H2.7 top features

Top feature 0 in H2.7: (feature 10686)

TOP ACTIVATIONS
MAX = 1.839

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.405
election
Token election
Feature activation+1.674
.
Token.
Feature activation+1.322
Ċ
TokenĊ
Feature activation+0.794
Ċ
TokenĊ
Feature activation+0.482
When
TokenWhen
Feature activation+0.146
Baldwin
Token Baldwin
Feature activation+0.000
-
Token-
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+1.381
once
Token once
Feature activation+1.235
voters
Token voters
Feature activation+1.839
saw
Token saw
Feature activation+1.309
that
Token that
Feature activation+0.972
he
Token he
Feature activation+0.775
and
Token and
Feature activation+0.664
the
Token the
Feature activation+0.537
party
Token party
Feature activation+0.794
Likely
Token Likely
Feature activation+0.000
Republican
Token Republican
Feature activation+0.201
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Primary
TokenPrimary
Feature activation+0.169
Voters
Token Voters
Feature activation+1.216
Supp
Token Supp
Feature activation+1.184
orter
Tokenorter
Feature activation+1.019
(
Token (
Feature activation+0.696
36
Token36
Feature activation+0.550
%)
Token%)
Feature activation+0.462
vote
Token vote
Feature activation+1.141
.
Token.
Feature activation+0.987
Ċ
TokenĊ
Feature activation+0.687
Ċ
TokenĊ
Feature activation+0.466
Elect
TokenElect
Feature activation+1.076
oral
Tokenoral
Feature activation+1.203
commission
Token commission
Feature activation+0.974
head
Token head
Feature activation+1.029
Maurice
Token Maurice
Feature activation+0.598
I
Token I
Feature activation+0.536
wu
Tokenwu
Feature activation+0.240
voting
Token voting
Feature activation+1.184
members
Token members
Feature activation+1.133
and
Token and
Feature activation+0.869
stand
Token stand
Feature activation+0.720
for
Token for
Feature activation+0.157
election
Token election
Feature activation+1.199
to
Token to
Feature activation+0.849
their
Token their
Feature activation+0.729
ruling
Token ruling
Feature activation+0.457
committees
Token committees
Feature activation+0.397
.
Token.
Feature activation+0.520
Republican
Token Republican
Feature activation+0.201
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Primary
TokenPrimary
Feature activation+0.169
Voters
Token Voters
Feature activation+1.216
Supp
Token Supp
Feature activation+1.184
orter
Tokenorter
Feature activation+1.019
(
Token (
Feature activation+0.696
36
Token36
Feature activation+0.550
%)
Token%)
Feature activation+0.462
Not
Token Not
Feature activation+0.390
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
support
Token support
Feature activation+0.000
among
Token among
Feature activation+0.000
Republican
Token Republican
Feature activation+0.028
voters
Token voters
Feature activation+1.153
and
Token and
Feature activation+1.176
her
Token her
Feature activation+0.764
speeches
Token speeches
Feature activation+0.818
draw
Token draw
Feature activation+0.881
large
Token large
Feature activation+0.756
crowds
Token crowds
Feature activation+1.048
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
initiative
Token initiative
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.000
voters
Token voters
Feature activation+1.163
to
Token to
Feature activation+0.977
approve
Token approve
Feature activation+0.828
of
Token of
Feature activation+0.484
the
Token the
Feature activation+0.500
state
Token state
Feature activation+0.478
also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+1.162
on
Token on
Feature activation+0.819
May
Token May
Feature activation+0.884
3
Token 3
Feature activation+0.748
rd
Tokenrd
Feature activation+0.426
,
Token,
Feature activation+0.530
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
council
Token council
Feature activation+0.000
before
Token before
Feature activation+0.000
its
Token its
Feature activation+0.000
vote
Token vote
Feature activation+1.146
terminating
Token terminating
Feature activation+0.924
his
Token his
Feature activation+0.622
position
Token position
Feature activation+0.366
this
Token this
Feature activation+0.275
month
Token month
Feature activation+0.256
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
poll
Token poll
Feature activation+0.693
asked
Token asked
Feature activation+0.733
respondents
Token respondents
Feature activation+1.136
if
Token if
Feature activation+0.895
they
Token they
Feature activation+0.467
would
Token would
Feature activation+0.220
support
Token support
Feature activation+0.257
or
Token or
Feature activation+0.242
who
Token who
Feature activation+0.646
are
Token are
Feature activation+0.345
supporting
Token supporting
Feature activation+0.602
Libertarian
Token Libertarian
Feature activation+0.526
Party
Token Party
Feature activation+0.677
candidate
Token candidate
Feature activation+1.130
Gary
Token Gary
Feature activation+1.029
Johnson
Token Johnson
Feature activation+0.798
or
Token or
Feature activation+0.663
Jill
Token Jill
Feature activation+0.494
Stein
Token Stein
Feature activation+0.361
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
since
Token since
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
vote
Token vote
Feature activation+1.112
in
Token in
Feature activation+0.886
favour
Token favour
Feature activation+0.658
of
Token of
Feature activation+0.745
the
Token the
Feature activation+0.740
bill
Token bill
Feature activation+0.587
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
7
Token 7
Feature activation+0.000
,
Token,
Feature activation+0.000
04
Token04
Feature activation+0.000
2
Token2
Feature activation+0.000
votes
Token votes
Feature activation+1.102
,
Token,
Feature activation+0.961
respectively
Token respectively
Feature activation+0.697
.
Token.
Feature activation+0.540
He
Token He
Feature activation+0.521
also
Token also
Feature activation+0.456
voters
Token voters
Feature activation+0.519
in
Token in
Feature activation+0.723
this
Token this
Feature activation+0.830
month
Token month
Feature activation+0.530
's
Token's
Feature activation+0.394
election
Token election
Feature activation+1.086
identified
Token identified
Feature activation+0.813
themselves
Token themselves
Feature activation+0.298
as
Token as
Feature activation+0.101
liberals
Token liberals
Feature activation+0.107
,
Token,
Feature activation+0.055
2007
Token 2007
Feature activation+0.000
vote
Token vote
Feature activation+1.141
.
Token.
Feature activation+0.987
Ċ
TokenĊ
Feature activation+0.687
Ċ
TokenĊ
Feature activation+0.466
Elect
TokenElect
Feature activation+1.076
oral
Tokenoral
Feature activation+1.203
commission
Token commission
Feature activation+0.974
head
Token head
Feature activation+1.029
Maurice
Token Maurice
Feature activation+0.598
I
Token I
Feature activation+0.536
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
a
Token a
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
election
Token election
Feature activation+1.062
was
Token was
Feature activation+0.676
challenged
Token challenged
Feature activation+0.672
in
Token in
Feature activation+0.558
the
Token the
Feature activation+0.485
courts
Token courts
Feature activation+0.476
the
Token the
Feature activation+0.000
6
Token 6
Feature activation+0.000
,
Token,
Feature activation+0.000
720
Token720
Feature activation+0.000
votes
Token votes
Feature activation+0.700
cast
Token cast
Feature activation+1.053
.
Token.
Feature activation+0.989
His
Token His
Feature activation+0.629
Democratic
Token Democratic
Feature activation+0.638
and
Token and
Feature activation+0.544
Republican
Token Republican
Feature activation+0.394
and
Token and
Feature activation+1.176
her
Token her
Feature activation+0.764
speeches
Token speeches
Feature activation+0.818
draw
Token draw
Feature activation+0.881
large
Token large
Feature activation+0.756
crowds
Token crowds
Feature activation+1.048
,
Token,
Feature activation+0.740
but
Token but
Feature activation+0.534
her
Token her
Feature activation+0.172
disapproval
Token disapproval
Feature activation+0.046
numbers
Token numbers
Feature activation+0.152
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
15
Token 15
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
may
Token may
Feature activation+0.000
vote
Token vote
Feature activation+1.039
for
Token for
Feature activation+0.786
the
Token the
Feature activation+0.834
Liberals
Token Liberals
Feature activation+0.496
.
Token.
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.157

Top DFA by src position
MAX = 1.575

<|endoftext|>
Token<|endoftext|>
Feature activation-0.071
Top resid features:
with
Token with
Feature activation+0.039
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
presidential
Token presidential
Feature activation+0.448
Top resid features:
election
Token election
Feature activation+1.106
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
When
TokenWhen
Feature activation+0.000
Top resid features:
Baldwin
Token Baldwin
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.055
Top resid features:
general
Token general
Feature activation+0.000
Top resid features:
election
Token election
Feature activation+0.554
Top resid features:
once
Token once
Feature activation-0.014
Top resid features:
voters
Token voters
Feature activation+0.976
Top resid features:
saw
Token saw
Feature activation-0.011
Top resid features:
that
Token that
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:
the
Token the
Feature activation+0.000
Top resid features:
Likely
Token Likely
Feature activation+0.068
Top resid features:
Republican
Token Republican
Feature activation+0.090
Top resid features:
Ċ
TokenĊ
Feature activation-0.053
Top resid features:
Ċ
TokenĊ
Feature activation-0.072
Top resid features:
Primary
TokenPrimary
Feature activation+0.290
Top resid features:
Voters
Token Voters
Feature activation+1.057
Top resid features:
Supp
Token Supp
Feature activation+0.000
Top resid features:
orter
Tokenorter
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
36
Token36
Feature activation+0.000
Top resid features:
%)
Token%)
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.106
Top resid features:
flawed
Token flawed
Feature activation+0.048
Top resid features:
2007
Token 2007
Feature activation+0.009
Top resid features:
vote
Token vote
Feature activation+0.590
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.073
Top resid features:
Ċ
TokenĊ
Feature activation-0.108
Top resid features:
Elect
TokenElect
Feature activation+0.498
Top resid features:
oral
Tokenoral
Feature activation+0.481
Top resid features:
voting
Token voting
Feature activation+0.419
Top resid features:
members
Token members
Feature activation-0.010
Top resid features:
and
Token and
Feature activation-0.058
Top resid features:
stand
Token stand
Feature activation+0.006
Top resid features:
for
Token for
Feature activation-0.085
Top resid features:
election
Token election
Feature activation+1.080
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
ruling
Token ruling
Feature activation+0.000
Top resid features:
committees
Token committees
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Likely
Token Likely
Feature activation+0.083
Top resid features:
Republican
Token Republican
Feature activation+0.084
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Primary
TokenPrimary
Feature activation+0.308
Top resid features:
Voters
Token Voters
Feature activation+0.825
Top resid features:
Supp
Token Supp
Feature activation+0.056
Top resid features:
orter
Tokenorter
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
36
Token36
Feature activation+0.000
Top resid features:
%)
Token%)
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.057
Top resid features:
support
Token support
Feature activation+0.088
Top resid features:
among
Token among
Feature activation+0.006
Top resid features:
Republican
Token Republican
Feature activation+0.121
Top resid features:
voters
Token voters
Feature activation+1.208
Top resid features:
and
Token and
Feature activation-0.049
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
speeches
Token speeches
Feature activation+0.000
Top resid features:
draw
Token draw
Feature activation+0.000
Top resid features:
large
Token large
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.084
Top resid features:
initiative
Token initiative
Feature activation+0.073
Top resid features:
to
Token to
Feature activation+0.080
Top resid features:
allow
Token allow
Feature activation-0.046
Top resid features:
Colorado
Token Colorado
Feature activation-0.003
Top resid features:
voters
Token voters
Feature activation+1.286
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
approve
Token approve
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
only
Token only
Feature activation+0.009
Top resid features:
state
Token state
Feature activation-0.135
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
vote
Token vote
Feature activation+1.486
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
rd
Tokenrd
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.085
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
council
Token council
Feature activation+0.028
Top resid features:
before
Token before
Feature activation+0.156
Top resid features:
its
Token its
Feature activation-0.283
Top resid features:
vote
Token vote
Feature activation+1.472
Top resid features:
terminating
Token terminating
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
position
Token position
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.021
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
The
Token The
Feature activation-0.095
Top resid features:
poll
Token poll
Feature activation+0.455
Top resid features:
asked
Token asked
Feature activation+0.269
Top resid features:
respondents
Token respondents
Feature activation+0.610
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
support
Token support
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
who
Token who
Feature activation-0.006
Top resid features:
are
Token are
Feature activation-0.005
Top resid features:
supporting
Token supporting
Feature activation+0.090
Top resid features:
Libertarian
Token Libertarian
Feature activation+0.033
Top resid features:
Party
Token Party
Feature activation+0.259
Top resid features:
candidate
Token candidate
Feature activation+0.556
Top resid features:
Gary
Token Gary
Feature activation+0.000
Top resid features:
Johnson
Token Johnson
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
Jill
Token Jill
Feature activation+0.000
Top resid features:
Stein
Token Stein
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.106
Top resid features:
since
Token since
Feature activation+0.076
Top resid features:
said
Token said
Feature activation-0.013
Top resid features:
he
Token he
Feature activation-0.082
Top resid features:
will
Token will
Feature activation-0.054
Top resid features:
vote
Token vote
Feature activation+1.431
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
favour
Token favour
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bill
Token bill
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.090
Top resid features:
7
Token 7
Feature activation+0.036
Top resid features:
,
Token,
Feature activation-0.031
Top resid features:
04
Token04
Feature activation-0.185
Top resid features:
2
Token2
Feature activation-0.057
Top resid features:
votes
Token votes
Feature activation+1.570
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
respectively
Token respectively
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
voters
Token voters
Feature activation+0.501
Top resid features:
in
Token in
Feature activation+0.066
Top resid features:
this
Token this
Feature activation-0.007
Top resid features:
month
Token month
Feature activation-0.160
Top resid features:
's
Token's
Feature activation-0.067
Top resid features:
election
Token election
Feature activation+0.909
Top resid features:
identified
Token identified
Feature activation+0.000
Top resid features:
themselves
Token themselves
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
liberals
Token liberals
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.129
Top resid features:
flawed
Token flawed
Feature activation+0.063
Top resid features:
2007
Token 2007
Feature activation-0.008
Top resid features:
vote
Token vote
Feature activation+0.774
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.096
Top resid features:
Ċ
TokenĊ
Feature activation-0.150
Top resid features:
Elect
TokenElect
Feature activation+0.761
Top resid features:
oral
Tokenoral
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.068
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
surprise
Token surprise
Feature activation-0.029
Top resid features:
that
Token that
Feature activation-0.059
Top resid features:
the
Token the
Feature activation-0.153
Top resid features:
election
Token election
Feature activation+1.510
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
challenged
Token challenged
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
courts
Token courts
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.046
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
6
Token 6
Feature activation+0.051
Top resid features:
,
Token,
Feature activation-0.030
Top resid features:
720
Token720
Feature activation-0.231
Top resid features:
votes
Token votes
Feature activation+0.775
Top resid features:
cast
Token cast
Feature activation+0.539
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
His
Token His
Feature activation+0.000
Top resid features:
Democratic
Token Democratic
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.011
Top resid features:
support
Token support
Feature activation+0.033
Top resid features:
among
Token among
Feature activation+0.022
Top resid features:
Republican
Token Republican
Feature activation+0.033
Top resid features:
voters
Token voters
Feature activation+0.384
Top resid features:
and
Token and
Feature activation-0.019
Top resid features:
her
Token her
Feature activation+0.021
Top resid features:
speeches
Token speeches
Feature activation+0.231
Top resid features:
draw
Token draw
Feature activation+0.079
Top resid features:
large
Token large
Feature activation+0.110
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.109
Top resid features:
15
Token 15
Feature activation+0.004
Top resid features:
per
Token per
Feature activation-0.065
Top resid features:
cent
Token cent
Feature activation-0.157
Top resid features:
may
Token may
Feature activation-0.067
Top resid features:
vote
Token vote
Feature activation+1.575
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Liberals
Token Liberals
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.05

Head 3: 0.04

Head 4: 0.04

Head 5: 0.05

Head 6: 0.06

Head 7: 0.22

Head 8: 0.06

Head 9: 0.11

Head 10: 0.18

Head 11: 0.09

Positive logits

thumbnails1.04

oston0.98

wcs0.98

Kathleen0.96

ourn0.94

racuse0.93

Rochester0.91

govtrack0.90

voted0.89

Qual0.89

USA0.87

POLITICO0.86

unning0.86

Voting0.86

Ott0.86

arte0.86

resa0.85

convened0.85

partisan0.84

idis0.84

Negative logits

orgasm-1.06

Gothic-0.95

otropic-0.93

climax-0.92

millennium-0.88

Labyrinth-0.87

CHAPTER-0.87

robbers-0.87

Nietzsche-0.86

-0.86

Grimoire-0.85

Gods-0.85

depressive-0.85

metaphysical-0.85

psycho-0.85

commandments-0.84

emate-0.83

prol-0.83

adventurers-0.83

adventurer-0.83

INTERVAL 1.655 - 1.839
CONTAINS 0.000%

INTERVAL 1.471 - 1.655
CONTAINS 0.000%

INTERVAL 1.287 - 1.471
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.405
election
Token election
Feature activation+1.674
.
Token.
Feature activation+1.322
Ċ
TokenĊ
Feature activation+0.794
Ċ
TokenĊ
Feature activation+0.482
When
TokenWhen
Feature activation+0.146
Baldwin
Token Baldwin
Feature activation+0.000
-
Token-
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+1.381
once
Token once
Feature activation+1.235
voters
Token voters
Feature activation+1.839
saw
Token saw
Feature activation+1.309
that
Token that
Feature activation+0.972
he
Token he
Feature activation+0.775
and
Token and
Feature activation+0.664
the
Token the
Feature activation+0.537
party
Token party
Feature activation+0.794

INTERVAL 1.103 - 1.287
CONTAINS 0.003%

Republican
Token Republican
Feature activation+0.201
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Primary
TokenPrimary
Feature activation+0.169
Voters
Token Voters
Feature activation+1.216
Supp
Token Supp
Feature activation+1.184
orter
Tokenorter
Feature activation+1.019
(
Token (
Feature activation+0.696
36
Token36
Feature activation+0.550
%)
Token%)
Feature activation+0.462
Not
Token Not
Feature activation+0.390
voting
Token voting
Feature activation+1.184
members
Token members
Feature activation+1.133
and
Token and
Feature activation+0.869
stand
Token stand
Feature activation+0.720
for
Token for
Feature activation+0.157
election
Token election
Feature activation+1.199
to
Token to
Feature activation+0.849
their
Token their
Feature activation+0.729
ruling
Token ruling
Feature activation+0.457
committees
Token committees
Feature activation+0.397
.
Token.
Feature activation+0.520
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
support
Token support
Feature activation+0.000
among
Token among
Feature activation+0.000
Republican
Token Republican
Feature activation+0.028
voters
Token voters
Feature activation+1.153
and
Token and
Feature activation+1.176
her
Token her
Feature activation+0.764
speeches
Token speeches
Feature activation+0.818
draw
Token draw
Feature activation+0.881
large
Token large
Feature activation+0.756
crowds
Token crowds
Feature activation+1.048
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
council
Token council
Feature activation+0.000
before
Token before
Feature activation+0.000
its
Token its
Feature activation+0.000
vote
Token vote
Feature activation+1.146
terminating
Token terminating
Feature activation+0.924
his
Token his
Feature activation+0.622
position
Token position
Feature activation+0.366
this
Token this
Feature activation+0.275
month
Token month
Feature activation+0.256
Likely
Token Likely
Feature activation+0.000
Republican
Token Republican
Feature activation+0.201
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Primary
TokenPrimary
Feature activation+0.169
Voters
Token Voters
Feature activation+1.216
Supp
Token Supp
Feature activation+1.184
orter
Tokenorter
Feature activation+1.019
(
Token (
Feature activation+0.696
36
Token36
Feature activation+0.550
%)
Token%)
Feature activation+0.462

INTERVAL 0.919 - 1.103
CONTAINS 0.005%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
15
Token 15
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
may
Token may
Feature activation+0.000
vote
Token vote
Feature activation+1.039
for
Token for
Feature activation+0.786
the
Token the
Feature activation+0.834
Liberals
Token Liberals
Feature activation+0.496
.
Token.
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.157
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
again
Token again
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
vote
Token vote
Feature activation+1.324
was
Token was
Feature activation+0.942
passed
Token passed
Feature activation+0.537
despite
Token despite
Feature activation+0.414
a
Token a
Feature activation+0.404
delay
Token delay
Feature activation+0.259
.
Token.
Feature activation+0.127
CNN
Token CNN
Feature activation+0.000
/
Token/
Feature activation+0.000
OR
TokenOR
Feature activation+0.000
C
TokenC
Feature activation+0.000
poll
Token poll
Feature activation+0.740
surveyed
Token surveyed
Feature activation+1.004
1
Token 1
Feature activation+1.008
,
Token,
Feature activation+0.537
010
Token010
Feature activation+0.189
Americans
Token Americans
Feature activation+0.317
and
Token and
Feature activation+0.278
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
independence
Token independence
Feature activation+0.000
referendum
Token referendum
Feature activation+1.222
and
Token and
Feature activation+1.083
enter
Token enter
Feature activation+0.929
talks
Token talks
Feature activation+0.596
with
Token with
Feature activation+0.222
Baghdad
Token Baghdad
Feature activation+0.141
aimed
Token aimed
Feature activation+0.049
at
Token at
Feature activation+0.162
the
Token the
Feature activation+0.000
council
Token council
Feature activation+0.000
before
Token before
Feature activation+0.000
its
Token its
Feature activation+0.000
vote
Token vote
Feature activation+1.146
terminating
Token terminating
Feature activation+0.924
his
Token his
Feature activation+0.622
position
Token position
Feature activation+0.366
this
Token this
Feature activation+0.275
month
Token month
Feature activation+0.256
.
Token.
Feature activation+0.147

INTERVAL 0.736 - 0.919
CONTAINS 0.009%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
referendum
Token referendum
Feature activation+1.039
result
Token result
Feature activation+1.298
on
Token on
Feature activation+0.843
23
Token 23
Feature activation+0.781
June
Token June
Feature activation+0.724
.
Token.
Feature activation+0.697
Ċ
TokenĊ
Feature activation+0.439
Ċ
TokenĊ
Feature activation+0.246
following
Token following
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
election
Token election
Feature activation+0.759
certification
Token certification
Feature activation+0.562
.
Token.
Feature activation+0.492
âĢ
Token âĢ
Feature activation+0.434
ľ
Tokenľ
Feature activation+0.153
We
TokenWe
Feature activation+0.168
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+1.479
for
Token for
Feature activation+0.849
some
Token some
Feature activation+1.036
personal
Token personal
Feature activation+0.832
favorite
Token favorite
Feature activation+0.804
knowing
Token knowing
Feature activation+0.642
full
Token full
Feature activation+0.391
well
Token well
Feature activation+0.193
that
Token that
Feature activation+0.000
15
Token 15
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
may
Token may
Feature activation+0.000
vote
Token vote
Feature activation+1.039
for
Token for
Feature activation+0.786
the
Token the
Feature activation+0.834
Liberals
Token Liberals
Feature activation+0.496
.
Token.
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.157
Ċ
TokenĊ
Feature activation+0.008
.
Token.
Feature activation+0.989
His
Token His
Feature activation+0.629
Democratic
Token Democratic
Feature activation+0.638
and
Token and
Feature activation+0.544
Republican
Token Republican
Feature activation+0.394
challengers
Token challengers
Feature activation+0.764
received
Token received
Feature activation+0.636
33
Token 33
Feature activation+0.393
and
Token and
Feature activation+0.191
24
Token 24
Feature activation+0.006
percent
Token percent
Feature activation+0.044

INTERVAL 0.552 - 0.736
CONTAINS 0.016%

Naval
Token Naval
Feature activation+0.000
ny
Tokenny
Feature activation+0.000
polling
Token polling
Feature activation+0.697
in
Token in
Feature activation+0.764
the
Token the
Feature activation+0.667
single
Token single
Feature activation+0.558
digits
Token digits
Feature activation+0.350
when
Token when
Feature activation+0.260
the
Token the
Feature activation+0.000
campaign
Token campaign
Feature activation+0.595
began
Token began
Feature activation+0.404
endorsement
Token endorsement
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.225
Ŀ
TokenĿ
Feature activation+0.028
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
campaign
Token campaign
Feature activation+0.562
.
Token.
Feature activation+0.439
Ċ
TokenĊ
Feature activation+0.149
Ċ
TokenĊ
Feature activation+0.000
Care
TokenCare
Feature activation+0.000
y
Tokeny
Feature activation+0.000
board
Token board
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
voted
Token voted
Feature activation+0.903
to
Token to
Feature activation+0.671
weaken
Token weaken
Feature activation+0.623
some
Token some
Feature activation+0.646
environmental
Token environmental
Feature activation+0.361
regulations
Token regulations
Feature activation+0.069
âĢĶ
Token âĢĶ
Feature activation+0.000
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
an
Token an
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
campaign
Token campaign
Feature activation+0.413
contribution
Token contribution
Feature activation+0.635
scandal
Token scandal
Feature activation+0.692
.
Token.
Feature activation+0.345
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Northwest
Token Northwest
Feature activation+0.000
victory
Token victory
Feature activation+0.113
party
Token party
Feature activation+0.658
.
Token.
Feature activation+0.437
"
Token "
Feature activation+0.234
V
TokenV
Feature activation+0.260
oters
Tokenoters
Feature activation+0.727
will
Token will
Feature activation+0.729
only
Token only
Feature activation+0.604
be
Token be
Feature activation+0.404
pushed
Token pushed
Feature activation+0.449
so
Token so
Feature activation+0.296

INTERVAL 0.368 - 0.552
CONTAINS 0.026%

will
Token will
Feature activation+0.000
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
an
Token an
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
campaign
Token campaign
Feature activation+0.413
contribution
Token contribution
Feature activation+0.635
scandal
Token scandal
Feature activation+0.692
.
Token.
Feature activation+0.345
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
25
Token 25
Feature activation+0.000
39
Token39
Feature activation+0.000
votes
Token votes
Feature activation+0.480
.
Token.
Feature activation+0.506
Please
Token Please
Feature activation+0.501
wait
Token wait
Feature activation+0.379
...
Token...
Feature activation+0.000
Discuss
Token Discuss
Feature activation+0.056
Card
Token Card
Feature activation+0.089
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.000
won
Token won
Feature activation+0.000
an
Token an
Feature activation+0.000
election
Token election
Feature activation+0.506
.
Token.
Feature activation+0.548
But
Token But
Feature activation+0.302
over
Token over
Feature activation+0.242
a
Token a
Feature activation+0.274
fren
Token fren
Feature activation+0.171
z
Tokenz
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
their
Token their
Feature activation+0.000
voter
Token voter
Feature activation+0.642
-
Token-
Feature activation+0.496
in
Tokenin
Feature activation+0.528
iti
Tokeniti
Feature activation+0.697
ated
Tokenated
Feature activation+0.503
deadline
Token deadline
Feature activation+0.416
has
Token has
Feature activation+0.181
Democratic
Token Democratic
Feature activation+0.638
and
Token and
Feature activation+0.544
Republican
Token Republican
Feature activation+0.394
challengers
Token challengers
Feature activation+0.764
received
Token received
Feature activation+0.636
33
Token 33
Feature activation+0.393
and
Token and
Feature activation+0.191
24
Token 24
Feature activation+0.006
percent
Token percent
Feature activation+0.044
,
Token,
Feature activation+0.000
respectively
Token respectively
Feature activation+0.009

INTERVAL 0.184 - 0.368
CONTAINS 0.051%

which
Token which
Feature activation+0.000
approved
Token approved
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
sweeping
Token sweeping
Feature activation+0.000
voter
Token voter
Feature activation+0.297
-
Token-
Feature activation+0.092
supp
Tokensupp
Feature activation+0.000
ression
Tokenression
Feature activation+0.000
law
Token law
Feature activation+0.000
in
Token in
Feature activation+0.068
the
Token the
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
Lok
Token Lok
Feature activation+0.000
Sabha
Token Sabha
Feature activation+0.000
elections
Token elections
Feature activation+0.452
from
Token from
Feature activation+0.242
Aur
Token Aur
Feature activation+0.184
ang
Tokenang
Feature activation+0.025
abad
Tokenabad
Feature activation+0.058
to
Token to
Feature activation+0.000
S
Token S
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Cor
TokenCor
Feature activation+0.000
byn
Tokenbyn
Feature activation+0.000
/
Token/
Feature activation+0.083
pro
Tokenpro
Feature activation+0.213
-
Token-
Feature activation+0.000
Lib
TokenLib
Feature activation+0.000
Dem
TokenDem
Feature activation+0.216
journalists
Token journalists
Feature activation+0.165
and
Token and
Feature activation+0.048
vote
Token vote
Feature activation+0.817
."
Token."
Feature activation+0.308
Ċ
TokenĊ
Feature activation+0.354
Ċ
TokenĊ
Feature activation+0.181
P
TokenP
Feature activation+0.074
ossible
Tokenossible
Feature activation+0.218
EU
Token EU
Feature activation+0.175
membership
Token membership
Feature activation+0.366
timeline
Token timeline
Feature activation+0.112
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
protect
Token protect
Feature activation+0.000
voters
Token voters
Feature activation+1.158
'
Token'
Feature activation+0.883
personal
Token personal
Feature activation+1.012
information
Token information
Feature activation+0.361
was
Token was
Feature activation+0.196
one
Token one
Feature activation+0.056
of
Token of
Feature activation+0.000
several
Token several
Feature activation+0.000
highly
Token highly
Feature activation+0.000
critical
Token critical
Feature activation+0.000

INTERVAL 0.000 - 0.184
CONTAINS 99.890%

13
Token 13
Feature activation+0.000
for
Token for
Feature activation+0.000
West
Token West
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
set
Token set
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+0.000
benchmark
Token benchmark
Feature activation+0.000
in
Token in
Feature activation+0.000
quality
Token quality
Feature activation+0.000
of
Token of
Feature activation+0.000
life
Token life
Feature activation+0.000
we
Token we
Feature activation+0.000
offer
Token offer
Feature activation+0.000
in
Token in
Feature activation+0.000
Blacks
Token Blacks
Feature activation+0.000
burg
Tokenburg
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
wings
Token wings
Feature activation+0.000
fl
Token fl
Feature activation+0.000
apping
Tokenapping
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
makes
Token makes
Feature activation+0.000
a
Token a
Feature activation+0.000
swift
Token swift
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+0.000
of
Token of
Feature activation+0.000
Independence
Token Independence
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
March
Token March
Feature activation+0.000
16
Token 16
Feature activation+0.000
Science
Token Science
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
heritage
Token heritage
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H2.7: (feature 15075)

TOP ACTIVATIONS
MAX = 1.352

but
Token but
Feature activation+0.000
moving
Token moving
Feature activation+0.000
from
Token from
Feature activation+0.000
Sheffield
Token Sheffield
Feature activation+0.626
,
Token,
Feature activation+0.515
England
Token England
Feature activation+1.170
to
Token to
Feature activation+0.783
L
Token L
Feature activation+0.866
.
Token.
Feature activation+0.559
A
TokenA
Feature activation+0.366
.
Token.
Feature activation+0.361
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
John
Token John
Feature activation+0.000
Lennon
Token Lennon
Feature activation+0.000
and
Token and
Feature activation+0.000
Newcastle
Token Newcastle
Feature activation+1.013
âĢĵ
Token âĢĵ
Feature activation+1.153
to
Token to
Feature activation+0.829
introduce
Token introduce
Feature activation+0.780
this
Token this
Feature activation+0.745
âĢ
Token âĢ
Feature activation+0.567
ľ
Tokenľ
Feature activation+0.200
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
believers
Token believers
Feature activation+0.000
.
Token.
Feature activation+0.000
Many
Token Many
Feature activation+0.000
Canadians
Token Canadians
Feature activation+0.820
would
Token would
Feature activation+0.992
suggest
Token suggest
Feature activation+0.632
this
Token this
Feature activation+0.532
is
Token is
Feature activation+0.107
by
Token by
Feature activation+0.000
design
Token design
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
way
Token way
Feature activation+0.000
stops
Token stops
Feature activation+0.000
UK
Token UK
Feature activation+1.116
trade
Token trade
Feature activation+0.942
with
Token with
Feature activation+0.992
the
Token the
Feature activation+0.647
EU
Token EU
Feature activation+0.739
,
Token,
Feature activation+0.650
as
Token as
Feature activation+0.589
some
Token some
Feature activation+0.397
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.480
,
Token,
Feature activation+0.369
Australian
Token Australian
Feature activation+0.868
and
Token and
Feature activation+0.725
British
Token British
Feature activation+0.974
trustees
Token trustees
Feature activation+0.673
hip
Tokenhip
Feature activation+0.584
was
Token was
Feature activation+0.421
set
Token set
Feature activation+0.321
up
Token up
Feature activation+0.062
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Destination
Token Destination
Feature activation+0.000
NSW
Token NSW
Feature activation+0.973
throw
Token throw
Feature activation+0.610
any
Token any
Feature activation+0.580
money
Token money
Feature activation+0.259
at
Token at
Feature activation+0.136
the
Token the
Feature activation+0.009
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
event
Token event
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+1.039
now
Token now
Feature activation+0.939
,
Token,
Feature activation+0.874
but
Token but
Feature activation+0.698
the
Token the
Feature activation+0.563
marriage
Token marriage
Feature activation+0.508
in
Token in
Feature activation+0.426
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
ipped
Tokenipped
Feature activation+0.000
back
Token back
Feature activation+0.000
home
Token home
Feature activation+0.000
to
Token to
Feature activation+0.000
Australia
Token Australia
Feature activation+0.919
"
Token"
Feature activation+0.581
to
Token to
Feature activation+0.437
renew
Token renew
Feature activation+0.319
/
Token /
Feature activation+0.466
protect
Token protect
Feature activation+0.214
of
Token of
Feature activation+0.222
house
Token house
Feature activation+0.214
premises
Token premises
Feature activation+0.392
in
Token in
Feature activation+0.319
Scotland
Token Scotland
Feature activation+0.847
.
Token.
Feature activation+0.918
Ċ
TokenĊ
Feature activation+0.588
Ċ
TokenĊ
Feature activation+0.396
It
TokenIt
Feature activation+0.218
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
with
Token with
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.584
-
Token-
Feature activation+0.743
born
Tokenborn
Feature activation+0.691
English
Token English
Feature activation+0.888
cr
Token cr
Feature activation+0.703
ick
Tokenick
Feature activation+0.350
eter
Tokeneter
Feature activation+0.309
Ben
Token Ben
Feature activation+0.277
St
Token St
Feature activation+0.032
plates
Token plates
Feature activation+0.000
through
Token through
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.552
and
Token and
Feature activation+0.628
realised
Token realised
Feature activation+0.886
they
Token they
Feature activation+0.882
were
Token were
Feature activation+0.578
so
Token so
Feature activation+0.399
much
Token much
Feature activation+0.306
bigger
Token bigger
Feature activation+0.144
through
Token through
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.552
and
Token and
Feature activation+0.628
realised
Token realised
Feature activation+0.886
they
Token they
Feature activation+0.882
were
Token were
Feature activation+0.578
so
Token so
Feature activation+0.399
much
Token much
Feature activation+0.306
bigger
Token bigger
Feature activation+0.144
than
Token than
Feature activation+0.063
event
Token event
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+1.039
now
Token now
Feature activation+0.939
,
Token,
Feature activation+0.874
but
Token but
Feature activation+0.698
the
Token the
Feature activation+0.563
marriage
Token marriage
Feature activation+0.508
in
Token in
Feature activation+0.426
1933
Token 1933
Feature activation+0.240
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
be
Token be
Feature activation+0.000
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.729
City
Token City
Feature activation+0.872
.
Token.
Feature activation+0.858
Ċ
TokenĊ
Feature activation+0.498
Ċ
TokenĊ
Feature activation+0.327
The
TokenThe
Feature activation+0.185
East
Token East
Feature activation+0.045
a
Token a
Feature activation+0.000
joint
Token joint
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.480
,
Token,
Feature activation+0.369
Australian
Token Australian
Feature activation+0.868
and
Token and
Feature activation+0.725
British
Token British
Feature activation+0.974
trustees
Token trustees
Feature activation+0.673
hip
Tokenhip
Feature activation+0.584
was
Token was
Feature activation+0.421
from
Token from
Feature activation+0.000
Sheffield
Token Sheffield
Feature activation+0.626
,
Token,
Feature activation+0.515
England
Token England
Feature activation+1.170
to
Token to
Feature activation+0.783
L
Token L
Feature activation+0.866
.
Token.
Feature activation+0.559
A
TokenA
Feature activation+0.366
.
Token.
Feature activation+0.361
are
Token are
Feature activation+0.196
two
Token two
Feature activation+0.024
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
affairs
Token affairs
Feature activation+0.000
could
Token could
Feature activation+0.000
occur
Token occur
Feature activation+0.000
in
Token in
Feature activation+0.000
England
Token England
Feature activation+0.861
a
Token a
Feature activation+0.703
system
Token system
Feature activation+0.484
of
Token of
Feature activation+0.274
purchasing
Token purchasing
Feature activation+0.207
rank
Token rank
Feature activation+0.010
be
Token be
Feature activation+0.000
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.729
City
Token City
Feature activation+0.872
.
Token.
Feature activation+0.858
Ċ
TokenĊ
Feature activation+0.498
Ċ
TokenĊ
Feature activation+0.327
The
TokenThe
Feature activation+0.185
East
Token East
Feature activation+0.045
lands
Tokenlands
Feature activation+0.049
aret
Tokenaret
Feature activation+0.000
Thatcher
Token Thatcher
Feature activation+0.730
and
Token and
Feature activation+0.600
her
Token her
Feature activation+0.221
chancellor
Token chancellor
Feature activation+0.603
Sir
Token Sir
Feature activation+0.856
Geoffrey
Token Geoffrey
Feature activation+0.596
Howe
Token Howe
Feature activation+0.452
were
Token were
Feature activation+0.531
behind
Token behind
Feature activation+0.309
a
Token a
Feature activation+0.372
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
why
Token why
Feature activation+0.000
Labour
Token Labour
Feature activation+0.852
has
Token has
Feature activation+0.450
committed
Token committed
Feature activation+0.520
to
Token to
Feature activation+0.162
building
Token building
Feature activation+0.215
200
Token 200
Feature activation+0.060

Top DFA by src position
MAX = 1.543

but
Token but
Feature activation+0.015
Top resid features:
moving
Token moving
Feature activation+0.021
Top resid features:
from
Token from
Feature activation-0.066
Top resid features:
Sheffield
Token Sheffield
Feature activation+0.558
Top resid features:
,
Token,
Feature activation-0.037
Top resid features:
England
Token England
Feature activation+0.935
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
L
Token L
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
TokenA
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.070
Top resid features:
John
Token John
Feature activation-0.065
Top resid features:
Lennon
Token Lennon
Feature activation+0.167
Top resid features:
and
Token and
Feature activation-0.060
Top resid features:
Newcastle
Token Newcastle
Feature activation+0.900
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.523
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
introduce
Token introduce
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.062
Top resid features:
believers
Token believers
Feature activation+0.069
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Many
Token Many
Feature activation-0.070
Top resid features:
Canadians
Token Canadians
Feature activation+1.209
Top resid features:
would
Token would
Feature activation+0.074
Top resid features:
suggest
Token suggest
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.024
Top resid features:
way
Token way
Feature activation-0.005
Top resid features:
stops
Token stops
Feature activation+0.012
Top resid features:
UK
Token UK
Feature activation+0.863
Top resid features:
trade
Token trade
Feature activation+0.281
Top resid features:
with
Token with
Feature activation+0.108
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
EU
Token EU
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
In
Token In
Feature activation-0.026
Top resid features:
1945
Token 1945
Feature activation+0.058
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
joint
Token joint
Feature activation+0.045
Top resid features:
New
Token New
Feature activation+0.018
Top resid features:
Zealand
Token Zealand
Feature activation+0.482
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Australian
Token Australian
Feature activation+0.394
Top resid features:
and
Token and
Feature activation-0.075
Top resid features:
British
Token British
Feature activation+0.301
Top resid features:
trustees
Token trustees
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.057
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.050
Top resid features:
t
Tokent
Feature activation+0.007
Top resid features:
Destination
Token Destination
Feature activation-0.229
Top resid features:
NSW
Token NSW
Feature activation+1.543
Top resid features:
throw
Token throw
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
money
Token money
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:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.054
Top resid features:
event
Token event
Feature activation+0.057
Top resid features:
in
Token in
Feature activation-0.064
Top resid features:
the
Token the
Feature activation-0.172
Top resid features:
UK
Token UK
Feature activation+1.154
Top resid features:
now
Token now
Feature activation+0.261
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
marriage
Token marriage
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.061
Top resid features:
ipped
Tokenipped
Feature activation-0.012
Top resid features:
back
Token back
Feature activation+0.072
Top resid features:
home
Token home
Feature activation+0.087
Top resid features:
to
Token to
Feature activation-0.210
Top resid features:
Australia
Token Australia
Feature activation+1.286
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
renew
Token renew
Feature activation+0.000
Top resid features:
/
Token /
Feature activation+0.000
Top resid features:
protect
Token protect
Feature activation+0.000
Top resid features:
back
Token back
Feature activation+0.062
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
house
Token house
Feature activation+0.063
Top resid features:
premises
Token premises
Feature activation+0.244
Top resid features:
in
Token in
Feature activation-0.068
Top resid features:
Scotland
Token Scotland
Feature activation+0.683
Top resid features:
.
Token.
Feature activation-0.080
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
air
Tokenair
Feature activation+0.010
Top resid features:
phone
Token phone
Feature activation+0.026
Top resid features:
conversation
Token conversation
Feature activation+0.036
Top resid features:
with
Token with
Feature activation-0.004
Top resid features:
New
Token New
Feature activation+0.039
Top resid features:
Zealand
Token Zealand
Feature activation+0.633
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
born
Tokenborn
Feature activation+0.059
Top resid features:
English
Token English
Feature activation+0.351
Top resid features:
cr
Token cr
Feature activation+0.000
Top resid features:
ick
Tokenick
Feature activation+0.000
Top resid features:
ect
Tokenect
Feature activation-0.014
Top resid features:
onic
Tokenonic
Feature activation+0.022
Top resid features:
plates
Token plates
Feature activation+0.010
Top resid features:
through
Token through
Feature activation-0.072
Top resid features:
New
Token New
Feature activation+0.089
Top resid features:
Zealand
Token Zealand
Feature activation+0.621
Top resid features:
and
Token and
Feature activation-0.058
Top resid features:
realised
Token realised
Feature activation+0.610
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
plates
Token plates
Feature activation+0.017
Top resid features:
through
Token through
Feature activation-0.026
Top resid features:
New
Token New
Feature activation+0.086
Top resid features:
Zealand
Token Zealand
Feature activation+0.479
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
realised
Token realised
Feature activation+0.524
Top resid features:
they
Token they
Feature activation+0.109
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
bigger
Token bigger
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.036
Top resid features:
event
Token event
Feature activation+0.055
Top resid features:
in
Token in
Feature activation-0.023
Top resid features:
the
Token the
Feature activation-0.062
Top resid features:
UK
Token UK
Feature activation+0.841
Top resid features:
now
Token now
Feature activation+0.204
Top resid features:
,
Token,
Feature activation+0.137
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
marriage
Token marriage
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.062
Top resid features:
be
Token be
Feature activation-0.061
Top resid features:
offered
Token offered
Feature activation+0.044
Top resid features:
to
Token to
Feature activation-0.076
Top resid features:
Manchester
Token Manchester
Feature activation+0.603
Top resid features:
City
Token City
Feature activation+0.666
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:
The
TokenThe
Feature activation+0.000
Top resid features:
East
Token East
Feature activation+0.000
Top resid features:
In
Token In
Feature activation-0.036
Top resid features:
1945
Token 1945
Feature activation+0.039
Top resid features:
a
Token a
Feature activation-0.021
Top resid features:
joint
Token joint
Feature activation+0.022
Top resid features:
New
Token New
Feature activation+0.020
Top resid features:
Zealand
Token Zealand
Feature activation+0.611
Top resid features:
,
Token,
Feature activation-0.108
Top resid features:
Australian
Token Australian
Feature activation+0.543
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
British
Token British
Feature activation+0.000
Top resid features:
trustees
Token trustees
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.015
Top resid features:
moving
Token moving
Feature activation+0.021
Top resid features:
from
Token from
Feature activation+0.030
Top resid features:
Sheffield
Token Sheffield
Feature activation+0.525
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
England
Token England
Feature activation+0.726
Top resid features:
to
Token to
Feature activation-0.196
Top resid features:
L
Token L
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
TokenA
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.072
Top resid features:
affairs
Token affairs
Feature activation+0.058
Top resid features:
could
Token could
Feature activation+0.018
Top resid features:
occur
Token occur
Feature activation-0.098
Top resid features:
in
Token in
Feature activation-0.185
Top resid features:
England
Token England
Feature activation+1.383
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
purchasing
Token purchasing
Feature activation+0.000
Top resid features:
rank
Token rank
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.058
Top resid features:
be
Token be
Feature activation-0.061
Top resid features:
offered
Token offered
Feature activation+0.030
Top resid features:
to
Token to
Feature activation-0.030
Top resid features:
Manchester
Token Manchester
Feature activation+0.717
Top resid features:
City
Token City
Feature activation+0.405
Top resid features:
.
Token.
Feature activation+0.098
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.076
Top resid features:
aret
Tokenaret
Feature activation+0.051
Top resid features:
Thatcher
Token Thatcher
Feature activation+0.418
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
her
Token her
Feature activation-0.013
Top resid features:
chancellor
Token chancellor
Feature activation+0.413
Top resid features:
Sir
Token Sir
Feature activation+0.280
Top resid features:
Geoffrey
Token Geoffrey
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.076
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
That
Token That
Feature activation+0.011
Top resid features:
's
Token's
Feature activation-0.078
Top resid features:
why
Token why
Feature activation-0.027
Top resid features:
Labour
Token Labour
Feature activation+1.272
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
committed
Token committed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
building
Token building
Feature activation+0.000
Top resid features:
200
Token 200
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.08

Head 2: 0.05

Head 3: 0.04

Head 4: 0.03

Head 5: 0.05

Head 6: 0.06

Head 7: 0.21

Head 8: 0.04

Head 9: 0.09

Head 10: 0.18

Head 11: 0.09

Positive logits

Maritime0.94

Islands0.93

England0.89

cair0.84

shores0.82

Scotland0.82

urs0.81

Centre0.80

abouts0.80

coast0.80

htaking0.80

coasts0.80

ember0.79

Confederation0.78

maxwell0.77

centre0.77

legraph0.76

abled0.76

Philippe0.76

raltar0.76

Negative logits

orph-0.79

Adin-0.78

Uz-0.76

assignments-0.75

ensional-0.74

Kenobi-0.74

Stard-0.74

organizational-0.73

izations-0.72

Anonymous-0.70

RUN-0.70

LLOW-0.70

agram-0.69

mood-0.69

TIME-0.69

wordpress-0.69

izable-0.69

sense-0.68

analytical-0.68

Proced-0.68

INTERVAL 1.217 - 1.352
CONTAINS 0.000%

INTERVAL 1.082 - 1.217
CONTAINS 0.001%

but
Token but
Feature activation+0.000
moving
Token moving
Feature activation+0.000
from
Token from
Feature activation+0.000
Sheffield
Token Sheffield
Feature activation+0.626
,
Token,
Feature activation+0.515
England
Token England
Feature activation+1.170
to
Token to
Feature activation+0.783
L
Token L
Feature activation+0.866
.
Token.
Feature activation+0.559
A
TokenA
Feature activation+0.366
.
Token.
Feature activation+0.361
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
John
Token John
Feature activation+0.000
Lennon
Token Lennon
Feature activation+0.000
and
Token and
Feature activation+0.000
Newcastle
Token Newcastle
Feature activation+1.013
âĢĵ
Token âĢĵ
Feature activation+1.153
to
Token to
Feature activation+0.829
introduce
Token introduce
Feature activation+0.780
this
Token this
Feature activation+0.745
âĢ
Token âĢ
Feature activation+0.567
ľ
Tokenľ
Feature activation+0.200

INTERVAL 0.946 - 1.082
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
way
Token way
Feature activation+0.000
stops
Token stops
Feature activation+0.000
UK
Token UK
Feature activation+1.116
trade
Token trade
Feature activation+0.942
with
Token with
Feature activation+0.992
the
Token the
Feature activation+0.647
EU
Token EU
Feature activation+0.739
,
Token,
Feature activation+0.650
as
Token as
Feature activation+0.589
some
Token some
Feature activation+0.397
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
believers
Token believers
Feature activation+0.000
.
Token.
Feature activation+0.000
Many
Token Many
Feature activation+0.000
Canadians
Token Canadians
Feature activation+0.820
would
Token would
Feature activation+0.992
suggest
Token suggest
Feature activation+0.632
this
Token this
Feature activation+0.532
is
Token is
Feature activation+0.107
by
Token by
Feature activation+0.000
design
Token design
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Destination
Token Destination
Feature activation+0.000
NSW
Token NSW
Feature activation+0.973
throw
Token throw
Feature activation+0.610
any
Token any
Feature activation+0.580
money
Token money
Feature activation+0.259
at
Token at
Feature activation+0.136
the
Token the
Feature activation+0.009
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.480
,
Token,
Feature activation+0.369
Australian
Token Australian
Feature activation+0.868
and
Token and
Feature activation+0.725
British
Token British
Feature activation+0.974
trustees
Token trustees
Feature activation+0.673
hip
Tokenhip
Feature activation+0.584
was
Token was
Feature activation+0.421
set
Token set
Feature activation+0.321
up
Token up
Feature activation+0.062

INTERVAL 0.811 - 0.946
CONTAINS 0.004%

of
Token of
Feature activation+0.222
house
Token house
Feature activation+0.214
premises
Token premises
Feature activation+0.392
in
Token in
Feature activation+0.319
Scotland
Token Scotland
Feature activation+0.847
.
Token.
Feature activation+0.918
Ċ
TokenĊ
Feature activation+0.588
Ċ
TokenĊ
Feature activation+0.396
It
TokenIt
Feature activation+0.218
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
plates
Token plates
Feature activation+0.000
through
Token through
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.552
and
Token and
Feature activation+0.628
realised
Token realised
Feature activation+0.886
they
Token they
Feature activation+0.882
were
Token were
Feature activation+0.578
so
Token so
Feature activation+0.399
much
Token much
Feature activation+0.306
bigger
Token bigger
Feature activation+0.144
John
Token John
Feature activation+0.000
Lennon
Token Lennon
Feature activation+0.000
and
Token and
Feature activation+0.000
Newcastle
Token Newcastle
Feature activation+1.013
âĢĵ
Token âĢĵ
Feature activation+1.153
to
Token to
Feature activation+0.829
introduce
Token introduce
Feature activation+0.780
this
Token this
Feature activation+0.745
âĢ
Token âĢ
Feature activation+0.567
ľ
Tokenľ
Feature activation+0.200
basic
Tokenbasic
Feature activation+0.316
back
Token back
Feature activation+0.151
of
Token of
Feature activation+0.222
house
Token house
Feature activation+0.214
premises
Token premises
Feature activation+0.392
in
Token in
Feature activation+0.319
Scotland
Token Scotland
Feature activation+0.847
.
Token.
Feature activation+0.918
Ċ
TokenĊ
Feature activation+0.588
Ċ
TokenĊ
Feature activation+0.396
It
TokenIt
Feature activation+0.218
said
Token said
Feature activation+0.000
Broadcasting
Token Broadcasting
Feature activation+0.442
Corporation
Token Corporation
Feature activation+0.569
last
Token last
Feature activation+0.466
week
Token week
Feature activation+0.488
showed
Token showed
Feature activation+0.355
Australians
Token Australians
Feature activation+0.843
overwhelmingly
Token overwhelmingly
Feature activation+0.697
believe
Token believe
Feature activation+0.490
focusing
Token focusing
Feature activation+0.317
on
Token on
Feature activation+0.112
the
Token the
Feature activation+0.058

INTERVAL 0.676 - 0.811
CONTAINS 0.007%

not
Token not
Feature activation+0.000
zero
Token zero
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Canada
TokenCanada
Feature activation+0.760
's
Token's
Feature activation+0.278
public
Token public
Feature activation+0.229
health
Token health
Feature activation+0.220
agency
Token agency
Feature activation+0.047
has
Token has
Feature activation+0.000
Corporation
Token Corporation
Feature activation+0.569
last
Token last
Feature activation+0.466
week
Token week
Feature activation+0.488
showed
Token showed
Feature activation+0.355
Australians
Token Australians
Feature activation+0.843
overwhelmingly
Token overwhelmingly
Feature activation+0.697
believe
Token believe
Feature activation+0.490
focusing
Token focusing
Feature activation+0.317
on
Token on
Feature activation+0.112
the
Token the
Feature activation+0.058
National
Token National
Feature activation+0.034
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+1.133
's
Token's
Feature activation+0.519
Overse
Token Overse
Feature activation+0.824
as
Tokenas
Feature activation+0.496
Territories
Token Territories
Feature activation+0.717
'
Token'
Feature activation+0.691
hidden
Token hidden
Feature activation+0.454
role
Token role
Feature activation+0.307
in
Token in
Feature activation+0.067
developing
Token developing
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
added
Token added
Feature activation+0.000
that
Token that
Feature activation+0.000
Canada
Token Canada
Feature activation+0.734
will
Token will
Feature activation+0.553
insist
Token insist
Feature activation+0.428
that
Token that
Feature activation+0.213
the
Token the
Feature activation+0.137
situation
Token situation
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
at
Token at
Feature activation+0.000
London
Token London
Feature activation+0.746
Gat
Token Gat
Feature activation+0.663
wick
Tokenwick
Feature activation+0.941
.
Token.
Feature activation+0.781
Ċ
TokenĊ
Feature activation+0.684
Ċ
TokenĊ
Feature activation+0.500
B
TokenB
Feature activation+0.416
oe
Tokenoe
Feature activation+0.000
ing
Tokening
Feature activation+0.000

INTERVAL 0.541 - 0.676
CONTAINS 0.012%

stories
Token stories
Feature activation+0.191
from
Token from
Feature activation+0.102
21
Token 21
Feature activation+0.002
places
Token places
Feature activation+0.000
around
Token around
Feature activation+0.000
Australia
Token Australia
Feature activation+0.629
âĢ
TokenâĢ
Feature activation+0.412
Ļ
TokenĻ
Feature activation+0.319
s
Tokens
Feature activation+0.156
coastline
Token coastline
Feature activation+0.129
,
Token,
Feature activation+0.019
Dir
Token Dir
Feature activation+0.000
.
Token.
Feature activation+0.000
David
Token David
Feature activation+0.000
Lean
Token Lean
Feature activation+0.000
-
Token -
Feature activation+0.000
UK
Token UK
Feature activation+0.662
(
Token (
Feature activation+0.536
19
Token19
Feature activation+0.475
62
Token62
Feature activation+0.425
)
Token)
Feature activation+0.354
Ċ
TokenĊ
Feature activation+0.198
The
TokenThe
Feature activation+0.000
fact
Token fact
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
playing
Token playing
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.669
in
Token in
Feature activation+0.544
the
Token the
Feature activation+0.549
group
Token group
Feature activation+0.411
stage
Token stage
Feature activation+0.209
is
Token is
Feature activation+0.085
Stoke
Token Stoke
Feature activation+0.558
City
Token City
Feature activation+1.029
,
Token,
Feature activation+0.835
while
Token while
Feature activation+0.545
experienced
Token experienced
Feature activation+0.480
defender
Token defender
Feature activation+0.629
Chris
Token Chris
Feature activation+0.668
Sam
Token Sam
Feature activation+0.333
ba
Tokenba
Feature activation+0.317
has
Token has
Feature activation+0.232
also
Token also
Feature activation+0.000
Network
Token Network
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.768
.
Token.
Feature activation+0.807
Ċ
TokenĊ
Feature activation+0.625
Ċ
TokenĊ
Feature activation+0.435
Discuss
TokenDiscuss
Feature activation+0.226
your
Token your
Feature activation+0.000
voices
Token voices
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.406 - 0.541
CONTAINS 0.022%

storm
Tokenstorm
Feature activation+0.000
ed
Tokened
Feature activation+0.000
'
Token'
Feature activation+0.000
Liverpool
Token Liverpool
Feature activation+0.840
's
Token's
Feature activation+0.521
Pier
Token Pier
Feature activation+0.436
head
Tokenhead
Feature activation+0.021
(
Token (
Feature activation+0.075
with
Tokenwith
Feature activation+0.103
about
Token about
Feature activation+0.000
18
Token 18
Feature activation+0.000
University
Token University
Feature activation+0.031
in
Token in
Feature activation+0.000
London
Token London
Feature activation+0.597
this
Token this
Feature activation+0.486
evening
Token evening
Feature activation+0.473
.
Token.
Feature activation+0.540
Ċ
TokenĊ
Feature activation+0.326
Ċ
TokenĊ
Feature activation+0.161
But
TokenBut
Feature activation+0.058
she
Token she
Feature activation+0.000
says
Token says
Feature activation+0.000
EU
Token EU
Feature activation+0.225
after
Token after
Feature activation+0.155
Brexit
Token Brexit
Feature activation+0.497
.
Token.
Feature activation+0.746
But
Token But
Feature activation+0.365
EU
Token EU
Feature activation+0.480
leaders
Token leaders
Feature activation+0.160
insist
Token insist
Feature activation+0.169
these
Token these
Feature activation+0.182
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
for
Token for
Feature activation+0.000
Indigenous
Token Indigenous
Feature activation+0.179
and
Token and
Feature activation+0.311
Northern
Token Northern
Feature activation+0.590
Affairs
Token Affairs
Feature activation+0.512
,
Token,
Feature activation+0.429
echoed
Token echoed
Feature activation+0.128
those
Token those
Feature activation+0.141
sentiments
Token sentiments
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Republic
Token Republic
Feature activation+0.024
.
Token.
Feature activation+0.000
Two
Token Two
Feature activation+0.000
goals
Token goals
Feature activation+0.027
for
Token for
Feature activation+0.000
Canada
Token Canada
Feature activation+0.431
were
Token were
Feature activation+0.221
scored
Token scored
Feature activation+0.213
by
Token by
Feature activation+0.004
Taylor
Token Taylor
Feature activation+0.009
Hall
Token Hall
Feature activation+0.000

INTERVAL 0.270 - 0.406
CONTAINS 0.040%

,
Token,
Feature activation+0.000
glac
Token glac
Feature activation+0.000
iologist
Tokeniologist
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
British
Token British
Feature activation+0.291
Antarctic
Token Antarctic
Feature activation+0.238
Survey
Token Survey
Feature activation+0.160
Ċ
TokenĊ
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.000
David
TokenDavid
Feature activation+0.000
hours
Token hours
Feature activation+0.000
after
Token after
Feature activation+0.000
Greens
Token Greens
Feature activation+0.347
leader
Token leader
Feature activation+0.324
,
Token,
Feature activation+0.368
Richard
Token Richard
Feature activation+0.317
Di
Token Di
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
,
Token,
Feature activation+0.000
secured
Token secured
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
Ontario
Token Ontario
Feature activation+0.000
,
Token,
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.301
and
Token and
Feature activation+0.158
other
Token other
Feature activation+0.063
provinces
Token provinces
Feature activation+0.339
put
Token put
Feature activation+0.000
in
Token in
Feature activation+0.000
between
Token between
Feature activation+0.000
UKIP
Token UKIP
Feature activation+0.400
2014
Token 2014
Feature activation+0.286
and
Token and
Feature activation+0.283
UKIP
Token UKIP
Feature activation+0.596
2010
Token 2010
Feature activation+0.393
.
Token.
Feature activation+0.481
Yes
Token Yes
Feature activation+0.462
,
Token,
Feature activation+0.463
they
Token they
Feature activation+0.170
âĢ
TokenâĢ
Feature activation+0.106
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.889
Championship
Token Championship
Feature activation+0.349
.
Token.
Feature activation+0.442
They
Token They
Feature activation+0.395
are
Token are
Feature activation+0.270
seven
Token seven
Feature activation+0.000
-
Token-
Feature activation+0.070
time
Tokentime
Feature activation+0.112
winners
Token winners
Feature activation+0.180

INTERVAL 0.135 - 0.270
CONTAINS 0.073%

Hegel
Token Hegel
Feature activation+0.000
also
Token also
Feature activation+0.000
looms
Token looms
Feature activation+0.000
large
Token large
Feature activation+0.000
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.243
.
Token.
Feature activation+0.082
Certain
Token Certain
Feature activation+0.067
broad
Token broad
Feature activation+0.000
Hegel
Token Hegel
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
ains
Tokenains
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
Centre
Token Centre
Feature activation+0.237
state
Token state
Feature activation+0.198
the
Token the
Feature activation+0.000
venue
Token venue
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
shut
Token shut
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
South
Token South
Feature activation+0.000
Africans
Token Africans
Feature activation+0.213
took
Token took
Feature activation+0.291
over
Token over
Feature activation+0.172
the
Token the
Feature activation+0.211
administrative
Token administrative
Feature activation+0.027
centre
Token centre
Feature activation+0.275
at
Token at
Feature activation+0.405
Sch
Token Sch
Feature activation+0.092
and
Token and
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Clarke
Token Clarke
Feature activation+0.000
to
Token to
Feature activation+0.073
draw
Token draw
Feature activation+0.261
Wolves
Token Wolves
Feature activation+0.268
'
Token'
Feature activation+0.173
defence
Token defence
Feature activation+0.435
out
Token out
Feature activation+0.417
of
Token of
Feature activation+0.487
position
Token position
Feature activation+0.216
added
Token added
Feature activation+0.000
that
Token that
Feature activation+0.000
Canada
Token Canada
Feature activation+0.734
will
Token will
Feature activation+0.553
insist
Token insist
Feature activation+0.428
that
Token that
Feature activation+0.213
the
Token the
Feature activation+0.137
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 0.000 - 0.135
CONTAINS 99.840%

their
Token their
Feature activation+0.000
fathers
Token fathers
Feature activation+0.000
during
Token during
Feature activation+0.000
adolescence
Token adolescence
Feature activation+0.000
.
Token.
Feature activation+0.000
FDR
Token FDR
Feature activation+0.000
was
Token was
Feature activation+0.000
measured
Token measured
Feature activation+0.000
by
Token by
Feature activation+0.000
two
Token two
Feature activation+0.000
scales
Token scales
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
market
Token market
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decree
Token decree
Feature activation+0.000
which
Token which
Feature activation+0.000
staff
Token staff
Feature activation+0.000
.
Token .
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.000
ago
Token ago
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
only
Token only
Feature activation+0.000
got
Token got
Feature activation+0.000
11
Token 11
Feature activation+0.000
carries
Token carries
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
r
Token r
Feature activation+0.000
ailed
Tokenailed
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
walls
Token walls
Feature activation+0.000
and
Token and
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+0.000
that
Token that
Feature activation+0.000
ring
Token ring
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
town
Token town
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
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 H2.7: (feature 23765)

TOP ACTIVATIONS
MAX = 2.167

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
very
Token very
Feature activation+0.000
fast
Token fast
Feature activation+0.000
sa
Token sa
Feature activation+0.000
iler
Tokeniler
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.553
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.168
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
command
Token command
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.298
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.386
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
says
Token says
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.366
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
massive
Token massive
Feature activation+0.000
debt
Token debt
Feature activation+0.000
and
Token and
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
over
Token over
Feature activation+0.000
party
Token party
Feature activation+0.000
workers
Token workers
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.345
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Raj
Token Raj
Feature activation+0.000
la
Tokenla
Feature activation+0.000
.
Token.
Feature activation+0.000
quick
Token quick
Feature activation+0.000
to
Token to
Feature activation+0.000
react
Token react
Feature activation+0.000
following
Token following
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.281
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
backlash
Token backlash
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
this
Token this
Feature activation+0.000
post
Token post
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.272
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
give
Token give
Feature activation+0.000
all
Token all
Feature activation+0.000
bets
Token bets
Feature activation+0.000
are
Token are
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.270
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
handful
Token handful
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.254
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.383
upt
Token upt
Feature activation+0.000
ight
Tokenight
Feature activation+0.000
in
Token in
Feature activation+0.000
college
Token college
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.251
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
reminded
Token reminded
Feature activation+0.000
her
Token her
Feature activation+0.000
friend
Token friend
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.239
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
have
Token have
Feature activation+0.000
some
Token some
Feature activation+0.079
good
Token good
Feature activation+0.000
things
Token things
Feature activation+0.000
from
Token from
Feature activation+0.000
their
Token their
Feature activation+0.000
sites
Token sites
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.226
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
@
Token @
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
tricked
Token tricked
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.208
ľ
Tokenľ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
lined
Token lined
Feature activation+0.000
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
live
Token live
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.195
Ļ
TokenĻ
Feature activation+0.000
Rockefeller
Token Rockefeller
Feature activation+0.000
continued
Token continued
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
read
Tokenread
Feature activation+0.000
Pirate
Token Pirate
Feature activation+0.000
Roberts
Token Roberts
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.188
Ŀ
TokenĿ
Feature activation+0.000
who
Token who
Feature activation+0.000
ran
Token ran
Feature activation+0.000
the
Token the
Feature activation+0.000
Silk
Token Silk
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
remorse
Token remorse
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.175
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
not
Token not
Feature activation+0.000
sure
Token sure
Feature activation+0.000
there
Token there
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
highest
Token highest
Feature activation+0.000
level
Token level
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.174
Ŀ
TokenĿ
Feature activation+0.000
Be
Token Be
Feature activation+0.000
yo
Tokenyo
Feature activation+0.000
ÄŁ
TokenÄŁ
Feature activation+0.000
lu
Tokenlu
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
building
Token building
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.170
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
has
Token has
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
round
Token round
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.170
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
draft
Token draft
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.169
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
student
Token student
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
made
Token made
Feature activation+0.000
of
Token of
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.165
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
enough
Token enough
Feature activation+0.000
:
Token:
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000

Top DFA by src position
MAX = 2.120

<|endoftext|>
Token<|endoftext|>
Feature activation+0.337
Top resid features:
very
Token very
Feature activation+0.086
Top resid features:
fast
Token fast
Feature activation+0.019
Top resid features:
sa
Token sa
Feature activation+0.140
Top resid features:
iler
Tokeniler
Feature activation+0.318
Top resid features:
âĢ
TokenâĢ
Feature activation+1.908
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
command
Token command
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.699
Top resid features:
Ļ
TokenĻ
Feature activation-0.197
Top resid features:
re
Tokenre
Feature activation+0.061
Top resid features:
old
Token old
Feature activation+0.226
Top resid features:
,
Token,
Feature activation-0.270
Top resid features:
âĢ
TokenâĢ
Feature activation+1.705
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.350
Top resid features:
leaders
Token leaders
Feature activation+0.417
Top resid features:
to
Token to
Feature activation-0.148
Top resid features:
cut
Token cut
Feature activation+0.174
Top resid features:
Italy
Token Italy
Feature activation+0.158
Top resid features:
âĢ
TokenâĢ
Feature activation+1.670
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
massive
Token massive
Feature activation+0.000
Top resid features:
debt
Token debt
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.374
Top resid features:
over
Token over
Feature activation+0.165
Top resid features:
party
Token party
Feature activation+0.147
Top resid features:
workers
Token workers
Feature activation+0.296
Top resid features:
,
Token,
Feature activation-0.364
Top resid features:
âĢ
TokenâĢ
Feature activation+1.982
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
Raj
Token Raj
Feature activation+0.000
Top resid features:
la
Tokenla
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
quick
Token quick
Feature activation+0.167
Top resid features:
to
Token to
Feature activation-0.070
Top resid features:
react
Token react
Feature activation+0.160
Top resid features:
following
Token following
Feature activation+0.164
Top resid features:
yesterday
Token yesterday
Feature activation+0.253
Top resid features:
âĢ
TokenâĢ
Feature activation+1.486
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
backlash
Token backlash
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.414
Top resid features:
this
Token this
Feature activation+0.164
Top resid features:
post
Token post
Feature activation+0.344
Top resid features:
,
Token,
Feature activation-0.142
Top resid features:
I
Token I
Feature activation-0.192
Top resid features:
âĢ
TokenâĢ
Feature activation+1.939
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
m
Tokenm
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.182
Top resid features:
bets
Token bets
Feature activation+0.255
Top resid features:
are
Token are
Feature activation-0.074
Top resid features:
off
Token off
Feature activation+0.074
Top resid features:
,
Token,
Feature activation-0.250
Top resid features:
âĢ
TokenâĢ
Feature activation+1.939
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
said
Token said
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.404
Top resid features:
handful
Token handful
Feature activation+0.204
Top resid features:
rather
Token rather
Feature activation+0.185
Top resid features:
than
Token than
Feature activation-0.058
Top resid features:
hundreds
Token hundreds
Feature activation-0.028
Top resid features:
âĢ
TokenâĢ
Feature activation+1.801
Top resid features:
Ŀ
TokenĿ
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:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
upt
Token upt
Feature activation+0.221
Top resid features:
ight
Tokenight
Feature activation+0.085
Top resid features:
in
Token in
Feature activation-0.082
Top resid features:
college
Token college
Feature activation+0.136
Top resid features:
,
Token,
Feature activation-0.217
Top resid features:
âĢ
TokenâĢ
Feature activation+1.852
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
reminded
Token reminded
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
friend
Token friend
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.423
Top resid features:
to
Token to
Feature activation+0.057
Top resid features:
Mars
Token Mars
Feature activation+0.365
Top resid features:
,
Token,
Feature activation-0.177
Top resid features:
you
Token you
Feature activation-0.159
Top resid features:
âĢ
TokenâĢ
Feature activation+1.985
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
ll
Tokenll
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
things
Token things
Feature activation+0.121
Top resid features:
from
Token from
Feature activation+0.066
Top resid features:
their
Token their
Feature activation+0.082
Top resid features:
sites
Token sites
Feature activation+0.239
Top resid features:
.
Token.
Feature activation-0.144
Top resid features:
âĢ
TokenâĢ
Feature activation+1.731
Top resid features:
Ŀ
TokenĿ
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:
The
TokenThe
Feature activation+0.000
Top resid features:
@
Token @
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.371
Top resid features:
tricked
Token tricked
Feature activation+0.293
Top resid features:
.
Token.
Feature activation+0.100
Top resid features:
Ċ
TokenĊ
Feature activation-0.081
Top resid features:
Ċ
TokenĊ
Feature activation-0.187
Top resid features:
âĢ
TokenâĢ
Feature activation+1.967
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
They
TokenThey
Feature activation+0.000
Top resid features:
lined
Token lined
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.445
Top resid features:
Ļ
TokenĻ
Feature activation-0.079
Top resid features:
t
Tokent
Feature activation+0.051
Top resid features:
live
Token live
Feature activation+0.284
Top resid features:
,
Token,
Feature activation-0.372
Top resid features:
âĢ
TokenâĢ
Feature activation+2.120
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
Rockefeller
Token Rockefeller
Feature activation+0.000
Top resid features:
continued
Token continued
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.382
Top resid features:
read
Tokenread
Feature activation+0.190
Top resid features:
Pirate
Token Pirate
Feature activation+0.026
Top resid features:
Roberts
Token Roberts
Feature activation+0.051
Top resid features:
,
Token,
Feature activation-0.312
Top resid features:
âĢ
TokenâĢ
Feature activation+2.106
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
ran
Token ran
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Silk
Token Silk
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.434
Top resid features:
remorse
Token remorse
Feature activation+0.338
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.108
Top resid features:
I
Token I
Feature activation-0.079
Top resid features:
âĢ
TokenâĢ
Feature activation+1.863
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
m
Tokenm
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
sure
Token sure
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.410
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
highest
Token highest
Feature activation+0.095
Top resid features:
level
Token level
Feature activation+0.202
Top resid features:
,
Token,
Feature activation-0.349
Top resid features:
âĢ
TokenâĢ
Feature activation+2.070
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Be
Token Be
Feature activation+0.000
Top resid features:
yo
Tokenyo
Feature activation+0.000
Top resid features:
ÄŁ
TokenÄŁ
Feature activation+0.000
Top resid features:
lu
Tokenlu
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.349
Top resid features:
building
Token building
Feature activation+0.362
Top resid features:
.
Token.
Feature activation+0.055
Top resid features:
Ċ
TokenĊ
Feature activation-0.117
Top resid features:
Ċ
TokenĊ
Feature activation-0.216
Top resid features:
âĢ
TokenâĢ
Feature activation+1.992
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.405
Top resid features:
round
Token round
Feature activation+0.192
Top resid features:
of
Token of
Feature activation-0.046
Top resid features:
this
Token this
Feature activation+0.007
Top resid features:
year
Token year
Feature activation+0.094
Top resid features:
âĢ
TokenâĢ
Feature activation+1.773
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
draft
Token draft
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.395
Top resid features:
is
Token is
Feature activation+0.061
Top resid features:
one
Token one
Feature activation+0.313
Top resid features:
thing
Token thing
Feature activation-0.046
Top resid features:
,
Token,
Feature activation-0.318
Top resid features:
âĢ
TokenâĢ
Feature activation+2.019
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
student
Token student
Feature activation+0.000
Top resid features:
wrote
Token wrote
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.391
Top resid features:
made
Token made
Feature activation+0.231
Top resid features:
of
Token of
Feature activation-0.071
Top resid features:
blocks
Token blocks
Feature activation+0.303
Top resid features:
wasn
Token wasn
Feature activation-0.461
Top resid features:
âĢ
TokenâĢ
Feature activation+2.026
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Thanks
Token Thanks
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.04

Head 2: 0.03

Head 3: 0.06

Head 4: 0.02

Head 5: 0.06

Head 6: 0.11

Head 7: 0.20

Head 8: 0.04

Head 9: 0.06

Head 10: 0.18

Head 11: 0.10

Positive logits

cknowled1.13

recated1.05

athi1.03

enhagen0.93

?)0.86

adv0.84

ertodd0.84

won0.82

must0.81

depends0.79

oret0.78

eded0.78

-)0.78

shr0.78

afety0.77

said0.77

perjury0.77

prus0.76

nder0.76

cipled0.76

Negative logits

itaire-0.89

="#-0.85

adolesc-0.84

Interstitial-0.84

liberating-0.83

destro-0.81

performing-0.81

confir-0.81

accomp-0.79

Participants-0.79

."[-0.77

";-0.77

whipping-0.77

Wiz-0.76

outlet-0.76

Blend-0.76

"(-0.76

odge-0.75

"[-0.75

initiation-0.75

INTERVAL 1.950 - 2.167
CONTAINS 0.003%

INTERVAL 1.734 - 1.950
CONTAINS 0.005%

INTERVAL 1.517 - 1.734
CONTAINS 0.007%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
very
Token very
Feature activation+0.000
fast
Token fast
Feature activation+0.000
sa
Token sa
Feature activation+0.000
iler
Tokeniler
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.553
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.168
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
command
Token command
Feature activation+0.000

INTERVAL 1.300 - 1.517
CONTAINS 0.007%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
over
Token over
Feature activation+0.000
party
Token party
Feature activation+0.000
workers
Token workers
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.345
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Raj
Token Raj
Feature activation+0.000
la
Tokenla
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.298
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.386
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
says
Token says
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.366
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
massive
Token massive
Feature activation+0.000
debt
Token debt
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.084 - 1.300
CONTAINS 0.017%

all
Token all
Feature activation+0.000
bets
Token bets
Feature activation+0.000
are
Token are
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.270
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
live
Token live
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.195
Ļ
TokenĻ
Feature activation+0.000
Rockefeller
Token Rockefeller
Feature activation+0.000
continued
Token continued
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
read
Tokenread
Feature activation+0.000
Pirate
Token Pirate
Feature activation+0.000
Roberts
Token Roberts
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.188
Ŀ
TokenĿ
Feature activation+0.000
who
Token who
Feature activation+0.000
ran
Token ran
Feature activation+0.000
the
Token the
Feature activation+0.000
Silk
Token Silk
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
made
Token made
Feature activation+0.000
of
Token of
Feature activation+0.000
blocks
Token blocks
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.165
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
enough
Token enough
Feature activation+0.000
:
Token:
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
remorse
Token remorse
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.175
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
not
Token not
Feature activation+0.000
sure
Token sure
Feature activation+0.000
there
Token there
Feature activation+0.000

INTERVAL 0.867 - 1.084
CONTAINS 0.011%

sp
Tokensp
Feature activation+0.000
it
Tokenit
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
footsteps
Token footsteps
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.966
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
officer
Token officer
Feature activation+0.000
if
Token if
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
saw
Token saw
Feature activation+0.000
.
Token.
Feature activation+0.000
Glover
Token Glover
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.932
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
neck
Token neck
Feature activation+0.000
remained
Token remained
Feature activation+0.000
locked
Token locked
Feature activation+0.000
experiencing
Token experiencing
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.079
ľ
Tokenľ
Feature activation+0.000
pain
Tokenpain
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.886
Ŀ
TokenĿ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.040
ľ
Tokenľ
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ear
Tokenear
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
personal
Token personal
Feature activation+0.000
account
Token account
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.903
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.000
noted
Token noted
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.873
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
achieved
Token achieved
Feature activation+0.000
thickness
Token thickness
Feature activation+0.000

INTERVAL 0.650 - 0.867
CONTAINS 0.013%

you
Token you
Feature activation+0.000
four
Token four
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.663
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000
titles
Token titles
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.660
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
President
Token President
Feature activation+0.000
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
called
Token called
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.130
ľ
Tokenľ
Feature activation+0.000
America
TokenAmerica
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.817
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Greece
Token Greece
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.081
a
Token a
Feature activation+0.000
simple
Token simple
Feature activation+0.000
ambush
Token ambush
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.678
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
love
Token love
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
really
Token really
Feature activation+0.000
listening
Token listening
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.692
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
so
Token so
Feature activation+0.000
fuckin
Token fuckin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.258

INTERVAL 0.433 - 0.650
CONTAINS 0.012%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
2
Token 2
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
prosecutor
Token prosecutor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.546
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
office
Token office
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
med
Tokenmed
Feature activation+0.000
Guy
Token Guy
Feature activation+0.000
F
Token F
Feature activation+0.000
ieri
Tokenieri
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.610
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
American
Token American
Feature activation+0.000
Kitchen
Token Kitchen
Feature activation+0.000
or
Token or
Feature activation+0.000
id
Tokenid
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
residents
Token residents
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.645
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
and
Token and
Feature activation+0.000
decades
Token decades
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.494
Ŀ
TokenĿ
Feature activation+0.000
Mill
Token Mill
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ridiculous
Token ridiculous
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.540
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
outrageous
Token outrageous
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.149

INTERVAL 0.217 - 0.433
CONTAINS 0.016%

with
Token with
Feature activation+0.000
impunity
Token impunity
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.258
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.000
do
Token do
Feature activation+0.000
something
Token something
Feature activation+0.000
well
Token well
Feature activation+0.000
,
Token,
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.387
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
student
Token student
Feature activation+0.000
loan
Token loan
Feature activation+0.000
borrowers
Token borrowers
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.397
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
seen
Token seen
Feature activation+0.000
advertisements
Token advertisements
Feature activation+0.000
for
Token for
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.305
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
governance
Token governance
Feature activation+0.000
reform
Token reform
Feature activation+0.000
at
Token at
Feature activation+0.000
long
Token long
Feature activation+0.000
stays
Token stays
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.264
ľ
Tokenľ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
such
Token such
Feature activation+0.000
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000

INTERVAL 0.000 - 0.217
CONTAINS 99.909%

them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
been
Token been
Feature activation+0.000
traveling
Token traveling
Feature activation+0.000
and
Token and
Feature activation+0.000
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
gather
Token gather
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
knew
Token knew
Feature activation+0.000
that
Token that
Feature activation+0.000
wealth
Token wealth
Feature activation+0.000
is
Token is
Feature activation+0.000
created
Token created
Feature activation+0.000
through
Token through
Feature activation+0.000
local
Token local
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.000
takes
Token takes
Feature activation+0.000
credit
Token credit
Feature activation+0.000
for
Token for
Feature activation+0.000
its
Token its
Feature activation+0.000
successes
Token successes
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
isn
Token isn
Feature activation+0.000
enthusiast
Token enthusiast
Feature activation+0.000
then
Token then
Feature activation+0.000
I
Token I
Feature activation+0.000
strongly
Token strongly
Feature activation+0.000
advise
Token advise
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
reading
Token reading
Feature activation+0.000
,
Token,
Feature activation+0.000
grab
Token grab
Feature activation+0.000
www
Token www
Feature activation+0.000
.
Token.
Feature activation+0.000
bos
Tokenbos
Feature activation+0.000
nian
Tokennian
Feature activation+0.000
-
Token-
Feature activation+0.000
py
Tokenpy
Feature activation+0.000
ramid
Tokenramid
Feature activation+0.000
.
Token.
Feature activation+0.000
org
Tokenorg
Feature activation+0.000
/
Token/
Feature activation+0.000
storage
Tokenstorage
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 H2.7: (feature 5383)

TOP ACTIVATIONS
MAX = 2.409

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.127
Most
TokenMost
Feature activation+0.249
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
dead
Token dead
Feature activation+0.000
were
Token were
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
certificate
Token certificate
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.116
My
TokenMy
Feature activation+0.584
job
Token job
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
issue
Token issue
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.045
We
TokenWe
Feature activation+0.439
have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
safe
Token safe
Feature activation+0.000
ways
Token ways
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
water
Token water
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.029
One
TokenOne
Feature activation+0.273
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
states
Token states
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.992
There
TokenThere
Feature activation+0.185
are
Token are
Feature activation+0.000
an
Token an
Feature activation+0.000
awful
Token awful
Feature activation+0.000
lot
Token lot
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.973
What
TokenWhat
Feature activation+0.393
this
Token this
Feature activation+0.000
bill
Token bill
Feature activation+0.000
does
Token does
Feature activation+0.000
is
Token is
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.888
C
TokenC
Feature activation+0.000
hern
Tokenhern
Feature activation+0.000
obyl
Tokenobyl
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
park
Token park
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
''
Token''
Feature activation+1.876
It
TokenIt
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
easiest
Token easiest
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.870
He
TokenHe
Feature activation+0.000
sought
Token sought
Feature activation+0.000
refuge
Token refuge
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
mag
Token mag
Feature activation+0.000
na
Tokenna
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.778
A
TokenA
Feature activation+0.225
third
Token third
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
atic
Tokenatic
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.669
We
TokenWe
Feature activation+0.411
think
Token think
Feature activation+0.161
first
Token first
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
century
Token century
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.612
Our
TokenOur
Feature activation+0.522
new
Token new
Feature activation+0.000
observations
Token observations
Feature activation+0.000
emphasize
Token emphasize
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
offered
Token offered
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+1.604
Human
TokenHuman
Feature activation+0.000
rights
Token rights
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
ignored
Token ignored
Feature activation+0.000
such
Token such
Feature activation+0.000
cases
Token cases
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.590
That
TokenThat
Feature activation+0.390
's
Token's
Feature activation+0.104
the
Token the
Feature activation+0.000
deputy
Token deputy
Feature activation+0.000
's
Token's
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Eric
Token Eric
Feature activation+0.000
kson
Tokenkson
Feature activation+0.000
acknowledged
Token acknowledged
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.582
We
TokenWe
Feature activation+0.509
âĢ
TokenâĢ
Feature activation+0.016
ļ
Tokenļ
Feature activation+0.000
Ã
TokenÃ
Feature activation+0.000
Ħ
TokenĦ
Feature activation+0.000
o
Token o
Feature activation+0.000
vation
Tokenvation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.582
It
TokenIt
Feature activation+0.209
tempt
Token tempt
Feature activation+0.000
s
Tokens
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
bench
Token bench
Feature activation+0.000
last
Token last
Feature activation+0.000
spring
Token spring
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.561
It
TokenIt
Feature activation+0.003
's
Token's
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
counties
Token counties
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.515
Remember
TokenRemember
Feature activation+0.070
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
only
Token only
Feature activation+0.000
civil
Tokencivil
Feature activation+0.000
war
Token war
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.499
President
TokenPresident
Feature activation+0.000
Ham
Token Ham
Feature activation+0.000
id
Tokenid
Feature activation+0.000
Kar
Token Kar
Feature activation+0.000
zai
Tokenzai
Feature activation+0.000
Andy
Token Andy
Feature activation+0.000
Thorn
Token Thorn
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.454
We
TokenWe
Feature activation+0.295
are
Token are
Feature activation+0.000
really
Token really
Feature activation+0.000
pleased
Token pleased
Feature activation+0.000
to
Token to
Feature activation+0.000

Top DFA by src position
MAX = 2.312

<|endoftext|>
Token<|endoftext|>
Feature activation+0.088
Top resid features:
forces
Token forces
Feature activation-0.069
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.229
Top resid features:
Ċ
TokenĊ
Feature activation+0.262
Top resid features:
"
Token"
Feature activation+2.233
Top resid features:
Most
TokenMost
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.075
Top resid features:
certificate
Token certificate
Feature activation-0.041
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.233
Top resid features:
Ċ
TokenĊ
Feature activation+0.263
Top resid features:
"
Token"
Feature activation+2.204
Top resid features:
My
TokenMy
Feature activation+0.000
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
military
Token military
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.086
Top resid features:
issue
Token issue
Feature activation-0.126
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.229
Top resid features:
Ċ
TokenĊ
Feature activation+0.269
Top resid features:
"
Token"
Feature activation+2.197
Top resid features:
We
TokenWe
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
safe
Token safe
Feature activation+0.000
Top resid features:
ways
Token ways
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.085
Top resid features:
water
Token water
Feature activation-0.108
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
Ċ
TokenĊ
Feature activation+0.234
Top resid features:
Ċ
TokenĊ
Feature activation+0.262
Top resid features:
"
Token"
Feature activation+2.160
Top resid features:
One
TokenOne
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
main
Token main
Feature activation+0.000
Top resid features:
reasons
Token reasons
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.063
Top resid features:
states
Token states
Feature activation-0.122
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.216
Top resid features:
Ċ
TokenĊ
Feature activation+0.236
Top resid features:
"
Token"
Feature activation+2.249
Top resid features:
There
TokenThere
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
awful
Token awful
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.064
Top resid features:
next
Token next
Feature activation-0.103
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+0.223
Top resid features:
Ċ
TokenĊ
Feature activation+0.275
Top resid features:
"
Token"
Feature activation+2.142
Top resid features:
What
TokenWhat
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
bill
Token bill
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
about
Token about
Feature activation-0.042
Top resid features:
it
Token it
Feature activation-0.064
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.206
Top resid features:
Ċ
TokenĊ
Feature activation+0.259
Top resid features:
"
Token"
Feature activation+2.055
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
hern
Tokenhern
Feature activation+0.000
Top resid features:
obyl
Tokenobyl
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.115
Top resid features:
park
Token park
Feature activation-0.112
Top resid features:
.
Token.
Feature activation+0.102
Top resid features:
Ċ
TokenĊ
Feature activation+0.207
Top resid features:
Ċ
TokenĊ
Feature activation+0.225
Top resid features:
''
Token''
Feature activation+2.008
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
easiest
Token easiest
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.027
Top resid features:
family
Token family
Feature activation+0.065
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
Ċ
TokenĊ
Feature activation+0.216
Top resid features:
Ċ
TokenĊ
Feature activation+0.264
Top resid features:
"
Token"
Feature activation+1.867
Top resid features:
He
TokenHe
Feature activation+0.000
Top resid features:
sought
Token sought
Feature activation+0.000
Top resid features:
refuge
Token refuge
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
mag
Token mag
Feature activation-0.132
Top resid features:
na
Tokenna
Feature activation-0.051
Top resid features:
).
Token).
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.184
Top resid features:
Ċ
TokenĊ
Feature activation+0.233
Top resid features:
"
Token"
Feature activation+2.088
Top resid features:
A
TokenA
Feature activation+0.000
Top resid features:
third
Token third
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ri
Tokenri
Feature activation-0.066
Top resid features:
atic
Tokenatic
Feature activation-0.050
Top resid features:
o
Tokeno
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.316
Top resid features:
Ċ
TokenĊ
Feature activation+0.340
Top resid features:
"
Token"
Feature activation+1.799
Top resid features:
We
TokenWe
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
century
Token century
Feature activation-0.104
Top resid features:
ago
Token ago
Feature activation-0.066
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.233
Top resid features:
Ċ
TokenĊ
Feature activation+0.281
Top resid features:
"
Token"
Feature activation+1.828
Top resid features:
Our
TokenOur
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
observations
Token observations
Feature activation+0.000
Top resid features:
emphasize
Token emphasize
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.071
Top resid features:
offered
Token offered
Feature activation-0.120
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.244
Top resid features:
Ċ
TokenĊ
Feature activation+0.296
Top resid features:
'
Token'
Feature activation+1.785
Top resid features:
Human
TokenHuman
Feature activation+0.000
Top resid features:
rights
Token rights
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
ignored
Token ignored
Feature activation+0.000
Top resid features:
such
Token such
Feature activation+0.035
Top resid features:
cases
Token cases
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.208
Top resid features:
Ċ
TokenĊ
Feature activation+0.272
Top resid features:
"
Token"
Feature activation+1.734
Top resid features:
That
TokenThat
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
deputy
Token deputy
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.123
Top resid features:
Eric
Token Eric
Feature activation-0.136
Top resid features:
kson
Tokenkson
Feature activation-0.105
Top resid features:
acknowledged
Token acknowledged
Feature activation-0.049
Top resid features:
.
Token.
Feature activation+0.106
Top resid features:
"
Token "
Feature activation+2.312
Top resid features:
We
TokenWe
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:
Ã
TokenÃ
Feature activation+0.000
Top resid features:
Ħ
TokenĦ
Feature activation+0.000
Top resid features:
o
Token o
Feature activation-0.072
Top resid features:
vation
Tokenvation
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.092
Top resid features:
Ċ
TokenĊ
Feature activation+0.210
Top resid features:
Ċ
TokenĊ
Feature activation+0.242
Top resid features:
"
Token"
Feature activation+1.720
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
tempt
Token tempt
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.160
Top resid features:
bench
Token bench
Feature activation-0.008
Top resid features:
last
Token last
Feature activation-0.100
Top resid features:
spring
Token spring
Feature activation-0.023
Top resid features:
.
Token.
Feature activation+0.219
Top resid features:
"
Token "
Feature activation+1.980
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
the
Tokenthe
Feature activation+0.000
Top resid features:
counties
Token counties
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.104
Top resid features:
com
Tokencom
Feature activation-0.068
Top resid features:
:
Token:
Feature activation-0.234
Top resid features:
Ċ
TokenĊ
Feature activation+0.244
Top resid features:
Ċ
TokenĊ
Feature activation+0.307
Top resid features:
"
Token"
Feature activation+1.711
Top resid features:
Remember
TokenRemember
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
civil
Tokencivil
Feature activation-0.179
Top resid features:
war
Token war
Feature activation-0.064
Top resid features:
".
Token".
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.193
Top resid features:
Ċ
TokenĊ
Feature activation+0.238
Top resid features:
"
Token"
Feature activation+1.640
Top resid features:
President
TokenPresident
Feature activation+0.000
Top resid features:
Ham
Token Ham
Feature activation+0.000
Top resid features:
id
Tokenid
Feature activation+0.000
Top resid features:
Kar
Token Kar
Feature activation+0.000
Top resid features:
zai
Tokenzai
Feature activation+0.000
Top resid features:
Andy
Token Andy
Feature activation-0.056
Top resid features:
Thorn
Token Thorn
Feature activation-0.065
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.251
Top resid features:
Ċ
TokenĊ
Feature activation+0.321
Top resid features:
"
Token"
Feature activation+1.539
Top resid features:
We
TokenWe
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.000
Top resid features:
pleased
Token pleased
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.03

Head 2: 0.05

Head 3: 0.06

Head 4: 0.03

Head 5: 0.04

Head 6: 0.07

Head 7: 0.20

Head 8: 0.06

Head 9: 0.07

Head 10: 0.20

Head 11: 0.10

Positive logits

sports1.03

1.01

Hung0.94

iera0.93

ertodd0.91

pers0.90

unts0.89

Church0.87

Official0.86

INC0.86

EPA0.85

South0.84

ikhail0.84

Notable0.82

Pg0.82

Major0.81

Turkey0.81

Reports0.80

ieth0.80

Houston0.80

Negative logits

?".-1.04

".-0.99

"(-0.97

illet-0.94

Blend-0.88

!".-0.88

""-0.85

abee-0.84

?",-0.84

ardless-0.83

".-0.82

[…]-0.82

camel-0.81

:"-0.81

lucid-0.81

"…-0.81

��-0.80

".[-0.79

.",-0.78

cruc-0.78

INTERVAL 2.168 - 2.409
CONTAINS 0.001%

INTERVAL 1.927 - 2.168
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.127
Most
TokenMost
Feature activation+0.249
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
dead
Token dead
Feature activation+0.000
were
Token were
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
states
Token states
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.992
There
TokenThere
Feature activation+0.185
are
Token are
Feature activation+0.000
an
Token an
Feature activation+0.000
awful
Token awful
Feature activation+0.000
lot
Token lot
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
issue
Token issue
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.045
We
TokenWe
Feature activation+0.439
have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
safe
Token safe
Feature activation+0.000
ways
Token ways
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
water
Token water
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+2.029
One
TokenOne
Feature activation+0.273
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.973
What
TokenWhat
Feature activation+0.393
this
Token this
Feature activation+0.000
bill
Token bill
Feature activation+0.000
does
Token does
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 1.686 - 1.927
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
park
Token park
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
''
Token''
Feature activation+1.876
It
TokenIt
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
easiest
Token easiest
Feature activation+0.000
mag
Token mag
Feature activation+0.000
na
Tokenna
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.778
A
TokenA
Feature activation+0.225
third
Token third
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.888
C
TokenC
Feature activation+0.000
hern
Tokenhern
Feature activation+0.000
obyl
Tokenobyl
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.870
He
TokenHe
Feature activation+0.000
sought
Token sought
Feature activation+0.000
refuge
Token refuge
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 1.445 - 1.686
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
offered
Token offered
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+1.604
Human
TokenHuman
Feature activation+0.000
rights
Token rights
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
ignored
Token ignored
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Eric
Token Eric
Feature activation+0.000
kson
Tokenkson
Feature activation+0.000
acknowledged
Token acknowledged
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.582
We
TokenWe
Feature activation+0.509
âĢ
TokenâĢ
Feature activation+0.016
ļ
Tokenļ
Feature activation+0.000
Ã
TokenÃ
Feature activation+0.000
Ħ
TokenĦ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
bench
Token bench
Feature activation+0.000
last
Token last
Feature activation+0.000
spring
Token spring
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.561
It
TokenIt
Feature activation+0.003
's
Token's
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
counties
Token counties
Feature activation+0.000
civil
Tokencivil
Feature activation+0.000
war
Token war
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.499
President
TokenPresident
Feature activation+0.000
Ham
Token Ham
Feature activation+0.000
id
Tokenid
Feature activation+0.000
Kar
Token Kar
Feature activation+0.000
zai
Tokenzai
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.515
Remember
TokenRemember
Feature activation+0.070
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
only
Token only
Feature activation+0.000

INTERVAL 1.204 - 1.445
CONTAINS 0.004%

sources
Token sources
Feature activation+0.000
insisted
Token insisted
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.309
The
TokenThe
Feature activation+0.158
IGN
Token IGN
Feature activation+0.000
OU
TokenOU
Feature activation+0.000
Board
Token Board
Feature activation+0.000
of
Token of
Feature activation+0.000
solo
Token solo
Feature activation+0.000
parent
Token parent
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.310
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
street
Token street
Feature activation+0.000
language
Token language
Feature activation+0.000
,
Token,
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
outreach
Token outreach
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.408
It
TokenIt
Feature activation+0.206
was
Token was
Feature activation+0.000
bad
Token bad
Feature activation+0.000
enough
Token enough
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.230
These
TokenThese
Feature activation+0.167
thugs
Token thugs
Feature activation+0.000
make
Token make
Feature activation+0.000
me
Token me
Feature activation+0.000
embarrassed
Token embarrassed
Feature activation+0.000
H
Token H
Feature activation+0.000
AD
TokenAD
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.371
DW
TokenDW
Feature activation+0.000
TS
TokenTS
Feature activation+0.000
"
Token"
Feature activation+0.166
also
Token also
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.963 - 1.204
CONTAINS 0.006%

of
Token of
Feature activation+0.000
weakness
Token weakness
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.049
This
TokenThis
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
how
Token how
Feature activation+0.000
negotiation
Token negotiation
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
harder
Token harder
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.152
This
TokenThis
Feature activation+0.055
new
Token new
Feature activation+0.000
delay
Token delay
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
is
Token is
Feature activation+0.000
Ban
Token Ban
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
delegates
Token delegates
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.189
Se
TokenSe
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
the
Token the
Feature activation+0.000
moment
Token moment
Feature activation+0.000
,
Token,
Feature activation+0.000
ding
Tokending
Feature activation+0.000
tours
Token tours
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.154
It
TokenIt
Feature activation+0.152
's
Token's
Feature activation+0.000
hard
Token hard
Feature activation+0.000
given
Token given
Feature activation+0.000
stories
Token stories
Feature activation+0.000
a
Token a
Feature activation+0.000
cover
Token cover
Feature activation+0.000
song
Token song
Feature activation+0.000
entitled
Token entitled
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+1.017
D
TokenD
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
Fe
Token Fe
Feature activation+0.000

INTERVAL 0.723 - 0.963
CONTAINS 0.007%

his
Token his
Feature activation+0.000
students
Token students
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.894
Sometimes
TokenSometimes
Feature activation+0.000
standing
Token standing
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
something
Token something
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.801
I
TokenI
Feature activation+0.154
was
Token was
Feature activation+0.000
quite
Token quite
Feature activation+0.000
amazed
Token amazed
Feature activation+0.000
,
Token,
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.765
Yeah
TokenYeah
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
mean
Token mean
Feature activation+0.000
,
Token,
Feature activation+0.000
commissioner
Token commissioner
Feature activation+0.000
Don
Token Don
Feature activation+0.000
Gar
Token Gar
Feature activation+0.000
ber
Tokenber
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.908
Obviously
TokenObviously
Feature activation+0.257
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
from
Token from
Feature activation+0.000
deforestation
Token deforestation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.819
Companies
TokenCompanies
Feature activation+0.000
are
Token are
Feature activation+0.000
moving
Token moving
Feature activation+0.000
forward
Token forward
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.482 - 0.723
CONTAINS 0.013%

in
Token in
Feature activation+0.000
Palestine
Token Palestine
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.632
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
women
Token women
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
Lancaster
Token Lancaster
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.621
I
TokenI
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
board
Token board
Feature activation+0.000
her
Token her
Feature activation+0.000
Lite
Token Lite
Feature activation+0.000
',
Token',
Feature activation+0.000
he
Token he
Feature activation+0.000
added
Token added
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.545
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
ObamaCare
Token ObamaCare
Feature activation+0.000
gone
Token gone
Feature activation+0.000
.'
Token.'
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
!"
Token!"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.569
No
TokenNo
Feature activation+0.000
!"
Token!"
Feature activation+0.000
Said
Token Said
Feature activation+0.000
Dom
Token Dom
Feature activation+0.000
P
Token P
Feature activation+0.000
le
Token le
Feature activation+0.000
prof
Token prof
Feature activation+0.000
esse
Tokenesse
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
.
Token.
Feature activation+0.000
«
Token «
Feature activation+0.542
N
Token N
Feature activation+0.000
OL
TokenOL
Feature activation+0.000
AF
TokenAF
Feature activation+0.000
ran
Tokenran
Feature activation+0.000
ça
Tokença
Feature activation+0.000

INTERVAL 0.241 - 0.482
CONTAINS 0.016%

's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
difference
Token difference
Feature activation+0.000
between
Token between
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.340
leg
Tokenleg
Feature activation+0.000
itimate
Tokenitimate
Feature activation+0.000
concern
Token concern
Feature activation+0.000
"
Token"
Feature activation+0.000
and
Token and
Feature activation+0.000
into
Token into
Feature activation+0.000
football
Token football
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.414
Mc
TokenMc
Feature activation+0.000
M
TokenM
Feature activation+0.000
ahon
Tokenahon
Feature activation+0.000
has
Token has
Feature activation+0.000
always
Token always
Feature activation+0.000
language
Token language
Feature activation+0.000
decent
Token decent
Feature activation+0.000
.
Token.
Feature activation+0.000
Use
Token Use
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.387
Report
TokenReport
Feature activation+0.000
Abuse
Token Abuse
Feature activation+0.000
"
Token"
Feature activation+0.000
button
Token button
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
bullet
Token bullet
Feature activation+0.000
cost
Token cost
Feature activation+0.000
$
Token $
Feature activation+0.000
.
Token .
Feature activation+0.000
''
Token ''
Feature activation+0.280
Man
TokenMan
Feature activation+0.000
,
Token,
Feature activation+0.000
l
Token l
Feature activation+0.000
would
Token would
Feature activation+0.000
blow
Token blow
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
room
Token room
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.276
we
Tokenwe
Feature activation+0.427
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
a
Token a
Feature activation+0.000
series
Token series
Feature activation+0.000

INTERVAL 0.000 - 0.241
CONTAINS 99.950%

for
Token for
Feature activation+0.000
about
Token about
Feature activation+0.000
8
Token 8
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
population
Token population
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
rocking
Token rocking
Feature activation+0.000
,
Token,
Feature activation+0.000
ultimately
Token ultimately
Feature activation+0.000
dev
Token dev
Feature activation+0.000
oured
Tokenoured
Feature activation+0.000
a
Token a
Feature activation+0.000
blunt
Token blunt
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
dimensional
Tokendimensional
Feature activation+0.000
AMD
Token AMD
Feature activation+0.000
Zen
Token Zen
Feature activation+0.000
CPU
Token CPU
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
,
Token,
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
and
Token and
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
seen
Token seen
Feature activation+0.000
to
Token to
Feature activation+0.000
welcome
Token welcome
Feature activation+0.000
onto
Token onto
Feature activation+0.000
their
Token their
Feature activation+0.000
teams
Token teams
Feature activation+0.000
roster
Token roster
Feature activation+0.000
tomorrow
Token tomorrow
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
smooth
Token smooth
Feature activation+0.000
talking
Token talking
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 H2.7: (feature 16850)

TOP ACTIVATIONS
MAX = 1.384

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
gross
Token gross
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
gross
Token gross
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
.
Token.
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.155
taxes
Token taxes
Feature activation+1.384
on
Token on
Feature activation+0.965
money
Token money
Feature activation+1.116
they
Token they
Feature activation+0.692
withdraw
Token withdraw
Feature activation+0.589
from
Token from
Feature activation+0.259
a
Token a
Feature activation+0.185
Roth
Token Roth
Feature activation+0.289
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
%
Token%
Feature activation+0.000
capital
Token capital
Feature activation+0.049
gains
Token gains
Feature activation+0.221
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
15
Token 15
Feature activation+0.163
percent
Token percent
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.155
taxes
Token taxes
Feature activation+1.384
on
Token on
Feature activation+0.965
money
Token money
Feature activation+1.116
they
Token they
Feature activation+0.692
withdraw
Token withdraw
Feature activation+0.589
from
Token from
Feature activation+0.259
a
Token a
Feature activation+0.185
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
,
Token,
Feature activation+0.000
capital
Token capital
Feature activation+0.049
gains
Token gains
Feature activation+0.221
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
15
Token 15
Feature activation+0.163
between
Token between
Feature activation+0.000
commercial
Token commercial
Feature activation+0.226
and
Token and
Feature activation+0.111
residential
Token residential
Feature activation+0.092
tax
Token tax
Feature activation+0.732
rates
Token rates
Feature activation+0.896
.
Token.
Feature activation+0.693
In
Token In
Feature activation+0.384
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
New
Token New
Feature activation+0.000
programs
Token programs
Feature activation+0.029
with
Token with
Feature activation+0.041
an
Token an
Feature activation+0.000
annual
Token annual
Feature activation+0.003
cash
Token cash
Feature activation+0.628
payment
Token payment
Feature activation+0.848
to
Token to
Feature activation+0.648
every
Token every
Feature activation+0.568
adult
Token adult
Feature activation+0.399
resident
Token resident
Feature activation+0.000
.
Token.
Feature activation+0.000
Yes
TokenYes
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
unemployment
Token unemployment
Feature activation+0.504
rate
Token rate
Feature activation+0.760
in
Token in
Feature activation+0.841
California
Token California
Feature activation+0.671
was
Token was
Feature activation+0.292
a
Token a
Feature activation+0.081
terrible
Token terrible
Feature activation+0.000
11
Token 11
Feature activation+0.000
our
Token our
Feature activation+0.000
economic
Token economic
Feature activation+0.232
infrastructure
Token infrastructure
Feature activation+0.527
and
Token and
Feature activation+0.419
the
Token the
Feature activation+0.225
debt
Token debt
Feature activation+0.832
would
Token would
Feature activation+0.525
be
Token be
Feature activation+0.264
wiped
Token wiped
Feature activation+0.392
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
is
Token is
Feature activation+0.000
you
Token you
Feature activation+0.000
pay
Token pay
Feature activation+0.257
your
Token your
Feature activation+0.000
taxes
Token taxes
Feature activation+0.809
."
Token."
Feature activation+0.488
Ċ
TokenĊ
Feature activation+0.275
Ċ
TokenĊ
Feature activation+0.101
Bur
TokenBur
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
afford
Token afford
Feature activation+0.000
the
Token the
Feature activation+0.000
tuition
Token tuition
Feature activation+0.807
after
Token after
Feature activation+0.659
the
Token the
Feature activation+0.533
first
Token first
Feature activation+0.307
year
Token year
Feature activation+0.458
and
Token and
Feature activation+0.283
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
UK
Token UK
Feature activation+0.000
VAT
Token VAT
Feature activation+0.487
rate
Token rate
Feature activation+1.347
of
Token of
Feature activation+1.154
20
Token 20
Feature activation+0.794
%
Token%
Feature activation+0.443
and
Token and
Feature activation+0.189
a
Token a
Feature activation+0.000
modified
Token modified
Feature activation+0.000
per
Token per
Feature activation+0.000
issue
Token issue
Feature activation+0.000
:
Token:
Feature activation+0.000
Can
Token Can
Feature activation+0.000
tax
Token tax
Feature activation+0.507
cuts
Token cuts
Feature activation+0.629
pay
Token pay
Feature activation+0.784
for
Token for
Feature activation+0.641
themselves
Token themselves
Feature activation+0.358
?
Token?
Feature activation+0.265
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
increase
Token increase
Feature activation+0.214
indexed
Token indexed
Feature activation+0.534
to
Token to
Feature activation+0.207
the
Token the
Feature activation+0.259
projected
Token projected
Feature activation+0.284
inflation
Token inflation
Feature activation+0.771
rate
Token rate
Feature activation+0.708
--
Token --
Feature activation+0.465
4
Token 4
Feature activation+0.202
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Yes
TokenYes
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
unemployment
Token unemployment
Feature activation+0.504
rate
Token rate
Feature activation+0.760
in
Token in
Feature activation+0.841
California
Token California
Feature activation+0.671
was
Token was
Feature activation+0.292
a
Token a
Feature activation+0.081
terrible
Token terrible
Feature activation+0.000
and
Token and
Feature activation+0.000
Crystal
Token Crystal
Feature activation+0.000
Scar
Token Scar
Feature activation+0.000
the
Token the
Feature activation+0.000
gold
Token gold
Feature activation+0.000
income
Token income
Feature activation+0.760
is
Token is
Feature activation+0.465
increased
Token increased
Feature activation+0.482
size
Token size
Feature activation+0.422
ably
Tokenably
Feature activation+0.322
to
Token to
Feature activation+0.069
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
15
Token 15
Feature activation+0.163
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+0.000
20
Token 20
Feature activation+0.000

Top DFA by src position
MAX = 1.029

<|endoftext|>
Token<|endoftext|>
Feature activation-0.113
Top resid features:
gross
Token gross
Feature activation+0.059
Top resid features:
national
Token national
Feature activation+0.112
Top resid features:
debt
Token debt
Feature activation+0.574
Top resid features:
to
Token to
Feature activation-0.109
Top resid features:
GDP
Token GDP
Feature activation+1.029
Top resid features:
ratio
Token ratio
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Cyprus
Token Cyprus
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
99
Token 99
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.086
Top resid features:
gross
Token gross
Feature activation+0.072
Top resid features:
national
Token national
Feature activation+0.092
Top resid features:
debt
Token debt
Feature activation+0.380
Top resid features:
to
Token to
Feature activation-0.182
Top resid features:
GDP
Token GDP
Feature activation+0.679
Top resid features:
ratio
Token ratio
Feature activation+0.497
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Cyprus
Token Cyprus
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
99
Token 99
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.063
Top resid features:
have
Token have
Feature activation-0.017
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
pay
Token pay
Feature activation+0.234
Top resid features:
taxes
Token taxes
Feature activation+0.885
Top resid features:
on
Token on
Feature activation-0.062
Top resid features:
money
Token money
Feature activation+0.395
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
withdraw
Token withdraw
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.080
Top resid features:
gross
Token gross
Feature activation+0.064
Top resid features:
national
Token national
Feature activation+0.066
Top resid features:
debt
Token debt
Feature activation+0.287
Top resid features:
to
Token to
Feature activation-0.043
Top resid features:
GDP
Token GDP
Feature activation+0.553
Top resid features:
ratio
Token ratio
Feature activation+0.304
Top resid features:
of
Token of
Feature activation-0.160
Top resid features:
Cyprus
Token Cyprus
Feature activation+0.248
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
99
Token 99
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
capital
Token capital
Feature activation+0.099
Top resid features:
gains
Token gains
Feature activation+0.215
Top resid features:
and
Token and
Feature activation-0.124
Top resid features:
dividend
Token dividend
Feature activation+0.238
Top resid features:
tax
Token tax
Feature activation+0.370
Top resid features:
rates
Token rates
Feature activation+0.346
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
increasing
Token increasing
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.078
Top resid features:
have
Token have
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
pay
Token pay
Feature activation+0.285
Top resid features:
taxes
Token taxes
Feature activation+1.019
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
money
Token money
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
withdraw
Token withdraw
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.078
Top resid features:
gross
Token gross
Feature activation+0.060
Top resid features:
national
Token national
Feature activation+0.077
Top resid features:
debt
Token debt
Feature activation+0.306
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
GDP
Token GDP
Feature activation+0.669
Top resid features:
ratio
Token ratio
Feature activation+0.250
Top resid features:
of
Token of
Feature activation-0.085
Top resid features:
Cyprus
Token Cyprus
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
99
Token 99
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
capital
Token capital
Feature activation+0.109
Top resid features:
gains
Token gains
Feature activation+0.279
Top resid features:
and
Token and
Feature activation-0.155
Top resid features:
dividend
Token dividend
Feature activation+0.276
Top resid features:
tax
Token tax
Feature activation+0.524
Top resid features:
rates
Token rates
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
increasing
Token increasing
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.021
Top resid features:
commercial
Token commercial
Feature activation+0.056
Top resid features:
and
Token and
Feature activation-0.131
Top resid features:
residential
Token residential
Feature activation+0.022
Top resid features:
tax
Token tax
Feature activation+0.550
Top resid features:
rates
Token rates
Feature activation+0.570
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
addition
Token addition
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
programs
Token programs
Feature activation+0.130
Top resid features:
with
Token with
Feature activation-0.098
Top resid features:
an
Token an
Feature activation-0.060
Top resid features:
annual
Token annual
Feature activation+0.147
Top resid features:
cash
Token cash
Feature activation+0.406
Top resid features:
payment
Token payment
Feature activation+0.466
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
adult
Token adult
Feature activation+0.000
Top resid features:
resident
Token resident
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.105
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
Yes
TokenYes
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
unemployment
Token unemployment
Feature activation+0.697
Top resid features:
rate
Token rate
Feature activation+0.581
Top resid features:
in
Token in
Feature activation-0.100
Top resid features:
California
Token California
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.007
Top resid features:
economic
Token economic
Feature activation+0.334
Top resid features:
infrastructure
Token infrastructure
Feature activation+0.254
Top resid features:
and
Token and
Feature activation-0.140
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
debt
Token debt
Feature activation+0.728
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
wiped
Token wiped
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:
citizen
Token citizen
Feature activation+0.023
Top resid features:
is
Token is
Feature activation+0.037
Top resid features:
you
Token you
Feature activation-0.020
Top resid features:
pay
Token pay
Feature activation+0.261
Top resid features:
your
Token your
Feature activation-0.007
Top resid features:
taxes
Token taxes
Feature activation+0.826
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:
Bur
TokenBur
Feature activation+0.000
Top resid features:
ke
Tokenke
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.123
Top resid features:
could
Token could
Feature activation+0.064
Top resid features:
not
Token not
Feature activation-0.025
Top resid features:
afford
Token afford
Feature activation+0.237
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
tuition
Token tuition
Feature activation+0.859
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.098
Top resid features:
UK
Token UK
Feature activation-0.015
Top resid features:
VAT
Token VAT
Feature activation+0.580
Top resid features:
rate
Token rate
Feature activation+0.746
Top resid features:
of
Token of
Feature activation-0.135
Top resid features:
20
Token 20
Feature activation-0.034
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
issue
Token issue
Feature activation+0.015
Top resid features:
:
Token:
Feature activation+0.041
Top resid features:
Can
Token Can
Feature activation+0.002
Top resid features:
tax
Token tax
Feature activation+0.432
Top resid features:
cuts
Token cuts
Feature activation+0.179
Top resid features:
pay
Token pay
Feature activation+0.431
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
themselves
Token themselves
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
increase
Token increase
Feature activation+0.135
Top resid features:
indexed
Token indexed
Feature activation+0.276
Top resid features:
to
Token to
Feature activation-0.121
Top resid features:
the
Token the
Feature activation-0.039
Top resid features:
projected
Token projected
Feature activation-0.005
Top resid features:
inflation
Token inflation
Feature activation+0.554
Top resid features:
rate
Token rate
Feature activation+0.000
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
4
Token 4
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.118
Top resid features:
Ċ
TokenĊ
Feature activation-0.035
Top resid features:
Yes
TokenYes
Feature activation-0.074
Top resid features:
,
Token,
Feature activation-0.082
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
unemployment
Token unemployment
Feature activation+0.651
Top resid features:
rate
Token rate
Feature activation+0.650
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
California
Token California
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.075
Top resid features:
Crystal
Token Crystal
Feature activation-0.078
Top resid features:
Scar
Token Scar
Feature activation-0.031
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
gold
Token gold
Feature activation+0.250
Top resid features:
income
Token income
Feature activation+1.003
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
increased
Token increased
Feature activation+0.000
Top resid features:
size
Token size
Feature activation+0.000
Top resid features:
ably
Tokenably
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
capital
Token capital
Feature activation+0.090
Top resid features:
gains
Token gains
Feature activation+0.134
Top resid features:
and
Token and
Feature activation-0.088
Top resid features:
dividend
Token dividend
Feature activation+0.217
Top resid features:
tax
Token tax
Feature activation+0.299
Top resid features:
rates
Token rates
Feature activation+0.215
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
increasing
Token increasing
Feature activation+0.083
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.05

Head 3: 0.05

Head 4: 0.04

Head 5: 0.05

Head 6: 0.07

Head 7: 0.20

Head 8: 0.06

Head 9: 0.09

Head 10: 0.18

Head 11: 0.10

Positive logits

``(1.01

salaries1.00

Fiscal0.96

NAFTA0.95

Fees0.95

payer0.95

ierrez0.94

accrued0.93

osate0.93

discretionary0.90

Medicare0.89

payable0.88

pensions0.88

quotas0.88

PACs0.87

issued0.87

levied0.87

fees0.87

negotiated0.86

USPS0.85

Negative logits

rooft-0.96

dit-0.94

torch-0.92

scenes-0.91

emonium-0.91

demonic-0.90

rypt-0.90

coli-0.90

atsuki-0.88

alleg-0.86

regenerate-0.86

footsteps-0.86

uminati-0.83

repent-0.82

tons-0.81

dracon-0.81

azo-0.81

Demonic-0.80

hack-0.80

rypted-0.80

INTERVAL 1.246 - 1.384
CONTAINS 0.000%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
gross
Token gross
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216

INTERVAL 1.108 - 1.246
CONTAINS 0.000%

gross
Token gross
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
.
Token.
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.155
taxes
Token taxes
Feature activation+1.384
on
Token on
Feature activation+0.965
money
Token money
Feature activation+1.116
they
Token they
Feature activation+0.692
withdraw
Token withdraw
Feature activation+0.589
from
Token from
Feature activation+0.259
a
Token a
Feature activation+0.185
Roth
Token Roth
Feature activation+0.289

INTERVAL 0.969 - 1.108
CONTAINS 0.000%

debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
%
Token%
Feature activation+0.000
capital
Token capital
Feature activation+0.049
gains
Token gains
Feature activation+0.221
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
15
Token 15
Feature activation+0.163
percent
Token percent
Feature activation+0.000

INTERVAL 0.831 - 0.969
CONTAINS 0.001%

between
Token between
Feature activation+0.000
commercial
Token commercial
Feature activation+0.226
and
Token and
Feature activation+0.111
residential
Token residential
Feature activation+0.092
tax
Token tax
Feature activation+0.732
rates
Token rates
Feature activation+0.896
.
Token.
Feature activation+0.693
In
Token In
Feature activation+0.384
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
New
Token New
Feature activation+0.000
programs
Token programs
Feature activation+0.029
with
Token with
Feature activation+0.041
an
Token an
Feature activation+0.000
annual
Token annual
Feature activation+0.003
cash
Token cash
Feature activation+0.628
payment
Token payment
Feature activation+0.848
to
Token to
Feature activation+0.648
every
Token every
Feature activation+0.568
adult
Token adult
Feature activation+0.399
resident
Token resident
Feature activation+0.000
.
Token.
Feature activation+0.000
Yes
TokenYes
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
unemployment
Token unemployment
Feature activation+0.504
rate
Token rate
Feature activation+0.760
in
Token in
Feature activation+0.841
California
Token California
Feature activation+0.671
was
Token was
Feature activation+0.292
a
Token a
Feature activation+0.081
terrible
Token terrible
Feature activation+0.000
11
Token 11
Feature activation+0.000
national
Token national
Feature activation+0.000
debt
Token debt
Feature activation+0.958
to
Token to
Feature activation+0.659
GDP
Token GDP
Feature activation+1.302
ratio
Token ratio
Feature activation+1.202
of
Token of
Feature activation+0.915
Cyprus
Token Cyprus
Feature activation+0.990
was
Token was
Feature activation+0.554
99
Token 99
Feature activation+0.216
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.155
taxes
Token taxes
Feature activation+1.384
on
Token on
Feature activation+0.965
money
Token money
Feature activation+1.116
they
Token they
Feature activation+0.692
withdraw
Token withdraw
Feature activation+0.589
from
Token from
Feature activation+0.259
a
Token a
Feature activation+0.185

INTERVAL 0.692 - 0.831
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
afford
Token afford
Feature activation+0.000
the
Token the
Feature activation+0.000
tuition
Token tuition
Feature activation+0.807
after
Token after
Feature activation+0.659
the
Token the
Feature activation+0.533
first
Token first
Feature activation+0.307
year
Token year
Feature activation+0.458
and
Token and
Feature activation+0.283
issue
Token issue
Feature activation+0.000
:
Token:
Feature activation+0.000
Can
Token Can
Feature activation+0.000
tax
Token tax
Feature activation+0.507
cuts
Token cuts
Feature activation+0.629
pay
Token pay
Feature activation+0.784
for
Token for
Feature activation+0.641
themselves
Token themselves
Feature activation+0.358
?
Token?
Feature activation+0.265
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
gains
Token gains
Feature activation+0.221
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
15
Token 15
Feature activation+0.163
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
15
Token 15
Feature activation+0.163
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+0.000
20
Token 20
Feature activation+0.000
indexed
Token indexed
Feature activation+0.534
to
Token to
Feature activation+0.207
the
Token the
Feature activation+0.259
projected
Token projected
Feature activation+0.284
inflation
Token inflation
Feature activation+0.771
rate
Token rate
Feature activation+0.708
--
Token --
Feature activation+0.465
4
Token 4
Feature activation+0.202
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
percent
Token percent
Feature activation+0.000

INTERVAL 0.554 - 0.692
CONTAINS 0.007%

less
Token less
Feature activation+0.269
money
Token money
Feature activation+0.633
after
Token after
Feature activation+0.549
Uber
Token Uber
Feature activation+0.421
cut
Token cut
Feature activation+0.285
fares
Token fares
Feature activation+0.600
.
Token.
Feature activation+0.365
âĢ
Token âĢ
Feature activation+0.062
ľ
Tokenľ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
people
Token people
Feature activation+0.000
long
Token long
Feature activation+0.000
periods
Token periods
Feature activation+0.000
of
Token of
Feature activation+0.000
sustained
Token sustained
Feature activation+0.000
economic
Token economic
Feature activation+0.395
growth
Token growth
Feature activation+0.605
âĢĶ
TokenâĢĶ
Feature activation+0.276
the
Tokenthe
Feature activation+0.158
"
Token "
Feature activation+0.000
seven
Tokenseven
Feature activation+0.000
fat
Token fat
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
updated
Token updated
Feature activation+0.000
resume
Token resume
Feature activation+0.000
with
Token with
Feature activation+0.000
salary
Token salary
Feature activation+0.609
requirements
Token requirements
Feature activation+0.595
to
Token to
Feature activation+0.507
ste
Token ste
Feature activation+0.552
ve
Tokenve
Feature activation+0.000
@
Token@
Feature activation+0.000
in
Tokenin
Feature activation+0.000
that
Token that
Feature activation+0.000
raising
Token raising
Feature activation+0.000
the
Token the
Feature activation+0.000
minimum
Token minimum
Feature activation+0.122
federal
Token federal
Feature activation+0.287
rate
Token rate
Feature activation+0.665
to
Token to
Feature activation+0.523
$
Token $
Feature activation+0.513
10
Token10
Feature activation+0.100
.
Token.
Feature activation+0.036
10
Token10
Feature activation+0.000
the
Token the
Feature activation+0.000
individual
Token individual
Feature activation+0.000
market
Token market
Feature activation+0.000
,
Token,
Feature activation+0.000
increase
Token increase
Feature activation+0.072
premiums
Token premiums
Feature activation+0.640
,
Token,
Feature activation+0.454
and
Token and
Feature activation+0.281
result
Token result
Feature activation+0.061
in
Token in
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000

INTERVAL 0.415 - 0.554
CONTAINS 0.013%

the
Token the
Feature activation+0.000
minimum
Token minimum
Feature activation+0.122
federal
Token federal
Feature activation+0.287
rate
Token rate
Feature activation+0.665
to
Token to
Feature activation+0.523
$
Token $
Feature activation+0.513
10
Token10
Feature activation+0.100
.
Token.
Feature activation+0.036
10
Token10
Feature activation+0.000
would
Token would
Feature activation+0.000
raise
Token raise
Feature activation+0.014
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
earning
Token earning
Feature activation+0.225
less
Token less
Feature activation+0.269
money
Token money
Feature activation+0.633
after
Token after
Feature activation+0.549
Uber
Token Uber
Feature activation+0.421
cut
Token cut
Feature activation+0.285
fares
Token fares
Feature activation+0.600
.
Token.
Feature activation+0.365
âĢ
Token âĢ
Feature activation+0.062
,
Token,
Feature activation+0.118
who
Token who
Feature activation+0.000
further
Token further
Feature activation+0.000
glut
Token glut
Feature activation+0.096
labor
Token labor
Feature activation+0.262
markets
Token markets
Feature activation+0.427
,
Token,
Feature activation+0.176
meaning
Token meaning
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
employer
Token employer
Feature activation+0.087
profit
Token profit
Feature activation+0.063
legislation
Token legislation
Feature activation+0.000
,
Token,
Feature activation+0.000
capital
Token capital
Feature activation+0.049
gains
Token gains
Feature activation+0.221
and
Token and
Feature activation+0.194
dividend
Token dividend
Feature activation+0.506
tax
Token tax
Feature activation+0.898
rates
Token rates
Feature activation+0.971
are
Token are
Feature activation+0.743
increasing
Token increasing
Feature activation+0.748
from
Token from
Feature activation+0.350
complained
Token complained
Feature activation+0.000
about
Token about
Feature activation+0.000
having
Token having
Feature activation+0.000
jobs
Token jobs
Feature activation+0.002
and
Token and
Feature activation+0.000
income
Token income
Feature activation+0.498
to
Token to
Feature activation+0.314
feed
Token feed
Feature activation+0.353
their
Token their
Feature activation+0.094
families
Token families
Feature activation+0.132
while
Token while
Feature activation+0.000

INTERVAL 0.277 - 0.415
CONTAINS 0.022%

will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
taxes
Token taxes
Feature activation+0.592
,
Token,
Feature activation+0.315
which
Token which
Feature activation+0.025
will
Token will
Feature activation+0.000
further
Token further
Feature activation+0.000
suppress
Token suppress
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Tokens
Feature activation+0.000
from
Token from
Feature activation+0.000
tuition
Token tuition
Feature activation+0.116
and
Token and
Feature activation+0.157
fees
Token fees
Feature activation+0.329
from
Token from
Feature activation+0.297
students
Token students
Feature activation+0.143
and
Token and
Feature activation+0.000
families
Token families
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
money
Token money
Feature activation+1.116
they
Token they
Feature activation+0.692
withdraw
Token withdraw
Feature activation+0.589
from
Token from
Feature activation+0.259
a
Token a
Feature activation+0.185
Roth
Token Roth
Feature activation+0.289
401
Token 401
Feature activation+0.155
(
Token(
Feature activation+0.000
k
Tokenk
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.097
prices
Token prices
Feature activation+0.268
for
Token for
Feature activation+0.419
two
Token two
Feature activation+0.335
-
Token-
Feature activation+0.260
bedroom
Tokenbedroom
Feature activation+0.327
units
Token units
Feature activation+0.316
starting
Token starting
Feature activation+0.259
in
Token in
Feature activation+0.057
the
Token the
Feature activation+0.000
low
Token low
Feature activation+0.000
$
Token $
Feature activation+0.000
"
Token"
Feature activation+0.000
than
Token than
Feature activation+0.000
off
Token off
Feature activation+0.000
of
Token of
Feature activation+0.000
ordinary
Token ordinary
Feature activation+0.000
income
Token income
Feature activation+0.414
.
Token.
Feature activation+0.133
The
Token The
Feature activation+0.000
question
Token question
Feature activation+0.000
is
Token is
Feature activation+0.000
hardly
Token hardly
Feature activation+0.000

INTERVAL 0.138 - 0.277
CONTAINS 0.046%

why
Token why
Feature activation+0.000
Mod
Token Mod
Feature activation+0.000
P
Token P
Feature activation+0.000
odge
Tokenodge
Feature activation+0.000
costs
Token costs
Feature activation+0.087
more
Token more
Feature activation+0.225
than
Token than
Feature activation+0.308
craft
Token craft
Feature activation+0.000
glue
Token glue
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.000
jobs
Token jobs
Feature activation+0.198
they
Token they
Feature activation+0.024
generate
Token generate
Feature activation+0.173
in
Token in
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
'
Token'
Feature activation+0.000
districts
Token districts
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
for
Token for
Feature activation+0.000
network
Token network
Feature activation+0.000
database
Token database
Feature activation+0.058
storage
Token storage
Feature activation+0.192
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
implementing
Token implementing
Feature activation+0.000
a
Token a
Feature activation+0.000
simplified
Token simplified
Feature activation+0.000
-
Token-
Feature activation+0.000
bank
Tokenbank
Feature activation+0.000
rupt
Tokenrupt
Feature activation+0.000
cy
Tokency
Feature activation+0.033
of
Token of
Feature activation+0.025
Greece
Token Greece
Feature activation+0.217
âĢ¦
TokenâĢ¦
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
massive
Token massive
Feature activation+0.000
migration
Token migration
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
visa
Token visa
Feature activation+0.043
lottery
Token lottery
Feature activation+0.268
;
Token;
Feature activation+0.194
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
Mand
Token Mand
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
employer
Token employer
Feature activation+0.003

INTERVAL 0.000 - 0.138
CONTAINS 99.908%

bug
Token bug
Feature activation+0.000
le
Tokenle
Feature activation+0.000
call
Token call
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
dog
Token dog
Feature activation+0.000
was
Token was
Feature activation+0.000
named
Token named
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
call
Token call
Feature activation+0.000
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
"
Token "
Feature activation+0.000
as
Tokenas
Feature activation+0.000
long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
May
TokenMay
Feature activation+0.000
their
Token their
Feature activation+0.000
number
Token number
Feature activation+0.000
increase
Token increase
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
s
Tokens
Feature activation+0.000
website
Token website
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
i
Tokeni
Feature activation+0.000
am
Token am
Feature activation+0.000
done
Token done
Feature activation+0.000
.
Token.
Feature activation+0.000
i
Tokeni
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
city
Token city
Feature activation+0.000
--
Token --
Feature activation+0.000
for
Token for
Feature activation+0.000
instance
Token instance
Feature activation+0.000
,
Token,
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
community
Token community
Feature activation+0.000
with
Token with
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 H2.7: (feature 23631)

TOP ACTIVATIONS
MAX = 1.699

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
over
Token over
Feature activation+0.000
North
Token North
Feature activation+0.000
Africa
Token Africa
Feature activation+0.837
,
Token,
Feature activation+0.648
Italy
Token Italy
Feature activation+1.592
,
Token,
Feature activation+1.026
France
Token France
Feature activation+1.370
and
Token and
Feature activation+0.774
Germany
Token Germany
Feature activation+1.021
,
Token,
Feature activation+0.613
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
internet
Token internet
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Czech
Token Czech
Feature activation+1.175
Republic
Token Republic
Feature activation+1.579
,
Token,
Feature activation+1.168
Mr
Token Mr
Feature activation+1.000
He
Token He
Feature activation+0.732
ger
Tokenger
Feature activation+0.467
said
Token said
Feature activation+0.137
disconnected
Token disconnected
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+1.114
-
Token-
Feature activation+1.290
Israeli
TokenIsraeli
Feature activation+1.577
reality
Token reality
Feature activation+1.280
,"
Token,"
Feature activation+0.890
"
Token"
Feature activation+0.362
he
Token he
Feature activation+0.233
said
Token said
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
of
Token of
Feature activation+0.000
Russian
Token Russian
Feature activation+1.121
president
Token president
Feature activation+0.935
Vladimir
Token Vladimir
Feature activation+1.376
Putin
Token Putin
Feature activation+1.565
.
Token.
Feature activation+1.195
Ċ
TokenĊ
Feature activation+0.664
Ċ
TokenĊ
Feature activation+0.417
P
TokenP
Feature activation+0.344
onom
Tokenonom
Feature activation+0.156
the
Token the
Feature activation+0.000
border
Token border
Feature activation+0.000
of
Token of
Feature activation+0.000
Lebanon
Token Lebanon
Feature activation+1.186
and
Token and
Feature activation+0.972
Syria
Token Syria
Feature activation+1.465
,
Token,
Feature activation+1.080
while
Token while
Feature activation+0.768
the
Token the
Feature activation+0.464
Turkish
Token Turkish
Feature activation+1.142
police
Token police
Feature activation+0.634
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Israel
Token Israel
Feature activation+0.716
in
Token in
Feature activation+0.671
the
Token the
Feature activation+0.493
occupied
Token occupied
Feature activation+0.601
Palestinian
Token Palestinian
Feature activation+1.414
territory
Token territory
Feature activation+1.294
has
Token has
Feature activation+1.019
become
Token become
Feature activation+0.860
increasingly
Token increasingly
Feature activation+0.721
institutional
Token institutional
Feature activation+0.630
private
Token private
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
of
Token of
Feature activation+0.000
Russian
Token Russian
Feature activation+1.121
president
Token president
Feature activation+0.935
Vladimir
Token Vladimir
Feature activation+1.376
Putin
Token Putin
Feature activation+1.565
.
Token.
Feature activation+1.195
Ċ
TokenĊ
Feature activation+0.664
Ċ
TokenĊ
Feature activation+0.417
P
TokenP
Feature activation+0.344
North
Token North
Feature activation+0.000
Africa
Token Africa
Feature activation+0.837
,
Token,
Feature activation+0.648
Italy
Token Italy
Feature activation+1.592
,
Token,
Feature activation+1.026
France
Token France
Feature activation+1.370
and
Token and
Feature activation+0.774
Germany
Token Germany
Feature activation+1.021
,
Token,
Feature activation+0.613
three
Token three
Feature activation+0.408
confirmed
Token confirmed
Feature activation+0.102
caption
Token caption
Feature activation+0.000
Germany
Token Germany
Feature activation+1.129
's
Token's
Feature activation+0.763
Chancellor
Token Chancellor
Feature activation+0.767
Angela
Token Angela
Feature activation+0.963
Merkel
Token Merkel
Feature activation+1.339
says
Token says
Feature activation+0.765
EU
Token EU
Feature activation+0.908
leaders
Token leaders
Feature activation+0.473
have
Token have
Feature activation+0.229
taken
Token taken
Feature activation+0.235
if
Token if
Feature activation+0.000
abducted
Token abducted
Feature activation+0.000
Eston
Token Eston
Feature activation+0.786
ian
Tokenian
Feature activation+0.916
official
Token official
Feature activation+0.739
Eston
Token Eston
Feature activation+1.306
Koh
Token Koh
Feature activation+1.068
ver
Tokenver
Feature activation+1.184
is
Token is
Feature activation+0.709
released
Token released
Feature activation+0.388
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
s
Tokens
Feature activation+0.000
hosts
Token hosts
Feature activation+0.000
,
Token,
Feature activation+0.000
Czech
Token Czech
Feature activation+1.013
Republic
Token Republic
Feature activation+1.296
.
Token.
Feature activation+1.146
Two
Token Two
Feature activation+0.671
goals
Token goals
Feature activation+0.356
for
Token for
Feature activation+0.128
Canada
Token Canada
Feature activation+0.309
Israel
Token Israel
Feature activation+0.716
in
Token in
Feature activation+0.671
the
Token the
Feature activation+0.493
occupied
Token occupied
Feature activation+0.601
Palestinian
Token Palestinian
Feature activation+1.414
territory
Token territory
Feature activation+1.294
has
Token has
Feature activation+1.019
become
Token become
Feature activation+0.860
increasingly
Token increasingly
Feature activation+0.721
institutional
Token institutional
Feature activation+0.630
ized
Tokenized
Feature activation+0.285
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
disconnected
Token disconnected
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+1.114
-
Token-
Feature activation+1.290
Israeli
TokenIsraeli
Feature activation+1.577
reality
Token reality
Feature activation+1.280
,"
Token,"
Feature activation+0.890
"
Token"
Feature activation+0.362
he
Token he
Feature activation+0.233
Javier
Token Javier
Feature activation+1.076
Esp
Token Esp
Feature activation+1.100
in
Tokenin
Feature activation+0.945
osa
Tokenosa
Feature activation+0.964
and
Token and
Feature activation+0.724
Spanish
Token Spanish
Feature activation+1.281
freelance
Token freelance
Feature activation+0.792
photographer
Token photographer
Feature activation+0.548
Ricardo
Token Ricardo
Feature activation+0.658
Garcia
Token Garcia
Feature activation+0.642
Vil
Token Vil
Feature activation+0.745
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+1.114
-
Token-
Feature activation+1.290
Israeli
TokenIsraeli
Feature activation+1.577
reality
Token reality
Feature activation+1.280
,"
Token,"
Feature activation+0.890
"
Token"
Feature activation+0.362
he
Token he
Feature activation+0.233
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
by
Token by
Feature activation+0.000
Saudi
Token Saudi
Feature activation+1.033
Arabia
Token Arabia
Feature activation+1.254
.
Token.
Feature activation+0.987
The
Token The
Feature activation+0.684
Saudis
Token Saudis
Feature activation+1.268
were
Token were
Feature activation+0.839
reported
Token reported
Feature activation+0.583
to
Token to
Feature activation+0.210
have
Token have
Feature activation+0.026
approved
Token approved
Feature activation+0.000
in
Token in
Feature activation+0.000
India
Token India
Feature activation+0.631
,
Token,
Feature activation+0.394
Pakistan
Token Pakistan
Feature activation+1.384
,
Token,
Feature activation+0.962
Sri
Token Sri
Feature activation+1.214
Lanka
Token Lanka
Feature activation+1.200
,
Token,
Feature activation+0.812
Somalia
Token Somalia
Feature activation+1.051
,
Token,
Feature activation+0.558
Australia
Token Australia
Feature activation+0.183
India
Token India
Feature activation+0.631
,
Token,
Feature activation+0.394
Pakistan
Token Pakistan
Feature activation+1.384
,
Token,
Feature activation+0.962
Sri
Token Sri
Feature activation+1.214
Lanka
Token Lanka
Feature activation+1.200
,
Token,
Feature activation+0.812
Somalia
Token Somalia
Feature activation+1.051
,
Token,
Feature activation+0.558
Australia
Token Australia
Feature activation+0.183
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
Russian
Token Russian
Feature activation+1.121
president
Token president
Feature activation+0.935
Vladimir
Token Vladimir
Feature activation+1.376
Putin
Token Putin
Feature activation+1.565
.
Token.
Feature activation+1.195
Ċ
TokenĊ
Feature activation+0.664
Ċ
TokenĊ
Feature activation+0.417
P
TokenP
Feature activation+0.344
onom
Tokenonom
Feature activation+0.156
aren
Tokenaren
Feature activation+0.153
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.000
former
Token former
Feature activation+0.000
President
Token President
Feature activation+0.000
Viktor
Token Viktor
Feature activation+0.526
Yanukovych
Token Yanukovych
Feature activation+1.192
was
Token was
Feature activation+0.870
removed
Token removed
Feature activation+0.518
from
Token from
Feature activation+0.373
power
Token power
Feature activation+0.000
at
Token at
Feature activation+0.000

Top DFA by src position
MAX = 1.606

<|endoftext|>
Token<|endoftext|>
Feature activation+0.011
Top resid features:
over
Token over
Feature activation+0.059
Top resid features:
North
Token North
Feature activation+0.113
Top resid features:
Africa
Token Africa
Feature activation+0.739
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
Italy
Token Italy
Feature activation+1.228
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
France
Token France
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Germany
Token Germany
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
internet
Token internet
Feature activation+0.065
Top resid features:
in
Token in
Feature activation-0.041
Top resid features:
the
Token the
Feature activation+0.156
Top resid features:
Czech
Token Czech
Feature activation+0.764
Top resid features:
Republic
Token Republic
Feature activation+1.216
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Mr
Token Mr
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
ger
Tokenger
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.014
Top resid features:
disconnected
Token disconnected
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.130
Top resid features:
Palestinian
Token Palestinian
Feature activation+1.064
Top resid features:
-
Token-
Feature activation-0.057
Top resid features:
Israeli
TokenIsraeli
Feature activation+1.021
Top resid features:
reality
Token reality
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
benefit
Token benefit
Feature activation+0.035
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
Russian
Token Russian
Feature activation+0.646
Top resid features:
president
Token president
Feature activation+0.270
Top resid features:
Vladimir
Token Vladimir
Feature activation+0.436
Top resid features:
Putin
Token Putin
Feature activation+0.714
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:
P
TokenP
Feature activation+0.000
Top resid features:
onom
Tokenonom
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
border
Token border
Feature activation+0.102
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
Lebanon
Token Lebanon
Feature activation+0.898
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
Syria
Token Syria
Feature activation+0.947
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Turkish
Token Turkish
Feature activation+0.000
Top resid features:
police
Token police
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.007
Top resid features:
Israel
Token Israel
Feature activation+0.507
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.089
Top resid features:
occupied
Token occupied
Feature activation+0.199
Top resid features:
Palestinian
Token Palestinian
Feature activation+1.209
Top resid features:
territory
Token territory
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
increasingly
Token increasingly
Feature activation+0.000
Top resid features:
institutional
Token institutional
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.020
Top resid features:
private
Token private
Feature activation+0.050
Top resid features:
benefit
Token benefit
Feature activation+0.032
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
Russian
Token Russian
Feature activation+0.849
Top resid features:
president
Token president
Feature activation+0.388
Top resid features:
Vladimir
Token Vladimir
Feature activation+0.650
Top resid features:
Putin
Token Putin
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.011
Top resid features:
over
Token over
Feature activation+0.030
Top resid features:
North
Token North
Feature activation+0.073
Top resid features:
Africa
Token Africa
Feature activation+0.433
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
Italy
Token Italy
Feature activation+0.770
Top resid features:
,
Token,
Feature activation-0.041
Top resid features:
France
Token France
Feature activation+0.671
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Germany
Token Germany
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
caption
Token caption
Feature activation+0.040
Top resid features:
Germany
Token Germany
Feature activation+0.524
Top resid features:
's
Token's
Feature activation+0.105
Top resid features:
Chancellor
Token Chancellor
Feature activation+0.226
Top resid features:
Angela
Token Angela
Feature activation+0.253
Top resid features:
Merkel
Token Merkel
Feature activation+0.808
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
EU
Token EU
Feature activation+0.000
Top resid features:
leaders
Token leaders
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
taken
Token taken
Feature activation+0.000
Top resid features:
if
Token if
Feature activation-0.038
Top resid features:
abducted
Token abducted
Feature activation+0.052
Top resid features:
Eston
Token Eston
Feature activation+0.465
Top resid features:
ian
Tokenian
Feature activation+0.355
Top resid features:
official
Token official
Feature activation+0.171
Top resid features:
Eston
Token Eston
Feature activation+0.586
Top resid features:
Koh
Token Koh
Feature activation+0.000
Top resid features:
ver
Tokenver
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
released
Token released
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.020
Top resid features:
hosts
Token hosts
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
Czech
Token Czech
Feature activation+0.799
Top resid features:
Republic
Token Republic
Feature activation+1.011
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Two
Token Two
Feature activation+0.000
Top resid features:
goals
Token goals
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Canada
Token Canada
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.011
Top resid features:
Israel
Token Israel
Feature activation+0.293
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.097
Top resid features:
occupied
Token occupied
Feature activation+0.175
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.773
Top resid features:
territory
Token territory
Feature activation+0.541
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
increasingly
Token increasingly
Feature activation+0.000
Top resid features:
institutional
Token institutional
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.029
Top resid features:
disconnected
Token disconnected
Feature activation+0.029
Top resid features:
from
Token from
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.120
Top resid features:
Palestinian
Token Palestinian
Feature activation+1.606
Top resid features:
-
Token-
Feature activation+0.048
Top resid features:
Israeli
TokenIsraeli
Feature activation+0.000
Top resid features:
reality
Token reality
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
Javier
Token Javier
Feature activation+0.332
Top resid features:
Esp
Token Esp
Feature activation+0.167
Top resid features:
in
Tokenin
Feature activation-0.014
Top resid features:
osa
Tokenosa
Feature activation+0.145
Top resid features:
and
Token and
Feature activation-0.028
Top resid features:
Spanish
Token Spanish
Feature activation+0.863
Top resid features:
freelance
Token freelance
Feature activation+0.000
Top resid features:
photographer
Token photographer
Feature activation+0.000
Top resid features:
Ricardo
Token Ricardo
Feature activation+0.000
Top resid features:
Garcia
Token Garcia
Feature activation+0.000
Top resid features:
Vil
Token Vil
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
Top resid features:
disconnected
Token disconnected
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.144
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.757
Top resid features:
-
Token-
Feature activation-0.043
Top resid features:
Israeli
TokenIsraeli
Feature activation+0.657
Top resid features:
reality
Token reality
Feature activation+0.331
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.024
Top resid features:
Saudi
Token Saudi
Feature activation+0.434
Top resid features:
Arabia
Token Arabia
Feature activation+0.374
Top resid features:
.
Token.
Feature activation-0.112
Top resid features:
The
Token The
Feature activation+0.159
Top resid features:
Saudis
Token Saudis
Feature activation+1.063
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
reported
Token reported
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
approved
Token approved
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.012
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
India
Token India
Feature activation+0.505
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
Pakistan
Token Pakistan
Feature activation+0.781
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
Sri
Token Sri
Feature activation+0.503
Top resid features:
Lanka
Token Lanka
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Somalia
Token Somalia
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
India
Token India
Feature activation+0.389
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
Pakistan
Token Pakistan
Feature activation+0.591
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Sri
Token Sri
Feature activation+0.259
Top resid features:
Lanka
Token Lanka
Feature activation+0.517
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Somalia
Token Somalia
Feature activation+0.000
Top resid features:
benefit
Token benefit
Feature activation+0.022
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Russian
Token Russian
Feature activation+0.524
Top resid features:
president
Token president
Feature activation+0.193
Top resid features:
Vladimir
Token Vladimir
Feature activation+0.445
Top resid features:
Putin
Token Putin
Feature activation+0.611
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
P
TokenP
Feature activation+0.000
Top resid features:
onom
Tokenonom
Feature activation+0.000
Top resid features:
ever
Token ever
Feature activation+0.019
Top resid features:
since
Token since
Feature activation+0.083
Top resid features:
former
Token former
Feature activation+0.057
Top resid features:
President
Token President
Feature activation+0.182
Top resid features:
Viktor
Token Viktor
Feature activation+0.397
Top resid features:
Yanukovych
Token Yanukovych
Feature activation+1.067
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
removed
Token removed
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.06

Head 2: 0.05

Head 3: 0.06

Head 4: 0.03

Head 5: 0.04

Head 6: 0.06

Head 7: 0.20

Head 8: 0.04

Head 9: 0.09

Head 10: 0.19

Head 11: 0.10

Positive logits

southeastern0.84

ön0.84

cair0.82

Shiite0.81

prus0.81

peninsula0.80

Benedict0.79

northern0.78

islands0.78

East0.77

outhern0.77

northwestern0.76

coast0.76

inav0.76

southwestern0.75

Southeast0.74

Naples0.74

western0.73

enes0.72

northeastern0.72

Negative logits

meta-0.82

feedback-0.81

Stard-0.78

Vaugh-0.77

adrenaline-0.77

-0.76

ACTION-0.76

expr-0.76

Aura-0.75

RUN-0.75

meter-0.75

lawy-0.73

Extras-0.72

binary-0.71

showc-0.71

mood-0.70

nit-0.69

antioxid-0.69

Holo-0.69

Yelp-0.69

INTERVAL 1.529 - 1.699
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
over
Token over
Feature activation+0.000
North
Token North
Feature activation+0.000
Africa
Token Africa
Feature activation+0.837
,
Token,
Feature activation+0.648
Italy
Token Italy
Feature activation+1.592
,
Token,
Feature activation+1.026
France
Token France
Feature activation+1.370
and
Token and
Feature activation+0.774
Germany
Token Germany
Feature activation+1.021
,
Token,
Feature activation+0.613
benefit
Token benefit
Feature activation+0.000
of
Token of
Feature activation+0.000
Russian
Token Russian
Feature activation+1.121
president
Token president
Feature activation+0.935
Vladimir
Token Vladimir
Feature activation+1.376
Putin
Token Putin
Feature activation+1.565
.
Token.
Feature activation+1.195
Ċ
TokenĊ
Feature activation+0.664
Ċ
TokenĊ
Feature activation+0.417
P
TokenP
Feature activation+0.344
onom
Tokenonom
Feature activation+0.156
disconnected
Token disconnected
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+1.114
-
Token-
Feature activation+1.290
Israeli
TokenIsraeli
Feature activation+1.577
reality
Token reality
Feature activation+1.280
,"
Token,"
Feature activation+0.890
"
Token"
Feature activation+0.362
he
Token he
Feature activation+0.233
said
Token said
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
internet
Token internet
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Czech
Token Czech
Feature activation+1.175
Republic
Token Republic
Feature activation+1.579
,
Token,
Feature activation+1.168
Mr
Token Mr
Feature activation+1.000
He
Token He
Feature activation+0.732
ger
Tokenger
Feature activation+0.467
said
Token said
Feature activation+0.137

INTERVAL 1.359 - 1.529
CONTAINS 0.001%

North
Token North
Feature activation+0.000
Africa
Token Africa
Feature activation+0.837
,
Token,
Feature activation+0.648
Italy
Token Italy
Feature activation+1.592
,
Token,
Feature activation+1.026
France
Token France
Feature activation+1.370
and
Token and
Feature activation+0.774
Germany
Token Germany
Feature activation+1.021
,
Token,
Feature activation+0.613
three
Token three
Feature activation+0.408
confirmed
Token confirmed
Feature activation+0.102
private
Token private
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
of
Token of
Feature activation+0.000
Russian
Token Russian
Feature activation+1.121
president
Token president
Feature activation+0.935
Vladimir
Token Vladimir
Feature activation+1.376
Putin
Token Putin
Feature activation+1.565
.
Token.
Feature activation+1.195
Ċ
TokenĊ
Feature activation+0.664
Ċ
TokenĊ
Feature activation+0.417
P
TokenP
Feature activation+0.344
the
Token the
Feature activation+0.000
border
Token border
Feature activation+0.000
of
Token of
Feature activation+0.000
Lebanon
Token Lebanon
Feature activation+1.186
and
Token and
Feature activation+0.972
Syria
Token Syria
Feature activation+1.465
,
Token,
Feature activation+1.080
while
Token while
Feature activation+0.768
the
Token the
Feature activation+0.464
Turkish
Token Turkish
Feature activation+1.142
police
Token police
Feature activation+0.634
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Israel
Token Israel
Feature activation+0.716
in
Token in
Feature activation+0.671
the
Token the
Feature activation+0.493
occupied
Token occupied
Feature activation+0.601
Palestinian
Token Palestinian
Feature activation+1.414
territory
Token territory
Feature activation+1.294
has
Token has
Feature activation+1.019
become
Token become
Feature activation+0.860
increasingly
Token increasingly
Feature activation+0.721
institutional
Token institutional
Feature activation+0.630

INTERVAL 1.189 - 1.359
CONTAINS 0.004%

if
Token if
Feature activation+0.000
abducted
Token abducted
Feature activation+0.000
Eston
Token Eston
Feature activation+0.786
ian
Tokenian
Feature activation+0.916
official
Token official
Feature activation+0.739
Eston
Token Eston
Feature activation+1.306
Koh
Token Koh
Feature activation+1.068
ver
Tokenver
Feature activation+1.184
is
Token is
Feature activation+0.709
released
Token released
Feature activation+0.388
in
Token in
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+1.114
-
Token-
Feature activation+1.290
Israeli
TokenIsraeli
Feature activation+1.577
reality
Token reality
Feature activation+1.280
,"
Token,"
Feature activation+0.890
"
Token"
Feature activation+0.362
he
Token he
Feature activation+0.233
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Javier
Token Javier
Feature activation+1.076
Esp
Token Esp
Feature activation+1.100
in
Tokenin
Feature activation+0.945
osa
Tokenosa
Feature activation+0.964
and
Token and
Feature activation+0.724
Spanish
Token Spanish
Feature activation+1.281
freelance
Token freelance
Feature activation+0.792
photographer
Token photographer
Feature activation+0.548
Ricardo
Token Ricardo
Feature activation+0.658
Garcia
Token Garcia
Feature activation+0.642
Vil
Token Vil
Feature activation+0.745
Israel
Token Israel
Feature activation+0.716
in
Token in
Feature activation+0.671
the
Token the
Feature activation+0.493
occupied
Token occupied
Feature activation+0.601
Palestinian
Token Palestinian
Feature activation+1.414
territory
Token territory
Feature activation+1.294
has
Token has
Feature activation+1.019
become
Token become
Feature activation+0.860
increasingly
Token increasingly
Feature activation+0.721
institutional
Token institutional
Feature activation+0.630
ized
Tokenized
Feature activation+0.285
India
Token India
Feature activation+0.631
,
Token,
Feature activation+0.394
Pakistan
Token Pakistan
Feature activation+1.384
,
Token,
Feature activation+0.962
Sri
Token Sri
Feature activation+1.214
Lanka
Token Lanka
Feature activation+1.200
,
Token,
Feature activation+0.812
Somalia
Token Somalia
Feature activation+1.051
,
Token,
Feature activation+0.558
Australia
Token Australia
Feature activation+0.183
,
Token,
Feature activation+0.000

INTERVAL 1.019 - 1.189
CONTAINS 0.008%

,
Token,
Feature activation+0.319
Belgium
Token Belgium
Feature activation+1.065
and
Token and
Feature activation+0.575
Sicily
Token Sicily
Feature activation+1.072
,
Token,
Feature activation+0.591
Italy
Token Italy
Feature activation+1.027
.
Token.
Feature activation+0.767
May
Token May
Feature activation+0.372
27
Token 27
Feature activation+0.274
,
Token,
Feature activation+0.080
2017
Token 2017
Feature activation+0.053
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
Russia
Token Russia
Feature activation+1.020
âĢ
TokenâĢ
Feature activation+0.934
Ļ
TokenĻ
Feature activation+0.654
s
Tokens
Feature activation+0.435
President
Token President
Feature activation+0.425
Vladimir
Token Vladimir
Feature activation+0.844
Qatar
Token Qatar
Feature activation+1.004
,
Token,
Feature activation+0.584
in
Token in
Feature activation+0.589
Cairo
Token Cairo
Feature activation+0.907
,
Token,
Feature activation+0.572
Egypt
Token Egypt
Feature activation+1.068
,
Token,
Feature activation+0.668
July
Token July
Feature activation+0.577
5
Token 5
Feature activation+0.375
,
Token,
Feature activation+0.321
2017
Token 2017
Feature activation+0.205
,
Token,
Feature activation+0.455
Rome
Token Rome
Feature activation+0.901
,
Token,
Feature activation+0.319
Belgium
Token Belgium
Feature activation+1.065
and
Token and
Feature activation+0.575
Sicily
Token Sicily
Feature activation+1.072
,
Token,
Feature activation+0.591
Italy
Token Italy
Feature activation+1.027
.
Token.
Feature activation+0.767
May
Token May
Feature activation+0.372
27
Token 27
Feature activation+0.274
leading
Token leading
Feature activation+0.000
the
Token the
Feature activation+0.000
southern
Token southern
Feature activation+0.185
Republic
Token Republic
Feature activation+0.462
of
Token of
Feature activation+0.177
Haiti
Token Haiti
Feature activation+1.032
and
Token and
Feature activation+0.796
Christ
Token Christ
Feature activation+0.583
ophe
Tokenophe
Feature activation+0.461
leading
Token leading
Feature activation+0.355
the
Token the
Feature activation+0.076

INTERVAL 0.849 - 1.019
CONTAINS 0.014%

the
Token the
Feature activation+0.493
occupied
Token occupied
Feature activation+0.601
Palestinian
Token Palestinian
Feature activation+1.414
territory
Token territory
Feature activation+1.294
has
Token has
Feature activation+1.019
become
Token become
Feature activation+0.860
increasingly
Token increasingly
Feature activation+0.721
institutional
Token institutional
Feature activation+0.630
ized
Tokenized
Feature activation+0.285
and
Token and
Feature activation+0.310
restrictive
Token restrictive
Feature activation+0.197
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
Italy
Token Italy
Feature activation+1.125
âĢ
TokenâĢ
Feature activation+0.971
Ļ
TokenĻ
Feature activation+0.671
s
Tokens
Feature activation+0.373
massive
Token massive
Feature activation+0.239
debt
Token debt
Feature activation+0.248
and
Token and
Feature activation+0.023
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
count
Token count
Feature activation+0.000
in
Token in
Feature activation+0.000
Uganda
Token Uganda
Feature activation+0.955
âĢ
TokenâĢ
Feature activation+0.712
Ļ
TokenĻ
Feature activation+0.491
s
Tokens
Feature activation+0.241
B
Token B
Feature activation+0.241
wind
Tokenwind
Feature activation+0.012
-
Token-
Feature activation+0.000
Saharan
TokenSaharan
Feature activation+0.218
Africa
Token Africa
Feature activation+1.112
such
Token such
Feature activation+1.109
as
Token as
Feature activation+0.633
Nam
Token Nam
Feature activation+0.857
ibia
Tokenibia
Feature activation+1.125
;
Token;
Feature activation+0.458
Poly
Token Poly
Feature activation+0.551
nesia
Tokennesia
Feature activation+0.375
).
Token).
Feature activation+0.183
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
half
Token half
Feature activation+0.000
the
Token the
Feature activation+0.000
Polish
Token Polish
Feature activation+0.984
striker
Token striker
Feature activation+0.720
came
Token came
Feature activation+0.404
off
Token off
Feature activation+0.265
second
Token second
Feature activation+0.000
best
Token best
Feature activation+0.000

INTERVAL 0.680 - 0.849
CONTAINS 0.024%

South
TokenSouth
Feature activation+0.009
Sudan
Token Sudan
Feature activation+1.149
's
Token's
Feature activation+0.987
President
Token President
Feature activation+1.024
Sal
Token Sal
Feature activation+0.985
va
Tokenva
Feature activation+0.757
Ki
Token Ki
Feature activation+0.641
ir
Tokenir
Feature activation+0.618
addresses
Token addresses
Feature activation+0.251
delegates
Token delegates
Feature activation+0.000
during
Token during
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
Madrid
Token Madrid
Feature activation+0.981
nearly
Token nearly
Feature activation+0.883
capital
Token capital
Feature activation+1.111
ized
Tokenized
Feature activation+0.844
on
Token on
Feature activation+0.623
that
Token that
Feature activation+0.317
in
Token in
Feature activation+0.188
the
Token the
Feature activation+0.189
seventh
Token seventh
Feature activation+0.003
Venezuelan
Token Venezuelan
Feature activation+1.173
President
Token President
Feature activation+1.189
Hugo
Token Hugo
Feature activation+1.416
Chavez
Token Chavez
Feature activation+1.699
sent
Token sent
Feature activation+1.080
troops
Token troops
Feature activation+0.771
to
Token to
Feature activation+0.320
seize
Token seize
Feature activation+0.290
oil
Token oil
Feature activation+0.081
service
Token service
Feature activation+0.000
companies
Token companies
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.562
President
Token President
Feature activation+0.472
Xi
Token Xi
Feature activation+0.853
Jinping
Token Jinping
Feature activation+0.780
during
Token during
Feature activation+0.614
the
Token the
Feature activation+0.356
recent
Token recent
Feature activation+0.168
National
Token National
Feature activation+0.183
Financial
Token Financial
Feature activation+0.004
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+1.171
foreign
Token foreign
Feature activation+1.283
office
Token office
Feature activation+0.832
reacted
Token reacted
Feature activation+0.458
to
Token to
Feature activation+0.207
the
Token the
Feature activation+0.172
India
Token India
Feature activation+0.510
's
Token's
Feature activation+0.159

INTERVAL 0.510 - 0.680
CONTAINS 0.040%

,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
captain
Token captain
Feature activation+0.000
of
Token of
Feature activation+0.000
Syria
Token Syria
Feature activation+0.525
âĢ
TokenâĢ
Feature activation+0.401
Ļ
TokenĻ
Feature activation+0.244
s
Tokens
Feature activation+0.045
national
Token national
Feature activation+0.000
youth
Token youth
Feature activation+0.000
largest
Token largest
Feature activation+0.000
economies
Token economies
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
China
TokenChina
Feature activation+0.560
on
Token on
Feature activation+0.301
Monday
Token Monday
Feature activation+0.076
launched
Token launched
Feature activation+0.201
a
Token a
Feature activation+0.101
complaint
Token complaint
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
branch
Token branch
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Egypt
Token Egypt
Feature activation+0.530
-
Token-
Feature activation+0.513
based
Tokenbased
Feature activation+0.299
Brotherhood
Token Brotherhood
Feature activation+0.494
.
Token.
Feature activation+0.366
But
Token But
Feature activation+0.116
in
Token in
Feature activation+0.000
Tel
Token Tel
Feature activation+0.276
Aviv
Token Aviv
Feature activation+1.081
,
Token,
Feature activation+0.728
and
Token and
Feature activation+0.568
officially
Token officially
Feature activation+0.516
does
Token does
Feature activation+0.297
not
Token not
Feature activation+0.100
recognize
Token recognize
Feature activation+0.084
Jerusalem
Token Jerusalem
Feature activation+0.617
as
Token as
Feature activation+0.141
ians
Tokenians
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.819
border
Token border
Feature activation+0.767
fence
Token fence
Feature activation+0.576
,
Token,
Feature activation+0.450
June
Token June
Feature activation+0.335
2
Token 2
Feature activation+0.169
,
Token,
Feature activation+0.048
2010
Token 2010
Feature activation+0.039

INTERVAL 0.340 - 0.510
CONTAINS 0.061%

apparently
Token apparently
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.000
Greece
Token Greece
Feature activation+0.361
quitting
Token quitting
Feature activation+0.077
the
Token the
Feature activation+0.000
currency
Token currency
Feature activation+0.076
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
calling
Token calling
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
removal
Token removal
Feature activation+0.000
of
Token of
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.405
settlements
Token settlements
Feature activation+0.308
and
Token and
Feature activation+0.302
a
Token a
Feature activation+0.192
right
Token right
Feature activation+0.081
of
Token of
Feature activation+0.000
of
Token of
Feature activation+0.000
Marxist
Token Marxist
Feature activation+0.096
Robert
Token Robert
Feature activation+0.000
Mug
Token Mug
Feature activation+0.311
abe
Tokenabe
Feature activation+0.783
".
Token".
Feature activation+0.498
The
Token The
Feature activation+0.271
energy
Token energy
Feature activation+0.191
monopol
Token monopol
Feature activation+0.015
ies
Tokenies
Feature activation+0.000
how
Token how
Feature activation+0.000
and
Token and
Feature activation+0.038
there
Token there
Feature activation+0.040
are
Token are
Feature activation+0.000
180
Token 180
Feature activation+0.000
million
Token million
Feature activation+0.000
Muslims
Token Muslims
Feature activation+0.389
in
Token in
Feature activation+0.086
India
Token India
Feature activation+0.604
);
Token);
Feature activation+0.263
mocked
Token mocked
Feature activation+0.010
a
Token a
Feature activation+0.000
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
Ukrainian
Token Ukrainian
Feature activation+0.903
Army
Token Army
Feature activation+0.708
Ċ
TokenĊ
Feature activation+0.588
Ċ
TokenĊ
Feature activation+0.409
In
TokenIn
Feature activation+0.398
P
Token P
Feature activation+0.031
isky
Tokenisky
Feature activation+0.000
,
Token,
Feature activation+0.000
combined
Token combined
Feature activation+0.000

INTERVAL 0.170 - 0.340
CONTAINS 0.105%

Xi
Token Xi
Feature activation+0.853
Jinping
Token Jinping
Feature activation+0.780
during
Token during
Feature activation+0.614
the
Token the
Feature activation+0.356
recent
Token recent
Feature activation+0.168
National
Token National
Feature activation+0.183
Financial
Token Financial
Feature activation+0.004
Work
Token Work
Feature activation+0.000
Conference
Token Conference
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
Daesh
Token Daesh
Feature activation+0.177
âĢ
TokenâĢ
Feature activation+0.172
Ļ
TokenĻ
Feature activation+0.051
s
Tokens
Feature activation+0.000
last
Token last
Feature activation+0.000
patch
Token patch
Feature activation+0.000
's
Token's
Feature activation+0.569
legislative
Token legislative
Feature activation+0.544
council
Token council
Feature activation+0.221
and
Token and
Feature activation+0.200
head
Token head
Feature activation+0.126
of
Token of
Feature activation+0.301
the
Token the
Feature activation+0.028
university
Token university
Feature activation+0.000
's
Token's
Feature activation+0.000
administrative
Token administrative
Feature activation+0.000
board
Token board
Feature activation+0.000
joy
Token joy
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+0.000
Turk
Token Turk
Feature activation+0.269
u
Tokenu
Feature activation+0.431
and
Token and
Feature activation+0.256
Helsinki
Token Helsinki
Feature activation+0.931
.
Token.
Feature activation+0.703
Ċ
TokenĊ
Feature activation+0.364
Ċ
TokenĊ
Feature activation+0.166
Anne
TokenAnne
Feature activation+0.007
citizens
Token citizens
Feature activation+0.032
.
Token.
Feature activation+0.157
In
Token In
Feature activation+0.058
Russia
Token Russia
Feature activation+0.692
it
Token it
Feature activation+0.287
is
Token is
Feature activation+0.258
particularly
Token particularly
Feature activation+0.043
popular
Token popular
Feature activation+0.000
amongst
Token amongst
Feature activation+0.000
night
Token night
Feature activation+0.000
watch
Token watch
Feature activation+0.000

INTERVAL 0.000 - 0.170
CONTAINS 99.742%

.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
this
Token this
Feature activation+0.000
coming
Token coming
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
who
Token who
Feature activation+0.000
loves
Token loves
Feature activation+0.000
to
Token to
Feature activation+0.000
turtle
Token turtle
Feature activation+0.000
while
Token while
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
will
Token will
Feature activation+0.000
sign
Token sign
Feature activation+0.000
off
Token off
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
version
Token version
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pitt
TokenPitt
Feature activation+0.000
sburgh
Tokensburgh
Feature activation+0.000
game
Token game
Feature activation+0.000
mattered
Token mattered
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
sense
Token sense
Feature activation+0.000
that
Token that
Feature activation+0.000
family
Token family
Feature activation+0.000
earnings
Token earnings
Feature activation+0.000
affect
Token affect
Feature activation+0.000
whether
Token whether
Feature activation+0.000
children
Token children
Feature activation+0.000
may
Token may
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
from
Token from
Feature activation+0.000
effective
Token effective
Feature activation+0.000
teachers
Token teachers
Feature activation+0.000
?
Token?
Feature activation+0.000
call
Token call
Feature activation+0.000
goes
Token goes
Feature activation+0.000
through
Token through
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
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
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
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
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
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
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.005
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.005
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.005
.
Token.
Feature activation+0.000
K
TokenK
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+0.005
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.005
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.005
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.005
.
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+0.005
.
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+0.005
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.005
.
Token.
Feature activation+0.000

Top feature 6 in H2.7: (feature 14150)

TOP ACTIVATIONS
MAX = 1.840

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
quasi
Token quasi
Feature activation+0.000
-
Token-
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.064
study
Token study
Feature activation+1.840
,
Token,
Feature activation+1.334
and
Token and
Feature activation+1.048
four
Token four
Feature activation+0.831
of
Token of
Feature activation+0.508
the
Token the
Feature activation+0.579
quasi
Token quasi
Feature activation+0.000
-
Token-
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.064
study
Token study
Feature activation+1.840
,
Token,
Feature activation+1.334
and
Token and
Feature activation+1.048
four
Token four
Feature activation+0.831
of
Token of
Feature activation+0.508
the
Token the
Feature activation+0.579
10
Token 10
Feature activation+0.529
),
Token),
Feature activation+0.000
lead
Token lead
Feature activation+0.000
author
Token author
Feature activation+0.252
of
Token of
Feature activation+0.258
the
Token the
Feature activation+0.299
study
Token study
Feature activation+1.325
.
Token.
Feature activation+1.178
âĢ
Token âĢ
Feature activation+0.872
ľ
Tokenľ
Feature activation+0.442
Over
TokenOver
Feature activation+0.519
the
Token the
Feature activation+0.494
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
educational
Token educational
Feature activation+0.000
attainment
Token attainment
Feature activation+0.000
study
Token study
Feature activation+1.308
(
Token (
Feature activation+0.910
of
Tokenof
Feature activation+0.651
almost
Token almost
Feature activation+0.426
107
Token 107
Feature activation+0.512
,
Token,
Feature activation+0.149
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
study
Token study
Feature activation+1.285
,
Token,
Feature activation+0.943
which
Token which
Feature activation+0.740
of
Token of
Feature activation+0.708
course
Token course
Feature activation+0.588
was
Token was
Feature activation+0.278
A
Token A
Feature activation+0.000
new
Token new
Feature activation+0.000
pale
Token pale
Feature activation+0.000
ocl
Tokenocl
Feature activation+0.000
imate
Tokenimate
Feature activation+0.308
study
Token study
Feature activation+1.211
has
Token has
Feature activation+0.923
recently
Token recently
Feature activation+0.853
found
Token found
Feature activation+0.914
that
Token that
Feature activation+0.682
levels
Token levels
Feature activation+0.525
lead
Token lead
Feature activation+0.000
author
Token author
Feature activation+0.252
of
Token of
Feature activation+0.258
the
Token the
Feature activation+0.299
study
Token study
Feature activation+1.325
.
Token.
Feature activation+1.178
âĢ
Token âĢ
Feature activation+0.872
ľ
Tokenľ
Feature activation+0.442
Over
TokenOver
Feature activation+0.519
the
Token the
Feature activation+0.494
next
Token next
Feature activation+0.298
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.582
survey
Token survey
Feature activation+1.152
did
Token did
Feature activation+0.949
not
Token not
Feature activation+0.661
have
Token have
Feature activation+0.371
an
Token an
Feature activation+0.292
adequate
Token adequate
Feature activation+0.176
-
Token-
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.064
study
Token study
Feature activation+1.840
,
Token,
Feature activation+1.334
and
Token and
Feature activation+1.048
four
Token four
Feature activation+0.831
of
Token of
Feature activation+0.508
the
Token the
Feature activation+0.579
10
Token 10
Feature activation+0.529
were
Token were
Feature activation+0.273
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
collaboration
Token collaboration
Feature activation+0.000
focused
Token focused
Feature activation+0.000
on
Token on
Feature activation+0.000
research
Token research
Feature activation+0.903
commercial
Token commercial
Feature activation+1.019
isation
Tokenisation
Feature activation+0.465
âĢĵ
Token âĢĵ
Feature activation+0.391
is
Token is
Feature activation+0.259
also
Token also
Feature activation+0.030
providing
Token providing
Feature activation+0.037
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
teams
Token teams
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
study
Token study
Feature activation+1.334
released
Token released
Feature activation+0.978
Tuesday
Token Tuesday
Feature activation+0.397
,
Token,
Feature activation+0.236
which
Token which
Feature activation+0.241
was
Token was
Feature activation+0.204
led
Token led
Feature activation+0.129
Objective
Token Objective
Feature activation+0.000
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
study
Token study
Feature activation+0.753
examined
Token examined
Feature activation+0.956
the
Token the
Feature activation+0.972
relations
Token relations
Feature activation+0.966
between
Token between
Feature activation+0.597
the
Token the
Feature activation+0.752
timing
Token timing
Feature activation+0.405
of
Token of
Feature activation+0.065
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
study
Token study
Feature activation+0.753
examined
Token examined
Feature activation+0.956
the
Token the
Feature activation+0.972
relations
Token relations
Feature activation+0.966
between
Token between
Feature activation+0.597
the
Token the
Feature activation+0.752
timing
Token timing
Feature activation+0.405
of
Token of
Feature activation+0.065
food
Token food
Feature activation+0.102
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
highlighted
Token highlighted
Feature activation+0.000
by
Token by
Feature activation+0.000
researchers
Token researchers
Feature activation+0.963
at
Token at
Feature activation+0.607
Massachusetts
Token Massachusetts
Feature activation+0.511
General
Token General
Feature activation+0.317
Hospital
Token Hospital
Feature activation+0.438
,
Token,
Feature activation+0.227
of
Token of
Feature activation+0.000
researchers
Token researchers
Feature activation+0.631
have
Token have
Feature activation+0.346
been
Token been
Feature activation+0.180
producing
Token producing
Feature activation+0.109
research
Token research
Feature activation+0.956
improving
Token improving
Feature activation+0.885
our
Token our
Feature activation+0.621
of
Token of
Feature activation+0.376
bisexual
Token bisexual
Feature activation+0.149
ity
Tokenity
Feature activation+0.113
.
Token.
Feature activation+0.000
Objective
Token Objective
Feature activation+0.000
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
study
Token study
Feature activation+0.753
examined
Token examined
Feature activation+0.956
the
Token the
Feature activation+0.972
relations
Token relations
Feature activation+0.966
between
Token between
Feature activation+0.597
the
Token the
Feature activation+0.752
timing
Token timing
Feature activation+0.405
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
study
Token study
Feature activation+0.953
was
Token was
Feature activation+0.673
published
Token published
Feature activation+0.650
in
Token in
Feature activation+0.591
the
Token the
Feature activation+0.595
prestigious
Token prestigious
Feature activation+0.511
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.582
survey
Token survey
Feature activation+1.152
did
Token did
Feature activation+0.949
not
Token not
Feature activation+0.661
have
Token have
Feature activation+0.371
an
Token an
Feature activation+0.292
adequate
Token adequate
Feature activation+0.176
sample
Token sample
Feature activation+0.625
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
study
Token study
Feature activation+1.285
,
Token,
Feature activation+0.943
which
Token which
Feature activation+0.740
of
Token of
Feature activation+0.708
course
Token course
Feature activation+0.588
was
Token was
Feature activation+0.278
funded
Token funded
Feature activation+0.324
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
authors
Tokenauthors
Feature activation+0.313
of
Token of
Feature activation+0.353
the
Token the
Feature activation+0.303
paper
Token paper
Feature activation+0.931
and
Token and
Feature activation+0.619
kind
Token kind
Feature activation+0.374
enough
Token enough
Feature activation+0.115
to
Token to
Feature activation+0.277
speak
Token speak
Feature activation+0.000

Top DFA by src position
MAX = 2.068

<|endoftext|>
Token<|endoftext|>
Feature activation-0.070
Top resid features:
quasi
Token quasi
Feature activation-0.050
Top resid features:
-
Token-
Feature activation-0.038
Top resid features:
exper
Tokenexper
Feature activation+0.170
Top resid features:
imental
Tokenimental
Feature activation+0.196
Top resid features:
study
Token study
Feature activation+2.068
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.039
Top resid features:
quasi
Token quasi
Feature activation-0.034
Top resid features:
-
Token-
Feature activation-0.012
Top resid features:
exper
Tokenexper
Feature activation+0.164
Top resid features:
imental
Tokenimental
Feature activation+0.207
Top resid features:
study
Token study
Feature activation+1.421
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
),
Token),
Feature activation-0.029
Top resid features:
lead
Token lead
Feature activation+0.108
Top resid features:
author
Token author
Feature activation+0.332
Top resid features:
of
Token of
Feature activation-0.090
Top resid features:
the
Token the
Feature activation-0.033
Top resid features:
study
Token study
Feature activation+1.477
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:
Over
TokenOver
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.041
Top resid features:
from
Token from
Feature activation-0.142
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
educational
Token educational
Feature activation+0.127
Top resid features:
attainment
Token attainment
Feature activation+0.264
Top resid features:
study
Token study
Feature activation+1.530
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
of
Tokenof
Feature activation+0.000
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
107
Token 107
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.032
Top resid features:
.
Token.
Feature activation-0.080
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
The
TokenThe
Feature activation-0.061
Top resid features:
study
Token study
Feature activation+1.847
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
A
Token A
Feature activation-0.039
Top resid features:
new
Token new
Feature activation-0.041
Top resid features:
pale
Token pale
Feature activation+0.112
Top resid features:
ocl
Tokenocl
Feature activation+0.059
Top resid features:
imate
Tokenimate
Feature activation+0.078
Top resid features:
study
Token study
Feature activation+1.496
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
recently
Token recently
Feature activation+0.000
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
levels
Token levels
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.002
Top resid features:
lead
Token lead
Feature activation+0.101
Top resid features:
author
Token author
Feature activation+0.350
Top resid features:
of
Token of
Feature activation-0.036
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
study
Token study
Feature activation+1.158
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Over
TokenOver
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.046
Top resid features:
because
Token because
Feature activation-0.044
Top resid features:
the
Token the
Feature activation-0.039
Top resid features:
Pew
Token Pew
Feature activation+0.158
Top resid features:
Research
Token Research
Feature activation+0.684
Top resid features:
survey
Token survey
Feature activation+0.876
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
adequate
Token adequate
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.019
Top resid features:
quasi
Token quasi
Feature activation+0.018
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
exper
Tokenexper
Feature activation+0.152
Top resid features:
imental
Tokenimental
Feature activation+0.168
Top resid features:
study
Token study
Feature activation+1.233
Top resid features:
,
Token,
Feature activation-0.092
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.032
Top resid features:
collaboration
Token collaboration
Feature activation+0.112
Top resid features:
focused
Token focused
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
research
Token research
Feature activation+1.202
Top resid features:
commercial
Token commercial
Feature activation+0.129
Top resid features:
isation
Tokenisation
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.016
Top resid features:
teams
Token teams
Feature activation+0.055
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
study
Token study
Feature activation+1.269
Top resid features:
released
Token released
Feature activation+0.134
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
hour
Token hour
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Objective
Token Objective
Feature activation+0.073
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
This
Token This
Feature activation-0.003
Top resid features:
study
Token study
Feature activation+0.902
Top resid features:
examined
Token examined
Feature activation+0.353
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
relations
Token relations
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
hour
Token hour
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Objective
Token Objective
Feature activation+0.044
Top resid features:
:
Token:
Feature activation-0.000
Top resid features:
This
Token This
Feature activation+0.012
Top resid features:
study
Token study
Feature activation+0.758
Top resid features:
examined
Token examined
Feature activation+0.454
Top resid features:
the
Token the
Feature activation-0.112
Top resid features:
relations
Token relations
Feature activation+0.190
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.010
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
as
Token as
Feature activation-0.013
Top resid features:
highlighted
Token highlighted
Feature activation+0.090
Top resid features:
by
Token by
Feature activation-0.114
Top resid features:
researchers
Token researchers
Feature activation+1.456
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Massachusetts
Token Massachusetts
Feature activation+0.000
Top resid features:
General
Token General
Feature activation+0.000
Top resid features:
Hospital
Token Hospital
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
researchers
Token researchers
Feature activation+0.432
Top resid features:
have
Token have
Feature activation-0.016
Top resid features:
been
Token been
Feature activation-0.023
Top resid features:
producing
Token producing
Feature activation-0.043
Top resid features:
research
Token research
Feature activation+1.001
Top resid features:
improving
Token improving
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
bisexual
Token bisexual
Feature activation+0.000
Top resid features:
ity
Tokenity
Feature activation+0.000
Top resid features:
hour
Token hour
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Objective
Token Objective
Feature activation+0.055
Top resid features:
:
Token:
Feature activation-0.074
Top resid features:
This
Token This
Feature activation-0.096
Top resid features:
study
Token study
Feature activation+0.862
Top resid features:
examined
Token examined
Feature activation+0.633
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
relations
Token relations
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
team
Token team
Feature activation+0.060
Top resid features:
.
Token.
Feature activation-0.047
Top resid features:
This
Token This
Feature activation-0.125
Top resid features:
study
Token study
Feature activation+1.210
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
published
Token published
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
prestigious
Token prestigious
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.057
Top resid features:
because
Token because
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Pew
Token Pew
Feature activation+0.168
Top resid features:
Research
Token Research
Feature activation+0.540
Top resid features:
survey
Token survey
Feature activation+0.575
Top resid features:
did
Token did
Feature activation+0.132
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
adequate
Token adequate
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
The
TokenThe
Feature activation-0.007
Top resid features:
study
Token study
Feature activation+1.331
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
co
Token co
Feature activation+0.030
Top resid features:
-
Token-
Feature activation-0.018
Top resid features:
authors
Tokenauthors
Feature activation+0.485
Top resid features:
of
Token of
Feature activation-0.055
Top resid features:
the
Token the
Feature activation-0.024
Top resid features:
paper
Token paper
Feature activation+0.905
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
kind
Token kind
Feature activation+0.000
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
speak
Token speak
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.07

Head 2: 0.05

Head 3: 0.04

Head 4: 0.04

Head 5: 0.06

Head 6: 0.07

Head 7: 0.20

Head 8: 0.05

Head 9: 0.11

Head 10: 0.18

Head 11: 0.10

Positive logits

quantitative1.35

ISI1.19

researchers1.14

Research1.13

earcher1.11

otin1.10

zyme1.09

enhagen1.08

NI1.07

NYU1.07

Researchers1.06

abwe1.05

Research1.04

omics1.03

methodological1.01

Enlarge1.01

packing1.01

research1.01

biased1.00

genomic0.99

Negative logits

revenge-1.33

childish-1.10

Stranger-1.02

Bowser-1.00

Revenge-0.98

Cind-0.96

Tart-0.95

cameo-0.95

forfeit-0.94

coward-0.94

Stamina-0.92

Corpse-0.92

-0.92

Yamato-0.91

Bros-0.91

Drama-0.91

arty-0.90

Grind-0.90

Comedy-0.89

Myster-0.89

INTERVAL 1.656 - 1.840
CONTAINS 0.000%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
quasi
Token quasi
Feature activation+0.000
-
Token-
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.064
study
Token study
Feature activation+1.840
,
Token,
Feature activation+1.334
and
Token and
Feature activation+1.048
four
Token four
Feature activation+0.831
of
Token of
Feature activation+0.508
the
Token the
Feature activation+0.579

INTERVAL 1.472 - 1.656
CONTAINS 0.000%

INTERVAL 1.288 - 1.472
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
educational
Token educational
Feature activation+0.000
attainment
Token attainment
Feature activation+0.000
study
Token study
Feature activation+1.308
(
Token (
Feature activation+0.910
of
Tokenof
Feature activation+0.651
almost
Token almost
Feature activation+0.426
107
Token 107
Feature activation+0.512
,
Token,
Feature activation+0.149
),
Token),
Feature activation+0.000
lead
Token lead
Feature activation+0.000
author
Token author
Feature activation+0.252
of
Token of
Feature activation+0.258
the
Token the
Feature activation+0.299
study
Token study
Feature activation+1.325
.
Token.
Feature activation+1.178
âĢ
Token âĢ
Feature activation+0.872
ľ
Tokenľ
Feature activation+0.442
Over
TokenOver
Feature activation+0.519
the
Token the
Feature activation+0.494
quasi
Token quasi
Feature activation+0.000
-
Token-
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.064
study
Token study
Feature activation+1.840
,
Token,
Feature activation+1.334
and
Token and
Feature activation+1.048
four
Token four
Feature activation+0.831
of
Token of
Feature activation+0.508
the
Token the
Feature activation+0.579
10
Token 10
Feature activation+0.529

INTERVAL 1.104 - 1.288
CONTAINS 0.001%

A
Token A
Feature activation+0.000
new
Token new
Feature activation+0.000
pale
Token pale
Feature activation+0.000
ocl
Tokenocl
Feature activation+0.000
imate
Tokenimate
Feature activation+0.308
study
Token study
Feature activation+1.211
has
Token has
Feature activation+0.923
recently
Token recently
Feature activation+0.853
found
Token found
Feature activation+0.914
that
Token that
Feature activation+0.682
levels
Token levels
Feature activation+0.525
lead
Token lead
Feature activation+0.000
author
Token author
Feature activation+0.252
of
Token of
Feature activation+0.258
the
Token the
Feature activation+0.299
study
Token study
Feature activation+1.325
.
Token.
Feature activation+1.178
âĢ
Token âĢ
Feature activation+0.872
ľ
Tokenľ
Feature activation+0.442
Over
TokenOver
Feature activation+0.519
the
Token the
Feature activation+0.494
next
Token next
Feature activation+0.298
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
study
Token study
Feature activation+1.285
,
Token,
Feature activation+0.943
which
Token which
Feature activation+0.740
of
Token of
Feature activation+0.708
course
Token course
Feature activation+0.588
was
Token was
Feature activation+0.278
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.582
survey
Token survey
Feature activation+1.152
did
Token did
Feature activation+0.949
not
Token not
Feature activation+0.661
have
Token have
Feature activation+0.371
an
Token an
Feature activation+0.292
adequate
Token adequate
Feature activation+0.176

INTERVAL 0.920 - 1.104
CONTAINS 0.002%

because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
Research
Token Research
Feature activation+0.582
survey
Token survey
Feature activation+1.152
did
Token did
Feature activation+0.949
not
Token not
Feature activation+0.661
have
Token have
Feature activation+0.371
an
Token an
Feature activation+0.292
adequate
Token adequate
Feature activation+0.176
sample
Token sample
Feature activation+0.625
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
study
Token study
Feature activation+0.953
was
Token was
Feature activation+0.673
published
Token published
Feature activation+0.650
in
Token in
Feature activation+0.591
the
Token the
Feature activation+0.595
prestigious
Token prestigious
Feature activation+0.511
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+0.000
describing
Token describing
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.923
.
Token.
Feature activation+0.802
Ċ
TokenĊ
Feature activation+0.572
Ċ
TokenĊ
Feature activation+0.367
Not
TokenNot
Feature activation+0.205
addictive
Token addictive
Feature activation+0.085
Objective
Token Objective
Feature activation+0.000
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
study
Token study
Feature activation+0.753
examined
Token examined
Feature activation+0.956
the
Token the
Feature activation+0.972
relations
Token relations
Feature activation+0.966
between
Token between
Feature activation+0.597
the
Token the
Feature activation+0.752
timing
Token timing
Feature activation+0.405
of
Token of
Feature activation+0.065
new
Token new
Feature activation+0.000
pale
Token pale
Feature activation+0.000
ocl
Tokenocl
Feature activation+0.000
imate
Tokenimate
Feature activation+0.308
study
Token study
Feature activation+1.211
has
Token has
Feature activation+0.923
recently
Token recently
Feature activation+0.853
found
Token found
Feature activation+0.914
that
Token that
Feature activation+0.682
levels
Token levels
Feature activation+0.525
of
Token of
Feature activation+0.194

INTERVAL 0.736 - 0.920
CONTAINS 0.004%

in
Token in
Feature activation+0.000
PL
Token PL
Feature activation+0.000
OS
TokenOS
Feature activation+0.000
One
Token One
Feature activation+0.000
.
Token.
Feature activation+0.000
Researchers
Token Researchers
Feature activation+0.893
found
Token found
Feature activation+0.695
that
Token that
Feature activation+0.407
couples
Token couples
Feature activation+0.258
âĢĶ
TokenâĢĶ
Feature activation+0.000
both
Tokenboth
Feature activation+0.021
sources
Token sources
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
scientific
Token scientific
Feature activation+0.068
studies
Token studies
Feature activation+0.889
suggest
Token suggest
Feature activation+0.791
that
Token that
Feature activation+0.634
bisexual
Token bisexual
Feature activation+0.419
ity
Tokenity
Feature activation+0.313
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
ocl
Tokenocl
Feature activation+0.000
imate
Tokenimate
Feature activation+0.308
study
Token study
Feature activation+1.211
has
Token has
Feature activation+0.923
recently
Token recently
Feature activation+0.853
found
Token found
Feature activation+0.914
that
Token that
Feature activation+0.682
levels
Token levels
Feature activation+0.525
of
Token of
Feature activation+0.194
atmospheric
Token atmospheric
Feature activation+0.151
greenhouse
Token greenhouse
Feature activation+0.121
),
Token),
Feature activation+0.000
review
Token review
Feature activation+0.000
relationships
Token relationships
Feature activation+0.053
between
Token between
Feature activation+0.000
our
Token our
Feature activation+0.077
study
Token study
Feature activation+0.803
and
Token and
Feature activation+0.616
the
Token the
Feature activation+0.385
many
Token many
Feature activation+0.301
other
Token other
Feature activation+0.089
molecular
Token molecular
Feature activation+0.203
decreases
Token decreases
Feature activation+0.000
with
Token with
Feature activation+0.000
age
Token age
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
study
Token study
Feature activation+0.814
also
Token also
Feature activation+0.503
shows
Token shows
Feature activation+0.249
a
Token a
Feature activation+0.198
similar
Token similar
Feature activation+0.099
trend
Token trend
Feature activation+0.226

INTERVAL 0.552 - 0.736
CONTAINS 0.009%

.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
this
Token this
Feature activation+0.000
study
Token study
Feature activation+0.579
in
Token in
Feature activation+0.595
detail
Token detail
Feature activation+0.464
when
Token when
Feature activation+0.407
it
Token it
Feature activation+0.125
originally
Token originally
Feature activation+0.074
came
Token came
Feature activation+0.000
at
Token at
Feature activation+0.000
Rutgers
Token Rutgers
Feature activation+0.000
University
Token University
Feature activation+0.000
to
Token to
Feature activation+0.000
foster
Token foster
Feature activation+0.000
research
Token research
Feature activation+0.598
on
Token on
Feature activation+0.346
the
Token the
Feature activation+0.380
role
Token role
Feature activation+0.351
emotional
Token emotional
Feature activation+0.257
intelligence
Token intelligence
Feature activation+0.249
mult
Token mult
Feature activation+0.000
idis
Tokenidis
Feature activation+0.000
ciplinary
Tokenciplinary
Feature activation+0.000
clinical
Token clinical
Feature activation+0.029
trial
Token trial
Feature activation+0.536
team
Token team
Feature activation+0.592
were
Token were
Feature activation+0.257
present
Token present
Feature activation+0.080
.
Token.
Feature activation+0.073
The
Token The
Feature activation+0.094
baby
Token baby
Feature activation+0.000
,
Token,
Feature activation+0.943
we
Token we
Feature activation+0.674
further
Token further
Feature activation+0.522
explored
Token explored
Feature activation+0.666
the
Token the
Feature activation+0.604
role
Token role
Feature activation+0.590
of
Token of
Feature activation+0.352
NA
Token NA
Feature activation+0.409
c
Tokenc
Feature activation+0.240
in
Token in
Feature activation+0.195
sleep
Token sleep
Feature activation+0.155
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ne
TokenNe
Feature activation+0.000
uro
Tokenuro
Feature activation+0.000
scient
Tokenscient
Feature activation+0.384
ists
Tokenists
Feature activation+0.577
believe
Token believe
Feature activation+0.418
that
Token that
Feature activation+0.375
if
Token if
Feature activation+0.283
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000

INTERVAL 0.368 - 0.552
CONTAINS 0.018%

:
Token:
Feature activation+0.219
"
Token "
Feature activation+0.019
The
TokenThe
Feature activation+0.207
study
Token study
Feature activation+0.899
indicates
Token indicates
Feature activation+0.503
that
Token that
Feature activation+0.378
during
Token during
Feature activation+0.358
laboratory
Token laboratory
Feature activation+0.661
exposure
Token exposure
Feature activation+0.474
to
Token to
Feature activation+0.032
8
Token 8
Feature activation+0.000
subject
Token subject
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
PhD
Token PhD
Feature activation+0.155
thesis
Token thesis
Feature activation+0.675
is
Token is
Feature activation+0.388
about
Token about
Feature activation+0.187
âĢ
Token âĢ
Feature activation+0.068
ľ
Tokenľ
Feature activation+0.000
quant
Tokenquant
Feature activation+0.000
itative
Tokenitative
Feature activation+0.047
investigations
Token investigations
Feature activation+0.078
and
Token and
Feature activation+0.000
damning
Token damning
Feature activation+0.000
evidence
Token evidence
Feature activation+0.255
from
Token from
Feature activation+0.120
Professor
Token Professor
Feature activation+0.424
Frances
Token Frances
Feature activation+0.358
co
Tokenco
Feature activation+0.135
Con
Token Con
Feature activation+0.064
coni
Tokenconi
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
post
Tokenpost
Feature activation+0.000
-
Token-
Feature activation+0.000
colonial
Tokencolonial
Feature activation+0.000
studies
Token studies
Feature activation+0.622
.
Token.
Feature activation+0.499
âĢ
TokenâĢ
Feature activation+0.169
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
citing
Token citing
Feature activation+0.000
research
Token research
Feature activation+0.547
by
Token by
Feature activation+0.477
the
Token the
Feature activation+0.489
American
Token American
Feature activation+0.447
Ped
Token Ped
Feature activation+0.248
iatric
Tokeniatric
Feature activation+0.282

INTERVAL 0.184 - 0.368
CONTAINS 0.036%

care
Token care
Feature activation+0.000
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
clear
Token clear
Feature activation+0.000
scientific
Token scientific
Feature activation+0.283
evidence
Token evidence
Feature activation+0.492
.
Token.
Feature activation+0.510
Ċ
TokenĊ
Feature activation+0.286
Ċ
TokenĊ
Feature activation+0.197
The
TokenThe
Feature activation+0.128
acies
Tokenacies
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
report
Token report
Feature activation+0.240
fails
Token fails
Feature activation+0.018
to
Token to
Feature activation+0.000
mention
Token mention
Feature activation+0.000
that
Token that
Feature activation+0.000
firearms
Token firearms
Feature activation+0.000
Professor
Token Professor
Feature activation+0.000
of
Token of
Feature activation+0.000
Gender
Token Gender
Feature activation+0.000
Studies
Token Studies
Feature activation+0.682
at
Token at
Feature activation+0.403
the
Token the
Feature activation+0.297
University
Token University
Feature activation+0.495
of
Token of
Feature activation+0.102
Notre
Token Notre
Feature activation+0.116
Dame
Token Dame
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
evaluation
Token evaluation
Feature activation+0.068
panel
Token panel
Feature activation+0.240
composed
Token composed
Feature activation+0.255
of
Token of
Feature activation+0.337
ESA
Token ESA
Feature activation+0.156
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Raspberry
Token Raspberry
Feature activation+0.000
Pi
Token Pi
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
scientists
Token scientists
Feature activation+0.704
concluded
Token concluded
Feature activation+0.635
:
Token:
Feature activation+0.219
"
Token "
Feature activation+0.019
The
TokenThe
Feature activation+0.207
study
Token study
Feature activation+0.899
indicates
Token indicates
Feature activation+0.503
that
Token that
Feature activation+0.378

INTERVAL 0.000 - 0.184
CONTAINS 99.931%

olds
Tokenolds
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
privileged
Token privileged
Feature activation+0.000
backgrounds
Token backgrounds
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
challenged
Token challenged
Feature activation+0.000
backgrounds
Token backgrounds
Feature activation+0.000
ourage
Tokenourage
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
boxer
Token boxer
Feature activation+0.000
's
Token's
Feature activation+0.000
proud
Token proud
Feature activation+0.000
dad
Token dad
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
rather
Token rather
Feature activation+0.000
level
Token level
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
five
Token five
Feature activation+0.000
games
Token games
Feature activation+0.000
before
Token before
Feature activation+0.000
I
Token I
Feature activation+0.000
got
Token got
Feature activation+0.000
suspended
Token suspended
Feature activation+0.000
.
Token.
Feature activation+0.000
Probably
Token Probably
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
add
Token add
Feature activation+0.000
insult
Token insult
Feature activation+0.000
to
Token to
Feature activation+0.000
injury
Token injury
Feature activation+0.000
the
Token the
Feature activation+0.000
Boy
Token Boy
Feature activation+0.000
nton
Tokennton
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
,
Token,
Feature activation+0.000
sustained
Token sustained
Feature activation+0.000
massive
Token massive
Feature activation+0.000
casualties
Token casualties
Feature activation+0.000
at
Token at
Feature activation+0.000
Had
Token Had
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
in
Token in
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 H2.7: (feature 8950)

TOP ACTIVATIONS
MAX = 1.498

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Representatives
Token Representatives
Feature activation+0.350
have
Token have
Feature activation+0.207
grilled
Token grilled
Feature activation+0.000
State
Token State
Feature activation+0.474
Department
Token Department
Feature activation+1.264
and
Token and
Feature activation+0.442
other
Token other
Feature activation+0.000
executive
Token executive
Feature activation+0.471
branch
Token branch
Feature activation+0.647
officials
Token officials
Feature activation+0.665
although
Token although
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.563
officials
Token officials
Feature activation+1.130
have
Token have
Feature activation+0.429
been
Token been
Feature activation+0.269
able
Token able
Feature activation+0.000
make
Token make
Feature activation+0.000
use
Token use
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
UN
Token UN
Feature activation+0.022
officials
Token officials
Feature activation+1.051
and
Token and
Feature activation+0.693
anti
Token anti
Feature activation+0.398
-
Token-
Feature activation+0.251
arms
Tokenarms
Feature activation+0.142
-
Token-
Feature activation+0.061
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
for
Token for
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.115
prosecutors
Token prosecutors
Feature activation+1.045
and
Token and
Feature activation+0.555
local
Token local
Feature activation+0.126
police
Token police
Feature activation+0.190
tolerated
Token tolerated
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
former
Token former
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.026
defense
Token defense
Feature activation+0.362
minister
Token minister
Feature activation+1.028
Amir
Token Amir
Feature activation+0.492
Pere
Token Pere
Feature activation+0.177
tz
Tokentz
Feature activation+0.000
and
Token and
Feature activation+0.000
architect
Token architect
Feature activation+0.000
all
Token all
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
ranking
Tokenranking
Feature activation+0.041
federal
Token federal
Feature activation+0.550
officials
Token officials
Feature activation+1.022
insisted
Token insisted
Feature activation+0.294
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.000
'
Token'
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Quinn
Token Quinn
Feature activation+0.000
and
Token and
Feature activation+0.000
state
Token state
Feature activation+0.000
Assembly
Token Assembly
Feature activation+1.053
man
Tokenman
Feature activation+0.965
Daniel
Token Daniel
Feature activation+0.000
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
--
Token --
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
core
Token core
Feature activation+0.000
policy
Token policy
Feature activation+0.299
of
Token of
Feature activation+0.000
Prime
Token Prime
Feature activation+0.439
Minister
Token Minister
Feature activation+0.953
Shinzo
Token Shinzo
Feature activation+0.638
Abe
Token Abe
Feature activation+0.376
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
has
Token has
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
city
Token city
Feature activation+0.404
council
Token council
Feature activation+1.201
candidate
Token candidate
Feature activation+0.935
who
Token who
Feature activation+0.337
lives
Token lives
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.920
played
Token played
Feature activation+0.270
a
Token a
Feature activation+0.000
central
Token central
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
counselor
Token counselor
Feature activation+0.197
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.915
;
Token;
Feature activation+0.021
Jake
Token Jake
Feature activation+0.000
Sullivan
Token Sullivan
Feature activation+0.000
,
Token,
Feature activation+0.000
formerly
Token formerly
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
T
TokenT
Feature activation+0.000
]
Token]
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
President
Token President
Feature activation+1.076
made
Token made
Feature activation+0.884
clear
Token clear
Feature activation+0.310
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
ought
Token ought
Feature activation+0.000
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
by
Token by
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
whether
Token whether
Feature activation+0.000
President
Token President
Feature activation+0.832
Barack
Token Barack
Feature activation+0.813
Obama
Token Obama
Feature activation+0.515
was
Token was
Feature activation+0.325
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
who
Token who
Feature activation+0.000
served
Token served
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.831
under
Token under
Feature activation+0.250
the
Token the
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
administration
Token administration
Feature activation+0.119
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
fer
Token fer
Feature activation+0.000
ocity
Tokenocity
Feature activation+0.000
of
Token of
Feature activation+0.000
Republican
Token Republican
Feature activation+0.232
officials
Token officials
Feature activation+0.827
in
Token in
Feature activation+0.224
North
Token North
Feature activation+0.063
Carolina
Token Carolina
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
by
Token by
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
whether
Token whether
Feature activation+0.000
President
Token President
Feature activation+0.832
Barack
Token Barack
Feature activation+0.813
Obama
Token Obama
Feature activation+0.515
was
Token was
Feature activation+0.325
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.079
Office
Token Office
Feature activation+0.806
report
Token report
Feature activation+0.534
issued
Token issued
Feature activation+0.190
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
found
Token found
Feature activation+0.000
/
Token/
Feature activation+0.000
Os
TokenOs
Feature activation+0.000
ce
Tokence
Feature activation+0.000
ola
Tokenola
Feature activation+0.000
State
Token State
Feature activation+0.000
Attorney
Token Attorney
Feature activation+0.799
Aram
Token Aram
Feature activation+0.104
is
Tokenis
Feature activation+0.000
Ay
Token Ay
Feature activation+0.000
ala
Tokenala
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.526
of
Token of
Feature activation+0.730
Defense
Token Defense
Feature activation+0.798
,
Token,
Feature activation+0.000
Patterson
Token Patterson
Feature activation+0.000
,
Token,
Feature activation+0.000
24
Token 24
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
former
Token former
Feature activation+0.000
US
Token US
Feature activation+0.047
National
Token National
Feature activation+0.711
Security
Token Security
Feature activation+0.704
Agency
Token Agency
Feature activation+0.788
contractor
Token contractor
Feature activation+0.439
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

Top DFA by src position
MAX = 1.368

<|endoftext|>
Token<|endoftext|>
Feature activation+0.472
Top resid features:
Representatives
Token Representatives
Feature activation+0.267
Top resid features:
have
Token have
Feature activation+0.071
Top resid features:
grilled
Token grilled
Feature activation+0.117
Top resid features:
State
Token State
Feature activation+0.610
Top resid features:
Department
Token Department
Feature activation+0.978
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
executive
Token executive
Feature activation+0.000
Top resid features:
branch
Token branch
Feature activation+0.000
Top resid features:
officials
Token officials
Feature activation+0.000
Top resid features:
although
Token although
Feature activation+0.047
Top resid features:
he
Token he
Feature activation+0.123
Top resid features:
and
Token and
Feature activation+0.077
Top resid features:
other
Token other
Feature activation+0.095
Top resid features:
Cabinet
Token Cabinet
Feature activation+0.706
Top resid features:
officials
Token officials
Feature activation+0.929
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.493
Top resid features:
S
TokenS
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.112
Top resid features:
UN
Token UN
Feature activation+0.441
Top resid features:
officials
Token officials
Feature activation+1.241
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
anti
Token anti
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
arms
Tokenarms
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.349
Top resid features:
for
Token for
Feature activation+0.055
Top resid features:
blacks
Token blacks
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.113
Top resid features:
State
Token State
Feature activation+0.854
Top resid features:
prosecutors
Token prosecutors
Feature activation+0.913
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
local
Token local
Feature activation+0.000
Top resid features:
police
Token police
Feature activation+0.000
Top resid features:
tolerated
Token tolerated
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.564
Top resid features:
Ŀ
TokenĿ
Feature activation+0.020
Top resid features:
former
Token former
Feature activation+0.240
Top resid features:
Israeli
Token Israeli
Feature activation+0.146
Top resid features:
defense
Token defense
Feature activation+0.361
Top resid features:
minister
Token minister
Feature activation+0.949
Top resid features:
Amir
Token Amir
Feature activation+0.000
Top resid features:
Pere
Token Pere
Feature activation+0.000
Top resid features:
tz
Tokentz
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
architect
Token architect
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
all
Token all
Feature activation+0.147
Top resid features:
high
Token high
Feature activation+0.095
Top resid features:
-
Token-
Feature activation-0.069
Top resid features:
ranking
Tokenranking
Feature activation+0.266
Top resid features:
federal
Token federal
Feature activation+0.673
Top resid features:
officials
Token officials
Feature activation+0.662
Top resid features:
insisted
Token insisted
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
terrorists
Token terrorists
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.573
Top resid features:
Quinn
Token Quinn
Feature activation+0.137
Top resid features:
and
Token and
Feature activation+0.057
Top resid features:
state
Token state
Feature activation+0.279
Top resid features:
Assembly
Token Assembly
Feature activation+0.843
Top resid features:
man
Tokenman
Feature activation+0.327
Top resid features:
Daniel
Token Daniel
Feature activation+0.000
Top resid features:
O
Token O
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Donnell
TokenDonnell
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.535
Top resid features:
core
Token core
Feature activation+0.087
Top resid features:
policy
Token policy
Feature activation+0.324
Top resid features:
of
Token of
Feature activation-0.055
Top resid features:
Prime
Token Prime
Feature activation+0.377
Top resid features:
Minister
Token Minister
Feature activation+0.936
Top resid features:
Shinzo
Token Shinzo
Feature activation+0.000
Top resid features:
Abe
Token Abe
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.539
Top resid features:
a
Token a
Feature activation-0.048
Top resid features:
former
Token former
Feature activation+0.283
Top resid features:
city
Token city
Feature activation+0.314
Top resid features:
council
Token council
Feature activation+0.705
Top resid features:
candidate
Token candidate
Feature activation+0.393
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.093
Top resid features:
âĢ
TokenâĢ
Feature activation+0.058
Top resid features:
Ļ
TokenĻ
Feature activation+0.052
Top resid features:
s
Tokens
Feature activation-0.068
Top resid features:
State
Token State
Feature activation+0.636
Top resid features:
Department
Token Department
Feature activation+0.896
Top resid features:
played
Token played
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
central
Token central
Feature activation+0.000
Top resid features:
role
Token role
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.510
Top resid features:
counselor
Token counselor
Feature activation+0.218
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.206
Top resid features:
State
Token State
Feature activation+0.580
Top resid features:
Department
Token Department
Feature activation+1.065
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
Jake
Token Jake
Feature activation+0.000
Top resid features:
Sullivan
Token Sullivan
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
formerly
Token formerly
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.431
Top resid features:
T
TokenT
Feature activation+0.040
Top resid features:
]
Token]
Feature activation+0.208
Top resid features:
he
Tokenhe
Feature activation+0.050
Top resid features:
President
Token President
Feature activation+1.368
Top resid features:
made
Token made
Feature activation+0.039
Top resid features:
clear
Token clear
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
ought
Token ought
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.476
Top resid features:
by
Token by
Feature activation-0.001
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.079
Top resid features:
questioning
Token questioning
Feature activation+0.195
Top resid features:
whether
Token whether
Feature activation+0.058
Top resid features:
President
Token President
Feature activation+1.278
Top resid features:
Barack
Token Barack
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
born
Token born
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.050
Top resid features:
served
Token served
Feature activation+0.048
Top resid features:
at
Token at
Feature activation+0.066
Top resid features:
the
Token the
Feature activation-0.175
Top resid features:
State
Token State
Feature activation+0.585
Top resid features:
Department
Token Department
Feature activation+1.028
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
administration
Token administration
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.436
Top resid features:
fer
Token fer
Feature activation+0.043
Top resid features:
ocity
Tokenocity
Feature activation+0.163
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
Republican
Token Republican
Feature activation+0.551
Top resid features:
officials
Token officials
Feature activation+0.878
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
Carolina
Token Carolina
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.446
Top resid features:
by
Token by
Feature activation-0.004
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.065
Top resid features:
questioning
Token questioning
Feature activation+0.158
Top resid features:
whether
Token whether
Feature activation+0.109
Top resid features:
President
Token President
Feature activation+0.959
Top resid features:
Barack
Token Barack
Feature activation+0.332
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
born
Token born
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
overtime
Token overtime
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
A
TokenA
Feature activation+0.004
Top resid features:
Cabinet
Token Cabinet
Feature activation+0.800
Top resid features:
Office
Token Office
Feature activation+0.766
Top resid features:
report
Token report
Feature activation+0.000
Top resid features:
issued
Token issued
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.056
Top resid features:
Os
TokenOs
Feature activation+0.049
Top resid features:
ce
Tokence
Feature activation+0.025
Top resid features:
ola
Tokenola
Feature activation+0.066
Top resid features:
State
Token State
Feature activation+0.642
Top resid features:
Attorney
Token Attorney
Feature activation+0.709
Top resid features:
Aram
Token Aram
Feature activation+0.000
Top resid features:
is
Tokenis
Feature activation+0.000
Top resid features:
Ay
Token Ay
Feature activation+0.000
Top resid features:
ala
Tokenala
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.489
Top resid features:
to
Token to
Feature activation+0.046
Top resid features:
the
Token the
Feature activation-0.050
Top resid features:
Department
Token Department
Feature activation+1.051
Top resid features:
of
Token of
Feature activation+0.091
Top resid features:
Defense
Token Defense
Feature activation+0.422
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Patterson
Token Patterson
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.565
Top resid features:
former
Token former
Feature activation+0.175
Top resid features:
US
Token US
Feature activation+0.053
Top resid features:
National
Token National
Feature activation+0.428
Top resid features:
Security
Token Security
Feature activation+0.357
Top resid features:
Agency
Token Agency
Feature activation+0.461
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.06

Head 3: 0.05

Head 4: 0.05

Head 5: 0.06

Head 6: 0.08

Head 7: 0.19

Head 8: 0.06

Head 9: 0.05

Head 10: 0.18

Head 11: 0.10

Positive logits

Ltd0.80

efer0.76

ornia0.73

unts0.70

efe0.69

Enterprises0.69

rote0.69

utch0.67

llor0.66

Distribut0.66

Deng0.66

DragonMagazine0.65

remlin0.65

WARN0.65

Ventures0.65

LTD0.65

Emanuel0.65

19760.65

obook0.64

Carth0.64

Negative logits

kward-0.72

ulous-0.72

\/\/-0.71

tons-0.71

$$$$-0.70

inward-0.70

giving-0.70

________-0.69

iosity-0.69

explos-0.68

bub-0.68

forwards-0.68

millisec-0.68

Characters-0.68

swing-0.68

icular-0.67

oooooooooooooooo-0.67

intellectually-0.67

coming-0.66

spectators-0.66

INTERVAL 1.348 - 1.498
CONTAINS 0.000%

INTERVAL 1.198 - 1.348
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Representatives
Token Representatives
Feature activation+0.350
have
Token have
Feature activation+0.207
grilled
Token grilled
Feature activation+0.000
State
Token State
Feature activation+0.474
Department
Token Department
Feature activation+1.264
and
Token and
Feature activation+0.442
other
Token other
Feature activation+0.000
executive
Token executive
Feature activation+0.471
branch
Token branch
Feature activation+0.647
officials
Token officials
Feature activation+0.665

INTERVAL 1.049 - 1.198
CONTAINS 0.002%

although
Token although
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.563
officials
Token officials
Feature activation+1.130
have
Token have
Feature activation+0.429
been
Token been
Feature activation+0.269
able
Token able
Feature activation+0.000
make
Token make
Feature activation+0.000
use
Token use
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
UN
Token UN
Feature activation+0.022
officials
Token officials
Feature activation+1.051
and
Token and
Feature activation+0.693
anti
Token anti
Feature activation+0.398
-
Token-
Feature activation+0.251
arms
Tokenarms
Feature activation+0.142
-
Token-
Feature activation+0.061

INTERVAL 0.899 - 1.049
CONTAINS 0.002%

Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.920
played
Token played
Feature activation+0.270
a
Token a
Feature activation+0.000
central
Token central
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
for
Token for
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.115
prosecutors
Token prosecutors
Feature activation+1.045
and
Token and
Feature activation+0.555
local
Token local
Feature activation+0.126
police
Token police
Feature activation+0.190
tolerated
Token tolerated
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
ranking
Tokenranking
Feature activation+0.041
federal
Token federal
Feature activation+0.550
officials
Token officials
Feature activation+1.022
insisted
Token insisted
Feature activation+0.294
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.000
'
Token'
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Quinn
Token Quinn
Feature activation+0.000
and
Token and
Feature activation+0.000
state
Token state
Feature activation+0.000
Assembly
Token Assembly
Feature activation+1.053
man
Tokenman
Feature activation+0.965
Daniel
Token Daniel
Feature activation+0.000
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
--
Token --
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
core
Token core
Feature activation+0.000
policy
Token policy
Feature activation+0.299
of
Token of
Feature activation+0.000
Prime
Token Prime
Feature activation+0.439
Minister
Token Minister
Feature activation+0.953
Shinzo
Token Shinzo
Feature activation+0.638
Abe
Token Abe
Feature activation+0.376
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.749 - 0.899
CONTAINS 0.005%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
fer
Token fer
Feature activation+0.000
ocity
Tokenocity
Feature activation+0.000
of
Token of
Feature activation+0.000
Republican
Token Republican
Feature activation+0.232
officials
Token officials
Feature activation+0.827
in
Token in
Feature activation+0.224
North
Token North
Feature activation+0.063
Carolina
Token Carolina
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
former
Token former
Feature activation+0.000
US
Token US
Feature activation+0.047
National
Token National
Feature activation+0.711
Security
Token Security
Feature activation+0.704
Agency
Token Agency
Feature activation+0.788
contractor
Token contractor
Feature activation+0.439
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Department
Token Department
Feature activation+0.526
of
Token of
Feature activation+0.730
Defense
Token Defense
Feature activation+0.798
,
Token,
Feature activation+0.000
Patterson
Token Patterson
Feature activation+0.000
,
Token,
Feature activation+0.000
24
Token 24
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
served
Token served
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.831
under
Token under
Feature activation+0.250
the
Token the
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
administration
Token administration
Feature activation+0.119
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
by
Token by
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
whether
Token whether
Feature activation+0.000
President
Token President
Feature activation+0.832
Barack
Token Barack
Feature activation+0.813
Obama
Token Obama
Feature activation+0.515
was
Token was
Feature activation+0.325
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.599 - 0.749
CONTAINS 0.006%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
office
Token office
Feature activation+0.706
reacted
Token reacted
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
India
Token India
Feature activation+0.000
's
Token's
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Department
Token Department
Feature activation+0.581
of
Token of
Feature activation+0.766
Homeland
Token Homeland
Feature activation+0.505
Security
Token Security
Feature activation+0.685
released
Token released
Feature activation+0.049
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+0.000
late
Token late
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
's
Token's
Feature activation+0.000
Ministry
Token Ministry
Feature activation+0.041
of
Token of
Feature activation+0.267
National
Token National
Feature activation+0.211
Defense
Token Defense
Feature activation+0.676
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
monitored
Token monitored
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token-
Feature activation+0.000
ranking
Tokenranking
Feature activation+0.191
retired
Token retired
Feature activation+0.375
Venezuelan
Token Venezuelan
Feature activation+0.106
military
Token military
Feature activation+0.469
officers
Token officers
Feature activation+0.623
in
Token in
Feature activation+0.024
Florida
Token Florida
Feature activation+0.000
urged
Token urged
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
seldom
Token seldom
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.613
of
Token of
Feature activation+0.497
a
Token a
Feature activation+0.312
country
Token country
Feature activation+0.090
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 0.449 - 0.599
CONTAINS 0.013%

the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.467
sources
Token sources
Feature activation+0.436
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
11
Token 11
Feature activation+0.000
,
Token,
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
Army
Token Army
Feature activation+0.147
staff
Token staff
Feature activation+0.559
sergeant
Token sergeant
Feature activation+0.499
Robert
Token Robert
Feature activation+0.043
B
Token B
Feature activation+0.000
ales
Tokenales
Feature activation+0.000
left
Token left
Feature activation+0.000
for
Token for
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.115
prosecutors
Token prosecutors
Feature activation+1.045
and
Token and
Feature activation+0.555
local
Token local
Feature activation+0.126
police
Token police
Feature activation+0.190
tolerated
Token tolerated
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
National
Token National
Feature activation+0.072
Association
Token Association
Feature activation+0.483
of
Token of
Feature activation+0.224
Insurance
Token Insurance
Feature activation+0.069
Commissioners
Token Commissioners
Feature activation+0.190
sent
Token sent
Feature activation+0.000
a
Token a
Feature activation+0.000
another
Token another
Feature activation+0.000
third
Token third
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.558
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
funds
Token funds
Feature activation+0.000
would
Token would
Feature activation+0.000
come
Token come
Feature activation+0.000

INTERVAL 0.300 - 0.449
CONTAINS 0.024%

contract
Token contract
Feature activation+0.000
,
Token,
Feature activation+0.000
Proc
Token Proc
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
ment
Tokenment
Feature activation+0.000
Minister
Token Minister
Feature activation+0.405
Judy
Token Judy
Feature activation+0.117
Foot
Token Foot
Feature activation+0.000
e
Tokene
Feature activation+0.000
said
Token said
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
private
Token private
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
of
Token of
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
president
Token president
Feature activation+0.561
Vladimir
Token Vladimir
Feature activation+0.379
Putin
Token Putin
Feature activation+0.134
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
director
Token director
Feature activation+0.324
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
House
Token House
Feature activation+0.113
Republican
Token Republican
Feature activation+0.461
Conference
Token Conference
Feature activation+0.332
would
Token would
Feature activation+0.000
snag
Token snag
Feature activation+0.000
six
Token six
Feature activation+0.000
entire
Token entire
Feature activation+0.000
electoral
Token electoral
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
kar
Tokenkar
Feature activation+0.000
,
Token,
Feature activation+0.000
Managing
Token Managing
Feature activation+0.000
Director
Token Director
Feature activation+0.348
of
Token of
Feature activation+0.000
Go
Token Go
Feature activation+0.000
a
Tokena
Feature activation+0.000
Meat
Token Meat
Feature activation+0.000
Complex
Token Complex
Feature activation+0.000
DHS
Token DHS
Feature activation+0.000
officials
Token officials
Feature activation+0.823
,
Token,
Feature activation+0.254
including
Token including
Feature activation+0.000
former
Token former
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.375
Je
Token Je
Feature activation+0.188
h
Tokenh
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
,
Token,
Feature activation+0.000
noted
Token noted
Feature activation+0.000

INTERVAL 0.150 - 0.300
CONTAINS 0.045%

going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
block
Token block
Feature activation+0.000
any
Token any
Feature activation+0.000
Republican
Token Republican
Feature activation+0.089
attempts
Token attempts
Feature activation+0.200
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
away
Token away
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
J
Token J
Feature activation+0.000
.
Token.
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.223
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
annual
Token annual
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Federal
Token Federal
Feature activation+0.352
Rules
Token Rules
Feature activation+0.776
of
Token of
Feature activation+0.000
Civil
Token Civil
Feature activation+0.343
Procedure
Token Procedure
Feature activation+0.214
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
Wal
Token Wal
Feature activation+0.000
-
Token-
Feature activation+0.000
Mart
TokenMart
Feature activation+0.000
Kerry
Token Kerry
Feature activation+0.000
Th
Token Th
Feature activation+0.000
arp
Tokenarp
Feature activation+0.000
,
Token,
Feature activation+0.000
president
Token president
Feature activation+0.324
,
Token,
Feature activation+0.167
Dar
Token Dar
Feature activation+0.000
lington
Tokenlington
Feature activation+0.000
Rac
Token Rac
Feature activation+0.000
eway
Tokeneway
Feature activation+0.000
.
Token.
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.000
office
Token office
Feature activation+0.235
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
National
Token National
Feature activation+0.000
Marine
Token Marine
Feature activation+0.205
Fisheries
Token Fisheries
Feature activation+0.000
Service
Token Service
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.150
CONTAINS 99.903%

que
Tokenque
Feature activation+0.000
horse
Token horse
Feature activation+0.000
ranch
Token ranch
Feature activation+0.000
complete
Token complete
Feature activation+0.000
with
Token with
Feature activation+0.000
leaf
Token leaf
Feature activation+0.000
y
Tokeny
Feature activation+0.000
shade
Token shade
Feature activation+0.000
trees
Token trees
Feature activation+0.000
,
Token,
Feature activation+0.000
white
Token white
Feature activation+0.000
uninterrupted
Token uninterrupted
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000
such
Token such
Feature activation+0.000
crude
Token crude
Feature activation+0.000
the
Token the
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
of
Token of
Feature activation+0.000
January
Token January
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
.
Token.
Feature activation+0.000
Rural
Token Rural
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
women
Token women
Feature activation+0.000
it
Token it
Feature activation+0.000
responds
Token responds
Feature activation+0.000
more
Token more
Feature activation+0.000
readily
Token readily
Feature activation+0.000
to
Token to
Feature activation+0.000
winds
Token winds
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
easily
Token easily
Feature activation+0.000
broken
Token broken
Feature activation+0.000
one
Token one
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
just
Token just
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

a
Token a
Feature 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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
Organisation
Token Organisation
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
<|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+0.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature 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
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.040
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.070
committee
Token committee
Feature activation+0.262
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 8 in H2.7: (feature 21357)

TOP ACTIVATIONS
MAX = 1.900

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
for
Token for
Feature activation+0.000
retailers
Token retailers
Feature activation+0.000
with
Token with
Feature activation+0.000
Intel
Token Intel
Feature activation+0.986
hardware
Token hardware
Feature activation+1.766
,
Token,
Feature activation+1.199
including
Token including
Feature activation+0.900
Intel
Token Intel
Feature activation+1.072
Core
Token Core
Feature activation+1.138
and
Token and
Feature activation+0.971
-
Token-
Feature activation+0.000
w
Tokenw
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
anty
Tokenanty
Feature activation+0.000
iPhone
Token iPhone
Feature activation+1.162
battery
Token battery
Feature activation+1.620
replacement
Token replacement
Feature activation+1.496
by
Token by
Feature activation+1.223
$
Token $
Feature activation+0.989
50
Token50
Feature activation+0.596
âĢĶ
Token âĢĶ
Feature activation+0.367
-
Token-
Feature activation+0.000
commercial
Tokencommercial
Feature activation+0.000
Kinect
Token Kinect
Feature activation+0.699
for
Token for
Feature activation+0.624
Windows
Token Windows
Feature activation+1.492
Software
Token Software
Feature activation+1.602
Development
Token Development
Feature activation+1.120
Kit
Token Kit
Feature activation+0.825
,
Token,
Feature activation+0.772
or
Token or
Feature activation+0.432
SDK
Token SDK
Feature activation+0.279
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
Ļ
TokenĻ
Feature activation+0.260
your
Token your
Feature activation+0.000
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
Ļ
TokenĻ
Feature activation+0.260
ll
Tokenll
Feature activation+0.098
w
Tokenw
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
anty
Tokenanty
Feature activation+0.000
iPhone
Token iPhone
Feature activation+1.162
battery
Token battery
Feature activation+1.620
replacement
Token replacement
Feature activation+1.496
by
Token by
Feature activation+1.223
$
Token $
Feature activation+0.989
50
Token50
Feature activation+0.596
âĢĶ
Token âĢĶ
Feature activation+0.367
from
Token from
Feature activation+0.281
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
-
Token-
Feature activation+0.000
commercial
Tokencommercial
Feature activation+0.000
Kinect
Token Kinect
Feature activation+0.699
for
Token for
Feature activation+0.624
Windows
Token Windows
Feature activation+1.492
Software
Token Software
Feature activation+1.602
Development
Token Development
Feature activation+1.120
Kit
Token Kit
Feature activation+0.825
,
Token,
Feature activation+0.772
or
Token or
Feature activation+0.432
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
Ļ
TokenĻ
Feature activation+0.260
ll
Tokenll
Feature activation+0.098
have
Token have
Feature activation+0.137
open
Token open
Feature activation+0.000
apps
Token apps
Feature activation+0.518
from
Token from
Feature activation+0.675
the
Token the
Feature activation+0.447
Mac
Token Mac
Feature activation+1.130
App
Token App
Feature activation+1.420
Store
Token Store
Feature activation+1.348
or
Token or
Feature activation+0.991
known
Token known
Feature activation+0.633
developers
Token developers
Feature activation+0.406
,
Token,
Feature activation+0.217
apps
Token apps
Feature activation+0.518
from
Token from
Feature activation+0.675
the
Token the
Feature activation+0.447
Mac
Token Mac
Feature activation+1.130
App
Token App
Feature activation+1.420
Store
Token Store
Feature activation+1.348
or
Token or
Feature activation+0.991
known
Token known
Feature activation+0.633
developers
Token developers
Feature activation+0.406
,
Token,
Feature activation+0.217
it
Token it
Feature activation+0.022
PCIe
Token PCIe
Feature activation+0.923
2
Token 2
Feature activation+0.920
x
Token x
Feature activation+1.108
PCIe
Token PCIe
Feature activation+1.267
x
Token x
Feature activation+1.280
16
Token16
Feature activation+1.289
Ċ
TokenĊ
Feature activation+0.890
Ċ
TokenĊ
Feature activation+0.631
2
Token2
Feature activation+0.499
x
Token x
Feature activation+0.504
PCIe
Token PCIe
Feature activation+0.628
4
Token 4
Feature activation+0.000
PCIe
Token PCIe
Feature activation+0.923
2
Token 2
Feature activation+0.920
x
Token x
Feature activation+1.108
PCIe
Token PCIe
Feature activation+1.267
x
Token x
Feature activation+1.280
16
Token16
Feature activation+1.289
Ċ
TokenĊ
Feature activation+0.890
Ċ
TokenĊ
Feature activation+0.631
2
Token2
Feature activation+0.499
x
Token x
Feature activation+0.504
,
Token,
Feature activation+0.000
tablet
Token tablet
Feature activation+0.766
,
Token,
Feature activation+0.827
PC
Token PC
Feature activation+1.327
,
Token,
Feature activation+1.023
laptop
Token laptop
Feature activation+1.271
,
Token,
Feature activation+0.988
home
Token home
Feature activation+0.653
sound
Token sound
Feature activation+0.364
system
Token system
Feature activation+0.385
,
Token,
Feature activation+0.243
4
Token 4
Feature activation+0.000
4
Token 4
Feature activation+0.000
PCIe
Token PCIe
Feature activation+0.923
2
Token 2
Feature activation+0.920
x
Token x
Feature activation+1.108
PCIe
Token PCIe
Feature activation+1.267
x
Token x
Feature activation+1.280
16
Token16
Feature activation+1.289
Ċ
TokenĊ
Feature activation+0.890
Ċ
TokenĊ
Feature activation+0.631
2
Token2
Feature activation+0.499
It
Token It
Feature activation+0.000
charged
Token charged
Feature activation+0.000
our
Token our
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.816
X
Token X
Feature activation+1.153
R
TokenR
Feature activation+1.255
a
Token a
Feature activation+1.007
bit
Token bit
Feature activation+0.728
faster
Token faster
Feature activation+0.676
than
Token than
Feature activation+0.534
most
Token most
Feature activation+0.464
arr
Tokenarr
Feature activation+0.000
anty
Tokenanty
Feature activation+0.000
iPhone
Token iPhone
Feature activation+1.162
battery
Token battery
Feature activation+1.620
replacement
Token replacement
Feature activation+1.496
by
Token by
Feature activation+1.223
$
Token $
Feature activation+0.989
50
Token50
Feature activation+0.596
âĢĶ
Token âĢĶ
Feature activation+0.367
from
Token from
Feature activation+0.281
$
Token $
Feature activation+0.127
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Nintendo
Token Nintendo
Feature activation+0.687
Wii
Token Wii
Feature activation+1.293
in
Token in
Feature activation+1.209
the
Token the
Feature activation+0.831
near
Token near
Feature activation+0.401
future
Token future
Feature activation+0.487
.
Token.
Feature activation+0.281
Also
Token Also
Feature activation+0.190
for
Token for
Feature activation+0.000
retailers
Token retailers
Feature activation+0.000
with
Token with
Feature activation+0.000
Intel
Token Intel
Feature activation+0.986
hardware
Token hardware
Feature activation+1.766
,
Token,
Feature activation+1.199
including
Token including
Feature activation+0.900
Intel
Token Intel
Feature activation+1.072
Core
Token Core
Feature activation+1.138
and
Token and
Feature activation+0.971
select
Token select
Feature activation+0.766
something
Token something
Feature activation+0.000
bad
Token bad
Feature activation+0.000
about
Token about
Feature activation+0.000
an
Token an
Feature activation+0.000
Android
Token Android
Feature activation+0.661
device
Token device
Feature activation+1.192
.
Token.
Feature activation+0.964
R
Token R
Feature activation+0.768
AGE
TokenAGE
Feature activation+0.202
!
Token!
Feature activation+0.018
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 1.225

<|endoftext|>
Token<|endoftext|>
Feature activation+0.077
Top resid features:
on
Token on
Feature activation-0.054
Top resid features:
your
Token your
Feature activation-0.031
Top resid features:
LG
Token LG
Feature activation+0.442
Top resid features:
Android
Token Android
Feature activation+0.914
Top resid features:
phone
Token phone
Feature activation+0.709
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
tablet
Token tablet
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.074
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
retailers
Token retailers
Feature activation+0.170
Top resid features:
with
Token with
Feature activation-0.116
Top resid features:
Intel
Token Intel
Feature activation+1.225
Top resid features:
hardware
Token hardware
Feature activation+0.584
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
Intel
Token Intel
Feature activation+0.000
Top resid features:
Core
Token Core
Feature activation+0.000
Top resid features:
of
Tokenof
Feature activation-0.082
Top resid features:
-
Token-
Feature activation-0.023
Top resid features:
w
Tokenw
Feature activation-0.023
Top resid features:
arr
Tokenarr
Feature activation-0.128
Top resid features:
anty
Tokenanty
Feature activation+0.191
Top resid features:
iPhone
Token iPhone
Feature activation+1.118
Top resid features:
battery
Token battery
Feature activation+0.644
Top resid features:
replacement
Token replacement
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
50
Token50
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.123
Top resid features:
-
Token-
Feature activation-0.009
Top resid features:
commercial
Tokencommercial
Feature activation-0.011
Top resid features:
Kinect
Token Kinect
Feature activation+0.422
Top resid features:
for
Token for
Feature activation-0.085
Top resid features:
Windows
Token Windows
Feature activation+0.879
Top resid features:
Software
Token Software
Feature activation+0.440
Top resid features:
Development
Token Development
Feature activation+0.000
Top resid features:
Kit
Token Kit
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.078
Top resid features:
on
Token on
Feature activation-0.034
Top resid features:
your
Token your
Feature activation-0.013
Top resid features:
LG
Token LG
Feature activation+0.372
Top resid features:
Android
Token Android
Feature activation+0.744
Top resid features:
phone
Token phone
Feature activation+0.675
Top resid features:
or
Token or
Feature activation-0.073
Top resid features:
tablet
Token tablet
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
your
Token your
Feature activation-0.004
Top resid features:
LG
Token LG
Feature activation+0.319
Top resid features:
Android
Token Android
Feature activation+0.527
Top resid features:
phone
Token phone
Feature activation+0.472
Top resid features:
or
Token or
Feature activation-0.259
Top resid features:
tablet
Token tablet
Feature activation+0.567
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
You
Token You
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:
ll
Tokenll
Feature activation+0.000
Top resid features:
of
Tokenof
Feature activation-0.046
Top resid features:
-
Token-
Feature activation-0.013
Top resid features:
w
Tokenw
Feature activation-0.015
Top resid features:
arr
Tokenarr
Feature activation-0.040
Top resid features:
anty
Tokenanty
Feature activation+0.109
Top resid features:
iPhone
Token iPhone
Feature activation+0.771
Top resid features:
battery
Token battery
Feature activation+0.599
Top resid features:
replacement
Token replacement
Feature activation+0.216
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
50
Token50
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.053
Top resid features:
-
Token-
Feature activation-0.027
Top resid features:
commercial
Tokencommercial
Feature activation-0.025
Top resid features:
Kinect
Token Kinect
Feature activation+0.729
Top resid features:
for
Token for
Feature activation-0.171
Top resid features:
Windows
Token Windows
Feature activation+1.092
Top resid features:
Software
Token Software
Feature activation+0.000
Top resid features:
Development
Token Development
Feature activation+0.000
Top resid features:
Kit
Token Kit
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.012
Top resid features:
LG
Token LG
Feature activation+0.227
Top resid features:
Android
Token Android
Feature activation+0.428
Top resid features:
phone
Token phone
Feature activation+0.442
Top resid features:
or
Token or
Feature activation-0.166
Top resid features:
tablet
Token tablet
Feature activation+0.603
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
You
Token You
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:
ll
Tokenll
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
open
Token open
Feature activation+0.002
Top resid features:
apps
Token apps
Feature activation+0.340
Top resid features:
from
Token from
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
Mac
Token Mac
Feature activation+0.562
Top resid features:
App
Token App
Feature activation+0.536
Top resid features:
Store
Token Store
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
known
Token known
Feature activation+0.000
Top resid features:
developers
Token developers
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
open
Token open
Feature activation+0.006
Top resid features:
apps
Token apps
Feature activation+0.265
Top resid features:
from
Token from
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
Mac
Token Mac
Feature activation+0.495
Top resid features:
App
Token App
Feature activation+0.322
Top resid features:
Store
Token Store
Feature activation+0.234
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
known
Token known
Feature activation+0.000
Top resid features:
developers
Token developers
Feature activation+0.000
Top resid features:
4
Token 4
Feature activation+0.027
Top resid features:
4
Token 4
Feature activation+0.007
Top resid features:
PCIe
Token PCIe
Feature activation+0.431
Top resid features:
2
Token 2
Feature activation+0.021
Top resid features:
x
Token x
Feature activation+0.118
Top resid features:
PCIe
Token PCIe
Feature activation+0.502
Top resid features:
x
Token x
Feature activation+0.115
Top resid features:
16
Token16
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
2
Token2
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.111
Top resid features:
ots
Tokenots
Feature activation-0.003
Top resid features:
8
Token 8
Feature activation+0.034
Top resid features:
4
Token 4
Feature activation+0.027
Top resid features:
4
Token 4
Feature activation+0.003
Top resid features:
PCIe
Token PCIe
Feature activation+0.419
Top resid features:
2
Token 2
Feature activation+0.015
Top resid features:
x
Token x
Feature activation+0.185
Top resid features:
PCIe
Token PCIe
Feature activation+0.399
Top resid features:
x
Token x
Feature activation+0.248
Top resid features:
16
Token16
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
tablet
Token tablet
Feature activation+0.331
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
PC
Token PC
Feature activation+0.545
Top resid features:
,
Token,
Feature activation-0.161
Top resid features:
laptop
Token laptop
Feature activation+0.643
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
sound
Token sound
Feature activation+0.000
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
4
Token 4
Feature activation+0.032
Top resid features:
4
Token 4
Feature activation+0.001
Top resid features:
PCIe
Token PCIe
Feature activation+0.469
Top resid features:
2
Token 2
Feature activation+0.041
Top resid features:
x
Token x
Feature activation+0.246
Top resid features:
PCIe
Token PCIe
Feature activation+0.566
Top resid features:
x
Token x
Feature activation+0.000
Top resid features:
16
Token16
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:
2
Token2
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.117
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
It
Token It
Feature activation+0.023
Top resid features:
charged
Token charged
Feature activation-0.019
Top resid features:
our
Token our
Feature activation+0.066
Top resid features:
iPhone
Token iPhone
Feature activation+0.851
Top resid features:
X
Token X
Feature activation+0.276
Top resid features:
R
TokenR
Feature activation+0.102
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
bit
Token bit
Feature activation+0.000
Top resid features:
faster
Token faster
Feature activation+0.000
Top resid features:
of
Tokenof
Feature activation-0.007
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
w
Tokenw
Feature activation+0.004
Top resid features:
arr
Tokenarr
Feature activation-0.022
Top resid features:
anty
Tokenanty
Feature activation+0.065
Top resid features:
iPhone
Token iPhone
Feature activation+0.645
Top resid features:
battery
Token battery
Feature activation+0.369
Top resid features:
replacement
Token replacement
Feature activation+0.185
Top resid features:
by
Token by
Feature activation+0.023
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
50
Token50
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.053
Top resid features:
for
Token for
Feature activation-0.047
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Nintendo
Token Nintendo
Feature activation+0.644
Top resid features:
Wii
Token Wii
Feature activation+0.732
Top resid features:
in
Token in
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
near
Token near
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.104
Top resid features:
for
Token for
Feature activation-0.019
Top resid features:
retailers
Token retailers
Feature activation+0.131
Top resid features:
with
Token with
Feature activation-0.060
Top resid features:
Intel
Token Intel
Feature activation+0.666
Top resid features:
hardware
Token hardware
Feature activation+0.592
Top resid features:
,
Token,
Feature activation-0.057
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
Intel
Token Intel
Feature activation+0.000
Top resid features:
Core
Token Core
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.005
Top resid features:
something
Token something
Feature activation+0.034
Top resid features:
bad
Token bad
Feature activation-0.041
Top resid features:
about
Token about
Feature activation-0.071
Top resid features:
an
Token an
Feature activation-0.017
Top resid features:
Android
Token Android
Feature activation+0.694
Top resid features:
device
Token device
Feature activation+0.581
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
R
Token R
Feature activation+0.000
Top resid features:
AGE
TokenAGE
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.08

Head 2: 0.04

Head 3: 0.05

Head 4: 0.03

Head 5: 0.05

Head 6: 0.06

Head 7: 0.19

Head 8: 0.04

Head 9: 0.11

Head 10: 0.19

Head 11: 0.10

Positive logits

Hardware1.11

LED1.11

GDDR1.07

upgrades1.06

Flags1.06

LED1.05

Target1.05

Built1.04

OEM1.04

Setup1.04

LEDs1.03

presets1.03

Launch1.03

Samsung1.02

optimizations1.02

setup1.02

specs1.01

BM1.01

DRM1.00

Lenovo0.99

Negative logits

Tanz-1.09

pardon-1.03

tu-1.00

-0.99

secut-0.98

prayed-0.98

ilitating-0.98

tu-0.97

rhy-0.97

א-0.96

ש-0.95

-0.95

sacrific-0.94

foreseen-0.92

nian-0.92

gard-0.92

mens-0.92

Adin-0.92

ו-0.91

-0.91

INTERVAL 1.710 - 1.900
CONTAINS 0.000%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
for
Token for
Feature activation+0.000
retailers
Token retailers
Feature activation+0.000
with
Token with
Feature activation+0.000
Intel
Token Intel
Feature activation+0.986
hardware
Token hardware
Feature activation+1.766
,
Token,
Feature activation+1.199
including
Token including
Feature activation+0.900
Intel
Token Intel
Feature activation+1.072
Core
Token Core
Feature activation+1.138
and
Token and
Feature activation+0.971
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619

INTERVAL 1.520 - 1.710
CONTAINS 0.000%

-
Token-
Feature activation+0.000
w
Tokenw
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
anty
Tokenanty
Feature activation+0.000
iPhone
Token iPhone
Feature activation+1.162
battery
Token battery
Feature activation+1.620
replacement
Token replacement
Feature activation+1.496
by
Token by
Feature activation+1.223
$
Token $
Feature activation+0.989
50
Token50
Feature activation+0.596
âĢĶ
Token âĢĶ
Feature activation+0.367
-
Token-
Feature activation+0.000
commercial
Tokencommercial
Feature activation+0.000
Kinect
Token Kinect
Feature activation+0.699
for
Token for
Feature activation+0.624
Windows
Token Windows
Feature activation+1.492
Software
Token Software
Feature activation+1.602
Development
Token Development
Feature activation+1.120
Kit
Token Kit
Feature activation+0.825
,
Token,
Feature activation+0.772
or
Token or
Feature activation+0.432
SDK
Token SDK
Feature activation+0.279
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
Ļ
TokenĻ
Feature activation+0.260
your
Token your
Feature activation+0.000
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
Ļ
TokenĻ
Feature activation+0.260
ll
Tokenll
Feature activation+0.098

INTERVAL 1.330 - 1.520
CONTAINS 0.001%

w
Tokenw
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
anty
Tokenanty
Feature activation+0.000
iPhone
Token iPhone
Feature activation+1.162
battery
Token battery
Feature activation+1.620
replacement
Token replacement
Feature activation+1.496
by
Token by
Feature activation+1.223
$
Token $
Feature activation+0.989
50
Token50
Feature activation+0.596
âĢĶ
Token âĢĶ
Feature activation+0.367
from
Token from
Feature activation+0.281
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
-
Token-
Feature activation+0.000
commercial
Tokencommercial
Feature activation+0.000
Kinect
Token Kinect
Feature activation+0.699
for
Token for
Feature activation+0.624
Windows
Token Windows
Feature activation+1.492
Software
Token Software
Feature activation+1.602
Development
Token Development
Feature activation+1.120
Kit
Token Kit
Feature activation+0.825
,
Token,
Feature activation+0.772
or
Token or
Feature activation+0.432
open
Token open
Feature activation+0.000
apps
Token apps
Feature activation+0.518
from
Token from
Feature activation+0.675
the
Token the
Feature activation+0.447
Mac
Token Mac
Feature activation+1.130
App
Token App
Feature activation+1.420
Store
Token Store
Feature activation+1.348
or
Token or
Feature activation+0.991
known
Token known
Feature activation+0.633
developers
Token developers
Feature activation+0.406
,
Token,
Feature activation+0.217
apps
Token apps
Feature activation+0.518
from
Token from
Feature activation+0.675
the
Token the
Feature activation+0.447
Mac
Token Mac
Feature activation+1.130
App
Token App
Feature activation+1.420
Store
Token Store
Feature activation+1.348
or
Token or
Feature activation+0.991
known
Token known
Feature activation+0.633
developers
Token developers
Feature activation+0.406
,
Token,
Feature activation+0.217
it
Token it
Feature activation+0.022
LG
Token LG
Feature activation+0.566
Android
Token Android
Feature activation+1.732
phone
Token phone
Feature activation+1.900
or
Token or
Feature activation+1.590
tablet
Token tablet
Feature activation+1.553
.
Token.
Feature activation+1.477
You
Token You
Feature activation+1.006
âĢ
TokenâĢ
Feature activation+0.619
Ļ
TokenĻ
Feature activation+0.260
ll
Tokenll
Feature activation+0.098
have
Token have
Feature activation+0.137

INTERVAL 1.140 - 1.330
CONTAINS 0.003%

4
Token 4
Feature activation+0.000
4
Token 4
Feature activation+0.000
PCIe
Token PCIe
Feature activation+0.923
2
Token 2
Feature activation+0.920
x
Token x
Feature activation+1.108
PCIe
Token PCIe
Feature activation+1.267
x
Token x
Feature activation+1.280
16
Token16
Feature activation+1.289
Ċ
TokenĊ
Feature activation+0.890
Ċ
TokenĊ
Feature activation+0.631
2
Token2
Feature activation+0.499
arr
Tokenarr
Feature activation+0.000
anty
Tokenanty
Feature activation+0.000
iPhone
Token iPhone
Feature activation+1.162
battery
Token battery
Feature activation+1.620
replacement
Token replacement
Feature activation+1.496
by
Token by
Feature activation+1.223
$
Token $
Feature activation+0.989
50
Token50
Feature activation+0.596
âĢĶ
Token âĢĶ
Feature activation+0.367
from
Token from
Feature activation+0.281
$
Token $
Feature activation+0.127
"
Token"
Feature activation+0.000
ARM
Token ARM
Feature activation+0.207
Cortex
Token Cortex
Feature activation+0.988
A
Token A
Feature activation+0.805
53
Token53
Feature activation+0.473
CPU
Token CPU
Feature activation+1.156
cores
Token cores
Feature activation+0.962
with
Token with
Feature activation+0.947
four
Token four
Feature activation+0.651
"
Token "
Feature activation+0.229
big
Tokenbig
Feature activation+0.240
It
Token It
Feature activation+0.000
charged
Token charged
Feature activation+0.000
our
Token our
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.816
X
Token X
Feature activation+1.153
R
TokenR
Feature activation+1.255
a
Token a
Feature activation+1.007
bit
Token bit
Feature activation+0.728
faster
Token faster
Feature activation+0.676
than
Token than
Feature activation+0.534
most
Token most
Feature activation+0.464
something
Token something
Feature activation+0.000
bad
Token bad
Feature activation+0.000
about
Token about
Feature activation+0.000
an
Token an
Feature activation+0.000
Android
Token Android
Feature activation+0.661
device
Token device
Feature activation+1.192
.
Token.
Feature activation+0.964
R
Token R
Feature activation+0.768
AGE
TokenAGE
Feature activation+0.202
!
Token!
Feature activation+0.018
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.950 - 1.140
CONTAINS 0.005%

from
Token from
Feature activation+0.675
the
Token the
Feature activation+0.447
Mac
Token Mac
Feature activation+1.130
App
Token App
Feature activation+1.420
Store
Token Store
Feature activation+1.348
or
Token or
Feature activation+0.991
known
Token known
Feature activation+0.633
developers
Token developers
Feature activation+0.406
,
Token,
Feature activation+0.217
it
Token it
Feature activation+0.022
won
Token won
Feature activation+0.000
network
Token network
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
unauthorized
Token unauthorized
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.784
users
Token users
Feature activation+0.981
have
Token have
Feature activation+0.534
been
Token been
Feature activation+0.464
on
Token on
Feature activation+0.288
their
Token their
Feature activation+0.197
network
Token network
Feature activation+0.232
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
macOS
Token macOS
Feature activation+0.792
operating
Token operating
Feature activation+1.099
systems
Token systems
Feature activation+1.339
.
Token.
Feature activation+1.072
Because
Token Because
Feature activation+0.774
speech
Token speech
Feature activation+0.520
recognition
Token recognition
Feature activation+0.131
requires
Token requires
Feature activation+0.092
tremendous
Token tremendous
Feature activation+0.076
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
tablet
Token tablet
Feature activation+0.766
,
Token,
Feature activation+0.827
PC
Token PC
Feature activation+1.327
,
Token,
Feature activation+1.023
laptop
Token laptop
Feature activation+1.271
,
Token,
Feature activation+0.988
home
Token home
Feature activation+0.653
sound
Token sound
Feature activation+0.364
system
Token system
Feature activation+0.385
7
Token 7
Feature activation+0.000
Plus
Token Plus
Feature activation+0.007
in
Token in
Feature activation+0.000
iOS
Token iOS
Feature activation+1.186
11
Token 11
Feature activation+1.147
.
Token.
Feature activation+1.041
2
Token2
Feature activation+0.679
.
Token.
Feature activation+0.712
Ċ
TokenĊ
Feature activation+0.424
Ċ
TokenĊ
Feature activation+0.219
Of
TokenOf
Feature activation+0.000

INTERVAL 0.760 - 0.950
CONTAINS 0.009%

retailers
Token retailers
Feature activation+0.000
with
Token with
Feature activation+0.000
Intel
Token Intel
Feature activation+0.986
hardware
Token hardware
Feature activation+1.766
,
Token,
Feature activation+1.199
including
Token including
Feature activation+0.900
Intel
Token Intel
Feature activation+1.072
Core
Token Core
Feature activation+1.138
and
Token and
Feature activation+0.971
select
Token select
Feature activation+0.766
Intel
Token Intel
Feature activation+0.582
you
Token you
Feature activation+0.328
make
Token make
Feature activation+0.114
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.000
Wear
Token Wear
Feature activation+0.603
OS
Token OS
Feature activation+0.947
watch
Token watch
Feature activation+1.166
faces
Token faces
Feature activation+0.756
.
Token.
Feature activation+0.529
The
Token The
Feature activation+0.257
app
Token app
Feature activation+0.362
Though
TokenThough
Feature activation+0.000
the
Token the
Feature activation+0.000
iPad
Token iPad
Feature activation+0.667
mini
Token mini
Feature activation+0.900
3
Token 3
Feature activation+0.837
and
Token and
Feature activation+0.817
the
Token the
Feature activation+0.597
iPad
Token iPad
Feature activation+0.797
Air
Token Air
Feature activation+0.632
2
Token 2
Feature activation+0.504
are
Token are
Feature activation+0.585
HD
Token HD
Feature activation+0.183
video
Token video
Feature activation+0.139
streaming
Token streaming
Feature activation+0.583
,
Token,
Feature activation+0.586
multiplayer
Token multiplayer
Feature activation+0.678
gaming
Token gaming
Feature activation+0.799
and
Token and
Feature activation+0.535
backing
Token backing
Feature activation+0.357
up
Token up
Feature activation+0.000
big
Token big
Feature activation+0.000
files
Token files
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.414
's
Token's
Feature activation+0.420
director
Token director
Feature activation+0.202
of
Token of
Feature activation+0.000
Windows
Token Windows
Feature activation+0.783
business
Token business
Feature activation+0.800
planning
Token planning
Feature activation+0.360
,
Token,
Feature activation+0.261
blog
Token blog
Feature activation+0.000
ged
Tokenged
Feature activation+0.000

INTERVAL 0.570 - 0.760
CONTAINS 0.018%

the
Token the
Feature activation+0.000
Xbox
Token Xbox
Feature activation+0.021
360
Token 360
Feature activation+0.304
,
Token,
Feature activation+0.427
PlayStation
Token PlayStation
Feature activation+0.439
Portable
Token Portable
Feature activation+0.583
,
Token,
Feature activation+0.362
PlayStation
Token PlayStation
Feature activation+0.328
3
Token 3
Feature activation+0.107
,
Token,
Feature activation+0.242
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.329
or
Token or
Feature activation+0.153
a
Token a
Feature activation+0.097
smartphone
Token smartphone
Feature activation+0.735
,
Token,
Feature activation+0.602
there
Token there
Feature activation+0.266
was
Token was
Feature activation+0.169
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
are
Token are
Feature activation+0.000
considering
Token considering
Feature activation+0.000
Internet
Token Internet
Feature activation+0.293
gaming
Token gaming
Feature activation+0.628
statutes
Token statutes
Feature activation+0.443
of
Token of
Feature activation+0.170
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.046
mini
Token mini
Feature activation+0.900
3
Token 3
Feature activation+0.837
and
Token and
Feature activation+0.817
the
Token the
Feature activation+0.597
iPad
Token iPad
Feature activation+0.797
Air
Token Air
Feature activation+0.632
2
Token 2
Feature activation+0.504
are
Token are
Feature activation+0.585
not
Token not
Feature activation+0.284
able
Token able
Feature activation+0.296
to
Token to
Feature activation+0.131
5
Token 5
Feature activation+0.780
based
Token based
Feature activation+0.892
on
Token on
Feature activation+0.698
Qt
Token Qt
Feature activation+0.991
5
Token5
Feature activation+0.711
will
Token will
Feature activation+0.758
also
Token also
Feature activation+0.515
come
Token come
Feature activation+0.366
soon
Token soon
Feature activation+0.345
(
Token (
Feature activation+0.424
dates
Tokendates
Feature activation+0.000

INTERVAL 0.380 - 0.570
CONTAINS 0.032%

although
Token although
Feature activation+0.000
unauthorized
Token unauthorized
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.784
users
Token users
Feature activation+0.981
have
Token have
Feature activation+0.534
been
Token been
Feature activation+0.464
on
Token on
Feature activation+0.288
their
Token their
Feature activation+0.197
network
Token network
Feature activation+0.232
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.033
revert
Token revert
Feature activation+0.000
to
Token to
Feature activation+0.000
stock
Token stock
Feature activation+0.000
Sony
Token Sony
Feature activation+0.426
firmware
Token firmware
Feature activation+0.820
be
Token be
Feature activation+0.462
flashing
Token flashing
Feature activation+0.548
an
Token an
Feature activation+0.350
official
Token official
Feature activation+0.174
Sony
Token Sony
Feature activation+0.459
Kit
Token Kit
Feature activation+0.483
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Xbox
Token Xbox
Feature activation+0.021
360
Token 360
Feature activation+0.304
,
Token,
Feature activation+0.427
PlayStation
Token PlayStation
Feature activation+0.439
Portable
Token Portable
Feature activation+0.583
,
Token,
Feature activation+0.362
PlayStation
Token PlayStation
Feature activation+0.328
3
Token 3
Feature activation+0.107
,
Token,
Feature activation+0.242
no
Token no
Feature activation+0.000
CSS
Token CSS
Feature activation+0.221
in
Token in
Feature activation+0.341
React
Token React
Feature activation+0.363
Native
TokenNative
Feature activation+0.411
;
Token;
Feature activation+0.412
everything
Token everything
Feature activation+0.098
is
Token is
Feature activation+0.000
styled
Token styled
Feature activation+0.000
with
Token with
Feature activation+0.000
JavaScript
Token JavaScript
Feature activation+0.113
Home
Token Home
Feature activation+0.093
Depot
Token Depot
Feature activation+0.292
,
Token,
Feature activation+0.197
Intel
Token Intel
Feature activation+0.730
,
Token,
Feature activation+0.733
and
Token and
Feature activation+0.438
Dell
Token Dell
Feature activation+0.649
Computer
Token Computer
Feature activation+0.908
;
Token;
Feature activation+0.675
the
Token the
Feature activation+0.489
1990
Token 1990
Feature activation+0.236

INTERVAL 0.190 - 0.380
CONTAINS 0.058%

buy
Token buy
Feature activation+0.000
your
Token your
Feature activation+0.000
next
Token next
Feature activation+0.000
computer
Token computer
Feature activation+0.412
in
Token in
Feature activation+0.377
three
Token three
Feature activation+0.286
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
bits
Token bits
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
mon
Token mon
Feature activation+0.000
och
Tokenoch
Feature activation+0.000
rome
Tokenrome
Feature activation+0.013
icon
Token icon
Feature activation+0.278
,
Token,
Feature activation+0.080
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
set
Token set
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Everybody
TokenEverybody
Feature activation+0.000
loves
Token loves
Feature activation+0.000
devices
Token devices
Feature activation+0.131
,
Token,
Feature activation+0.203
but
Token but
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
loves
Token loves
Feature activation+0.000
cords
Token cords
Feature activation+0.000
.
Token.
Feature activation+0.000
now
Token now
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Mozilla
Token Mozilla
Feature activation+0.384
website
Token website
Feature activation+0.350
.
Token.
Feature activation+0.213
The
Token The
Feature activation+0.020
security
Token security
Feature activation+0.000
hole
Token hole
Feature activation+0.000
had
Token had
Feature activation+0.000
led
Token led
Feature activation+0.000
official
Token official
Feature activation+0.000
reason
Token reason
Feature activation+0.000
why
Token why
Feature activation+0.000
PS
Token PS
Feature activation+0.178
G
TokenG
Feature activation+0.496
were
Token were
Feature activation+0.266
seized
Token seized
Feature activation+0.143
upon
Token upon
Feature activation+0.000
by
Token by
Feature activation+0.000
Q
Token Q
Feature activation+0.040
SI
TokenSI
Feature activation+0.000

INTERVAL 0.000 - 0.190
CONTAINS 99.873%

pioneering
Token pioneering
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
words
Token words
Feature activation+0.000
of
Token of
Feature activation+0.000
Marie
Token Marie
Feature activation+0.000
Cur
Token Cur
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
and
Token and
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
to
Token to
Feature activation+0.000
us
Token us
Feature activation+0.000
,"
Token,"
Feature activation+0.000
de
Token de
Feature activation+0.000
Vill
Token Vill
Feature activation+0.000
iers
Tokeniers
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Elect
TokenElect
Feature activation+0.000
oral
Tokenoral
Feature activation+0.000
commission
Token commission
Feature activation+0.000
head
Token head
Feature activation+0.000
Maurice
Token Maurice
Feature activation+0.000
I
Token I
Feature activation+0.000
wu
Tokenwu
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
become
Token become
Feature activation+0.000
his
Token his
Feature activation+0.000
iron
Token iron
Feature activation+0.000
will
Token will
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
pride
Token pride
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
or
Token or
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
and
Token and
Feature activation+0.000
retrieve
Token retrieve
Feature activation+0.000
values
Token values
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 H2.7: (feature 5688)

TOP ACTIVATIONS
MAX = 1.251

warriors
Token warriors
Feature activation+0.341
within
Token within
Feature activation+0.218
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629
discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.000
remnants
Token remnants
Feature activation+0.000
of
Token of
Feature activation+0.000
Jesus
Token Jesus
Feature activation+0.725
Christ
Token Christ
Feature activation+1.155
âĢ
TokenâĢ
Feature activation+0.924
Ļ
TokenĻ
Feature activation+0.795
s
Tokens
Feature activation+0.739
cross
Token cross
Feature activation+0.940
.
Token.
Feature activation+0.685
within
Token within
Feature activation+0.218
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629
found
Token found
Feature activation+0.487
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
cross
Token cross
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Christian
Token Christian
Feature activation+0.620
symbol
Token symbol
Feature activation+1.078
âĢ
Token âĢ
Feature activation+0.758
ľ
Tokenľ
Feature activation+0.371
has
Tokenhas
Feature activation+0.256
no
Token no
Feature activation+0.132
place
Token place
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
give
Token give
Feature activation+0.000
their
Token their
Feature activation+0.000
suffering
Token suffering
Feature activation+0.000
unto
Token unto
Feature activation+0.201
God
Token God
Feature activation+1.058
.
Token.
Feature activation+0.973
They
Token They
Feature activation+0.887
lift
Token lift
Feature activation+0.777
it
Token it
Feature activation+0.428
up
Token up
Feature activation+0.303
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
City
Token City
Feature activation+0.000
of
Token of
Feature activation+0.000
Light
Token Light
Feature activation+0.000
Protestant
Token Protestant
Feature activation+0.350
church
Token church
Feature activation+1.055
,
Token,
Feature activation+0.829
said
Token said
Feature activation+0.542
he
Token he
Feature activation+0.406
believes
Token believes
Feature activation+0.696
the
Token the
Feature activation+0.619
last
Token last
Feature activation+0.256
few
Token few
Feature activation+0.188
verses
Token verses
Feature activation+0.761
of
Token of
Feature activation+0.675
the
Token the
Feature activation+0.669
Torah
Token Torah
Feature activation+1.050
.
Token.
Feature activation+1.014
I
Token I
Feature activation+0.864
dance
Token dance
Feature activation+0.624
because
Token because
Feature activation+0.488
I
Token I
Feature activation+0.508
lesiastical
Tokenlesiastical
Feature activation+1.032
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
and
Token and
Feature activation+0.903
,
Token,
Feature activation+0.749
in
Token in
Feature activation+0.656
general
Token general
Feature activation+0.487
,
Token,
Feature activation+0.373
by
Token by
Feature activation+0.000
God
Token God
Feature activation+0.679
,
Token,
Feature activation+0.633
and
Token and
Feature activation+0.577
that
Token that
Feature activation+0.422
God
Token God
Feature activation+1.040
had
Token had
Feature activation+0.968
called
Token called
Feature activation+1.032
upon
Token upon
Feature activation+1.015
him
Token him
Feature activation+0.965
to
Token to
Feature activation+0.945
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Scriptures
Token Scriptures
Feature activation+0.883
and
Token and
Feature activation+0.771
the
Token the
Feature activation+0.719
Ecc
Token Ecc
Feature activation+1.186
lesiastical
Tokenlesiastical
Feature activation+1.032
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
,
Token,
Feature activation+0.633
and
Token and
Feature activation+0.577
that
Token that
Feature activation+0.422
God
Token God
Feature activation+1.040
had
Token had
Feature activation+0.968
called
Token called
Feature activation+1.032
upon
Token upon
Feature activation+1.015
him
Token him
Feature activation+0.965
to
Token to
Feature activation+0.945
murder
Token murder
Feature activation+0.732
Dr
Token Dr
Feature activation+0.475
and
Token and
Feature activation+0.577
that
Token that
Feature activation+0.422
God
Token God
Feature activation+1.040
had
Token had
Feature activation+0.968
called
Token called
Feature activation+1.032
upon
Token upon
Feature activation+1.015
him
Token him
Feature activation+0.965
to
Token to
Feature activation+0.945
murder
Token murder
Feature activation+0.732
Dr
Token Dr
Feature activation+0.475
.
Token.
Feature activation+0.350
few
Token few
Feature activation+0.188
verses
Token verses
Feature activation+0.761
of
Token of
Feature activation+0.675
the
Token the
Feature activation+0.669
Torah
Token Torah
Feature activation+1.050
.
Token.
Feature activation+1.014
I
Token I
Feature activation+0.864
dance
Token dance
Feature activation+0.624
because
Token because
Feature activation+0.488
I
Token I
Feature activation+0.508
will
Token will
Feature activation+0.519
Scriptures
Token Scriptures
Feature activation+0.883
and
Token and
Feature activation+0.771
the
Token the
Feature activation+0.719
Ecc
Token Ecc
Feature activation+1.186
lesiastical
Tokenlesiastical
Feature activation+1.032
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
and
Token and
Feature activation+0.903
Ecc
Token Ecc
Feature activation+1.186
lesiastical
Tokenlesiastical
Feature activation+1.032
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
and
Token and
Feature activation+0.903
,
Token,
Feature activation+0.749
in
Token in
Feature activation+0.656
general
Token general
Feature activation+0.487
Christian
Token Christian
Feature activation+0.277
warriors
Token warriors
Feature activation+0.341
within
Token within
Feature activation+0.218
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629
found
Token found
Feature activation+0.487
it
Token it
Feature activation+0.333
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629
found
Token found
Feature activation+0.487
it
Token it
Feature activation+0.333
fascinating
Token fascinating
Feature activation+0.225
believe
Token believe
Feature activation+0.000
God
Token God
Feature activation+0.702
wants
Token wants
Feature activation+0.581
you
Token you
Feature activation+0.378
to
Token to
Feature activation+0.395
pray
Token pray
Feature activation+0.990
for
Token for
Feature activation+0.540
them
Token them
Feature activation+0.833
instead
Token instead
Feature activation+0.622
?
Token?
Feature activation+0.576
Yes
Token Yes
Feature activation+0.263
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
atheist
Token atheist
Feature activation+0.059
because
Token because
Feature activation+0.000
I
Token I
Feature activation+0.000
love
Token love
Feature activation+0.001
sin
Token sin
Feature activation+0.977
.
Token.
Feature activation+0.819
I
Token I
Feature activation+0.570
am
Token am
Feature activation+0.519
not
Token not
Feature activation+0.270
an
Token an
Feature activation+0.197

Top DFA by src position
MAX = 0.928

warriors
Token warriors
Feature activation+0.097
Top resid features:
within
Token within
Feature activation-0.109
Top resid features:
the
Token the
Feature activation-0.039
Top resid features:
Roman
Token Roman
Feature activation+0.328
Top resid features:
Catholic
Token Catholic
Feature activation+0.300
Top resid features:
Church
Token Church
Feature activation+0.526
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
discovery
Token discovery
Feature activation+0.032
Top resid features:
of
Token of
Feature activation-0.027
Top resid features:
remnants
Token remnants
Feature activation-0.011
Top resid features:
of
Token of
Feature activation-0.152
Top resid features:
Jesus
Token Jesus
Feature activation+0.464
Top resid features:
Christ
Token Christ
Feature activation+0.825
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:
cross
Token cross
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
warriors
Token warriors
Feature activation+0.061
Top resid features:
within
Token within
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.022
Top resid features:
Roman
Token Roman
Feature activation+0.351
Top resid features:
Catholic
Token Catholic
Feature activation+0.309
Top resid features:
Church
Token Church
Feature activation+0.443
Top resid features:
at
Token at
Feature activation-0.083
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.236
Top resid features:
cross
Token cross
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.113
Top resid features:
The
Token The
Feature activation-0.046
Top resid features:
Christian
Token Christian
Feature activation+0.783
Top resid features:
symbol
Token symbol
Feature activation+0.564
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
has
Tokenhas
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
ile
Tokenile
Feature activation+0.065
Top resid features:
give
Token give
Feature activation-0.030
Top resid features:
their
Token their
Feature activation-0.078
Top resid features:
suffering
Token suffering
Feature activation+0.076
Top resid features:
unto
Token unto
Feature activation+0.312
Top resid features:
God
Token God
Feature activation+0.781
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
lift
Token lift
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.288
Top resid features:
City
Token City
Feature activation-0.031
Top resid features:
of
Token of
Feature activation-0.069
Top resid features:
Light
Token Light
Feature activation-0.039
Top resid features:
Protestant
Token Protestant
Feature activation+0.493
Top resid features:
church
Token church
Feature activation+0.867
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
believes
Token believes
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.002
Top resid features:
few
Token few
Feature activation-0.002
Top resid features:
verses
Token verses
Feature activation+0.369
Top resid features:
of
Token of
Feature activation-0.111
Top resid features:
the
Token the
Feature activation-0.060
Top resid features:
Torah
Token Torah
Feature activation+0.616
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
dance
Token dance
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
lesiastical
Tokenlesiastical
Feature activation+0.107
Top resid features:
Teaching
Token Teaching
Feature activation+0.162
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
of
Token of
Feature activation-0.041
Top resid features:
classical
Token classical
Feature activation+0.150
Top resid features:
texts
Token texts
Feature activation+0.393
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
general
Token general
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.050
Top resid features:
God
Token God
Feature activation+0.396
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
and
Token and
Feature activation-0.166
Top resid features:
that
Token that
Feature activation-0.076
Top resid features:
God
Token God
Feature activation+0.789
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
called
Token called
Feature activation+0.000
Top resid features:
upon
Token upon
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.288
Top resid features:
Scriptures
Token Scriptures
Feature activation+0.695
Top resid features:
and
Token and
Feature activation-0.126
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ecc
Token Ecc
Feature activation+0.230
Top resid features:
lesiastical
Tokenlesiastical
Feature activation+0.399
Top resid features:
Teaching
Token Teaching
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.016
Top resid features:
God
Token God
Feature activation+0.346
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
and
Token and
Feature activation-0.132
Top resid features:
that
Token that
Feature activation+0.025
Top resid features:
God
Token God
Feature activation+0.538
Top resid features:
had
Token had
Feature activation-0.016
Top resid features:
called
Token called
Feature activation+0.217
Top resid features:
upon
Token upon
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.014
Top resid features:
God
Token God
Feature activation+0.249
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
and
Token and
Feature activation-0.069
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
God
Token God
Feature activation+0.474
Top resid features:
had
Token had
Feature activation-0.025
Top resid features:
called
Token called
Feature activation+0.121
Top resid features:
upon
Token upon
Feature activation+0.172
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.006
Top resid features:
few
Token few
Feature activation-0.003
Top resid features:
verses
Token verses
Feature activation+0.343
Top resid features:
of
Token of
Feature activation-0.043
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
Torah
Token Torah
Feature activation+0.601
Top resid features:
.
Token.
Feature activation-0.101
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
dance
Token dance
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
Scriptures
Token Scriptures
Feature activation+0.370
Top resid features:
and
Token and
Feature activation-0.120
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Ecc
Token Ecc
Feature activation+0.294
Top resid features:
lesiastical
Tokenlesiastical
Feature activation+0.170
Top resid features:
Teaching
Token Teaching
Feature activation+0.372
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
classical
Token classical
Feature activation+0.000
Top resid features:
texts
Token texts
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ecc
Token Ecc
Feature activation+0.164
Top resid features:
lesiastical
Tokenlesiastical
Feature activation+0.168
Top resid features:
Teaching
Token Teaching
Feature activation+0.223
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.044
Top resid features:
classical
Token classical
Feature activation+0.264
Top resid features:
texts
Token texts
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
general
Token general
Feature activation+0.000
Top resid features:
Christian
Token Christian
Feature activation+0.233
Top resid features:
warriors
Token warriors
Feature activation+0.119
Top resid features:
within
Token within
Feature activation-0.121
Top resid features:
the
Token the
Feature activation-0.080
Top resid features:
Roman
Token Roman
Feature activation+0.405
Top resid features:
Catholic
Token Catholic
Feature activation+0.480
Top resid features:
Church
Token Church
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:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
warriors
Token warriors
Feature activation+0.057
Top resid features:
within
Token within
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
Roman
Token Roman
Feature activation+0.313
Top resid features:
Catholic
Token Catholic
Feature activation+0.299
Top resid features:
Church
Token Church
Feature activation+0.406
Top resid features:
at
Token at
Feature activation-0.232
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
warriors
Token warriors
Feature activation+0.051
Top resid features:
within
Token within
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Roman
Token Roman
Feature activation+0.250
Top resid features:
Catholic
Token Catholic
Feature activation+0.245
Top resid features:
Church
Token Church
Feature activation+0.348
Top resid features:
at
Token at
Feature activation-0.154
Top resid features:
the
Token the
Feature activation-0.042
Top resid features:
time
Token time
Feature activation+0.145
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
believe
Token believe
Feature activation+0.104
Top resid features:
God
Token God
Feature activation+0.581
Top resid features:
wants
Token wants
Feature activation-0.035
Top resid features:
you
Token you
Feature activation-0.081
Top resid features:
to
Token to
Feature activation-0.178
Top resid features:
pray
Token pray
Feature activation+0.626
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
instead
Token instead
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Yes
Token Yes
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.230
Top resid features:
atheist
Token atheist
Feature activation+0.407
Top resid features:
because
Token because
Feature activation-0.004
Top resid features:
I
Token I
Feature activation-0.082
Top resid features:
love
Token love
Feature activation-0.163
Top resid features:
sin
Token sin
Feature activation+0.928
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
am
Token am
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.11

Head 2: 0.04

Head 3: 0.04

Head 4: 0.03

Head 5: 0.05

Head 6: 0.06

Head 7: 0.18

Head 8: 0.04

Head 9: 0.11

Head 10: 0.19

Head 11: 0.09

Positive logits

Christianity1.56

Biblical1.52

Christians1.45

churches1.42

Protestants1.41

Jerusalem1.38

Judaism1.37

ospels1.35

Zionism1.34

biblical1.32

theolog1.31

worship1.31

Scripture1.31

Religion1.29

Bahá1.29

Psal1.28

Jews1.28

Juda1.27

Catholics1.26

Hebrew1.25

Negative logits

captcha-1.27

metry-1.20

bender-1.16

scram-1.12

pricing-1.08

azard-1.07

escalate-1.07

IPM-1.06

UDP-1.06

metric-1.05

RJ-1.03

BUG-1.02

chemistry-1.01

agame-1.00

TOR-0.99

CPU-0.99

PID-0.98

rigging-0.98

UFC-0.98

bots-0.97

INTERVAL 1.126 - 1.251
CONTAINS 0.000%

discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.000
remnants
Token remnants
Feature activation+0.000
of
Token of
Feature activation+0.000
Jesus
Token Jesus
Feature activation+0.725
Christ
Token Christ
Feature activation+1.155
âĢ
TokenâĢ
Feature activation+0.924
Ļ
TokenĻ
Feature activation+0.795
s
Tokens
Feature activation+0.739
cross
Token cross
Feature activation+0.940
.
Token.
Feature activation+0.685
warriors
Token warriors
Feature activation+0.341
within
Token within
Feature activation+0.218
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629

INTERVAL 1.001 - 1.126
CONTAINS 0.001%

few
Token few
Feature activation+0.188
verses
Token verses
Feature activation+0.761
of
Token of
Feature activation+0.675
the
Token the
Feature activation+0.669
Torah
Token Torah
Feature activation+1.050
.
Token.
Feature activation+1.014
I
Token I
Feature activation+0.864
dance
Token dance
Feature activation+0.624
because
Token because
Feature activation+0.488
I
Token I
Feature activation+0.508
will
Token will
Feature activation+0.519
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Scriptures
Token Scriptures
Feature activation+0.883
and
Token and
Feature activation+0.771
the
Token the
Feature activation+0.719
Ecc
Token Ecc
Feature activation+1.186
lesiastical
Tokenlesiastical
Feature activation+1.032
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
Scriptures
Token Scriptures
Feature activation+0.883
and
Token and
Feature activation+0.771
the
Token the
Feature activation+0.719
Ecc
Token Ecc
Feature activation+1.186
lesiastical
Tokenlesiastical
Feature activation+1.032
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
and
Token and
Feature activation+0.903
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
City
Token City
Feature activation+0.000
of
Token of
Feature activation+0.000
Light
Token Light
Feature activation+0.000
Protestant
Token Protestant
Feature activation+0.350
church
Token church
Feature activation+1.055
,
Token,
Feature activation+0.829
said
Token said
Feature activation+0.542
he
Token he
Feature activation+0.406
believes
Token believes
Feature activation+0.696
the
Token the
Feature activation+0.619
within
Token within
Feature activation+0.218
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629
found
Token found
Feature activation+0.487

INTERVAL 0.875 - 1.001
CONTAINS 0.003%

that
Token that
Feature activation+0.422
God
Token God
Feature activation+1.040
had
Token had
Feature activation+0.968
called
Token called
Feature activation+1.032
upon
Token upon
Feature activation+1.015
him
Token him
Feature activation+0.965
to
Token to
Feature activation+0.945
murder
Token murder
Feature activation+0.732
Dr
Token Dr
Feature activation+0.475
.
Token.
Feature activation+0.350
Britt
Token Britt
Feature activation+0.312
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
of
Token of
Feature activation+0.000
Jesus
Token Jesus
Feature activation+0.960
of
Token of
Feature activation+0.924
whom
Token whom
Feature activation+0.896
we
Token we
Feature activation+0.877
here
Token here
Feature activation+0.756
on
Token on
Feature activation+0.421
Earth
Token Earth
Feature activation+0.503
have
Token have
Feature activation+0.403
never
Token never
Feature activation+0.379
Teaching
Token Teaching
Feature activation+1.007
,
Token,
Feature activation+0.928
of
Token of
Feature activation+0.905
classical
Token classical
Feature activation+1.003
texts
Token texts
Feature activation+1.049
and
Token and
Feature activation+0.903
,
Token,
Feature activation+0.749
in
Token in
Feature activation+0.656
general
Token general
Feature activation+0.487
,
Token,
Feature activation+0.373
of
Token of
Feature activation+0.298
Christian
Token Christian
Feature activation+0.277
warriors
Token warriors
Feature activation+0.341
within
Token within
Feature activation+0.218
the
Token the
Feature activation+0.230
Roman
Token Roman
Feature activation+0.855
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
atheist
Token atheist
Feature activation+0.059
because
Token because
Feature activation+0.000
I
Token I
Feature activation+0.000
love
Token love
Feature activation+0.001
sin
Token sin
Feature activation+0.977
.
Token.
Feature activation+0.819
I
Token I
Feature activation+0.570
am
Token am
Feature activation+0.519
not
Token not
Feature activation+0.270
an
Token an
Feature activation+0.197

INTERVAL 0.750 - 0.875
CONTAINS 0.004%

member
Token member
Feature activation+0.562
of
Token of
Feature activation+0.509
the
Token the
Feature activation+0.545
Syn
Token Syn
Feature activation+0.791
od
Tokenod
Feature activation+0.934
,
Token,
Feature activation+0.790
said
Token said
Feature activation+0.530
he
Token he
Feature activation+0.406
would
Token would
Feature activation+0.197
be
Token be
Feature activation+0.170
voting
Token voting
Feature activation+0.225
Catholic
Token Catholic
Feature activation+0.998
Church
Token Church
Feature activation+1.251
at
Token at
Feature activation+1.109
the
Token the
Feature activation+0.993
time
Token time
Feature activation+0.991
.
Token.
Feature activation+0.785
I
Token I
Feature activation+0.629
found
Token found
Feature activation+0.487
it
Token it
Feature activation+0.333
fascinating
Token fascinating
Feature activation+0.225
,
Token,
Feature activation+0.097
Christians
Token Christians
Feature activation+0.488
,
Token,
Feature activation+0.529
but
Token but
Feature activation+0.357
minister
Token minister
Feature activation+0.639
unto
Token unto
Feature activation+0.564
them
Token them
Feature activation+0.822
âĢ
TokenâĢ
Feature activation+0.654
Ŀ
TokenĿ
Feature activation+0.422
.
Token.
Feature activation+0.466
Is
Token Is
Feature activation+0.250
it
Token it
Feature activation+0.182
virgin
Token virgin
Feature activation+0.343
birth
Token birth
Feature activation+0.432
to
Token to
Feature activation+0.375
the
Token the
Feature activation+0.343
Messiah
Token Messiah
Feature activation+0.757
(
Token (
Feature activation+0.793
L
TokenL
Feature activation+0.723
k
Tokenk
Feature activation+0.561
1
Token 1
Feature activation+0.603
:
Token:
Feature activation+0.506
26
Token26
Feature activation+0.289
remnants
Token remnants
Feature activation+0.000
of
Token of
Feature activation+0.000
Jesus
Token Jesus
Feature activation+0.725
Christ
Token Christ
Feature activation+1.155
âĢ
TokenâĢ
Feature activation+0.924
Ļ
TokenĻ
Feature activation+0.795
s
Tokens
Feature activation+0.739
cross
Token cross
Feature activation+0.940
.
Token.
Feature activation+0.685
The
Token The
Feature activation+0.538
pope
Token pope
Feature activation+0.833

INTERVAL 0.625 - 0.750
CONTAINS 0.007%

abortion
Token abortion
Feature activation+0.000
was
Token was
Feature activation+0.000
sanctioned
Token sanctioned
Feature activation+0.000
by
Token by
Feature activation+0.000
God
Token God
Feature activation+0.679
,
Token,
Feature activation+0.633
and
Token and
Feature activation+0.577
that
Token that
Feature activation+0.422
God
Token God
Feature activation+1.040
had
Token had
Feature activation+0.968
called
Token called
Feature activation+1.032
ami
Tokenami
Feature activation+0.000
.
Token.
Feature activation+0.000
Appears
Token Appears
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Bible
Token Bible
Feature activation+0.665
at
Token at
Feature activation+0.833
:
Token:
Feature activation+0.715
Genesis
Token Genesis
Feature activation+0.847
39
Token 39
Feature activation+0.871
:
Token:
Feature activation+0.716
hs
Tokenhs
Feature activation+0.392
.
Token.
Feature activation+0.333
D
Token D
Feature activation+0.316
abb
Tokenabb
Feature activation+0.568
i
Tokeni
Feature activation+0.861
Va
Token Va
Feature activation+0.725
ale
Tokenale
Feature activation+0.552
Par
Token Par
Feature activation+0.363
ne
Tokenne
Feature activation+0.162
is
Token is
Feature activation+0.133
a
Token a
Feature activation+0.025
,
Token,
Feature activation+0.529
but
Token but
Feature activation+0.357
minister
Token minister
Feature activation+0.639
unto
Token unto
Feature activation+0.564
them
Token them
Feature activation+0.822
âĢ
TokenâĢ
Feature activation+0.654
Ŀ
TokenĿ
Feature activation+0.422
.
Token.
Feature activation+0.466
Is
Token Is
Feature activation+0.250
it
Token it
Feature activation+0.182
possible
Token possible
Feature activation+0.000
Guide
Token Guide
Feature activation+0.000
to
Token to
Feature activation+0.000
Spirit
Token Spirit
Feature activation+0.217
uality
Tokenuality
Feature activation+0.411
without
Token without
Feature activation+0.432
Religion
Token Religion
Feature activation+0.631
.
Token.
Feature activation+0.549
Ċ
TokenĊ
Feature activation+0.337
Ċ
TokenĊ
Feature activation+0.219
To
TokenTo
Feature activation+0.239
refute
Token refute
Feature activation+0.231

INTERVAL 0.500 - 0.625
CONTAINS 0.013%

could
Token could
Feature activation+0.000
include
Token include
Feature activation+0.000
these
Token these
Feature activation+0.000
words
Token words
Feature activation+0.233
from
Token from
Feature activation+0.000
God
Token God
Feature activation+0.594
:
Token:
Feature activation+0.582
Ċ
TokenĊ
Feature activation+0.328
Ċ
TokenĊ
Feature activation+0.224
I
TokenI
Feature activation+0.121
had
Token had
Feature activation+0.000
Islam
Token Islam
Feature activation+0.208
is
Token is
Feature activation+0.024
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.000
.
Token.
Feature activation+0.000
Islam
Token Islam
Feature activation+0.512
is
Token is
Feature activation+0.338
peace
Token peace
Feature activation+0.478
.
Token.
Feature activation+0.305
âĢ
TokenâĢ
Feature activation+0.302
Ŀ
TokenĿ
Feature activation+0.186
Gn
Token Gn
Feature activation+0.416
ostics
Tokenostics
Feature activation+0.541
believed
Token believed
Feature activation+0.855
that
Token that
Feature activation+0.753
they
Token they
Feature activation+0.700
were
Token were
Feature activation+0.615
priv
Token priv
Feature activation+0.666
y
Tokeny
Feature activation+0.396
to
Token to
Feature activation+0.480
a
Token a
Feature activation+0.409
secret
Token secret
Feature activation+0.405
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
Jews
Token Jews
Feature activation+0.311
and
Token and
Feature activation+0.305
Muslims
Token Muslims
Feature activation+0.500
,
Token,
Feature activation+0.507
though
Token though
Feature activation+0.446
Arabs
Token Arabs
Feature activation+0.488
have
Token have
Feature activation+0.222
charged
Token charged
Feature activation+0.179
Israeli
Token Israeli
Feature activation+0.000
strong
Token strong
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
do
Token do
Feature activation+0.000
Buddh
Token Buddh
Feature activation+0.522
ists
Tokenists
Feature activation+0.541
who
Token who
Feature activation+0.337
visit
Token visit
Feature activation+0.333
S
Token S
Feature activation+0.602
arn
Tokenarn
Feature activation+0.513

INTERVAL 0.375 - 0.500
CONTAINS 0.020%

unto
Token unto
Feature activation+0.201
God
Token God
Feature activation+1.058
.
Token.
Feature activation+0.973
They
Token They
Feature activation+0.887
lift
Token lift
Feature activation+0.777
it
Token it
Feature activation+0.428
up
Token up
Feature activation+0.303
to
Token to
Feature activation+0.287
the
Token the
Feature activation+0.289
Father
Token Father
Feature activation+0.533
in
Token in
Feature activation+0.611
classical
Token classical
Feature activation+0.000
empires
Token empires
Feature activation+0.000
of
Token of
Feature activation+0.000
Greece
Token Greece
Feature activation+0.285
and
Token and
Feature activation+0.170
Rome
Token Rome
Feature activation+0.430
were
Token were
Feature activation+0.299
based
Token based
Feature activation+0.169
on
Token on
Feature activation+0.129
slave
Token slave
Feature activation+0.213
labor
Token labor
Feature activation+0.173
á¹
Tokená¹
Feature activation+0.115
£
Token£
Feature activation+0.258
a
Tokena
Feature activation+0.373
s
Token s
Feature activation+0.416
Å«
Tokenū
Feature activation+0.443
k
Tokenk
Feature activation+0.387
ta
Tokenta
Feature activation+0.338
of
Token of
Feature activation+0.359
Rig
Token Rig
Feature activation+0.318
V
Token V
Feature activation+0.215
eda
Tokeneda
Feature activation+0.276
despise
Token despise
Feature activation+0.066
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
poorest
Token poorest
Feature activation+0.000
of
Token of
Feature activation+0.000
Christians
Token Christians
Feature activation+0.488
,
Token,
Feature activation+0.529
but
Token but
Feature activation+0.357
minister
Token minister
Feature activation+0.639
unto
Token unto
Feature activation+0.564
them
Token them
Feature activation+0.822
a
Token a
Feature activation+0.327
touch
Token touch
Feature activation+0.256
of
Token of
Feature activation+0.264
mercy
Token mercy
Feature activation+0.445
and
Token and
Feature activation+0.420
to
Token to
Feature activation+0.381
plant
Token plant
Feature activation+0.481
joy
Token joy
Feature activation+0.373
on
Token on
Feature activation+0.343
the
Token the
Feature activation+0.239
hearts
Token hearts
Feature activation+0.395

INTERVAL 0.250 - 0.375
CONTAINS 0.036%

necessary
Token necessary
Feature activation+0.000
for
Token for
Feature activation+0.000
us
Token us
Feature activation+0.000
as
Token as
Feature activation+0.000
Egyptians
Token Egyptians
Feature activation+0.071
to
Token to
Feature activation+0.257
enrich
Token enrich
Feature activation+0.169
this
Token this
Feature activation+0.000
picture
Token picture
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.005
and
Tokenand
Feature activation+0.000
become
Token become
Feature activation+0.074
acceptable
Token acceptable
Feature activation+0.002
just
Token just
Feature activation+0.000
because
Token because
Feature activation+0.000
God
Token God
Feature activation+0.493
says
Token says
Feature activation+0.356
so
Token so
Feature activation+0.217
?
Token?
Feature activation+0.255
Ċ
TokenĊ
Feature activation+0.101
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
that
Token that
Feature activation+0.054
Jews
Token Jews
Feature activation+0.302
reve
Token reve
Feature activation+0.418
re
Tokenre
Feature activation+0.330
as
Token as
Feature activation+0.380
the
Token the
Feature activation+0.332
Temple
Token Temple
Feature activation+0.496
Mount
Token Mount
Feature activation+0.347
and
Token and
Feature activation+0.327
Muslims
Token Muslims
Feature activation+0.462
as
Token as
Feature activation+0.228
and
Token and
Feature activation+0.472
morality
Token morality
Feature activation+0.725
,
Token,
Feature activation+0.467
Hit
Token Hit
Feature activation+0.546
chens
Tokenchens
Feature activation+0.368
needs
Token needs
Feature activation+0.276
to
Token to
Feature activation+0.149
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
religion
Token religion
Feature activation+0.339
itself
Token itself
Feature activation+0.217
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
priests
Token priests
Feature activation+0.593
and
Token and
Feature activation+0.516
nine
Token nine
Feature activation+0.568
years
Token years
Feature activation+0.346
after
Token after
Feature activation+0.345
electing
Token electing
Feature activation+0.317
its
Token its
Feature activation+0.221
first
Token first
Feature activation+0.083
gay
Token gay
Feature activation+0.026

INTERVAL 0.125 - 0.250
CONTAINS 0.065%

âĢ
TokenâĢ
Feature activation+0.693
Ŀ
TokenĿ
Feature activation+0.516
.
Token.
Feature activation+0.479
Ċ
TokenĊ
Feature activation+0.274
Ċ
TokenĊ
Feature activation+0.158
Hyp
TokenHyp
Feature activation+0.200
ocr
Tokenocr
Feature activation+0.008
ite
Tokenite
Feature activation+0.190
Ċ
TokenĊ
Feature activation+0.152
Ċ
TokenĊ
Feature activation+0.048
To
TokenTo
Feature activation+0.042
and
Token and
Feature activation+0.000
shape
Token shape
Feature activation+0.000
the
Token the
Feature activation+0.000
Be
Token Be
Feature activation+0.000
eth
Tokeneth
Feature activation+0.000
oven
Tokenoven
Feature activation+0.140
persona
Token persona
Feature activation+0.051
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
to
Token to
Feature activation+0.000
remind
Token remind
Feature activation+0.000
me
Token me
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
Christmas
Token Christmas
Feature activation+0.134
means
Token means
Feature activation+0.077
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Up
Token Up
Feature activation+0.000
:
Token:
Feature activation+0.000
A
Token A
Feature activation+0.000
Guide
Token Guide
Feature activation+0.000
to
Token to
Feature activation+0.000
Spirit
Token Spirit
Feature activation+0.217
uality
Tokenuality
Feature activation+0.411
without
Token without
Feature activation+0.432
Religion
Token Religion
Feature activation+0.631
.
Token.
Feature activation+0.549
Ċ
TokenĊ
Feature activation+0.337
with
Token with
Feature activation+0.070
a
Token a
Feature activation+0.027
conscience
Token conscience
Feature activation+0.371
did
Token did
Feature activation+0.225
little
Token little
Feature activation+0.178
or
Token or
Feature activation+0.213
nothing
Token nothing
Feature activation+0.000
while
Token while
Feature activation+0.000
evil
Token evil
Feature activation+0.141
was
Token was
Feature activation+0.000
tri
Token tri
Feature activation+0.000

INTERVAL 0.000 - 0.125
CONTAINS 99.850%

ICAL
TokenICAL
Feature activation+0.000
,
Token,
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Oscar
Token Oscar
Feature activation+0.000
®
Token®
Feature activation+0.000
winning
Token winning
Feature activation+0.000
Dream
Token Dream
Feature activation+0.000
Works
TokenWorks
Feature activation+0.000
film
Token film
Feature activation+0.000
,
Token,
Feature activation+0.000
make
Token make
Feature activation+0.000
sure
Token sure
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
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+0.000
of
Token of
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
"
Token "
Feature activation+0.000
Person
TokenPerson
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Year
Token Year
Feature activation+0.000
."
Token."
Feature activation+0.000
production
Token production
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
particular
Token particular
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
point
Token point
Feature activation+0.000
I
Token I
Feature activation+0.000
first
Token first
Feature activation+0.000
made
Token made
Feature activation+0.000
here
Token here
Feature activation+0.000
the
Token the
Feature activation+0.000
border
Token border
Feature activation+0.000
bill
Token bill
Feature activation+0.000
before
Token before
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
leave
Token leave
Feature activation+0.000
town
Token town
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Under
TokenUnder
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