuel
Token fuel
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000

Top DFA by src position
MAX = 7.307

Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
arrogance
Token arrogance
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
have
Token have
Feature activation+0.005
Top resid features:
provided
Token provided
Feature activation+7.307
Top resid features:
Hillary
Token Hillary
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
Chelsea
Token Chelsea
Feature activation+0.023
Top resid features:
Clinton
Token Clinton
Feature activation+0.143
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
best
Token best
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
times
Token times
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
Prov
Token Prov
Feature activation+0.354
Top resid features:
iding
Tokeniding
Feature activation+6.548
Top resid features:
your
Token your
Feature activation+0.291
Top resid features:
baby
Token baby
Feature activation-0.043
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
content
Token content
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
session
Token session
Feature activation+0.081
Top resid features:
that
Token that
Feature activation+0.071
Top resid features:
happened
Token happened
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.109
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
provides
Token provides
Feature activation+6.026
Top resid features:
the
Token the
Feature activation+0.381
Top resid features:
reader
Token reader
Feature activation+0.216
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
blueprint
Token blueprint
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.004
Top resid features:
upcoming
Token upcoming
Feature activation-0.010
Top resid features:
community
Token community
Feature activation+0.012
Top resid features:
competition
Token competition
Feature activation+0.046
Top resid features:
will
Token will
Feature activation+0.031
Top resid features:
provide
Token provide
Feature activation+5.950
Top resid features:
you
Token you
Feature activation+0.165
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
opportunity
Token opportunity
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.028
Top resid features:
automatically
Token automatically
Feature activation-0.043
Top resid features:
correlated
Token correlated
Feature activation-0.089
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
providing
Token providing
Feature activation+5.915
Top resid features:
users
Token users
Feature activation+0.140
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
comprehensive
Token comprehensive
Feature activation+0.000
Top resid features:
view
Token view
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.022
Top resid features:
them
Token them
Feature activation-0.043
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
it
Token it
Feature activation-0.013
Top resid features:
would
Token would
Feature activation-0.023
Top resid features:
provide
Token provide
Feature activation+6.356
Top resid features:
them
Token them
Feature activation+0.164
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
detailed
Token detailed
Feature activation+0.000
Top resid features:
blue
Token blue
Feature activation+0.000
Top resid features:
prints
Tokenprints
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation-0.010
Top resid features:
arrogance
Token arrogance
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
have
Token have
Feature activation-0.009
Top resid features:
provided
Token provided
Feature activation+6.062
Top resid features:
Hillary
Token Hillary
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Chelsea
Token Chelsea
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
mission
Token mission
Feature activation-0.010
Top resid features:
is
Token is
Feature activation-0.027
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
to
Tokento
Feature activation+0.013
Top resid features:
provide
Token provide
Feature activation+5.804
Top resid features:
any
Token any
Feature activation+0.065
Top resid features:
child
Token child
Feature activation+0.204
Top resid features:
with
Token with
Feature activation+0.144
Top resid features:
special
Token special
Feature activation+0.039
Top resid features:
needs
Token needs
Feature activation+0.025
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
2021
Token 2021
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.046
Top resid features:
This
Token This
Feature activation+0.008
Top resid features:
solution
Token solution
Feature activation-0.055
Top resid features:
provides
Token provides
Feature activation+5.856
Top resid features:
every
Token every
Feature activation+0.088
Top resid features:
nation
Token nation
Feature activation+0.007
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
opportunity
Token opportunity
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
arrogance
Token arrogance
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
have
Token have
Feature activation+0.005
Top resid features:
provided
Token provided
Feature activation+5.788
Top resid features:
Hillary
Token Hillary
Feature activation+0.062
Top resid features:
and
Token and
Feature activation-0.060
Top resid features:
Chelsea
Token Chelsea
Feature activation+0.039
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Those
TokenThose
Feature activation+0.020
Top resid features:
moves
Token moves
Feature activation-0.025
Top resid features:
provided
Token provided
Feature activation+5.368
Top resid features:
Washington
Token Washington
Feature activation+0.230
Top resid features:
help
Token help
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
special
Token special
Feature activation+0.000
Top resid features:
teams
Token teams
Feature activation+0.000
Top resid features:
Friday
TokenFriday
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
We
Token We
Feature activation+0.011
Top resid features:
strive
Token strive
Feature activation-0.041
Top resid features:
to
Token to
Feature activation-0.075
Top resid features:
provide
Token provide
Feature activation+5.094
Top resid features:
our
Token our
Feature activation+0.379
Top resid features:
fans
Token fans
Feature activation+0.134
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
best
Token best
Feature activation+0.000
Top resid features:
Blu
Token Blu
Feature activation+0.000
Top resid features:
consciousness
Token consciousness
Feature activation+0.056
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ŀ
TokenĿ
Feature activation+0.070
Top resid features:
which
Token which
Feature activation+0.115
Top resid features:
provides
Token provides
Feature activation+4.987
Top resid features:
them
Token them
Feature activation+0.192
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
sense
Token sense
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.019
Top resid features:
foreign
Token foreign
Feature activation-0.021
Top resid features:
post
Token post
Feature activation+0.000
Top resid features:
offices
Token offices
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
provided
Token provided
Feature activation+5.054
Top resid features:
the
Token the
Feature activation+0.141
Top resid features:
sovereign
Token sovereign
Feature activation+0.030
Top resid features:
's
Token's
Feature activation+0.215
Top resid features:
eff
Token eff
Feature activation-0.096
Top resid features:
ig
Tokenig
Feature activation+0.004
Top resid features:
customers
Token customers
Feature activation+0.053
Top resid features:
are
Token are
Feature activation+0.025
Top resid features:
rarely
Token rarely
Feature activation-0.012
Top resid features:
going
Token going
Feature activation-0.016
Top resid features:
to
Token to
Feature activation+0.106
Top resid features:
provide
Token provide
Feature activation+4.898
Top resid features:
you
Token you
Feature activation+0.123
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
materials
Token materials
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
said
Token said
Feature activation-0.050
Top resid features:
his
Token his
Feature activation+0.003
Top resid features:
group
Token group
Feature activation+0.001
Top resid features:
was
Token was
Feature activation-0.008
Top resid features:
providing
Token providing
Feature activation+4.550
Top resid features:
the
Token the
Feature activation+0.600
Top resid features:
government
Token government
Feature activation+0.090
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
additional
Token additional
Feature activation+0.000
Top resid features:
details
Token details
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.016
Top resid features:
software
Token software
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
order
Token order
Feature activation+0.034
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
provide
Token provide
Feature activation+3.831
Top resid features:
the
Token the
Feature activation+0.756
Top resid features:
network
Token network
Feature activation+0.188
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
cheaper
Token cheaper
Feature activation+0.000
Top resid features:
transactions
Token transactions
Feature activation+0.000
Top resid features:
Apple
Token Apple
Feature activation+0.004
Top resid features:
claims
Token claims
Feature activation-0.017
Top resid features:
it
Token it
Feature activation-0.004
Top resid features:
does
Token does
Feature activation-0.011
Top resid features:
not
Token not
Feature activation+0.051
Top resid features:
provide
Token provide
Feature activation+4.885
Top resid features:
"
Token "
Feature activation+0.140
Top resid features:
any
Tokenany
Feature activation+0.076
Top resid features:
government
Token government
Feature activation+0.066
Top resid features:
agency
Token agency
Feature activation+0.034
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
Apple
Token Apple
Feature activation+0.014
Top resid features:
claims
Token claims
Feature activation-0.013
Top resid features:
it
Token it
Feature activation-0.013
Top resid features:
does
Token does
Feature activation-0.006
Top resid features:
not
Token not
Feature activation+0.134
Top resid features:
provide
Token provide
Feature activation+4.625
Top resid features:
"
Token "
Feature activation-0.017
Top resid features:
any
Tokenany
Feature activation+0.019
Top resid features:
government
Token government
Feature activation+0.083
Top resid features:
agency
Token agency
Feature activation+0.071
Top resid features:
"
Token"
Feature activation+0.034
Top resid features:
killings
Token killings
Feature activation-0.008
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
Sutherland
Token Sutherland
Feature activation-0.002
Top resid features:
Springs
Token Springs
Feature activation-0.000
Top resid features:
may
Token may
Feature activation+0.132
Top resid features:
provide
Token provide
Feature activation+4.223
Top resid features:
new
Token new
Feature activation+0.251
Top resid features:
fuel
Token fuel
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
anti
Token anti
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.03

Head 3: 0.02

Head 4: 0.57

Head 5: 0.05

Head 6: 0.02

Head 7: 0.12

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

with2.31

dots1.91

opportunities1.87

fodder1.83

necessities1.80

sust1.80

ample1.76

with1.76

succ1.71

hra1.70

WITH1.69

avenues1.69

avenue1.69

ammunition1.64

iciency1.63

cushion1.63

With1.62

With1.62

remedies1.61

itions1.60

Negative logits

quickShipAvailable-2.75

soType-2.22

tera-2.08

inventoryQuantity-2.02

utenberg-1.83

¨-1.81

disagrees-1.71

viol-1.69

erno-1.68

ovie-1.68

footsteps-1.67

intend-1.66

ipel-1.65

EStream-1.63

cens-1.63

anship-1.62

scl-1.61

tone-1.60

onson-1.60

SCP-1.60

INTERVAL 4.809 - 5.343
CONTAINS 0.000%

have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
election
Tokenelection
Feature activation+0.000
times
Token times
Feature activation+0.000
.
Token.
Feature activation+0.000
Prov
Token Prov
Feature activation+0.000
iding
Tokeniding
Feature activation+0.000
your
Token your
Feature activation+1.087
baby
Token baby
Feature activation+5.039
is
Token is
Feature activation+0.000
content
Token content
Feature activation+0.000
,
Token,
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 4.274 - 4.809
CONTAINS 0.000%

upcoming
Token upcoming
Feature activation+0.000
community
Token community
Feature activation+0.000
competition
Token competition
Feature activation+0.000
will
Token will
Feature activation+0.000
provide
Token provide
Feature activation+0.000
you
Token you
Feature activation+4.288
with
Token with
Feature activation+0.541
the
Token the
Feature activation+0.716
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
happened
Token happened
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
provides
Token provides
Feature activation+0.000
the
Token the
Feature activation+1.619
reader
Token reader
Feature activation+4.797
with
Token with
Feature activation+0.612
a
Token a
Feature activation+0.101
blueprint
Token blueprint
Feature activation+0.000
to
Token to
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000

INTERVAL 3.740 - 4.274
CONTAINS 0.001%

them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
provide
Token provide
Feature activation+0.000
them
Token them
Feature activation+4.076
with
Token with
Feature activation+0.484
detailed
Token detailed
Feature activation+0.000
blue
Token blue
Feature activation+0.000
prints
Tokenprints
Feature activation+0.000
of
Token of
Feature activation+0.000
s
Tokens
Feature activation+0.000
arrogance
Token arrogance
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
provide
Token provide
Feature activation+0.000
any
Token any
Feature activation+0.137
child
Token child
Feature activation+2.432
with
Token with
Feature activation+1.795
special
Token special
Feature activation+0.000
needs
Token needs
Feature activation+3.971
equipment
Token equipment
Feature activation+0.303
a
Token a
Feature activation+1.469
unique
Token unique
Feature activation+0.000
and
Token and
Feature activation+0.000
custom
Token custom
Feature activation+0.000
is
Token is
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
correlated
Token correlated
Feature activation+0.000
,
Token,
Feature activation+0.000
providing
Token providing
Feature activation+0.000
users
Token users
Feature activation+4.131
with
Token with
Feature activation+0.084
a
Token a
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
solution
Token solution
Feature activation+0.000
provides
Token provides
Feature activation+0.000
every
Token every
Feature activation+0.000
nation
Token nation
Feature activation+3.861
with
Token with
Feature activation+0.493
that
Token that
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
whilst
Token whilst
Feature activation+0.000
rewarding
Token rewarding
Feature activation+0.000

INTERVAL 3.206 - 3.740
CONTAINS 0.001%

are
Token are
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
you
Token you
Feature activation+3.236
with
Token with
Feature activation+0.000
materials
Token materials
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
your
Token your
Feature activation+0.000
the
Token the
Feature activation+0.000
sovereign
Token sovereign
Feature activation+2.168
's
Token's
Feature activation+0.000
eff
Token eff
Feature activation+0.000
ig
Tokenig
Feature activation+0.000
y
Tokeny
Feature activation+3.540
appeared
Token appeared
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
stamp
Token stamp
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
strive
Token strive
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
our
Token our
Feature activation+0.378
fans
Token fans
Feature activation+3.590
the
Token the
Feature activation+0.984
best
Token best
Feature activation+0.071
Blu
Token Blu
Feature activation+0.000
-
Token-
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Those
TokenThose
Feature activation+0.000
moves
Token moves
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Washington
Token Washington
Feature activation+3.635
help
Token help
Feature activation+0.572
on
Token on
Feature activation+0.000
special
Token special
Feature activation+0.000
teams
Token teams
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.672 - 3.206
CONTAINS 0.001%

his
Token his
Feature activation+0.000
group
Token group
Feature activation+0.000
was
Token was
Feature activation+0.000
providing
Token providing
Feature activation+0.000
the
Token the
Feature activation+0.069
government
Token government
Feature activation+3.023
with
Token with
Feature activation+0.509
additional
Token additional
Feature activation+0.000
details
Token details
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+0.230
network
Token network
Feature activation+2.992
with
Token with
Feature activation+0.000
cheaper
Token cheaper
Feature activation+0.000
transactions
Token transactions
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
not
Token not
Feature activation+0.000
provide
Token provide
Feature activation+0.000
"
Token "
Feature activation+0.000
any
Tokenany
Feature activation+1.076
government
Token government
Feature activation+1.579
agency
Token agency
Feature activation+2.899
"
Token"
Feature activation+2.730
with
Token with
Feature activation+0.000
direct
Token direct
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
"
Token "
Feature activation+0.000
any
Tokenany
Feature activation+1.076
government
Token government
Feature activation+1.579
agency
Token agency
Feature activation+2.899
"
Token"
Feature activation+2.730
with
Token with
Feature activation+0.000
direct
Token direct
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
its
Token its
Feature activation+0.000

INTERVAL 2.137 - 2.672
CONTAINS 0.002%

were
Token were
Feature activation+0.000
required
Token required
Feature activation+0.000
to
Token to
Feature activation+0.000
supply
Token supply
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+2.249
with
Token with
Feature activation+0.000
warrants
Token warrants
Feature activation+0.000
to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
future
Token future
Feature activation+0.000
will
Token will
Feature activation+0.000
provide
Token provide
Feature activation+0.000
250
Token 250
Feature activation+0.000
billion
Token billion
Feature activation+0.000
British
Token British
Feature activation+0.260
pounds
Token pounds
Feature activation+2.441
0
Token 0
Feature activation+0.000
:
Token:
Feature activation+0.000
53
Token53
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
task
Token task
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
provide
Token provide
Feature activation+0.000
them
Token them
Feature activation+2.257
a
Token a
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
digital
Token digital
Feature activation+0.000
reinforcement
Token reinforcement
Feature activation+0.000
of
Token of
Feature activation+0.000
providing
Token providing
Feature activation+0.000
a
Token a
Feature activation+0.000
working
Token working
Feature activation+0.000
-
Token-
Feature activation+0.000
class
Tokenclass
Feature activation+2.266
and
Token and
Feature activation+0.000
peoples
Token peoples
Feature activation+1.970
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
solution
Token solution
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
to
Tokento
Feature activation+0.000
provide
Token provide
Feature activation+0.000
any
Token any
Feature activation+0.137
child
Token child
Feature activation+2.432
with
Token with
Feature activation+1.795
special
Token special
Feature activation+0.000
needs
Token needs
Feature activation+3.971
equipment
Token equipment
Feature activation+0.303
a
Token a
Feature activation+1.469

INTERVAL 1.603 - 2.137
CONTAINS 0.002%

provided
Token provided
Feature activation+0.000
a
Token a
Feature activation+0.381
w
Token w
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
abe
Tokenabe
Feature activation+0.383
terrorist
Token terrorist
Feature activation+2.091
with
Token with
Feature activation+0.992
dummy
Token dummy
Feature activation+0.000
explosives
Token explosives
Feature activation+0.339
loaded
Token loaded
Feature activation+0.000
in
Token in
Feature activation+0.000
agency
Token agency
Feature activation+0.000
that
Token that
Feature activation+0.000
provides
Token provides
Feature activation+0.000
finance
Token finance
Feature activation+0.160
and
Token and
Feature activation+0.000
accounting
Token accounting
Feature activation+2.053
services
Token services
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Pentagon
Token Pentagon
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
RT
Token RT
Feature activation+0.000
since
Token since
Feature activation+0.000
my
Token my
Feature activation+0.000
jewelry
Token jewelry
Feature activation+0.000
provides
Token provides
Feature activation+0.000
me
Token me
Feature activation+2.123
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
accuracy
Token accuracy
Feature activation+0.000
,
Token,
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
has
Token has
Feature activation+0.000
supplied
Token supplied
Feature activation+0.000
Bast
Token Bast
Feature activation+0.000
ion
Tokenion
Feature activation+1.979
coastal
Token coastal
Feature activation+0.000
missile
Token missile
Feature activation+0.000
systems
Token systems
Feature activation+0.605
with
Token with
Feature activation+0.000
Y
Token Y
Feature activation+0.000
provided
Token provided
Feature activation+0.000
Hillary
Token Hillary
Feature activation+3.987
and
Token and
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+3.701
Clinton
Token Clinton
Feature activation+5.343
with
Token with
Feature activation+1.933
favorable
Token favorable
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
election
Tokenelection
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000

INTERVAL 1.069 - 1.603
CONTAINS 0.002%

.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
also
Token also
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+1.224
standards
Token standards
Feature activation+1.103
for
Token for
Feature activation+0.000
financial
Token financial
Feature activation+0.000
cards
Token cards
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
provide
Token provide
Feature activation+0.000
"
Token "
Feature activation+0.000
any
Tokenany
Feature activation+1.076
government
Token government
Feature activation+1.579
agency
Token agency
Feature activation+2.899
"
Token"
Feature activation+2.730
with
Token with
Feature activation+0.000
direct
Token direct
Feature activation+0.000
access
Token access
Feature activation+0.000
,
Token,
Feature activation+0.000
headquartered
Token headquartered
Feature activation+0.000
at
Token at
Feature activation+0.000
Rochester
Token Rochester
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
of
Token of
Feature activation+1.114
Technology
Token Technology
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
),
Token),
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Changing
TokenChanging
Feature activation+0.000
technology
Token technology
Feature activation+0.000
has
Token has
Feature activation+0.000
provided
Token provided
Feature activation+0.000
some
Token some
Feature activation+1.315
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.753
momentum
Token momentum
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
De
Token De
Feature activation+0.000
utsch
Tokenutsch
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
provided
Tokenprovided
Feature activation+0.000
no
Token no
Feature activation+1.160
evidence
Token evidence
Feature activation+0.000
to
Token to
Feature activation+0.000
i
Token i
Feature activation+0.000
Media
TokenMedia
Feature activation+0.000
Eth
TokenEth
Feature activation+0.000

INTERVAL 0.534 - 1.069
CONTAINS 0.006%

arms
Token arms
Feature activation+0.000
provided
Token provided
Feature activation+0.000
by
Token by
Feature activation+0.000
Lockheed
Token Lockheed
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
to
Token to
Feature activation+0.680
Israel
Token Israel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
very
Token very
Feature activation+0.000
same
Token same
Feature activation+0.000
ial
Tokenial
Feature activation+0.000
of
Token of
Feature activation+0.000
Service
Token Service
Feature activation+0.256
(
Token (
Feature activation+0.000
DoS
TokenDoS
Feature activation+0.000
)
Token)
Feature activation+0.671
attack
Token attack
Feature activation+0.000
prevention
Token prevention
Feature activation+0.131
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
CR
TokenCR
Feature activation+0.000
TA
TokenTA
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
a
Token a
Feature activation+0.497
written
Token written
Feature activation+1.044
response
Token response
Feature activation+0.000
to
Token to
Feature activation+0.000
FTA
Token FTA
Feature activation+0.000
's
Token's
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
gradient
Token gradient
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
provided
Token provided
Feature activation+0.000
a
Token a
Feature activation+0.000
chemical
Token chemical
Feature activation+0.745
energy
Token energy
Feature activation+0.000
source
Token source
Feature activation+0.000
for
Token for
Feature activation+0.000
microbes
Token microbes
Feature activation+0.000
.
Token.
Feature activation+0.000
P
TokenP
Feature activation+0.000
2
Token2
Feature activation+0.000
results
Token results
Feature activation+0.000
could
Token could
Feature activation+0.000
provide
Token provide
Feature activation+0.000
the
Token the
Feature activation+0.908
best
Token best
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000

INTERVAL 0.000 - 0.534
CONTAINS 99.987%

and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
take
Token take
Feature activation+0.000
enough
Token enough
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
halluc
Token halluc
Feature activation+0.000
inate
Tokeninate
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
digital
Token digital
Feature activation+0.000
age
Token age
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
But
Token But
Feature activation+0.000
after
Token after
Feature activation+0.000
some
Token some
Feature activation+0.000
arm
Token arm
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
punt
Token punt
Feature activation+0.000
return
Token return
Feature activation+0.000
unit
Token unit
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
been
Token been
Feature activation+0.000
desk
Token desk
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Search
TokenSearch
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Adv
TokenAdv
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Beginning
Token Beginning
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
of
Token of
Feature activation+0.000
mult
Token mult
Feature activation+0.000
ilateral
Tokenilateral
Feature activation+0.000
institutions
Token institutions
Feature activation+0.000
are
Token are
Feature activation+0.000
selected
Token selected
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
process
Token process
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H8.4: (feature 2802)

TOP ACTIVATIONS
MAX = 8.722

machine
Token machine
Feature activation+0.000
and
Token and
Feature activation+0.000
air
Token air
Feature activation+0.000
condition
Token condition
Feature activation+0.000
er
Tokener
Feature activation+3.163
)
Token)
Feature activation+8.722
âĢĵ
Token âĢĵ
Feature activation+0.000
popular
Token popular
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.431
Internet
Token Internet
Feature activation+2.533
-
Token-
Feature activation+0.000
connected
Tokenconnected
Feature activation+0.000
devices
Token devices
Feature activation+8.545
(
Token (
Feature activation+0.000
pr
Tokenpr
Feature activation+0.000
inter
Tokeninter
Feature activation+0.000
,
Token,
Feature activation+0.000
washing
Token washing
Feature activation+0.000
enabled
Token enabled
Feature activation+0.000
and
Token and
Feature activation+0.000
users
Token users
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+8.292
off
Token off
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Additional
TokenAdditional
Feature activation+0.000
be
Token be
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.000
that
Token that
Feature activation+0.000
turns
Token turns
Feature activation+0.000
teams
Token teams
Feature activation+8.242
off
Token off
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
your
Token your
Feature activation+1.163
Twitter
Token Twitter
Feature activation+3.150
frown
Token frown
Feature activation+6.115
s
Tokens
Feature activation+8.110
upside
Token upside
Feature activation+0.221
down
Token down
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
turned
Token turned
Feature activation+0.000
my
Token my
Feature activation+0.261
view
Token view
Feature activation+3.439
of
Token of
Feature activation+0.000
computer
Token computer
Feature activation+0.000
science
Token science
Feature activation+8.067
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.084
head
Token head
Feature activation+0.000
in
Token in
Feature activation+0.000
less
Token less
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
turn
Token turn
Feature activation+0.000
that
Token that
Feature activation+7.717
concept
Token concept
Feature activation+8.020
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+0.000
?
Token?
Feature activation+0.000
When
Token When
Feature activation+0.000
of
Token of
Feature activation+0.000
human
Token human
Feature activation+0.000
biodiversity
Token biodiversity
Feature activation+0.000
without
Token without
Feature activation+0.000
turning
Token turning
Feature activation+0.000
it
Token it
Feature activation+8.019
into
Token into
Feature activation+0.000
an
Token an
Feature activation+0.000
ideology
Token ideology
Feature activation+0.000
of
Token of
Feature activation+0.000
dehuman
Token dehuman
Feature activation+0.000
in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+7.948
off
Token off
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
track
Token track
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
since
Token since
Feature activation+0.000
turned
Token turned
Feature activation+0.000
Alabama
Token Alabama
Feature activation+7.944
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
sport
Token sport
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
modular
Token modular
Feature activation+0.000
phone
Token phone
Feature activation+0.000
without
Token without
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+1.298
device
Token device
Feature activation+7.925
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
notes
Token notes
Feature activation+0.000
the
Token the
Feature activation+0.000
Phone
Token Phone
Feature activation+0.000
problems
Token problems
Feature activation+0.000
turned
Token turned
Feature activation+0.000
Kris
Token Kris
Feature activation+1.115
py
Tokenpy
Feature activation+7.361
K
Token K
Feature activation+0.000
reme
Tokenreme
Feature activation+7.838
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
textbook
Token textbook
Feature activation+0.000
debacle
Token debacle
Feature activation+0.000
for
Token for
Feature activation+0.000
-
Token-
Feature activation+0.000
square
Tokensquare
Feature activation+0.000
-
Token-
Feature activation+0.000
foot
Tokenfoot
Feature activation+1.415
dup
Token dup
Feature activation+0.000
lex
Tokenlex
Feature activation+7.777
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
example
Token example
Feature activation+0.000
for
Token for
Feature activation+0.000
brief
Token brief
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
the
Token the
Feature activation+1.282
proposals
Token proposals
Feature activation+7.772
into
Token into
Feature activation+0.000
law
Token law
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.444
hit
Token hit
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
turn
Token turn
Feature activation+0.000
that
Token that
Feature activation+7.717
concept
Token concept
Feature activation+8.020
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+0.000
?
Token?
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+7.715
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
*
Token *
Feature activation+0.000
H
TokenH
Feature activation+0.000
oor
Tokenoor
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
will
Token will
Feature activation+0.000
turn
Token turn
Feature activation+0.000
you
Token you
Feature activation+7.418
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
problems
Token problems
Feature activation+0.000
turned
Token turned
Feature activation+0.000
Kris
Token Kris
Feature activation+1.115
py
Tokenpy
Feature activation+7.361
K
Token K
Feature activation+0.000
reme
Tokenreme
Feature activation+7.838
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
textbook
Token textbook
Feature activation+0.000
,
Token,
Feature activation+0.000
turn
Token turn
Feature activation+0.000
the
Token the
Feature activation+0.872
leftover
Token leftover
Feature activation+3.688
coffee
Token coffee
Feature activation+5.950
grounds
Token grounds
Feature activation+7.311
into
Token into
Feature activation+0.000
compost
Token compost
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
recycle
Token recycle
Feature activation+0.000
muscular
Token muscular
Feature activation+0.000
,
Token,
Feature activation+0.000
brain
Token brain
Feature activation+0.000
y
Tokeny
Feature activation+0.000
r
Token r
Feature activation+0.000
iffs
Tokeniffs
Feature activation+7.299
into
Token into
Feature activation+0.000
accessible
Token accessible
Feature activation+0.000
,
Token,
Feature activation+0.000
catchy
Token catchy
Feature activation+0.000
songs
Token songs
Feature activation+0.000

Top DFA by src position
MAX = 10.076

hack
Token hack
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
potential
Token potential
Feature activation+0.038
Top resid features:
to
Token to
Feature activation-0.019
Top resid features:
turn
Token turn
Feature activation+9.756
Top resid features:
Internet
Token Internet
Feature activation+0.055
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
connected
Tokenconnected
Feature activation+0.076
Top resid features:
devices
Token devices
Feature activation+0.591
Top resid features:
(
Token (
Feature activation-0.010
Top resid features:
hack
Token hack
Feature activation-0.006
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
potential
Token potential
Feature activation+0.055
Top resid features:
to
Token to
Feature activation-0.029
Top resid features:
turn
Token turn
Feature activation+10.076
Top resid features:
Internet
Token Internet
Feature activation+0.094
Top resid features:
-
Token-
Feature activation+0.010
Top resid features:
connected
Tokenconnected
Feature activation+0.112
Top resid features:
devices
Token devices
Feature activation+0.141
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
permanently
Token permanently
Feature activation-0.055
Top resid features:
enabled
Token enabled
Feature activation+0.116
Top resid features:
and
Token and
Feature activation-0.036
Top resid features:
users
Token users
Feature activation+0.094
Top resid features:
cannot
Token cannot
Feature activation-0.029
Top resid features:
turn
Token turn
Feature activation+9.663
Top resid features:
it
Token it
Feature activation+0.123
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
could
Token could
Feature activation-0.006
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
an
Token an
Feature activation+0.016
Top resid features:
issue
Token issue
Feature activation-0.010
Top resid features:
that
Token that
Feature activation+0.072
Top resid features:
turns
Token turns
Feature activation+9.453
Top resid features:
teams
Token teams
Feature activation+0.029
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
though
Token though
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
udding
Tokenudding
Feature activation-0.001
Top resid features:
brand
Token brand
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
looking
Token looking
Feature activation+0.044
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
turn
Token turn
Feature activation+8.593
Top resid features:
your
Token your
Feature activation+0.377
Top resid features:
Twitter
Token Twitter
Feature activation+0.219
Top resid features:
frown
Token frown
Feature activation+0.458
Top resid features:
s
Tokens
Feature activation+0.182
Top resid features:
upside
Token upside
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.004
Top resid features:
instantaneous
Token instantaneous
Feature activation+0.004
Top resid features:
enlightenment
Token enlightenment
Feature activation-0.005
Top resid features:
experience
Token experience
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.031
Top resid features:
turned
Token turned
Feature activation+9.001
Top resid features:
my
Token my
Feature activation+0.352
Top resid features:
view
Token view
Feature activation+0.400
Top resid features:
of
Token of
Feature activation+0.230
Top resid features:
computer
Token computer
Feature activation+0.048
Top resid features:
science
Token science
Feature activation+0.044
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
e
Token e
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
mail
Tokenmail
Feature activation-0.018
Top resid features:
marketing
Token marketing
Feature activation-0.045
Top resid features:
turn
Token turn
Feature activation+9.368
Top resid features:
that
Token that
Feature activation+0.482
Top resid features:
concept
Token concept
Feature activation+0.069
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
reality
Token reality
Feature activation+0.000
Top resid features:
knowledge
Token knowledge
Feature activation-0.070
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
human
Token human
Feature activation-0.015
Top resid features:
biodiversity
Token biodiversity
Feature activation-0.041
Top resid features:
without
Token without
Feature activation+0.623
Top resid features:
turning
Token turning
Feature activation+9.024
Top resid features:
it
Token it
Feature activation+0.132
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ideology
Token ideology
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
others
Token others
Feature activation-0.006
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
place
Token place
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
but
Token but
Feature activation+0.155
Top resid features:
turn
Token turn
Feature activation+9.087
Top resid features:
it
Token it
Feature activation+0.273
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
track
Token track
Feature activation+0.000
Top resid features:
Saban
Token Saban
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
who
Token who
Feature activation-0.016
Top resid features:
has
Token has
Feature activation+0.008
Top resid features:
since
Token since
Feature activation+0.037
Top resid features:
turned
Token turned
Feature activation+9.565
Top resid features:
Alabama
Token Alabama
Feature activation+0.074
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
sport
Token sport
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Project
Token Project
Feature activation-0.005
Top resid features:
Ara
Token Ara
Feature activation+0.016
Top resid features:
modular
Token modular
Feature activation+0.048
Top resid features:
phone
Token phone
Feature activation+0.008
Top resid features:
without
Token without
Feature activation+0.151
Top resid features:
turning
Token turning
Feature activation+9.236
Top resid features:
the
Token the
Feature activation+0.299
Top resid features:
device
Token device
Feature activation+0.038
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
notes
Token notes
Feature activation+0.000
Top resid features:
accounting
Token accounting
Feature activation-0.044
Top resid features:
practices
Token practices
Feature activation-0.015
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
other
Token other
Feature activation+0.016
Top resid features:
problems
Token problems
Feature activation+0.011
Top resid features:
turned
Token turned
Feature activation+9.667
Top resid features:
Kris
Token Kris
Feature activation+0.055
Top resid features:
py
Tokenpy
Feature activation+0.006
Top resid features:
K
Token K
Feature activation+0.015
Top resid features:
reme
Tokenreme
Feature activation+0.023
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
That
TokenThat
Feature activation+0.007
Top resid features:
has
Token has
Feature activation-0.004
Top resid features:
turned
Token turned
Feature activation+8.868
Top resid features:
the
Token the
Feature activation+0.582
Top resid features:
six
Token six
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
bedroom
Tokenbedroom
Feature activation-0.034
Top resid features:
,
Token,
Feature activation-0.060
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
A
TokenA
Feature activation-0.017
Top resid features:
brief
Token brief
Feature activation-0.022
Top resid features:
attempt
Token attempt
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.075
Top resid features:
turn
Token turn
Feature activation+7.862
Top resid features:
the
Token the
Feature activation+1.532
Top resid features:
proposals
Token proposals
Feature activation+0.152
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
law
Token law
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
e
Token e
Feature activation-0.003
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
mail
Tokenmail
Feature activation-0.062
Top resid features:
marketing
Token marketing
Feature activation-0.070
Top resid features:
turn
Token turn
Feature activation+9.679
Top resid features:
that
Token that
Feature activation+0.120
Top resid features:
concept
Token concept
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
reality
Token reality
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.108
Top resid features:
Ļ
TokenĻ
Feature activation+0.026
Top resid features:
ve
Tokenve
Feature activation+0.020
Top resid features:
decided
Token decided
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.113
Top resid features:
turn
Token turn
Feature activation+8.821
Top resid features:
it
Token it
Feature activation+0.292
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
*
Token *
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.023
Top resid features:
âĢ
Token âĢ
Feature activation+0.056
Top resid features:
ľ
Tokenľ
Feature activation+0.055
Top resid features:
this
Tokenthis
Feature activation-0.045
Top resid features:
will
Token will
Feature activation+0.019
Top resid features:
turn
Token turn
Feature activation+8.811
Top resid features:
you
Token you
Feature activation+0.061
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
man
Token man
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
accounting
Token accounting
Feature activation-0.011
Top resid features:
practices
Token practices
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
other
Token other
Feature activation+0.003
Top resid features:
problems
Token problems
Feature activation-0.004
Top resid features:
turned
Token turned
Feature activation+8.868
Top resid features:
Kris
Token Kris
Feature activation+0.122
Top resid features:
py
Tokenpy
Feature activation-0.038
Top resid features:
K
Token K
Feature activation+0.000
Top resid features:
reme
Tokenreme
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
open
Token open
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
discarded
Token discarded
Feature activation-0.042
Top resid features:
cups
Token cups
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.044
Top resid features:
turn
Token turn
Feature activation+8.580
Top resid features:
the
Token the
Feature activation+0.378
Top resid features:
leftover
Token leftover
Feature activation-0.015
Top resid features:
coffee
Token coffee
Feature activation+0.089
Top resid features:
grounds
Token grounds
Feature activation+0.042
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.028
Top resid features:
does
Token does
Feature activation-0.027
Top resid features:
well
Token well
Feature activation-0.018
Top resid features:
.
Token.
Feature activation+0.074
Top resid features:
They
Token They
Feature activation-0.066
Top resid features:
turn
Token turn
Feature activation+9.361
Top resid features:
muscular
Token muscular
Feature activation+0.066
Top resid features:
,
Token,
Feature activation-0.042
Top resid features:
brain
Token brain
Feature activation+0.041
Top resid features:
y
Tokeny
Feature activation+0.045
Top resid features:
r
Token r
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.02

Head 3: 0.04

Head 4: 0.56

Head 5: 0.07

Head 6: 0.02

Head 7: 0.11

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

into4.32

into3.66

Into3.47

INTO3.13

onto2.57

sideways2.27

vil2.19

2.02

toward2.00

upside1.96

overboard1.95

heel1.87

inward1.83

azard1.81

osphere1.81

razy1.80

wig1.80

rador1.77

away1.77

frown1.75

Negative logits

explain-1.94

Reasons-1.88

ptoms-1.85

addons-1.76

覚醒-1.75

]).-1.73

adequ-1.70

Dimensions-1.65

cope-1.64

rising-1.62

regate-1.61

nor-1.59

organise-1.59

onement-1.58

compensate-1.56

explaining-1.55

Updated-1.55

Proof-1.54

Leilan-1.53

unique-1.53

INTERVAL 7.850 - 8.722
CONTAINS 0.001%

in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+7.948
off
Token off
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
track
Token track
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
turn
Token turn
Feature activation+0.000
that
Token that
Feature activation+7.717
concept
Token concept
Feature activation+8.020
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+0.000
?
Token?
Feature activation+0.000
When
Token When
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
your
Token your
Feature activation+1.163
Twitter
Token Twitter
Feature activation+3.150
frown
Token frown
Feature activation+6.115
s
Tokens
Feature activation+8.110
upside
Token upside
Feature activation+0.221
down
Token down
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
be
Token be
Feature activation+0.000
an
Token an
Feature activation+0.000
issue
Token issue
Feature activation+0.000
that
Token that
Feature activation+0.000
turns
Token turns
Feature activation+0.000
teams
Token teams
Feature activation+8.242
off
Token off
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
modular
Token modular
Feature activation+0.000
phone
Token phone
Feature activation+0.000
without
Token without
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+1.298
device
Token device
Feature activation+7.925
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
notes
Token notes
Feature activation+0.000
the
Token the
Feature activation+0.000
Phone
Token Phone
Feature activation+0.000

INTERVAL 6.978 - 7.850
CONTAINS 0.002%

asked
Token asked
Feature activation+0.000
Oregon
Token Oregon
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
him
Token him
Feature activation+7.064
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
will
Token will
Feature activation+0.000
turn
Token turn
Feature activation+0.000
you
Token you
Feature activation+7.418
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
This
Token This
Feature activation+0.000
progress
Token progress
Feature activation+0.000
has
Token has
Feature activation+0.000
quietly
Token quietly
Feature activation+0.000
turned
Token turned
Feature activation+0.000
him
Token him
Feature activation+7.123
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
lockdown
Token lockdown
Feature activation+0.000
corner
Token corner
Feature activation+0.000
.
Token.
Feature activation+0.000
recycle
Token recycle
Feature activation+0.000
bots
Tokenbots
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
plastic
Token plastic
Feature activation+2.899
waste
Token waste
Feature activation+7.082
into
Token into
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
printing
Token printing
Feature activation+0.000
filament
Token filament
Feature activation+0.000
muscular
Token muscular
Feature activation+0.000
,
Token,
Feature activation+0.000
brain
Token brain
Feature activation+0.000
y
Tokeny
Feature activation+0.000
r
Token r
Feature activation+0.000
iffs
Tokeniffs
Feature activation+7.299
into
Token into
Feature activation+0.000
accessible
Token accessible
Feature activation+0.000
,
Token,
Feature activation+0.000
catchy
Token catchy
Feature activation+0.000
songs
Token songs
Feature activation+0.000

INTERVAL 6.105 - 6.978
CONTAINS 0.001%

48
Token 48
Feature activation+0.000
Laws
Token Laws
Feature activation+0.000
of
Token of
Feature activation+0.000
Power
Token Power
Feature activation+0.000
turned
Token turned
Feature activation+0.000
Greene
Token Greene
Feature activation+6.725
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
cult
Tokencult
Feature activation+0.000
hero
Token hero
Feature activation+0.000
past
Token past
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
turned
Token turned
Feature activation+0.000
it
Token it
Feature activation+6.408
around
Token around
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
context
Token context
Feature activation+0.000
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+6.375
into
Token into
Feature activation+0.000
good
Token good
Feature activation+0.000
training
Token training
Feature activation+0.000
methodology
Token methodology
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
your
Token your
Feature activation+1.775
own
Token own
Feature activation+1.215
i
Token i
Feature activation+0.000
Mac
TokenMac
Feature activation+6.266
into
Token into
Feature activation+0.000
an
Token an
Feature activation+0.000
aquarium
Token aquarium
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
.
Token.
Feature activation+0.000
Brown
Token Brown
Feature activation+0.000
helped
Token helped
Feature activation+0.000
turn
Token turn
Feature activation+0.000
Lex
Token Lex
Feature activation+0.645
Luthor
Token Luthor
Feature activation+6.606
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
sill
Token sill
Feature activation+0.000
ier
Tokenier
Feature activation+0.329
version
Token version
Feature activation+0.000

INTERVAL 5.233 - 6.105
CONTAINS 0.001%

cups
Token cups
Feature activation+0.000
,
Token,
Feature activation+0.000
turn
Token turn
Feature activation+0.000
the
Token the
Feature activation+0.872
leftover
Token leftover
Feature activation+3.688
coffee
Token coffee
Feature activation+5.950
grounds
Token grounds
Feature activation+7.311
into
Token into
Feature activation+0.000
compost
Token compost
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
process
Token process
Feature activation+0.000
of
Token of
Feature activation+0.000
turning
Token turning
Feature activation+0.000
complex
Token complex
Feature activation+0.000
scientific
Token scientific
Feature activation+0.564
topics
Token topics
Feature activation+6.040
into
Token into
Feature activation+0.000
compelling
Token compelling
Feature activation+0.000
visual
Token visual
Feature activation+0.000
narratives
Token narratives
Feature activation+0.000
.
Token.
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
"
Token"
Feature activation+0.000
turned
Token turned
Feature activation+0.000
their
Token their
Feature activation+1.274
personal
Token personal
Feature activation+0.398
tragedy
Token tragedy
Feature activation+5.821
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
practical
Token practical
Feature activation+0.000
nightmare
Token nightmare
Feature activation+0.000
,
Token,
Feature activation+0.000
M
Token M
Feature activation+0.000
WD
TokenWD
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+6.037
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
cool
Token cool
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Factor
TokenFactor
Feature activation+0.000
turned
Token turned
Feature activation+0.000
my
Token my
Feature activation+2.357
brain
Token brain
Feature activation+5.609
inside
Token inside
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 4.361 - 5.233
CONTAINS 0.002%

of
Token of
Feature activation+0.000
Planning
Token Planning
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+0.106
area
Token area
Feature activation+4.896
around
Token around
Feature activation+0.706
the
Token the
Feature activation+0.000
rail
Token rail
Feature activation+0.000
over
Token over
Feature activation+1.214
pass
Tokenpass
Feature activation+5.280
ing
Tokening
Feature activation+0.000
her
Token her
Feature activation+0.000
passport
Token passport
Feature activation+0.000
and
Token and
Feature activation+0.000
turning
Token turning
Feature activation+0.000
her
Token her
Feature activation+4.540
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.000
Kenya
Token Kenya
Feature activation+0.000
for
Token for
Feature activation+0.000
prosecution
Token prosecution
Feature activation+0.000
th
Tokenth
Feature activation+0.000
!
Token!
Feature activation+0.000
We
Token We
Feature activation+0.000
really
Token really
Feature activation+0.000
turn
Token turn
Feature activation+0.000
this
Token this
Feature activation+5.158
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
full
Token full
Feature activation+0.000
month
Token month
Feature activation+0.000
celebration
Token celebration
Feature activation+0.000
take
Token take
Feature activation+0.000
over
Token over
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+4.999
into
Token into
Feature activation+0.000
New
Token New
Feature activation+0.000
D
Token D
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
am
Tokenam
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
turned
Token turned
Feature activation+0.000
this
Token this
Feature activation+2.831
perfect
Token perfect
Feature activation+0.000
process
Token process
Feature activation+4.710
of
Token of
Feature activation+0.000
regener
Token regener
Feature activation+0.000
ating
Tokenating
Feature activation+1.151
a
Token a
Feature activation+0.000
limb
Token limb
Feature activation+7.050

INTERVAL 3.489 - 4.361
CONTAINS 0.002%

and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
turn
Token turn
Feature activation+0.000
very
Token very
Feature activation+3.896
toxic
Token toxic
Feature activation+0.000
in
Token in
Feature activation+0.000
cases
Token cases
Feature activation+0.000
where
Token where
Feature activation+0.000
consent
Token consent
Feature activation+0.000
turned
Token turned
Feature activation+0.000
good
Token good
Feature activation+0.000
ol
Token ol
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.030
fashioned
Token fashioned
Feature activation+3.705
v
Token v
Feature activation+0.000
aud
Tokenaud
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
ille
Tokenille
Feature activation+1.154
slap
Token slap
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
the
Token the
Feature activation+0.000
template
Token template
Feature activation+4.561
counter
Token counter
Feature activation+4.133
clock
Tokenclock
Feature activation+0.000
wise
Tokenwise
Feature activation+0.000
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
undergoing
Token undergoing
Feature activation+0.000
a
Token a
Feature activation+0.000
renovation
Token renovation
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+4.318
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
displays
Token displays
Feature activation+0.000
a
Token a
Feature activation+0.000
clock
Token clock
Feature activation+0.000
,
Token,
Feature activation+0.000
turning
Token turning
Feature activation+0.000
it
Token it
Feature activation+3.889
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
bed
Token bed
Feature activation+0.000
side
Tokenside
Feature activation+0.000
time
Token time
Feature activation+0.000

INTERVAL 2.617 - 3.489
CONTAINS 0.002%

example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
WiFi
Token WiFi
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
turned
Token turned
Feature activation+3.015
off
Token off
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
during
Token during
Feature activation+0.000
weekends
Token weekends
Feature activation+0.000
.
Token.
Feature activation+0.000
turns
Token turns
Feature activation+0.000
stand
Token stand
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
regular
Token regular
Feature activation+0.000
people
Token people
Feature activation+3.257
into
Token into
Feature activation+0.000
Norman
Token Norman
Feature activation+0.000
Te
Token Te
Feature activation+0.000
b
Tokenb
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
over
Token over
Feature activation+1.214
pass
Tokenpass
Feature activation+5.280
and
Token and
Feature activation+1.967
5
Token 5
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Street
Token Street
Feature activation+3.471
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
this
Token this
Feature activation+0.000
offseason
Token offseason
Feature activation+0.000
to
Token to
Feature activation+0.000
turning
Token turning
Feature activation+0.000
his
Token his
Feature activation+2.735
weaknesses
Token weaknesses
Feature activation+7.266
into
Token into
Feature activation+0.000
strengths
Token strengths
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
confident
Token confident
Feature activation+0.000
of
Token of
Feature activation+0.000
victory
Token victory
Feature activation+0.000
,
Token,
Feature activation+0.000
turned
Token turned
Feature activation+0.000
her
Token her
Feature activation+3.386
attention
Token attention
Feature activation+3.373
to
Token to
Feature activation+0.000
down
Token down
Feature activation+0.000
-
Token-
Feature activation+0.000
ticket
Tokenticket
Feature activation+0.000

INTERVAL 1.744 - 2.617
CONTAINS 0.001%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
(
Token (
Feature activation+0.000
something
Tokensomething
Feature activation+0.000
)
Token)
Feature activation+2.545
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.144
head
Token head
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
-
Token-
Feature activation+0.000
turned
Tokenturned
Feature activation+0.000
-
Token-
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.576
pro
Tokenpro
Feature activation+0.000
gressive
Tokengressive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
former
Token former
Feature activation+0.000
Conclusion
TokenConclusion
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Factor
TokenFactor
Feature activation+0.000
turned
Token turned
Feature activation+0.000
my
Token my
Feature activation+2.357
brain
Token brain
Feature activation+5.609
inside
Token inside
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
the
Token the
Feature activation+0.000
N
Token N
Feature activation+0.000
900
Token900
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
turned
Token turned
Feature activation+1.927
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
custom
Token custom
Feature activation+0.000
schedule
Token schedule
Feature activation+0.000
calling
Token calling
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
feature
Token feature
Feature activation+0.000
was
Token was
Feature activation+0.000
turned
Token turned
Feature activation+2.215
on
Token on
Feature activation+0.000
within
Token within
Feature activation+0.000
days
Token days
Feature activation+0.000
of
Token of
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000

INTERVAL 0.872 - 1.744
CONTAINS 0.005%

with
Token with
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
designers
Token designers
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
his
Token his
Feature activation+1.006
rough
Token rough
Feature activation+0.784
sketches
Token sketches
Feature activation+7.099
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
work
Token work
Feature activation+0.000
idge
Tokenidge
Feature activation+0.000
said
Token said
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
stalled
Token stalled
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+1.206
information
Token information
Feature activation+5.731
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
the
Token the
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
was
Token was
Feature activation+0.000
converted
Token converted
Feature activation+0.260
back
Token back
Feature activation+0.997
to
Token to
Feature activation+0.000
civilian
Token civilian
Feature activation+0.000
production
Token production
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
safe
Token safe
Feature activation+0.000
and
Token and
Feature activation+0.000
turned
Token turned
Feature activation+0.000
the
Token the
Feature activation+0.000
tide
Token tide
Feature activation+0.894
of
Token of
Feature activation+1.115
war
Token war
Feature activation+3.583
âĢ
TokenâĢ
Feature activation+0.777
Ŀ
TokenĿ
Feature activation+5.204
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
know
Token know
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
turned
Token turned
Feature activation+0.000
himself
Token himself
Feature activation+1.066
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
yet
Token yet
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 0.000 - 0.872
CONTAINS 99.984%

detail
Token detail
Feature activation+0.000
and
Token and
Feature activation+0.000
were
Token were
Feature activation+0.000
likely
Token likely
Feature activation+0.000
telling
Token telling
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mc
TokenMc
Feature activation+0.000
next
Token next
Feature activation+0.000
week
Token week
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Save
TokenSave
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Save
TokenSave
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
good
Token good
Feature activation+0.000
fil
Token fil
Feature activation+0.000
t
Tokent
Feature activation+0.000
ration
Tokenration
Feature activation+0.000
system
Token system
Feature activation+0.000
and
Token and
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
designed
Token designed
Feature activation+0.000
water
Token water
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
into
Token into
Feature activation+0.000
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Kenya
Token Kenya
Feature activation+0.000
's
Token's
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
na
Tokenna
Feature activation+0.000
Ki
Token Ki
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
YORK
Token YORK
Feature activation+0.000
(
Token (
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
Money
TokenMoney
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
)
Token)
Feature activation+0.000
--
Token --
Feature activation+0.000
The
Token The
Feature activation+0.000
value
Token value
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H8.4: (feature 10283)

TOP ACTIVATIONS
MAX = 7.309

after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.000
asked
Token asked
Feature activation+0.000
on
Token on
Feature activation+0.000
live
Token live
Feature activation+0.000
TV
Token TV
Feature activation+7.309
what
Token what
Feature activation+0.000
"
Token "
Feature activation+0.000
sub
Tokensub
Feature activation+0.000
groups
Tokengroups
Feature activation+0.000
"
Token"
Feature activation+0.000
Designer
Token Designer
Feature activation+0.000
on
Token on
Feature activation+0.000
World
Token World
Feature activation+0.000
of
Token of
Feature activation+0.000
Warcraft
Token Warcraft
Feature activation+0.981
,
Token,
Feature activation+7.246
one
Token one
Feature activation+1.412
of
Token of
Feature activation+0.754
Blizzard
Token Blizzard
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.647
Ļ
TokenĻ
Feature activation+0.647
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000
franchises
Token franchises
Feature activation+0.443
,
Token,
Feature activation+7.226
about
Token about
Feature activation+0.000
whether
Token whether
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
called
Token called
Feature activation+0.000
me
Token me
Feature activation+0.000
asking
Token asking
Feature activation+0.069
me
Token me
Feature activation+7.154
to
Token to
Feature activation+0.291
call
Token call
Feature activation+0.000
a
Token a
Feature activation+0.000
mechanic
Token mechanic
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.868
drag
Token drag
Feature activation+0.000
and
Token and
Feature activation+0.000
L
Token L
Feature activation+0.000
GB
TokenGB
Feature activation+1.522
communities
Token communities
Feature activation+6.945
to
Token to
Feature activation+0.198
stop
Token stop
Feature activation+0.000
using
Token using
Feature activation+0.000
words
Token words
Feature activation+0.000
they
Token they
Feature activation+0.000
Paul
Token Paul
Feature activation+5.310
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Texas
TokenTexas
Feature activation+5.887
)
Token)
Feature activation+6.917
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
favored
Token favored
Feature activation+0.000
abol
Token abol
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
fellow
Token fellow
Feature activation+0.048
mo
Token mo
Feature activation+0.000
vers
Tokenvers
Feature activation+6.602
and
Token and
Feature activation+0.000
sh
Token sh
Feature activation+0.000
akers
Tokenakers
Feature activation+6.801
to
Token to
Feature activation+0.307
shake
Token shake
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
recently
Token recently
Feature activation+0.000
asked
Token asked
Feature activation+0.000
her
Token her
Feature activation+4.638
fellow
Token fellow
Feature activation+0.048
mo
Token mo
Feature activation+0.000
vers
Tokenvers
Feature activation+6.602
and
Token and
Feature activation+0.000
sh
Token sh
Feature activation+0.000
akers
Tokenakers
Feature activation+6.801
to
Token to
Feature activation+0.307
shake
Token shake
Feature activation+0.000
walked
Token walked
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
his
Token his
Feature activation+0.224
father
Token father
Feature activation+6.601
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
Kevin
Token Kevin
Feature activation+0.000
could
Token could
Feature activation+0.000
interpreter
Token interpreter
Feature activation+0.000
to
Token to
Feature activation+0.126
three
Token three
Feature activation+0.000
pop
Token pop
Feature activation+0.000
es
Tokenes
Feature activation+0.000
,
Token,
Feature activation+6.591
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.000
that
Token that
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
Group
Token Group
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
asks
Token asks
Feature activation+1.516
agents
Token agents
Feature activation+6.535
to
Token to
Feature activation+0.000
spit
Token spit
Feature activation+0.000
ball
Tokenball
Feature activation+0.000
methods
Token methods
Feature activation+0.000
of
Token of
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
asking
Token asking
Feature activation+0.000
her
Token her
Feature activation+6.514
for
Token for
Feature activation+0.752
nude
Token nude
Feature activation+0.000
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+0.000
had
Token had
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
corner
Token corner
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.200
them
Token them
Feature activation+6.472
to
Token to
Feature activation+1.074
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
int
Token int
Feature activation+0.000
ently
Tokenently
Feature activation+0.000
staring
Token staring
Feature activation+0.000
at
Token at
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+6.432
to
Token to
Feature activation+0.305
stop
Token stop
Feature activation+0.000
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
station
Token station
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
Officer
Token Officer
Feature activation+0.000
McGu
Token McGu
Feature activation+0.000
iness
Tokeniness
Feature activation+6.421
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
partner
Token partner
Feature activation+5.291
a
Token a
Feature activation+0.832
few
Token few
Feature activation+0.572
merely
Token merely
Feature activation+0.000
asking
Token asking
Feature activation+0.355
Mr
Token Mr
Feature activation+0.419
N
Token N
Feature activation+0.000
ger
Tokenger
Feature activation+0.000
ng
Tokenng
Feature activation+6.397
if
Token if
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
is
Token is
Feature activation+0.000
asking
Token asking
Feature activation+0.184
its
Token its
Feature activation+0.186
operatives
Token operatives
Feature activation+6.353
to
Token to
Feature activation+0.261
carry
Token carry
Feature activation+0.000
out
Token out
Feature activation+0.000
lone
Token lone
Feature activation+0.000
wolf
Token wolf
Feature activation+0.000
Wright
Token Wright
Feature activation+3.951
,
Token,
Feature activation+0.519
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
chanting
Token chanting
Feature activation+0.000
,
Token,
Feature activation+6.306
beating
Token beating
Feature activation+0.000
his
Token his
Feature activation+0.000
chest
Token chest
Feature activation+0.000
,
Token,
Feature activation+3.130
mim
Token mim
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+6.252
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
are
Token are
Feature activation+0.000
asked
Token asked
Feature activation+0.597
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.210
personality
Token personality
Feature activation+0.000
questionnaire
Token questionnaire
Feature activation+6.177
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000

Top DFA by src position
MAX = 8.642

than
Token than
Feature activation+0.002
Top resid features:
48
Token 48
Feature activation+0.007
Top resid features:
hours
Token hours
Feature activation-0.003
Top resid features:
after
Token after
Feature activation+0.060
Top resid features:
he
Token he
Feature activation+0.024
Top resid features:
asked
Token asked
Feature activation+8.642
Top resid features:
on
Token on
Feature activation+0.034
Top resid features:
live
Token live
Feature activation+0.063
Top resid features:
TV
Token TV
Feature activation-0.009
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
We
TokenWe
Feature activation+0.011
Top resid features:
also
Token also
Feature activation-0.007
Top resid features:
asked
Token asked
Feature activation+8.452
Top resid features:
Matt
Token Matt
Feature activation+0.008
Top resid features:
G
Token G
Feature activation-0.007
Top resid features:
oss
Tokenoss
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
We
TokenWe
Feature activation+0.006
Top resid features:
also
Token also
Feature activation-0.003
Top resid features:
asked
Token asked
Feature activation+8.029
Top resid features:
Matt
Token Matt
Feature activation+0.003
Top resid features:
G
Token G
Feature activation-0.004
Top resid features:
oss
Tokenoss
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
cabin
Token cabin
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
He
Token He
Feature activation+0.020
Top resid features:
called
Token called
Feature activation+0.134
Top resid features:
me
Token me
Feature activation+0.069
Top resid features:
asking
Token asking
Feature activation+7.863
Top resid features:
me
Token me
Feature activation+0.293
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
call
Token call
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
mechanic
Token mechanic
Feature activation+0.000
Top resid features:
trans
Token trans
Feature activation-0.002
Top resid features:
activists
Token activists
Feature activation+0.005
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
continue
Token continue
Feature activation-0.055
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
ask
Token ask
Feature activation+8.068
Top resid features:
members
Token members
Feature activation+0.232
Top resid features:
of
Token of
Feature activation+0.044
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
drag
Token drag
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
s
Tokens
Feature activation+0.014
Top resid features:
Wolf
Token Wolf
Feature activation+0.002
Top resid features:
Bl
Token Bl
Feature activation-0.004
Top resid features:
itzer
Tokenitzer
Feature activation-0.011
Top resid features:
asked
Token asked
Feature activation+8.047
Top resid features:
Rep
Token Rep
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ron
Token Ron
Feature activation+0.006
Top resid features:
Paul
Token Paul
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
but
Token but
Feature activation-0.012
Top resid features:
one
Token one
Feature activation-0.015
Top resid features:
mogul
Token mogul
Feature activation+0.003
Top resid features:
recently
Token recently
Feature activation+0.049
Top resid features:
asked
Token asked
Feature activation+7.523
Top resid features:
her
Token her
Feature activation+0.408
Top resid features:
fellow
Token fellow
Feature activation-0.009
Top resid features:
mo
Token mo
Feature activation+0.029
Top resid features:
vers
Tokenvers
Feature activation+0.113
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
,
Token,
Feature activation-0.029
Top resid features:
but
Token but
Feature activation-0.016
Top resid features:
one
Token one
Feature activation-0.027
Top resid features:
mogul
Token mogul
Feature activation+0.017
Top resid features:
recently
Token recently
Feature activation+0.069
Top resid features:
asked
Token asked
Feature activation+7.186
Top resid features:
her
Token her
Feature activation+0.460
Top resid features:
fellow
Token fellow
Feature activation+0.024
Top resid features:
mo
Token mo
Feature activation+0.051
Top resid features:
vers
Tokenvers
Feature activation+0.054
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Don
TokenDon
Feature activation+0.015
Top resid features:
walked
Token walked
Feature activation-0.046
Top resid features:
in
Token in
Feature activation-0.029
Top resid features:
and
Token and
Feature activation+0.047
Top resid features:
asked
Token asked
Feature activation+7.647
Top resid features:
his
Token his
Feature activation+0.159
Top resid features:
father
Token father
Feature activation+0.067
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.052
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
I
Token I
Feature activation+0.005
Top resid features:
once
Token once
Feature activation+0.016
Top resid features:
asked
Token asked
Feature activation+7.411
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
late
Token late
Feature activation-0.011
Top resid features:
Miguel
Token Miguel
Feature activation+0.006
Top resid features:
Ar
Token Ar
Feature activation+0.003
Top resid features:
ran
Tokenran
Feature activation-0.003
Top resid features:
Equ
Token Equ
Feature activation-0.001
Top resid features:
ation
Tokenation
Feature activation-0.004
Top resid features:
Group
Token Group
Feature activation-0.026
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
asks
Token asks
Feature activation+7.892
Top resid features:
agents
Token agents
Feature activation+0.086
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
spit
Token spit
Feature activation+0.000
Top resid features:
ball
Tokenball
Feature activation+0.000
Top resid features:
methods
Token methods
Feature activation+0.000
Top resid features:
She
Token She
Feature activation+0.032
Top resid features:
said
Token said
Feature activation+0.024
Top resid features:
he
Token he
Feature activation+0.065
Top resid features:
had
Token had
Feature activation+0.034
Top resid features:
been
Token been
Feature activation+0.052
Top resid features:
asking
Token asking
Feature activation+7.309
Top resid features:
her
Token her
Feature activation+0.137
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
nude
Token nude
Feature activation+0.000
Top resid features:
photographs
Token photographs
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
couple
Token couple
Feature activation+0.014
Top resid features:
in
Token in
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
corner
Token corner
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.100
Top resid features:
asked
Token asked
Feature activation+7.231
Top resid features:
them
Token them
Feature activation+0.160
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
leave
Token leave
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Staff
TokenStaff
Feature activation-0.043
Top resid features:
monitoring
Token monitoring
Feature activation-0.049
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
enclosure
Token enclosure
Feature activation+0.001
Top resid features:
repeatedly
Token repeatedly
Feature activation-0.017
Top resid features:
asked
Token asked
Feature activation+7.621
Top resid features:
Wright
Token Wright
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
chanting
Token chanting
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
police
Token police
Feature activation-0.000
Top resid features:
station
Token station
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
ask
Token ask
Feature activation+7.615
Top resid features:
Officer
Token Officer
Feature activation+0.151
Top resid features:
McGu
Token McGu
Feature activation+0.036
Top resid features:
iness
Tokeniness
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
First
TokenFirst
Feature activation+0.015
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
he
Token he
Feature activation+0.016
Top resid features:
was
Token was
Feature activation+0.015
Top resid features:
merely
Token merely
Feature activation+0.158
Top resid features:
asking
Token asking
Feature activation+7.438
Top resid features:
Mr
Token Mr
Feature activation+0.026
Top resid features:
N
Token N
Feature activation+0.005
Top resid features:
ger
Tokenger
Feature activation+0.014
Top resid features:
ng
Tokenng
Feature activation+0.030
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
police
Token police
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
person
Token person
Feature activation+0.023
Top resid features:
is
Token is
Feature activation+0.059
Top resid features:
asking
Token asking
Feature activation+7.352
Top resid features:
its
Token its
Feature activation+0.227
Top resid features:
operatives
Token operatives
Feature activation+0.062
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
carry
Token carry
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
Staff
TokenStaff
Feature activation-0.036
Top resid features:
monitoring
Token monitoring
Feature activation-0.065
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
enclosure
Token enclosure
Feature activation+0.013
Top resid features:
repeatedly
Token repeatedly
Feature activation-0.015
Top resid features:
asked
Token asked
Feature activation+7.408
Top resid features:
Wright
Token Wright
Feature activation+0.048
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
who
Token who
Feature activation+0.038
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
chanting
Token chanting
Feature activation+0.018
Top resid features:
not
Token not
Feature activation-0.019
Top resid features:
interesting
Token interesting
Feature activation-0.061
Top resid features:
to
Token to
Feature activation-0.027
Top resid features:
me
Token me
Feature activation-0.045
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
asked
Token asked
Feature activation+7.599
Top resid features:
him
Token him
Feature activation+0.192
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
example
Token example
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
if
Token if
Feature activation+0.013
Top resid features:
people
Token people
Feature activation+0.048
Top resid features:
are
Token are
Feature activation+0.028
Top resid features:
asked
Token asked
Feature activation+7.431
Top resid features:
on
Token on
Feature activation+0.099
Top resid features:
a
Token a
Feature activation+0.083
Top resid features:
personality
Token personality
Feature activation+0.000
Top resid features:
questionnaire
Token questionnaire
Feature activation+0.056
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.02

Head 3: 0.02

Head 4: 0.56

Head 5: 0.06

Head 6: 0.01

Head 7: 0.12

Head 8: 0.04

Head 9: 0.02

Head 10: 0.09

Head 11: 0.02

Positive logits

questions2.94

whether2.91

why2.88

QUEST2.85

question2.58

WHY2.53

why2.49

rhet2.38

Questions2.26

question2.26

forgiveness2.24

how2.19

WHERE2.14

whether2.12

Question2.00

Why2.00

answer1.94

secondly1.91

probing1.87

Questions1.83

Negative logits

-1.94

erno-1.83

Default-1.73

Torrent-1.72

aphael-1.72

xon-1.71

Clock-1.70

earthqu-1.69

ushima-1.68

uclear-1.62

oppable-1.55

effect-1.54

Reilly-1.54

Urban-1.53

Sounds-1.52

ocumented-1.52

due-1.50

Liber-1.48

xi-1.47

Shrine-1.47

INTERVAL 6.578 - 7.309
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.647
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000
franchises
Token franchises
Feature activation+0.443
,
Token,
Feature activation+7.226
about
Token about
Feature activation+0.000
whether
Token whether
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Paul
Token Paul
Feature activation+5.310
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Texas
TokenTexas
Feature activation+5.887
)
Token)
Feature activation+6.917
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
favored
Token favored
Feature activation+0.000
abol
Token abol
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
the
Token the
Feature activation+0.868
drag
Token drag
Feature activation+0.000
and
Token and
Feature activation+0.000
L
Token L
Feature activation+0.000
GB
TokenGB
Feature activation+1.522
communities
Token communities
Feature activation+6.945
to
Token to
Feature activation+0.198
stop
Token stop
Feature activation+0.000
using
Token using
Feature activation+0.000
words
Token words
Feature activation+0.000
they
Token they
Feature activation+0.000
walked
Token walked
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
his
Token his
Feature activation+0.224
father
Token father
Feature activation+6.601
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
Kevin
Token Kevin
Feature activation+0.000
could
Token could
Feature activation+0.000
interpreter
Token interpreter
Feature activation+0.000
to
Token to
Feature activation+0.126
three
Token three
Feature activation+0.000
pop
Token pop
Feature activation+0.000
es
Tokenes
Feature activation+0.000
,
Token,
Feature activation+6.591
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 5.848 - 6.578
CONTAINS 0.002%

Wright
Token Wright
Feature activation+3.951
,
Token,
Feature activation+0.519
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
chanting
Token chanting
Feature activation+0.000
,
Token,
Feature activation+6.306
beating
Token beating
Feature activation+0.000
his
Token his
Feature activation+0.000
chest
Token chest
Feature activation+0.000
,
Token,
Feature activation+3.130
mim
Token mim
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
asked
Token asked
Feature activation+0.890
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
reporter
Token reporter
Feature activation+6.025
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
ever
Token ever
Feature activation+0.000
seen
Token seen
Feature activation+0.000
merely
Token merely
Feature activation+0.000
asking
Token asking
Feature activation+0.355
Mr
Token Mr
Feature activation+0.419
N
Token N
Feature activation+0.000
ger
Tokenger
Feature activation+0.000
ng
Tokenng
Feature activation+6.397
if
Token if
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
is
Token is
Feature activation+0.000
asking
Token asking
Feature activation+0.184
its
Token its
Feature activation+0.186
operatives
Token operatives
Feature activation+6.353
to
Token to
Feature activation+0.261
carry
Token carry
Feature activation+0.000
out
Token out
Feature activation+0.000
lone
Token lone
Feature activation+0.000
wolf
Token wolf
Feature activation+0.000
,
Token,
Feature activation+0.000
asking
Token asking
Feature activation+0.000
Pete
Token Pete
Feature activation+4.814
De
Token De
Feature activation+0.000
ev
Tokenev
Feature activation+0.086
ak
Tokenak
Feature activation+5.975
ul
Tokenul
Feature activation+5.318
to
Token to
Feature activation+1.350
shoot
Token shoot
Feature activation+0.000
straightforward
Token straightforward
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 5.117 - 5.848
CONTAINS 0.003%

asked
Token asked
Feature activation+0.000
Cardinal
Token Cardinal
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
W
Token W
Feature activation+0.000
uer
Tokenuer
Feature activation+0.000
l
Tokenl
Feature activation+5.532
if
Token if
Feature activation+0.000
Mormons
Token Mormons
Feature activation+0.000
were
Token were
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
call
Token call
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
him
Token him
Feature activation+5.316
what
Token what
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
like
Token like
Feature activation+0.000
working
Token working
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
she
Token she
Feature activation+0.000
asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+5.497
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Don
TokenDon
Feature activation+0.000
Mat
Token Mat
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
asked
Token asked
Feature activation+0.000
me
Token me
Feature activation+5.708
to
Token to
Feature activation+0.179
get
Token get
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
bat
Token bat
Feature activation+0.000
,
Token,
Feature activation+0.000
would
Token would
Feature activation+0.000
you
Token you
Feature activation+0.000
be
Token be
Feature activation+0.000
asking
Token asking
Feature activation+0.000
me
Token me
Feature activation+5.529
the
Token the
Feature activation+2.395
same
Token same
Feature activation+3.532
questions
Token questions
Feature activation+0.221
about
Token about
Feature activation+0.000
breaking
Token breaking
Feature activation+0.000

INTERVAL 4.386 - 5.117
CONTAINS 0.003%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
recall
Token recall
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
asking
Token asking
Feature activation+0.037
Obama
Token Obama
Feature activation+4.852
to
Token to
Feature activation+0.709
apologize
Token apologize
Feature activation+0.000
for
Token for
Feature activation+0.000
being
Token being
Feature activation+0.000
careful
Token careful
Feature activation+0.000
the
Token the
Feature activation+0.000
massacres
Token massacres
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.485
the
Token the
Feature activation+0.232
media
Token media
Feature activation+4.745
to
Token to
Feature activation+0.215
show
Token show
Feature activation+0.000
him
Token him
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
but
Token but
Feature activation+0.000
one
Token one
Feature activation+0.000
mogul
Token mogul
Feature activation+0.000
recently
Token recently
Feature activation+0.000
asked
Token asked
Feature activation+0.000
her
Token her
Feature activation+4.638
fellow
Token fellow
Feature activation+0.048
mo
Token mo
Feature activation+0.000
vers
Tokenvers
Feature activation+6.602
and
Token and
Feature activation+0.000
sh
Token sh
Feature activation+0.000
Baby
Token Baby
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
asks
Token asks
Feature activation+0.000
his
Token his
Feature activation+0.011
mother
Token mother
Feature activation+5.009
why
Token why
Feature activation+0.000
Finn
Token Finn
Feature activation+0.000
is
Token is
Feature activation+0.000
locked
Token locked
Feature activation+0.000
up
Token up
Feature activation+0.000
N
Token N
Feature activation+0.000
ouri
Tokenouri
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Mal
TokenMal
Feature activation+0.000
iki
Tokeniki
Feature activation+4.943
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 3.655 - 4.386
CONTAINS 0.003%

the
Token the
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
asked
Token asked
Feature activation+0.000
tax
Token tax
Feature activation+0.268
men
Tokenmen
Feature activation+4.380
to
Token to
Feature activation+0.071
clear
Token clear
Feature activation+0.000
pend
Token pend
Feature activation+0.000
ency
Tokenency
Feature activation+0.000
of
Token of
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
leading
Token leading
Feature activation+0.000
German
Token German
Feature activation+0.000
physics
Token physics
Feature activation+0.000
journal
Token journal
Feature activation+4.190
(
Token (
Feature activation+0.000
P
TokenP
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
endor
Tokenendor
Feature activation+0.000
ff
Tokenff
Feature activation+0.453
Dead
Token Dead
Feature activation+0.000
spin
Tokenspin
Feature activation+0.000
says
Token says
Feature activation+0.000
ESPN
Token ESPN
Feature activation+0.000
asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+3.928
to
Token to
Feature activation+0.771
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
break
Token break
Feature activation+0.000
itself
Token itself
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ask
TokenAsk
Feature activation+0.000
people
Token people
Feature activation+3.767
to
Token to
Feature activation+0.430
do
Token do
Feature activation+0.240
something
Token something
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
Family
Token Family
Feature activation+0.000
Association
Token Association
Feature activation+0.000
website
Token website
Feature activation+0.000
,
Token,
Feature activation+0.000
asking
Token asking
Feature activation+0.127
people
Token people
Feature activation+3.790
to
Token to
Feature activation+0.752
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
television
Token television
Feature activation+0.000
stars
Token stars
Feature activation+0.000

INTERVAL 2.924 - 3.655
CONTAINS 0.003%

asking
Token asking
Feature activation+0.000
@
Token @
Feature activation+0.000
Brend
TokenBrend
Feature activation+0.000
an
Tokenan
Feature activation+0.000
E
TokenE
Feature activation+0.000
ich
Tokenich
Feature activation+3.374
to
Token to
Feature activation+0.152
step
Token step
Feature activation+0.000
down
Token down
Feature activation+0.000
as
Token as
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
ab
Token ab
Feature activation+0.000
bot
Tokenbot
Feature activation+0.000
asked
Token asked
Feature activation+0.000
me
Token me
Feature activation+3.550
if
Token if
Feature activation+0.000
Shin
Token Shin
Feature activation+0.000
zen
Tokenzen
Feature activation+0.000
(
Token (
Feature activation+0.000
çľ
Tokençľ
Feature activation+0.000
School
Token School
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
is
Token is
Feature activation+0.000
asked
Token asked
Feature activation+0.000
regularly
Token regularly
Feature activation+3.123
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
attend
Token attend
Feature activation+0.000
New
Token New
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
asked
Token asked
Feature activation+0.000
the
Token the
Feature activation+0.068
country
Token country
Feature activation+3.067
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.550
s
Tokens
Feature activation+1.328
commerce
Token commerce
Feature activation+1.164
commission
Token commission
Feature activation+6.025
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
asked
Token asked
Feature activation+0.111
head
Token head
Feature activation+0.122
te
Tokente
Feature activation+0.000
acher
Tokenacher
Feature activation+3.513
Matthew
Token Matthew
Feature activation+2.772
Tate
Token Tate
Feature activation+5.185
to
Token to
Feature activation+0.827
give
Token give
Feature activation+0.000
her
Token her
Feature activation+0.000

INTERVAL 2.193 - 2.924
CONTAINS 0.002%

his
Token his
Feature activation+0.000
administration
Token administration
Feature activation+0.000
has
Token has
Feature activation+0.000
asked
Token asked
Feature activation+0.000
state
Token state
Feature activation+0.000
officials
Token officials
Feature activation+2.461
to
Token to
Feature activation+0.000
decide
Token decide
Feature activation+0.000
by
Token by
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
one
Token one
Feature activation+0.304
of
Token of
Feature activation+0.053
you
Token you
Feature activation+2.621
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
your
Token your
Feature activation+0.000
duty
Token duty
Feature activation+0.000
,
Token,
Feature activation+0.000
posted
Token posted
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
just
Token just
Feature activation+0.000
ask
Token ask
Feature activation+0.000
him
Token him
Feature activation+2.501
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
?
Token?
Feature activation+0.000
Contact
Token Contact
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
D
Token D
Feature activation+0.000
and
Tokenand
Feature activation+0.000
ala
Tokenala
Feature activation+0.000
asked
Token asked
Feature activation+0.000
her
Token her
Feature activation+2.535
how
Token how
Feature activation+0.000
she
Token she
Feature activation+0.000
knows
Token knows
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
ask
Token ask
Feature activation+0.000
me
Token me
Feature activation+2.383
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.103
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000

INTERVAL 1.462 - 2.193
CONTAINS 0.005%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
asked
Token asked
Feature activation+0.041
again
Token again
Feature activation+0.766
Tuesday
Token Tuesday
Feature activation+1.581
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
R
TokenR
Feature activation+0.000
if
Tokenif
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
sentiments
Token sentiments
Feature activation+0.000
by
Token by
Feature activation+0.000
asking
Token asking
Feature activation+0.000
,
Token,
Feature activation+1.892
âĢ
Token âĢ
Feature activation+0.058
ľ
Tokenľ
Feature activation+1.374
What
TokenWhat
Feature activation+0.000
country
Token country
Feature activation+0.000
is
Token is
Feature activation+0.000
asked
Token asked
Feature activation+0.000
by
Token by
Feature activation+0.000
Senator
Token Senator
Feature activation+0.000
Or
Token Or
Feature activation+0.000
rin
Tokenrin
Feature activation+0.000
Hatch
Token Hatch
Feature activation+1.686
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Utah
TokenUtah
Feature activation+0.892
),
Token),
Feature activation+0.773
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
asking
Token asking
Feature activation+0.000
him
Token him
Feature activation+2.162
in
Token in
Feature activation+0.000
private
Token private
Feature activation+1.796
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
13
Token 13
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
asking
Token asking
Feature activation+0.000
yourselves
Token yourselves
Feature activation+0.442
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.667
How
TokenHow
Feature activation+0.000
did
Token did
Feature activation+0.000
this
Token this
Feature activation+0.000
happen
Token happen
Feature activation+0.000
?
Token?
Feature activation+0.000

INTERVAL 0.731 - 1.462
CONTAINS 0.012%

World
Token World
Feature activation+0.000
of
Token of
Feature activation+0.000
Warcraft
Token Warcraft
Feature activation+0.981
,
Token,
Feature activation+7.246
one
Token one
Feature activation+1.412
of
Token of
Feature activation+0.754
Blizzard
Token Blizzard
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.647
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
coalition
Token coalition
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
battling
Token battling
Feature activation+0.000
IS
Token IS
Feature activation+0.898
in
Token in
Feature activation+0.000
Syria
Token Syria
Feature activation+0.751
and
Token and
Feature activation+0.000
neighbouring
Token neighbouring
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.801
often
Token often
Feature activation+0.000
ask
Token ask
Feature activation+0.000
me
Token me
Feature activation+2.218
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.082
But
TokenBut
Feature activation+0.000
how
Token how
Feature activation+0.000
is
Token is
Feature activation+0.000
this
Token this
Feature activation+0.000
different
Token different
Feature activation+0.000
focused
Token focused
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
ask
Token ask
Feature activation+0.000
Zoe
Token Zoe
Feature activation+0.000
Quinn
Token Quinn
Feature activation+1.037
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
object
Token object
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
'm
Token'm
Feature activation+0.000
just
Token just
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
wondering
Token wondering
Feature activation+0.000
,
Token,
Feature activation+0.948
what
Token what
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000

INTERVAL 0.000 - 0.731
CONTAINS 99.966%

continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
exert
Token exert
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
".
Token".
Feature activation+0.000
It
TokenIt
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
remains
Token remains
Feature activation+0.000
stable
Token stable
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
baskets
Token baskets
Feature activation+0.000
it
Token it
Feature activation+0.000
rests
Token rests
Feature activation+0.000
in
Token in
Feature activation+0.000
are
Token are
Feature activation+0.000
;
Token;
Feature activation+0.000
then
Token then
Feature activation+0.000
a
Token a
Feature activation+0.000
plum
Token plum
Feature activation+0.000
pudding
Token pudding
Feature activation+0.000
;
Token;
Feature activation+0.000
then
Token then
Feature activation+0.000
cocoa
Token cocoa
Feature activation+0.000
with
Token with
Feature activation+0.000
ra
Token ra
Feature activation+0.000
is
Tokenis
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
in
Token in
Feature activation+0.000
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
five
Token five
Feature activation+0.000
books
Token books
Feature activation+0.000
on
Token on
Feature activation+0.000
Buenos
Token Buenos
Feature activation+0.000
ca
Tokenca
Feature activation+0.000
ution
Tokenution
Feature activation+0.000
;
Token;
Feature activation+0.000
reckless
Token reckless
Feature activation+0.000
foul
Token foul
Feature activation+0.000
)
Token)
Feature activation+0.000
118
Token 118
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SEA
TokenSEA
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 8 in H8.4: (feature 9386)

TOP ACTIVATIONS
MAX = 7.097

put
Tokenput
Feature activation+0.091
right
Token right
Feature activation+0.000
-
Token-
Feature activation+0.000
wing
Tokenwing
Feature activation+1.383
radical
Token radical
Feature activation+0.000
ism
Tokenism
Feature activation+7.097
in
Token in
Feature activation+2.486
its
Token its
Feature activation+0.135
place
Token place
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
mand
Tokenmand
Feature activation+0.000
ering
Tokenering
Feature activation+6.169
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
landscape
Token landscape
Feature activation+6.711
entirely
Token entirely
Feature activation+4.732
off
Token off
Feature activation+0.000
limits
Token limits
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
've
Token've
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
him
Token him
Feature activation+0.000
put
Token put
Feature activation+0.112
anyone
Token anyone
Feature activation+6.678
in
Token in
Feature activation+1.972
a
Token a
Feature activation+0.611
bad
Token bad
Feature activation+0.000
situation
Token situation
Feature activation+0.000
.'
Token.'
Feature activation+0.000
office
Token office
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.567
their
Token their
Feature activation+1.441
own
Token own
Feature activation+2.423
policies
Token policies
Feature activation+6.636
into
Token into
Feature activation+1.971
place
Token place
Feature activation+0.128
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
argue
Token argue
Feature activation+0.000
s
Tokens
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.544
socialist
Token socialist
Feature activation+1.505
idea
Token idea
Feature activation+6.631
on
Token on
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
,
Token,
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
,
Token,
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
many
Token many
Feature activation+4.474
Americans
Token Americans
Feature activation+6.508
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
putting
Token putting
Feature activation+0.037
them
Token them
Feature activation+6.463
into
Token into
Feature activation+0.565
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
projects
Token projects
Feature activation+0.000
and
Token and
Feature activation+0.000
helping
Token helping
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.784
them
Token them
Feature activation+6.438
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
She
Token She
Feature activation+0.000
historical
Token historical
Feature activation+0.000
cleansing
Token cleansing
Feature activation+0.000
that
Token that
Feature activation+0.000
puts
Token puts
Feature activation+0.000
human
Token human
Feature activation+0.212
beings
Token beings
Feature activation+6.419
in
Token in
Feature activation+1.823
the
Token the
Feature activation+0.000
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
God
Token God
Feature activation+0.000
incomplete
Token incomplete
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
,
Token,
Feature activation+0.000
putting
Token putting
Feature activation+0.681
the
Token the
Feature activation+1.968
movie
Token movie
Feature activation+6.200
three
Token three
Feature activation+1.384
million
Token million
Feature activation+2.483
dollars
Token dollars
Feature activation+3.218
over
Token over
Feature activation+0.047
budget
Token budget
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+0.000
championship
Token championship
Feature activation+4.581
-
Token-
Feature activation+0.000
caliber
Tokencaliber
Feature activation+3.084
team
Token team
Feature activation+6.175
on
Token on
Feature activation+0.321
the
Token the
Feature activation+0.000
field
Token field
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
clerk
Token clerk
Feature activation+0.000
insists
Token insists
Feature activation+0.000
on
Token on
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+0.164
items
Token items
Feature activation+6.171
in
Token in
Feature activation+0.441
a
Token a
Feature activation+0.000
plastic
Token plastic
Feature activation+0.000
bag
Token bag
Feature activation+0.000
.
Token.
Feature activation+0.000
not
Token not
Feature activation+0.000
put
Token put
Feature activation+0.000
g
Token g
Feature activation+0.000
erry
Tokenerry
Feature activation+0.000
mand
Tokenmand
Feature activation+0.000
ering
Tokenering
Feature activation+6.169
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
landscape
Token landscape
Feature activation+6.711
entirely
Token entirely
Feature activation+4.732
reducing
Token reducing
Feature activation+0.000
employee
Token employee
Feature activation+0.000
travel
Token travel
Feature activation+0.000
and
Token and
Feature activation+0.000
putting
Token putting
Feature activation+1.050
workers
Token workers
Feature activation+6.089
on
Token on
Feature activation+0.053
f
Token f
Feature activation+0.000
url
Tokenurl
Feature activation+0.000
ough
Tokenough
Feature activation+0.000
to
Token to
Feature activation+0.000
might
Token might
Feature activation+0.000
not
Token not
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.177
two
Token two
Feature activation+1.263
companies
Token companies
Feature activation+6.077
together
Token together
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
head
Token head
Feature activation+0.000
-
Token -
Feature activation+0.000
him
Token him
Feature activation+0.000
a
Token a
Feature activation+0.000
beer
Token beer
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
him
Token him
Feature activation+6.071
in
Token in
Feature activation+0.000
time
Token time
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
instruct
Token instruct
Feature activation+0.000
put
Token put
Feature activation+0.000
N
Token N
Feature activation+0.000
uke
Tokenuke
Feature activation+4.604
or
Token or
Feature activation+0.000
Over
Token Over
Feature activation+0.000
pass
Tokenpass
Feature activation+5.969
in
Token in
Feature activation+0.669
the
Token the
Feature activation+0.000
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.519
lot
Token lot
Feature activation+2.339
of
Token of
Feature activation+3.242
that
Token that
Feature activation+5.968
into
Token into
Feature activation+0.364
effect
Token effect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
rest
Token rest
Feature activation+0.000
until
Token until
Feature activation+0.000
she
Token she
Feature activation+0.000
puts
Token puts
Feature activation+0.003
me
Token me
Feature activation+5.928
to
Token to
Feature activation+0.211
rest
Token rest
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
putting
Token putting
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.288
creat
Tokencreat
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
solutions
Token solutions
Feature activation+5.907
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.186
to
Token to
Feature activation+2.982
Minister
Token Minister
Feature activation+0.000
for
Token for
Feature activation+0.000

Top DFA by src position
MAX = 8.005

confident
Token confident
Feature activation+0.027
Top resid features:
Mr
Token Mr
Feature activation+0.007
Top resid features:
Macron
Token Macron
Feature activation+0.018
Top resid features:
would
Token would
Feature activation+0.016
Top resid features:
"
Token "
Feature activation+0.077
Top resid features:
put
Tokenput
Feature activation+8.005
Top resid features:
right
Token right
Feature activation+0.164
Top resid features:
-
Token-
Feature activation+0.018
Top resid features:
wing
Tokenwing
Feature activation+0.101
Top resid features:
radical
Token radical
Feature activation+0.047
Top resid features:
ism
Tokenism
Feature activation+0.084
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
but
Token but
Feature activation-0.029
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
did
Token did
Feature activation+0.003
Top resid features:
not
Token not
Feature activation+0.053
Top resid features:
put
Token put
Feature activation+7.717
Top resid features:
g
Token g
Feature activation+0.006
Top resid features:
erry
Tokenerry
Feature activation-0.004
Top resid features:
mand
Tokenmand
Feature activation+0.041
Top resid features:
ering
Tokenering
Feature activation+0.167
Top resid features:
of
Token of
Feature activation+0.255
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
've
Token've
Feature activation-0.008
Top resid features:
never
Token never
Feature activation+0.068
Top resid features:
seen
Token seen
Feature activation+0.097
Top resid features:
him
Token him
Feature activation+0.030
Top resid features:
put
Token put
Feature activation+7.631
Top resid features:
anyone
Token anyone
Feature activation+0.189
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
bad
Token bad
Feature activation+0.000
Top resid features:
situation
Token situation
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.029
Top resid features:
ran
Token ran
Feature activation+0.064
Top resid features:
for
Token for
Feature activation+0.014
Top resid features:
office
Token office
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.080
Top resid features:
put
Token put
Feature activation+6.916
Top resid features:
their
Token their
Feature activation+0.319
Top resid features:
own
Token own
Feature activation+0.243
Top resid features:
policies
Token policies
Feature activation+0.117
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
Bernie
Token Bernie
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
campaign
Token campaign
Feature activation+0.018
Top resid features:
put
Token put
Feature activation+7.048
Top resid features:
the
Token the
Feature activation+0.629
Top resid features:
socialist
Token socialist
Feature activation+0.124
Top resid features:
idea
Token idea
Feature activation+0.191
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
breakfast
Token breakfast
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.599
Top resid features:
of
Token of
Feature activation-0.011
Top resid features:
climate
Token climate
Feature activation-0.007
Top resid features:
change
Token change
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.022
Top resid features:
put
Token put
Feature activation+7.414
Top resid features:
many
Token many
Feature activation+0.234
Top resid features:
Americans
Token Americans
Feature activation+0.055
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
as
Token as
Feature activation+0.023
Top resid features:
well
Token well
Feature activation+0.006
Top resid features:
as
Token as
Feature activation+0.089
Top resid features:
putting
Token putting
Feature activation+7.206
Top resid features:
them
Token them
Feature activation+0.134
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
group
Token group
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
great
Token great
Feature activation-0.083
Top resid features:
projects
Token projects
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.028
Top resid features:
helping
Token helping
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
put
Token put
Feature activation+7.665
Top resid features:
them
Token them
Feature activation+0.074
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
demand
Token demand
Feature activation+0.032
Top resid features:
for
Token for
Feature activation+0.040
Top resid features:
historical
Token historical
Feature activation+0.016
Top resid features:
cleansing
Token cleansing
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
puts
Token puts
Feature activation+7.276
Top resid features:
human
Token human
Feature activation+0.218
Top resid features:
beings
Token beings
Feature activation+0.156
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.031
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
incomplete
Token incomplete
Feature activation-0.015
Top resid features:
scenes
Token scenes
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
putting
Token putting
Feature activation+6.790
Top resid features:
the
Token the
Feature activation+0.518
Top resid features:
movie
Token movie
Feature activation+0.037
Top resid features:
three
Token three
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.000
Top resid features:
dollars
Token dollars
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.019
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
cost
Token cost
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
not
Token not
Feature activation+0.014
Top resid features:
putting
Token putting
Feature activation+6.347
Top resid features:
a
Token a
Feature activation+0.728
Top resid features:
championship
Token championship
Feature activation+0.100
Top resid features:
-
Token-
Feature activation-0.012
Top resid features:
caliber
Tokencaliber
Feature activation+0.130
Top resid features:
team
Token team
Feature activation+0.184
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
clerk
Token clerk
Feature activation+0.046
Top resid features:
insists
Token insists
Feature activation+0.087
Top resid features:
on
Token on
Feature activation+0.053
Top resid features:
putting
Token putting
Feature activation+7.055
Top resid features:
the
Token the
Feature activation+0.212
Top resid features:
items
Token items
Feature activation+0.072
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
plastic
Token plastic
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
but
Token but
Feature activation-0.016
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
did
Token did
Feature activation+0.004
Top resid features:
not
Token not
Feature activation+0.146
Top resid features:
put
Token put
Feature activation+7.404
Top resid features:
g
Token g
Feature activation+0.018
Top resid features:
erry
Tokenerry
Feature activation-0.001
Top resid features:
mand
Tokenmand
Feature activation+0.053
Top resid features:
ering
Tokenering
Feature activation+0.057
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
reducing
Token reducing
Feature activation+0.012
Top resid features:
employee
Token employee
Feature activation+0.011
Top resid features:
travel
Token travel
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
putting
Token putting
Feature activation+6.829
Top resid features:
workers
Token workers
Feature activation+0.195
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
f
Token f
Feature activation+0.000
Top resid features:
url
Tokenurl
Feature activation+0.000
Top resid features:
ough
Tokenough
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
You
TokenYou
Feature activation+0.006
Top resid features:
might
Token might
Feature activation+0.005
Top resid features:
not
Token not
Feature activation+0.010
Top resid features:
put
Token put
Feature activation+7.085
Top resid features:
the
Token the
Feature activation+0.168
Top resid features:
two
Token two
Feature activation+0.292
Top resid features:
companies
Token companies
Feature activation+0.055
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
gave
Token gave
Feature activation+0.055
Top resid features:
him
Token him
Feature activation+0.023
Top resid features:
a
Token a
Feature activation-0.017
Top resid features:
beer
Token beer
Feature activation-0.160
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
put
Token put
Feature activation+7.284
Top resid features:
him
Token him
Feature activation+0.142
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
huge
Token huge
Feature activation-0.012
Top resid features:
surprise
Token surprise
Feature activation+0.014
Top resid features:
if
Token if
Feature activation+0.110
Top resid features:
they
Token they
Feature activation+0.047
Top resid features:
put
Token put
Feature activation+6.868
Top resid features:
N
Token N
Feature activation+0.036
Top resid features:
uke
Tokenuke
Feature activation+0.118
Top resid features:
or
Token or
Feature activation+0.020
Top resid features:
Over
Token Over
Feature activation+0.040
Top resid features:
pass
Tokenpass
Feature activation+0.074
Top resid features:
We
Token We
Feature activation-0.000
Top resid features:
get
Token get
Feature activation-0.005
Top resid features:
good
Token good
Feature activation-0.072
Top resid features:
feedback
Token feedback
Feature activation+0.362
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
put
Token put
Feature activation+5.530
Top resid features:
a
Token a
Feature activation+0.278
Top resid features:
lot
Token lot
Feature activation+0.330
Top resid features:
of
Token of
Feature activation+0.637
Top resid features:
that
Token that
Feature activation+0.262
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
rest
Token rest
Feature activation+0.095
Top resid features:
until
Token until
Feature activation+0.069
Top resid features:
she
Token she
Feature activation+0.025
Top resid features:
puts
Token puts
Feature activation+6.660
Top resid features:
me
Token me
Feature activation+0.205
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
rest
Token rest
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.005
Top resid features:
with
Token with
Feature activation-0.008
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
view
Token view
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.074
Top resid features:
putting
Token putting
Feature activation+6.848
Top resid features:
âĢ
Token âĢ
Feature activation+0.045
Top resid features:
ľ
Tokenľ
Feature activation+0.079
Top resid features:
creat
Tokencreat
Feature activation+0.052
Top resid features:
ive
Tokenive
Feature activation+0.098
Top resid features:
solutions
Token solutions
Feature activation+0.101
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.04

Head 3: 0.02

Head 4: 0.56

Head 5: 0.06

Head 6: 0.01

Head 7: 0.10

Head 8: 0.03

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

into3.37

squarely2.77

onto2.67

aside2.46

Into2.33

into2.27

INTO2.21

atop2.18

together2.16

down2.14

firmly2.07

upside1.95

smack1.95

overboard1.94

inside1.91

aboard1.83

icum1.81

solidly1.81

pinned1.77

neatly1.76

Negative logits

etheless-1.91

fail-1.76

success-1.76

}{-1.73

ptoms-1.72

Repe-1.70

ERG-1.66

sqor-1.59

Passage-1.56

rel-1.55

ranging-1.54

Applic-1.54

normal-1.54

cessive-1.53

HM-1.53

increasing-1.52

devices-1.51

apply-1.49

version-1.46

metast-1.46

INTERVAL 6.387 - 7.097
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.544
socialist
Token socialist
Feature activation+1.505
idea
Token idea
Feature activation+6.631
on
Token on
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
,
Token,
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
,
Token,
Feature activation+0.000
historical
Token historical
Feature activation+0.000
cleansing
Token cleansing
Feature activation+0.000
that
Token that
Feature activation+0.000
puts
Token puts
Feature activation+0.000
human
Token human
Feature activation+0.212
beings
Token beings
Feature activation+6.419
in
Token in
Feature activation+1.823
the
Token the
Feature activation+0.000
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
God
Token God
Feature activation+0.000
mand
Tokenmand
Feature activation+0.000
ering
Tokenering
Feature activation+6.169
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
landscape
Token landscape
Feature activation+6.711
entirely
Token entirely
Feature activation+4.732
off
Token off
Feature activation+0.000
limits
Token limits
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
putting
Token putting
Feature activation+0.037
them
Token them
Feature activation+6.463
into
Token into
Feature activation+0.565
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
've
Token've
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
him
Token him
Feature activation+0.000
put
Token put
Feature activation+0.112
anyone
Token anyone
Feature activation+6.678
in
Token in
Feature activation+1.972
a
Token a
Feature activation+0.611
bad
Token bad
Feature activation+0.000
situation
Token situation
Feature activation+0.000
.'
Token.'
Feature activation+0.000

INTERVAL 5.677 - 6.387
CONTAINS 0.002%

put
Token put
Feature activation+0.000
N
Token N
Feature activation+0.000
uke
Tokenuke
Feature activation+4.604
or
Token or
Feature activation+0.000
Over
Token Over
Feature activation+0.000
pass
Tokenpass
Feature activation+5.969
in
Token in
Feature activation+0.669
the
Token the
Feature activation+0.000
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
putting
Token putting
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.288
creat
Tokencreat
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
solutions
Token solutions
Feature activation+5.907
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.186
to
Token to
Feature activation+2.982
Minister
Token Minister
Feature activation+0.000
for
Token for
Feature activation+0.000
not
Token not
Feature activation+0.000
put
Token put
Feature activation+0.000
g
Token g
Feature activation+0.000
erry
Tokenerry
Feature activation+0.000
mand
Tokenmand
Feature activation+0.000
ering
Tokenering
Feature activation+6.169
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
landscape
Token landscape
Feature activation+6.711
entirely
Token entirely
Feature activation+4.732
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
put
Token put
Feature activation+0.000
that
Token that
Feature activation+4.309
copper
Token copper
Feature activation+5.817
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
incomplete
Token incomplete
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
,
Token,
Feature activation+0.000
putting
Token putting
Feature activation+0.681
the
Token the
Feature activation+1.968
movie
Token movie
Feature activation+6.200
three
Token three
Feature activation+1.384
million
Token million
Feature activation+2.483
dollars
Token dollars
Feature activation+3.218
over
Token over
Feature activation+0.047
budget
Token budget
Feature activation+0.000

INTERVAL 4.968 - 5.677
CONTAINS 0.004%

and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+0.257
comprehensive
Token comprehensive
Feature activation+3.378
rehabilitation
Token rehabilitation
Feature activation+4.054
program
Token program
Feature activation+5.064
around
Token around
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
him
Token him
Feature activation+0.000
challenger
Token challenger
Feature activation+0.000
in
Token in
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
,
Token,
Feature activation+0.000
putting
Token putting
Feature activation+0.000
him
Token him
Feature activation+5.246
at
Token at
Feature activation+0.000
odds
Token odds
Feature activation+0.000
with
Token with
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
majority
Token majority
Feature activation+0.000
an
Token an
Feature activation+0.000
ad
Token ad
Feature activation+3.285
-
Token-
Feature activation+0.000
lib
Tokenlib
Feature activation+0.495
bing
Tokenbing
Feature activation+3.429
comedian
Token comedian
Feature activation+5.114
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
stage
Token stage
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
Jeremy
Token Jeremy
Feature activation+0.000
Corbyn
Token Corbyn
Feature activation+0.000
put
Token put
Feature activation+0.000
you
Token you
Feature activation+5.243
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
start
Token start
Feature activation+0.000
defending
Token defending
Feature activation+0.000
-
Token-
Feature activation+0.000
car
Tokencar
Feature activation+0.000
riage
Tokenriage
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
them
Token them
Feature activation+5.023
in
Token in
Feature activation+0.298
(
Token (
Feature activation+0.000
although
Tokenalthough
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000

INTERVAL 4.258 - 4.968
CONTAINS 0.005%

Ben
Token Ben
Feature activation+0.000
Gins
Token Gins
Feature activation+0.000
berg
Tokenberg
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.124
list
Token list
Feature activation+4.876
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
has
Token has
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
would
Token would
Feature activation+0.000
put
Token put
Feature activation+0.000
them
Token them
Feature activation+4.411
in
Token in
Feature activation+0.200
places
Token places
Feature activation+0.000
where
Token where
Feature activation+0.000
people
Token people
Feature activation+0.000
would
Token would
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
tried
Token tried
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+0.218
pump
Token pump
Feature activation+4.571
motor
Token motor
Feature activation+3.988
and
Token and
Feature activation+0.218
my
Token my
Feature activation+0.000
wallet
Token wallet
Feature activation+5.350
in
Token in
Feature activation+0.896
ou
Tokenou
Feature activation+0.000
ches
Tokenches
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
her
Token her
Feature activation+4.064
food
Token food
Feature activation+4.385
into
Token into
Feature activation+0.099
them
Token them
Feature activation+0.000
so
Token so
Feature activation+0.000
she
Token she
Feature activation+0.000
can
Token can
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
puts
Token puts
Feature activation+0.000
his
Token his
Feature activation+0.000
vanity
Token vanity
Feature activation+4.840
before
Token before
Feature activation+0.009
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 3.548 - 4.258
CONTAINS 0.003%

s
Tokens
Feature activation+0.000
embell
Token embell
Feature activation+0.000
ishment
Tokenishment
Feature activation+0.000
has
Token has
Feature activation+0.000
placed
Token placed
Feature activation+0.490
him
Token him
Feature activation+3.785
in
Token in
Feature activation+0.027
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
where
Token where
Feature activation+0.000
his
Token his
Feature activation+0.000
streak
Token streak
Feature activation+0.000
would
Token would
Feature activation+0.000
put
Token put
Feature activation+0.000
both
Token both
Feature activation+0.428
of
Token of
Feature activation+0.000
those
Token those
Feature activation+4.149
numbers
Token numbers
Feature activation+5.772
back
Token back
Feature activation+1.802
in
Token in
Feature activation+1.526
more
Token more
Feature activation+0.000
respectable
Token respectable
Feature activation+0.000
incremental
Token incremental
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
politics
Token politics
Feature activation+0.000
,
Token,
Feature activation+0.000
putting
Token putting
Feature activation+0.000
power
Token power
Feature activation+3.596
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.938
in
Tokenin
Feature activation+1.274
the
Token the
Feature activation+1.381
hands
Token hands
Feature activation+0.000
p
Token p
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
ches
Tokenches
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
her
Token her
Feature activation+4.064
food
Token food
Feature activation+4.385
into
Token into
Feature activation+0.099
them
Token them
Feature activation+0.000
so
Token so
Feature activation+0.000
she
Token she
Feature activation+0.000
basic
Token basic
Feature activation+0.000
approaches
Token approaches
Feature activation+0.000
to
Token to
Feature activation+0.000
putting
Token putting
Feature activation+0.037
a
Token a
Feature activation+0.514
printer
Token printer
Feature activation+3.712
on
Token on
Feature activation+0.212
a
Token a
Feature activation+0.000
network
Token network
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 2.839 - 3.548
CONTAINS 0.005%

able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.128
Times
Token Times
Feature activation+4.705
in
Token in
Feature activation+3.443
contact
Token contact
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+0.000
,
Token,
Feature activation+0.000
office
Token office
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
printer
Token printer
Feature activation+3.144
on
Token on
Feature activation+0.287
the
Token the
Feature activation+0.000
office
Token office
Feature activation+0.000
network
Token network
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
putting
Token putting
Feature activation+0.000
100
Token 100
Feature activation+0.480
%
Token%
Feature activation+3.009
faith
Token faith
Feature activation+1.649
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
.
Token.
Feature activation+0.000
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.714
pressure
Token pressure
Feature activation+2.909
on
Token on
Feature activation+0.095
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
combatants
Token combatants
Feature activation+0.000
gains
Token gains
Feature activation+0.000
territory
Token territory
Feature activation+0.000
placing
Token placing
Feature activation+0.320
them
Token them
Feature activation+3.182
further
Token further
Feature activation+0.970
in
Token in
Feature activation+0.000
debt
Token debt
Feature activation+0.000
and
Token and
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000

INTERVAL 2.129 - 2.839
CONTAINS 0.006%

which
Token which
Feature activation+0.000
point
Token point
Feature activation+0.000
the
Token the
Feature activation+0.000
custom
Token custom
Feature activation+0.000
was
Token was
Feature activation+0.000
put
Token put
Feature activation+2.546
to
Token to
Feature activation+0.509
rest
Token rest
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
.
Token.
Feature activation+0.000
Can
Token Can
Feature activation+0.000
you
Token you
Feature activation+0.000
finish
Token finish
Feature activation+0.000
putting
Token putting
Feature activation+0.000
these
Token these
Feature activation+2.682
away
Token away
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
up
Token up
Feature activation+0.000
few
Token few
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
things
Token things
Feature activation+2.195
into
Token into
Feature activation+0.672
perspective
Token perspective
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
put
Token put
Feature activation+0.000
it
Token it
Feature activation+2.242
in
Token in
Feature activation+2.344
writing
Token writing
Feature activation+0.696
before
Token before
Feature activation+0.104
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
putting
Token putting
Feature activation+0.681
the
Token the
Feature activation+1.968
movie
Token movie
Feature activation+6.200
three
Token three
Feature activation+1.384
million
Token million
Feature activation+2.483
dollars
Token dollars
Feature activation+3.218
over
Token over
Feature activation+0.047
budget
Token budget
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.419 - 2.129
CONTAINS 0.010%

$
Token $
Feature activation+0.000
600
Token600
Feature activation+0.000
fine
Token fine
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
put
Token put
Feature activation+2.042
on
Token on
Feature activation+0.539
probation
Token probation
Feature activation+0.000
for
Token for
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.567
their
Token their
Feature activation+1.441
own
Token own
Feature activation+2.423
policies
Token policies
Feature activation+6.636
into
Token into
Feature activation+1.971
place
Token place
Feature activation+0.128
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
argue
Token argue
Feature activation+0.000
for
Token for
Feature activation+0.000
so
Token so
Feature activation+0.000
good
Token good
Feature activation+0.000
at
Token at
Feature activation+0.000
putting
Token putting
Feature activation+0.000
wins
Token wins
Feature activation+5.551
into
Token into
Feature activation+1.621
perspective
Token perspective
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Consider
TokenConsider
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
im
Token im
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
se
Tokense
Feature activation+0.983
ourselves
Token ourselves
Feature activation+1.728
in
Token in
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
's
Token's
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
for
Token for
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+1.837
any
Token any
Feature activation+4.502
weight
Token weight
Feature activation+1.778
on
Token on
Feature activation+1.182
this
Token this
Feature activation+0.000
number
Token number
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000

INTERVAL 0.710 - 1.419
CONTAINS 0.018%

rules
Token rules
Feature activation+0.000
have
Token have
Feature activation+0.000
put
Token put
Feature activation+0.000
even
Token even
Feature activation+0.000
tougher
Token tougher
Feature activation+0.576
limits
Token limits
Feature activation+0.768
on
Token on
Feature activation+0.000
down
Token down
Feature activation+0.000
payments
Token payments
Feature activation+0.000
,
Token,
Feature activation+0.000
loan
Token loan
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
First
TokenFirst
Feature activation+0.000
,
Token,
Feature activation+0.000
place
Token place
Feature activation+1.218
two
Token two
Feature activation+0.453
brig
Token brig
Feature activation+0.000
ades
Tokenades
Feature activation+2.508
on
Token on
Feature activation+0.429
its
Token its
Feature activation+0.000
has
Token has
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
requested
Token requested
Feature activation+0.000
putting
Token putting
Feature activation+0.000
ally
Token ally
Feature activation+1.089
in
Token in
Feature activation+0.000
charge
Token charge
Feature activation+0.000
of
Token of
Feature activation+0.000
Cohen
Token Cohen
Feature activation+0.000
probe
Token probe
Feature activation+0.000
aval
Tokenaval
Feature activation+0.000
ny
Tokenny
Feature activation+0.000
put
Token put
Feature activation+0.000
his
Token his
Feature activation+0.167
shoulder
Token shoulder
Feature activation+0.288
in
Token in
Feature activation+0.710
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sexuality
Token sexuality
Feature activation+0.000
that
Token that
Feature activation+0.000
Sue
Token Sue
Feature activation+0.000
Law
Token Law
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
put
Token put
Feature activation+1.113
to
Token to
Feature activation+0.610
him
Token him
Feature activation+0.000
on
Token on
Feature activation+0.000
Desert
Token Desert
Feature activation+0.000
Island
Token Island
Feature activation+0.000

INTERVAL 0.000 - 0.710
CONTAINS 99.946%

,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
great
Token great
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
disliked
Token disliked
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
despised
Token despised
Feature activation+0.000
ast
Token ast
Feature activation+0.000
a
Tokena
Feature activation+0.000
s
Token s
Feature activation+0.000
unt
Tokenunt
Feature activation+0.000
to
Token to
Feature activation+0.000
Å
TokenÅ
Feature activation+0.000
£
Token£
Feature activation+0.000
i
Tokeni
Feature activation+0.000
de
Token de
Feature activation+0.000
ac
Token ac
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
350
Token 350
Feature activation+0.000
engines
Token engines
Feature activation+0.000
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
state
Token state
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
fire
Token fire
Feature activation+0.000
has
Token has
Feature activation+0.000
This
TokenThis
Feature activation+0.000
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
work
Token work
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
day
Token day
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
passionate
Token passionate
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
reens
Tokenreens
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
often
Token often
Feature activation+0.000
bon
Token bon
Feature activation+0.000
kers
Tokenkers
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 H8.4: (feature 9401)

TOP ACTIVATIONS
MAX = 6.420

in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.160
the
Token the
Feature activation+3.325
president
Token president
Feature activation+6.420
from
Token from
Feature activation+2.993
being
Token being
Feature activation+2.209
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
elected
Tokenelected
Feature activation+0.000
the
Token the
Feature activation+0.000
statue
Token statue
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
Sci
Token Sci
Feature activation+0.090
oli
Tokenoli
Feature activation+6.190
from
Token from
Feature activation+2.871
picking
Token picking
Feature activation+0.000
it
Token it
Feature activation+0.000
back
Token back
Feature activation+0.000
up
Token up
Feature activation+0.000
malicious
Token malicious
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.399
his
Token his
Feature activation+2.578
wife
Token wife
Feature activation+6.119
from
Token from
Feature activation+2.475
recovering
Token recovering
Feature activation+0.000
marital
Token marital
Feature activation+0.000
assets
Token assets
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
prevent
Token prevent
Feature activation+0.246
him
Token him
Feature activation+6.102
from
Token from
Feature activation+0.879
having
Token having
Feature activation+0.355
a
Token a
Feature activation+0.000
fair
Token fair
Feature activation+0.000
sentencing
Token sentencing
Feature activation+0.000
to
Token to
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.000
threads
Token threads
Feature activation+5.699
from
Token from
Feature activation+1.390
getting
Token getting
Feature activation+0.000
tangled
Token tangled
Feature activation+0.000
.
Token.
Feature activation+0.000
Eventually
Token Eventually
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
road
Token road
Feature activation+0.000
blocks
Tokenblocks
Feature activation+0.000
that
Token that
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
him
Token him
Feature activation+5.433
from
Token from
Feature activation+0.567
dealing
Token dealing
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
at
Token at
Feature activation+0.000
risk
Token risk
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
anyone
Token anyone
Feature activation+3.982
else
Token else
Feature activation+5.356
from
Token from
Feature activation+0.824
getting
Token getting
Feature activation+0.000
injured
Token injured
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.949
tar
Token tar
Feature activation+0.000
sands
Token sands
Feature activation+2.092
oil
Token oil
Feature activation+5.232
from
Token from
Feature activation+1.208
flowing
Token flowing
Feature activation+0.000
to
Token to
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
his
Token his
Feature activation+1.967
mother
Token mother
Feature activation+5.171
from
Token from
Feature activation+1.594
being
Token being
Feature activation+0.627
killed
Token killed
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
your
Token your
Feature activation+0.000
plan
Token plan
Feature activation+0.000
may
Token may
Feature activation+0.000
also
Token also
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
you
Token you
Feature activation+5.088
from
Token from
Feature activation+0.452
rolling
Token rolling
Feature activation+0.000
over
Token over
Feature activation+0.000
portions
Token portions
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+0.000
countries
Token countries
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
prevents
Token prevents
Feature activation+0.000
Congress
Token Congress
Feature activation+5.075
changing
Token changing
Feature activation+0.000
the
Token the
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
her
Token her
Feature activation+5.042
from
Token from
Feature activation+0.402
having
Token having
Feature activation+0.407
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
time
Token time
Feature activation+0.000
With
Token With
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
endings
Token endings
Feature activation+0.000
,
Token,
Feature activation+0.000
preventing
Token preventing
Feature activation+0.240
Earth
Token Earth
Feature activation+5.014
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.229
s
Tokens
Feature activation+4.590
destruction
Token destruction
Feature activation+0.000
is
Token is
Feature activation+0.000
from
Token from
Feature activation+1.732
fragment
Token fragment
Feature activation+0.000
ing
Tokening
Feature activation+0.000
and
Token and
Feature activation+0.000
social
Token social
Feature activation+0.000
networks
Token networks
Feature activation+4.996
from
Token from
Feature activation+0.445
diss
Token diss
Feature activation+0.000
olving
Tokenolving
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
used
Token used
Feature activation+2.826
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
object
Token object
Feature activation+4.995
from
Token from
Feature activation+1.915
being
Token being
Feature activation+0.398
freed
Token freed
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
an
Token an
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
other
Token other
Feature activation+0.000
teams
Token teams
Feature activation+4.972
-
Token -
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
Cowboys
Token Cowboys
Feature activation+0.000
-
Token -
Feature activation+4.433
'
Token'
Feature activation+0.000
a
Token a
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
her
Token her
Feature activation+4.965
from
Token from
Feature activation+0.575
becoming
Token becoming
Feature activation+0.000
a
Token a
Feature activation+0.000
surgeon
Token surgeon
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
iveness
Tokeniveness
Feature activation+0.000
is
Token is
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.185
anyone
Token anyone
Feature activation+4.867
from
Token from
Feature activation+1.007
taking
Token taking
Feature activation+0.000
offense
Token offense
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
an
Token an
Feature activation+0.000
iron
Token iron
Feature activation+0.000
deficiency
Token deficiency
Feature activation+0.000
that
Token that
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
him
Token him
Feature activation+4.855
from
Token from
Feature activation+0.418
giving
Token giving
Feature activation+0.000
full
Token full
Feature activation+0.000
effort
Token effort
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
neo
Token neo
Feature activation+0.000
-
Token-
Feature activation+0.000
Nazi
TokenNazi
Feature activation+0.455
organizations
Token organizations
Feature activation+4.849
from
Token from
Feature activation+0.638
overt
Token overt
Feature activation+0.000
aking
Tokenaking
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
in
Token in
Feature activation+0.000

Top DFA by src position
MAX = 8.113

the
Token the
Feature activation+0.018
Top resid features:
recovery
Token recovery
Feature activation+0.145
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
order
Token order
Feature activation+0.039
Top resid features:
to
Token to
Feature activation-0.020
Top resid features:
prevent
Token prevent
Feature activation+7.241
Top resid features:
the
Token the
Feature activation+0.550
Top resid features:
president
Token president
Feature activation+0.090
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
re
Token re
Feature activation+0.000
Top resid features:
down
Token down
Feature activation-0.051
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
statue
Token statue
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
prevent
Token prevent
Feature activation+8.113
Top resid features:
Sci
Token Sci
Feature activation+0.165
Top resid features:
oli
Tokenoli
Feature activation+0.065
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
picking
Token picking
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
simply
Token simply
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
malicious
Token malicious
Feature activation+0.025
Top resid features:
attempt
Token attempt
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
prevent
Token prevent
Feature activation+7.402
Top resid features:
his
Token his
Feature activation+0.401
Top resid features:
wife
Token wife
Feature activation+0.128
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
recovering
Token recovering
Feature activation+0.000
Top resid features:
marital
Token marital
Feature activation+0.000
Top resid features:
comments
Token comments
Feature activation-0.021
Top resid features:
about
Token about
Feature activation+0.023
Top resid features:
Ber
Token Ber
Feature activation+0.028
Top resid features:
gd
Tokengd
Feature activation+0.007
Top resid features:
ahl
Tokenahl
Feature activation+0.011
Top resid features:
prevent
Token prevent
Feature activation+7.774
Top resid features:
him
Token him
Feature activation+0.041
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
having
Token having
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
fair
Token fair
Feature activation+0.000
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
time
Token time
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.013
Top resid features:
time
Token time
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
prevent
Token prevent
Feature activation+6.840
Top resid features:
the
Token the
Feature activation+0.861
Top resid features:
threads
Token threads
Feature activation+0.095
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
tangled
Token tangled
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
biggest
Token biggest
Feature activation+0.013
Top resid features:
road
Token road
Feature activation+0.009
Top resid features:
blocks
Tokenblocks
Feature activation-0.034
Top resid features:
that
Token that
Feature activation+0.118
Top resid features:
prevented
Token prevented
Feature activation+7.028
Top resid features:
him
Token him
Feature activation+0.091
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
dealing
Token dealing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
own
Token own
Feature activation-0.017
Top resid features:
life
Token life
Feature activation-0.015
Top resid features:
at
Token at
Feature activation-0.028
Top resid features:
risk
Token risk
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.031
Top resid features:
prevent
Token prevent
Feature activation+6.986
Top resid features:
anyone
Token anyone
Feature activation+0.369
Top resid features:
else
Token else
Feature activation+0.152
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
injured
Token injured
Feature activation+0.000
Top resid features:
fine
Token fine
Feature activation+0.006
Top resid features:
example
Token example
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.024
Top resid features:
If
Token If
Feature activation-0.027
Top resid features:
opponents
Token opponents
Feature activation-0.065
Top resid features:
prevent
Token prevent
Feature activation+6.775
Top resid features:
Canadian
Token Canadian
Feature activation+0.457
Top resid features:
tar
Token tar
Feature activation+0.076
Top resid features:
sands
Token sands
Feature activation+0.105
Top resid features:
oil
Token oil
Feature activation+0.120
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
traveling
Token traveling
Feature activation+0.015
Top resid features:
back
Token back
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.022
Top resid features:
time
Token time
Feature activation+0.032
Top resid features:
to
Token to
Feature activation+0.054
Top resid features:
prevent
Token prevent
Feature activation+6.680
Top resid features:
his
Token his
Feature activation+0.376
Top resid features:
mother
Token mother
Feature activation+0.098
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
killed
Token killed
Feature activation+0.000
Top resid features:
within
Token within
Feature activation-0.021
Top resid features:
your
Token your
Feature activation-0.055
Top resid features:
plan
Token plan
Feature activation-0.076
Top resid features:
may
Token may
Feature activation-0.082
Top resid features:
also
Token also
Feature activation-0.037
Top resid features:
prevent
Token prevent
Feature activation+7.310
Top resid features:
you
Token you
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
rolling
Token rolling
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
portions
Token portions
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.021
Top resid features:
other
Token other
Feature activation+0.014
Top resid features:
countries
Token countries
Feature activation+0.016
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
prevents
Token prevents
Feature activation+6.466
Top resid features:
Congress
Token Congress
Feature activation+0.032
Top resid features:
changing
Token changing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
details
Token details
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
a
Token a
Feature activation-0.047
Top resid features:
Muslim
Token Muslim
Feature activation-0.086
Top resid features:
does
Token does
Feature activation+0.019
Top resid features:
not
Token not
Feature activation-0.052
Top resid features:
prevent
Token prevent
Feature activation+7.519
Top resid features:
her
Token her
Feature activation+0.005
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
having
Token having
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
With
Token With
Feature activation-0.015
Top resid features:
multiple
Token multiple
Feature activation-0.001
Top resid features:
endings
Token endings
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
preventing
Token preventing
Feature activation+6.815
Top resid features:
Earth
Token Earth
Feature activation+0.224
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
destruction
Token destruction
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.013
Top resid features:
always
Token always
Feature activation-0.021
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
how
Token how
Feature activation+0.067
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
prevent
Token prevent
Feature activation+6.242
Top resid features:
communities
Token communities
Feature activation+0.043
Top resid features:
from
Token from
Feature activation+0.364
Top resid features:
fragment
Token fragment
Feature activation+0.091
Top resid features:
ing
Tokening
Feature activation+0.139
Top resid features:
and
Token and
Feature activation+0.141
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
weak
Token weak
Feature activation-0.001
Top resid features:
_
Token_
Feature activation+0.001
Top resid features:
ptr
Tokenptr
Feature activation+0.011
Top resid features:
will
Token will
Feature activation+0.073
Top resid features:
prevent
Token prevent
Feature activation+5.460
Top resid features:
the
Token the
Feature activation+0.314
Top resid features:
memory
Token memory
Feature activation+0.103
Top resid features:
that
Token that
Feature activation+0.114
Top resid features:
was
Token was
Feature activation+0.161
Top resid features:
used
Token used
Feature activation+0.288
Top resid features:
held
Token held
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
an
Token an
Feature activation+0.003
Top resid features:
effort
Token effort
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
prevent
Token prevent
Feature activation+6.490
Top resid features:
other
Token other
Feature activation+0.184
Top resid features:
teams
Token teams
Feature activation+0.062
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
severe
Token severe
Feature activation-0.000
Top resid features:
'
Token'
Feature activation+0.041
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
punishment
Token punishment
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
prevent
Token prevent
Feature activation+7.349
Top resid features:
her
Token her
Feature activation+0.040
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
becoming
Token becoming
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
surgeon
Token surgeon
Feature activation+0.000
Top resid features:
ens
Tokenens
Feature activation+0.001
Top resid features:
iveness
Tokeniveness
Feature activation+0.078
Top resid features:
is
Token is
Feature activation+0.039
Top resid features:
supposed
Token supposed
Feature activation+0.069
Top resid features:
to
Token to
Feature activation+0.046
Top resid features:
prevent
Token prevent
Feature activation+6.069
Top resid features:
anyone
Token anyone
Feature activation+0.249
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
offense
Token offense
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.013
Top resid features:
an
Token an
Feature activation-0.008
Top resid features:
iron
Token iron
Feature activation-0.006
Top resid features:
deficiency
Token deficiency
Feature activation-0.192
Top resid features:
that
Token that
Feature activation+0.079
Top resid features:
prevented
Token prevented
Feature activation+6.775
Top resid features:
him
Token him
Feature activation+0.070
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
giving
Token giving
Feature activation+0.000
Top resid features:
full
Token full
Feature activation+0.000
Top resid features:
effort
Token effort
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.200
Top resid features:
even
Token even
Feature activation+0.041
Top resid features:
partnered
Token partnered
Feature activation-0.102
Top resid features:
together
Token together
Feature activation-0.078
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
prevent
Token prevent
Feature activation+6.602
Top resid features:
neo
Token neo
Feature activation+0.041
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
Nazi
TokenNazi
Feature activation+0.099
Top resid features:
organizations
Token organizations
Feature activation+0.077
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.56

Head 5: 0.07

Head 6: 0.02

Head 7: 0.10

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.02

Positive logits

from3.18

from2.92

From2.47

harming2.36

accidental2.30

FROM2.23

escaping2.22

leakage2.14

accessing2.14

access2.13

From2.13

damaging2.07

unintended2.04

happening2.03

compromise2.01

wasting2.00

contamination1.99

getting1.98

poisoning1.98

escape1.95

Negative logits

龍喚士-2.17

200000-2.15

��極-2.01

english-1.90

SUP-1.89

Dragonbound-1.88

itcher-1.83

nob-1.80

AMA-1.80

Downloadha-1.80

bush-1.77

-1.75

-1.74

KNOWN-1.73

ores-1.71

rices-1.71

\",-1.71

Independent-1.71

YES-1.71

Reviewer-1.70

INTERVAL 5.778 - 6.420
CONTAINS 0.000%

in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.160
the
Token the
Feature activation+3.325
president
Token president
Feature activation+6.420
from
Token from
Feature activation+2.993
being
Token being
Feature activation+2.209
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
elected
Tokenelected
Feature activation+0.000
about
Token about
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
prevent
Token prevent
Feature activation+0.246
him
Token him
Feature activation+6.102
from
Token from
Feature activation+0.879
having
Token having
Feature activation+0.355
a
Token a
Feature activation+0.000
fair
Token fair
Feature activation+0.000
sentencing
Token sentencing
Feature activation+0.000
the
Token the
Feature activation+0.000
statue
Token statue
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
Sci
Token Sci
Feature activation+0.090
oli
Tokenoli
Feature activation+6.190
from
Token from
Feature activation+2.871
picking
Token picking
Feature activation+0.000
it
Token it
Feature activation+0.000
back
Token back
Feature activation+0.000
up
Token up
Feature activation+0.000
malicious
Token malicious
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.399
his
Token his
Feature activation+2.578
wife
Token wife
Feature activation+6.119
from
Token from
Feature activation+2.475
recovering
Token recovering
Feature activation+0.000
marital
Token marital
Feature activation+0.000
assets
Token assets
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 5.136 - 5.778
CONTAINS 0.001%

at
Token at
Feature activation+0.000
risk
Token risk
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
anyone
Token anyone
Feature activation+3.982
else
Token else
Feature activation+5.356
from
Token from
Feature activation+0.824
getting
Token getting
Feature activation+0.000
injured
Token injured
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.000
threads
Token threads
Feature activation+5.699
from
Token from
Feature activation+1.390
getting
Token getting
Feature activation+0.000
tangled
Token tangled
Feature activation+0.000
.
Token.
Feature activation+0.000
Eventually
Token Eventually
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.949
tar
Token tar
Feature activation+0.000
sands
Token sands
Feature activation+2.092
oil
Token oil
Feature activation+5.232
from
Token from
Feature activation+1.208
flowing
Token flowing
Feature activation+0.000
to
Token to
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
his
Token his
Feature activation+1.967
mother
Token mother
Feature activation+5.171
from
Token from
Feature activation+1.594
being
Token being
Feature activation+0.627
killed
Token killed
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
road
Token road
Feature activation+0.000
blocks
Tokenblocks
Feature activation+0.000
that
Token that
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
him
Token him
Feature activation+5.433
from
Token from
Feature activation+0.567
dealing
Token dealing
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000

INTERVAL 4.494 - 5.136
CONTAINS 0.002%

other
Token other
Feature activation+0.000
countries
Token countries
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
prevents
Token prevents
Feature activation+0.000
Congress
Token Congress
Feature activation+5.075
changing
Token changing
Feature activation+0.000
the
Token the
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
With
Token With
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
endings
Token endings
Feature activation+0.000
,
Token,
Feature activation+0.000
preventing
Token preventing
Feature activation+0.240
Earth
Token Earth
Feature activation+5.014
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.229
s
Tokens
Feature activation+4.590
destruction
Token destruction
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+4.607
from
Token from
Feature activation+0.703
drying
Token drying
Feature activation+0.000
or
Token or
Feature activation+0.733
burning
Token burning
Feature activation+0.000
up
Token up
Feature activation+0.000
from
Token from
Feature activation+1.732
fragment
Token fragment
Feature activation+0.000
ing
Tokening
Feature activation+0.000
and
Token and
Feature activation+0.000
social
Token social
Feature activation+0.000
networks
Token networks
Feature activation+4.996
from
Token from
Feature activation+0.445
diss
Token diss
Feature activation+0.000
olving
Tokenolving
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
iveness
Tokeniveness
Feature activation+0.000
is
Token is
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.185
anyone
Token anyone
Feature activation+4.867
from
Token from
Feature activation+1.007
taking
Token taking
Feature activation+0.000
offense
Token offense
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 3.852 - 4.494
CONTAINS 0.002%

achieved
Token achieved
Feature activation+0.000
by
Token by
Feature activation+0.000
preventing
Token preventing
Feature activation+0.000
the
Token the
Feature activation+0.000
tumor
Token tumor
Feature activation+4.339
cells
Token cells
Feature activation+4.125
from
Token from
Feature activation+2.053
inducing
Token inducing
Feature activation+0.000
cell
Token cell
Feature activation+0.000
death
Token death
Feature activation+0.000
in
Token in
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
preventing
Token preventing
Feature activation+0.000
an
Token an
Feature activation+0.789
application
Token application
Feature activation+4.382
from
Token from
Feature activation+2.095
using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
massive
Token massive
Feature activation+0.000
process
Token process
Feature activation+0.000
responsibility
Token responsibility
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
free
Token free
Feature activation+0.000
press
Token press
Feature activation+4.098
âĢĶ
Token âĢĶ
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
teams
Token teams
Feature activation+4.972
-
Token -
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
Cowboys
Token Cowboys
Feature activation+0.000
-
Token -
Feature activation+4.433
from
Token from
Feature activation+0.000
knowing
Token knowing
Feature activation+0.000
which
Token which
Feature activation+0.000
prospect
Token prospect
Feature activation+0.000
they
Token they
Feature activation+0.000
preventing
Token preventing
Feature activation+0.000
any
Token any
Feature activation+1.108
shipping
Token shipping
Feature activation+1.330
or
Token or
Feature activation+0.000
fer
Token fer
Feature activation+0.000
ries
Tokenries
Feature activation+4.426
to
Token to
Feature activation+2.031
run
Token run
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000

INTERVAL 3.210 - 3.852
CONTAINS 0.001%

to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.594
Federal
Token Federal
Feature activation+1.029
Communications
Token Communications
Feature activation+0.000
Commission
Token Commission
Feature activation+3.494
from
Token from
Feature activation+0.000
regulating
Token regulating
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
prices
Token prices
Feature activation+0.000
passed
Token passed
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
non
Token non
Feature activation+0.000
wh
Tokenwh
Feature activation+0.000
ites
Tokenites
Feature activation+3.650
to
Token to
Feature activation+0.392
own
Token own
Feature activation+0.000
land
Token land
Feature activation+0.000
or
Token or
Feature activation+0.000
to
Token to
Feature activation+0.000
CO
Token CO
Feature activation+0.000
2
Token2
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
and
Token and
Feature activation+0.000
prevent
Token prevent
Feature activation+0.179
global
Token global
Feature activation+3.427
warming
Token warming
Feature activation+0.709
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
death
Token death
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
that
Token that
Feature activation+3.745
,
Token,
Feature activation+0.000
farm
Token farm
Feature activation+0.000
workers
Token workers
Feature activation+0.000
dock
Token dock
Feature activation+0.000
pig
Token pig
Feature activation+0.000
Play
Token Play
Feature activation+0.000
policy
Token policy
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
prevents
Token prevents
Feature activation+0.000
parents
Token parents
Feature activation+3.251
from
Token from
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000
childcare
Token childcare
Feature activation+0.000
reb
Token reb
Feature activation+0.000
ates
Tokenates
Feature activation+0.000

INTERVAL 2.568 - 3.210
CONTAINS 0.001%

of
Token of
Feature activation+0.000
measures
Token measures
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
something
Token something
Feature activation+3.149
similar
Token similar
Feature activation+2.817
from
Token from
Feature activation+1.019
occurring
Token occurring
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
act
Token act
Feature activation+0.000
by
Token by
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.110
the
Token the
Feature activation+2.848
publication
Token publication
Feature activation+0.141
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
expected
Token expected
Feature activation+0.000
photographs
Token photographs
Feature activation+0.000
said
Token said
Feature activation+0.000
government
Token government
Feature activation+0.000
shutdown
Token shutdown
Feature activation+0.000
prevented
Token prevented
Feature activation+2.185
benefits
Token benefits
Feature activation+4.023
from
Token from
Feature activation+3.200
being
Token being
Feature activation+1.694
paid
Token paid
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
that
Token that
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
a
Token a
Feature activation+0.000
wheel
Token wheel
Feature activation+0.686
ed
Tokened
Feature activation+0.000
robot
Token robot
Feature activation+2.629
from
Token from
Feature activation+0.172
running
Token running
Feature activation+0.000
into
Token into
Feature activation+0.000
walls
Token walls
Feature activation+0.000
.
Token.
Feature activation+0.000
prevent
Token prevent
Feature activation+0.576
the
Token the
Feature activation+0.000
memory
Token memory
Feature activation+2.210
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
used
Token used
Feature activation+2.826
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
object
Token object
Feature activation+4.995
from
Token from
Feature activation+1.915
being
Token being
Feature activation+0.398

INTERVAL 1.926 - 2.568
CONTAINS 0.002%

entirely
Token entirely
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
a
Token a
Feature activation+0.000
Content
Token Content
Feature activation+0.000
ID
TokenID
Feature activation+2.062
claim
Token claim
Feature activation+2.104
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
any
Token any
Feature activation+1.108
shipping
Token shipping
Feature activation+1.330
or
Token or
Feature activation+0.000
fer
Token fer
Feature activation+0.000
ries
Tokenries
Feature activation+4.426
to
Token to
Feature activation+2.031
run
Token run
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
If
Token If
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.949
tar
Token tar
Feature activation+0.000
sands
Token sands
Feature activation+2.092
oil
Token oil
Feature activation+5.232
from
Token from
Feature activation+1.208
flowing
Token flowing
Feature activation+0.000
to
Token to
Feature activation+0.000
U
Token U
Feature activation+0.000
Nordic
Token Nordic
Feature activation+0.291
(
Token (
Feature activation+0.000
or
Tokenor
Feature activation+0.000
other
Token other
Feature activation+0.000
pagan
Token pagan
Feature activation+0.000
)
Token)
Feature activation+2.317
tribes
Token tribes
Feature activation+3.739
to
Token to
Feature activation+2.560
develop
Token develop
Feature activation+0.000
norms
Token norms
Feature activation+0.000
and
Token and
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.399
his
Token his
Feature activation+2.578
wife
Token wife
Feature activation+6.119
from
Token from
Feature activation+2.475
recovering
Token recovering
Feature activation+0.000
marital
Token marital
Feature activation+0.000
assets
Token assets
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.284 - 1.926
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
hib
Tokenhib
Feature activation+0.000
its
Tokenits
Feature activation+0.000
cities
Token cities
Feature activation+1.454
from
Token from
Feature activation+0.000
establishing
Token establishing
Feature activation+0.000
higher
Token higher
Feature activation+0.000
minimum
Token minimum
Feature activation+0.000
wages
Token wages
Feature activation+0.000
post
Token post
Feature activation+0.000
Salt
Token Salt
Feature activation+0.000
Will
Token Will
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
Your
Token Your
Feature activation+0.000
Beans
Token Beans
Feature activation+1.389
from
Token from
Feature activation+0.000
Soft
Token Soft
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
you
Token you
Feature activation+0.000
on
Token on
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
remove
Token remove
Feature activation+0.000
yourself
Token yourself
Feature activation+1.304
from
Token from
Feature activation+0.000
mailing
Token mailing
Feature activation+0.000
lists
Token lists
Feature activation+0.000
.
Token.
Feature activation+0.000
Nobody
Token Nobody
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.000
threads
Token threads
Feature activation+5.699
from
Token from
Feature activation+1.390
getting
Token getting
Feature activation+0.000
tangled
Token tangled
Feature activation+0.000
.
Token.
Feature activation+0.000
Eventually
Token Eventually
Feature activation+0.000
you
Token you
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
such
Token such
Feature activation+0.016
a
Token a
Feature activation+1.581
conflict
Token conflict
Feature activation+1.062
.
Token.
Feature activation+0.000
Massive
Token Massive
Feature activation+0.000
industrialized
Token industrialized
Feature activation+0.000
powers
Token powers
Feature activation+0.000

INTERVAL 0.642 - 1.284
CONTAINS 0.006%

his
Token his
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
moms
Token moms
Feature activation+1.211
âĢĶ
Token âĢĶ
Feature activation+0.000
or
Token or
Feature activation+0.000
any
Token any
Feature activation+0.000
one
Token one
Feature activation+0.000
else
Token else
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
or
Token or
Feature activation+0.000
any
Token any
Feature activation+0.000
one
Token one
Feature activation+0.000
else
Token else
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.987
from
Token from
Feature activation+0.000
buying
Token buying
Feature activation+0.000
cups
Token cups
Feature activation+0.000
of
Token of
Feature activation+0.000
soda
Token soda
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
what
Token what
Feature activation+0.000
just
Token just
Feature activation+0.000
happened
Token happened
Feature activation+0.188
to
Token to
Feature activation+0.885
JPMorgan
Token JPMorgan
Feature activation+1.160
.
Token.
Feature activation+0.000
Levin
Token Levin
Feature activation+0.000
told
Token told
Feature activation+0.000
CNBC
Token CNBC
Feature activation+0.000
"
Token "
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
the
Token the
Feature activation+0.944
plunder
Token plunder
Feature activation+0.000
ing
Tokening
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fighters
Token fighters
Feature activation+0.000
news
Token news
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
Recovery
Token Recovery
Feature activation+0.000
and
Token and
Feature activation+0.819
Rein
Token Rein
Feature activation+0.000
vest
Tokenvest
Feature activation+0.000
ment
Tokenment
Feature activation+0.300
Act
Token Act
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.642
CONTAINS 99.982%

related
Tokenrelated
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
-
Token -
Feature activation+0.000
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+0.000
7
Token 7
Feature activation+0.000
43
Token43
Feature activation+0.000
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
relies
Token relies
Feature activation+0.000
instead
Token instead
Feature activation+0.000
on
Token on
Feature activation+0.000
touch
Token touch
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mom
TokenMom
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
hall
Token hall
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Adding
TokenAdding
Feature activation+0.000
a
Token a
Feature activation+0.000
ladder
Token ladder
Feature activation+0.000
rack
Token rack
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
commercial
Token commercial
Feature activation+0.000
truck
Token truck
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
our
Token our
Feature activation+0.000
world
Token world
Feature activation+0.000
-
Token-
Feature activation+0.000
class
Tokenclass
Feature activation+0.000
ref
Token ref
Feature activation+0.000
ineries
Tokenineries
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
ultimately
Token ultimately
Feature activation+0.000
comments
Token comments
Feature activation+0.000
,
Token,
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Netanyahu
Token Netanyahu
Feature activation+0.000
announced
Token announced
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
18
Token 18
Feature activation+0.000
-
Token-
Feature activation+0.000
mile
Tokenmile
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