H8.3 top features

Top feature 0 in H8.3: (feature 4287)

TOP ACTIVATIONS
MAX = 3.031

currently
Token currently
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
missing
Token missing
Feature activation+3.031
the
Token the
Feature activation+2.034
only
Token only
Feature activation+1.549
opportunity
Token opportunity
Feature activation+0.000
for
Token for
Feature activation+0.220
grace
Token grace
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+1.437
the
Token the
Feature activation+2.676
DEA
Token DEA
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
che
Tokenche
Feature activation+0.000
dule
Tokendule
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.343
remain
Token remain
Feature activation+1.196
a
Token a
Feature activation+0.788
member
Token member
Feature activation+1.921
of
Token of
Feature activation+2.418
the
Token the
Feature activation+2.243
European
Token European
Feature activation+0.086
Union
Token Union
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.179
to
Token to
Feature activation+0.343
remain
Token remain
Feature activation+1.196
a
Token a
Feature activation+0.788
member
Token member
Feature activation+1.921
of
Token of
Feature activation+2.418
the
Token the
Feature activation+2.243
European
Token European
Feature activation+0.086
Union
Token Union
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.179
has
Token has
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
publications
Token publications
Feature activation+0.000
on
Token on
Feature activation+1.469
the
Token the
Feature activation+2.181
Internet
Token Internet
Feature activation+0.191
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
interest
Token interest
Feature activation+0.000
rate
Token rate
Feature activation+0.000
differential
Token differential
Feature activation+0.000
between
Token between
Feature activation+0.983
the
Token the
Feature activation+1.464
two
Token two
Feature activation+2.165
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Drug
Token Drug
Feature activation+0.000
Enforcement
Token Enforcement
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
asking
Token asking
Feature activation+2.104
that
Token that
Feature activation+1.348
federal
Token federal
Feature activation+0.103
controls
Token controls
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+2.071
it
Token it
Feature activation+0.026
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
purposes
Token purposes
Feature activation+0.000
of
Token of
Feature activation+1.477
the
Token the
Feature activation+2.061
public
Token public
Feature activation+0.032
broadcaster
Token broadcaster
Feature activation+0.143
,
Token,
Feature activation+0.000
guarantees
Token guarantees
Feature activation+0.000
its
Token its
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
missing
Token missing
Feature activation+3.031
the
Token the
Feature activation+2.034
only
Token only
Feature activation+1.549
opportunity
Token opportunity
Feature activation+0.000
for
Token for
Feature activation+0.220
grace
Token grace
Feature activation+0.000
that
Token that
Feature activation+0.143
it
Token it
Feature activation+0.222
has
Token has
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.568
leave
Token leave
Feature activation+1.895
the
Token the
Feature activation+1.993
European
Token European
Feature activation+0.277
"
Token "
Feature activation+0.000
family
Tokenfamily
Feature activation+0.000
."
Token."
Feature activation+0.045
Ċ
TokenĊ
Feature activation+0.000
UK
Token UK
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
living
Token living
Feature activation+0.570
and
Token and
Feature activation+0.000
working
Token working
Feature activation+1.434
in
Token in
Feature activation+1.958
Europe
Token Europe
Feature activation+0.000
:
Token:
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
refusal
Token refusal
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+1.953
the
Token the
Feature activation+1.949
debt
Token debt
Feature activation+0.000
ceiling
Token ceiling
Feature activation+0.000
unless
Token unless
Feature activation+0.000
the
Token the
Feature activation+0.162
refusal
Token refusal
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+1.953
the
Token the
Feature activation+1.949
debt
Token debt
Feature activation+0.000
ceiling
Token ceiling
Feature activation+0.000
unless
Token unless
Feature activation+0.000
the
Token the
Feature activation+0.162
White
Token White
Feature activation+0.000
country
Token country
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.343
remain
Token remain
Feature activation+1.196
a
Token a
Feature activation+0.788
member
Token member
Feature activation+1.921
of
Token of
Feature activation+2.418
the
Token the
Feature activation+2.243
European
Token European
Feature activation+0.086
Union
Token Union
Feature activation+0.000
or
Token or
Feature activation+0.000
that
Token that
Feature activation+0.457
it
Token it
Feature activation+0.222
has
Token has
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.568
leave
Token leave
Feature activation+1.895
the
Token the
Feature activation+1.993
European
Token European
Feature activation+0.277
"
Token "
Feature activation+0.000
family
Tokenfamily
Feature activation+0.000
."
Token."
Feature activation+0.045
Republicans
Token Republicans
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.552
five
Token five
Feature activation+0.000
-
Token-
Feature activation+0.000
member
Tokenmember
Feature activation+1.890
NL
Token NL
Feature activation+0.000
RB
TokenRB
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
only
Token only
Feature activation+0.000
one
Token one
Feature activation+0.000
reason
Token reason
Feature activation+0.000
he
Token he
Feature activation+0.000
sued
Token sued
Feature activation+1.711
the
Token the
Feature activation+1.884
ABC
Token ABC
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
executive
Token executive
Feature activation+0.000
committee
Token committee
Feature activation+0.000
must
Token must
Feature activation+0.000
file
Token file
Feature activation+0.000
reports
Token reports
Feature activation+0.000
with
Token with
Feature activation+1.847
the
Token the
Feature activation+1.635
FEC
Token FEC
Feature activation+0.000
,
Token,
Feature activation+0.000
listing
Token listing
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
helping
Token helping
Feature activation+0.526
us
Token us
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
on
Token on
Feature activation+0.684
the
Token the
Feature activation+1.809
road
Token road
Feature activation+0.000
ways
Tokenways
Feature activation+0.000
,
Token,
Feature activation+0.000
providing
Token providing
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000

Top DFA by src position
MAX = 2.975

and
Token and
Feature activation-0.000
Top resid features:
unable
Token unable
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
find
Token find
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Lord
Token Lord
Feature activation+2.975
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+0.034
Top resid features:
hand
Token hand
Feature activation+0.006
Top resid features:
working
Token working
Feature activation+0.025
Top resid features:
letter
Token letter
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Drug
Token Drug
Feature activation+0.003
Top resid features:
Enforcement
Token Enforcement
Feature activation+0.007
Top resid features:
Administration
Token Administration
Feature activation+2.971
Top resid features:
asking
Token asking
Feature activation-0.007
Top resid features:
that
Token that
Feature activation-0.005
Top resid features:
federal
Token federal
Feature activation-0.021
Top resid features:
controls
Token controls
Feature activation+0.002
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
its
Token its
Feature activation-0.002
Top resid features:
future
Token future
Feature activation+0.005
Top resid features:
relationship
Token relationship
Feature activation+0.004
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
EU
Token EU
Feature activation+2.143
Top resid features:
now
Token now
Feature activation-0.000
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
decided
Token decided
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.006
Top resid features:
future
Token future
Feature activation+0.005
Top resid features:
relationship
Token relationship
Feature activation+0.002
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
EU
Token EU
Feature activation+1.715
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
has
Token has
Feature activation+0.004
Top resid features:
decided
Token decided
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
courts
Token courts
Feature activation-0.000
Top resid features:
will
Token will
Feature activation+0.001
Top resid features:
recognize
Token recognize
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Internet
Token Internet
Feature activation+2.085
Top resid features:
as
Token as
Feature activation+0.149
Top resid features:
a
Token a
Feature activation+0.048
Top resid features:
medium
Token medium
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
publication
Token publication
Feature activation+0.017
Top resid features:
dollar
Token dollar
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
US
Token US
Feature activation+0.894
Top resid features:
dollar
Token dollar
Feature activation+1.667
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
interest
Token interest
Feature activation+0.009
Top resid features:
rate
Token rate
Feature activation+0.022
Top resid features:
letter
Token letter
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.015
Top resid features:
Drug
Token Drug
Feature activation+0.011
Top resid features:
Enforcement
Token Enforcement
Feature activation+0.010
Top resid features:
Administration
Token Administration
Feature activation+2.664
Top resid features:
asking
Token asking
Feature activation-0.014
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
federal
Token federal
Feature activation+0.000
Top resid features:
controls
Token controls
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
After
Token After
Feature activation+0.003
Top resid features:
finding
Token finding
Feature activation-0.002
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
Cup
Token Cup
Feature activation+1.043
Top resid features:
has
Token has
Feature activation+0.184
Top resid features:
been
Token been
Feature activation+0.103
Top resid features:
mountain
Token mountain
Feature activation+0.003
Top resid features:
climbing
Token climbing
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
constitutional
Token constitutional
Feature activation-0.003
Top resid features:
basis
Token basis
Feature activation-0.006
Top resid features:
for
Token for
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
BBC
Token BBC
Feature activation+2.363
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
sets
Token sets
Feature activation+0.010
Top resid features:
out
Token out
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
public
Token public
Feature activation-0.015
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
unable
Token unable
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
find
Token find
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Lord
Token Lord
Feature activation+1.999
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.055
Top resid features:
hand
Token hand
Feature activation+0.013
Top resid features:
working
Token working
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
keep
Token keep
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
privileges
Token privileges
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
EU
Token EU
Feature activation+1.050
Top resid features:
membership
Token membership
Feature activation+0.010
Top resid features:
without
Token without
Feature activation+0.001
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
obligations
Token obligations
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
EU
Token EU
Feature activation+0.273
Top resid features:
citizens
Token citizens
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.013
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
UK
Token UK
Feature activation+1.020
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
UK
Token UK
Feature activation+0.540
Top resid features:
citizens
Token citizens
Feature activation+0.047
Top resid features:
living
Token living
Feature activation+0.060
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
an
Token an
Feature activation-0.003
Top resid features:
increase
Token increase
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
debt
Token debt
Feature activation+0.098
Top resid features:
limit
Token limit
Feature activation+2.361
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
Treasury
Token Treasury
Feature activation+0.004
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
increase
Token increase
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
debt
Token debt
Feature activation+0.070
Top resid features:
limit
Token limit
Feature activation+2.517
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
Treasury
Token Treasury
Feature activation+0.002
Top resid features:
its
Token its
Feature activation+0.005
Top resid features:
future
Token future
Feature activation+0.002
Top resid features:
relationship
Token relationship
Feature activation+0.001
Top resid features:
with
Token with
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
EU
Token EU
Feature activation+1.922
Top resid features:
now
Token now
Feature activation-0.011
Top resid features:
that
Token that
Feature activation-0.009
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
decided
Token decided
Feature activation-0.001
Top resid features:
its
Token its
Feature activation-0.009
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
relationship
Token relationship
Feature activation+0.002
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
EU
Token EU
Feature activation+1.606
Top resid features:
now
Token now
Feature activation+0.011
Top resid features:
that
Token that
Feature activation+0.030
Top resid features:
it
Token it
Feature activation-0.023
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
decided
Token decided
Feature activation+0.012
Top resid features:
by
Token by
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
National
Token National
Feature activation-0.007
Top resid features:
Labor
Token Labor
Feature activation-0.001
Top resid features:
Relations
Token Relations
Feature activation+0.029
Top resid features:
Board
Token Board
Feature activation+2.313
Top resid features:
reversed
Token reversed
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
standard
Token standard
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.002
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
gered
Tokengered
Feature activation+0.003
Top resid features:
by
Token by
Feature activation-0.002
Top resid features:
criticism
Token criticism
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
ABC
Token ABC
Feature activation+1.675
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.000
Top resid features:
're
Token're
Feature activation-0.000
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
FEC
Token FEC
Feature activation+1.988
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.001
Top resid features:
resolved
Token resolved
Feature activation+0.002
Top resid features:
."
Token."
Feature activation+0.003
Top resid features:
following
Token following
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
C
Token C
Feature activation+0.004
Top resid features:
TA
TokenTA
Feature activation-0.019
Top resid features:
Blue
Token Blue
Feature activation+0.005
Top resid features:
Line
Token Line
Feature activation+2.128
Top resid features:
plans
Token plans
Feature activation+0.004
Top resid features:
very
Token very
Feature activation+0.002
Top resid features:
closely
Token closely
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.04

Head 3: 0.49

Head 4: 0.03

Head 5: 0.06

Head 6: 0.02

Head 7: 0.06

Head 8: 0.05

Head 9: 0.04

Head 10: 0.10

Head 11: 0.06

Positive logits

roying2.50

NetMessage2.43

the2.42

los2.18

thro2.10

quartered2.10

largeDownload2.06

guts2.05

rieg2.04

verning2.02

IELD2.02

brook2.01

ettlement2.01

itaire2.01

udd2.00

immersion1.98

ongyang1.98

tha1.97

uala1.94

ingred1.91

Negative logits

Student-2.10

Gamble-2.10

ymes-2.03

Georg-1.96

Pyro-1.91

Greek-1.89

Shake-1.87

Students-1.86

Cartoon-1.84

Statement-1.78

Shar-1.77

Actor-1.76

Dunham-1.76

TY-1.74

diagn-1.71

Tyson-1.68

Artist-1.66

Metal-1.66

Sym-1.66

Appearance-1.64

INTERVAL 2.728 - 3.031
CONTAINS 0.000%

currently
Token currently
Feature activation+0.000
,
Token,
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
missing
Token missing
Feature activation+3.031
the
Token the
Feature activation+2.034
only
Token only
Feature activation+1.549
opportunity
Token opportunity
Feature activation+0.000
for
Token for
Feature activation+0.220
grace
Token grace
Feature activation+0.000

INTERVAL 2.425 - 2.728
CONTAINS 0.000%

m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+1.437
the
Token the
Feature activation+2.676
DEA
Token DEA
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
che
Tokenche
Feature activation+0.000
dule
Tokendule
Feature activation+0.000

INTERVAL 2.122 - 2.425
CONTAINS 0.000%

ent
Tokenent
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
publications
Token publications
Feature activation+0.000
on
Token on
Feature activation+1.469
the
Token the
Feature activation+2.181
Internet
Token Internet
Feature activation+0.191
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
interest
Token interest
Feature activation+0.000
rate
Token rate
Feature activation+0.000
differential
Token differential
Feature activation+0.000
between
Token between
Feature activation+0.983
the
Token the
Feature activation+1.464
two
Token two
Feature activation+2.165
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.343
remain
Token remain
Feature activation+1.196
a
Token a
Feature activation+0.788
member
Token member
Feature activation+1.921
of
Token of
Feature activation+2.418
the
Token the
Feature activation+2.243
European
Token European
Feature activation+0.086
Union
Token Union
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.179
to
Token to
Feature activation+0.343
remain
Token remain
Feature activation+1.196
a
Token a
Feature activation+0.788
member
Token member
Feature activation+1.921
of
Token of
Feature activation+2.418
the
Token the
Feature activation+2.243
European
Token European
Feature activation+0.086
Union
Token Union
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.179
has
Token has
Feature activation+0.000

INTERVAL 1.819 - 2.122
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
refusal
Token refusal
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+1.953
the
Token the
Feature activation+1.949
debt
Token debt
Feature activation+0.000
ceiling
Token ceiling
Feature activation+0.000
unless
Token unless
Feature activation+0.000
the
Token the
Feature activation+0.162
UK
Token UK
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
living
Token living
Feature activation+0.570
and
Token and
Feature activation+0.000
working
Token working
Feature activation+1.434
in
Token in
Feature activation+1.958
Europe
Token Europe
Feature activation+0.000
:
Token:
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
t
Tokent
Feature activation+0.000
executive
Token executive
Feature activation+0.000
committee
Token committee
Feature activation+0.000
must
Token must
Feature activation+0.000
file
Token file
Feature activation+0.000
reports
Token reports
Feature activation+0.000
with
Token with
Feature activation+1.847
the
Token the
Feature activation+1.635
FEC
Token FEC
Feature activation+0.000
,
Token,
Feature activation+0.000
listing
Token listing
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
that
Token that
Feature activation+0.457
it
Token it
Feature activation+0.222
has
Token has
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.568
leave
Token leave
Feature activation+1.895
the
Token the
Feature activation+1.993
European
Token European
Feature activation+0.277
"
Token "
Feature activation+0.000
family
Tokenfamily
Feature activation+0.000
."
Token."
Feature activation+0.045
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
purposes
Token purposes
Feature activation+0.000
of
Token of
Feature activation+1.477
the
Token the
Feature activation+2.061
public
Token public
Feature activation+0.032
broadcaster
Token broadcaster
Feature activation+0.143
,
Token,
Feature activation+0.000
guarantees
Token guarantees
Feature activation+0.000
its
Token its
Feature activation+0.000

INTERVAL 1.516 - 1.819
CONTAINS 0.002%

frequently
Token frequently
Feature activation+0.000
targets
Token targets
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
blasting
Token blasting
Feature activation+1.544
networks
Token networks
Feature activation+0.814
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
of
Token of
Feature activation+0.000
was
Token was
Feature activation+0.000
only
Token only
Feature activation+0.000
one
Token one
Feature activation+0.000
reason
Token reason
Feature activation+0.000
he
Token he
Feature activation+0.000
sued
Token sued
Feature activation+1.711
the
Token the
Feature activation+1.884
ABC
Token ABC
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
%,
Token%,
Feature activation+0.000
he
Token he
Feature activation+0.000
'll
Token'll
Feature activation+0.016
fall
Token fall
Feature activation+0.632
off
Token off
Feature activation+1.382
the
Token the
Feature activation+1.635
ballot
Token ballot
Feature activation+0.000
for
Token for
Feature activation+0.117
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Wilson
Token Wilson
Feature activation+0.000
,
Token,
Feature activation+0.000
North
Token North
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
,
Token,
Feature activation+0.557
the
Token the
Feature activation+1.594
FCC
Token FCC
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
though
Token though
Feature activation+0.000
the
Token the
Feature activation+0.000
salary
Token salary
Feature activation+0.000
level
Token level
Feature activation+0.000
approved
Token approved
Feature activation+0.000
by
Token by
Feature activation+1.623
the
Token the
Feature activation+1.311
H
Token H
Feature activation+0.000
SE
TokenSE
Feature activation+0.000
was
Token was
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000

INTERVAL 1.212 - 1.516
CONTAINS 0.007%

in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
future
Token future
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
with
Token with
Feature activation+0.678
the
Token the
Feature activation+1.394
EU
Token EU
Feature activation+0.053
now
Token now
Feature activation+0.000
that
Token that
Feature activation+0.457
it
Token it
Feature activation+0.222
has
Token has
Feature activation+0.000
s
Tokens
Feature activation+0.000
new
Token new
Feature activation+0.000
border
Token border
Feature activation+0.000
management
Token management
Feature activation+0.000
regime
Token regime
Feature activation+0.000
along
Token along
Feature activation+1.240
with
Token with
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Smart
TokenSmart
Feature activation+0.000
Borders
Token Borders
Feature activation+0.000
and
Token and
Feature activation+0.000
light
Token light
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
stimulated
Token stimulated
Feature activation+0.551
the
Token the
Feature activation+1.354
d
Token d
Feature activation+0.000
m
Tokenm
Feature activation+0.000
P
TokenP
Feature activation+0.000
FC
TokenFC
Feature activation+0.000
region
Token region
Feature activation+0.000
appears
Token appears
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
watching
Token watching
Feature activation+1.216
the
Token the
Feature activation+0.911
BET
Token BET
Feature activation+0.000
Hip
Token Hip
Feature activation+0.000
Hop
Token Hop
Feature activation+0.000
Awards
Token Awards
Feature activation+0.000
and
Token and
Feature activation+0.000
UK
Token UK
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
living
Token living
Feature activation+0.570
and
Token and
Feature activation+0.000
working
Token working
Feature activation+1.434
in
Token in
Feature activation+1.958
Europe
Token Europe
Feature activation+0.000
:
Token:
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000

INTERVAL 0.909 - 1.212
CONTAINS 0.016%

that
Token that
Feature activation+0.000
someone
Token someone
Feature activation+0.000
had
Token had
Feature activation+0.000
entered
Token entered
Feature activation+0.257
through
Token through
Feature activation+1.669
the
Token the
Feature activation+1.057
back
Token back
Feature activation+0.000
door
Token door
Feature activation+0.040
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
security
Token security
Feature activation+0.000
still
Token still
Feature activation+0.000
compatible
Token compatible
Feature activation+0.000
with
Token with
Feature activation+0.000
key
Token key
Feature activation+0.000
aims
Token aims
Feature activation+0.000
of
Token of
Feature activation+1.203
Liam
Token Liam
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
show
Token show
Feature activation+0.000
battle
Token battle
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
from
Token from
Feature activation+0.820
the
Token the
Feature activation+1.067
conflict
Token conflict
Feature activation+0.922
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Is
Token Is
Feature activation+0.000
Much
Token Much
Feature activation+0.000
Big
Token Big
Feature activation+0.000
ger
Tokenger
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.100
The
TokenThe
Feature activation+0.516
First
Token First
Feature activation+0.000
Order
Token Order
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.043
S
TokenS
Feature activation+0.000
ect
Tokenect
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
of
Token of
Feature activation+0.329
the
Token the
Feature activation+0.980
colon
Token colon
Feature activation+0.191
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.273
[
Token[
Feature activation+0.000
12
Token12
Feature activation+0.000

INTERVAL 0.606 - 0.909
CONTAINS 0.043%

keep
Token keep
Feature activation+0.000
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
ARE
Token ARE
Feature activation+0.783
people
Token people
Feature activation+0.631
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
who
Token who
Feature activation+0.000
believe
Token believe
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
reach
Token reach
Feature activation+0.000
,
Token,
Feature activation+0.634
the
Token the
Feature activation+0.000
stronger
Token stronger
Feature activation+0.000
the
Token the
Feature activation+0.000
64
Token 64
Feature activation+0.000
community
Token community
Feature activation+0.000
the
Token the
Feature activation+0.363
third
Token third
Feature activation+0.080
of
Token of
Feature activation+0.000
five
Token five
Feature activation+0.292
books
Token books
Feature activation+0.429
of
Token of
Feature activation+0.729
the
Token the
Feature activation+0.691
Torah
Token Torah
Feature activation+0.395
,
Token,
Feature activation+0.000
assuming
Token assuming
Feature activation+0.000
that
Token that
Feature activation+0.000
-
Token-
Feature activation+0.000
private
Tokenprivate
Feature activation+0.000
partnership
Token partnership
Feature activation+0.000
to
Token to
Feature activation+0.000
develop
Token develop
Feature activation+0.228
the
Token the
Feature activation+0.749
initial
Token initial
Feature activation+0.000
sky
Token sky
Feature activation+0.000
way
Tokenway
Feature activation+0.000
line
Token line
Feature activation+0.000
from
Token from
Feature activation+0.000
,
Token,
Feature activation+0.000
eleven
Token eleven
Feature activation+0.000
years
Token years
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.000
wrote
Token wrote
Feature activation+0.847
the
Token the
Feature activation+0.453
Declaration
Token Declaration
Feature activation+0.000
of
Token of
Feature activation+0.000
Independence
Token Independence
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.303 - 0.606
CONTAINS 0.121%

supported
Token supported
Feature activation+0.000
vast
Token vast
Feature activation+0.000
armies
Token armies
Feature activation+0.000
that
Token that
Feature activation+0.000
defeated
Token defeated
Feature activation+0.241
the
Token the
Feature activation+0.350
National
Token National
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
of
Token of
Feature activation+0.000
Things
Token Things
Feature activation+0.000
(
Token (
Feature activation+0.374
I
TokenI
Feature activation+0.000
o
Tokeno
Feature activation+0.000
T
TokenT
Feature activation+0.000
)
Token)
Feature activation+0.000
concept
Token concept
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
and
Token and
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
in
Token in
Feature activation+0.318
the
Token the
Feature activation+1.115
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
Singapore
Token Singapore
Feature activation+0.000
Armed
Token Armed
Feature activation+0.000
Forces
Token Forces
Feature activation+0.000
(
Token (
Feature activation+0.523
SA
TokenSA
Feature activation+0.000
F
TokenF
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
Indonesia
Token Indonesia
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
unveiled
Token unveiled
Feature activation+0.070
Monday
Token Monday
Feature activation+0.000
by
Token by
Feature activation+0.558
House
Token House
Feature activation+0.393
Republicans
Token Republicans
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
move
Token move
Feature activation+0.000

INTERVAL 0.000 - 0.303
CONTAINS 99.809%

Jes
Token Jes
Feature activation+0.000
uits
Tokenuits
Feature activation+0.000
are
Token are
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
priv
Token priv
Feature activation+0.000
y
Tokeny
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
F
Token F
Feature activation+0.000
ilde
Tokenilde
Feature activation+0.000
brand
Tokenbrand
Feature activation+0.000
t
Tokent
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
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
is
Token is
Feature activation+0.000
restricted
Token restricted
Feature activation+0.000
to
Token to
Feature activation+0.000
users
Token users
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Lumia
Token Lumia
Feature activation+0.000
Icon
Token Icon
Feature activation+0.000
,
Token,
Feature activation+0.001
10
Token 10
Feature activation+0.000
sprite
Token sprite
Feature activation+0.000
.
Token.
Feature activation+0.000
save
Tokensave
Feature activation+0.000
("
Token("
Feature activation+0.000
p
Tokenp
Feature activation+0.000
okemon
Tokenokemon
Feature activation+0.000
_
Token_
Feature activation+0.000
"
Token"
Feature activation+0.000
+
Token +
Feature activation+0.000
str
Token str
Feature activation+0.000
(
Token(
Feature activation+0.000
wife
Token wife
Feature activation+0.000
role
Token role
Feature activation+0.000
,
Token,
Feature activation+0.000
initially
Token initially
Feature activation+0.000
she
Token she
Feature activation+0.000
hesitated
Token hesitated
Feature activation+0.000
as
Token as
Feature activation+0.000
in
Token in
Feature activation+0.000
most
Token most
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H8.3: (feature 12841)

TOP ACTIVATIONS
MAX = 2.448

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216
C
TokenC
Feature activation+0.052
razy
Tokenrazy
Feature activation+1.019
World
TokenWorld
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216
C
TokenC
Feature activation+0.052
since
Token since
Feature activation+0.629
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.740
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
posted
Token posted
Feature activation+0.000
a
Token a
Feature activation+0.000
triple
Token triple
Feature activation+0.000
-
Token-
Feature activation+0.000
double
Tokendouble
Feature activation+0.000
in
Token in
Feature activation+1.547
an
Token an
Feature activation+0.000
epic
Token epic
Feature activation+0.000
Game
Token Game
Feature activation+0.000
7
Token 7
Feature activation+0.000
that
Token that
Feature activation+0.000
care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.000
Child
Token Child
Feature activation+0.000
Protective
Token Protective
Feature activation+0.000
Services
Token Services
Feature activation+0.000
(
Token (
Feature activation+1.517
C
TokenC
Feature activation+0.000
PS
TokenPS
Feature activation+0.000
).
Token).
Feature activation+0.000
Since
Token Since
Feature activation+0.000
then
Token then
Feature activation+0.000
He
TokenHe
Feature activation+0.000
's
Token's
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
in
Token in
Feature activation+0.000
touch
Token touch
Feature activation+0.000
,"
Token,"
Feature activation+1.379
Clippers
Token Clippers
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
coach
Token coach
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Wood
Token Wood
Feature activation+0.000
agreed
Token agreed
Feature activation+0.000
to
Token to
Feature activation+0.000
appear
Token appear
Feature activation+0.000
on
Token on
Feature activation+0.000
Face
Token Face
Feature activation+0.000
to
Token to
Feature activation+1.376
Face
Token Face
Feature activation+0.000
,
Token,
Feature activation+0.000
W
Token W
Feature activation+0.000
augh
Tokenaugh
Feature activation+0.000
replies
Token replies
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+1.361
No
Token No
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
gain
Token gain
Feature activation+0.000
of
Token of
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
using
Token using
Feature activation+0.000
game
Token game
Feature activation+0.000
boys
Tokenboys
Feature activation+0.000
and
Token and
Feature activation+1.306
other
Token other
Feature activation+0.116
retro
Token retro
Feature activation+0.000
gaming
Token gaming
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
to
Token to
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Area
Token Area
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Authority
Token Authority
Feature activation+0.000
(
Token (
Feature activation+1.298
C
TokenC
Feature activation+0.000
ADA
TokenADA
Feature activation+0.000
)
Token)
Feature activation+0.000
spokesperson
Token spokesperson
Feature activation+0.000
Wendy
Token Wendy
Feature activation+0.000
.
Token.
Feature activation+0.740
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
voting
Token voting
Feature activation+0.000
has
Token has
Feature activation+0.000
become
Token become
Feature activation+0.000
very
Token very
Feature activation+0.000
popular
Token popular
Feature activation+0.000
in
Token in
Feature activation+1.236
Nashville
Token Nashville
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
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216
C
TokenC
Feature activation+0.052
razy
Tokenrazy
Feature activation+1.019
World
TokenWorld
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.396
Tre
Token Tre
Feature activation+0.000
ifies
Tokenifies
Feature activation+0.000
the
Token the
Feature activation+0.000
scaling
Token scaling
Feature activation+0.000
factor
Token factor
Feature activation+0.000
for
Token for
Feature activation+1.037
player
Token player
Feature activation+1.204
characters
Token characters
Feature activation+0.589
\'
Token\'
Feature activation+0.870
stamina
Token stamina
Feature activation+0.000
consumption
Token consumption
Feature activation+0.000
.
Token.
Feature activation+0.000
longer
Token longer
Feature activation+0.000
occupied
Token occupied
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
accused
Token accused
Feature activation+1.202
Mr
Token Mr
Feature activation+0.000
Corbyn
Token Corbyn
Feature activation+0.000
's
Token's
Feature activation+0.000
critics
Token critics
Feature activation+0.000
of
Token of
Feature activation+0.000
verge
Token verge
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
broken
Token broken
Feature activation+0.000
heading
Token heading
Feature activation+0.000
into
Token into
Feature activation+1.185
this
Token this
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
picking
Token picking
Feature activation+0.000
WA
TokenWA
Feature activation+0.000
)
Token)
Feature activation+0.000
who
Token who
Feature activation+0.000
work
Token work
Feature activation+0.000
or
Token or
Feature activation+0.000
have
Token have
Feature activation+1.179
experience
Token experience
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
door
Token door
Feature activation+0.000
-
Token-
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
hair
Token hair
Feature activation+0.000
pin
Tokenpin
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+1.171
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.094
lap
Token lap
Feature activation+0.000
,
Token,
Feature activation+0.000
Toro
Token Toro
Feature activation+0.000
of
Token of
Feature activation+0.442
the
Token the
Feature activation+0.252
legislation
Token legislation
Feature activation+0.000
unveiled
Token unveiled
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
by
Token by
Feature activation+1.167
House
Token House
Feature activation+1.012
Republicans
Token Republicans
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
move
Token move
Feature activation+0.000

Top DFA by src position
MAX = 3.058

emotional
Token emotional
Feature activation+0.004
Top resid features:
t
Token t
Feature activation+0.001
Top resid features:
ributes
Tokenributes
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
Hall
Token Hall
Feature activation+0.029
Top resid features:
man
Tokenman
Feature activation+3.058
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
his
Token his
Feature activation-0.015
Top resid features:
Twitter
Token Twitter
Feature activation+0.179
Top resid features:
account
Token account
Feature activation+0.005
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
emotional
Token emotional
Feature activation+0.002
Top resid features:
t
Token t
Feature activation-0.001
Top resid features:
ributes
Tokenributes
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
Hall
Token Hall
Feature activation+0.047
Top resid features:
man
Tokenman
Feature activation+2.419
Top resid features:
on
Token on
Feature activation-0.010
Top resid features:
his
Token his
Feature activation-0.007
Top resid features:
Twitter
Token Twitter
Feature activation+0.136
Top resid features:
account
Token account
Feature activation+0.003
Top resid features:
since
Token since
Feature activation+0.003
Top resid features:
emotional
Token emotional
Feature activation+0.007
Top resid features:
t
Token t
Feature activation-0.001
Top resid features:
ributes
Tokenributes
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
Hall
Token Hall
Feature activation+0.032
Top resid features:
man
Tokenman
Feature activation+2.419
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
his
Token his
Feature activation-0.028
Top resid features:
Twitter
Token Twitter
Feature activation+0.050
Top resid features:
account
Token account
Feature activation+0.005
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
emotional
Token emotional
Feature activation+0.008
Top resid features:
t
Token t
Feature activation-0.001
Top resid features:
ributes
Tokenributes
Feature activation+0.041
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
Hall
Token Hall
Feature activation+0.027
Top resid features:
man
Tokenman
Feature activation+2.120
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.002
Top resid features:
Twitter
Token Twitter
Feature activation+0.122
Top resid features:
account
Token account
Feature activation+0.028
Top resid features:
since
Token since
Feature activation+0.006
Top resid features:
scored
Token scored
Feature activation+0.003
Top resid features:
41
Token 41
Feature activation+0.016
Top resid features:
points
Token points
Feature activation+0.020
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
Games
Token Games
Feature activation-0.221
Top resid features:
5
Token 5
Feature activation+1.578
Top resid features:
and
Token and
Feature activation+0.076
Top resid features:
6
Token 6
Feature activation+0.823
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
posted
Token posted
Feature activation+0.013
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
into
Token into
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
care
Token care
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.016
Top resid features:
Child
Token Child
Feature activation-0.047
Top resid features:
Protective
Token Protective
Feature activation+2.409
Top resid features:
Services
Token Services
Feature activation+0.257
Top resid features:
(
Token (
Feature activation-0.215
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
PS
TokenPS
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Clippers
Token Clippers
Feature activation-0.013
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
team
Token team
Feature activation-0.004
Top resid features:
representative
Token representative
Feature activation+2.368
Top resid features:
said
Token said
Feature activation+0.040
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
G
TokenG
Feature activation+0.003
Top resid features:
agreed
Token agreed
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
appear
Token appear
Feature activation-0.023
Top resid features:
on
Token on
Feature activation-0.011
Top resid features:
Face
Token Face
Feature activation-0.271
Top resid features:
to
Token to
Feature activation+2.537
Top resid features:
Face
Token Face
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
W
Token W
Feature activation+0.000
Top resid features:
augh
Tokenaugh
Feature activation+0.000
Top resid features:
replies
Token replies
Feature activation+0.000
Top resid features:
In
TokenIn
Feature activation-0.010
Top resid features:
terms
Token terms
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
annual
Token annual
Feature activation-0.044
Top resid features:
job
Token job
Feature activation+0.010
Top resid features:
changes
Token changes
Feature activation+2.201
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
jugg
Token jugg
Feature activation+0.002
Top resid features:
ernaut
Tokenernaut
Feature activation+0.004
Top resid features:
Texas
Token Texas
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
artists
Token artists
Feature activation-0.000
Top resid features:
have
Token have
Feature activation-0.003
Top resid features:
been
Token been
Feature activation-0.005
Top resid features:
using
Token using
Feature activation-0.033
Top resid features:
game
Token game
Feature activation-0.007
Top resid features:
boys
Tokenboys
Feature activation+2.176
Top resid features:
and
Token and
Feature activation-0.035
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
retro
Token retro
Feature activation+0.000
Top resid features:
gaming
Token gaming
Feature activation+0.000
Top resid features:
hardware
Token hardware
Feature activation+0.000
Top resid features:
downtown
Token downtown
Feature activation-0.018
Top resid features:
Sacramento
Token Sacramento
Feature activation-0.005
Top resid features:
,"
Token,"
Feature activation+0.010
Top resid features:
Capitol
Token Capitol
Feature activation+0.273
Top resid features:
Area
Token Area
Feature activation+0.089
Top resid features:
Development
Token Development
Feature activation+1.771
Top resid features:
Authority
Token Authority
Feature activation+0.076
Top resid features:
(
Token (
Feature activation-0.055
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
ADA
TokenADA
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
emotional
Token emotional
Feature activation+0.005
Top resid features:
t
Token t
Feature activation-0.002
Top resid features:
ributes
Tokenributes
Feature activation+0.007
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
Hall
Token Hall
Feature activation+0.015
Top resid features:
man
Tokenman
Feature activation+1.903
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
his
Token his
Feature activation-0.016
Top resid features:
Twitter
Token Twitter
Feature activation+0.129
Top resid features:
account
Token account
Feature activation+0.003
Top resid features:
since
Token since
Feature activation+0.001
Top resid features:
isn
Token isn
Feature activation+0.001
Top resid features:
't
Token't
Feature activation+0.002
Top resid features:
reversed
Token reversed
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Music
Token Music
Feature activation-0.001
Top resid features:
City
Token City
Feature activation+2.254
Top resid features:
risks
Token risks
Feature activation-0.000
Top resid features:
committing
Token committing
Feature activation-0.000
Top resid features:
mass
Token mass
Feature activation+0.002
Top resid features:
voter
Token voter
Feature activation-0.005
Top resid features:
suppression
Token suppression
Feature activation-0.001
Top resid features:
emotional
Token emotional
Feature activation+0.003
Top resid features:
t
Token t
Feature activation-0.002
Top resid features:
ributes
Tokenributes
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
Hall
Token Hall
Feature activation+0.032
Top resid features:
man
Tokenman
Feature activation+2.008
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
his
Token his
Feature activation-0.010
Top resid features:
Twitter
Token Twitter
Feature activation+0.027
Top resid features:
account
Token account
Feature activation+0.002
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Player
TokenPlayer
Feature activation+0.008
Top resid features:
Character
TokenCharacter
Feature activation+0.418
Top resid features:
St
TokenSt
Feature activation+0.244
Top resid features:
amina
Tokenamina
Feature activation+0.502
Top resid features:
D
TokenD
Feature activation+0.490
Top resid features:
rain
Tokenrain
Feature activation+0.102
Top resid features:
Mult
TokenMult
Feature activation+0.015
Top resid features:
ipl
Tokenipl
Feature activation+0.003
Top resid features:
ier
Tokenier
Feature activation-0.003
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
complaint
Token complaint
Feature activation-0.017
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
his
Token his
Feature activation+0.025
Top resid features:
office
Token office
Feature activation-0.009
Top resid features:
manager
Token manager
Feature activation+2.072
Top resid features:
thought
Token thought
Feature activation+0.058
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
premises
Token premises
Feature activation+0.003
Top resid features:
were
Token were
Feature activation-0.002
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
face
Token face
Feature activation-0.002
Top resid features:
offs
Tokenoffs
Feature activation+0.020
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
season
Token season
Feature activation-0.044
Top resid features:
four
Token four
Feature activation+2.111
Top resid features:
times
Token times
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
F
Token F
Feature activation+0.004
Top resid features:
ACT
TokenACT
Feature activation-0.001
Top resid features:
!
Token!
Feature activation+0.002
Top resid features:
I
TokenI
Feature activation+0.004
Top resid features:
WA
TokenWA
Feature activation+0.002
Top resid features:
)
Token)
Feature activation+0.004
Top resid features:
who
Token who
Feature activation+0.022
Top resid features:
work
Token work
Feature activation-0.045
Top resid features:
or
Token or
Feature activation+2.146
Top resid features:
have
Token have
Feature activation-0.043
Top resid features:
experience
Token experience
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:
door
Token door
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
On
TokenOn
Feature activation+0.003
Top resid features:
lap
Token lap
Feature activation-0.538
Top resid features:
15
Token 15
Feature activation+2.418
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
St
Token St
Feature activation+0.003
Top resid features:
roll
Tokenroll
Feature activation+0.008
Top resid features:
blew
Token blew
Feature activation+0.002
Top resid features:
past
Token past
Feature activation-0.004
Top resid features:
IG
TokenIG
Feature activation-0.000
Top resid features:
HL
TokenHL
Feature activation+0.000
Top resid features:
IGHTS
TokenIGHTS
Feature activation-0.001
Top resid features:
OF
Token OF
Feature activation+0.002
Top resid features:
HOUSE
Token HOUSE
Feature activation+0.010
Top resid features:
GOP
Token GOP
Feature activation+1.726
Top resid features:
HE
Token HE
Feature activation-0.005
Top resid features:
ALTH
TokenALTH
Feature activation+0.003
Top resid features:
CARE
Token CARE
Feature activation+0.003
Top resid features:
LEG
Token LEG
Feature activation+0.012
Top resid features:
IS
TokenIS
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.48

Head 4: 0.03

Head 5: 0.05

Head 6: 0.03

Head 7: 0.04

Head 8: 0.06

Head 9: 0.05

Head 10: 0.09

Head 11: 0.07

Positive logits

livest2.73

creen2.66

workplace2.61

FORM2.21

site2.14

mental2.14

body2.12

LAND2.10

STEM2.08

MAP2.05

cosmetic2.05

ODY2.02

ometric2.02

Desktop1.99

mount1.98

ength1.98

actory1.98

HOME1.97

workspace1.97

persist1.96

Negative logits

luaj-2.96

iro-2.95

rir-2.59

Kurdistan-2.56

Rouhani-2.51

Xiang-2.48

Ö-2.48

ivan-2.47

lez-2.45

و-2.42

dra-2.40

Tur-2.35

uj-2.35

asi-2.35

Í-2.35

龍�-2.33

Gors-2.33

ı-2.32

Liberties-2.31

notations-2.31

INTERVAL 2.203 - 2.448
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216

INTERVAL 1.959 - 2.203
CONTAINS 0.000%

INTERVAL 1.714 - 1.959
CONTAINS 0.000%

ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216
C
TokenC
Feature activation+0.052
razy
Tokenrazy
Feature activation+1.019
World
TokenWorld
Feature activation+0.000

INTERVAL 1.469 - 1.714
CONTAINS 0.000%

care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.000
Child
Token Child
Feature activation+0.000
Protective
Token Protective
Feature activation+0.000
Services
Token Services
Feature activation+0.000
(
Token (
Feature activation+1.517
C
TokenC
Feature activation+0.000
PS
TokenPS
Feature activation+0.000
).
Token).
Feature activation+0.000
Since
Token Since
Feature activation+0.000
then
Token then
Feature activation+0.000
since
Token since
Feature activation+0.629
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.740
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
Ċ
TokenĊ
Feature activation+1.572
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.094
ing
Tokening
Feature activation+1.251
For
Token For
Feature activation+2.448
my
Token my
Feature activation+1.671
lil
Token lil
Feature activation+0.855
cousin
Token cousin
Feature activation+1.778
man
Token man
Feature activation+0.959
#
Token #
Feature activation+1.216
C
TokenC
Feature activation+0.052
posted
Token posted
Feature activation+0.000
a
Token a
Feature activation+0.000
triple
Token triple
Feature activation+0.000
-
Token-
Feature activation+0.000
double
Tokendouble
Feature activation+0.000
in
Token in
Feature activation+1.547
an
Token an
Feature activation+0.000
epic
Token epic
Feature activation+0.000
Game
Token Game
Feature activation+0.000
7
Token 7
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.224 - 1.469
CONTAINS 0.001%

,"
Token,"
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Area
Token Area
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Authority
Token Authority
Feature activation+0.000
(
Token (
Feature activation+1.298
C
TokenC
Feature activation+0.000
ADA
TokenADA
Feature activation+0.000
)
Token)
Feature activation+0.000
spokesperson
Token spokesperson
Feature activation+0.000
Wendy
Token Wendy
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
using
Token using
Feature activation+0.000
game
Token game
Feature activation+0.000
boys
Tokenboys
Feature activation+0.000
and
Token and
Feature activation+1.306
other
Token other
Feature activation+0.116
retro
Token retro
Feature activation+0.000
gaming
Token gaming
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
to
Token to
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+1.361
No
Token No
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
gain
Token gain
Feature activation+0.000
of
Token of
Feature activation+0.000
voting
Token voting
Feature activation+0.000
has
Token has
Feature activation+0.000
become
Token become
Feature activation+0.000
very
Token very
Feature activation+0.000
popular
Token popular
Feature activation+0.000
in
Token in
Feature activation+1.236
Nashville
Token Nashville
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
agreed
Token agreed
Feature activation+0.000
to
Token to
Feature activation+0.000
appear
Token appear
Feature activation+0.000
on
Token on
Feature activation+0.000
Face
Token Face
Feature activation+0.000
to
Token to
Feature activation+1.376
Face
Token Face
Feature activation+0.000
,
Token,
Feature activation+0.000
W
Token W
Feature activation+0.000
augh
Tokenaugh
Feature activation+0.000
replies
Token replies
Feature activation+0.000

INTERVAL 0.979 - 1.224
CONTAINS 0.003%

officers
Token officers
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
placed
Token placed
Feature activation+0.000
on
Token on
Feature activation+0.031
paid
Token paid
Feature activation+0.989
leave
Token leave
Feature activation+0.000
pending
Token pending
Feature activation+0.000
an
Token an
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
by
Token by
Feature activation+0.000
:
Token:
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
48
Token48
Feature activation+0.000
million
Token million
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.097
Ċ
TokenĊ
Feature activation+0.382
Hour
TokenHour
Feature activation+0.000
two
Token two
Feature activation+0.000
:
Token:
Feature activation+0.000
3
Token 3
Feature activation+0.000
the
Token the
Feature activation+0.252
legislation
Token legislation
Feature activation+0.000
unveiled
Token unveiled
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
by
Token by
Feature activation+1.167
House
Token House
Feature activation+1.012
Republicans
Token Republicans
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
move
Token move
Feature activation+0.000
to
Token to
Feature activation+0.000
verge
Token verge
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
broken
Token broken
Feature activation+0.000
heading
Token heading
Feature activation+0.000
into
Token into
Feature activation+1.185
this
Token this
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
picking
Token picking
Feature activation+0.000
custody
Token custody
Feature activation+0.000
battles
Token battles
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.000
by
Token by
Feature activation+1.063
case
Token case
Feature activation+0.000
basis
Token basis
Feature activation+0.000
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.000

INTERVAL 0.734 - 0.979
CONTAINS 0.004%

.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
billion
Token billion
Feature activation+0.000
,
Token,
Feature activation+0.000
worth
Token worth
Feature activation+0.000
of
Token of
Feature activation+0.947
fruits
Token fruits
Feature activation+0.000
and
Token and
Feature activation+0.000
vegetables
Token vegetables
Feature activation+0.000
due
Token due
Feature activation+0.073
to
Token to
Feature activation+0.828
ab
Tokenab
Feature activation+0.000
inding
Tokeninding
Feature activation+0.000
Hub
Token Hub
Feature activation+0.000
Tile
TokenTile
Feature activation+0.000
Step
Token Step
Feature activation+0.000
by
Token by
Feature activation+0.825
Step
Token Step
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
example
Token example
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
greater
Token greater
Feature activation+0.000
risk
Token risk
Feature activation+0.000
of
Token of
Feature activation+0.659
developing
Token developing
Feature activation+0.749
cancer
Token cancer
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
smokers
Token smokers
Feature activation+0.000
could
Token could
Feature activation+0.000
the
Token the
Feature activation+0.031
case
Token case
Feature activation+0.000
were
Token were
Feature activation+0.000
keen
Token keen
Feature activation+0.000
to
Token to
Feature activation+0.000
tackle
Token tackle
Feature activation+0.867
a
Token a
Feature activation+0.384
torrent
Token torrent
Feature activation+0.000
site
Token site
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
for
Token for
Feature activation+0.000
people
Token people
Feature activation+0.000
like
Token like
Feature activation+0.000
them
Token them
Feature activation+0.000
than
Token than
Feature activation+0.100
it
Token it
Feature activation+0.843
was
Token was
Feature activation+0.110
50
Token 50
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.490 - 0.734
CONTAINS 0.011%

very
Token very
Feature activation+0.000
controvers
Token controvers
Feature activation+0.000
ially
Tokenially
Feature activation+0.000
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.544
the
Token the
Feature activation+0.629
bedroom
Token bedroom
Feature activation+0.000
tax
Token tax
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
wastes
Token wastes
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.000
measure
Token measure
Feature activation+0.000
of
Token of
Feature activation+0.532
household
Token household
Feature activation+0.502
debt
Token debt
Feature activation+0.000
has
Token has
Feature activation+0.000
hit
Token hit
Feature activation+0.000
a
Token a
Feature activation+0.000
record
Token record
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
install
Token install
Feature activation+0.345
the
Token the
Feature activation+0.684
bench
Token bench
Feature activation+0.073
top
Token top
Feature activation+0.028
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
glued
Token glued
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.516
the
Token the
Feature activation+0.203
payments
Token payments
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
cost
Token cost
Feature activation+0.000
singled
Token singled
Feature activation+0.000
out
Token out
Feature activation+0.000
fat
Token fat
Feature activation+0.000
and
Token and
Feature activation+0.000
cholesterol
Token cholesterol
Feature activation+0.000
as
Token as
Feature activation+0.517
the
Token the
Feature activation+0.376
dietary
Token dietary
Feature activation+0.000
causes
Token causes
Feature activation+0.000
of
Token of
Feature activation+0.480
CH
Token CH
Feature activation+0.000

INTERVAL 0.245 - 0.490
CONTAINS 0.031%

is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
setback
Token setback
Feature activation+0.000
with
Token with
Feature activation+0.000
wearing
Token wearing
Feature activation+0.441
a
Token a
Feature activation+0.323
regular
Token regular
Feature activation+0.000
face
Token face
Feature activation+0.000
mask
Token mask
Feature activation+0.000
for
Token for
Feature activation+0.000
hard
Token hard
Feature activation+0.000
although
Token although
Feature activation+0.000
this
Token this
Feature activation+0.000
feature
Token feature
Feature activation+0.000
was
Token was
Feature activation+0.000
absent
Token absent
Feature activation+0.000
on
Token on
Feature activation+0.477
many
Token many
Feature activation+0.003
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
base
Tokenbase
Feature activation+0.000
and
Token and
Feature activation+0.000
copy
Token copy
Feature activation+0.000
each
Token each
Feature activation+0.000
section
Token section
Feature activation+0.000
to
Token to
Feature activation+0.316
memory
Token memory
Feature activation+0.000
so
Token so
Feature activation+0.000
virtual
Token virtual
Feature activation+0.000
addresses
Token addresses
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
looked
Token looked
Feature activation+0.000
at
Token at
Feature activation+0.000
for
Token for
Feature activation+0.332
a
Token a
Feature activation+0.061
Cabinet
Token Cabinet
Feature activation+0.000
position
Token position
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
store
Tokenstore
Feature activation+0.000
Out
Token Out
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
,
Token,
Feature activation+0.000
www
Token www
Feature activation+0.000
.
Token.
Feature activation+0.435
ticket
Tokenticket
Feature activation+0.000
atlantic
Tokenatlantic
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 0.000 - 0.245
CONTAINS 99.950%

are
Token are
Feature activation+0.000
extremely
Token extremely
Feature activation+0.000
sick
Token sick
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
dist
Token dist
Feature activation+0.000
em
Tokenem
Feature activation+0.000
per
Tokenper
Feature activation+0.000
,
Token,
Feature activation+0.000
par
Token par
Feature activation+0.000
vo
Tokenvo
Feature activation+0.000
ido
Tokenido
Feature activation+0.000
de
Token de
Feature activation+0.000
Acc
Token Acc
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ón
Tokenón
Feature activation+0.000
N
Token N
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
ional
Tokenional
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
falsehood
Token falsehood
Feature activation+0.000
s
Tokens
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
an
Token an
Feature activation+0.000
extra
Token extra
Feature activation+0.000
special
Token special
Feature activation+0.000
Fest
Token Fest
Feature activation+0.000
offering
Token offering
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
get
Token get
Feature activation+0.000
an
Token an
Feature activation+0.000
awesome
Token awesome
Feature activation+0.000
BBQ
Token BBQ
Feature activation+0.000
mammal
Token mammal
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
Ly
Token Ly
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
Morris
Token Morris
Feature activation+0.000
ette
Tokenette
Feature activation+0.000
said
Token said
Feature activation+0.000
warmer
Token warmer
Feature activation+0.000
than
Token than
Feature activation+0.000
usual
Token usual
Feature activation+0.000
sea
Token sea
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H8.3: (feature 5580)

TOP ACTIVATIONS
MAX = 3.305

Society
Token Society
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
,
Token,
Feature activation+3.305
and
Token and
Feature activation+0.000
offices
Token offices
Feature activation+0.000
for
Token for
Feature activation+0.000
medical
Token medical
Feature activation+0.000
services
Token services
Feature activation+0.000
arts
Token arts
Feature activation+0.000
groups
Token groups
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
created
Token created
Feature activation+0.000
,
Token,
Feature activation+3.278
according
Token according
Feature activation+0.560
to
Token to
Feature activation+1.855
the
Token the
Feature activation+0.112
plans
Token plans
Feature activation+0.271
,
Token,
Feature activation+1.661
own
Token own
Feature activation+0.000
conversion
Token conversion
Feature activation+0.000
story
Token story
Feature activation+0.000
?
Token?
Feature activation+0.593
Ċ
TokenĊ
Feature activation+2.259
Ċ
TokenĊ
Feature activation+3.181
Dou
TokenDou
Feature activation+0.000
glas
Tokenglas
Feature activation+0.352
M
Token M
Feature activation+0.000
.
Token.
Feature activation+0.315
Be
Token Be
Feature activation+0.000
Clark
Token Clark
Feature activation+0.000
County
Token County
Feature activation+0.000
departments
Token departments
Feature activation+0.000
.
Token.
Feature activation+2.858
Ċ
TokenĊ
Feature activation+0.045
Ċ
TokenĊ
Feature activation+3.034
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.048
I
TokenI
Feature activation+0.371
just
Token just
Feature activation+0.000
want
Token want
Feature activation+0.000
in
Token in
Feature activation+0.252
the
Token the
Feature activation+0.168
process
Token process
Feature activation+0.329
.
Token.
Feature activation+2.564
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.919
The
TokenThe
Feature activation+0.852
Conservative
Token Conservative
Feature activation+0.114
party
Token party
Feature activation+0.000
is
Token is
Feature activation+0.000
having
Token having
Feature activation+0.136
Vegas
Token Vegas
Feature activation+0.000
and
Token and
Feature activation+0.000
Clark
Token Clark
Feature activation+0.000
County
Token County
Feature activation+0.000
departments
Token departments
Feature activation+0.000
.
Token.
Feature activation+2.858
Ċ
TokenĊ
Feature activation+0.045
Ċ
TokenĊ
Feature activation+3.034
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.048
I
TokenI
Feature activation+0.371
abor
Tokenabor
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
on
Token on
Feature activation+0.000
these
Token these
Feature activation+0.000
steps
Token steps
Feature activation+0.000
,
Token,
Feature activation+2.653
the
Token the
Feature activation+2.154
adviser
Token adviser
Feature activation+0.671
said
Token said
Feature activation+0.115
J
Token J
Feature activation+0.000
adh
Tokenadh
Feature activation+0.000
implies
Token implies
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
infiltration
Token infiltration
Feature activation+0.000
,"
Token,"
Feature activation+2.616
Salem
Token Salem
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+0.090
Ċ
TokenĊ
Feature activation+0.338
Ċ
TokenĊ
Feature activation+1.148
Like
TokenLike
Feature activation+0.931
his
Token his
Feature activation+0.058
predecessor
Token predecessor
Feature activation+0.851
,
Token,
Feature activation+2.606
Vol
Token Vol
Feature activation+0.000
iva
Tokeniva
Feature activation+0.000
increasingly
Token increasingly
Feature activation+0.308
developed
Token developed
Feature activation+0.223
an
Token an
Feature activation+0.219
keep
Token keep
Feature activation+0.000
knocking
Token knocking
Feature activation+0.000
down
Token down
Feature activation+0.000
these
Token these
Feature activation+0.000
barriers
Token barriers
Feature activation+0.000
,"
Token,"
Feature activation+2.601
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+0.069
"
Token "
Feature activation+0.000
new
Tokennew
Feature activation+0.000
aining
Tokenaining
Feature activation+0.000
technique
Token technique
Feature activation+0.000
invented
Token invented
Feature activation+0.000
by
Token by
Feature activation+2.137
Cam
Token Cam
Feature activation+0.281
illo
Tokenillo
Feature activation+2.585
Gol
Token Gol
Feature activation+0.000
gi
Tokengi
Feature activation+0.115
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
tests
Token tests
Feature activation+0.000
,
Token,
Feature activation+0.066
police
Token police
Feature activation+0.000
said
Token said
Feature activation+0.576
.
Token.
Feature activation+2.576
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.852
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.292
They
TokenThey
Feature activation+0.000
species
Token species
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
harvested
Token harvested
Feature activation+0.000
,
Token,
Feature activation+2.574
although
Token although
Feature activation+0.000
some
Token some
Feature activation+0.000
have
Token have
Feature activation+0.000
size
Token size
Feature activation+0.000
limits
Token limits
Feature activation+0.000
class
Token class
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
bubbles
Token bubbles
Feature activation+0.000
,
Token,
Feature activation+2.570
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.468
he
Token he
Feature activation+0.595
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.697
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
runoff
Token runoff
Feature activation+0.000
.
Token.
Feature activation+2.568
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.159
We
TokenWe
Feature activation+0.000
recognized
Token recognized
Feature activation+0.000
that
Token that
Feature activation+0.000
key
Token key
Feature activation+0.000
roles
Token roles
Feature activation+0.054
in
Token in
Feature activation+0.252
the
Token the
Feature activation+0.168
process
Token process
Feature activation+0.329
.
Token.
Feature activation+2.564
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.919
The
TokenThe
Feature activation+0.852
Conservative
Token Conservative
Feature activation+0.114
party
Token party
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
hip
Token hip
Feature activation+0.000
,
Token,
Feature activation+2.504
she
Token she
Feature activation+0.000
broke
Token broke
Feature activation+0.000
down
Token down
Feature activation+0.000
in
Token in
Feature activation+0.000
tears
Token tears
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
and
Token and
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
.
Token.
Feature activation+1.516
Ċ
TokenĊ
Feature activation+0.020
Ċ
TokenĊ
Feature activation+2.500
"
Token"
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
latest
Token latest
Feature activation+0.000
not
Token not
Feature activation+0.000
in
Token in
Feature activation+0.000
good
Token good
Feature activation+0.000
working
Token working
Feature activation+0.000
order
Token order
Feature activation+0.000
,"
Token,"
Feature activation+2.485
Law
Token Law
Feature activation+0.000
hon
Tokenhon
Feature activation+0.000
said
Token said
Feature activation+0.359
.
Token.
Feature activation+0.271
Ċ
TokenĊ
Feature activation+0.192
higher
Token higher
Feature activation+0.000
rates
Token rates
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.000
before
Token before
Feature activation+0.000
,"
Token,"
Feature activation+2.473
Shin
Token Shin
Feature activation+0.478
se
Tokense
Feature activation+0.000
ki
Tokenki
Feature activation+0.000
testified
Token testified
Feature activation+0.000
.
Token.
Feature activation+0.540

Top DFA by src position
MAX = 3.828

in
Token in
Feature activation-0.000
Top resid features:
Chicago
Token Chicago
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
C
Token C
Feature activation-0.001
Top resid features:
ui
Tokenui
Feature activation-0.002
Top resid features:
said
Token said
Feature activation+3.755
Top resid features:
.
Token.
Feature activation-0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
A
TokenA
Feature activation+0.003
Top resid features:
300
Token 300
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
Chicago
Token Chicago
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
C
Token C
Feature activation-0.001
Top resid features:
ui
Tokenui
Feature activation-0.005
Top resid features:
said
Token said
Feature activation+3.828
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
A
TokenA
Feature activation+0.001
Top resid features:
300
Token 300
Feature activation+0.000
Top resid features:
ius
Tokenius
Feature activation+0.017
Top resid features:
Press
Token Press
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Be
Token Be
Feature activation-0.001
Top resid features:
aum
Tokenaum
Feature activation+0.020
Top resid features:
ont
Tokenont
Feature activation+2.272
Top resid features:
responded
Token responded
Feature activation+1.283
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
questions
Token questions
Feature activation+0.002
Top resid features:
from
Token from
Feature activation-0.002
Top resid features:
Catholic
Token Catholic
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
B
TokenB
Feature activation-0.009
Top resid features:
irt
Tokenirt
Feature activation+0.012
Top resid features:
amassed
Token amassed
Feature activation+3.572
Top resid features:
50
Token 50
Feature activation+0.003
Top resid features:
8
Token8
Feature activation-0.001
Top resid features:
signatures
Token signatures
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
accounting
Token accounting
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Liberals
Token Liberals
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Day
Token Day
Feature activation-0.069
Top resid features:
fought
Token fought
Feature activation+3.377
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
campaign
Token campaign
Feature activation+0.005
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
sho
Token sho
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
B
TokenB
Feature activation-0.010
Top resid features:
irt
Tokenirt
Feature activation+0.007
Top resid features:
amassed
Token amassed
Feature activation+3.365
Top resid features:
50
Token 50
Feature activation+0.010
Top resid features:
8
Token8
Feature activation+0.001
Top resid features:
signatures
Token signatures
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
accounting
Token accounting
Feature activation+0.004
Top resid features:
transparency
Token transparency
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Az
TokenAz
Feature activation-0.027
Top resid features:
iz
Tokeniz
Feature activation-0.021
Top resid features:
reassured
Token reassured
Feature activation+3.222
Top resid features:
critics
Token critics
Feature activation+0.012
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
steps
Token steps
Feature activation-0.001
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
with
Token with
Feature activation-0.000
Top resid features:
regime
Token regime
Feature activation-0.002
Top resid features:
forces
Token forces
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Salem
Token Salem
Feature activation-0.055
Top resid features:
said
Token said
Feature activation+3.128
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
nature
Token nature
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
bomb
Token bomb
Feature activation+0.002
Top resid features:
).[
Token).[
Feature activation+0.001
Top resid features:
6
Token6
Feature activation-0.000
Top resid features:
]
Token]
Feature activation-0.005
Top resid features:
Vol
Token Vol
Feature activation-0.008
Top resid features:
iva
Tokeniva
Feature activation+0.051
Top resid features:
also
Token also
Feature activation+2.846
Top resid features:
predicted
Token predicted
Feature activation+0.222
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
end
Token end
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
mobile
Token mobile
Feature activation-0.000
Top resid features:
connection
Token connection
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Vin
Token Vin
Feature activation-0.038
Top resid features:
h
Tokenh
Feature activation+0.001
Top resid features:
says
Token says
Feature activation+3.223
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
expected
Token expected
Feature activation+0.006
Top resid features:
Thanks
Token Thanks
Feature activation+0.003
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
C
Token C
Feature activation-0.004
Top resid features:
aj
Tokenaj
Feature activation+0.001
Top resid features:
al
Tokenal
Feature activation+0.036
Top resid features:
's
Token's
Feature activation+3.003
Top resid features:
application
Token application
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
new
Token new
Feature activation-0.001
Top resid features:
st
Token st
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
H
TokenH
Feature activation-0.018
Top resid features:
ogan
Tokenogan
Feature activation+0.035
Top resid features:
also
Token also
Feature activation+2.828
Top resid features:
failed
Token failed
Feature activation+0.196
Top resid features:
sob
Token sob
Feature activation-0.007
Top resid features:
ri
Tokenri
Feature activation+0.000
Top resid features:
ety
Tokenety
Feature activation+0.003
Top resid features:
tests
Token tests
Feature activation+0.017
Top resid features:
any
Token any
Feature activation-0.001
Top resid features:
charges
Token charges
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Ste
Token Ste
Feature activation-0.012
Top resid features:
iding
Tokeniding
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+3.168
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Black
TokenBlack
Feature activation-0.001
Top resid features:
tip
Tokentip
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Con
TokenCon
Feature activation+0.001
Top resid features:
cha
Tokencha
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+3.122
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
feelings
Token feelings
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
average
Token average
Feature activation-0.000
Top resid features:
Americans
Token Americans
Feature activation-0.001
Top resid features:
campaign
Token campaign
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Cr
Token Cr
Feature activation-0.044
Top resid features:
ud
Tokenud
Feature activation+0.011
Top resid features:
up
Tokenup
Feature activation+1.051
Top resid features:
,
Token,
Feature activation+1.431
Top resid features:
who
Token who
Feature activation+0.331
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
African
Token African
Feature activation-0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
American
TokenAmerican
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Liberals
Token Liberals
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Day
Token Day
Feature activation-0.067
Top resid features:
fought
Token fought
Feature activation+2.907
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
campaign
Token campaign
Feature activation+0.002
Top resid features:
on
Token on
Feature activation+0.023
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
sho
Token sho
Feature activation-0.003
Top resid features:
?
Token?
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Boat
Token Boat
Feature activation-0.005
Top resid features:
right
Tokenright
Feature activation+0.017
Top resid features:
remembers
Token remembers
Feature activation+3.117
Top resid features:
thinking
Token thinking
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.084
Top resid features:
âĢ
Token âĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.006
Top resid features:
Is
TokenIs
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Sh
TokenSh
Feature activation-0.036
Top resid features:
inse
Tokeninse
Feature activation+0.121
Top resid features:
ki
Tokenki
Feature activation+0.568
Top resid features:
,
Token,
Feature activation+1.689
Top resid features:
a
Token a
Feature activation+0.365
Top resid features:
retired
Token retired
Feature activation+0.003
Top resid features:
four
Token four
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
star
Tokenstar
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
according
Token according
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
Law
Token Law
Feature activation-0.018
Top resid features:
hon
Tokenhon
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+3.141
Top resid features:
There
Token There
Feature activation-0.000
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
no
Token no
Feature activation-0.001
Top resid features:
damage
Token damage
Feature activation-0.001
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Sh
TokenSh
Feature activation-0.087
Top resid features:
inse
Tokeninse
Feature activation+0.139
Top resid features:
ki
Tokenki
Feature activation+0.604
Top resid features:
,
Token,
Feature activation+1.644
Top resid features:
a
Token a
Feature activation+0.433
Top resid features:
retired
Token retired
Feature activation+0.001
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
star
Tokenstar
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.01

Head 2: 0.05

Head 3: 0.48

Head 4: 0.03

Head 5: 0.04

Head 6: 0.05

Head 7: 0.03

Head 8: 0.03

Head 9: 0.06

Head 10: 0.11

Head 11: 0.06

Positive logits

him3.19

Bott2.70

Born2.65

Quint2.59

Trey2.54

Hardy2.44

Flav2.40

Schwarz2.37

Couch2.35

Vent2.34

Coch2.28

Bret2.28

Tiff2.22

Aub2.22

Pt2.21

Quentin2.20

Dare2.19

Amon2.18

Claud2.16

Moor2.15

Negative logits

ataka-2.37

arms-2.36

enegger-2.35

enium-2.34

committee-2.31

terness-2.29

ormonal-2.29

irs-2.25

aban-2.23

internal-2.21

aves-2.20

ancial-2.16

amiya-2.15

liga-2.15

roups-2.14

ihad-2.14

gorithm-2.14

aters-2.11

uminium-2.10

ados-2.09

INTERVAL 2.974 - 3.305
CONTAINS 0.000%

own
Token own
Feature activation+0.000
conversion
Token conversion
Feature activation+0.000
story
Token story
Feature activation+0.000
?
Token?
Feature activation+0.593
Ċ
TokenĊ
Feature activation+2.259
Ċ
TokenĊ
Feature activation+3.181
Dou
TokenDou
Feature activation+0.000
glas
Tokenglas
Feature activation+0.352
M
Token M
Feature activation+0.000
.
Token.
Feature activation+0.315
Be
Token Be
Feature activation+0.000
Clark
Token Clark
Feature activation+0.000
County
Token County
Feature activation+0.000
departments
Token departments
Feature activation+0.000
.
Token.
Feature activation+2.858
Ċ
TokenĊ
Feature activation+0.045
Ċ
TokenĊ
Feature activation+3.034
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.048
I
TokenI
Feature activation+0.371
just
Token just
Feature activation+0.000
want
Token want
Feature activation+0.000
Society
Token Society
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
,
Token,
Feature activation+3.305
and
Token and
Feature activation+0.000
offices
Token offices
Feature activation+0.000
for
Token for
Feature activation+0.000
medical
Token medical
Feature activation+0.000
services
Token services
Feature activation+0.000
arts
Token arts
Feature activation+0.000
groups
Token groups
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
created
Token created
Feature activation+0.000
,
Token,
Feature activation+3.278
according
Token according
Feature activation+0.560
to
Token to
Feature activation+1.855
the
Token the
Feature activation+0.112
plans
Token plans
Feature activation+0.271
,
Token,
Feature activation+1.661

INTERVAL 2.644 - 2.974
CONTAINS 0.000%

in
Token in
Feature activation+0.252
the
Token the
Feature activation+0.168
process
Token process
Feature activation+0.329
.
Token.
Feature activation+2.564
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.919
The
TokenThe
Feature activation+0.852
Conservative
Token Conservative
Feature activation+0.114
party
Token party
Feature activation+0.000
is
Token is
Feature activation+0.000
having
Token having
Feature activation+0.136
Vegas
Token Vegas
Feature activation+0.000
and
Token and
Feature activation+0.000
Clark
Token Clark
Feature activation+0.000
County
Token County
Feature activation+0.000
departments
Token departments
Feature activation+0.000
.
Token.
Feature activation+2.858
Ċ
TokenĊ
Feature activation+0.045
Ċ
TokenĊ
Feature activation+3.034
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.048
I
TokenI
Feature activation+0.371
abor
Tokenabor
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
on
Token on
Feature activation+0.000
these
Token these
Feature activation+0.000
steps
Token steps
Feature activation+0.000
,
Token,
Feature activation+2.653
the
Token the
Feature activation+2.154
adviser
Token adviser
Feature activation+0.671
said
Token said
Feature activation+0.115
J
Token J
Feature activation+0.000
adh
Tokenadh
Feature activation+0.000

INTERVAL 2.313 - 2.644
CONTAINS 0.002%

it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
troubling
Token troubling
Feature activation+0.000
.'
Token.'
Feature activation+2.338
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.414
He
TokenHe
Feature activation+0.086
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
troubling
Token troubling
Feature activation+0.000
.'
Token.'
Feature activation+2.338
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.414
He
TokenHe
Feature activation+0.086
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
change
Token change
Feature activation+0.000
keep
Token keep
Feature activation+0.000
knocking
Token knocking
Feature activation+0.000
down
Token down
Feature activation+0.000
these
Token these
Feature activation+0.000
barriers
Token barriers
Feature activation+0.000
,"
Token,"
Feature activation+2.601
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+0.069
"
Token "
Feature activation+0.000
new
Tokennew
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
bubbles
Token bubbles
Feature activation+0.000
,
Token,
Feature activation+2.570
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.468
he
Token he
Feature activation+0.595
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.697
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
tests
Token tests
Feature activation+0.000
,
Token,
Feature activation+0.066
police
Token police
Feature activation+0.000
said
Token said
Feature activation+0.576
.
Token.
Feature activation+2.576
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.852
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.292
They
TokenThey
Feature activation+0.000

INTERVAL 1.983 - 2.313
CONTAINS 0.004%

,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
began
Token began
Feature activation+0.000
April
Token April
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+2.232
The
Token The
Feature activation+0.593
NDP
Token NDP
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
such
Token such
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.000
in
Token in
Feature activation+0.000
English
Token English
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+2.151
Fog
Token Fog
Feature activation+0.000
el
Tokenel
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
present
Token present
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
be
Token be
Feature activation+0.000
around
Token around
Feature activation+0.000
,"
Token,"
Feature activation+2.266
Rob
Token Rob
Feature activation+1.307
e
Tokene
Feature activation+0.153
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
countries
Token countries
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
pressured
Token pressured
Feature activation+0.000
further
Token further
Feature activation+0.000
,
Token,
Feature activation+2.017
said
Token said
Feature activation+1.919
the
Token the
Feature activation+0.149
Cardinal
Token Cardinal
Feature activation+0.251
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
unique
Token unique
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
comics
Token comics
Feature activation+0.000
.
Token.
Feature activation+2.214
What
Token What
Feature activation+0.027
might
Token might
Feature activation+0.000
Rick
Token Rick
Feature activation+0.237
's
Token's
Feature activation+0.000
reaction
Token reaction
Feature activation+0.000

INTERVAL 1.652 - 1.983
CONTAINS 0.010%

Twitter
Token Twitter
Feature activation+0.000
.
Token.
Feature activation+1.059
In
Token In
Feature activation+0.000
August
Token August
Feature activation+0.006
2015
Token 2015
Feature activation+1.121
,
Token,
Feature activation+1.845
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
tweets
Token tweets
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+2.228
Over
Token Over
Feature activation+0.000
eight
Token eight
Feature activation+0.000
years
Token years
Feature activation+0.733
,
Token,
Feature activation+1.896
Un
Token Un
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
man
Tokenman
Feature activation+0.025
brought
Token brought
Feature activation+0.416
in
Token in
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
age
Token age
Feature activation+0.000
and
Token and
Feature activation+0.000
pedigree
Token pedigree
Feature activation+0.000
."
Token."
Feature activation+1.834
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.570
The
TokenThe
Feature activation+0.784
Jets
Token Jets
Feature activation+0.022
didn
Token didn
Feature activation+0.000
election
Token election
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.506
Ċ
TokenĊ
Feature activation+0.741
Ċ
TokenĊ
Feature activation+1.671
WATCH
TokenWATCH
Feature activation+0.143
DA
Token DA
Feature activation+0.000
ILY
TokenILY
Feature activation+0.000
CALL
Token CALL
Feature activation+0.000
ER
TokenER
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.628
A
TokenA
Feature activation+0.000
search
Token search
Feature activation+0.000
of
Token of
Feature activation+0.003
Jason
Token Jason
Feature activation+1.761
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.286
s
Tokens
Feature activation+0.000
bedroom
Token bedroom
Feature activation+0.000
supports
Token supports
Feature activation+0.000

INTERVAL 1.322 - 1.652
CONTAINS 0.020%

]
Token]
Feature activation+0.000
and
Token and
Feature activation+0.000
1935
Token 1935
Feature activation+0.000
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+1.505
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.746
Decl
TokenDecl
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
and
Token and
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
pet
Token pet
Feature activation+0.000
.
Token.
Feature activation+1.413
(
Token (
Feature activation+0.000
Note
TokenNote
Feature activation+0.000
:
Token:
Feature activation+0.135
this
Token this
Feature activation+0.000
video
Token video
Feature activation+0.000
enberg
Tokenenberg
Feature activation+0.000
sought
Token sought
Feature activation+0.000
the
Token the
Feature activation+0.000
assistance
Token assistance
Feature activation+0.000
of
Token of
Feature activation+0.000
Robert
Token Robert
Feature activation+1.420
L
Token L
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
2000
Token 2000
Feature activation+0.000
.
Token.
Feature activation+0.611
Collins
Token Collins
Feature activation+0.021
and
Token and
Feature activation+1.358
S
Token S
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
each
Token each
Feature activation+0.000
take
Token take
Feature activation+0.000
on
Token on
Feature activation+0.000
left
Token left
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
Party
Token Party
Feature activation+0.000
.
Token.
Feature activation+1.570
He
Token He
Feature activation+0.150
said
Token said
Feature activation+0.452
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
membership
Token membership
Feature activation+0.000

INTERVAL 0.991 - 1.322
CONTAINS 0.052%

this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.299
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.344
Senator
TokenSenator
Feature activation+1.103
Day
Token Day
Feature activation+0.000
was
Token was
Feature activation+0.000
officially
Token officially
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
tor
Token tor
Feature activation+0.000
mented
Tokenmented
Feature activation+0.000
,
Token,
Feature activation+0.000
disabled
Token disabled
Feature activation+0.068
survivor
Token survivor
Feature activation+0.140
.
Token.
Feature activation+1.110
While
Token While
Feature activation+0.645
the
Token the
Feature activation+0.652
conversation
Token conversation
Feature activation+0.000
over
Token over
Feature activation+0.308
whether
Token whether
Feature activation+0.700
London
Token London
Feature activation+0.000
this
Token this
Feature activation+0.000
evening
Token evening
Feature activation+0.000
.
Token.
Feature activation+0.749
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.043
But
TokenBut
Feature activation+0.377
she
Token she
Feature activation+0.000
says
Token says
Feature activation+0.152
her
Token her
Feature activation+0.000
show
Token show
Feature activation+0.000
V
Token V
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
oba
Tokenoba
Feature activation+0.000
.
Token.
Feature activation+1.347
Ċ
TokenĊ
Feature activation+0.050
Ċ
TokenĊ
Feature activation+1.196
On
TokenOn
Feature activation+0.000
July
Token July
Feature activation+0.000
7
Token 7
Feature activation+0.151
,
Token,
Feature activation+1.437
he
Token he
Feature activation+0.000
,
Token,
Feature activation+0.000
Pant
Token Pant
Feature activation+0.000
ani
Tokenani
Feature activation+0.000
never
Token never
Feature activation+0.000
confessed
Token confessed
Feature activation+0.000
.
Token.
Feature activation+1.125
He
Token He
Feature activation+0.000
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.661 - 0.991
CONTAINS 0.113%

vote
Token vote
Feature activation+0.000
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
overwhelming
Token overwhelming
Feature activation+0.000
majority
Token majority
Feature activation+0.000
.
Token.
Feature activation+0.769
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.054
Others
TokenOthers
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000
votes
Token votes
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.625
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.869
Supporters
TokenSupporters
Feature activation+0.000
celebrate
Token celebrate
Feature activation+0.000
at
Token at
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
's
Token's
Feature activation+0.000
AUD
TokenAUD
Feature activation+0.000
as
Token as
Feature activation+0.177
an
Token an
Feature activation+0.000
asset
Token asset
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.537
Ċ
TokenĊ
Feature activation+0.749
The
TokenThe
Feature activation+0.417
Australian
Token Australian
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
which
Token which
Feature activation+0.000
the
Token the
Feature activation+0.169
union
Token union
Feature activation+0.000
recommended
Token recommended
Feature activation+0.000
against
Token against
Feature activation+0.000
.
Token.
Feature activation+0.893
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.662
Thirty
TokenThirty
Feature activation+0.000
-
Token-
Feature activation+0.000
four
Tokenfour
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
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
.
Token.
Feature activation+0.692
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.590
S
TokenS
Feature activation+0.368
ELF
TokenELF
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.330 - 0.661
CONTAINS 0.278%

ÙĪ
TokenÙĪ
Feature activation+0.187
اØ
TokenاØ
Feature activation+0.000
²
Token²
Feature activation+0.631
Ùĩ
TokenÙĩ
Feature activation+0.000
âĢİ
TokenâĢİ
Feature activation+0.527
,
Token,
Feature activation+0.535
literally
Token literally
Feature activation+0.000
"
Token "
Feature activation+0.620
gate
Tokengate
Feature activation+0.000
";
Token";
Feature activation+0.000
also
Token also
Feature activation+0.000
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.000
too
Token too
Feature activation+0.000
few
Token few
Feature activation+0.000
apprentices
Token apprentices
Feature activation+0.000
."
Token."
Feature activation+0.444
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.454
Despite
TokenDespite
Feature activation+0.000
the
Token the
Feature activation+0.000
criticism
Token criticism
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
photo
Token photo
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
Gu
TokenGu
Feature activation+0.403
and
Token and
Feature activation+0.000
family
Token family
Feature activation+0.000
aide
Token aide
Feature activation+0.216
Zhang
Token Zhang
Feature activation+0.000
Xia
Token Xia
Feature activation+0.000
with
Token with
Feature activation+0.000
ash
Token ash
Feature activation+0.000
and
Token and
Feature activation+0.000
acid
Token acid
Feature activation+0.000
rain
Token rain
Feature activation+0.000
.
Token.
Feature activation+0.340
Additionally
Token Additionally
Feature activation+0.000
,
Token,
Feature activation+0.802
most
Token most
Feature activation+1.024
peoples
Token peoples
Feature activation+0.000
'
Token'
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
just
Tokenjust
Feature activation+0.000
knows
Token knows
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.528
As
Token As
Feature activation+0.000
far
Token far
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 0.000 - 0.330
CONTAINS 99.520%

Ramos
Token Ramos
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
free
Token free
Feature activation+0.000
kick
Token kick
Feature activation+0.000
,
Token,
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000
quick
Token quick
Feature activation+0.000
return
Token return
Feature activation+0.000
pass
Token pass
Feature activation+0.000
possible
Token possible
Feature activation+0.000
terms
Token terms
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
what
Token what
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
could
Token could
Feature activation+0.000
get
Token get
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
a
Token a
Feature activation+0.000
line
Token line
Feature activation+0.000
that
Token that
Feature activation+0.000
mixes
Token mixes
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
formula
Token formula
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
Nintendo
Token Nintendo
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
media
Token media
Feature activation+0.000
journalists
Token journalists
Feature activation+0.000
who
Token who
Feature activation+0.000
lav
Token lav
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
election
Token election
Feature activation+0.000
bid
Token bid
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
village
Token village
Feature activation+0.000
board
Token board
Feature activation+0.000
member
Token member
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
has
Token has
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+0.023
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.023
A
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+0.023
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+0.023
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+0.023
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.023
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.023
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature 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+0.023
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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+0.023
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.023
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 3 in H8.3: (feature 21284)

TOP ACTIVATIONS
MAX = 2.126

.
Token.
Feature activation+0.139
Find
Token Find
Feature activation+0.000
out
Token out
Feature activation+0.000
what
Token what
Feature activation+0.628
happened
Token happened
Feature activation+0.000
to
Token to
Feature activation+2.126
the
Token the
Feature activation+0.758
world
Token world
Feature activation+0.152
and
Token and
Feature activation+0.000
return
Token return
Feature activation+0.000
the
Token the
Feature activation+0.117
pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
an
Token an
Feature activation+0.000
in
Token in
Feature activation+0.000
/
Token/
Feature activation+2.106
out
Tokenout
Feature activation+0.000
referendum
Token referendum
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
operate
Token operate
Feature activation+0.000
or
Token or
Feature activation+0.000
work
Token work
Feature activation+0.000
for
Token for
Feature activation+2.103
an
Token an
Feature activation+1.252
un
Token un
Feature activation+0.000
approved
Tokenapproved
Feature activation+0.000
food
Token food
Feature activation+0.000
business
Token business
Feature activation+0.000
et
Tokenet
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
etic
Tokenetic
Feature activation+0.000
acid
Token acid
Feature activation+0.000
(
Token (
Feature activation+2.056
and
Tokenand
Feature activation+0.033
breathe
Token breathe
Feature activation+0.344
),
Token),
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
See
Token See
Feature activation+0.000
our
Token our
Feature activation+0.000
website
Token website
Feature activation+0.000
www
Token www
Feature activation+0.065
.
Token.
Feature activation+2.028
in
Tokenin
Feature activation+0.403
4
Token4
Feature activation+0.452
ins
Tokenins
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
Fine
Token Fine
Feature activation+0.000
Cannabis
Token Cannabis
Feature activation+0.000
Disp
Token Disp
Feature activation+0.000
ens
Tokenens
Feature activation+0.000
ary
Tokenary
Feature activation+0.000
in
Token in
Feature activation+2.007
Las
Token Las
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
,
Token,
Feature activation+0.000
grabbed
Token grabbed
Feature activation+0.000
a
Token a
Feature activation+0.000
and
Token and
Feature activation+0.000
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+0.000
ample
Token ample
Feature activation+0.000
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+1.940
both
Token both
Feature activation+0.942
developing
Token developing
Feature activation+0.000
and
Token and
Feature activation+0.000
mature
Token mature
Feature activation+0.000
was
Token was
Feature activation+0.000
Aid
TokenAid
Feature activation+0.000
and
Token and
Feature activation+0.000
reveal
Token reveal
Feature activation+0.000
what
Token what
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+1.912
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
syn
Token syn
Feature activation+0.000
onyms
Tokenonyms
Feature activation+0.055
for
Token for
Feature activation+1.212
the
Token the
Feature activation+0.651
word
Token word
Feature activation+1.899
As
Token As
Feature activation+0.021
ura
Tokenura
Feature activation+0.000
is
Token is
Feature activation+0.935
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.729
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+0.000
Family
Token Family
Feature activation+0.000
Association
Token Association
Feature activation+0.000
(
Token (
Feature activation+1.834
A
TokenA
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
),
Token),
Feature activation+0.000
based
Token based
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.051
Flowers
Token Flowers
Feature activation+0.000
and
Token and
Feature activation+0.000
plant
Token plant
Feature activation+0.000
life
Token life
Feature activation+0.000
attract
Token attract
Feature activation+1.747
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
yards
Token yards
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
rule
Token rule
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
in
Token in
Feature activation+0.000
effect
Token effect
Feature activation+0.000
."
Token."
Feature activation+1.611
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.654
Allen
TokenAllen
Feature activation+0.000
completed
Token completed
Feature activation+0.000
9
Token 9
Feature activation+0.000
goes
Token goes
Feature activation+0.000
also
Token also
Feature activation+0.000
A
Token A
Feature activation+0.000
rian
Tokenrian
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
.
Token.
Feature activation+1.597
Sn
Token Sn
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.793
an
Token an
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
side
Tokenside
Feature activation+0.134
with
Token with
Feature activation+0.729
a
Token a
Feature activation+1.574
never
Token never
Feature activation+0.000
-
Token-
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
-
Token-
Feature activation+0.000
heard
Tokenheard
Feature activation+0.233
Joel
Token Joel
Feature activation+0.000
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
Eric
Token Eric
Feature activation+0.000
kson
Tokenkson
Feature activation+0.000
(@
Token (@
Feature activation+1.557
Jo
TokenJo
Feature activation+0.867
el
Tokenel
Feature activation+0.702
AE
TokenAE
Feature activation+0.000
ricks
Tokenricks
Feature activation+0.000
on
Tokenon
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
thigh
Token thigh
Feature activation+0.000
cont
Token cont
Feature activation+0.000
usion
Tokenusion
Feature activation+0.000
.
Token.
Feature activation+1.553
He
Token He
Feature activation+0.000
's
Token's
Feature activation+0.000
averaging
Token averaging
Feature activation+0.000
a
Token a
Feature activation+0.000
mere
Token mere
Feature activation+0.000
was
Token was
Feature activation+0.000
As
Token As
Feature activation+0.000
ura
Tokenura
Feature activation+0.000
.
Token.
Feature activation+0.390
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.546
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Our
TokenOur
Feature activation+0.012
[
Token [
Feature activation+0.030
goal
Tokengoal
Feature activation+0.000
In
Token In
Feature activation+0.000
verse
Tokenverse
Feature activation+0.000
Phase
Token Phase
Feature activation+0.000
(
Token (
Feature activation+0.000
http
Token http
Feature activation+0.000
://
Token://
Feature activation+1.543
in
Tokenin
Feature activation+0.141
verse
Tokenverse
Feature activation+0.000
phase
Tokenphase
Feature activation+0.000
.
Token.
Feature activation+0.009
band
Tokenband
Feature activation+0.000
International
Token International
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
of
Token of
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
Thought
Token Thought
Feature activation+0.000
(
Token (
Feature activation+1.527
II
TokenII
Feature activation+0.212
IT
TokenIT
Feature activation+0.000
).
Token).
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.279
issue
Token issue
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
for
Token for
Feature activation+1.018
the
Token the
Feature activation+1.520
A
Token A
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000

Top DFA by src position
MAX = 2.909

unravel
Token unravel
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
mysteries
Token mysteries
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
A
Token A
Feature activation+0.109
Top resid features:
ez
Tokenez
Feature activation+1.518
Top resid features:
ir
Tokenir
Feature activation+0.739
Top resid features:
.
Token.
Feature activation+0.380
Top resid features:
Find
Token Find
Feature activation+0.018
Top resid features:
out
Token out
Feature activation-0.004
Top resid features:
what
Token what
Feature activation+0.006
Top resid features:
pledge
Token pledge
Feature activation-0.013
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
hold
Token hold
Feature activation-0.005
Top resid features:
an
Token an
Feature activation+0.055
Top resid features:
in
Token in
Feature activation-0.093
Top resid features:
/
Token/
Feature activation+2.894
Top resid features:
out
Tokenout
Feature activation+0.000
Top resid features:
referendum
Token referendum
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:
Alberta
Token Alberta
Feature activation+0.005
Top resid features:
."
Token."
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
A
TokenA
Feature activation+0.029
Top resid features:
HS
TokenHS
Feature activation+2.443
Top resid features:
said
Token said
Feature activation+0.012
Top resid features:
people
Token people
Feature activation+0.019
Top resid features:
who
Token who
Feature activation-0.001
Top resid features:
operate
Token operate
Feature activation+0.025
Top resid features:
or
Token or
Feature activation+0.002
Top resid features:
using
Token using
Feature activation+0.031
Top resid features:
eth
Token eth
Feature activation-0.329
Top resid features:
yl
Tokenyl
Feature activation+0.176
Top resid features:
ened
Tokenened
Feature activation+0.395
Top resid features:
iam
Tokeniam
Feature activation+0.199
Top resid features:
inet
Tokeninet
Feature activation+1.642
Top resid features:
et
Tokenet
Feature activation+0.065
Top resid features:
ra
Tokenra
Feature activation+0.004
Top resid features:
ac
Tokenac
Feature activation+0.448
Top resid features:
etic
Tokenetic
Feature activation+0.139
Top resid features:
acid
Token acid
Feature activation+0.064
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
ste
Token ste
Feature activation+0.000
Top resid features:
ve
Tokenve
Feature activation+0.007
Top resid features:
@
Token@
Feature activation-0.015
Top resid features:
in
Tokenin
Feature activation+0.482
Top resid features:
4
Token4
Feature activation+1.634
Top resid features:
ins
Tokenins
Feature activation+0.473
Top resid features:
.
Token.
Feature activation+0.111
Top resid features:
com
Tokencom
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
See
Token See
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
worker
Token worker
Feature activation-0.010
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
In
Token In
Feature activation+0.055
Top resid features:
yo
Tokenyo
Feature activation+2.585
Top resid features:
Fine
Token Fine
Feature activation-0.001
Top resid features:
Cannabis
Token Cannabis
Feature activation-0.015
Top resid features:
Disp
Token Disp
Feature activation+0.001
Top resid features:
ens
Tokenens
Feature activation-0.001
Top resid features:
ary
Tokenary
Feature activation+0.007
Top resid features:
regularly
Token regularly
Feature activation-0.000
Top resid features:
emptied
Token emptied
Feature activation+0.001
Top resid features:
also
Token also
Feature activation+0.001
Top resid features:
attract
Token attract
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.064
Top resid features:
ps
Tokenps
Feature activation+2.359
Top resid features:
that
Token that
Feature activation+0.048
Top resid features:
are
Token are
Feature activation-0.000
Top resid features:
seeking
Token seeking
Feature activation+0.013
Top resid features:
sources
Token sources
Feature activation+0.005
Top resid features:
food
Token food
Feature activation+0.006
Top resid features:
Aid
TokenAid
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
reveal
Token reveal
Feature activation-0.003
Top resid features:
what
Token what
Feature activation-0.016
Top resid features:
was
Token was
Feature activation-0.218
Top resid features:
and
Token and
Feature activation+2.909
Top resid features:
wasn
Token wasn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.007
Top resid features:
word
Token word
Feature activation-0.001
Top resid features:
As
Token As
Feature activation+0.100
Top resid features:
ura
Tokenura
Feature activation+2.111
Top resid features:
in
Token in
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Nir
Token Nir
Feature activation+0.004
Top resid features:
uk
Tokenuk
Feature activation+0.027
Top resid features:
ta
Tokenta
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
The
TokenThe
Feature activation+0.046
Top resid features:
American
Token American
Feature activation-0.092
Top resid features:
Family
Token Family
Feature activation+2.190
Top resid features:
Association
Token Association
Feature activation+0.444
Top resid features:
(
Token (
Feature activation-0.016
Top resid features:
A
TokenA
Feature activation+0.000
Top resid features:
FA
TokenFA
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.157
Top resid features:
was
Token was
Feature activation+0.032
Top resid features:
p
Tokenp
Feature activation+2.225
Top resid features:
nesting
Token nesting
Feature activation+0.046
Top resid features:
spots
Token spots
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Flowers
Token Flowers
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
tank
Token tank
Feature activation+0.001
Top resid features:
too
Token too
Feature activation+0.001
Top resid features:
,"
Token,"
Feature activation+0.003
Top resid features:
En
Token En
Feature activation+0.023
Top resid features:
os
Tokenos
Feature activation+2.040
Top resid features:
said
Token said
Feature activation+0.222
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
My
TokenMy
Feature activation+0.002
Top resid features:
wife
Token wife
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.048
Top resid features:
it
Token it
Feature activation+0.022
Top resid features:
goes
Token goes
Feature activation+0.003
Top resid features:
also
Token also
Feature activation-0.001
Top resid features:
A
Token A
Feature activation+0.158
Top resid features:
rian
Tokenrian
Feature activation+0.975
Top resid features:
ism
Tokenism
Feature activation+0.327
Top resid features:
.
Token.
Feature activation+0.199
Top resid features:
Sn
Token Sn
Feature activation+0.000
Top resid features:
iff
Tokeniff
Feature activation+0.000
Top resid features:
.)
Token.)
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
couple
Token couple
Feature activation+0.009
Top resid features:
an
Token an
Feature activation+0.011
Top resid features:
A
Token A
Feature activation+0.137
Top resid features:
-
Token-
Feature activation+0.373
Top resid features:
side
Tokenside
Feature activation+1.568
Top resid features:
with
Token with
Feature activation+0.161
Top resid features:
a
Token a
Feature activation+0.083
Top resid features:
never
Token never
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
before
Tokenbefore
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.013
Top resid features:
Joel
Token Joel
Feature activation+0.186
Top resid features:
A
Token A
Feature activation+0.108
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
Eric
Token Eric
Feature activation+1.490
Top resid features:
kson
Tokenkson
Feature activation+0.457
Top resid features:
(@
Token (@
Feature activation+0.041
Top resid features:
Jo
TokenJo
Feature activation+0.000
Top resid features:
el
Tokenel
Feature activation+0.000
Top resid features:
AE
TokenAE
Feature activation+0.000
Top resid features:
season
Token season
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
As
TokenAs
Feature activation+0.025
Top resid features:
ik
Tokenik
Feature activation+1.656
Top resid features:
was
Token was
Feature activation+0.501
Top resid features:
shel
Token shel
Feature activation+0.025
Top resid features:
ved
Tokenved
Feature activation+0.028
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
week
Token week
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
The
Token The
Feature activation+0.037
Top resid features:
result
Token result
Feature activation+0.014
Top resid features:
was
Token was
Feature activation+0.016
Top resid features:
As
Token As
Feature activation+0.139
Top resid features:
ura
Tokenura
Feature activation+1.632
Top resid features:
.
Token.
Feature activation+0.341
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
ch
Token ch
Feature activation+0.002
Top resid features:
ipt
Tokenipt
Feature activation-0.001
Top resid features:
une
Tokenune
Feature activation+0.009
Top resid features:
artist
Token artist
Feature activation+0.003
Top resid features:
In
Token In
Feature activation+0.272
Top resid features:
verse
Tokenverse
Feature activation+1.727
Top resid features:
Phase
Token Phase
Feature activation+0.115
Top resid features:
(
Token (
Feature activation+0.080
Top resid features:
http
Token http
Feature activation+0.063
Top resid features:
://
Token://
Feature activation+0.023
Top resid features:
in
Tokenin
Feature activation+0.000
Top resid features:
NA
TokenNA
Feature activation+0.103
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
International
Token International
Feature activation-0.648
Top resid features:
Institute
Token Institute
Feature activation+0.652
Top resid features:
of
Token of
Feature activation+1.115
Top resid features:
Islamic
Token Islamic
Feature activation+0.995
Top resid features:
Thought
Token Thought
Feature activation+0.117
Top resid features:
(
Token (
Feature activation-0.090
Top resid features:
II
TokenII
Feature activation+0.000
Top resid features:
IT
TokenIT
Feature activation+0.000
Top resid features:
hold
Tokenhold
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
A
Token A
Feature activation+0.025
Top resid features:
FA
TokenFA
Feature activation+1.774
Top resid features:
has
Token has
Feature activation+0.064
Top resid features:
also
Token also
Feature activation+0.002
Top resid features:
recently
Token recently
Feature activation-0.001
Top resid features:
weighed
Token weighed
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.03

Head 3: 0.48

Head 4: 0.02

Head 5: 0.04

Head 6: 0.03

Head 7: 0.03

Head 8: 0.05

Head 9: 0.04

Head 10: 0.12

Head 11: 0.11

Positive logits

Amen3.71

Ao3.02

Ib3.02

Izan3.01

Amon2.97

Ame2.96

Ai2.91

Anon2.78

Ara2.75

Ancients2.74

Ain2.71

Aus2.63

Om2.62

Oral2.62

Aki2.60

Anne2.59

Aval2.52

Ae2.50

Inn2.50

Aven2.50

Negative logits

kefeller-2.60

owell-2.39

pace-2.36

yrinth-2.34

rower-2.21

paces-2.18

leground-2.15

luster-2.12

VC-2.07

Rockefeller-2.06

caucuses-2.06

itudinal-2.06

ungle-2.05

WF-2.04

uliffe-2.02

riott-2.02

psey-2.02

rador-2.00

WM-2.00

Speaker-1.99

INTERVAL 1.913 - 2.126
CONTAINS 0.001%

pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
an
Token an
Feature activation+0.000
in
Token in
Feature activation+0.000
/
Token/
Feature activation+2.106
out
Tokenout
Feature activation+0.000
referendum
Token referendum
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
operate
Token operate
Feature activation+0.000
or
Token or
Feature activation+0.000
work
Token work
Feature activation+0.000
for
Token for
Feature activation+2.103
an
Token an
Feature activation+1.252
un
Token un
Feature activation+0.000
approved
Tokenapproved
Feature activation+0.000
food
Token food
Feature activation+0.000
business
Token business
Feature activation+0.000
.
Token.
Feature activation+0.139
Find
Token Find
Feature activation+0.000
out
Token out
Feature activation+0.000
what
Token what
Feature activation+0.628
happened
Token happened
Feature activation+0.000
to
Token to
Feature activation+2.126
the
Token the
Feature activation+0.758
world
Token world
Feature activation+0.152
and
Token and
Feature activation+0.000
return
Token return
Feature activation+0.000
the
Token the
Feature activation+0.117
and
Token and
Feature activation+0.000
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+0.000
ample
Token ample
Feature activation+0.000
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+1.940
both
Token both
Feature activation+0.942
developing
Token developing
Feature activation+0.000
and
Token and
Feature activation+0.000
mature
Token mature
Feature activation+0.000
was
Token was
Feature activation+0.000
et
Tokenet
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
etic
Tokenetic
Feature activation+0.000
acid
Token acid
Feature activation+0.000
(
Token (
Feature activation+2.056
and
Tokenand
Feature activation+0.033
breathe
Token breathe
Feature activation+0.344
),
Token),
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.701 - 1.913
CONTAINS 0.000%

Aid
TokenAid
Feature activation+0.000
and
Token and
Feature activation+0.000
reveal
Token reveal
Feature activation+0.000
what
Token what
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+1.912
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+0.000
Family
Token Family
Feature activation+0.000
Association
Token Association
Feature activation+0.000
(
Token (
Feature activation+1.834
A
TokenA
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
),
Token),
Feature activation+0.000
based
Token based
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.051
Flowers
Token Flowers
Feature activation+0.000
and
Token and
Feature activation+0.000
plant
Token plant
Feature activation+0.000
life
Token life
Feature activation+0.000
attract
Token attract
Feature activation+1.747
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
yards
Token yards
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
syn
Token syn
Feature activation+0.000
onyms
Tokenonyms
Feature activation+0.055
for
Token for
Feature activation+1.212
the
Token the
Feature activation+0.651
word
Token word
Feature activation+1.899
As
Token As
Feature activation+0.021
ura
Tokenura
Feature activation+0.000
is
Token is
Feature activation+0.935
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.729

INTERVAL 1.488 - 1.701
CONTAINS 0.001%

In
Token In
Feature activation+0.000
verse
Tokenverse
Feature activation+0.000
Phase
Token Phase
Feature activation+0.000
(
Token (
Feature activation+0.000
http
Token http
Feature activation+0.000
://
Token://
Feature activation+1.543
in
Tokenin
Feature activation+0.141
verse
Tokenverse
Feature activation+0.000
phase
Tokenphase
Feature activation+0.000
.
Token.
Feature activation+0.009
band
Tokenband
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
thigh
Token thigh
Feature activation+0.000
cont
Token cont
Feature activation+0.000
usion
Tokenusion
Feature activation+0.000
.
Token.
Feature activation+1.553
He
Token He
Feature activation+0.000
's
Token's
Feature activation+0.000
averaging
Token averaging
Feature activation+0.000
a
Token a
Feature activation+0.000
mere
Token mere
Feature activation+0.000
an
Token an
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
side
Tokenside
Feature activation+0.134
with
Token with
Feature activation+0.729
a
Token a
Feature activation+1.574
never
Token never
Feature activation+0.000
-
Token-
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
-
Token-
Feature activation+0.000
heard
Tokenheard
Feature activation+0.233
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.279
issue
Token issue
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
for
Token for
Feature activation+1.018
the
Token the
Feature activation+1.520
A
Token A
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
said
Token said
Feature activation+0.000
rule
Token rule
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
in
Token in
Feature activation+0.000
effect
Token effect
Feature activation+0.000
."
Token."
Feature activation+1.611
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.654
Allen
TokenAllen
Feature activation+0.000
completed
Token completed
Feature activation+0.000
9
Token 9
Feature activation+0.000

INTERVAL 1.276 - 1.488
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000
8
Token8
Feature activation+0.000
-
Token -
Feature activation+1.337
1
Token 1
Feature activation+0.083
/
Token/
Feature activation+0.000
4
Token4
Feature activation+0.000
teaspoon
Token teaspoon
Feature activation+0.000
c
Token c
Feature activation+0.000
William
Token William
Feature activation+1.179
Elf
Token Elf
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
Le
Token Le
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
established
Token established
Feature activation+1.363
the
Token the
Feature activation+1.350
genus
Token genus
Feature activation+1.056
Lab
Token Lab
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
club
Token club
Feature activation+0.000
's
Token's
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+1.351
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
MER
TokenMER
Feature activation+0.000
C
TokenC
Feature activation+0.000
ED
TokenED
Feature activation+0.000
(
Token (
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
A
TokenA
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+1.320
a
Token a
Feature activation+0.565
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
B
TokenB
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.977
to
Token to
Feature activation+1.286
result
Token result
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
physical
Token physical
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.063 - 1.276
CONTAINS 0.003%

545
Token545
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
.
Token.
Feature activation+0.580
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.163
P
TokenP
Feature activation+0.000
ose
Tokenose
Feature activation+0.000
y
Tokeny
Feature activation+0.000
joined
Token joined
Feature activation+0.000
Evans
Token Evans
Feature activation+0.000
least
Token least
Feature activation+0.000
two
Token two
Feature activation+0.000
bedrooms
Token bedrooms
Feature activation+0.000
,
Token,
Feature activation+0.000
developers
Token developers
Feature activation+0.000
Robin
Token Robin
Feature activation+1.104
Lou
Token Lou
Feature activation+0.000
der
Tokender
Feature activation+0.000
mil
Tokenmil
Feature activation+0.000
k
Tokenk
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
coasts
Token coasts
Feature activation+0.000
.
Token.
Feature activation+0.556
An
Token An
Feature activation+0.000
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+1.223
Opt
Token Opt
Feature activation+0.000
ima
Tokenima
Feature activation+0.000
paid
Token paid
Feature activation+0.000
$
Token $
Feature activation+0.000
34
Token34
Feature activation+0.000
-
Token-
Feature activation+0.000
B
TokenB
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
@
Token@
Feature activation+0.000
"
Token"
Feature activation+0.000
and
Token and
Feature activation+1.161
the
Token the
Feature activation+0.410
region
Token region
Feature activation+0.000
around
Token around
Feature activation+0.442
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
with
Token with
Feature activation+0.000
AR
Token AR
Feature activation+0.000
IM
TokenIM
Feature activation+0.000
A
TokenA
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.014
Ċ
TokenĊ
Feature activation+1.197
A
TokenA
Feature activation+0.585
rim
Tokenrim
Feature activation+0.000
aa
Tokenaa
Feature activation+0.224
()
Token ()
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 0.850 - 1.063
CONTAINS 0.006%

.
Token.
Feature activation+0.084
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.413
As
TokenAs
Feature activation+0.000
described
Token described
Feature activation+0.000
on
Token on
Feature activation+0.886
the
Token the
Feature activation+0.677
official
Token official
Feature activation+0.065
Xbox
Token Xbox
Feature activation+0.000
One
Token One
Feature activation+0.000
web
Token web
Feature activation+0.000
and
Token and
Feature activation+0.194
facilitating
Token facilitating
Feature activation+0.000
the
Token the
Feature activation+0.306
growth
Token growth
Feature activation+0.000
of
Token of
Feature activation+1.332
an
Token an
Feature activation+0.917
a
Token a
Feature activation+0.000
sexual
Tokensexual
Feature activation+0.000
community
Token community
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.216
the
Token the
Feature activation+0.191
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
assassination
Token assassination
Feature activation+0.000
comedy
Token comedy
Feature activation+0.900
The
Token The
Feature activation+0.405
Interview
Token Interview
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
to
Tokento
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
creators
Token creators
Feature activation+0.000
told
Token told
Feature activation+1.026
Torrent
Token Torrent
Feature activation+0.322
Fre
TokenFre
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token '
Feature activation+0.000
a
Tokena
Feature activation+0.000
.
Token .
Feature activation+0.962
This
Token This
Feature activation+0.923
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
named
Token named
Feature activation+0.084
lifetime
Token lifetime
Feature activation+0.000
parameter
Token parameter
Feature activation+0.225

INTERVAL 0.638 - 0.850
CONTAINS 0.012%

.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
and
Token and
Feature activation+0.000
prior
Token prior
Feature activation+0.000
,
Token,
Feature activation+0.000
placing
Token placing
Feature activation+0.725
a
Token a
Feature activation+1.184
new
Token new
Feature activation+0.332
block
Token block
Feature activation+0.000
on
Token on
Feature activation+0.214
the
Token the
Feature activation+0.481
postponed
Token postponed
Feature activation+0.000
again
Token again
Feature activation+0.000
until
Token until
Feature activation+0.000
March
Token March
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.778
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.519
These
TokenThese
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
Find
Token Find
Feature activation+0.000
out
Token out
Feature activation+0.000
what
Token what
Feature activation+0.628
happened
Token happened
Feature activation+0.000
to
Token to
Feature activation+2.126
the
Token the
Feature activation+0.758
world
Token world
Feature activation+0.152
and
Token and
Feature activation+0.000
return
Token return
Feature activation+0.000
the
Token the
Feature activation+0.117
nine
Token nine
Feature activation+0.291
uc
Tokenuc
Feature activation+0.000
ible
Tokenible
Feature activation+0.000
components
Token components
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.693
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
collection
Token collection
Feature activation+0.000
of
Token of
Feature activation+0.000
for
Token for
Feature activation+0.000
humans
Token humans
Feature activation+0.000
.
Token.
Feature activation+0.491
Since
Token Since
Feature activation+0.000
2004
Token 2004
Feature activation+0.000
,
Token,
Feature activation+0.695
the
Token the
Feature activation+0.319
Ar
Token Ar
Feature activation+0.039
im
Tokenim
Feature activation+0.000
aa
Tokenaa
Feature activation+0.000
community
Token community
Feature activation+0.000

INTERVAL 0.425 - 0.638
CONTAINS 0.024%

that
Token that
Feature activation+0.000
being
Token being
Feature activation+0.000
suspended
Token suspended
Feature activation+0.000
or
Token or
Feature activation+0.000
expelled
Token expelled
Feature activation+0.000
from
Token from
Feature activation+0.517
school
Token school
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Token a
Feature activation+0.000
student
Token student
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.173
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.427
Re
TokenRe
Feature activation+0.000
-
Token-
Feature activation+0.000
ex
Tokenex
Feature activation+0.000
amine
Tokenamine
Feature activation+0.000
the
Token the
Feature activation+0.000
t
Tokent
Feature activation+0.000
your
Token your
Feature activation+0.000
typical
Token typical
Feature activation+0.000
subject
Token subject
Feature activation+0.000
.
Token.
Feature activation+0.425
The
Token The
Feature activation+0.501
India
Token India
Feature activation+0.000
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.704
,
Token,
Feature activation+0.000
South
Token South
Feature activation+0.000
as
Tokenas
Feature activation+0.000
for
Token for
Feature activation+0.000
sale
Token sale
Feature activation+0.000
in
Token in
Feature activation+0.000
Italy
Token Italy
Feature activation+0.000
.
Token.
Feature activation+0.543
The
Token The
Feature activation+0.135
post
Token post
Feature activation+0.000
was
Token was
Feature activation+0.000
short
Token short
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.933
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.228
the
Token the
Feature activation+0.092
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.511
most
Token most
Feature activation+0.064
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
RN
Token RN
Feature activation+0.000
As
TokenAs
Feature activation+0.000

INTERVAL 0.213 - 0.425
CONTAINS 0.065%

Hear
Token Hear
Feature activation+0.000
n
Tokenn
Feature activation+0.000
testified
Token testified
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.276
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
Hear
Token Hear
Feature activation+0.000
n
Tokenn
Feature activation+0.000
,
Token,
Feature activation+0.000
calls
Token calls
Feature activation+0.000
from
Token from
Feature activation+0.000
God
Token God
Feature activation+0.000
.
Token.
Feature activation+0.000
Sometimes
Token Sometimes
Feature activation+0.000
these
Token these
Feature activation+0.278
calls
Token calls
Feature activation+0.000
are
Token are
Feature activation+0.000
subtle
Token subtle
Feature activation+0.000
in
Token in
Feature activation+0.000
nature
Token nature
Feature activation+0.000
do
Token do
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.290
:
Token:
Feature activation+0.000
38
Token38
Feature activation+0.000
those
Token those
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
of
Token of
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.279
a
Token a
Feature activation+0.059
new
Token new
Feature activation+0.000
sensor
Token sensor
Feature activation+0.000
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.222
supposed
Token supposed
Feature activation+0.207
to
Token to
Feature activation+0.509
be
Token be
Feature activation+0.294
when
Token when
Feature activation+0.000
we
Token we
Feature activation+0.000

INTERVAL 0.000 - 0.213
CONTAINS 99.886%

wise
Token wise
Feature activation+0.000
men
Token men
Feature activation+0.000
(
Token (
Feature activation+0.000
who
Tokenwho
Feature activation+0.000
surprisingly
Token surprisingly
Feature activation+0.000
weren
Token weren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
led
Token led
Feature activation+0.000
by
Token by
Feature activation+0.000
get
Token get
Feature activation+0.000
around
Token around
Feature activation+0.000
this
Token this
Feature activation+0.000
by
Token by
Feature activation+0.000
using
Token using
Feature activation+0.000
an
Token an
Feature activation+0.000
increment
Token increment
Feature activation+0.000
b
Token b
Feature activation+0.000
orer
Tokenorer
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
man
Token man
Feature activation+0.000
who
Token who
Feature activation+0.000
they
Token they
Feature activation+0.000
most
Token most
Feature activation+0.000
admire
Token admire
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
part
Token part
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.000
news
Token news
Feature activation+0.000
and
Token and
Feature activation+0.000
current
Token current
Feature activation+0.000
affairs
Token affairs
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
often
Token often
Feature activation+0.000
h
Tokenh
Feature activation+0.000
Des
Token Des
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
policy
Token policy
Feature activation+0.000
adviser
Token adviser
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H8.3: (feature 23600)

TOP ACTIVATIONS
MAX = 3.229

300
Token 300
Feature activation+0.000
million
Token million
Feature activation+0.000
people
Token people
Feature activation+0.035
,
Token,
Feature activation+0.066
who
Token who
Feature activation+0.060
use
Token use
Feature activation+3.229
its
Token its
Feature activation+0.856
photo
Token photo
Feature activation+0.000
app
Token app
Feature activation+0.226
every
Token every
Feature activation+0.000
month
Token month
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
micro
Token micro
Feature activation+1.937
blog
Tokenblog
Feature activation+0.621
ging
Tokenging
Feature activation+2.953
site
Token site
Feature activation+0.558
hit
Token hit
Feature activation+0.000
the
Token the
Feature activation+0.000
100
Token 100
Feature activation+0.000
million
Token million
Feature activation+0.000
%)
Token%)
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
total
Token total
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
on
Token on
Feature activation+2.268
Twitter
Token Twitter
Feature activation+0.006
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
."
Token."
Feature activation+0.000
the
Token the
Feature activation+0.065
selection
Token selection
Feature activation+0.000
of
Token of
Feature activation+0.389
potential
Token potential
Feature activation+0.000
matches
Token matches
Feature activation+0.000
on
Token on
Feature activation+2.262
OK
Token OK
Feature activation+0.130
C
TokenC
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
blame
Token blame
Feature activation+0.000
everything
Token everything
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
life
Token life
Feature activation+0.000
on
Token on
Feature activation+2.228
somebody
Token somebody
Feature activation+0.151
else
Token else
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
luck
Token luck
Feature activation+0.000
zones
Token zones
Feature activation+0.000
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.000
different
Token different
Feature activation+0.000
sites
Token sites
Feature activation+0.130
on
Token on
Feature activation+2.153
the
Token the
Feature activation+1.971
red
Token red
Feature activation+1.205
planet
Token planet
Feature activation+0.250
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
span
Token span
Feature activation+0.000
that
Token that
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+1.845
secretive
Token secretive
Feature activation+2.114
company
Token company
Feature activation+0.324
embarrassed
Token embarrassed
Feature activation+0.000
when
Token when
Feature activation+0.000
important
Token important
Feature activation+0.000
trade
Token trade
Feature activation+0.000
6
Token 6
Feature activation+0.000
32
Token32
Feature activation+0.000
people
Token people
Feature activation+0.000
had
Token had
Feature activation+0.000
died
Token died
Feature activation+0.386
from
Token from
Feature activation+2.024
the
Token the
Feature activation+1.451
illness
Token illness
Feature activation+0.000
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
July
Token July
Feature activation+0.000
authorization
Token authorization
Feature activation+0.000
for
Token for
Feature activation+0.000
military
Token military
Feature activation+0.000
action
Token action
Feature activation+0.067
against
Token against
Feature activation+1.711
the
Token the
Feature activation+2.007
terrorist
Token terrorist
Feature activation+1.369
group
Token group
Feature activation+0.854
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
large
Token large
Feature activation+0.000
segments
Token segments
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
faculty
Token faculty
Feature activation+0.000
at
Token at
Feature activation+1.961
Harvard
Token Harvard
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.388
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
micro
Token micro
Feature activation+1.937
blog
Tokenblog
Feature activation+0.621
ging
Tokenging
Feature activation+2.953
site
Token site
Feature activation+0.558
hit
Token hit
Feature activation+0.000
the
Token the
Feature activation+0.000
are
Token are
Feature activation+0.000
on
Token on
Feature activation+1.626
Facebook
Token Facebook
Feature activation+0.101
accessed
Token accessed
Feature activation+0.069
news
Token news
Feature activation+0.000
through
Token through
Feature activation+1.874
the
Token the
Feature activation+1.783
social
Token social
Feature activation+1.731
site
Token site
Feature activation+0.995
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
old
Token old
Feature activation+0.000
got
Token got
Feature activation+0.078
their
Token their
Feature activation+0.000
political
Token political
Feature activation+0.000
news
Token news
Feature activation+0.000
from
Token from
Feature activation+1.855
Facebook
Token Facebook
Feature activation+0.330
every
Token every
Feature activation+0.000
week
Token week
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
span
Token span
Feature activation+0.000
that
Token that
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+1.845
secretive
Token secretive
Feature activation+2.114
company
Token company
Feature activation+0.324
embarrassed
Token embarrassed
Feature activation+0.000
when
Token when
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.115
they
Token they
Feature activation+0.297
might
Token might
Feature activation+0.000
think
Token think
Feature activation+0.000
is
Token is
Feature activation+1.815
a
Token a
Feature activation+0.972
terrorist
Token terrorist
Feature activation+0.144
organisation
Token organisation
Feature activation+0.056
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
80
Token 80
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
posts
Token posts
Feature activation+0.000
on
Token on
Feature activation+0.824
the
Token the
Feature activation+1.812
platform
Token platform
Feature activation+0.000
from
Token from
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
to
Token to
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
on
Token on
Feature activation+1.626
Facebook
Token Facebook
Feature activation+0.101
accessed
Token accessed
Feature activation+0.069
news
Token news
Feature activation+0.000
through
Token through
Feature activation+1.874
the
Token the
Feature activation+1.783
social
Token social
Feature activation+1.731
site
Token site
Feature activation+0.995
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
se
Token se
Feature activation+0.000
ced
Tokenced
Feature activation+0.000
e
Tokene
Feature activation+0.741
from
Token from
Feature activation+1.774
my
Token my
Feature activation+0.647
previous
Token previous
Feature activation+0.000
statement
Token statement
Feature activation+0.000
on
Token on
Feature activation+0.000
Yahoo
Token Yahoo
Feature activation+0.000
of
Token of
Feature activation+0.000
Exxon
Token Exxon
Feature activation+0.000
Mobil
TokenMobil
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+0.000
whether
Token whether
Feature activation+1.744
Exxon
Token Exxon
Feature activation+0.000
Mobil
TokenMobil
Feature activation+0.000
hid
Token hid
Feature activation+0.000
risks
Token risks
Feature activation+0.000
of
Token of
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
calling
Token calling
Feature activation+1.731
us
Token us
Feature activation+0.000
today
Token today
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
an
Token an
Feature activation+0.000

Top DFA by src position
MAX = 3.410

period
Token period
Feature activation-0.008
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
nine
Token nine
Feature activation-0.002
Top resid features:
months
Token months
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Instagram
Token Instagram
Feature activation+3.410
Top resid features:
now
Token now
Feature activation+0.021
Top resid features:
has
Token has
Feature activation+0.016
Top resid features:
300
Token 300
Feature activation+0.032
Top resid features:
million
Token million
Feature activation+0.036
Top resid features:
people
Token people
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
At
TokenAt
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Twitter
Token Twitter
Feature activation+2.818
Top resid features:
had
Token had
Feature activation+0.053
Top resid features:
an
Token an
Feature activation+0.020
Top resid features:
estimated
Token estimated
Feature activation-0.006
Top resid features:
32
Token 32
Feature activation-0.000
Top resid features:
million
Token million
Feature activation-0.003
Top resid features:
million
Token million
Feature activation+0.008
Top resid features:
impressions
Token impressions
Feature activation+0.001
Top resid features:
."
Token."
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Twitter
TokenTwitter
Feature activation+2.679
Top resid features:
emphasized
Token emphasized
Feature activation-0.007
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
its
Token its
Feature activation-0.005
Top resid features:
prepared
Token prepared
Feature activation-0.007
Top resid features:
remarks
Token remarks
Feature activation-0.014
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
peril
Token peril
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
OK
Token OK
Feature activation+0.012
Top resid features:
C
TokenC
Feature activation+0.055
Top resid features:
upid
Tokenupid
Feature activation+2.548
Top resid features:
alone
Token alone
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Suff
Token Suff
Feature activation+0.000
Top resid features:
ice
Tokenice
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
97
Token97
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
000
Token000
Feature activation+0.001
Top resid features:
because
Token because
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Uber
Token Uber
Feature activation+2.271
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
âĢ
Token âĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
They
TokenThey
Feature activation+0.116
Top resid features:
blame
Token blame
Feature activation+0.015
Top resid features:
still
Token still
Feature activation+0.001
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
hard
Token hard
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
Mars
Token Mars
Feature activation+1.850
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
collecting
Token collecting
Feature activation+0.003
Top resid features:
data
Token data
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
sending
Token sending
Feature activation+0.001
Top resid features:
employees
Token employees
Feature activation+0.004
Top resid features:
imperson
Token imperson
Feature activation+0.001
Top resid features:
ated
Tokenated
Feature activation+0.003
Top resid features:
policemen
Token policemen
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Apple
Token Apple
Feature activation+0.881
Top resid features:
's
Token's
Feature activation+0.142
Top resid features:
chief
Token chief
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
security
Token security
Feature activation-0.006
Top resid features:
operations
Token operations
Feature activation-0.004
Top resid features:
no
Token no
Feature activation-0.001
Top resid features:
cure
Token cure
Feature activation+0.001
Top resid features:
or
Token or
Feature activation-0.001
Top resid features:
vaccine
Token vaccine
Feature activation-0.016
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
Ebola
Token Ebola
Feature activation+2.640
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
but
Token but
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
case
Token case
Feature activation-0.005
Top resid features:
fat
Token fat
Feature activation-0.003
Top resid features:
Paul
Token Paul
Feature activation-0.002
Top resid features:
declared
Token declared
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
war
Token war
Feature activation-0.004
Top resid features:
against
Token against
Feature activation-0.007
Top resid features:
ISIS
Token ISIS
Feature activation+2.720
Top resid features:
"
Token "
Feature activation+0.009
Top resid features:
illegal
Tokenillegal
Feature activation-0.003
Top resid features:
"
Token"
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
points
Token points
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
telling
Token telling
Feature activation+0.001
Top resid features:
Henry
Token Henry
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.003
Top resid features:
Harvard
Token Harvard
Feature activation+2.272
Top resid features:
professors
Token professors
Feature activation-0.006
Top resid features:
can
Token can
Feature activation-0.003
Top resid features:
benefit
Token benefit
Feature activation+0.002
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
At
TokenAt
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Twitter
Token Twitter
Feature activation+1.701
Top resid features:
had
Token had
Feature activation+0.035
Top resid features:
an
Token an
Feature activation+0.009
Top resid features:
estimated
Token estimated
Feature activation-0.004
Top resid features:
32
Token 32
Feature activation-0.000
Top resid features:
million
Token million
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.001
Top resid features:
The
TokenThe
Feature activation+0.002
Top resid features:
rise
Token rise
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
Facebook
Token Facebook
Feature activation+1.525
Top resid features:
as
Token as
Feature activation+0.067
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
news
Token news
Feature activation-0.002
Top resid features:
source
Token source
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
politics
Token politics
Feature activation-0.031
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
particularly
Token particularly
Feature activation-0.002
Top resid features:
important
Token important
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
Facebook
Token Facebook
Feature activation+1.122
Top resid features:
users
Token users
Feature activation+0.006
Top resid features:
-
Token -
Feature activation-0.005
Top resid features:
32
Token 32
Feature activation-0.002
Top resid features:
per
Token per
Feature activation-0.001
Top resid features:
cent
Token cent
Feature activation+0.001
Top resid features:
FBI
Token FBI
Feature activation-0.012
Top resid features:
agent
Token agent
Feature activation-0.007
Top resid features:
who
Token who
Feature activation-0.004
Top resid features:
came
Token came
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Apple
Token Apple
Feature activation+0.785
Top resid features:
from
Token from
Feature activation-0.003
Top resid features:
Pf
Token Pf
Feature activation+0.014
Top resid features:
izer
Tokenizer
Feature activation+0.029
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
2007
Token 2007
Feature activation-0.003
Top resid features:
because
Token because
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
association
Token association
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
Wikileaks
Token Wikileaks
Feature activation+1.796
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
who
Token who
Feature activation+0.032
Top resid features:
they
Token they
Feature activation+0.006
Top resid features:
might
Token might
Feature activation+0.012
Top resid features:
think
Token think
Feature activation+0.067
Top resid features:
million
Token million
Feature activation+0.001
Top resid features:
impressions
Token impressions
Feature activation+0.001
Top resid features:
."
Token."
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Twitter
TokenTwitter
Feature activation+0.975
Top resid features:
emphasized
Token emphasized
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
its
Token its
Feature activation-0.001
Top resid features:
prepared
Token prepared
Feature activation-0.005
Top resid features:
remarks
Token remarks
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
rise
Token rise
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
Facebook
Token Facebook
Feature activation+1.212
Top resid features:
as
Token as
Feature activation+0.098
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
news
Token news
Feature activation-0.003
Top resid features:
source
Token source
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
claimed
Token claimed
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
Yahoo
Token Yahoo
Feature activation+1.775
Top resid features:
!
Token!
Feature activation+0.197
Top resid features:
buy
Token buy
Feature activation+0.002
Top resid features:
out
Tokenout
Feature activation+0.022
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
unlikely
Token unlikely
Feature activation-0.000
Top resid features:
launched
Token launched
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
sweeping
Token sweeping
Feature activation+0.012
Top resid features:
probe
Token probe
Feature activation-0.012
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
Exxon
Token Exxon
Feature activation+1.781
Top resid features:
Mobil
TokenMobil
Feature activation+0.423
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
determine
Token determine
Feature activation+0.025
Top resid features:
whether
Token whether
Feature activation+0.005
Top resid features:
Exxon
Token Exxon
Feature activation+0.000
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.003
Top resid features:
aware
Token aware
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
Planned
Token Planned
Feature activation+0.355
Top resid features:
Parenthood
Token Parenthood
Feature activation+1.246
Top resid features:
provides
Token provides
Feature activation+0.323
Top resid features:
breast
Token breast
Feature activation-0.003
Top resid features:
exams
Token exams
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.04

Head 3: 0.48

Head 4: 0.03

Head 5: 0.06

Head 6: 0.02

Head 7: 0.06

Head 8: 0.05

Head 9: 0.06

Head 10: 0.09

Head 11: 0.08

Positive logits

quartered2.61

Genius2.26

company2.26

wonder2.26

2.20

2.13

porting2.12

PLIED2.12

forcement2.11

2.08

antly2.06

ーティ2.05

ゴン2.04

organisation2.02

ionics1.99

1.98

embattled1.98

Already1.96

®1.95

endment1.94

Negative logits

aterasu-2.21

Isa-2.21

ombo-2.19

Leia-2.18

Qin-2.18

Zhou-2.13

obyl-2.09

Angola-2.04

Vegeta-2.03

Homer-2.03

Xu-1.98

Laos-1.97

Krishna-1.97

Gohan-1.95

Pyrrha-1.95

Jiang-1.95

arre-1.94

uto-1.93

insk-1.92

Sims-1.91

INTERVAL 2.906 - 3.229
CONTAINS 0.000%

300
Token 300
Feature activation+0.000
million
Token million
Feature activation+0.000
people
Token people
Feature activation+0.035
,
Token,
Feature activation+0.066
who
Token who
Feature activation+0.060
use
Token use
Feature activation+3.229
its
Token its
Feature activation+0.856
photo
Token photo
Feature activation+0.000
app
Token app
Feature activation+0.226
every
Token every
Feature activation+0.000
month
Token month
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
micro
Token micro
Feature activation+1.937
blog
Tokenblog
Feature activation+0.621
ging
Tokenging
Feature activation+2.953
site
Token site
Feature activation+0.558
hit
Token hit
Feature activation+0.000
the
Token the
Feature activation+0.000
100
Token 100
Feature activation+0.000
million
Token million
Feature activation+0.000

INTERVAL 2.584 - 2.906
CONTAINS 0.000%

INTERVAL 2.261 - 2.584
CONTAINS 0.000%

the
Token the
Feature activation+0.065
selection
Token selection
Feature activation+0.000
of
Token of
Feature activation+0.389
potential
Token potential
Feature activation+0.000
matches
Token matches
Feature activation+0.000
on
Token on
Feature activation+2.262
OK
Token OK
Feature activation+0.130
C
TokenC
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
%)
Token%)
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
total
Token total
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
on
Token on
Feature activation+2.268
Twitter
Token Twitter
Feature activation+0.006
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
."
Token."
Feature activation+0.000

INTERVAL 1.938 - 2.261
CONTAINS 0.001%

large
Token large
Feature activation+0.000
segments
Token segments
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
faculty
Token faculty
Feature activation+0.000
at
Token at
Feature activation+1.961
Harvard
Token Harvard
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.388
authorization
Token authorization
Feature activation+0.000
for
Token for
Feature activation+0.000
military
Token military
Feature activation+0.000
action
Token action
Feature activation+0.067
against
Token against
Feature activation+1.711
the
Token the
Feature activation+2.007
terrorist
Token terrorist
Feature activation+1.369
group
Token group
Feature activation+0.854
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
zones
Token zones
Feature activation+0.000
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.000
different
Token different
Feature activation+0.000
sites
Token sites
Feature activation+0.130
on
Token on
Feature activation+2.153
the
Token the
Feature activation+1.971
red
Token red
Feature activation+1.205
planet
Token planet
Feature activation+0.250
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
6
Token 6
Feature activation+0.000
32
Token32
Feature activation+0.000
people
Token people
Feature activation+0.000
had
Token had
Feature activation+0.000
died
Token died
Feature activation+0.386
from
Token from
Feature activation+2.024
the
Token the
Feature activation+1.451
illness
Token illness
Feature activation+0.000
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
July
Token July
Feature activation+0.000
a
Token a
Feature activation+0.000
span
Token span
Feature activation+0.000
that
Token that
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+1.845
secretive
Token secretive
Feature activation+2.114
company
Token company
Feature activation+0.324
embarrassed
Token embarrassed
Feature activation+0.000
when
Token when
Feature activation+0.000
important
Token important
Feature activation+0.000
trade
Token trade
Feature activation+0.000

INTERVAL 1.615 - 1.938
CONTAINS 0.002%

announcement
Token announcement
Feature activation+0.000
says
Token says
Feature activation+0.000
only
Token only
Feature activation+0.000
that
Token that
Feature activation+0.068
the
Token the
Feature activation+0.302
two
Token two
Feature activation+1.726
cameras
Token cameras
Feature activation+0.000
have
Token have
Feature activation+0.000
"
Token "
Feature activation+0.000
Le
TokenLe
Feature activation+0.000
ica
Tokenica
Feature activation+0.000
as
Token as
Feature activation+0.000
Luc
Token Luc
Feature activation+0.000
key
Tokenkey
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.335
with
Token with
Feature activation+1.724
the
Token the
Feature activation+1.283
company
Token company
Feature activation+0.532
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
span
Token span
Feature activation+0.000
that
Token that
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+1.845
secretive
Token secretive
Feature activation+2.114
company
Token company
Feature activation+0.324
embarrassed
Token embarrassed
Feature activation+0.000
when
Token when
Feature activation+0.000
important
Token important
Feature activation+0.000
had
Token had
Feature activation+0.000
recommended
Token recommended
Feature activation+0.000
that
Token that
Feature activation+0.588
users
Token users
Feature activation+0.242
stop
Token stop
Feature activation+0.997
using
Token using
Feature activation+1.716
Firefox
Token Firefox
Feature activation+0.169
until
Token until
Feature activation+0.300
the
Token the
Feature activation+0.000
tested
Token tested
Feature activation+0.463
fix
Token fix
Feature activation+0.000
are
Token are
Feature activation+0.000
on
Token on
Feature activation+1.626
Facebook
Token Facebook
Feature activation+0.101
accessed
Token accessed
Feature activation+0.069
news
Token news
Feature activation+0.000
through
Token through
Feature activation+1.874
the
Token the
Feature activation+1.783
social
Token social
Feature activation+1.731
site
Token site
Feature activation+0.995
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.000

INTERVAL 1.292 - 1.615
CONTAINS 0.003%

another
Token another
Feature activation+0.000
copy
Token copy
Feature activation+0.000
cat
Tokencat
Feature activation+0.000
job
Token job
Feature activation+0.000
by
Token by
Feature activation+1.162
the
Token the
Feature activation+1.379
makers
Token makers
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Galaxy
Token Galaxy
Feature activation+0.000
line
Token line
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
usage
Token usage
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
users
Token users
Feature activation+0.000
,
Token,
Feature activation+1.591
Google
Token Google
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
this
Token this
Feature activation+0.000
data
Token data
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
saw
Token saw
Feature activation+0.000
two
Token two
Feature activation+0.000
posts
Token posts
Feature activation+0.000
on
Token on
Feature activation+1.376
my
Token my
Feature activation+0.703
Facebook
Token Facebook
Feature activation+0.000
feed
Token feed
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
million
Token million
Feature activation+0.000
in
Token in
Feature activation+0.000
tax
Token tax
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+1.509
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
commerce
Tokencommerce
Feature activation+1.536
giant
Token giant
Feature activation+0.085
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
represent
Token represent
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.262
died
Token died
Feature activation+1.337
in
Token in
Feature activation+0.327
the
Token the
Feature activation+0.572
terrorist
Token terrorist
Feature activation+0.073
attacks
Token attacks
Feature activation+0.083
.
Token.
Feature activation+0.000

INTERVAL 0.969 - 1.292
CONTAINS 0.008%

opening
Token opening
Feature activation+0.000
trio
Token trio
Feature activation+0.000
of
Token of
Feature activation+0.000
missions
Token missions
Feature activation+0.000
for
Token for
Feature activation+1.214
the
Token the
Feature activation+1.073
first
Token first
Feature activation+0.868
time
Token time
Feature activation+0.280
alongside
Token alongside
Feature activation+0.000
the
Token the
Feature activation+0.000
gaming
Token gaming
Feature activation+0.016
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
purposes
Token purposes
Feature activation+0.000
of
Token of
Feature activation+0.730
the
Token the
Feature activation+1.114
public
Token public
Feature activation+0.000
broadcaster
Token broadcaster
Feature activation+0.000
,
Token,
Feature activation+0.000
guarantees
Token guarantees
Feature activation+0.000
its
Token its
Feature activation+0.000
former
Token former
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
agent
Token agent
Feature activation+0.000
who
Token who
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.988
Apple
Token Apple
Feature activation+0.000
from
Token from
Feature activation+0.000
Pf
Token Pf
Feature activation+0.000
izer
Tokenizer
Feature activation+0.000
in
Token in
Feature activation+0.000
48
Token 48
Feature activation+0.184
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.675
people
Token people
Feature activation+0.021
suffering
Token suffering
Feature activation+0.829
from
Token from
Feature activation+1.051
this
Token this
Feature activation+0.976
disease
Token disease
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+0.000
6
Token 6
Feature activation+0.000
22
Token 22
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
veteran
Token veteran
Feature activation+0.481
of
Token of
Feature activation+0.689
the
Token the
Feature activation+1.074
search
Token search
Feature activation+0.598
field
Token field
Feature activation+0.259
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000

INTERVAL 0.646 - 0.969
CONTAINS 0.024%

Martin
Token Martin
Feature activation+0.000
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
given
Token given
Feature activation+0.039
the
Token the
Feature activation+0.000
contract
Token contract
Feature activation+0.648
to
Token to
Feature activation+0.000
oversee
Token oversee
Feature activation+0.000
the
Token the
Feature activation+0.000
census
Token census
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
in
Token in
Feature activation+0.227
the
Token the
Feature activation+0.142
Florida
Token Florida
Feature activation+0.000
town
Token town
Feature activation+0.000
where
Token where
Feature activation+0.778
the
Token the
Feature activation+0.910
17
Token 17
Feature activation+0.074
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.219
hands
Token hands
Feature activation+0.000
and
Token and
Feature activation+0.000
planted
Token planted
Feature activation+0.000
a
Token a
Feature activation+0.000
message
Token message
Feature activation+0.000
on
Token on
Feature activation+0.824
CEO
Token CEO
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Zuckerberg
Token Zuckerberg
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
planning
Token planning
Feature activation+0.000
on
Token on
Feature activation+0.000
visiting
Token visiting
Feature activation+0.857
either
Token either
Feature activation+0.641
amusement
Token amusement
Feature activation+0.000
park
Token park
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
encouraging
Token encouraging
Feature activation+0.000
.
Token.
Feature activation+0.342
The
Token The
Feature activation+0.762
App
Token App
Feature activation+0.000
Store
Token Store
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
indis
Token indis
Feature activation+0.000

INTERVAL 0.323 - 0.646
CONTAINS 0.075%

feelings
Token feelings
Feature activation+0.000
are
Token are
Feature activation+0.000
:
Token:
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
for
Token for
Feature activation+0.497
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Apprentice
Token Apprentice
Feature activation+0.000
boss
Token boss
Feature activation+0.000
,
Token,
Feature activation+0.342
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.027
L
TokenL
Feature activation+0.000
standard
Token standard
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
online
Token online
Feature activation+0.000
streaming
Token streaming
Feature activation+0.045
giant
Token giant
Feature activation+0.514
's
Token's
Feature activation+0.000
end
Token end
Feature activation+0.000
game
Tokengame
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
budding
Token budding
Feature activation+0.000
trainers
Token trainers
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
hitting
Token hitting
Feature activation+0.166
the
Token the
Feature activation+0.363
streets
Token streets
Feature activation+0.000
looking
Token looking
Feature activation+0.030
for
Token for
Feature activation+0.422
wild
Token wild
Feature activation+0.207
Pokémon
Token Pokémon
Feature activation+0.000
The
TokenThe
Feature activation+0.000
rise
Token rise
Feature activation+0.000
of
Token of
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
as
Token as
Feature activation+0.319
a
Token a
Feature activation+0.556
news
Token news
Feature activation+0.000
source
Token source
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.213
News
TokenNews
Feature activation+0.000

INTERVAL 0.000 - 0.323
CONTAINS 99.886%

last
Token last
Feature activation+0.000
five
Token five
Feature activation+0.000
months
Token months
Feature activation+0.000
of
Token of
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
period
Token period
Feature activation+0.000
that
Token that
Feature activation+0.000
Orn
Token Orn
Feature activation+0.000
stein
Tokenstein
Feature activation+0.000
tell
Token tell
Feature activation+0.000
of
Token of
Feature activation+0.000
physical
Token physical
Feature activation+0.000
and
Token and
Feature activation+0.000
verbal
Token verbal
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
destructive
Token destructive
Feature activation+0.000
toll
Token toll
Feature activation+0.000
taken
Token taken
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
-
Token-
Feature activation+0.000
w
Tokenw
Feature activation+0.000
anted
Tokenanted
Feature activation+0.000
list
Token list
Feature activation+0.000
by
Token by
Feature activation+0.000
Skyrim
Token Skyrim
Feature activation+0.000
owners
Token owners
Feature activation+0.000
because
Token because
Feature activation+0.000
or
Token or
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
house
Token house
Feature activation+0.000
cat
Token cat
Feature activation+0.000
?
Token?
Feature activation+0.000
View
Token View
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.000
report
Token report
Feature activation+0.000
lock
Token lock
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
patiently
Token patiently
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
girls
Token girls
Feature activation+0.000
laced
Token laced
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H8.3: (feature 5584)

TOP ACTIVATIONS
MAX = 3.691

key
Token key
Feature activation+0.000
activists
Token activists
Feature activation+0.000
and
Token and
Feature activation+0.000
consultants
Token consultants
Feature activation+0.000
in
Token in
Feature activation+0.913
those
Token those
Feature activation+3.691
crucial
Token crucial
Feature activation+0.322
states
Token states
Feature activation+0.000
as
Token as
Feature activation+0.000
others
Token others
Feature activation+0.000
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
and
Token and
Feature activation+0.518
claimed
Token claimed
Feature activation+0.000
by
Token by
Feature activation+1.096
both
Token both
Feature activation+3.547
.
Token.
Feature activation+0.671
The
Token The
Feature activation+0.751
two
Token two
Feature activation+3.496
countries
Token countries
Feature activation+0.005
fought
Token fought
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
by
Token by
Feature activation+1.096
both
Token both
Feature activation+3.547
.
Token.
Feature activation+0.671
The
Token The
Feature activation+0.751
two
Token two
Feature activation+3.496
countries
Token countries
Feature activation+0.005
fought
Token fought
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
with
Token with
Feature activation+1.271
political
Token political
Feature activation+0.000
and
Token and
Feature activation+0.000
executive
Token executive
Feature activation+0.000
leaders
Token leaders
Feature activation+0.929
of
Token of
Feature activation+3.346
Ethiopia
Token Ethiopia
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
He
Token He
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
acial
Tokenacial
Feature activation+0.000
people
Token people
Feature activation+0.133
interviewed
Token interviewed
Feature activation+0.000
in
Token in
Feature activation+0.282
those
Token those
Feature activation+3.087
states
Token states
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
strain
Token strain
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
health
Token health
Feature activation+0.000
systems
Token systems
Feature activation+1.236
of
Token of
Feature activation+3.059
some
Token some
Feature activation+0.802
of
Token of
Feature activation+0.419
Africa
Token Africa
Feature activation+0.000
's
Token's
Feature activation+0.000
poorest
Token poorest
Feature activation+0.000
or
Token or
Feature activation+1.223
15
Token 15
Feature activation+0.000
20
Token20
Feature activation+0.000
,
Token,
Feature activation+0.010
however
Token however
Feature activation+0.051
in
Token in
Feature activation+3.047
the
Token the
Feature activation+1.658
US
Token US
Feature activation+0.000
the
Token the
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
is
Token is
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
two
Token two
Feature activation+2.945
countries
Token countries
Feature activation+0.000
will
Token will
Feature activation+0.000
formally
Token formally
Feature activation+0.000
move
Token move
Feature activation+0.000
a
Token a
Feature activation+0.000
teams
Token teams
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+1.070
All
Token All
Feature activation+2.705
of
Token of
Feature activation+1.451
these
Token these
Feature activation+1.758
teams
Token teams
Feature activation+0.000
caused
Token caused
Feature activation+0.000
prices
Token prices
Feature activation+0.000
Fi
TokenFi
Feature activation+0.000
calling
Token calling
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.218
Sprint
Token Sprint
Feature activation+0.000
and
Token and
Feature activation+2.632
T
Token T
Feature activation+0.000
-
Token-
Feature activation+0.000
Mobile
TokenMobile
Feature activation+0.000
have
Token have
Feature activation+0.000
done
Token done
Feature activation+0.000
Thai
Token Thai
Feature activation+0.000
auto
Token auto
Feature activation+0.000
subsidies
Token subsidies
Feature activation+0.000
have
Token have
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
from
Token from
Feature activation+2.473
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
globe
Token globe
Feature activation+0.000
scrambling
Token scrambling
Feature activation+0.000
to
Token to
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+2.469
are
Token are
Feature activation+0.530
serious
Token serious
Feature activation+0.000
substances
Token substances
Feature activation+0.000
.
Token.
Feature activation+0.409
According
Token According
Feature activation+0.000
Brazil
Token Brazil
Feature activation+0.000
and
Token and
Feature activation+0.000
into
Token into
Feature activation+0.000
sixth
Token sixth
Feature activation+0.000
place
Token place
Feature activation+0.154
behind
Token behind
Feature activation+2.460
the
Token the
Feature activation+0.216
United
Token United
Feature activation+0.000
Kingdom
Token Kingdom
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
late
Token late
Feature activation+0.000
December
Token December
Feature activation+0.000
and
Token and
Feature activation+0.000
early
Token early
Feature activation+0.000
January
Token January
Feature activation+0.181
both
Token both
Feature activation+2.457
had
Token had
Feature activation+0.000
stretches
Token stretches
Feature activation+0.000
that
Token that
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
adding
Token adding
Feature activation+1.326
gran
Token gran
Feature activation+0.000
ulated
Tokenulated
Feature activation+0.257
products
Token products
Feature activation+0.226
made
Token made
Feature activation+0.200
from
Token from
Feature activation+2.303
al
Token al
Feature activation+0.000
f
Tokenf
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
a
Tokena
Feature activation+0.625
and
Token and
Feature activation+1.737
built
Token built
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
strengths
Token strengths
Feature activation+0.000
of
Token of
Feature activation+0.788
each
Token each
Feature activation+2.302
country
Token country
Feature activation+0.000
,
Token,
Feature activation+0.000
contributing
Token contributing
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
f
Tokenf
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
a
Tokena
Feature activation+0.625
and
Token and
Feature activation+1.737
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+2.268
cotton
Token cotton
Feature activation+0.450
seed
Tokenseed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
soil
Token soil
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
says
Token says
Feature activation+0.000
only
Token only
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+2.251
cameras
Token cameras
Feature activation+0.000
have
Token have
Feature activation+0.000
"
Token "
Feature activation+0.000
Le
TokenLe
Feature activation+0.000
ica
Tokenica
Feature activation+0.000
as
Token as
Feature activation+0.562
the
Token the
Feature activation+0.969
leaders
Token leaders
Feature activation+0.349
of
Token of
Feature activation+0.915
the
Token the
Feature activation+0.685
two
Token two
Feature activation+2.244
countries
Token countries
Feature activation+0.000
met
Token met
Feature activation+0.000
for
Token for
Feature activation+0.000
talks
Token talks
Feature activation+0.000
in
Token in
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.038
back
Token back
Feature activation+0.000
to
Token to
Feature activation+2.129
the
Token the
Feature activation+0.322
city
Token city
Feature activation+0.447
after
Token after
Feature activation+0.000
they
Token they
Feature activation+0.000
moved
Token moved
Feature activation+0.000

Top DFA by src position
MAX = 4.201

states
Token states
Feature activation+0.139
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
Iowa
Token Iowa
Feature activation+0.056
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
South
Token South
Feature activation+0.120
Top resid features:
Carolina
Token Carolina
Feature activation+3.760
Top resid features:
last
Token last
Feature activation+0.005
Top resid features:
year
Token year
Feature activation+0.003
Top resid features:
during
Token during
Feature activation-0.001
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
book
Token book
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
divided
Token divided
Feature activation-0.002
Top resid features:
between
Token between
Feature activation-0.013
Top resid features:
India
Token India
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
Pakistan
Token Pakistan
Feature activation+4.201
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
claimed
Token claimed
Feature activation-0.035
Top resid features:
by
Token by
Feature activation+0.015
Top resid features:
both
Token both
Feature activation-0.067
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
divided
Token divided
Feature activation-0.008
Top resid features:
between
Token between
Feature activation-0.027
Top resid features:
India
Token India
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
Pakistan
Token Pakistan
Feature activation+4.180
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
claimed
Token claimed
Feature activation+0.006
Top resid features:
by
Token by
Feature activation-0.007
Top resid features:
both
Token both
Feature activation-0.043
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
liaison
Token liaison
Feature activation+0.002
Top resid features:
between
Token between
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Egyptian
Token Egyptian
Feature activation-0.010
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
Ethiopian
Token Ethiopian
Feature activation+3.588
Top resid features:
churches
Token churches
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+0.007
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
South
Token South
Feature activation+0.029
Top resid features:
Dakota
Token Dakota
Feature activation+0.285
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
Vermont
Token Vermont
Feature activation+0.109
Top resid features:
and
Token and
Feature activation+0.142
Top resid features:
Wyoming
Token Wyoming
Feature activation+1.999
Top resid features:
were
Token were
Feature activation+0.305
Top resid features:
not
Token not
Feature activation+0.009
Top resid features:
analyzed
Token analyzed
Feature activation+0.018
Top resid features:
due
Token due
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
Guinea
Token Guinea
Feature activation+0.227
Top resid features:
,
Token,
Feature activation+0.053
Top resid features:
Liberia
Token Liberia
Feature activation+0.474
Top resid features:
and
Token and
Feature activation+0.142
Top resid features:
Sierra
Token Sierra
Feature activation+0.106
Top resid features:
Leone
Token Leone
Feature activation+2.487
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
according
Token according
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
data
Token data
Feature activation+0.001
Top resid features:
from
Token from
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
In
Token In
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.030
Top resid features:
UK
Token UK
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
Australia
Token Australia
Feature activation+3.344
Top resid features:
,
Token,
Feature activation+0.163
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
promotion
Token promotion
Feature activation+0.005
Top resid features:
extends
Token extends
Feature activation+0.005
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
record
Token record
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
India
Token India
Feature activation-0.009
Top resid features:
and
Token and
Feature activation+0.072
Top resid features:
China
Token China
Feature activation+3.254
Top resid features:
will
Token will
Feature activation+0.201
Top resid features:
negotiate
Token negotiate
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
treaty
Token treaty
Feature activation-0.030
Top resid features:
Pittsburgh
Token Pittsburgh
Feature activation+0.056
Top resid features:
Steelers
Token Steelers
Feature activation+0.181
Top resid features:
and
Token and
Feature activation+0.896
Top resid features:
New
Token New
Feature activation+0.047
Top resid features:
England
Token England
Feature activation+0.035
Top resid features:
Patriots
Token Patriots
Feature activation+1.570
Top resid features:
were
Token were
Feature activation+0.288
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
top
Token top
Feature activation+0.012
Top resid features:
three
Token three
Feature activation-0.054
Top resid features:
teams
Token teams
Feature activation+0.050
Top resid features:
Sprint
Token Sprint
Feature activation+0.440
Top resid features:
,
Token,
Feature activation+0.300
Top resid features:
and
Token and
Feature activation+0.443
Top resid features:
T
Token T
Feature activation+0.218
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Mobile
TokenMobile
Feature activation+1.625
Top resid features:
have
Token have
Feature activation+0.149
Top resid features:
all
Token all
Feature activation+0.051
Top resid features:
already
Token already
Feature activation+0.018
Top resid features:
implemented
Token implemented
Feature activation+0.004
Top resid features:
Wi
Token Wi
Feature activation-0.000
Top resid features:
Southeast
Token Southeast
Feature activation-0.014
Top resid features:
Asia
Token Asia
Feature activation+0.036
Top resid features:
means
Token means
Feature activation-0.017
Top resid features:
Indonesia
Token Indonesia
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.064
Top resid features:
Thailand
Token Thailand
Feature activation+2.818
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Imp
TokenImp
Feature activation+0.002
Top resid features:
ending
Tokenending
Feature activation+0.015
Top resid features:
one
Tokenone
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.142
Top resid features:
Tr
Token Tr
Feature activation+0.045
Top resid features:
am
Tokenam
Feature activation+0.108
Top resid features:
ad
Tokenad
Feature activation+0.018
Top resid features:
ol
Tokenol
Feature activation+2.268
Top resid features:
".
Token".
Feature activation+0.390
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
These
TokenThese
Feature activation+0.027
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
rankings
Token rankings
Feature activation+0.009
Top resid features:
ahead
Token ahead
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
France
Token France
Feature activation+0.247
Top resid features:
and
Token and
Feature activation+0.126
Top resid features:
Brazil
Token Brazil
Feature activation+1.935
Top resid features:
and
Token and
Feature activation+0.118
Top resid features:
into
Token into
Feature activation+0.003
Top resid features:
sixth
Token sixth
Feature activation+0.011
Top resid features:
place
Token place
Feature activation+0.031
Top resid features:
behind
Token behind
Feature activation+0.087
Top resid features:
were
Token were
Feature activation-0.003
Top resid features:
expected
Token expected
Feature activation+0.004
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
Louisville
Token Louisville
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.714
Top resid features:
Wisconsin
Token Wisconsin
Feature activation+1.702
Top resid features:
this
Token this
Feature activation+0.006
Top resid features:
season
Token season
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
but
Token but
Feature activation+0.009
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
Alf
Token Alf
Feature activation-0.006
Top resid features:
alf
Tokenalf
Feature activation-0.000
Top resid features:
a
Tokena
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
Cotton
Token Cotton
Feature activation+1.061
Top resid features:
seed
Tokenseed
Feature activation+1.712
Top resid features:
Meal
Token Meal
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
To
TokenTo
Feature activation+0.001
Top resid features:
correct
Token correct
Feature activation+0.003
Top resid features:
25
Token 25
Feature activation-0.001
Top resid features:
years
Token years
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
India
Token India
Feature activation+0.031
Top resid features:
and
Token and
Feature activation+0.050
Top resid features:
Israel
Token Israel
Feature activation+2.200
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.117
Top resid features:
growing
Token growing
Feature activation-0.007
Top resid features:
partnership
Token partnership
Feature activation-0.021
Top resid features:
Alf
Token Alf
Feature activation-0.009
Top resid features:
alf
Tokenalf
Feature activation+0.002
Top resid features:
a
Tokena
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
Cotton
Token Cotton
Feature activation+1.295
Top resid features:
seed
Tokenseed
Feature activation+1.433
Top resid features:
Meal
Token Meal
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
To
TokenTo
Feature activation+0.001
Top resid features:
correct
Token correct
Feature activation+0.000
Top resid features:
exact
Token exact
Feature activation+0.002
Top resid features:
details
Token details
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Leica
Token Leica
Feature activation+0.023
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
Huawei
Token Huawei
Feature activation+2.587
Top resid features:
's
Token's
Feature activation+0.084
Top resid features:
partnership
Token partnership
Feature activation-0.026
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
camera
Token camera
Feature activation-0.012
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.148
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
China
TokenChina
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
US
Token US
Feature activation+2.335
Top resid features:
have
Token have
Feature activation+0.405
Top resid features:
unveiled
Token unveiled
Feature activation+0.011
Top resid features:
new
Token new
Feature activation+0.004
Top resid features:
pledges
Token pledges
Feature activation-0.000
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
both
Token both
Feature activation+0.010
Top resid features:
Montreal
Token Montreal
Feature activation+0.171
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
Mexico
Token Mexico
Feature activation+0.289
Top resid features:
City
Token City
Feature activation+1.883
Top resid features:
are
Token are
Feature activation+0.086
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
sights
Token sights
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.03

Head 3: 0.47

Head 4: 0.02

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.05

Head 9: 0.11

Head 10: 0.10

Head 11: 0.05

Positive logits

latter5.06

Both4.99

Both4.74

respectively4.49

both4.28

both4.13

These3.96

these3.88

these3.85

Neither3.71

respective3.66

These3.59

Neither3.56

whichever3.56

them3.55

OTH3.52

neither3.28

pair3.15

THESE3.12

THEM3.06

Negative logits

ermanent-2.23

onal-1.95

eli-1.95

legate-1.93

lvl-1.88

bits-1.87

bag-1.83

onse-1.81

trailer-1.81

aval-1.79

herd-1.77

hemer-1.77

queue-1.76

desc-1.75

jac-1.75

coli-1.73

-1.73

URI-1.72

murm-1.72

iHUD-1.71

INTERVAL 3.322 - 3.691
CONTAINS 0.000%

with
Token with
Feature activation+1.271
political
Token political
Feature activation+0.000
and
Token and
Feature activation+0.000
executive
Token executive
Feature activation+0.000
leaders
Token leaders
Feature activation+0.929
of
Token of
Feature activation+3.346
Ethiopia
Token Ethiopia
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
He
Token He
Feature activation+0.000
and
Token and
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
and
Token and
Feature activation+0.518
claimed
Token claimed
Feature activation+0.000
by
Token by
Feature activation+1.096
both
Token both
Feature activation+3.547
.
Token.
Feature activation+0.671
The
Token The
Feature activation+0.751
two
Token two
Feature activation+3.496
countries
Token countries
Feature activation+0.005
fought
Token fought
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
by
Token by
Feature activation+1.096
both
Token both
Feature activation+3.547
.
Token.
Feature activation+0.671
The
Token The
Feature activation+0.751
two
Token two
Feature activation+3.496
countries
Token countries
Feature activation+0.005
fought
Token fought
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
key
Token key
Feature activation+0.000
activists
Token activists
Feature activation+0.000
and
Token and
Feature activation+0.000
consultants
Token consultants
Feature activation+0.000
in
Token in
Feature activation+0.913
those
Token those
Feature activation+3.691
crucial
Token crucial
Feature activation+0.322
states
Token states
Feature activation+0.000
as
Token as
Feature activation+0.000
others
Token others
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 2.953 - 3.322
CONTAINS 0.000%

or
Token or
Feature activation+1.223
15
Token 15
Feature activation+0.000
20
Token20
Feature activation+0.000
,
Token,
Feature activation+0.010
however
Token however
Feature activation+0.051
in
Token in
Feature activation+3.047
the
Token the
Feature activation+1.658
US
Token US
Feature activation+0.000
the
Token the
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
is
Token is
Feature activation+0.000
strain
Token strain
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
health
Token health
Feature activation+0.000
systems
Token systems
Feature activation+1.236
of
Token of
Feature activation+3.059
some
Token some
Feature activation+0.802
of
Token of
Feature activation+0.419
Africa
Token Africa
Feature activation+0.000
's
Token's
Feature activation+0.000
poorest
Token poorest
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
acial
Tokenacial
Feature activation+0.000
people
Token people
Feature activation+0.133
interviewed
Token interviewed
Feature activation+0.000
in
Token in
Feature activation+0.282
those
Token those
Feature activation+3.087
states
Token states
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000

INTERVAL 2.584 - 2.953
CONTAINS 0.000%

Fi
TokenFi
Feature activation+0.000
calling
Token calling
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.218
Sprint
Token Sprint
Feature activation+0.000
and
Token and
Feature activation+2.632
T
Token T
Feature activation+0.000
-
Token-
Feature activation+0.000
Mobile
TokenMobile
Feature activation+0.000
have
Token have
Feature activation+0.000
done
Token done
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
two
Token two
Feature activation+2.945
countries
Token countries
Feature activation+0.000
will
Token will
Feature activation+0.000
formally
Token formally
Feature activation+0.000
move
Token move
Feature activation+0.000
a
Token a
Feature activation+0.000
teams
Token teams
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+1.070
All
Token All
Feature activation+2.705
of
Token of
Feature activation+1.451
these
Token these
Feature activation+1.758
teams
Token teams
Feature activation+0.000
caused
Token caused
Feature activation+0.000
prices
Token prices
Feature activation+0.000

INTERVAL 2.215 - 2.584
CONTAINS 0.001%

adding
Token adding
Feature activation+1.326
gran
Token gran
Feature activation+0.000
ulated
Tokenulated
Feature activation+0.257
products
Token products
Feature activation+0.226
made
Token made
Feature activation+0.200
from
Token from
Feature activation+2.303
al
Token al
Feature activation+0.000
f
Tokenf
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
a
Tokena
Feature activation+0.625
and
Token and
Feature activation+1.737
late
Token late
Feature activation+0.000
December
Token December
Feature activation+0.000
and
Token and
Feature activation+0.000
early
Token early
Feature activation+0.000
January
Token January
Feature activation+0.181
both
Token both
Feature activation+2.457
had
Token had
Feature activation+0.000
stretches
Token stretches
Feature activation+0.000
that
Token that
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
f
Tokenf
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
a
Tokena
Feature activation+0.625
and
Token and
Feature activation+1.737
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+2.268
cotton
Token cotton
Feature activation+0.450
seed
Tokenseed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
soil
Token soil
Feature activation+0.000
as
Token as
Feature activation+0.562
the
Token the
Feature activation+0.969
leaders
Token leaders
Feature activation+0.349
of
Token of
Feature activation+0.915
the
Token the
Feature activation+0.685
two
Token two
Feature activation+2.244
countries
Token countries
Feature activation+0.000
met
Token met
Feature activation+0.000
for
Token for
Feature activation+0.000
talks
Token talks
Feature activation+0.000
in
Token in
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
says
Token says
Feature activation+0.000
only
Token only
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+2.251
cameras
Token cameras
Feature activation+0.000
have
Token have
Feature activation+0.000
"
Token "
Feature activation+0.000
Le
TokenLe
Feature activation+0.000
ica
Tokenica
Feature activation+0.000

INTERVAL 1.846 - 2.215
CONTAINS 0.002%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
ring
Token ring
Feature activation+0.000
,
Token,
Feature activation+1.559
nor
Token nor
Feature activation+0.017
are
Token are
Feature activation+2.121
they
Token they
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.131
of
Token of
Feature activation+0.000
spaces
Token spaces
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
ones
Token ones
Feature activation+0.000
),
Token),
Feature activation+2.025
neither
Token neither
Feature activation+2.021
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
impressive
Token impressive
Feature activation+0.000
as
Token as
Feature activation+0.221
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
ones
Token ones
Feature activation+0.000
),
Token),
Feature activation+2.025
neither
Token neither
Feature activation+2.021
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
impressive
Token impressive
Feature activation+0.000
as
Token as
Feature activation+0.221
the
Token the
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
team
Token team
Feature activation+0.038
back
Token back
Feature activation+0.000
to
Token to
Feature activation+2.129
the
Token the
Feature activation+0.322
city
Token city
Feature activation+0.447
after
Token after
Feature activation+0.000
they
Token they
Feature activation+0.000
moved
Token moved
Feature activation+0.000
Giants
Token Giants
Feature activation+0.066
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
watched
Token watched
Feature activation+0.519
Bonds
Token Bonds
Feature activation+0.000
,
Token,
Feature activation+2.116
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
MVP
Token MVP
Feature activation+0.000

INTERVAL 1.476 - 1.846
CONTAINS 0.004%

The
Token The
Feature activation+0.402
award
Token award
Feature activation+0.000
-
Token-
Feature activation+0.000
winning
Tokenwinning
Feature activation+0.569
NL
Token NL
Feature activation+0.103
SS
TokenSS
Feature activation+1.527
Gateway
Token Gateway
Feature activation+0.749
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
unified
Token unified
Feature activation+0.000
solution
Token solution
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
and
Token and
Feature activation+0.000
Int
Token Int
Feature activation+0.000
ran
Tokenran
Feature activation+0.000
ets
Tokenets
Feature activation+0.000
.
Token.
Feature activation+1.565
The
Token The
Feature activation+0.682
public
Token public
Feature activation+0.176
blockchain
Token blockchain
Feature activation+0.044
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.576
played
Token played
Feature activation+0.000
by
Token by
Feature activation+0.000
June
Token June
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
hart
Tokenhart
Feature activation+0.000
in
Token in
Feature activation+1.774
Irwin
Token Irwin
Feature activation+0.000
Allen
Token Allen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.252
15
Token 15
Feature activation+0.000
20
Token20
Feature activation+0.000
,
Token,
Feature activation+0.010
however
Token however
Feature activation+0.051
in
Token in
Feature activation+3.047
the
Token the
Feature activation+1.658
US
Token US
Feature activation+0.000
the
Token the
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
is
Token is
Feature activation+0.000
restricted
Token restricted
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
represented
Tokenrepresented
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
by
Token by
Feature activation+0.716
either
Token either
Feature activation+1.498
.
Token.
Feature activation+0.097
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
weren
Token weren
Feature activation+0.000

INTERVAL 1.107 - 1.476
CONTAINS 0.010%

10
Token 10
Feature activation+0.000
20
Token20
Feature activation+0.000
,
Token,
Feature activation+0.607
13
Token 13
Feature activation+0.000
20
Token20
Feature activation+0.000
or
Token or
Feature activation+1.223
15
Token 15
Feature activation+0.000
20
Token20
Feature activation+0.000
,
Token,
Feature activation+0.010
however
Token however
Feature activation+0.051
in
Token in
Feature activation+3.047
to
Token to
Feature activation+0.000
favour
Token favour
Feature activation+0.568
Mr
Token Mr
Feature activation+0.075
Cruz
Token Cruz
Feature activation+0.000
over
Token over
Feature activation+0.000
Mr
Token Mr
Feature activation+1.313
Trump
Token Trump
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
mainly
Token mainly
Feature activation+0.000
because
Token because
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
shot
Token shot
Feature activation+0.000
at
Token at
Feature activation+1.295
Sanders
Token Sanders
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
UK
Token UK
Feature activation+0.000
and
Token and
Feature activation+0.000
Denmark
Token Denmark
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.010
only
Token only
Feature activation+1.402
states
Token states
Feature activation+0.000
with
Token with
Feature activation+0.000
explicit
Token explicit
Feature activation+0.000
opt
Token opt
Feature activation+0.000
-
Token-
Feature activation+0.000
details
Token details
Feature activation+0.000
the
Token the
Feature activation+0.045
use
Token use
Feature activation+0.328
of
Token of
Feature activation+1.515
a
Token a
Feature activation+0.762
specific
Token specific
Feature activation+1.301
integrated
Token integrated
Feature activation+0.000
circuit
Token circuit
Feature activation+0.000
designed
Token designed
Feature activation+0.000
for
Token for
Feature activation+0.000
handling
Token handling
Feature activation+0.000

INTERVAL 0.738 - 1.107
CONTAINS 0.024%

July
Token July
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
recovered
Token recovered
Feature activation+0.000
to
Token to
Feature activation+0.000
beat
Token beat
Feature activation+0.760
Jar
Token Jar
Feature activation+0.000
rod
Tokenrod
Feature activation+0.000
Fletcher
Token Fletcher
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+0.000
Peru
Token Peru
Feature activation+0.000
in
Token in
Feature activation+0.000
1978
Token 1978
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.312
Both
TokenBoth
Feature activation+0.832
of
Token of
Feature activation+0.743
those
Token those
Feature activation+0.759
matches
Token matches
Feature activation+0.000
technically
Token technically
Feature activation+0.000
came
Token came
Feature activation+0.000
amara
Tokenamara
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
at
Token at
Feature activation+0.000
cornerback
Token cornerback
Feature activation+0.000
.
Token.
Feature activation+0.823
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.365
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
productions
Token productions
Feature activation+0.079
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.660
the
Token the
Feature activation+0.638
television
Token television
Feature activation+0.101
show
Token show
Feature activation+0.911
Firefly
Token Firefly
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
J
TokenJ
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
Whedon
Token Whedon
Feature activation+0.000
ene
Tokenene
Feature activation+0.000
,
Token,
Feature activation+0.002
dro
Token dro
Feature activation+0.000
plets
Tokenplets
Feature activation+0.000
of
Token of
Feature activation+0.956
that
Token that
Feature activation+1.040
solvent
Token solvent
Feature activation+0.000
are
Token are
Feature activation+0.000
produced
Token produced
Feature activation+0.000
.
Token.
Feature activation+0.000
Polar
Token Polar
Feature activation+0.000

INTERVAL 0.369 - 0.738
CONTAINS 0.078%

Z
Token Z
Feature activation+0.000
and
Tokenand
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
e
Tokene
Feature activation+0.000
(
Token (
Feature activation+0.000
though
Tokenthough
Feature activation+0.491
none
Token none
Feature activation+0.131
more
Token more
Feature activation+0.000
so
Token so
Feature activation+0.000
than
Token than
Feature activation+0.212
Dead
Token Dead
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
were
Token were
Feature activation+0.088
fault
Token fault
Feature activation+0.000
ed
Tokened
Feature activation+0.037
by
Token by
Feature activation+0.359
the
Token the
Feature activation+0.589
groups
Token groups
Feature activation+0.571
for
Token for
Feature activation+0.001
supposedly
Token supposedly
Feature activation+0.000
draining
Token draining
Feature activation+0.000
money
Token money
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
P
Token P
Feature activation+0.000
9
Token9
Feature activation+0.000
in
Token in
Feature activation+1.325
the
Token the
Feature activation+0.734
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
the
Token the
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
local
Token local
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
takeaway
Token takeaway
Feature activation+0.000
.
Token.
Feature activation+0.418
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+0.000
He
Token He
Feature activation+0.000
would
Token would
Feature activation+0.000
likely
Token likely
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
favor
Token favor
Feature activation+0.408
of
Token of
Feature activation+0.166
lowering
Token lowering
Feature activation+0.000
the
Token the
Feature activation+0.000
value
Token value
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.369
CONTAINS 99.881%

'll
Token'll
Feature activation+0.000
also
Token also
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
up
Token up
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
conven
Token conven
Feature activation+0.000
iences
Tokeniences
Feature activation+0.000
these
Token these
Feature activation+0.000
interactions
Token interactions
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
bot
Token bot
Feature activation+0.000
can
Token can
Feature activation+0.000
understand
Token understand
Feature activation+0.000
intent
Token intent
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
user
Token user
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
stand
Token stand
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
won
Token won
Feature activation+0.000
panel
Token panel
Feature activation+0.000
(
Token (
Feature activation+0.000
F
TokenF
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
i
Tokeni
Feature activation+0.000
SS
Token SS
Feature activation+0.000
50
Token50
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
78
Token78
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
closer
Token closer
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
where
Token where
Feature activation+0.000
Lara
Token Lara
Feature activation+0.000
's
Token's
Feature activation+0.000
headed
Token headed
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H8.3: (feature 20819)

TOP ACTIVATIONS
MAX = 3.070

SPORTS
Token SPORTS
Feature activation+0.000
NETWORK
Token NETWORK
Feature activation+0.355
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
57
Token57
Feature activation+0.000
AM
Token AM
Feature activation+3.070
1
Token 1
Feature activation+0.000
:
Token:
Feature activation+0.000
03
Token03
Feature activation+0.000
PM
Token PM
Feature activation+0.000
387
Token 387
Feature activation+0.000
L
Token L
Feature activation+0.000
ESPN
Token ESPN
Feature activation+0.000
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
58
Token58
Feature activation+0.000
PM
Token PM
Feature activation+2.971
12
Token 12
Feature activation+0.057
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
AM
Token AM
Feature activation+0.000
8
Token 8
Feature activation+0.000
Since
TokenSince
Feature activation+0.000
its
Token its
Feature activation+0.000
founding
Token founding
Feature activation+0.000
in
Token in
Feature activation+0.000
1998
Token 1998
Feature activation+0.000
,
Token,
Feature activation+1.942
the
Token the
Feature activation+1.786
Working
Token Working
Feature activation+0.000
Families
Token Families
Feature activation+0.000
Party
Token Party
Feature activation+0.000
has
Token has
Feature activation+0.000
its
Token its
Feature activation+0.000
founding
Token founding
Feature activation+0.000
in
Token in
Feature activation+0.000
1998
Token 1998
Feature activation+0.000
,
Token,
Feature activation+1.942
the
Token the
Feature activation+1.786
Working
Token Working
Feature activation+0.000
Families
Token Families
Feature activation+0.000
Party
Token Party
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.000
.
Token.
Feature activation+0.000
56
Token56
Feature activation+0.000
to
Token to
Feature activation+1.544
7
Token 7
Feature activation+0.029
.
Token.
Feature activation+0.000
73
Token73
Feature activation+0.000
range
Token range
Feature activation+0.000
of
Token of
Feature activation+0.000
With
TokenWith
Feature activation+0.000
the
Token the
Feature activation+0.000
res
Token res
Feature activation+0.000
ounding
Tokenounding
Feature activation+0.000
success
Token success
Feature activation+0.000
of
Token of
Feature activation+1.543
the
Token the
Feature activation+0.185
j
Token j
Feature activation+0.000
all
Tokenall
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
ANN
TokenANN
Feature activation+0.000
EL
TokenEL
Feature activation+0.000
9
Token 9
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
PM
Token PM
Feature activation+1.530
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.012
PM
Token PM
Feature activation+0.000
2
Token 2
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.008
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.043
ing
Tokening
Feature activation+0.761
For
Token For
Feature activation+1.527
my
Token my
Feature activation+1.088
lil
Token lil
Feature activation+0.658
cousin
Token cousin
Feature activation+1.116
man
Token man
Feature activation+0.673
#
Token #
Feature activation+0.675
pursue
Token pursue
Feature activation+0.000
another
Token another
Feature activation+0.000
path
Token path
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.031
Ċ
TokenĊ
Feature activation+1.516
Sc
TokenSc
Feature activation+0.000
ratch
Tokenratch
Feature activation+0.000
Jim
Token Jim
Feature activation+0.073
Hill
Token Hill
Feature activation+0.000
er
Tokener
Feature activation+0.000
do
Token do
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
8
Token8
Feature activation+0.000
and
Token and
Feature activation+1.501
the
Token the
Feature activation+0.000
Note
Token Note
Feature activation+0.000
8
Token 8
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
native
Token native
Feature activation+0.000
has
Token has
Feature activation+0.000
earned
Token earned
Feature activation+0.000
the
Token the
Feature activation+0.000
title
Token title
Feature activation+0.000
of
Token of
Feature activation+1.458
being
Token being
Feature activation+0.120
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
Draft
Token Draft
Feature activation+0.000
,
Token,
Feature activation+1.419
We
Token We
Feature activation+0.000
ems
Tokenems
Feature activation+0.000
earned
Token earned
Feature activation+0.000
All
Token All
Feature activation+0.000
-
Token-
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
disaster
Token disaster
Feature activation+0.000
.
Token.
Feature activation+0.860
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.398
"
Token"
Feature activation+0.000
At
TokenAt
Feature activation+0.000
first
Token first
Feature activation+0.000
I
Token I
Feature activation+0.000
felt
Token felt
Feature activation+0.000
How
Token How
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
twitter
Token twitter
Feature activation+0.000
account
Token account
Feature activation+0.000
.
Token.
Feature activation+1.382
With
Token With
Feature activation+0.088
a
Token a
Feature activation+0.000
star
Token star
Feature activation+0.000
-
Token-
Feature activation+0.000
st
Tokenst
Feature activation+0.000
sw
Token sw
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.000
including
Token including
Feature activation+0.000
S
Token S
Feature activation+0.000
4
Token4
Feature activation+0.000
,
Token,
Feature activation+1.379
S
Token S
Feature activation+0.000
5
Token5
Feature activation+0.000
and
Token and
Feature activation+0.288
S
Token S
Feature activation+0.000
6
Token6
Feature activation+0.000
-
Token-
Feature activation+0.000
e
Tokene
Feature activation+0.000
-
Token-
Feature activation+0.000
Ins
TokenIns
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
(
Token (
Feature activation+1.347
PT
TokenPT
Feature activation+0.470
I
TokenI
Feature activation+0.039
)
Token)
Feature activation+0.000
chairman
Token chairman
Feature activation+0.000
Imran
Token Imran
Feature activation+0.000
the
Token the
Feature activation+0.000
groundwork
Token groundwork
Feature activation+0.000
for
Token for
Feature activation+0.000
future
Token future
Feature activation+0.000
improvements
Token improvements
Feature activation+0.000
along
Token along
Feature activation+1.328
5
Token 5
Feature activation+0.528
th
Tokenth
Feature activation+0.000
Street
Token Street
Feature activation+0.000
NE
Token NE
Feature activation+0.000
.
Token.
Feature activation+0.000
sounds
Token sounds
Feature activation+0.000
familiar
Token familiar
Feature activation+0.000
,
Token,
Feature activation+0.759
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
because
Token because
Feature activation+1.309
CNN
Token CNN
Feature activation+0.000
just
Token just
Feature activation+0.000
did
Token did
Feature activation+0.000
an
Token an
Feature activation+0.000
exp
Token exp
Feature activation+0.000
OS
Token OS
Feature activation+0.000
X
Token X
Feature activation+0.000
10
Token 10
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
or
Token or
Feature activation+1.302
later
Token later
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
CPU
TokenCPU
Feature activation+0.000
:
Token :
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
World
Token World
Feature activation+0.000
Wrestling
Token Wrestling
Feature activation+0.000
Federation
Token Federation
Feature activation+0.000
(
Token (
Feature activation+1.295
WW
TokenWW
Feature activation+0.000
F
TokenF
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
WWE
Token WWE
Feature activation+0.000

Top DFA by src position
MAX = 4.297

NBC
Token NBC
Feature activation+0.002
Top resid features:
SPORTS
Token SPORTS
Feature activation-0.025
Top resid features:
NETWORK
Token NETWORK
Feature activation-0.020
Top resid features:
10
Token 10
Feature activation-0.296
Top resid features:
:
Token:
Feature activation+0.023
Top resid features:
57
Token57
Feature activation+4.297
Top resid features:
AM
Token AM
Feature activation-0.130
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
03
Token03
Feature activation+0.000
Top resid features:
PM
Token PM
Feature activation+0.000
Top resid features:
ATE
TokenATE
Feature activation+0.000
Top resid features:
L
Token L
Feature activation-0.004
Top resid features:
ESPN
Token ESPN
Feature activation-0.017
Top resid features:
10
Token 10
Feature activation-0.381
Top resid features:
:
Token:
Feature activation-0.008
Top resid features:
58
Token58
Feature activation+4.109
Top resid features:
PM
Token PM
Feature activation-0.099
Top resid features:
12
Token 12
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
30
Token30
Feature activation+0.000
Top resid features:
AM
Token AM
Feature activation+0.000
Top resid features:
political
Token political
Feature activation-0.000
Top resid features:
organization
Token organization
Feature activation+0.017
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
W
Token W
Feature activation+0.099
Top resid features:
FP
TokenFP
Feature activation+2.621
Top resid features:
.
Token.
Feature activation+0.177
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Since
TokenSince
Feature activation-0.007
Top resid features:
its
Token its
Feature activation+0.018
Top resid features:
political
Token political
Feature activation-0.000
Top resid features:
organization
Token organization
Feature activation+0.018
Top resid features:
:
Token:
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
W
Token W
Feature activation+0.095
Top resid features:
FP
TokenFP
Feature activation+2.529
Top resid features:
.
Token.
Feature activation+0.137
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Since
TokenSince
Feature activation-0.005
Top resid features:
its
Token its
Feature activation+0.024
Top resid features:
already
Token already
Feature activation-0.002
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
7
Token 7
Feature activation+0.092
Top resid features:
.
Token.
Feature activation+0.176
Top resid features:
56
Token56
Feature activation+1.702
Top resid features:
to
Token to
Feature activation+0.369
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
73
Token73
Feature activation+0.000
Top resid features:
range
Token range
Feature activation+0.000
Top resid features:
Status
Token Status
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Wh
TokenWh
Feature activation+0.001
Top resid features:
ats
Tokenats
Feature activation+0.001
Top resid features:
app
Tokenapp
Feature activation+2.375
Top resid features:
groups
Token groups
Feature activation+0.075
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
Facebook
Token Facebook
Feature activation-0.050
Top resid features:
pages
Token pages
Feature activation+0.012
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
CH
Token CH
Feature activation-0.001
Top resid features:
ANN
TokenANN
Feature activation+0.004
Top resid features:
EL
TokenEL
Feature activation-0.003
Top resid features:
9
Token 9
Feature activation-0.657
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
00
Token00
Feature activation+2.897
Top resid features:
PM
Token PM
Feature activation-0.074
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
00
Token00
Feature activation+0.000
Top resid features:
PM
Token PM
Feature activation+0.000
Top resid features:
emotional
Token emotional
Feature activation-0.003
Top resid features:
t
Token t
Feature activation-0.001
Top resid features:
ributes
Tokenributes
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
Hall
Token Hall
Feature activation-0.027
Top resid features:
man
Tokenman
Feature activation+2.363
Top resid features:
on
Token on
Feature activation+0.015
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
Twitter
Token Twitter
Feature activation+0.034
Top resid features:
account
Token account
Feature activation-0.004
Top resid features:
since
Token since
Feature activation-0.000
Top resid features:
E
Token E
Feature activation-0.012
Top resid features:
wen
Tokenwen
Feature activation+0.132
Top resid features:
reported
Token reported
Feature activation+0.011
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
Hill
Token Hill
Feature activation+0.021
Top resid features:
er
Tokener
Feature activation+1.863
Top resid features:
turned
Token turned
Feature activation+0.101
Top resid features:
down
Token down
Feature activation+0.033
Top resid features:
offers
Token offers
Feature activation+0.032
Top resid features:
from
Token from
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
you
Token you
Feature activation-0.031
Top resid features:
do
Token do
Feature activation-0.005
Top resid features:
on
Token on
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
S
Token S
Feature activation+0.039
Top resid features:
8
Token8
Feature activation+2.226
Top resid features:
and
Token and
Feature activation+0.098
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Note
Token Note
Feature activation+0.000
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.185
Top resid features:
Left
Token Left
Feature activation-0.015
Top resid features:
W
Token W
Feature activation+0.068
Top resid features:
inger
Tokeninger
Feature activation+2.116
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
Anaheim
Token Anaheim
Feature activation+0.010
Top resid features:
Ducks
Token Ducks
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
his
Token his
Feature activation-0.008
Top resid features:
NBA
Token NBA
Feature activation-0.001
Top resid features:
career
Token career
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
We
Token We
Feature activation-0.038
Top resid features:
ems
Tokenems
Feature activation+2.063
Top resid features:
has
Token has
Feature activation+0.200
Top resid features:
averaged
Token averaged
Feature activation-0.003
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
7
Token7
Feature activation-0.000
Top resid features:
Res
TokenRes
Feature activation+0.010
Top resid features:
ident
Tokenident
Feature activation+0.012
Top resid features:
Jan
Token Jan
Feature activation-0.014
Top resid features:
W
Token W
Feature activation-0.031
Top resid features:
ie
Tokenie
Feature activation+0.285
Top resid features:
be
Tokenbe
Feature activation+1.894
Top resid features:
,
Token,
Feature activation+0.144
Top resid features:
who
Token who
Feature activation+0.063
Top resid features:
recently
Token recently
Feature activation-0.003
Top resid features:
received
Token received
Feature activation-0.003
Top resid features:
her
Token her
Feature activation-0.001
Top resid features:
below
Token below
Feature activation-0.002
Top resid features:
would
Token would
Feature activation-0.004
Top resid features:
be
Token be
Feature activation-0.007
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
How
Token How
Feature activation+0.002
Top resid features:
ie
Tokenie
Feature activation+1.705
Top resid features:
Rose
Token Rose
Feature activation+0.235
Top resid features:
twitter
Token twitter
Feature activation+0.186
Top resid features:
account
Token account
Feature activation+0.118
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
With
Token With
Feature activation+0.000
Top resid features:
1
Token1
Feature activation-0.028
Top resid features:
sw
Token sw
Feature activation+0.006
Top resid features:
immers
Tokenimmers
Feature activation-0.018
Top resid features:
including
Token including
Feature activation+0.040
Top resid features:
S
Token S
Feature activation-0.142
Top resid features:
4
Token4
Feature activation+2.487
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sue
Token sue
Feature activation+0.010
Top resid features:
Pakistan
Token Pakistan
Feature activation+0.111
Top resid features:
Te
Token Te
Feature activation+0.057
Top resid features:
h
Tokenh
Feature activation+0.110
Top resid features:
reek
Tokenreek
Feature activation+0.523
Top resid features:
-
Token-
Feature activation+0.169
Top resid features:
e
Tokene
Feature activation+0.146
Top resid features:
-
Token-
Feature activation+0.153
Top resid features:
Ins
TokenIns
Feature activation+0.371
Top resid features:
af
Tokenaf
Feature activation+0.438
Top resid features:
X
TokenX
Feature activation+0.001
Top resid features:
tracks
Token tracks
Feature activation+0.362
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
down
Token down
Feature activation+0.009
Top resid features:
W
Token W
Feature activation+0.016
Top resid features:
Street
Token Street
Feature activation+1.725
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
better
Token better
Feature activation+0.006
Top resid features:
connect
Token connect
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
station
Token station
Feature activation-0.024
Top resid features:
name
Token name
Feature activation+0.000
Top resid features:
Wal
Token Wal
Feature activation+0.144
Top resid features:
id
Tokenid
Feature activation+0.545
Top resid features:
Sho
Token Sho
Feature activation+0.079
Top resid features:
eb
Tokeneb
Feature activation+0.100
Top resid features:
at
Tokenat
Feature activation+1.097
Top resid features:
sounds
Token sounds
Feature activation+0.002
Top resid features:
familiar
Token familiar
Feature activation+0.020
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
it
Token it
Feature activation-0.005
Top resid features:
's
Token's
Feature activation-0.016
Top resid features:
Mac
TokenMac
Feature activation-0.039
Top resid features:
OS
Token OS
Feature activation-0.029
Top resid features:
X
Token X
Feature activation-0.173
Top resid features:
10
Token 10
Feature activation+0.065
Top resid features:
.
Token.
Feature activation+0.636
Top resid features:
4
Token4
Feature activation+1.356
Top resid features:
or
Token or
Feature activation+0.205
Top resid features:
later
Token later
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:
CPU
TokenCPU
Feature activation+0.000
Top resid features:
signed
Token signed
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.022
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
World
Token World
Feature activation-0.615
Top resid features:
Wrestling
Token Wrestling
Feature activation+1.067
Top resid features:
Federation
Token Federation
Feature activation+1.669
Top resid features:
(
Token (
Feature activation+0.018
Top resid features:
WW
TokenWW
Feature activation+0.000
Top resid features:
F
TokenF
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.47

Head 4: 0.02

Head 5: 0.03

Head 6: 0.04

Head 7: 0.03

Head 8: 0.05

Head 9: 0.04

Head 10: 0.12

Head 11: 0.11

Positive logits

Sew2.73

WS2.65

SW2.63

Weiss2.62

HW2.51

Wis2.46

SW2.39

hew2.38

WM2.38

WP2.35

ZE2.33

WS2.31

CLS2.30

Kw2.30

sett2.29

RW2.29

Ws2.29

WIND2.27

Swe2.27

wcs2.27

Negative logits

ibal-2.68

aton-2.61

onica-2.57

               -2.36

>>\-2.35

ashtra-2.35

arian-2.31

tera-2.30

Parameter-2.24

-2.21

argo-2.21

aminer-2.21

atis-2.19

Minion-2.19

Anarchy-2.17

agar-2.17

berto-2.16

ivan-2.13

irez-2.12

inar-2.12

INTERVAL 2.763 - 3.070
CONTAINS 0.000%

L
Token L
Feature activation+0.000
ESPN
Token ESPN
Feature activation+0.000
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
58
Token58
Feature activation+0.000
PM
Token PM
Feature activation+2.971
12
Token 12
Feature activation+0.057
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
AM
Token AM
Feature activation+0.000
8
Token 8
Feature activation+0.000
SPORTS
Token SPORTS
Feature activation+0.000
NETWORK
Token NETWORK
Feature activation+0.355
10
Token 10
Feature activation+0.000
:
Token:
Feature activation+0.000
57
Token57
Feature activation+0.000
AM
Token AM
Feature activation+3.070
1
Token 1
Feature activation+0.000
:
Token:
Feature activation+0.000
03
Token03
Feature activation+0.000
PM
Token PM
Feature activation+0.000
387
Token 387
Feature activation+0.000

INTERVAL 2.456 - 2.763
CONTAINS 0.000%

INTERVAL 2.149 - 2.456
CONTAINS 0.000%

INTERVAL 1.842 - 2.149
CONTAINS 0.000%

Since
TokenSince
Feature activation+0.000
its
Token its
Feature activation+0.000
founding
Token founding
Feature activation+0.000
in
Token in
Feature activation+0.000
1998
Token 1998
Feature activation+0.000
,
Token,
Feature activation+1.942
the
Token the
Feature activation+1.786
Working
Token Working
Feature activation+0.000
Families
Token Families
Feature activation+0.000
Party
Token Party
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 1.535 - 1.842
CONTAINS 0.000%

With
TokenWith
Feature activation+0.000
the
Token the
Feature activation+0.000
res
Token res
Feature activation+0.000
ounding
Tokenounding
Feature activation+0.000
success
Token success
Feature activation+0.000
of
Token of
Feature activation+1.543
the
Token the
Feature activation+0.185
j
Token j
Feature activation+0.000
all
Tokenall
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
its
Token its
Feature activation+0.000
founding
Token founding
Feature activation+0.000
in
Token in
Feature activation+0.000
1998
Token 1998
Feature activation+0.000
,
Token,
Feature activation+1.942
the
Token the
Feature activation+1.786
Working
Token Working
Feature activation+0.000
Families
Token Families
Feature activation+0.000
Party
Token Party
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.000
.
Token.
Feature activation+0.000
56
Token56
Feature activation+0.000
to
Token to
Feature activation+1.544
7
Token 7
Feature activation+0.029
.
Token.
Feature activation+0.000
73
Token73
Feature activation+0.000
range
Token range
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.228 - 1.535
CONTAINS 0.002%

OS
Token OS
Feature activation+0.000
X
Token X
Feature activation+0.000
10
Token 10
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
or
Token or
Feature activation+1.302
later
Token later
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
CPU
TokenCPU
Feature activation+0.000
:
Token :
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
another
Token another
Feature activation+0.000
path
Token path
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.031
Ċ
TokenĊ
Feature activation+1.516
Sc
TokenSc
Feature activation+0.000
ratch
Tokenratch
Feature activation+0.000
Jim
Token Jim
Feature activation+0.073
Hill
Token Hill
Feature activation+0.000
er
Tokener
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.008
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.043
ing
Tokening
Feature activation+0.761
For
Token For
Feature activation+1.527
my
Token my
Feature activation+1.088
lil
Token lil
Feature activation+0.658
cousin
Token cousin
Feature activation+1.116
man
Token man
Feature activation+0.673
#
Token #
Feature activation+0.675
native
Token native
Feature activation+0.000
has
Token has
Feature activation+0.000
earned
Token earned
Feature activation+0.000
the
Token the
Feature activation+0.000
title
Token title
Feature activation+0.000
of
Token of
Feature activation+1.458
being
Token being
Feature activation+0.120
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
-
Token-
Feature activation+0.000
private
Tokenprivate
Feature activation+0.000
partnership
Token partnership
Feature activation+0.000
to
Token to
Feature activation+0.000
develop
Token develop
Feature activation+0.390
the
Token the
Feature activation+1.237
initial
Token initial
Feature activation+0.032
sky
Token sky
Feature activation+0.000
way
Tokenway
Feature activation+0.000
line
Token line
Feature activation+0.000
from
Token from
Feature activation+0.000

INTERVAL 0.921 - 1.228
CONTAINS 0.003%

company
Token company
Feature activation+0.000
has
Token has
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.050
in
Token in
Feature activation+1.087
our
Token our
Feature activation+0.000
community
Token community
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
though
Token though
Feature activation+0.000
the
Token the
Feature activation+0.000
salary
Token salary
Feature activation+0.000
level
Token level
Feature activation+0.000
approved
Token approved
Feature activation+0.000
by
Token by
Feature activation+0.967
the
Token the
Feature activation+0.674
H
Token H
Feature activation+0.000
SE
TokenSE
Feature activation+0.000
was
Token was
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.008
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.043
ing
Tokening
Feature activation+0.761
For
Token For
Feature activation+1.527
my
Token my
Feature activation+1.088
lil
Token lil
Feature activation+0.658
cousin
Token cousin
Feature activation+1.116
man
Token man
Feature activation+0.673
#
Token #
Feature activation+0.675
C
TokenC
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
TokenNew
Feature activation+0.000
bie
Tokenbie
Feature activation+0.000
Activity
TokenActivity
Feature activation+0.000
:
Token:
Feature activation+0.996
3
Token 3
Feature activation+0.040
Merit
TokenMerit
Feature activation+0.000
:
Token:
Feature activation+0.000
0
Token 0
Feature activation+0.000
To
Token To
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
a
Token a
Feature activation+0.000
line
Token line
Feature activation+0.000
of
Token of
Feature activation+0.000
S
Token S
Feature activation+0.000
+,
Token+,
Feature activation+1.017
M
Token M
Feature activation+0.000
+,
Token+,
Feature activation+0.000
L
Token L
Feature activation+0.000
+
Token+
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.614 - 0.921
CONTAINS 0.007%

Taliban
Token Taliban
Feature activation+0.000
in
Token in
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
.
Token.
Feature activation+0.521
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.883
A
TokenA
Feature activation+0.000
small
Token small
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
/
Token/
Feature activation+0.000
NEW
TokenNEW
Feature activation+0.000
YORK
Token YORK
Feature activation+0.000
MET
Token MET
Feature activation+0.000
S
TokenS
Feature activation+0.000
ESPN
Token ESPN
Feature activation+0.732
8
Token 8
Feature activation+0.165
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
PM
Token PM
Feature activation+1.237
10
Token 10
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.157
Talk
TokenTalk
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.671
you
Token you
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
told
Token told
Feature activation+0.000
icket
Tokenicket
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
widely
Token widely
Feature activation+0.000
played
Token played
Feature activation+0.000
.
Token.
Feature activation+0.683
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
Military
Token Military
Feature activation+0.000
Journal
Token Journal
Feature activation+0.000
,
Token,
Feature activation+0.000
Market
Token Market
Feature activation+0.000
in
Token in
Feature activation+0.000
Honolulu
Token Honolulu
Feature activation+0.000
,
Token,
Feature activation+0.000
Hawaii
Token Hawaii
Feature activation+0.000
.
Token.
Feature activation+0.688
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.547
M
TokenM
Feature activation+0.000
ama
Tokenama
Feature activation+0.000
T
Token T
Feature activation+0.000

INTERVAL 0.307 - 0.614
CONTAINS 0.027%

body
Token body
Feature activation+0.000
past
Token past
Feature activation+0.000
the
Token the
Feature activation+0.000
tiger
Token tiger
Feature activation+0.000
cage
Token cage
Feature activation+0.000
at
Token at
Feature activation+0.431
the
Token the
Feature activation+0.322
zoo
Token zoo
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
Delhi
Token Delhi
Feature activation+0.000
dead
Token dead
Feature activation+0.000
character
Token character
Feature activation+0.000
,
Token,
Feature activation+0.000
Sh
Token Sh
Feature activation+0.000
ae
Tokenae
Feature activation+0.000
.
Token.
Feature activation+0.417
As
Token As
Feature activation+0.000
you
Token you
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
remember
Token remember
Feature activation+0.010
The
Token The
Feature activation+0.000
bill
Token bill
Feature activation+0.000
now
Token now
Feature activation+0.000
heads
Token heads
Feature activation+0.000
to
Token to
Feature activation+0.395
the
Token the
Feature activation+0.395
House
Token House
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
apping
Tokenapping
Feature activation+0.000
Princess
Token Princess
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
Story
Token Story
Feature activation+0.000
of
Token of
Feature activation+0.506
the
Token the
Feature activation+0.379
Unknown
Token Unknown
Feature activation+0.000
Me
Token Me
Feature activation+0.000
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
welcome
Token welcome
Feature activation+0.000
,
Token,
Feature activation+0.000
yes
Token yes
Feature activation+0.000
and
Token and
Feature activation+0.329
no
Token no
Feature activation+0.000
thank
Token thank
Feature activation+0.000
you
Token you
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.307
CONTAINS 99.961%

possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
Whether
Token Whether
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
tables
Token tables
Feature activation+0.000
or
Token or
Feature activation+0.000
indexes
Token indexes
Feature activation+0.000
,
Token,
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
headache
Token headache
Feature activation+0.000
every
Token every
Feature activation+0.000
club
Token club
Feature activation+0.000
would
Token would
Feature activation+0.000
love
Token love
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.000
of
Token of
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
by
Token by
Feature activation+0.000
email
Token email
Feature activation+0.000
and
Token and
Feature activation+0.000
never
Token never
Feature activation+0.000
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.000
more
Token more
Feature activation+0.000
information
Token information
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
pipeline
Token pipeline
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
actual
Token actual
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
night
Token night
Feature activation+0.000
,
Token,
Feature activation+0.000
Maduro
Token Maduro
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
failure
Token failure
Feature activation+0.000
was
Token was
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H8.3: (feature 9105)

TOP ACTIVATIONS
MAX = 2.959

committed
Token committed
Feature activation+0.000
a
Token a
Feature activation+0.000
crime
Token crime
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
up
Token up
Feature activation+2.535
their
Token their
Feature activation+0.123
constitutional
Token constitutional
Feature activation+0.098
rights
Token rights
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
targets
Token targets
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
attain
Token attain
Feature activation+2.492
them
Token them
Feature activation+0.102
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
alterations
Token alterations
Feature activation+0.000
as
Token as
Feature activation+0.000
"
Token"
Feature activation+0.000
from
Token from
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
don
Token don
Feature activation+0.865
't
Token't
Feature activation+2.312
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
presumptive
Token presumptive
Feature activation+0.000
the
Token the
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
Draft
Token Draft
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+2.197
same
Token same
Feature activation+1.817
traits
Token traits
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
him
Token him
Feature activation+0.000
resumed
Token resumed
Feature activation+0.000
their
Token their
Feature activation+0.000
hunger
Token hunger
Feature activation+0.000
strike
Token strike
Feature activation+0.000
,
Token,
Feature activation+0.000
demanding
Token demanding
Feature activation+2.134
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
California
Token California
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
activists
Token activists
Feature activation+0.000
are
Token are
Feature activation+0.000
unwilling
Token unwilling
Feature activation+0.000
to
Token to
Feature activation+0.970
cross
Token cross
Feature activation+2.058
to
Token to
Feature activation+0.000
inflict
Token inflict
Feature activation+0.000
damage
Token damage
Feature activation+0.000
on
Token on
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
developer
Token developer
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
One
TokenOne
Feature activation+1.927
of
Token of
Feature activation+2.020
my
Token my
Feature activation+1.901
favorite
Token favorite
Feature activation+0.000
things
Token things
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
rot
Tokenrot
Feature activation+0.882
the
Token the
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.967
Obamacare
Token Obamacare
Feature activation+0.000
talking
Token talking
Feature activation+0.000
points
Token points
Feature activation+0.000
and
Token and
Feature activation+0.000
un
Token un
Feature activation+0.000
indie
Token indie
Feature activation+0.000
developer
Token developer
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
One
TokenOne
Feature activation+1.927
of
Token of
Feature activation+2.020
my
Token my
Feature activation+1.901
favorite
Token favorite
Feature activation+0.000
things
Token things
Feature activation+0.000
is
Token is
Feature activation+0.000
have
Token have
Feature activation+0.000
values
Token values
Feature activation+0.000
."
Token."
Feature activation+0.000
Rel
TokenRel
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
those
Token those
Feature activation+1.906
undeniable
Token undeniable
Feature activation+1.473
rights
Token rights
Feature activation+0.000
to
Token to
Feature activation+0.000
tech
Token tech
Feature activation+0.000
,
Token,
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
One
TokenOne
Feature activation+1.927
of
Token of
Feature activation+2.020
my
Token my
Feature activation+1.901
favorite
Token favorite
Feature activation+0.000
things
Token things
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
a
Token a
Feature activation+0.000
her
Token her
Feature activation+0.000
interests
Token interests
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
those
Token those
Feature activation+1.883
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
mon
Token mon
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
elite
Token elite
Feature activation+0.000
with
Token with
Feature activation+0.147
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
lowered
Token lowered
Feature activation+1.851
rates
Token rates
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Up
TokenUp
Feature activation+0.000
,
Token,
Feature activation+0.064
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
plan
Token plan
Feature activation+0.000
on
Token on
Feature activation+0.000
executing
Token executing
Feature activation+1.823
them
Token them
Feature activation+0.638
exactly
Token exactly
Feature activation+0.106
as
Token as
Feature activation+0.080
stated
Token stated
Feature activation+0.730
.
Token.
Feature activation+0.000
rights
Token rights
Feature activation+0.191
enshr
Token enshr
Feature activation+0.000
ined
Tokenined
Feature activation+0.000
in
Token in
Feature activation+0.000
law
Token law
Feature activation+0.000
.
Token.
Feature activation+1.817
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
of
Token of
Feature activation+0.000
no
Token no
Feature activation+0.000
woman
Token woman
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
Draft
Token Draft
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+2.197
same
Token same
Feature activation+1.817
traits
Token traits
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
him
Token him
Feature activation+0.000
one
Token one
Feature activation+0.000
do
Token do
Feature activation+0.247
you
Token you
Feature activation+0.000
care
Token care
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
preserve
Token preserve
Feature activation+1.750
them
Token them
Feature activation+0.000
here
Token here
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
s
Tokens
Feature activation+0.000
intu
Token intu
Feature activation+0.000
itions
Tokenitions
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.312
as
Token as
Feature activation+1.747
describing
Token describing
Feature activation+0.000
the
Token the
Feature activation+0.000
site
Token site
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
as
Token as
Feature activation+0.000
often
Token often
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.126
changed
Token changed
Feature activation+1.733
wives
Token wives
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
France
Token France
Feature activation+0.000
rejected
Token rejected
Feature activation+1.702
it
Token it
Feature activation+0.065
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
drafted
Token drafted
Feature activation+0.000
a
Token a
Feature activation+0.000

Top DFA by src position
MAX = 2.911

up
Token up
Feature activation+0.004
Top resid features:
some
Token some
Feature activation+0.004
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
your
Token your
Feature activation-0.029
Top resid features:
constitutional
Token constitutional
Feature activation+0.063
Top resid features:
rights
Token rights
Feature activation+2.849
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
used
Token used
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
set
Token set
Feature activation+0.004
Top resid features:
out
Token out
Feature activation-0.002
Top resid features:
your
Token your
Feature activation-0.000
Top resid features:
targets
Token targets
Feature activation+2.911
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
how
Token how
Feature activation+0.048
Top resid features:
you
Token you
Feature activation+0.026
Top resid features:
will
Token will
Feature activation+0.053
Top resid features:
attain
Token attain
Feature activation-0.011
Top resid features:
immigrants
Token immigrants
Feature activation+0.003
Top resid features:
who
Token who
Feature activation-0.003
Top resid features:
"
Token "
Feature activation-0.017
Top resid features:
share
Tokenshare
Feature activation-0.014
Top resid features:
our
Token our
Feature activation-0.012
Top resid features:
values
Token values
Feature activation+2.093
Top resid features:
"
Token"
Feature activation+0.549
Top resid features:
and
Token and
Feature activation-0.027
Top resid features:
"
Token "
Feature activation-0.008
Top resid features:
love
Tokenlove
Feature activation+0.032
Top resid features:
our
Token our
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
power
Token power
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
strength
Token strength
Feature activation+0.051
Top resid features:
and
Token and
Feature activation-0.082
Top resid features:
instincts
Token instincts
Feature activation+1.869
Top resid features:
that
Token that
Feature activation+0.905
Top resid features:
made
Token made
Feature activation+0.045
Top resid features:
him
Token him
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
No
Token No
Feature activation-0.000
Top resid features:
demand
Token demand
Feature activation+0.003
Top resid features:
basic
Token basic
Feature activation+0.014
Top resid features:
rights
Token rights
Feature activation+0.983
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
constitutional
Token constitutional
Feature activation+0.083
Top resid features:
protections
Token protections
Feature activation+1.302
Top resid features:
for
Token for
Feature activation+0.029
Top resid features:
themselves
Token themselves
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
one
Token one
Feature activation-0.003
Top resid features:
another
Token another
Feature activation-0.004
Top resid features:
need
Token need
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
there
Token there
Feature activation-0.009
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
no
Token no
Feature activation+0.003
Top resid features:
bounds
Token bounds
Feature activation+2.475
Top resid features:
Republicans
Token Republicans
Feature activation+0.013
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
their
Token their
Feature activation+0.002
Top resid features:
conservative
Token conservative
Feature activation+0.005
Top resid features:
activists
Token activists
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
What
TokenWhat
Feature activation-0.007
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
your
Token your
Feature activation-0.010
Top resid features:
goals
Token goals
Feature activation+2.639
Top resid features:
as
Token as
Feature activation+0.014
Top resid features:
an
Token an
Feature activation-0.004
Top resid features:
indie
Token indie
Feature activation-0.025
Top resid features:
developer
Token developer
Feature activation-0.027
Top resid features:
?
Token?
Feature activation+0.056
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
Administration
Token Administration
Feature activation+0.005
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
Obamacare
Token Obamacare
Feature activation+0.032
Top resid features:
Talking
Token Talking
Feature activation-0.004
Top resid features:
Points
Token Points
Feature activation+2.447
Top resid features:
'
Token'
Feature activation+0.070
Top resid features:
|
Token |
Feature activation-0.004
Top resid features:
Truth
Token Truth
Feature activation-0.001
Top resid features:
Rev
Token Rev
Feature activation+0.000
Top resid features:
olt
Tokenolt
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
What
TokenWhat
Feature activation-0.013
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
goals
Token goals
Feature activation+2.379
Top resid features:
as
Token as
Feature activation+0.008
Top resid features:
an
Token an
Feature activation-0.006
Top resid features:
indie
Token indie
Feature activation-0.012
Top resid features:
developer
Token developer
Feature activation-0.023
Top resid features:
?
Token?
Feature activation+0.129
Top resid features:
can
Token can
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
should
Token should
Feature activation+0.008
Top resid features:
have
Token have
Feature activation+0.005
Top resid features:
values
Token values
Feature activation+2.269
Top resid features:
."
Token."
Feature activation+0.021
Top resid features:
Rel
TokenRel
Feature activation+0.002
Top resid features:
ating
Tokenating
Feature activation+0.117
Top resid features:
those
Token those
Feature activation-0.081
Top resid features:
undeniable
Token undeniable
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
What
TokenWhat
Feature activation-0.001
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
your
Token your
Feature activation-0.003
Top resid features:
goals
Token goals
Feature activation+2.438
Top resid features:
as
Token as
Feature activation+0.008
Top resid features:
an
Token an
Feature activation-0.010
Top resid features:
indie
Token indie
Feature activation-0.052
Top resid features:
developer
Token developer
Feature activation-0.047
Top resid features:
?
Token?
Feature activation+0.097
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation+0.011
Top resid features:
serving
Token serving
Feature activation-0.001
Top resid features:
her
Token her
Feature activation+0.024
Top resid features:
interests
Token interests
Feature activation+1.993
Top resid features:
so
Token so
Feature activation+0.120
Top resid features:
much
Token much
Feature activation+0.009
Top resid features:
as
Token as
Feature activation+0.053
Top resid features:
those
Token those
Feature activation+0.132
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
next
Token next
Feature activation-0.001
Top resid features:
decade
Token decade
Feature activation+0.010
Top resid features:
with
Token with
Feature activation+0.010
Top resid features:
current
Token current
Feature activation-0.006
Top resid features:
tax
Token tax
Feature activation+0.046
Top resid features:
rates
Token rates
Feature activation+2.103
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
even
Token even
Feature activation+0.002
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.035
Top resid features:
Trump
Token Trump
Feature activation+0.103
Top resid features:
like
Token like
Feature activation+0.005
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
think
Token think
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Our
Token Our
Feature activation-0.000
Top resid features:
plans
Token plans
Feature activation+1.689
Top resid features:
are
Token are
Feature activation+0.330
Top resid features:
straight
Token straight
Feature activation+0.035
Top resid features:
forward
Token forward
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
All
Token All
Feature activation-0.072
Top resid features:
humans
Token humans
Feature activation-0.029
Top resid features:
exist
Token exist
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.016
Top resid features:
basic
Token basic
Feature activation+0.021
Top resid features:
rights
Token rights
Feature activation+1.153
Top resid features:
enshr
Token enshr
Feature activation+0.376
Top resid features:
ined
Tokenined
Feature activation+0.565
Top resid features:
in
Token in
Feature activation+0.079
Top resid features:
law
Token law
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.163
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
power
Token power
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
strength
Token strength
Feature activation+0.066
Top resid features:
and
Token and
Feature activation-0.050
Top resid features:
instincts
Token instincts
Feature activation+1.573
Top resid features:
that
Token that
Feature activation+0.599
Top resid features:
made
Token made
Feature activation+0.139
Top resid features:
him
Token him
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
No
Token No
Feature activation-0.001
Top resid features:
well
Token well
Feature activation+0.008
Top resid features:
does
Token does
Feature activation+0.002
Top resid features:
our
Token our
Feature activation-0.001
Top resid features:
government
Token government
Feature activation+0.002
Top resid features:
respect
Token respect
Feature activation+0.011
Top resid features:
them
Token them
Feature activation+1.478
Top resid features:
?
Token?
Feature activation+0.006
Top resid features:
And
Token And
Feature activation+0.004
Top resid features:
do
Token do
Feature activation+0.018
Top resid features:
you
Token you
Feature activation+0.013
Top resid features:
care
Token care
Feature activation+0.001
Top resid features:
people
Token people
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
intu
Token intu
Feature activation+0.207
Top resid features:
itions
Tokenitions
Feature activation+1.773
Top resid features:
as
Token as
Feature activation+0.160
Top resid features:
well
Token well
Feature activation+0.033
Top resid features:
as
Token as
Feature activation+0.010
Top resid features:
describing
Token describing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
frail
Token frail
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
changed
Token changed
Feature activation-0.002
Top resid features:
political
Token political
Feature activation-0.014
Top resid features:
views
Token views
Feature activation+2.036
Top resid features:
almost
Token almost
Feature activation+0.019
Top resid features:
as
Token as
Feature activation-0.011
Top resid features:
often
Token often
Feature activation+0.003
Top resid features:
as
Token as
Feature activation+0.029
Top resid features:
he
Token he
Feature activation+0.106
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
honoring
Token honoring
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
commitments
Token commitments
Feature activation+0.577
Top resid features:
they
Token they
Feature activation+0.389
Top resid features:
made
Token made
Feature activation+0.846
Top resid features:
in
Token in
Feature activation+0.090
Top resid features:
Geneva
Token Geneva
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.070
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
U
Token U
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.46

Head 4: 0.03

Head 5: 0.07

Head 6: 0.03

Head 7: 0.05

Head 8: 0.06

Head 9: 0.05

Head 10: 0.13

Head 11: 0.03

Positive logits

ones4.21

them3.81

those3.43

theirs3.15

those2.87

these2.76

originals2.71

These2.70

THEM2.67

BILITIES2.60

These2.53

THESE2.51

Those2.49

Those2.48

these2.41

them2.38

Them2.36

ements2.35

hers2.31

yours2.09

Negative logits

apego-2.29

oscope-2.26

oz-2.02

ospons-1.97

odynam-1.96

-1.96

ographed-1.95

arta-1.94

la-1.93

okin-1.91

zai-1.87

ozyg-1.87

omorph-1.83

oti-1.83

ograp-1.82

ocy-1.81

osponsors-1.77

itaire-1.76

ritis-1.73

iltr-1.72

INTERVAL 2.663 - 2.959
CONTAINS 0.000%

INTERVAL 2.367 - 2.663
CONTAINS 0.000%

targets
Token targets
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
attain
Token attain
Feature activation+2.492
them
Token them
Feature activation+0.102
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
alterations
Token alterations
Feature activation+0.000
as
Token as
Feature activation+0.000
committed
Token committed
Feature activation+0.000
a
Token a
Feature activation+0.000
crime
Token crime
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
up
Token up
Feature activation+2.535
their
Token their
Feature activation+0.123
constitutional
Token constitutional
Feature activation+0.098
rights
Token rights
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000

INTERVAL 2.071 - 2.367
CONTAINS 0.000%

"
Token"
Feature activation+0.000
from
Token from
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
don
Token don
Feature activation+0.865
't
Token't
Feature activation+2.312
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
presumptive
Token presumptive
Feature activation+0.000
resumed
Token resumed
Feature activation+0.000
their
Token their
Feature activation+0.000
hunger
Token hunger
Feature activation+0.000
strike
Token strike
Feature activation+0.000
,
Token,
Feature activation+0.000
demanding
Token demanding
Feature activation+2.134
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
California
Token California
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
Draft
Token Draft
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+2.197
same
Token same
Feature activation+1.817
traits
Token traits
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
him
Token him
Feature activation+0.000

INTERVAL 1.775 - 2.071
CONTAINS 0.001%

developer
Token developer
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
One
TokenOne
Feature activation+1.927
of
Token of
Feature activation+2.020
my
Token my
Feature activation+1.901
favorite
Token favorite
Feature activation+0.000
things
Token things
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
activists
Token activists
Feature activation+0.000
are
Token are
Feature activation+0.000
unwilling
Token unwilling
Feature activation+0.000
to
Token to
Feature activation+0.970
cross
Token cross
Feature activation+2.058
to
Token to
Feature activation+0.000
inflict
Token inflict
Feature activation+0.000
damage
Token damage
Feature activation+0.000
on
Token on
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
her
Token her
Feature activation+0.000
interests
Token interests
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
those
Token those
Feature activation+1.883
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
mon
Token mon
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
elite
Token elite
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
Draft
Token Draft
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+2.197
same
Token same
Feature activation+1.817
traits
Token traits
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+0.000
him
Token him
Feature activation+0.000
one
Token one
Feature activation+0.000
indie
Token indie
Feature activation+0.000
developer
Token developer
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
One
TokenOne
Feature activation+1.927
of
Token of
Feature activation+2.020
my
Token my
Feature activation+1.901
favorite
Token favorite
Feature activation+0.000
things
Token things
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 1.479 - 1.775
CONTAINS 0.002%

explore
Token explore
Feature activation+0.000
boundaries
Token boundaries
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
push
Token push
Feature activation+0.121
them
Token them
Feature activation+1.520
forward
Token forward
Feature activation+0.160
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
's
Token's
Feature activation+0.000
make
Token make
Feature activation+0.318
idently
Tokenidently
Feature activation+0.000
nationalist
Token nationalist
Feature activation+0.000
views
Token views
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
reflect
Token reflect
Feature activation+0.930
those
Token those
Feature activation+1.602
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
central
Token central
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.000
do
Token do
Feature activation+0.247
you
Token you
Feature activation+0.000
care
Token care
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
preserve
Token preserve
Feature activation+1.750
them
Token them
Feature activation+0.000
here
Token here
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
and
Token and
Feature activation+0.000
provide
Token provide
Feature activation+0.000
early
Token early
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
for
Token for
Feature activation+1.514
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
minim
Token minim
Feature activation+0.000
ally
Tokenally
Feature activation+0.032
reflective
Token reflective
Feature activation+0.000
and
Token and
Feature activation+0.000
people
Token people
Feature activation+0.000
will
Token will
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.875
carry
Token carry
Feature activation+1.578
on
Token on
Feature activation+0.209
having
Token having
Feature activation+0.335
them
Token them
Feature activation+0.308
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.011

INTERVAL 1.184 - 1.479
CONTAINS 0.005%

which
Token which
Feature activation+0.872
you
Token you
Feature activation+0.384
seek
Token seek
Feature activation+1.111
to
Token to
Feature activation+0.997
bring
Token bring
Feature activation+1.386
them
Token them
Feature activation+1.267
to
Token to
Feature activation+0.795
pass
Token pass
Feature activation+0.221
can
Token can
Feature activation+0.086
put
Token put
Feature activation+0.709
you
Token you
Feature activation+0.000
values
Token values
Feature activation+0.000
."
Token."
Feature activation+0.000
Rel
TokenRel
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
those
Token those
Feature activation+1.906
undeniable
Token undeniable
Feature activation+1.473
rights
Token rights
Feature activation+0.000
to
Token to
Feature activation+0.000
tech
Token tech
Feature activation+0.000
,
Token,
Feature activation+0.000
Cook
Token Cook
Feature activation+0.000
-
Token-
Feature activation+0.000
opp
Tokenopp
Feature activation+0.000
ressive
Tokenressive
Feature activation+0.000
organizing
Token organizing
Feature activation+0.000
must
Token must
Feature activation+0.000
dismantle
Token dismantle
Feature activation+1.389
the
Token the
Feature activation+0.444
ongoing
Token ongoing
Feature activation+0.000
colonization
Token colonization
Feature activation+0.000
of
Token of
Feature activation+0.000
Turtle
Token Turtle
Feature activation+0.000
The
Token The
Feature activation+0.000
targets
Token targets
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.553
hit
Token hit
Feature activation+1.244
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
require
Token require
Feature activation+0.000
and
Token and
Feature activation+0.000
shows
Token shows
Feature activation+0.000
a
Token a
Feature activation+0.000
fundamental
Token fundamental
Feature activation+0.000
disrespect
Token disrespect
Feature activation+0.000
for
Token for
Feature activation+1.311
human
Token human
Feature activation+0.075
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.888 - 1.184
CONTAINS 0.009%

on
Token on
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
tam
Token tam
Feature activation+0.000
per
Tokenper
Feature activation+0.004
with
Token with
Feature activation+1.171
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
she
Token she
Feature activation+0.000
lifted
Token lifted
Feature activation+0.953
them
Token them
Feature activation+0.000
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
and
Token and
Feature activation+0.000
rights
Token rights
Feature activation+0.000
,
Token,
Feature activation+0.000
do
Token do
Feature activation+0.000
we
Token we
Feature activation+0.000
infring
Token infring
Feature activation+0.000
e
Tokene
Feature activation+1.182
commercial
Token commercial
Feature activation+0.000
rights
Token rights
Feature activation+0.000
for
Token for
Feature activation+0.000
folks
Token folks
Feature activation+0.000
?"
Token?"
Feature activation+0.000
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
from
Token from
Feature activation+0.000
those
Token those
Feature activation+0.000
closed
Token closed
Feature activation+1.083
loopholes
Token loopholes
Feature activation+0.000
to
Token to
Feature activation+0.000
invest
Token invest
Feature activation+0.000
in
Token in
Feature activation+0.000
things
Token things
Feature activation+0.000
could
Token could
Feature activation+0.000
even
Token even
Feature activation+0.000
speak
Token speak
Feature activation+1.037
.
Token.
Feature activation+0.015
I
Token I
Feature activation+0.000
believed
Token believed
Feature activation+1.175
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
church
Token church
Feature activation+0.000
taught
Token taught
Feature activation+0.000

INTERVAL 0.592 - 0.888
CONTAINS 0.028%

is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
operator
Token operator
Feature activation+0.000
that
Token that
Feature activation+0.000
takes
Token takes
Feature activation+0.310
an
Token an
Feature activation+0.616
oper
Token oper
Feature activation+0.000
and
Tokenand
Feature activation+0.000
and
Token and
Feature activation+0.000
returns
Token returns
Feature activation+0.170
undefined
Token undefined
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.195
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
see
Token see
Feature activation+0.600
them
Token them
Feature activation+0.000
here
Token here
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
must
Token must
Feature activation+0.000
now
Token now
Feature activation+0.000
exempt
Token exempt
Feature activation+0.000
from
Token from
Feature activation+0.692
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
part
Token part
Feature activation+0.795
of
Token of
Feature activation+1.251
the
Token the
Feature activation+0.675
Oath
Token Oath
Feature activation+0.000
of
Token of
Feature activation+0.000
Alleg
Token Alleg
Feature activation+0.000
If
Token If
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
what
Token what
Feature activation+0.653
are
Token are
Feature activation+1.162
they
Token they
Feature activation+0.770
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ter
TokenTer
Feature activation+0.000
i
Tokeni
Feature activation+0.000
're
Token're
Feature activation+0.000
still
Token still
Feature activation+0.000
required
Token required
Feature activation+0.000
to
Token to
Feature activation+0.000
adhere
Token adhere
Feature activation+0.000
to
Token to
Feature activation+0.655
the
Token the
Feature activation+0.354
strict
Token strict
Feature activation+0.109
data
Token data
Feature activation+0.000
regulations
Token regulations
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.296 - 0.592
CONTAINS 0.085%

family
Token family
Feature activation+0.000
or
Token or
Feature activation+0.000
church
Token church
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
shared
Token shared
Feature activation+0.416
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.032
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
congressional
Token congressional
Feature activation+0.000
aides
Token aides
Feature activation+0.000
leaked
Token leaked
Feature activation+0.611
false
Token false
Feature activation+0.367
versions
Token versions
Feature activation+0.000
of
Token of
Feature activation+0.551
the
Token the
Feature activation+0.000
inter
Token inter
Feature activation+0.000
agency
Tokenagency
Feature activation+0.000
emails
Token emails
Feature activation+0.000
and
Token and
Feature activation+0.000
these
Token these
Feature activation+0.626
models
Token models
Feature activation+0.000
to
Token to
Feature activation+0.000
choose
Token choose
Feature activation+0.369
the
Token the
Feature activation+0.064
best
Token best
Feature activation+0.513
pricing
Token pricing
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
came
Token came
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+0.000
charged
Token charged
Feature activation+0.000
me
Token me
Feature activation+0.000
with
Token with
Feature activation+0.383
animal
Token animal
Feature activation+0.000
cruelty
Token cruelty
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
really
Token really
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
northern
Token northern
Feature activation+0.000
landscape
Token landscape
Feature activation+0.000
.
Token.
Feature activation+0.542
Some
Token Some
Feature activation+0.317
are
Token are
Feature activation+0.000
actually
Token actually
Feature activation+0.000
founded
Token founded
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.296
CONTAINS 99.870%

a
Token a
Feature activation+0.000
Character
Token Character
Feature activation+0.000
would
Token would
Feature activation+0.000
allow
Token allow
Feature activation+0.000
the
Token the
Feature activation+0.000
player
Token player
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.000
character
Token character
Feature activation+0.000
rank
Token rank
Feature activation+0.000
:
Token:
Feature activation+0.000
Good
Token Good
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Greens
Token Greens
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
,
Token,
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
on
Token on
Feature activation+0.000
Sw
Token Sw
Feature activation+0.000
ope
Tokenope
Feature activation+0.000
Park
Token Park
Feature activation+0.000
Rangers
Token Rangers
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
USL
Token USL
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
Finals
Token Finals
Feature activation+0.000
-
Token-
Feature activation+0.000
minute
Tokenminute
Feature activation+0.000
video
Token video
Feature activation+0.000
of
Token of
Feature activation+0.000
producer
Token producer
Feature activation+0.000
Rick
Token Rick
Feature activation+0.000
Rubin
Token Rubin
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
studio
Token studio
Feature activation+0.000
with
Token with
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
13
Token13
Feature activation+0.000
.
Token.
Feature activation+0.000
Definitely
Token Definitely
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
wants
Token wants
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H8.3: (feature 11310)

TOP ACTIVATIONS
MAX = 2.355

was
Token was
Feature activation+0.000
compelled
Token compelled
Feature activation+0.000
to
Token to
Feature activation+0.638
turn
Token turn
Feature activation+1.150
over
Token over
Feature activation+1.322
the
Token the
Feature activation+2.355
video
Token video
Feature activation+0.206
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Food
Token Food
Feature activation+0.000
&
Token &
Feature activation+0.000
Commercial
Token Commercial
Feature activation+0.000
Workers
Token Workers
Feature activation+0.000
union
Token union
Feature activation+0.000
.
Token.
Feature activation+2.222
Target
Token Target
Feature activation+0.000
was
Token was
Feature activation+0.000
compelled
Token compelled
Feature activation+0.000
to
Token to
Feature activation+0.638
turn
Token turn
Feature activation+1.150
matching
Token matching
Feature activation+0.063
production
Token production
Feature activation+0.000
and
Token and
Feature activation+0.000
demand
Token demand
Feature activation+0.000
cycles
Token cycles
Feature activation+0.000
,
Token,
Feature activation+1.980
the
Token the
Feature activation+1.154
researchers
Token researchers
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
balance
Token balance
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
children
Token children
Feature activation+0.000
.
Token.
Feature activation+1.899
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
attack
Token attack
Feature activation+0.000
on
Token on
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
means
Token means
Feature activation+0.000
committee
Token committee
Feature activation+0.000
.
Token.
Feature activation+0.593
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.824
Unless
TokenUnless
Feature activation+0.011
Mr
Token Mr
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
is
Token is
Feature activation+0.430
granted
Token granted
Feature activation+0.370
be
Token be
Feature activation+0.000
measured
Token measured
Feature activation+0.000
in
Token in
Feature activation+0.552
minute
Token minute
Feature activation+0.000
detail
Token detail
Feature activation+0.000
.
Token.
Feature activation+1.815
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.227
an
Token an
Feature activation+0.152
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sh
TokenSh
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Alaska
Token Alaska
Feature activation+0.000
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
]
Token]
Feature activation+1.757
Fair
Token Fair
Feature activation+0.000
banks
Tokenbanks
Feature activation+0.524
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
smallest
Token smallest
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
.
Token.
Feature activation+1.738
Ċ
TokenĊ
Feature activation+0.211
Ċ
TokenĊ
Feature activation+1.752
You
TokenYou
Feature activation+0.355
must
Token must
Feature activation+0.000
consciously
Token consciously
Feature activation+0.000
decide
Token decide
Feature activation+0.000
to
Token to
Feature activation+0.000
apostles
Token apostles
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
.
Token.
Feature activation+1.738
Ċ
TokenĊ
Feature activation+0.211
Ċ
TokenĊ
Feature activation+1.752
You
TokenYou
Feature activation+0.355
must
Token must
Feature activation+0.000
consciously
Token consciously
Feature activation+0.000
said
Token said
Feature activation+0.288
.
Token.
Feature activation+0.455
Thousands
Token Thousands
Feature activation+0.000
turned
Token turned
Feature activation+0.000
out
Token out
Feature activation+0.000
for
Token for
Feature activation+1.731
the
Token the
Feature activation+1.584
speech
Token speech
Feature activation+0.132
"
Token "
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
fare
Token fare
Feature activation+0.000
.
Token.
Feature activation+1.198
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.730
The
TokenThe
Feature activation+1.224
Al
Token Al
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
aman
Tokenaman
Feature activation+0.383
law
Token law
Feature activation+0.000
to
Tokento
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
creators
Token creators
Feature activation+0.000
told
Token told
Feature activation+1.720
Torrent
Token Torrent
Feature activation+0.922
Fre
TokenFre
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.245
According
TokenAccording
Feature activation+0.144
to
Token to
Feature activation+0.545
police
Token police
Feature activation+0.000
investigators
Token investigators
Feature activation+0.115
,
Token,
Feature activation+1.694
Qu
Token Qu
Feature activation+0.361
is
Tokenis
Feature activation+0.000
pe
Tokenpe
Feature activation+0.211
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
directly
Token directly
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
rabbit
Token rabbit
Feature activation+0.000
.
Token.
Feature activation+1.683
However
Token However
Feature activation+0.078
,
Token,
Feature activation+0.723
as
Token as
Feature activation+0.000
with
Token with
Feature activation+0.136
all
Token all
Feature activation+0.000
critical
Token critical
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
against
Token against
Feature activation+0.000
unknown
Token unknown
Feature activation+0.000
threats
Token threats
Feature activation+0.000
.
Token.
Feature activation+1.681
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.863
Mario
TokenMario
Feature activation+0.241
Cohen
Token Cohen
Feature activation+0.000
,
Token,
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
released
Token released
Feature activation+0.895
an
Token an
Feature activation+0.444
explanatory
Token explanatory
Feature activation+0.000
teaser
Token teaser
Feature activation+0.022
for
Token for
Feature activation+1.673
2016
Token 2016
Feature activation+0.001
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.176
s
Tokens
Feature activation+0.518
âĢ
Token âĢ
Feature activation+0.000
hugely
Token hugely
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
.
Token.
Feature activation+1.051
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.112
The
TokenThe
Feature activation+1.588
policy
Token policy
Feature activation+0.848
is
Token is
Feature activation+0.413
protection
Token protection
Feature activation+0.106
ist
Tokenist
Feature activation+0.081
and
Token and
Feature activation+0.431
.
Token.
Feature activation+0.455
Thousands
Token Thousands
Feature activation+0.000
turned
Token turned
Feature activation+0.000
out
Token out
Feature activation+0.000
for
Token for
Feature activation+1.731
the
Token the
Feature activation+1.584
speech
Token speech
Feature activation+0.132
"
Token "
Feature activation+0.000
In
TokenIn
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
,
Token,
Feature activation+0.000
means
Token means
Feature activation+0.000
of
Token of
Feature activation+0.000
transportation
Token transportation
Feature activation+0.000
and
Token and
Feature activation+0.000
recreation
Token recreation
Feature activation+0.186
.
Token.
Feature activation+1.571
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.558
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.376
She
TokenShe
Feature activation+0.241
www
Token www
Feature activation+0.105
.
Token.
Feature activation+0.256
facebook
Tokenfacebook
Feature activation+0.089
.
Token.
Feature activation+0.366
com
Tokencom
Feature activation+0.293
/
Token/
Feature activation+1.562
as
Tokenas
Feature activation+0.605
am
Tokenam
Feature activation+0.079
news
Tokennews
Feature activation+0.000
,
Token ,
Feature activation+0.000
following
Token following
Feature activation+0.000

Top DFA by src position
MAX = 2.479

<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
Signature
Token Signature
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+2.346
Top resid features:
shown
Token shown
Feature activation+0.560
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
Valley
Token Valley
Feature activation-0.000
Top resid features:
Stream
Token Stream
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
Signature
Token Signature
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.096
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation-0.017
Top resid features:
was
Token was
Feature activation+2.479
Top resid features:
shown
Token shown
Feature activation+0.229
Top resid features:
to
Token to
Feature activation+0.050
Top resid features:
Valley
Token Valley
Feature activation+0.001
Top resid features:
Stream
Token Stream
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.002
Top resid features:
High
Token High
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+2.002
Top resid features:
the
Token the
Feature activation+0.503
Top resid features:
opposite
Token opposite
Feature activation+0.005
Top resid features:
effect
Token effect
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
often
Token often
Feature activation+0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.010
Top resid features:
T
TokenT
Feature activation-0.035
Top resid features:
TP
TokenTP
Feature activation+0.211
Top resid features:
is
Token is
Feature activation+1.564
Top resid features:
implicated
Token implicated
Feature activation+0.375
Top resid features:
in
Token in
Feature activation+0.287
Top resid features:
many
Token many
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
Pakistan
Token Pakistan
Feature activation-0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.026
Top resid features:
means
Token means
Feature activation+2.358
Top resid features:
committee
Token committee
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Unless
TokenUnless
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.007
Top resid features:
Ŀ
TokenĿ
Feature activation-0.032
Top resid features:
is
Token is
Feature activation+1.627
Top resid features:
,
Token,
Feature activation+0.212
Top resid features:
by
Token by
Feature activation+0.074
Top resid features:
definition
Token definition
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
a
Token a
Feature activation+0.183
Top resid features:
ID
TokenID
Feature activation-0.000
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
FA
Token FA
Feature activation-0.006
Top resid features:
I
TokenI
Feature activation-0.004
Top resid features:
)
Token)
Feature activation-0.013
Top resid features:
is
Token is
Feature activation+1.510
Top resid features:
a
Token a
Feature activation+0.635
Top resid features:
state
Token state
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
owned
Tokenowned
Feature activation+0.014
Top resid features:
public
Token public
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.009
Top resid features:
means
Token means
Feature activation+2.183
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Even
Token Even
Feature activation+0.005
Top resid features:
if
Token if
Feature activation+0.016
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
desires
Token desires
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.004
Top resid features:
means
Token means
Feature activation+2.263
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Even
Token Even
Feature activation+0.001
Top resid features:
if
Token if
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
desires
Token desires
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.031
Top resid features:
21
Token 21
Feature activation-0.004
Top resid features:
st
Tokenst
Feature activation-0.000
Top resid features:
has
Token has
Feature activation+1.996
Top resid features:
revealed
Token revealed
Feature activation+0.115
Top resid features:
a
Token a
Feature activation+0.079
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
more
Token more
Feature activation-0.001
Top resid features:
intertwined
Token intertwined
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.012
Top resid features:
refers
Token refers
Feature activation+1.828
Top resid features:
to
Token to
Feature activation+0.172
Top resid features:
âĢ
Token âĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.003
Top resid features:
season
Tokenseason
Feature activation+0.035
Top resid features:
ed
Tokened
Feature activation+0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
ak
Tokenak
Feature activation-0.001
Top resid features:
reported
Token reported
Feature activation+2.294
Top resid features:
on
Token on
Feature activation+0.081
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
anonymous
Token anonymous
Feature activation+0.011
Top resid features:
creators
Token creators
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.015
Top resid features:
is
Tokenis
Feature activation+0.297
Top resid features:
pe
Tokenpe
Feature activation+0.085
Top resid features:
is
Token is
Feature activation+1.043
Top resid features:
a
Token a
Feature activation+0.591
Top resid features:
master
Token master
Feature activation+0.019
Top resid features:
counterfe
Token counterfe
Feature activation+0.014
Top resid features:
iter
Tokeniter
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.118
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.012
Top resid features:
means
Token means
Feature activation+2.152
Top resid features:
it
Token it
Feature activation+0.064
Top resid features:
will
Token will
Feature activation+0.043
Top resid features:
not
Token not
Feature activation+0.018
Top resid features:
burn
Token burn
Feature activation+0.028
Top resid features:
your
Token your
Feature activation-0.019
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.001
Top resid features:
ta
Tokenta
Feature activation-0.036
Top resid features:
Ray
TokenRay
Feature activation+0.289
Top resid features:
is
Token is
Feature activation+1.284
Top resid features:
the
Token the
Feature activation+0.643
Top resid features:
leading
Token leading
Feature activation+0.011
Top resid features:
provider
Token provider
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.031
Top resid features:
opia
Tokenopia
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.195
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
is
Token is
Feature activation+1.809
Top resid features:
no
Token no
Feature activation+0.019
Top resid features:
exception
Token exception
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.021
Top resid features:
eliminated
Token eliminated
Feature activation+0.289
Top resid features:
has
Token has
Feature activation+0.850
Top resid features:
been
Token been
Feature activation+0.666
Top resid features:
hugely
Token hugely
Feature activation+0.112
Top resid features:
controversial
Token controversial
Feature activation+0.108
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.028
Top resid features:
21
Token 21
Feature activation-0.003
Top resid features:
st
Tokenst
Feature activation+0.028
Top resid features:
has
Token has
Feature activation+1.746
Top resid features:
revealed
Token revealed
Feature activation+0.135
Top resid features:
a
Token a
Feature activation+0.098
Top resid features:
world
Token world
Feature activation-0.004
Top resid features:
more
Token more
Feature activation-0.005
Top resid features:
intertwined
Token intertwined
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.016
Top resid features:
means
Token means
Feature activation+2.046
Top resid features:
of
Token of
Feature activation+0.091
Top resid features:
transportation
Token transportation
Feature activation-0.005
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
recreation
Token recreation
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
As
TokenAs
Feature activation-0.001
Top resid features:
Am
TokenAm
Feature activation+0.188
Top resid features:
News
TokenNews
Feature activation+0.048
Top resid features:
is
Token is
Feature activation+1.012
Top resid features:
an
Token an
Feature activation+0.918
Top resid features:
all
Token all
Feature activation+0.014
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
vol
Tokenvol
Feature activation-0.001
Top resid features:
unte
Tokenunte
Feature activation-0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.07

Head 3: 0.46

Head 4: 0.02

Head 5: 0.04

Head 6: 0.03

Head 7: 0.03

Head 8: 0.05

Head 9: 0.06

Head 10: 0.10

Head 11: 0.07

Positive logits

の�2.29

AST2.20

Anon2.12

understatement2.04

2.04

Reincarnated1.95

Rite1.93

mk1.89

1.88

Proof1.87

localization1.85

Origin1.83

Alternative1.80

FORM1.79

«1.79

citation1.79

Trace1.79

Accessory1.79

Offline1.78

Unicode1.78

Negative logits

enegger-2.81

terness-2.48

MRI-2.29

////////////////-2.26

erity-2.20

iets-2.14

tern-2.12

leans-2.09

rices-2.08

mar-2.07

roller-2.04

gru-2.00

ardo-1.94

ffff-1.94

psey-1.93

idav-1.93

rique-1.92

cius-1.91

erness-1.89

zag-1.88

INTERVAL 2.120 - 2.355
CONTAINS 0.000%

Food
Token Food
Feature activation+0.000
&
Token &
Feature activation+0.000
Commercial
Token Commercial
Feature activation+0.000
Workers
Token Workers
Feature activation+0.000
union
Token union
Feature activation+0.000
.
Token.
Feature activation+2.222
Target
Token Target
Feature activation+0.000
was
Token was
Feature activation+0.000
compelled
Token compelled
Feature activation+0.000
to
Token to
Feature activation+0.638
turn
Token turn
Feature activation+1.150
was
Token was
Feature activation+0.000
compelled
Token compelled
Feature activation+0.000
to
Token to
Feature activation+0.638
turn
Token turn
Feature activation+1.150
over
Token over
Feature activation+1.322
the
Token the
Feature activation+2.355
video
Token video
Feature activation+0.206
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.884 - 2.120
CONTAINS 0.000%

matching
Token matching
Feature activation+0.063
production
Token production
Feature activation+0.000
and
Token and
Feature activation+0.000
demand
Token demand
Feature activation+0.000
cycles
Token cycles
Feature activation+0.000
,
Token,
Feature activation+1.980
the
Token the
Feature activation+1.154
researchers
Token researchers
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
balance
Token balance
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
children
Token children
Feature activation+0.000
.
Token.
Feature activation+1.899
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
attack
Token attack
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 1.649 - 1.884
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
means
Token means
Feature activation+0.000
committee
Token committee
Feature activation+0.000
.
Token.
Feature activation+0.593
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.824
Unless
TokenUnless
Feature activation+0.011
Mr
Token Mr
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
is
Token is
Feature activation+0.430
granted
Token granted
Feature activation+0.370
be
Token be
Feature activation+0.000
measured
Token measured
Feature activation+0.000
in
Token in
Feature activation+0.552
minute
Token minute
Feature activation+0.000
detail
Token detail
Feature activation+0.000
.
Token.
Feature activation+1.815
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.227
an
Token an
Feature activation+0.152
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sh
TokenSh
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
.
Token.
Feature activation+1.738
Ċ
TokenĊ
Feature activation+0.211
Ċ
TokenĊ
Feature activation+1.752
You
TokenYou
Feature activation+0.355
must
Token must
Feature activation+0.000
consciously
Token consciously
Feature activation+0.000
decide
Token decide
Feature activation+0.000
to
Token to
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
fare
Token fare
Feature activation+0.000
.
Token.
Feature activation+1.198
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.730
The
TokenThe
Feature activation+1.224
Al
Token Al
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
aman
Tokenaman
Feature activation+0.383
law
Token law
Feature activation+0.000
to
Tokento
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
creators
Token creators
Feature activation+0.000
told
Token told
Feature activation+1.720
Torrent
Token Torrent
Feature activation+0.922
Fre
TokenFre
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.413 - 1.649
CONTAINS 0.002%

transportation
Token transportation
Feature activation+0.000
and
Token and
Feature activation+0.000
recreation
Token recreation
Feature activation+0.186
.
Token.
Feature activation+1.571
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.558
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.376
She
TokenShe
Feature activation+0.241
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
NL
Token NL
Feature activation+0.000
RB
TokenRB
Feature activation+0.000
found
Token found
Feature activation+1.517
sufficient
Token sufficient
Feature activation+0.000
wrongdoing
Token wrongdoing
Feature activation+0.000
by
Token by
Feature activation+0.451
Target
Token Target
Feature activation+0.000
to
Token to
Feature activation+0.000
our
Token our
Feature activation+0.000
bones
Token bones
Feature activation+0.000
.
Token.
Feature activation+1.153
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.280
About
TokenAbout
Feature activation+1.431
Tech
Token Tech
Feature activation+0.600
T
TokenT
Feature activation+0.000
alks
Tokenalks
Feature activation+0.000
:
Token:
Feature activation+0.186
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
Director
Token Director
Feature activation+0.000
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
Intelligence
Token Intelligence
Feature activation+0.000
.
Token.
Feature activation+1.430
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.749
Be
TokenBe
Feature activation+0.000
a
Token a
Feature activation+0.000
hero
Token hero
Feature activation+0.000
650
Token 650
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
outpatient
Token outpatient
Feature activation+0.000
visits
Token visits
Feature activation+0.000
.
Token.
Feature activation+1.497
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.555
VC
TokenVC
Feature activation+0.000
U
TokenU
Feature activation+0.000
officials
Token officials
Feature activation+0.000

INTERVAL 1.178 - 1.413
CONTAINS 0.005%

of
Token of
Feature activation+0.110
heart
Token heart
Feature activation+0.000
disease
Token disease
Feature activation+0.000
,
Token,
Feature activation+0.000
suggests
Token suggests
Feature activation+1.127
that
Token that
Feature activation+1.257
alcohol
Token alcohol
Feature activation+0.000
may
Token may
Feature activation+0.099
even
Token even
Feature activation+0.225
provide
Token provide
Feature activation+0.000
some
Token some
Feature activation+0.000
see
Token see
Feature activation+0.000
how
Token how
Feature activation+0.250
many
Token many
Feature activation+0.076
parts
Token parts
Feature activation+0.668
make
Token make
Feature activation+0.000
up
Token up
Feature activation+1.313
the
Token the
Feature activation+0.781
component
Token component
Feature activation+0.061
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
of
Token of
Feature activation+0.000
war
Token war
Feature activation+0.000
.
Token.
Feature activation+0.887
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.961
The
TokenThe
Feature activation+1.183
Crit
Token Crit
Feature activation+0.000
erion
Tokenerion
Feature activation+0.000
Collection
Token Collection
Feature activation+0.020
Blu
Token Blu
Feature activation+0.000
-
Token-
Feature activation+0.000
Board
Token Board
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
of
Token of
Feature activation+1.225
alleged
Token alleged
Feature activation+0.140
illegal
Token illegal
Feature activation+0.000
union
Token union
Feature activation+0.000
-
Token-
Feature activation+0.000
b
Tokenb
Feature activation+0.000
but
Token but
Feature activation+1.082
seriously
Token seriously
Feature activation+0.409
,
Token,
Feature activation+1.137
DON
Token DON
Feature activation+0.125
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.339
T
TokenT
Feature activation+0.543
P
Token P
Feature activation+0.100
EE
TokenEE
Feature activation+0.264
IN
Token IN
Feature activation+0.313
THE
Token THE
Feature activation+0.182

INTERVAL 0.942 - 1.178
CONTAINS 0.010%

hits
Token hits
Feature activation+0.000
market
Token market
Feature activation+0.000
shelves
Token shelves
Feature activation+0.000
.
Token.
Feature activation+0.555
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.131
Direct
TokenDirect
Feature activation+0.000
channels
Token channels
Feature activation+0.114
also
Token also
Feature activation+0.154
allow
Token allow
Feature activation+0.714
farmers
Token farmers
Feature activation+0.000
and
Token and
Feature activation+0.000
technology
Token technology
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
bones
Token bones
Feature activation+0.000
.
Token.
Feature activation+1.153
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.280
About
TokenAbout
Feature activation+1.431
Tech
Token Tech
Feature activation+0.600
T
TokenT
Feature activation+0.000
objectives
Token objectives
Feature activation+0.373
you
Token you
Feature activation+0.069
have
Token have
Feature activation+0.041
are
Token are
Feature activation+0.573
righteous
Token righteous
Feature activation+0.000
,
Token,
Feature activation+0.974
the
Token the
Feature activation+0.416
means
Token means
Feature activation+0.000
by
Token by
Feature activation+0.203
which
Token which
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
e
Tokene
Feature activation+0.000
.
Token.
Feature activation+0.018
women
Token women
Feature activation+0.000
),
Token),
Feature activation+0.427
but
Token but
Feature activation+1.163
their
Token their
Feature activation+0.179
reach
Token reach
Feature activation+0.000
and
Token and
Feature activation+0.000
influence
Token influence
Feature activation+0.000
can
Token can
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+1.099
Any
Token Any
Feature activation+0.000
time
Token time
Feature activation+0.000
someone
Token someone
Feature activation+0.000
says
Token says
Feature activation+0.942
"
Token "
Feature activation+1.366

INTERVAL 0.707 - 0.942
CONTAINS 0.029%

of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
guardian
Token guardian
Feature activation+0.000
.
Token.
Feature activation+0.401
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.883
L
TokenL
Feature activation+0.000
aws
Tokenaws
Feature activation+0.526
in
Token in
Feature activation+0.243
the
Token the
Feature activation+0.295
kingdom
Token kingdom
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
lead
Token lead
Feature activation+0.000
.
Token.
Feature activation+1.185
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.741
The
TokenThe
Feature activation+0.005
gap
Token gap
Feature activation+0.000
balloon
Token balloon
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
instruments
Token instruments
Feature activation+0.000
between
Token between
Feature activation+0.000
every
Token every
Feature activation+0.000
song
Token song
Feature activation+0.000
.
Token.
Feature activation+0.766
Everything
TokenEverything
Feature activation+0.053
felt
Token felt
Feature activation+0.000
live
Token live
Feature activation+0.000
and
Token and
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
against
Token against
Feature activation+0.000
unknown
Token unknown
Feature activation+0.000
threats
Token threats
Feature activation+0.000
.
Token.
Feature activation+1.681
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.863
Mario
TokenMario
Feature activation+0.241
Cohen
Token Cohen
Feature activation+0.000
,
Token,
Feature activation+0.000
Sales
Token Sales
Feature activation+0.000
Director
Token Director
Feature activation+0.000
The
Token The
Feature activation+0.663
state
Token state
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
general
Token general
Feature activation+0.000
settled
Token settled
Feature activation+0.721
the
Token the
Feature activation+0.918
case
Token case
Feature activation+0.000
with
Token with
Feature activation+0.000
C
Token C
Feature activation+0.000
MD
TokenMD
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.471 - 0.707
CONTAINS 0.073%

.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
immigration
Token immigration
Feature activation+0.000
officials
Token officials
Feature activation+0.000
say
Token say
Feature activation+0.646
the
Token the
Feature activation+0.674
crisis
Token crisis
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
driven
Token driven
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.402
Title
TokenTitle
Feature activation+0.000
Page
Token Page
Feature activation+0.000
-
Token -
Feature activation+0.000
What
Token What
Feature activation+0.556
is
Token is
Feature activation+0.546
Ant
Token Ant
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atter
Tokenatter
Feature activation+0.059
?
Token?
Feature activation+0.137
-
Token -
Feature activation+0.000
a
Token a
Feature activation+0.020
named
Token named
Feature activation+0.205
lifetime
Token lifetime
Feature activation+0.000
parameter
Token parameter
Feature activation+0.194
,
Token,
Feature activation+0.341
and
Token and
Feature activation+0.492
it
Token it
Feature activation+0.000
says
Token says
Feature activation+0.278
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.235
opened
Token opened
Feature activation+0.000
doors
Token doors
Feature activation+0.000
to
Token to
Feature activation+0.000
concerts
Token concerts
Feature activation+0.000
abroad
Token abroad
Feature activation+0.000
.
Token.
Feature activation+0.561
In
Token In
Feature activation+0.000
1991
Token 1991
Feature activation+0.000
K
Token K
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
version
Token version
Feature activation+0.000
is
Token is
Feature activation+0.000
already
Token already
Feature activation+0.000
installed
Token installed
Feature activation+0.000
will
Token will
Feature activation+0.408
be
Token be
Feature activation+0.483
installed
Token installed
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
remaining
Token remaining
Feature activation+0.000
specified
Token specified
Feature activation+0.000

INTERVAL 0.236 - 0.471
CONTAINS 0.223%

to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.224
people
Token people
Feature activation+0.000
that
Token that
Feature activation+0.525
statistics
Token statistics
Feature activation+0.000
proving
Token proving
Feature activation+0.281
the
Token the
Feature activation+0.095
war
Token war
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
has
Token has
Feature activation+0.000
perceptions
Token perceptions
Feature activation+0.000
formerly
Token formerly
Feature activation+0.000
were
Token were
Feature activation+0.000
held
Token held
Feature activation+0.000
about
Token about
Feature activation+0.596
the
Token the
Feature activation+0.241
Pac
Token Pac
Feature activation+0.000
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.000
--
Token --
Feature activation+0.000
fines
Token fines
Feature activation+0.000
.[
Token.[
Feature activation+0.000
10
Token10
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.145
The
TokenThe
Feature activation+0.266
length
Token length
Feature activation+0.000
of
Token of
Feature activation+0.097
the
Token the
Feature activation+0.165
adult
Token adult
Feature activation+0.031
human
Token human
Feature activation+0.059
Ċ
TokenĊ
Feature activation+0.167
There
TokenThere
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.236
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
boils
Token boils
Feature activation+0.000
down
Token down
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
were
Token were
Feature activation+0.000
losing
Token losing
Feature activation+0.000
entire
Token entire
Feature activation+0.000
communities
Token communities
Feature activation+0.000
to
Token to
Feature activation+0.276
UKIP
Token UKIP
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.744
I
Token I
Feature activation+0.000
questioned
Token questioned
Feature activation+0.412
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.236
CONTAINS 99.658%

most
Token most
Feature activation+0.000
players
Token players
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.000
even
Token even
Feature activation+0.000
have
Token have
Feature activation+0.000
thought
Token thought
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
best
Token best
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ign
TokenIgn
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ance
Tokenance
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ign
TokenIgn
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ance
Tokenance
Feature activation+0.000
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
these
Token these
Feature activation+0.000
days
Token days
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
might
Token might
Feature activation+0.000
like
Token like
Feature activation+0.000
of
Token of
Feature activation+0.000
firefighters
Token firefighters
Feature activation+0.000
..."
Token..."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
more
Token more
Feature activation+0.000
at
Token at
Feature activation+0.000
http
Token http
Feature activation+0.000
://
Token://
Feature activation+0.000
www
Tokenwww
Feature activation+0.000
In
Token In
Feature activation+0.000
18
Token 18
Feature activation+0.000
53
Token53
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
attained
Token attained
Feature activation+0.000
the
Token the
Feature activation+0.000
prestigious
Token prestigious
Feature activation+0.000
appointment
Token appointment
Feature activation+0.000
of
Token of
Feature activation+0.000
Professor
Token Professor
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H8.3: (feature 7150)

TOP ACTIVATIONS
MAX = 2.167

","
Token","
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.123
460
Token460
Feature activation+0.218
,"
Token,"
Feature activation+2.167
small
Tokensmall
Feature activation+1.481
Height
TokenHeight
Feature activation+0.000
":
Token":
Feature activation+0.000
345
Token345
Feature activation+0.000
,"
Token,"
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
teams
Token teams
Feature activation+0.000
stay
Token stay
Feature activation+1.376
good
Token good
Feature activation+0.129
.
Token.
Feature activation+1.994
Bad
Token Bad
Feature activation+0.157
teams
Token teams
Feature activation+0.021
stay
Token stay
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
taken
Token taken
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
;
Token;
Feature activation+1.914
too
Token too
Feature activation+0.511
proper
Token proper
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+0.000
real
Token real
Feature activation+0.000
place
Token place
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
of
Token of
Feature activation+0.000
called
Token called
Feature activation+1.889
M
Token M
Feature activation+0.226
uddy
Tokenuddy
Feature activation+0.000
Bottom
Token Bottom
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
matching
Token matching
Feature activation+0.076
production
Token production
Feature activation+0.000
and
Token and
Feature activation+0.000
demand
Token demand
Feature activation+0.000
cycles
Token cycles
Feature activation+0.000
,
Token,
Feature activation+1.808
the
Token the
Feature activation+0.944
researchers
Token researchers
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
balance
Token balance
Feature activation+0.000
weak
Token weak
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
<
Token <
Feature activation+0.000
boost
Tokenboost
Feature activation+0.000
/
Token/
Feature activation+1.748
weak
Tokenweak
Feature activation+0.011
_
Token_
Feature activation+0.232
ptr
Tokenptr
Feature activation+0.000
.
Token.
Feature activation+0.000
h
Tokenh
Feature activation+0.000
the
Token the
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.517
of
Token of
Feature activation+0.924
fully
Token fully
Feature activation+0.590
strict
Token strict
Feature activation+0.108
to
Token to
Feature activation+1.738
mostly
Token mostly
Feature activation+1.495
lazy
Token lazy
Feature activation+0.000
.
Token.
Feature activation+1.182
With
Token With
Feature activation+0.545
regard
Token regard
Feature activation+0.044
practice
Token practice
Feature activation+0.000
of
Token of
Feature activation+0.000
regulating
Token regulating
Feature activation+0.000
it
Token it
Feature activation+0.000
little
Token little
Feature activation+0.000
by
Token by
Feature activation+1.655
little
Token little
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
unsure
Token unsure
Feature activation+0.000
if
Token if
Feature activation+0.030
your
Token your
Feature activation+0.000
use
Token use
Feature activation+0.000
qualifies
Token qualifies
Feature activation+0.000
as
Token as
Feature activation+1.574
fair
Token fair
Feature activation+0.000
use
Token use
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
strongly
Token strongly
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
damage
Token damage
Feature activation+0.000
of
Token of
Feature activation+1.551
being
Token being
Feature activation+1.203
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.221
it
Token it
Feature activation+0.000
least
Token least
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+1.547
great
Token great
Feature activation+0.000
running
Token running
Feature activation+0.000
play
Token play
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
l
Tokenl
Feature activation+0.000
isters
Tokenisters
Feature activation+0.000
can
Token can
Feature activation+0.000
sport
Token sport
Feature activation+1.536
longer
Token longer
Feature activation+0.922
t
Token t
Feature activation+0.000
resses
Tokenresses
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
ED
TokenED
Feature activation+0.000
v
Token v
Feature activation+0.000
3
Token3
Feature activation+0.000
Platinum
Token Platinum
Feature activation+0.000
-
Token-
Feature activation+0.000
designed
Tokendesigned
Feature activation+1.528
buildings
Token buildings
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
District
Token District
Feature activation+0.000
to
Token to
Feature activation+0.169
spectrum
Token spectrum
Feature activation+0.517
of
Token of
Feature activation+0.924
fully
Token fully
Feature activation+0.590
strict
Token strict
Feature activation+0.108
to
Token to
Feature activation+1.738
mostly
Token mostly
Feature activation+1.495
lazy
Token lazy
Feature activation+0.000
.
Token.
Feature activation+1.182
With
Token With
Feature activation+0.545
regard
Token regard
Feature activation+0.044
to
Token to
Feature activation+0.775
small
Tokensmall
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.123
460
Token460
Feature activation+0.218
,"
Token,"
Feature activation+2.167
small
Tokensmall
Feature activation+1.481
Height
TokenHeight
Feature activation+0.000
":
Token":
Feature activation+0.000
345
Token345
Feature activation+0.000
,"
Token,"
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
be
Token be
Feature activation+0.000
referenced
Token referenced
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
better
Token better
Feature activation+0.000
or
Token or
Feature activation+1.464
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Article
TokenArticle
Feature activation+0.000
,"
Token,"
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.000
760
Token760
Feature activation+0.153
,"
Token,"
Feature activation+1.434
big
Tokenbig
Feature activation+1.427
Height
TokenHeight
Feature activation+0.245
":
Token":
Feature activation+0.150
570
Token570
Feature activation+0.000
}
Token}
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.000
760
Token760
Feature activation+0.153
,"
Token,"
Feature activation+1.434
big
Tokenbig
Feature activation+1.427
Height
TokenHeight
Feature activation+0.245
":
Token":
Feature activation+0.150
570
Token570
Feature activation+0.000
}
Token}
Feature activation+0.000
2
Token 2
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
is
Token is
Feature activation+0.000
available
Token available
Feature activation+0.000
to
Token to
Feature activation+1.381
free
Token free
Feature activation+0.334
users
Token users
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
teams
Token teams
Feature activation+0.000
stay
Token stay
Feature activation+1.376
good
Token good
Feature activation+0.129
.
Token.
Feature activation+1.994
Bad
Token Bad
Feature activation+0.157
teams
Token teams
Feature activation+0.021
stay
Token stay
Feature activation+0.000

Top DFA by src position
MAX = 3.296

2
Token2
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
jpg
Tokenjpg
Feature activation-0.011
Top resid features:
","
Token","
Feature activation+0.003
Top resid features:
small
Tokensmall
Feature activation-0.179
Top resid features:
Width
TokenWidth
Feature activation+2.773
Top resid features:
":
Token":
Feature activation+0.103
Top resid features:
460
Token460
Feature activation+0.022
Top resid features:
,"
Token,"
Feature activation+0.033
Top resid features:
small
Tokensmall
Feature activation+0.000
Top resid features:
Height
TokenHeight
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
same
Token same
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Good
Token Good
Feature activation-0.591
Top resid features:
teams
Token teams
Feature activation+2.810
Top resid features:
stay
Token stay
Feature activation+0.093
Top resid features:
good
Token good
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.093
Top resid features:
Bad
Token Bad
Feature activation+0.000
Top resid features:
teams
Token teams
Feature activation+0.000
Top resid features:
Too
Token Too
Feature activation-0.239
Top resid features:
fl
Token fl
Feature activation+0.001
Top resid features:
irty
Tokenirty
Feature activation+0.086
Top resid features:
at
Token at
Feature activation+0.718
Top resid features:
work
Token work
Feature activation-0.021
Top resid features:
mean
Token mean
Feature activation+1.717
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
s
Tokens
Feature activation+0.038
Top resid features:
you
Token you
Feature activation+0.055
Top resid features:
won
Token won
Feature activation+0.007
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
like
Token like
Feature activation+0.001
Top resid features:
'
Token '
Feature activation+0.003
Top resid features:
M
TokenM
Feature activation+0.021
Top resid features:
uddy
Tokenuddy
Feature activation-0.006
Top resid features:
Bottom
Token Bottom
Feature activation+2.309
Top resid features:
,'
Token,'
Feature activation+0.020
Top resid features:
which
Token which
Feature activation+0.012
Top resid features:
was
Token was
Feature activation+0.008
Top resid features:
another
Token another
Feature activation+0.003
Top resid features:
single
Token single
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.102
Top resid features:
High
Token High
Feature activation-0.000
Top resid features:
has
Token has
Feature activation+2.046
Top resid features:
the
Token the
Feature activation+0.135
Top resid features:
opposite
Token opposite
Feature activation-0.001
Top resid features:
effect
Token effect
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
often
Token often
Feature activation+0.002
Top resid features:
h
Tokenh
Feature activation-0.001
Top resid features:
pp
Tokenpp
Feature activation+0.000
Top resid features:
>
Token>
Feature activation-0.007
Top resid features:
weak
Token weak
Feature activation+0.087
Top resid features:
_
Token_
Feature activation+0.500
Top resid features:
ptr
Tokenptr
Feature activation+0.845
Top resid features:
<
Token <
Feature activation+0.372
Top resid features:
boost
Tokenboost
Feature activation+0.032
Top resid features:
/
Token/
Feature activation+0.083
Top resid features:
weak
Tokenweak
Feature activation+0.000
Top resid features:
_
Token_
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
spectrum
Token spectrum
Feature activation-0.017
Top resid features:
of
Token of
Feature activation-0.017
Top resid features:
fully
Token fully
Feature activation-0.206
Top resid features:
strict
Token strict
Feature activation+1.807
Top resid features:
to
Token to
Feature activation+0.458
Top resid features:
mostly
Token mostly
Feature activation+0.000
Top resid features:
lazy
Token lazy
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:
practice
Token practice
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
regulating
Token regulating
Feature activation-0.005
Top resid features:
it
Token it
Feature activation-0.008
Top resid features:
little
Token little
Feature activation-0.158
Top resid features:
by
Token by
Feature activation+2.390
Top resid features:
little
Token little
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
videos
Token videos
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Fair
TokenFair
Feature activation+0.012
Top resid features:
use
Token use
Feature activation+2.046
Top resid features:
relies
Token relies
Feature activation+0.044
Top resid features:
on
Token on
Feature activation+0.022
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
complex
Token complex
Feature activation+0.001
Top resid features:
four
Token four
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Looking
TokenLooking
Feature activation-0.004
Top resid features:
taller
Token taller
Feature activation-0.074
Top resid features:
can
Token can
Feature activation+2.086
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
repair
Token repair
Feature activation+0.075
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
at
Token at
Feature activation-0.002
Top resid features:
least
Token least
Feature activation-0.033
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
good
Token good
Feature activation-0.266
Top resid features:
,
Token,
Feature activation+0.951
Top resid features:
if
Token if
Feature activation+1.481
Top resid features:
not
Token not
Feature activation+0.074
Top resid features:
great
Token great
Feature activation+0.000
Top resid features:
running
Token running
Feature activation+0.000
Top resid features:
play
Token play
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
might
Token might
Feature activation-0.000
Top resid features:
think
Token think
Feature activation-0.002
Top resid features:
that
Token that
Feature activation-0.004
Top resid features:
rocking
Token rocking
Feature activation+0.006
Top resid features:
long
Token long
Feature activation+0.033
Top resid features:
hair
Token hair
Feature activation+1.419
Top resid features:
isn
Token isn
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
t
Tokent
Feature activation+0.004
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
makers
Token makers
Feature activation+0.002
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
deep
Token deep
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
green
Tokengreen
Feature activation+0.002
Top resid features:
buildings
Token buildings
Feature activation+1.884
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
incentives
Token incentives
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Their
Token Their
Feature activation+0.000
Top resid features:
findings
Token findings
Feature activation-0.001
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
spectrum
Token spectrum
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
fully
Token fully
Feature activation-0.123
Top resid features:
strict
Token strict
Feature activation+1.070
Top resid features:
to
Token to
Feature activation+0.787
Top resid features:
mostly
Token mostly
Feature activation+0.023
Top resid features:
lazy
Token lazy
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:
2
Token2
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
jpg
Tokenjpg
Feature activation-0.005
Top resid features:
","
Token","
Feature activation-0.009
Top resid features:
small
Tokensmall
Feature activation-0.018
Top resid features:
Width
TokenWidth
Feature activation+1.944
Top resid features:
":
Token":
Feature activation+0.114
Top resid features:
460
Token460
Feature activation+0.037
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
small
Tokensmall
Feature activation+0.028
Top resid features:
Height
TokenHeight
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.007
Top resid features:
referenced
Token referenced
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
For
Token For
Feature activation-0.004
Top resid features:
better
Token better
Feature activation-1.259
Top resid features:
or
Token or
Feature activation+3.296
Top resid features:
worse
Token worse
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:
Article
TokenArticle
Feature activation+0.000
Top resid features:
Height
TokenHeight
Feature activation-0.025
Top resid features:
":
Token":
Feature activation+0.016
Top resid features:
345
Token345
Feature activation+0.014
Top resid features:
,"
Token,"
Feature activation+0.017
Top resid features:
big
Tokenbig
Feature activation-0.067
Top resid features:
Width
TokenWidth
Feature activation+1.345
Top resid features:
":
Token":
Feature activation+0.056
Top resid features:
760
Token760
Feature activation+0.004
Top resid features:
,"
Token,"
Feature activation+0.031
Top resid features:
big
Tokenbig
Feature activation+0.000
Top resid features:
Height
TokenHeight
Feature activation+0.000
Top resid features:
Height
TokenHeight
Feature activation-0.013
Top resid features:
":
Token":
Feature activation+0.011
Top resid features:
345
Token345
Feature activation+0.010
Top resid features:
,"
Token,"
Feature activation+0.009
Top resid features:
big
Tokenbig
Feature activation+0.050
Top resid features:
Width
TokenWidth
Feature activation+1.554
Top resid features:
":
Token":
Feature activation+0.029
Top resid features:
760
Token760
Feature activation+0.009
Top resid features:
,"
Token,"
Feature activation+0.011
Top resid features:
big
Tokenbig
Feature activation-0.034
Top resid features:
Height
TokenHeight
Feature activation+0.000
Top resid features:
available
Token available
Feature activation+0.005
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
premium
Token premium
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
free
Token free
Feature activation+0.021
Top resid features:
users
Token users
Feature activation+2.051
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
United
Token United
Feature activation-0.006
Top resid features:
States
Token States
Feature activation-0.017
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
are
Token are
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
same
Token same
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Good
Token Good
Feature activation+0.034
Top resid features:
teams
Token teams
Feature activation+1.726
Top resid features:
stay
Token stay
Feature activation+0.145
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Bad
Token Bad
Feature activation+0.000
Top resid features:
teams
Token teams
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.46

Head 4: 0.03

Head 5: 0.04

Head 6: 0.05

Head 7: 0.03

Head 8: 0.08

Head 9: 0.06

Head 10: 0.12

Head 11: 0.04

Positive logits

medium2.80

Medium2.70

softer2.66

brut2.53

soft2.52

lighter2.49

heavier2.42

hardness2.39

skinny2.37

Bold2.32

ordinary2.29

Medium2.26

heavy2.22

Soft2.20

ordinary2.19

plain2.19

bold2.18

whit2.18

Straw2.18

yellow2.15

Negative logits

ahime-2.67

artney-2.28

osponsors-2.26

Receiver-2.18

ospons-2.14

lia-2.12

mosqu-2.11

ssh-2.10

Animation-2.10

phia-2.09

aucuses-2.08

enhagen-2.08

EPA-2.06

-2.06

mpeg-2.05

ivan-2.05

HDMI-2.04

VPN-2.04

record-2.03

Accounts-2.02

INTERVAL 1.950 - 2.167
CONTAINS 0.000%

","
Token","
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.123
460
Token460
Feature activation+0.218
,"
Token,"
Feature activation+2.167
small
Tokensmall
Feature activation+1.481
Height
TokenHeight
Feature activation+0.000
":
Token":
Feature activation+0.000
345
Token345
Feature activation+0.000
,"
Token,"
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
teams
Token teams
Feature activation+0.000
stay
Token stay
Feature activation+1.376
good
Token good
Feature activation+0.129
.
Token.
Feature activation+1.994
Bad
Token Bad
Feature activation+0.157
teams
Token teams
Feature activation+0.021
stay
Token stay
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.734 - 1.950
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
taken
Token taken
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
;
Token;
Feature activation+1.914
too
Token too
Feature activation+0.511
proper
Token proper
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+0.000
the
Token the
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.517
of
Token of
Feature activation+0.924
fully
Token fully
Feature activation+0.590
strict
Token strict
Feature activation+0.108
to
Token to
Feature activation+1.738
mostly
Token mostly
Feature activation+1.495
lazy
Token lazy
Feature activation+0.000
.
Token.
Feature activation+1.182
With
Token With
Feature activation+0.545
regard
Token regard
Feature activation+0.044
matching
Token matching
Feature activation+0.076
production
Token production
Feature activation+0.000
and
Token and
Feature activation+0.000
demand
Token demand
Feature activation+0.000
cycles
Token cycles
Feature activation+0.000
,
Token,
Feature activation+1.808
the
Token the
Feature activation+0.944
researchers
Token researchers
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
balance
Token balance
Feature activation+0.000
weak
Token weak
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
<
Token <
Feature activation+0.000
boost
Tokenboost
Feature activation+0.000
/
Token/
Feature activation+1.748
weak
Tokenweak
Feature activation+0.011
_
Token_
Feature activation+0.232
ptr
Tokenptr
Feature activation+0.000
.
Token.
Feature activation+0.000
h
Tokenh
Feature activation+0.000
real
Token real
Feature activation+0.000
place
Token place
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
of
Token of
Feature activation+0.000
called
Token called
Feature activation+1.889
M
Token M
Feature activation+0.226
uddy
Tokenuddy
Feature activation+0.000
Bottom
Token Bottom
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 1.517 - 1.734
CONTAINS 0.001%

A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
l
Tokenl
Feature activation+0.000
isters
Tokenisters
Feature activation+0.000
can
Token can
Feature activation+0.000
sport
Token sport
Feature activation+1.536
longer
Token longer
Feature activation+0.922
t
Token t
Feature activation+0.000
resses
Tokenresses
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
ED
TokenED
Feature activation+0.000
v
Token v
Feature activation+0.000
3
Token3
Feature activation+0.000
Platinum
Token Platinum
Feature activation+0.000
-
Token-
Feature activation+0.000
designed
Tokendesigned
Feature activation+1.528
buildings
Token buildings
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
District
Token District
Feature activation+0.000
to
Token to
Feature activation+0.169
unsure
Token unsure
Feature activation+0.000
if
Token if
Feature activation+0.030
your
Token your
Feature activation+0.000
use
Token use
Feature activation+0.000
qualifies
Token qualifies
Feature activation+0.000
as
Token as
Feature activation+1.574
fair
Token fair
Feature activation+0.000
use
Token use
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
strongly
Token strongly
Feature activation+0.000
least
Token least
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+1.547
great
Token great
Feature activation+0.000
running
Token running
Feature activation+0.000
play
Token play
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
damage
Token damage
Feature activation+0.000
of
Token of
Feature activation+1.551
being
Token being
Feature activation+1.203
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.221
it
Token it
Feature activation+0.000

INTERVAL 1.300 - 1.517
CONTAINS 0.001%

ses
Tokenses
Feature activation+0.000
Plus
Token Plus
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Go
Token Go
Feature activation+0.079
to
Token to
Feature activation+0.726
The
Token The
Feature activation+1.327
Great
TokenGreat
Feature activation+0.000
C
TokenC
Feature activation+0.128
ourses
Tokenourses
Feature activation+0.000
Plus
TokenPlus
Feature activation+0.000
.
Token.
Feature activation+0.000
email
Token email
Feature activation+0.062
Subscribe
Token Subscribe
Feature activation+0.006
Thank
Token Thank
Feature activation+0.000
you
Token you
Feature activation+0.000
for
Token for
Feature activation+0.000
subscribing
Token subscribing
Feature activation+1.327
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.068
newsletters
Token newsletters
Feature activation+0.000
Show
Token Show
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.123
460
Token460
Feature activation+0.218
,"
Token,"
Feature activation+2.167
small
Tokensmall
Feature activation+1.481
Height
TokenHeight
Feature activation+0.000
":
Token":
Feature activation+0.000
345
Token345
Feature activation+0.000
,"
Token,"
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
output
Token output
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
positive
Token positive
Feature activation+0.000
or
Token or
Feature activation+1.368
negative
Token negative
Feature activation+0.000
number
Token number
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
signifies
Token signifies
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.517
of
Token of
Feature activation+0.924
fully
Token fully
Feature activation+0.590
strict
Token strict
Feature activation+0.108
to
Token to
Feature activation+1.738
mostly
Token mostly
Feature activation+1.495
lazy
Token lazy
Feature activation+0.000
.
Token.
Feature activation+1.182
With
Token With
Feature activation+0.545
regard
Token regard
Feature activation+0.044
to
Token to
Feature activation+0.775

INTERVAL 1.083 - 1.300
CONTAINS 0.003%

.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
with
Token with
Feature activation+0.000
this
Token this
Feature activation+0.000
graphic
Token graphic
Feature activation+0.000
.
Token.
Feature activation+1.267
strong
Tokenstrong
Feature activation+0.000
>
Token>
Feature activation+0.051
p
Tokenp
Feature activation+0.000
><
Token><
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
and
Token and
Feature activation+0.000
China
Token China
Feature activation+0.000
,
Token,
Feature activation+0.383
and
Token and
Feature activation+1.290
a
Token a
Feature activation+0.786
half
Token half
Feature activation+0.624
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.326
there
Token there
Feature activation+0.197
's
Token's
Feature activation+0.381
plenty
Token plenty
Feature activation+1.192
of
Token of
Feature activation+1.290
bad
Token bad
Feature activation+1.025
teams
Token teams
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
of
Token of
Feature activation+0.000
noteworthy
Token noteworthy
Feature activation+0.000
g
Token g
Feature activation+0.000
ents
Tokenents
Feature activation+0.000
with
Token with
Feature activation+1.080
long
Token long
Feature activation+1.270
locks
Token locks
Feature activation+0.000
is
Token is
Feature activation+0.000
bound
Token bound
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
on
Token on
Feature activation+0.000
what
Token what
Feature activation+0.000
your
Token your
Feature activation+0.000
definition
Token definition
Feature activation+0.000
of
Token of
Feature activation+0.813
"
Token "
Feature activation+1.123
free
Tokenfree
Feature activation+0.000
"
Token"
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.867 - 1.083
CONTAINS 0.006%

homes
Token homes
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
For
TokenFor
Feature activation+0.000
better
Token better
Feature activation+0.000
or
Token or
Feature activation+0.984
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
computation
Token computation
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.952
Most
Token Most
Feature activation+0.072
languages
Token languages
Feature activation+0.000
exist
Token exist
Feature activation+0.370
somewhere
Token somewhere
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.487
short
Token short
Feature activation+0.306
stories
Token stories
Feature activation+0.000
.
Token.
Feature activation+0.577
Some
Token Some
Feature activation+0.993
of
Token of
Feature activation+1.052
the
Token the
Feature activation+0.592
short
Token short
Feature activation+0.320
stories
Token stories
Feature activation+0.000
will
Token will
Feature activation+0.000
fast
Tokenfast
Feature activation+0.000
_
Token_
Feature activation+0.000
forward
Tokenforward
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
>
Token>
Feature activation+0.926
Fast
TokenFast
Feature activation+0.410
forward
Token forward
Feature activation+0.000
Token
Feature activation+0.000
string
Tokenstring
Feature activation+0.000
>
Token>
Feature activation+0.000
take
Token take
Feature activation+0.000
into
Token into
Feature activation+0.000
account
Token account
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.929
loud
Token loud
Feature activation+0.752
the
Token the
Feature activation+1.051
noise
Token noise
Feature activation+0.020
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.650 - 0.867
CONTAINS 0.011%

16
Token 16
Feature activation+0.000
,
Token,
Feature activation+0.055
New
Token New
Feature activation+0.000
Haven
Token Haven
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.674
Prime
TokenPrime
Feature activation+0.000
16
Token 16
Feature activation+0.000
,
Token,
Feature activation+0.106
Orange
Token Orange
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
misinterpret
Token misinterpret
Feature activation+0.000
an
Token an
Feature activation+0.000
airliner
Token airliner
Feature activation+0.000
at
Token at
Feature activation+0.739
such
Token such
Feature activation+0.189
height
Token height
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
threat
Token threat
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
invisible
Token invisible
Feature activation+0.000
.
Token.
Feature activation+0.793
Under
Token Under
Feature activation+0.027
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Token the
Feature activation+0.000
OS
Token OS
Feature activation+0.000
I
TokenI
Feature activation+0.000
's
Token's
Feature activation+0.000
definition
Token definition
Feature activation+0.000
of
Token of
Feature activation+0.832
open
Token open
Feature activation+0.000
source
Token source
Feature activation+0.000
software
Token software
Feature activation+0.000
is
Token is
Feature activation+0.009
âĢ
Token âĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
Dark
Token Dark
Feature activation+0.000
brown
Token brown
Feature activation+0.389
can
Token can
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.721
but
Token but
Feature activation+1.173
avoid
Token avoid
Feature activation+0.996
tan
Token tan
Feature activation+0.000
shoes
Token shoes
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.433 - 0.650
CONTAINS 0.026%

;
Token;
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
use
Token use
Feature activation+0.477
a
Token a
Feature activation+0.267
soft
Token soft
Feature activation+0.000
-
Token-
Feature activation+0.000
edged
Tokenedged
Feature activation+0.270
mask
Token mask
Feature activation+0.032
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
"
Token "
Feature activation+0.000
too
Tokentoo
Feature activation+0.000
little
Token little
Feature activation+0.000
,
Token,
Feature activation+0.535
too
Token too
Feature activation+0.000
late
Token late
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
could
Token could
Feature activation+0.000
also
Token also
Feature activation+0.000
reliably
Token reliably
Feature activation+0.000
achieve
Token achieve
Feature activation+0.153
very
Token very
Feature activation+0.217
good
Token good
Feature activation+0.456
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
two
Token two
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
believed
Token believed
Feature activation+0.000
proposing
Token proposing
Feature activation+0.110
to
Token to
Feature activation+0.073
rescind
Token rescind
Feature activation+0.034
the
Token the
Feature activation+0.035
2015
Token 2015
Feature activation+0.000
Clean
Token Clean
Feature activation+0.508
Water
Token Water
Feature activation+0.000
Rule
Token Rule
Feature activation+0.000
.
Token.
Feature activation+0.257
This
Token This
Feature activation+0.000
rule
Token rule
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tax
Token tax
Feature activation+0.000
code
Token code
Feature activation+0.000
that
Token that
Feature activation+0.000
treat
Token treat
Feature activation+0.556
legal
Token legal
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
as
Token as
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000

INTERVAL 0.217 - 0.433
CONTAINS 0.073%

LEG
Token LEG
Feature activation+0.000
IS
TokenIS
Feature activation+0.000
L
TokenL
Feature activation+0.000
ATION
TokenATION
Feature activation+0.000
Here
Token Here
Feature activation+0.000
are
Token are
Feature activation+0.294
highlights
Token highlights
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
unveiled
Token unveiled
Feature activation+0.000
the
Token the
Feature activation+0.000
rough
Token rough
Feature activation+0.000
ground
Token ground
Feature activation+0.000
was
Token was
Feature activation+0.297
unsu
Token unsu
Feature activation+0.000
itable
Tokenitable
Feature activation+0.316
for
Token for
Feature activation+0.000
char
Token char
Feature activation+0.000
iots
Tokeniots
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
peace
Token peace
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.219
want
Token want
Feature activation+0.363
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Mich
Token Mich
Feature activation+0.000
al
Tokenal
Feature activation+0.000
From
Token From
Feature activation+0.000
involved
Token involved
Feature activation+0.000
with
Token with
Feature activation+0.000
anything
Token anything
Feature activation+0.000
that
Token that
Feature activation+0.000
goes
Token goes
Feature activation+0.000
into
Token into
Feature activation+0.240
the
Token the
Feature activation+0.000
stands
Token stands
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
right
Token right
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.033
t
Tokent
Feature activation+0.373
apply
Token apply
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.013
kids
Token kids
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 0.000 - 0.217
CONTAINS 99.879%

33
Token33
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Non
Token Non
Feature activation+0.000
-
Token-
Feature activation+0.000
Kit
TokenKit
Feature activation+0.000
n
Tokenn
Feature activation+0.000
iy
Tokeniy
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
K
Token K
Feature activation+0.000
ed
Tokened
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
evident
Token evident
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
is
Token is
Feature activation+0.000
going
Token going
Feature activation+0.000
through
Token through
Feature activation+0.000
increased
Token increased
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
farm
Token farm
Feature activation+0.000
aci
Tokenaci
Feature activation+0.000
in
Token in
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
ili
Tokenili
Feature activation+0.000
La
Token La
Feature activation+0.000
tr
Token tr
Feature activation+0.000
uff
Tokenuff
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
settlement
Token settlement
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
companies
Token companies
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
similar
Token similar
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+0.000
have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
has
Token has
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
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