H3.1 top features

Top feature 0 in H3.1: (feature 11582)

TOP ACTIVATIONS
MAX = 5.215

have
Token have
Feature activation+2.453
besieged
Token besieged
Feature activation+1.404
a
Token a
Feature activation+1.274
rebel
Token rebel
Feature activation+1.006
district
Token district
Feature activation+0.176
and
Token and
Feature activation+5.215
offered
Token offered
Feature activation+0.272
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
between
Token between
Feature activation+0.285
starvation
Token starvation
Feature activation+0.000
either
Token either
Feature activation+0.000
rice
Token rice
Feature activation+0.000
agriculture
Token agriculture
Feature activation+1.262
spreading
Token spreading
Feature activation+0.369
north
Token north
Feature activation+0.596
and
Token and
Feature activation+4.983
encouraging
Token encouraging
Feature activation+0.000
mil
Token mil
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
domest
Token domest
Feature activation+0.000
ication
Tokenication
Feature activation+0.337
out
Token out
Feature activation+0.647
of
Token of
Feature activation+0.674
the
Token the
Feature activation+0.804
presidential
Token presidential
Feature activation+0.414
debates
Token debates
Feature activation+1.796
and
Token and
Feature activation+4.815
campaigns
Token campaigns
Feature activation+0.000
or
Token or
Feature activation+0.000
had
Token had
Feature activation+0.000
its
Token its
Feature activation+0.000
worst
Token worst
Feature activation+0.000
J
Token J
Feature activation+0.511
.
Token.
Feature activation+0.000
T
TokenT
Feature activation+0.102
.
Token.
Feature activation+0.000
Barrett
Token Barrett
Feature activation+0.849
and
Token and
Feature activation+4.370
Baker
Token Baker
Feature activation+0.000
May
Token May
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
either
Token either
Feature activation+0.000
natural
Token natural
Feature activation+1.390
gas
Token gas
Feature activation+1.231
for
Token for
Feature activation+1.523
auto
Token auto
Feature activation+0.000
and
Token and
Feature activation+4.345
truck
Token truck
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
or
Token or
Feature activation+0.000
to
Token to
Feature activation+0.000
produce
Token produce
Feature activation+0.000
either
Token either
Feature activation+0.000
close
Token close
Feature activation+0.000
enough
Token enough
Feature activation+1.806
to
Token to
Feature activation+0.229
clinch
Token clinch
Feature activation+0.211
and
Token and
Feature activation+3.912
avoid
Token avoid
Feature activation+0.029
strikes
Token strikes
Feature activation+0.000
or
Token or
Feature activation+0.000
far
Token far
Feature activation+0.000
enough
Token enough
Feature activation+0.000
participant
Token participant
Feature activation+0.000
will
Token will
Feature activation+0.000
cancel
Token cancel
Feature activation+0.464
the
Token the
Feature activation+0.778
brawl
Token brawl
Feature activation+0.492
and
Token and
Feature activation+3.624
may
Token may
Feature activation+0.000
cause
Token cause
Feature activation+0.000
the
Token the
Feature activation+0.000
opponent
Token opponent
Feature activation+0.000
to
Token to
Feature activation+0.000
straight
Token straight
Feature activation+0.690
or
Token or
Feature activation+0.000
gay
Token gay
Feature activation+0.023
is
Token is
Feature activation+0.000
pervasive
Token pervasive
Feature activation+0.262
and
Token and
Feature activation+3.304
persistent
Token persistent
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.000
sold
Token sold
Feature activation+1.147
delivered
Token delivered
Feature activation+1.582
,
Token,
Feature activation+3.087
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
..
Token..
Feature activation+0.000
in
Tokenin
Feature activation+0.000
which
Token which
Feature activation+0.000
families
Token families
Feature activation+0.000
either
Token either
Feature activation+0.000
choose
Token choose
Feature activation+1.951
to
Token to
Feature activation+0.151
travel
Token travel
Feature activation+2.186
abroad
Token abroad
Feature activation+2.788
during
Token during
Feature activation+0.813
holiday
Token holiday
Feature activation+0.423
season
Token season
Feature activation+0.293
or
Token or
Feature activation+0.000
spend
Token spend
Feature activation+0.000
share
Token share
Feature activation+0.000
of
Token of
Feature activation+0.000
renters
Token renters
Feature activation+0.000
paying
Token paying
Feature activation+0.000
more
Token more
Feature activation+0.455
than
Token than
Feature activation+2.673
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
is
Token is
Feature activation+0.000
significant
Token significant
Feature activation+0.000
of
Token of
Feature activation+0.000
poor
Token poor
Feature activation+0.000
people
Token people
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.009
slashed
Token slashed
Feature activation+2.662
or
Token or
Feature activation+0.000
eliminated
Token eliminated
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
overall
Token overall
Feature activation+0.000
-
Token -
Feature activation+0.000
either
Token either
Feature activation+0.004
for
Token for
Feature activation+0.594
security
Token security
Feature activation+2.579
forces
Token forces
Feature activation+1.486
,
Token,
Feature activation+1.265
civilians
Token civilians
Feature activation+1.223
or
Token or
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
two
Token two
Feature activation+0.000
contexts
Token contexts
Feature activation+0.000
:
Token:
Feature activation+0.000
either
Token either
Feature activation+0.000
regime
Token regime
Feature activation+0.856
forces
Token forces
Feature activation+2.566
have
Token have
Feature activation+2.453
besieged
Token besieged
Feature activation+1.404
a
Token a
Feature activation+1.274
rebel
Token rebel
Feature activation+1.006
district
Token district
Feature activation+0.176
filter
Token filter
Feature activation+0.551
the
Token the
Feature activation+1.078
table
Token table
Feature activation+0.077
by
Token by
Feature activation+0.773
the
Token the
Feature activation+0.772
most
Token most
Feature activation+2.514
recent
Token recent
Feature activation+1.367
month
Token month
Feature activation+0.045
or
Token or
Feature activation+0.000
click
Token click
Feature activation+0.000
the
Token the
Feature activation+0.107
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
either
Token either
Feature activation+0.000
this
Token this
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+2.478
thermal
Token thermal
Feature activation+0.238
printed
Token printed
Feature activation+0.181
or
Token or
Feature activation+0.012
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
contexts
Token contexts
Feature activation+0.000
:
Token:
Feature activation+0.000
either
Token either
Feature activation+0.000
regime
Token regime
Feature activation+0.856
forces
Token forces
Feature activation+2.566
have
Token have
Feature activation+2.453
besieged
Token besieged
Feature activation+1.404
a
Token a
Feature activation+1.274
rebel
Token rebel
Feature activation+1.006
district
Token district
Feature activation+0.176
and
Token and
Feature activation+5.215
ca
Tokenca
Feature activation+0.000
ask
Token ask
Feature activation+0.000
either
Token either
Feature activation+0.000
P
Token P
Feature activation+0.946
ian
Tokenian
Feature activation+0.000
O
TokenO
Feature activation+2.409
,
Token,
Feature activation+1.831
Zer
Token Zer
Feature activation+0.595
O
TokenO
Feature activation+0.976
or
Token or
Feature activation+0.000
free
Token free
Feature activation+0.000
chance
Token chance
Feature activation+0.000
either
Token either
Feature activation+0.000
side
Token side
Feature activation+0.000
will
Token will
Feature activation+0.000
relent
Token relent
Feature activation+0.044
and
Token and
Feature activation+2.335
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
step
Token step
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+0.930
would
Token would
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.000
held
Token held
Feature activation+0.692
on
Token on
Feature activation+1.425
22
Token 22
Feature activation+2.303
January
Token January
Feature activation+0.792
or
Token or
Feature activation+0.000
23
Token 23
Feature activation+0.000
April
Token April
Feature activation+0.000
2011
Token 2011
Feature activation+0.000

Top DFA by src position
MAX = 5.773

come
Token come
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
contexts
Token contexts
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.030
Top resid features:
either
Token either
Feature activation+5.773
Top resid features:
regime
Token regime
Feature activation+0.009
Top resid features:
forces
Token forces
Feature activation+0.013
Top resid features:
have
Token have
Feature activation+0.055
Top resid features:
besieged
Token besieged
Feature activation+0.105
Top resid features:
a
Token a
Feature activation-0.025
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
single
Token single
Feature activation+0.009
Top resid features:
origin
Token origin
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
with
Token with
Feature activation+0.025
Top resid features:
either
Token either
Feature activation+5.532
Top resid features:
rice
Token rice
Feature activation-0.002
Top resid features:
agriculture
Token agriculture
Feature activation+0.019
Top resid features:
spreading
Token spreading
Feature activation+0.074
Top resid features:
north
Token north
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
hugely
Token hugely
Feature activation-0.003
Top resid features:
important
Token important
Feature activation-0.004
Top resid features:
issue
Token issue
Feature activation-0.004
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
either
Token either
Feature activation+5.499
Top resid features:
left
Token left
Feature activation+0.043
Top resid features:
out
Token out
Feature activation+0.024
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
presidential
Token presidential
Feature activation-0.054
Top resid features:
Trophy
Token Trophy
Feature activation+0.001
Top resid features:
implications
Token implications
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.013
Top resid features:
this
Token this
Feature activation+0.004
Top resid features:
one
Token one
Feature activation+0.018
Top resid features:
either
Token either
Feature activation+4.806
Top resid features:
with
Token with
Feature activation+0.224
Top resid features:
quarterbacks
Token quarterbacks
Feature activation+0.063
Top resid features:
J
Token J
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
T
TokenT
Feature activation+0.022
Top resid features:
can
Token can
Feature activation+0.019
Top resid features:
then
Token then
Feature activation+0.011
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
used
Token used
Feature activation-0.000
Top resid features:
as
Token as
Feature activation-0.008
Top resid features:
either
Token either
Feature activation+4.758
Top resid features:
natural
Token natural
Feature activation+0.011
Top resid features:
gas
Token gas
Feature activation+0.039
Top resid features:
for
Token for
Feature activation+0.125
Top resid features:
auto
Token auto
Feature activation+0.104
Top resid features:
and
Token and
Feature activation+0.037
Top resid features:
way
Token way
Feature activation-0.001
Top resid features:
out
Token out
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
He
Token He
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
either
Token either
Feature activation+4.360
Top resid features:
close
Token close
Feature activation+0.023
Top resid features:
enough
Token enough
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.061
Top resid features:
clinch
Token clinch
Feature activation+0.149
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
Any
Token Any
Feature activation+0.055
Top resid features:
magic
Token magic
Feature activation+0.004
Top resid features:
effects
Token effects
Feature activation+0.005
Top resid features:
applied
Token applied
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
either
Token either
Feature activation+4.107
Top resid features:
participant
Token participant
Feature activation+0.020
Top resid features:
will
Token will
Feature activation+0.043
Top resid features:
cancel
Token cancel
Feature activation+0.152
Top resid features:
the
Token the
Feature activation+0.061
Top resid features:
brawl
Token brawl
Feature activation-0.047
Top resid features:
all
Token all
Feature activation-0.002
Top resid features:
people
Token people
Feature activation+0.003
Top resid features:
have
Token have
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
either
Token either
Feature activation+3.913
Top resid features:
straight
Token straight
Feature activation+0.022
Top resid features:
or
Token or
Feature activation+0.004
Top resid features:
gay
Token gay
Feature activation+0.011
Top resid features:
is
Token is
Feature activation-0.033
Top resid features:
pervasive
Token pervasive
Feature activation+0.166
Top resid features:
local
Token local
Feature activation+0.002
Top resid features:
papers
Token papers
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
It
Token It
Feature activation+0.004
Top resid features:
will
Token will
Feature activation+0.010
Top resid features:
either
Token either
Feature activation+3.565
Top resid features:
be
Token be
Feature activation+0.035
Top resid features:
sold
Token sold
Feature activation+0.031
Top resid features:
delivered
Token delivered
Feature activation+0.051
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
year
Token year
Feature activation-0.010
Top resid features:
when
Token when
Feature activation-0.006
Top resid features:
Australian
Token Australian
Feature activation+0.008
Top resid features:
families
Token families
Feature activation+0.024
Top resid features:
either
Token either
Feature activation+3.318
Top resid features:
choose
Token choose
Feature activation+0.059
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
travel
Token travel
Feature activation+0.119
Top resid features:
abroad
Token abroad
Feature activation-0.007
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
shelter
Token shelter
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Either
TokenEither
Feature activation+3.426
Top resid features:
way
Token way
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
share
Token share
Feature activation-0.019
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
growing
Token growing
Feature activation-0.000
Top resid features:
number
Token number
Feature activation-0.024
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
poor
Token poor
Feature activation+0.019
Top resid features:
people
Token people
Feature activation+0.001
Top resid features:
either
Token either
Feature activation+3.250
Top resid features:
be
Token be
Feature activation+0.052
Top resid features:
slashed
Token slashed
Feature activation+0.096
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
eliminated
Token eliminated
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Mosul
Token Mosul
Feature activation+0.003
Top resid features:
campaign
Token campaign
Feature activation+0.006
Top resid features:
overall
Token overall
Feature activation+0.007
Top resid features:
-
Token -
Feature activation+0.041
Top resid features:
either
Token either
Feature activation+3.133
Top resid features:
for
Token for
Feature activation+0.156
Top resid features:
security
Token security
Feature activation-0.045
Top resid features:
forces
Token forces
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
civilians
Token civilians
Feature activation+0.000
Top resid features:
come
Token come
Feature activation-0.010
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
two
Token two
Feature activation-0.006
Top resid features:
contexts
Token contexts
Feature activation+0.003
Top resid features:
:
Token:
Feature activation+0.079
Top resid features:
either
Token either
Feature activation+3.114
Top resid features:
regime
Token regime
Feature activation+0.001
Top resid features:
forces
Token forces
Feature activation+0.021
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
besieged
Token besieged
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
latest
Token latest
Feature activation-0.015
Top resid features:
releases
Token releases
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
you
Token you
Feature activation+0.035
Top resid features:
can
Token can
Feature activation+0.059
Top resid features:
either
Token either
Feature activation+2.957
Top resid features:
filter
Token filter
Feature activation+0.096
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
table
Token table
Feature activation+0.004
Top resid features:
by
Token by
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
image
Token image
Feature activation-0.005
Top resid features:
behind
Token behind
Feature activation-0.004
Top resid features:
it
Token it
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
So
Token So
Feature activation+0.075
Top resid features:
either
Token either
Feature activation+3.065
Top resid features:
this
Token this
Feature activation-0.054
Top resid features:
isn
Token isn
Feature activation+0.065
Top resid features:
't
Token't
Feature activation+0.011
Top resid features:
thermal
Token thermal
Feature activation+0.000
Top resid features:
printed
Token printed
Feature activation+0.000
Top resid features:
come
Token come
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+0.005
Top resid features:
contexts
Token contexts
Feature activation+0.005
Top resid features:
:
Token:
Feature activation+0.141
Top resid features:
either
Token either
Feature activation+2.912
Top resid features:
regime
Token regime
Feature activation+0.023
Top resid features:
forces
Token forces
Feature activation+0.022
Top resid features:
have
Token have
Feature activation+0.053
Top resid features:
besieged
Token besieged
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
Af
Token Af
Feature activation+0.001
Top resid features:
ree
Tokenree
Feature activation+0.001
Top resid features:
ca
Tokenca
Feature activation+0.007
Top resid features:
ask
Token ask
Feature activation-0.063
Top resid features:
either
Token either
Feature activation+3.086
Top resid features:
P
Token P
Feature activation-0.002
Top resid features:
ian
Tokenian
Feature activation+0.048
Top resid features:
O
TokenO
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Zer
Token Zer
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
There
Token There
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
no
Token no
Feature activation+0.027
Top resid features:
chance
Token chance
Feature activation+0.012
Top resid features:
either
Token either
Feature activation+2.961
Top resid features:
side
Token side
Feature activation+0.036
Top resid features:
will
Token will
Feature activation+0.002
Top resid features:
relent
Token relent
Feature activation+0.042
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.024
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
presidential
Token presidential
Feature activation-0.010
Top resid features:
poll
Token poll
Feature activation-0.042
Top resid features:
would
Token would
Feature activation+0.009
Top resid features:
either
Token either
Feature activation+2.868
Top resid features:
be
Token be
Feature activation+0.047
Top resid features:
held
Token held
Feature activation+0.024
Top resid features:
on
Token on
Feature activation+0.221
Top resid features:
22
Token 22
Feature activation-0.032
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.48

Head 2: 0.06

Head 3: 0.02

Head 4: 0.03

Head 5: 0.05

Head 6: 0.04

Head 7: 0.04

Head 8: 0.04

Head 9: 0.04

Head 10: 0.06

Head 11: 0.09

Positive logits

1.73

or1.71

1.61

}1.59

1.58

nor1.51

|1.51

ファ1.49

★★1.48

](1.39

*,1.38

*.1.37

?]1.35

acea1.32

istry1.31

ULAR1.30

¯¯¯¯¯¯¯¯1.30

ドラ1.29

---------1.29

1.28

Negative logits

itivity-1.52

ongyang-1.52

anmar-1.43

ramid-1.42

ielding-1.42

iosyncr-1.39

rero-1.39

merce-1.39

adena-1.38

condem-1.36

thodox-1.35

vu-1.35

proble-1.35

ancial-1.34

achev-1.34

Ez-1.34

ricane-1.33

uterte-1.33

eele-1.33

lower-1.32

INTERVAL 4.694 - 5.215
CONTAINS 0.000%

either
Token either
Feature activation+0.000
rice
Token rice
Feature activation+0.000
agriculture
Token agriculture
Feature activation+1.262
spreading
Token spreading
Feature activation+0.369
north
Token north
Feature activation+0.596
and
Token and
Feature activation+4.983
encouraging
Token encouraging
Feature activation+0.000
mil
Token mil
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
domest
Token domest
Feature activation+0.000
ication
Tokenication
Feature activation+0.337
have
Token have
Feature activation+2.453
besieged
Token besieged
Feature activation+1.404
a
Token a
Feature activation+1.274
rebel
Token rebel
Feature activation+1.006
district
Token district
Feature activation+0.176
and
Token and
Feature activation+5.215
offered
Token offered
Feature activation+0.272
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
between
Token between
Feature activation+0.285
starvation
Token starvation
Feature activation+0.000
out
Token out
Feature activation+0.647
of
Token of
Feature activation+0.674
the
Token the
Feature activation+0.804
presidential
Token presidential
Feature activation+0.414
debates
Token debates
Feature activation+1.796
and
Token and
Feature activation+4.815
campaigns
Token campaigns
Feature activation+0.000
or
Token or
Feature activation+0.000
had
Token had
Feature activation+0.000
its
Token its
Feature activation+0.000
worst
Token worst
Feature activation+0.000

INTERVAL 4.172 - 4.694
CONTAINS 0.000%

J
Token J
Feature activation+0.511
.
Token.
Feature activation+0.000
T
TokenT
Feature activation+0.102
.
Token.
Feature activation+0.000
Barrett
Token Barrett
Feature activation+0.849
and
Token and
Feature activation+4.370
Baker
Token Baker
Feature activation+0.000
May
Token May
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
either
Token either
Feature activation+0.000
natural
Token natural
Feature activation+1.390
gas
Token gas
Feature activation+1.231
for
Token for
Feature activation+1.523
auto
Token auto
Feature activation+0.000
and
Token and
Feature activation+4.345
truck
Token truck
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
or
Token or
Feature activation+0.000
to
Token to
Feature activation+0.000
produce
Token produce
Feature activation+0.000

INTERVAL 3.651 - 4.172
CONTAINS 0.000%

either
Token either
Feature activation+0.000
close
Token close
Feature activation+0.000
enough
Token enough
Feature activation+1.806
to
Token to
Feature activation+0.229
clinch
Token clinch
Feature activation+0.211
and
Token and
Feature activation+3.912
avoid
Token avoid
Feature activation+0.029
strikes
Token strikes
Feature activation+0.000
or
Token or
Feature activation+0.000
far
Token far
Feature activation+0.000
enough
Token enough
Feature activation+0.000

INTERVAL 3.129 - 3.651
CONTAINS 0.000%

participant
Token participant
Feature activation+0.000
will
Token will
Feature activation+0.000
cancel
Token cancel
Feature activation+0.464
the
Token the
Feature activation+0.778
brawl
Token brawl
Feature activation+0.492
and
Token and
Feature activation+3.624
may
Token may
Feature activation+0.000
cause
Token cause
Feature activation+0.000
the
Token the
Feature activation+0.000
opponent
Token opponent
Feature activation+0.000
to
Token to
Feature activation+0.000
straight
Token straight
Feature activation+0.690
or
Token or
Feature activation+0.000
gay
Token gay
Feature activation+0.023
is
Token is
Feature activation+0.000
pervasive
Token pervasive
Feature activation+0.262
and
Token and
Feature activation+3.304
persistent
Token persistent
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 2.608 - 3.129
CONTAINS 0.000%

of
Token of
Feature activation+0.000
poor
Token poor
Feature activation+0.000
people
Token people
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.009
slashed
Token slashed
Feature activation+2.662
or
Token or
Feature activation+0.000
eliminated
Token eliminated
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
will
Token will
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.000
sold
Token sold
Feature activation+1.147
delivered
Token delivered
Feature activation+1.582
,
Token,
Feature activation+3.087
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
..
Token..
Feature activation+0.000
in
Tokenin
Feature activation+0.000
which
Token which
Feature activation+0.000
families
Token families
Feature activation+0.000
either
Token either
Feature activation+0.000
choose
Token choose
Feature activation+1.951
to
Token to
Feature activation+0.151
travel
Token travel
Feature activation+2.186
abroad
Token abroad
Feature activation+2.788
during
Token during
Feature activation+0.813
holiday
Token holiday
Feature activation+0.423
season
Token season
Feature activation+0.293
or
Token or
Feature activation+0.000
spend
Token spend
Feature activation+0.000
share
Token share
Feature activation+0.000
of
Token of
Feature activation+0.000
renters
Token renters
Feature activation+0.000
paying
Token paying
Feature activation+0.000
more
Token more
Feature activation+0.455
than
Token than
Feature activation+2.673
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
is
Token is
Feature activation+0.000
significant
Token significant
Feature activation+0.000

INTERVAL 2.086 - 2.608
CONTAINS 0.002%

contexts
Token contexts
Feature activation+0.000
:
Token:
Feature activation+0.000
either
Token either
Feature activation+0.000
regime
Token regime
Feature activation+0.856
forces
Token forces
Feature activation+2.566
have
Token have
Feature activation+2.453
besieged
Token besieged
Feature activation+1.404
a
Token a
Feature activation+1.274
rebel
Token rebel
Feature activation+1.006
district
Token district
Feature activation+0.176
and
Token and
Feature activation+5.215
either
Token either
Feature activation+0.000
US
Token US
Feature activation+1.023
-
Token-
Feature activation+0.822
led
Tokenled
Feature activation+1.650
Coalition
Token Coalition
Feature activation+0.105
personnel
Token personnel
Feature activation+2.183
or
Token or
Feature activation+0.000
Iraqis
Token Iraqis
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
overall
Token overall
Feature activation+0.000
-
Token -
Feature activation+0.000
either
Token either
Feature activation+0.004
for
Token for
Feature activation+0.594
security
Token security
Feature activation+2.579
forces
Token forces
Feature activation+1.486
,
Token,
Feature activation+1.265
civilians
Token civilians
Feature activation+1.223
or
Token or
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
filter
Token filter
Feature activation+0.551
the
Token the
Feature activation+1.078
table
Token table
Feature activation+0.077
by
Token by
Feature activation+0.773
the
Token the
Feature activation+0.772
most
Token most
Feature activation+2.514
recent
Token recent
Feature activation+1.367
month
Token month
Feature activation+0.045
or
Token or
Feature activation+0.000
click
Token click
Feature activation+0.000
the
Token the
Feature activation+0.107
chance
Token chance
Feature activation+0.000
either
Token either
Feature activation+0.000
side
Token side
Feature activation+0.000
will
Token will
Feature activation+0.000
relent
Token relent
Feature activation+0.044
and
Token and
Feature activation+2.335
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
step
Token step
Feature activation+0.000
back
Token back
Feature activation+0.000
and
Token and
Feature activation+0.930

INTERVAL 1.565 - 2.086
CONTAINS 0.005%

that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
either
Token either
Feature activation+0.000
killed
Token killed
Feature activation+1.660
at
Token at
Feature activation+1.968
the
Token the
Feature activation+1.627
treatment
Token treatment
Feature activation+1.147
or
Token or
Feature activation+0.000
script
Token script
Feature activation+0.000
stage
Token stage
Feature activation+0.000
or
Token or
Feature activation+0.000
frustrated
Token frustrated
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
financial
Token financial
Feature activation+0.000
problems
Token problems
Feature activation+0.000
and
Token and
Feature activation+1.934
Forbes
Token Forbes
Feature activation+0.000
resigned
Token resigned
Feature activation+0.000
in
Token in
Feature activation+0.000
1971
Token 1971
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
either
Tokeneither
Feature activation+0.000
misc
Token misc
Feature activation+0.426
ari
Tokenari
Feature activation+0.042
age
Tokenage
Feature activation+1.139
,
Token,
Feature activation+1.729
or
Token or
Feature activation+0.000
a
Token a
Feature activation+0.000
phen
Token phen
Feature activation+0.000
otyp
Tokenotyp
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
will
Token will
Feature activation+0.000
qualify
Token qualify
Feature activation+0.000
either
Token either
Feature activation+0.000
for
Token for
Feature activation+0.687
Medicaid
Token Medicaid
Feature activation+1.724
âĢĶ
Token âĢĶ
Feature activation+2.002
the
Token the
Feature activation+0.613
public
Token public
Feature activation+0.000
health
Token health
Feature activation+0.000
program
Token program
Feature activation+0.079
that
Token that
Feature activation+0.000
things
Token things
Feature activation+0.000
are
Token are
Feature activation+0.000
either
Token either
Feature activation+0.000
never
Token never
Feature activation+1.788
stored
Token stored
Feature activation+1.356
,
Token,
Feature activation+1.838
or
Token or
Feature activation+0.000
deleted
Token deleted
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
close
Token close
Feature activation+0.000

INTERVAL 1.043 - 1.565
CONTAINS 0.007%

monopol
Token monopol
Feature activation+0.322
izing
Tokenizing
Feature activation+0.420
pillar
Token pillar
Feature activation+0.254
industries
Token industries
Feature activation+1.872
such
Token such
Feature activation+1.277
as
Token as
Feature activation+1.088
energy
Token energy
Feature activation+0.221
,
Token,
Feature activation+0.079
finance
Token finance
Feature activation+0.000
and
Token and
Feature activation+0.894
telecom
Token telecom
Feature activation+0.000
used
Token used
Feature activation+0.000
as
Token as
Feature activation+0.000
either
Token either
Feature activation+0.000
natural
Token natural
Feature activation+1.390
gas
Token gas
Feature activation+1.231
for
Token for
Feature activation+1.523
auto
Token auto
Feature activation+0.000
and
Token and
Feature activation+4.345
truck
Token truck
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+1.078
table
Token table
Feature activation+0.077
by
Token by
Feature activation+0.773
the
Token the
Feature activation+0.772
most
Token most
Feature activation+2.514
recent
Token recent
Feature activation+1.367
month
Token month
Feature activation+0.045
or
Token or
Feature activation+0.000
click
Token click
Feature activation+0.000
the
Token the
Feature activation+0.107
Release
Token Release
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
either
Token either
Feature activation+0.000
keep
Token keep
Feature activation+0.694
the
Token the
Feature activation+1.319
file
Token file
Feature activation+0.374
open
Token open
Feature activation+1.039
or
Token or
Feature activation+0.000
bring
Token bring
Feature activation+0.000
charges
Token charges
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Whether
TokenWhether
Feature activation+0.000
I
Token I
Feature activation+0.000
succeeded
Token succeeded
Feature activation+1.143
in
Token in
Feature activation+0.521
that
Token that
Feature activation+0.167
aspiration
Token aspiration
Feature activation+0.000
I
Token I
Feature activation+0.320
leave
Token leave
Feature activation+0.482

INTERVAL 0.522 - 1.043
CONTAINS 0.017%

United
Token United
Feature activation+0.000
Airlines
Token Airlines
Feature activation+0.000
and
Token and
Feature activation+1.192
American
Token American
Feature activation+0.000
Airlines
Token Airlines
Feature activation+0.000
and
Token and
Feature activation+0.810
other
Token other
Feature activation+0.000
trades
Token trades
Feature activation+0.000
indicate
Token indicate
Feature activation+0.000
fore
Token fore
Feature activation+0.000
knowledge
Tokenknowledge
Feature activation+0.000
by
Token by
Feature activation+0.738
having
Token having
Feature activation+0.331
to
Token to
Feature activation+0.040
develop
Token develop
Feature activation+1.353
special
Token special
Feature activation+0.867
hiring
Token hiring
Feature activation+0.565
packages
Token packages
Feature activation+1.120
,
Token,
Feature activation+1.899
or
Token or
Feature activation+0.000
subsid
Token subsid
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
deliberately
Token deliberately
Feature activation+0.000
withholding
Token withholding
Feature activation+0.952
food
Token food
Feature activation+0.306
,
Token,
Feature activation+0.953
shelter
Token shelter
Feature activation+0.226
,
Token,
Feature activation+0.682
or
Token or
Feature activation+0.000
medical
Token medical
Feature activation+0.000
assistance
Token assistance
Feature activation+0.000
from
Token from
Feature activation+0.000
people
Token people
Feature activation+0.000
either
Token either
Feature activation+0.000
filter
Token filter
Feature activation+0.551
the
Token the
Feature activation+1.078
table
Token table
Feature activation+0.077
by
Token by
Feature activation+0.773
the
Token the
Feature activation+0.772
most
Token most
Feature activation+2.514
recent
Token recent
Feature activation+1.367
month
Token month
Feature activation+0.045
or
Token or
Feature activation+0.000
click
Token click
Feature activation+0.000
ortun
Tokenortun
Feature activation+0.000
es
Tokenes
Feature activation+0.051
and
Token and
Feature activation+0.302
temporary
Token temporary
Feature activation+0.033
setbacks
Token setbacks
Feature activation+0.000
that
Token that
Feature activation+0.839
are
Token are
Feature activation+0.000
only
Token only
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
expected
Token expected
Feature activation+0.000

INTERVAL 0.000 - 0.522
CONTAINS 99.969%

in
Token in
Feature activation+0.000
Delhi
Token Delhi
Feature activation+0.000
and
Token and
Feature activation+0.000
added
Token added
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
am
Tokenam
Feature activation+0.000
Aad
Token Aad
Feature activation+0.000
mi
Tokenmi
Feature activation+0.000
Party
Token Party
Feature activation+0.000
with
Token with
Feature activation+0.000
laws
Token laws
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
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
then
Token then
Feature activation+0.000
explains
Token explains
Feature activation+0.000
:
Token:
Feature activation+0.000
onym
Tokenonym
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
has
Token has
Feature activation+0.000
long
Token long
Feature activation+0.000
been
Token been
Feature activation+0.000
hailed
Token hailed
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
founding
Token founding
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
also
Token also
Feature activation+0.000
reproduced
Token reproduced
Feature activation+0.000
Harrington
Token Harrington
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
own
Token own
Feature activation+0.000
panc
Token panc
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
green
Token green
Feature activation+0.000
technology
Token technology
Feature activation+0.000
.
Token.
Feature activation+0.000
Aw
Token Aw
Feature activation+0.000
es
Tokenes
Feature activation+0.000
omen
Tokenomen
Feature activation+0.000
ess
Tokeness
Feature activation+0.000
TV
TokenTV
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
Dream
Token Dream
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 H3.1: (feature 19734)

TOP ACTIVATIONS
MAX = 3.245

of
Token of
Feature activation+0.000
>
Token >
Feature activation+0.000
optimizations
Token optimizations
Feature activation+0.149
are
Token are
Feature activation+1.526
possible
Token possible
Feature activation+2.082
given
Token given
Feature activation+3.245
Haskell
Token Haskell
Feature activation+0.959
's
Token's
Feature activation+2.227
language
Token language
Feature activation+0.360
model
Token model
Feature activation+0.005
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
want
Token want
Feature activation+0.040
|
Token |
Feature activation+0.538
|
Token |
Feature activation+0.709
expect
Token expect
Feature activation+0.873
to
Token to
Feature activation+2.552
learn
Token learn
Feature activation+1.020
.
Token.
Feature activation+2.780
Some
Token Some
Feature activation+1.751
course
Token course
Feature activation+0.603
terminology
Token terminology
Feature activation+0.000
is
Token is
Feature activation+0.486
covered
Token covered
Feature activation+0.192
this
Token this
Feature activation+0.000
program
Token program
Feature activation+0.000
is
Token is
Feature activation+0.000
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.202
brief
Token brief
Feature activation+1.151
refres
Token refres
Feature activation+1.336
her
Tokenher
Feature activation+2.574
of
Token of
Feature activation+2.338
the
Token the
Feature activation+2.164
background
Token background
Feature activation+1.583
material
Token material
Feature activation+1.426
required
Token required
Feature activation+0.840
can
Token can
Feature activation+0.000
|
Token |
Feature activation+0.081
|
Token |
Feature activation+0.538
|
Token |
Feature activation+0.709
expect
Token expect
Feature activation+0.873
to
Token to
Feature activation+2.552
learn
Token learn
Feature activation+1.020
.
Token.
Feature activation+2.780
Some
Token Some
Feature activation+1.751
course
Token course
Feature activation+0.603
terminology
Token terminology
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
want
Token want
Feature activation+0.040
to
Token to
Feature activation+1.142
better
Token better
Feature activation+0.369
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
want
Token want
Feature activation+0.040
to
Token to
Feature activation+1.142
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
back
Tokenback
Feature activation+0.309
any
Token any
Feature activation+1.722
kinds
Token kinds
Feature activation+1.434
of
Token of
Feature activation+2.370
legislation
Token legislation
Feature activation+1.503
that
Token that
Feature activation+1.141
would
Token would
Feature activation+0.883
hinder
Token hinder
Feature activation+0.953
or
Token or
Feature activation+0.751
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.202
brief
Token brief
Feature activation+1.151
refres
Token refres
Feature activation+1.336
her
Tokenher
Feature activation+2.574
of
Token of
Feature activation+2.338
the
Token the
Feature activation+2.164
background
Token background
Feature activation+1.583
material
Token material
Feature activation+1.426
required
Token required
Feature activation+0.840
for
Token for
Feature activation+0.555
program
Token program
Feature activation+0.000
is
Token is
Feature activation+0.000
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
language
Token language
Feature activation+0.360
model
Token model
Feature activation+0.005
.
Token.
Feature activation+0.000
>
Token >
Feature activation+0.000
So
Token So
Feature activation+1.913
the
Token the
Feature activation+2.290
optimization
Token optimization
Feature activation+0.526
you
Token you
Feature activation+0.888
're
Token're
Feature activation+1.494
looking
Token looking
Feature activation+0.392
for
Token for
Feature activation+0.310
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
levels
Tokenlevels
Feature activation+0.000
that
Token that
Feature activation+0.444
would
Token would
Feature activation+1.762
be
Token be
Feature activation+2.273
required
Token required
Feature activation+1.969
to
Token to
Feature activation+2.030
induce
Token induce
Feature activation+1.751
a
Token a
Feature activation+1.669
massive
Token massive
Feature activation+0.562
,
Token,
Feature activation+1.146
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.037
you
Tokenyou
Feature activation+0.191
can
Token can
Feature activation+1.317
leave
Token leave
Feature activation+2.262
now
Token now
Feature activation+1.543
.
Token.
Feature activation+1.980
ok
Token ok
Feature activation+0.573
,
Token,
Feature activation+0.844
so
Token so
Feature activation+0.780
optimizations
Token optimizations
Feature activation+0.149
are
Token are
Feature activation+1.526
possible
Token possible
Feature activation+2.082
given
Token given
Feature activation+3.245
Haskell
Token Haskell
Feature activation+0.959
's
Token's
Feature activation+2.227
language
Token language
Feature activation+0.360
model
Token model
Feature activation+0.005
.
Token.
Feature activation+0.000
>
Token >
Feature activation+0.000
So
Token So
Feature activation+1.913
|
Token |
Feature activation+0.202
brief
Token brief
Feature activation+1.151
refres
Token refres
Feature activation+1.336
her
Tokenher
Feature activation+2.574
of
Token of
Feature activation+2.338
the
Token the
Feature activation+2.164
background
Token background
Feature activation+1.583
material
Token material
Feature activation+1.426
required
Token required
Feature activation+0.840
for
Token for
Feature activation+0.555
the
Token the
Feature activation+0.665
quite
Tokenquite
Feature activation+0.000
a
Token a
Feature activation+1.008
bit
Token bit
Feature activation+1.471
more
Token more
Feature activation+1.679
complicated
Token complicated
Feature activation+0.942
,
Token,
Feature activation+2.145
and
Token and
Feature activation+1.534
more
Token more
Feature activation+1.238
interesting
Token interesting
Feature activation+0.401
,
Token,
Feature activation+1.146
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
way
Tokenway
Feature activation+0.445
that
Token that
Feature activation+0.565
they
Token they
Feature activation+2.136
have
Token have
Feature activation+2.032
,
Token,
Feature activation+1.956
and
Token and
Feature activation+1.969
the
Token the
Feature activation+1.433
way
Token way
Feature activation+0.741
Ċ
TokenĊ
Feature activation+0.000
section
Tokensection
Feature activation+0.393
of
Token of
Feature activation+1.373
some
Token some
Feature activation+1.051
type
Token type
Feature activation+1.435
,
Token,
Feature activation+2.135
with
Token with
Feature activation+1.982
its
Token its
Feature activation+2.128
content
Token content
Feature activation+0.517
below
Token below
Feature activation+0.000
;
Token;
Feature activation+1.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fire
TokenFire
Feature activation+0.000
ball
Tokenball
Feature activation+0.380
as
Token as
Feature activation+1.142
a
Token a
Feature activation+2.134
progression
Token progression
Feature activation+1.227
into
Token into
Feature activation+0.928
a
Token a
Feature activation+1.055
more
Token more
Feature activation+0.811
organic
Token organic
Feature activation+0.465

Top DFA by src position
MAX = 3.948

better
Token better
Feature activation+0.020
Top resid features:
understand
Token understand
Feature activation-0.006
Top resid features:
what
Token what
Feature activation-0.021
Top resid features:
kind
Token kind
Feature activation-0.012
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
>
Token >
Feature activation+3.948
Top resid features:
optimizations
Token optimizations
Feature activation-0.055
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
possible
Token possible
Feature activation-0.183
Top resid features:
given
Token given
Feature activation-0.014
Top resid features:
Haskell
Token Haskell
Feature activation+0.000
Top resid features:
obvious
Token obvious
Feature activation-0.007
Top resid features:
this
Token this
Feature activation-0.002
Top resid features:
program
Token program
Feature activation-0.013
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
trivial
Token trivial
Feature activation-0.038
Top resid features:
>
Token >
Feature activation+3.864
Top resid features:
and
Token and
Feature activation-0.059
Top resid features:
takes
Token takes
Feature activation-0.094
Top resid features:
no
Token no
Feature activation-0.018
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.002
Top resid features:
students
Token students
Feature activation+0.007
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
|
Token |
Feature activation+0.824
Top resid features:
|
Token |
Feature activation+1.156
Top resid features:
|
Token |
Feature activation+1.373
Top resid features:
expect
Token expect
Feature activation+0.054
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
learn
Token learn
Feature activation-0.074
Top resid features:
.
Token.
Feature activation-0.079
Top resid features:
Some
Token Some
Feature activation+0.000
Top resid features:
obvious
Token obvious
Feature activation-0.010
Top resid features:
this
Token this
Feature activation-0.038
Top resid features:
program
Token program
Feature activation-0.040
Top resid features:
is
Token is
Feature activation-0.060
Top resid features:
trivial
Token trivial
Feature activation-0.104
Top resid features:
>
Token >
Feature activation+3.372
Top resid features:
and
Token and
Feature activation-0.047
Top resid features:
takes
Token takes
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
covered
Token covered
Feature activation+0.003
Top resid features:
along
Token along
Feature activation-0.005
Top resid features:
with
Token with
Feature activation-0.006
Top resid features:
a
Token a
Feature activation-0.015
Top resid features:
|
Token |
Feature activation+1.060
Top resid features:
|
Token |
Feature activation+1.040
Top resid features:
|
Token |
Feature activation+1.011
Top resid features:
brief
Token brief
Feature activation-0.015
Top resid features:
refres
Token refres
Feature activation-0.174
Top resid features:
her
Tokenher
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
what
Token what
Feature activation-0.036
Top resid features:
students
Token students
Feature activation+0.010
Top resid features:
can
Token can
Feature activation-0.009
Top resid features:
|
Token |
Feature activation+1.127
Top resid features:
|
Token |
Feature activation+1.022
Top resid features:
|
Token |
Feature activation+0.878
Top resid features:
expect
Token expect
Feature activation-0.066
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
learn
Token learn
Feature activation+0.000
Top resid features:
obvious
Token obvious
Feature activation-0.007
Top resid features:
this
Token this
Feature activation-0.009
Top resid features:
program
Token program
Feature activation-0.018
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
trivial
Token trivial
Feature activation-0.025
Top resid features:
>
Token >
Feature activation+3.397
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
takes
Token takes
Feature activation-0.016
Top resid features:
no
Token no
Feature activation-0.023
Top resid features:
time
Token time
Feature activation-0.049
Top resid features:
.
Token.
Feature activation-0.133
Top resid features:
obvious
Token obvious
Feature activation-0.006
Top resid features:
this
Token this
Feature activation-0.005
Top resid features:
program
Token program
Feature activation-0.017
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
trivial
Token trivial
Feature activation-0.027
Top resid features:
>
Token >
Feature activation+3.034
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
takes
Token takes
Feature activation-0.127
Top resid features:
no
Token no
Feature activation-0.059
Top resid features:
time
Token time
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.008
Top resid features:
successful
Token successful
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
beating
Token beating
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation+1.613
Top resid features:
Ċ
TokenĊ
Feature activation+1.114
Top resid features:
back
Tokenback
Feature activation-0.032
Top resid features:
any
Token any
Feature activation+0.018
Top resid features:
kinds
Token kinds
Feature activation-0.057
Top resid features:
of
Token of
Feature activation-0.019
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
covered
Token covered
Feature activation-0.000
Top resid features:
along
Token along
Feature activation-0.011
Top resid features:
with
Token with
Feature activation-0.004
Top resid features:
a
Token a
Feature activation-0.014
Top resid features:
|
Token |
Feature activation+1.155
Top resid features:
|
Token |
Feature activation+0.957
Top resid features:
|
Token |
Feature activation+0.784
Top resid features:
brief
Token brief
Feature activation+0.002
Top resid features:
refres
Token refres
Feature activation-0.096
Top resid features:
her
Tokenher
Feature activation-0.059
Top resid features:
obvious
Token obvious
Feature activation-0.008
Top resid features:
this
Token this
Feature activation-0.029
Top resid features:
program
Token program
Feature activation-0.077
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
trivial
Token trivial
Feature activation-0.036
Top resid features:
>
Token >
Feature activation+3.118
Top resid features:
and
Token and
Feature activation-0.237
Top resid features:
takes
Token takes
Feature activation-0.016
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Haskell
Token Haskell
Feature activation-0.010
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
language
Token language
Feature activation-0.005
Top resid features:
model
Token model
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.045
Top resid features:
>
Token >
Feature activation+2.846
Top resid features:
So
Token So
Feature activation-0.099
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
optimization
Token optimization
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
're
Token're
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
especially
Token especially
Feature activation+0.010
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+1.323
Top resid features:
Ċ
TokenĊ
Feature activation+1.360
Top resid features:
levels
Tokenlevels
Feature activation-0.014
Top resid features:
that
Token that
Feature activation-0.090
Top resid features:
would
Token would
Feature activation-0.052
Top resid features:
be
Token be
Feature activation+0.039
Top resid features:
required
Token required
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
more
Token more
Feature activation+0.020
Top resid features:
interesting
Token interesting
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+1.366
Top resid features:
Ċ
TokenĊ
Feature activation+1.091
Top resid features:
you
Tokenyou
Feature activation+0.013
Top resid features:
can
Token can
Feature activation-0.079
Top resid features:
leave
Token leave
Feature activation+0.033
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
better
Token better
Feature activation+0.005
Top resid features:
understand
Token understand
Feature activation-0.002
Top resid features:
what
Token what
Feature activation-0.003
Top resid features:
kind
Token kind
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
>
Token >
Feature activation+2.839
Top resid features:
optimizations
Token optimizations
Feature activation-0.016
Top resid features:
are
Token are
Feature activation+0.012
Top resid features:
possible
Token possible
Feature activation-0.031
Top resid features:
given
Token given
Feature activation-0.047
Top resid features:
Haskell
Token Haskell
Feature activation-0.162
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
covered
Token covered
Feature activation-0.002
Top resid features:
along
Token along
Feature activation-0.002
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
|
Token |
Feature activation+1.121
Top resid features:
|
Token |
Feature activation+0.881
Top resid features:
|
Token |
Feature activation+0.696
Top resid features:
brief
Token brief
Feature activation+0.002
Top resid features:
refres
Token refres
Feature activation-0.071
Top resid features:
her
Tokenher
Feature activation-0.064
Top resid features:
whole
Token whole
Feature activation+0.001
Top resid features:
story
Token story
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
which
Token which
Feature activation+0.003
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+1.573
Top resid features:
Ċ
TokenĊ
Feature activation+0.927
Top resid features:
quite
Tokenquite
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
bit
Token bit
Feature activation-0.014
Top resid features:
more
Token more
Feature activation+0.025
Top resid features:
public
Token public
Feature activation+0.014
Top resid features:
policy
Token policy
Feature activation-0.007
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+1.160
Top resid features:
Ċ
TokenĊ
Feature activation+1.358
Top resid features:
way
Tokenway
Feature activation-0.000
Top resid features:
that
Token that
Feature activation-0.058
Top resid features:
they
Token they
Feature activation-0.032
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
header
Token header
Feature activation+0.003
Top resid features:
announcing
Token announcing
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+1.368
Top resid features:
Ċ
TokenĊ
Feature activation+1.027
Top resid features:
section
Tokensection
Feature activation-0.005
Top resid features:
of
Token of
Feature activation-0.040
Top resid features:
some
Token some
Feature activation-0.039
Top resid features:
type
Token type
Feature activation+0.080
Top resid features:
recorded
Token recorded
Feature activation-0.035
Top resid features:
Um
Token Um
Feature activation-0.014
Top resid features:
ami
Tokenami
Feature activation-0.004
Top resid features:
Sound
Token Sound
Feature activation-0.004
Top resid features:
ing
Tokening
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+1.470
Top resid features:
Ċ
TokenĊ
Feature activation+1.171
Top resid features:
Fire
TokenFire
Feature activation-0.010
Top resid features:
ball
Tokenball
Feature activation-0.058
Top resid features:
as
Token as
Feature activation-0.088
Top resid features:
a
Token a
Feature activation+0.056
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.47

Head 2: 0.04

Head 3: 0.03

Head 4: 0.08

Head 5: 0.07

Head 6: 0.06

Head 7: 0.04

Head 8: 0.04

Head 9: 0.04

Head 10: 0.05

Head 11: 0.04

Positive logits

1.77

GOODMAN1.49

ゼウス1.43

1.41

eki1.40

COUN1.35

guiActiveUn1.35

CLSID1.33

anwhile1.27

Caption1.25

dding1.24

').1.22

senal1.22

]),1.20

'.1.18

Condition1.18

wcsstore1.17

],"1.16

Lauder1.16

rect1.16

Negative logits

"--1.45

"...-1.31

Unix-1.21

bats-1.20

Shank-1.19

,,-1.16

anan-1.15

recy-1.11

BELOW-1.10

Collins-1.10

unia-1.08

tart-1.07

Nissan-1.07

appro-1.07

—"-1.07

mash-1.06

toget-1.06

--------------1.05

@@-1.04

Moon-1.04

INTERVAL 2.920 - 3.245
CONTAINS 0.000%

is
Token is
Feature activation+0.000
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
want
Token want
Feature activation+0.040
of
Token of
Feature activation+0.000
>
Token >
Feature activation+0.000
optimizations
Token optimizations
Feature activation+0.149
are
Token are
Feature activation+1.526
possible
Token possible
Feature activation+2.082
given
Token given
Feature activation+3.245
Haskell
Token Haskell
Feature activation+0.959
's
Token's
Feature activation+2.227
language
Token language
Feature activation+0.360
model
Token model
Feature activation+0.005
.
Token.
Feature activation+0.000

INTERVAL 2.596 - 2.920
CONTAINS 0.000%

this
Token this
Feature activation+0.000
program
Token program
Feature activation+0.000
is
Token is
Feature activation+0.000
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
|
Token |
Feature activation+0.538
|
Token |
Feature activation+0.709
expect
Token expect
Feature activation+0.873
to
Token to
Feature activation+2.552
learn
Token learn
Feature activation+1.020
.
Token.
Feature activation+2.780
Some
Token Some
Feature activation+1.751
course
Token course
Feature activation+0.603
terminology
Token terminology
Feature activation+0.000
is
Token is
Feature activation+0.486
covered
Token covered
Feature activation+0.192

INTERVAL 2.271 - 2.596
CONTAINS 0.001%

language
Token language
Feature activation+0.360
model
Token model
Feature activation+0.005
.
Token.
Feature activation+0.000
>
Token >
Feature activation+0.000
So
Token So
Feature activation+1.913
the
Token the
Feature activation+2.290
optimization
Token optimization
Feature activation+0.526
you
Token you
Feature activation+0.888
're
Token're
Feature activation+1.494
looking
Token looking
Feature activation+0.392
for
Token for
Feature activation+0.310
program
Token program
Feature activation+0.000
is
Token is
Feature activation+0.000
trivial
Token trivial
Feature activation+0.000
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
>
Token >
Feature activation+0.000
and
Token and
Feature activation+2.677
takes
Token takes
Feature activation+2.321
no
Token no
Feature activation+3.177
time
Token time
Feature activation+2.428
.
Token.
Feature activation+2.461
I
Token I
Feature activation+2.034
just
Token just
Feature activation+1.190
want
Token want
Feature activation+0.040
to
Token to
Feature activation+1.142
better
Token better
Feature activation+0.369
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.202
brief
Token brief
Feature activation+1.151
refres
Token refres
Feature activation+1.336
her
Tokenher
Feature activation+2.574
of
Token of
Feature activation+2.338
the
Token the
Feature activation+2.164
background
Token background
Feature activation+1.583
material
Token material
Feature activation+1.426
required
Token required
Feature activation+0.840
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
levels
Tokenlevels
Feature activation+0.000
that
Token that
Feature activation+0.444
would
Token would
Feature activation+1.762
be
Token be
Feature activation+2.273
required
Token required
Feature activation+1.969
to
Token to
Feature activation+2.030
induce
Token induce
Feature activation+1.751
a
Token a
Feature activation+1.669
massive
Token massive
Feature activation+0.562

INTERVAL 1.947 - 2.271
CONTAINS 0.003%

way
Tokenway
Feature activation+0.445
that
Token that
Feature activation+0.565
they
Token they
Feature activation+2.136
have
Token have
Feature activation+2.032
,
Token,
Feature activation+1.956
and
Token and
Feature activation+1.969
the
Token the
Feature activation+1.433
way
Token way
Feature activation+0.741
that
Token that
Feature activation+0.270
they
Token they
Feature activation+0.423
've
Token've
Feature activation+0.448
Ċ
TokenĊ
Feature activation+0.000
in
Tokenin
Feature activation+0.563
a
Token a
Feature activation+2.009
very
Token very
Feature activation+2.069
compelling
Token compelling
Feature activation+0.777
example
Token example
Feature activation+2.035
of
Token of
Feature activation+1.280
input
Token input
Feature activation+0.394
/
Token/
Feature activation+0.000
output
Tokenoutput
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+1.373
some
Token some
Feature activation+1.051
type
Token type
Feature activation+1.435
,
Token,
Feature activation+2.135
with
Token with
Feature activation+1.982
its
Token its
Feature activation+2.128
content
Token content
Feature activation+0.517
below
Token below
Feature activation+0.000
;
Token;
Feature activation+1.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
way
Tokenway
Feature activation+0.445
that
Token that
Feature activation+0.565
they
Token they
Feature activation+2.136
have
Token have
Feature activation+2.032
,
Token,
Feature activation+1.956
and
Token and
Feature activation+1.969
the
Token the
Feature activation+1.433
way
Token way
Feature activation+0.741
that
Token that
Feature activation+0.270
they
Token they
Feature activation+0.423
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Tokenthat
Feature activation+0.318
you
Token you
Feature activation+1.816
will
Token will
Feature activation+1.358
never
Token never
Feature activation+2.019
ever
Token ever
Feature activation+2.051
see
Token see
Feature activation+1.185
in
Token in
Feature activation+1.575
the
Token the
Feature activation+1.647
real
Token real
Feature activation+1.995

INTERVAL 1.622 - 1.947
CONTAINS 0.002%

1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
42
Token42
Feature activation+0.011
at
Token at
Feature activation+0.777
the
Token the
Feature activation+1.662
same
Token same
Feature activation+1.764
time
Token time
Feature activation+1.821
?
Token?
Feature activation+0.731
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
42
Token42
Feature activation+0.011
at
Token at
Feature activation+0.777
the
Token the
Feature activation+1.662
same
Token same
Feature activation+1.764
time
Token time
Feature activation+1.821
?
Token?
Feature activation+0.731
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
containing
Token containing
Feature activation+1.213
no
Token no
Feature activation+1.000
content
Token content
Feature activation+0.755
underneath
Token underneath
Feature activation+0.387
it
Token it
Feature activation+1.156
.
Token.
Feature activation+1.706
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
some
Tokensome
Feature activation+0.000
cheat
Token cheat
Feature activation+0.563
will
Token will
Feature activation+1.358
never
Token never
Feature activation+2.019
ever
Token ever
Feature activation+2.051
see
Token see
Feature activation+1.185
in
Token in
Feature activation+1.575
the
Token the
Feature activation+1.647
real
Token real
Feature activation+1.995
world
Token world
Feature activation+1.447
.)
Token.)
Feature activation+1.764
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.151
beating
Token beating
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
back
Tokenback
Feature activation+0.309
any
Token any
Feature activation+1.722
kinds
Token kinds
Feature activation+1.434
of
Token of
Feature activation+2.370
legislation
Token legislation
Feature activation+1.503
that
Token that
Feature activation+1.141
would
Token would
Feature activation+0.883

INTERVAL 1.298 - 1.622
CONTAINS 0.005%

>
Token >
Feature activation+0.000
So
Token So
Feature activation+1.913
the
Token the
Feature activation+2.290
optimization
Token optimization
Feature activation+0.526
you
Token you
Feature activation+0.888
're
Token're
Feature activation+1.494
looking
Token looking
Feature activation+0.392
for
Token for
Feature activation+0.310
here
Token here
Feature activation+0.596
is
Token is
Feature activation+0.512
fusion
Token fusion
Feature activation+0.007
.
Token.
Feature activation+0.061
>
Token >
Feature activation+0.000
>
Token >
Feature activation+0.000
I
Token I
Feature activation+1.322
'm
Token'm
Feature activation+1.628
not
Token not
Feature activation+1.370
looking
Token looking
Feature activation+0.926
so
Token so
Feature activation+1.064
much
Token much
Feature activation+0.575
for
Token for
Feature activation+0.759
profiling
Token profiling
Feature activation+0.069
brief
Token brief
Feature activation+1.151
refres
Token refres
Feature activation+1.336
her
Tokenher
Feature activation+2.574
of
Token of
Feature activation+2.338
the
Token the
Feature activation+2.164
background
Token background
Feature activation+1.583
material
Token material
Feature activation+1.426
required
Token required
Feature activation+0.840
for
Token for
Feature activation+0.555
the
Token the
Feature activation+0.665
course
Token course
Feature activation+0.018
Ċ
TokenĊ
Feature activation+0.000
profit
Tokenprofit
Feature activation+0.810
ability
Tokenability
Feature activation+0.461
of
Token of
Feature activation+1.062
the
Token the
Feature activation+1.619
companies
Token companies
Feature activation+1.517
.
Token.
Feature activation+2.074
B
Token B
Feature activation+1.539
ILL
TokenILL
Feature activation+0.000
MO
Token MO
Feature activation+0.037
Y
TokenY
Feature activation+0.193
a
Token a
Feature activation+1.008
bit
Token bit
Feature activation+1.471
more
Token more
Feature activation+1.679
complicated
Token complicated
Feature activation+0.942
,
Token,
Feature activation+2.145
and
Token and
Feature activation+1.534
more
Token more
Feature activation+1.238
interesting
Token interesting
Feature activation+0.401
,
Token,
Feature activation+1.146
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.037

INTERVAL 0.973 - 1.298
CONTAINS 0.006%

|
Token |
Feature activation+0.081
|
Token |
Feature activation+0.538
|
Token |
Feature activation+0.709
expect
Token expect
Feature activation+0.873
to
Token to
Feature activation+2.552
learn
Token learn
Feature activation+1.020
.
Token.
Feature activation+2.780
Some
Token Some
Feature activation+1.751
course
Token course
Feature activation+0.603
terminology
Token terminology
Feature activation+0.000
is
Token is
Feature activation+0.486
ľ
Tokenľ
Feature activation+0.173
It
TokenIt
Feature activation+0.572
is
Token is
Feature activation+1.060
a
Token a
Feature activation+1.297
possibility
Token possibility
Feature activation+0.446
we
Token we
Feature activation+1.102
cannot
Token cannot
Feature activation+0.780
ignore
Token ignore
Feature activation+0.558
that
Token that
Feature activation+0.643
there
Token there
Feature activation+0.635
is
Token is
Feature activation+0.119
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
54
Token54
Feature activation+0.000
In
Token In
Feature activation+0.510
fact
Token fact
Feature activation+0.746
,
Token,
Feature activation+0.996
I
Token I
Feature activation+0.878
see
Token see
Feature activation+0.834
a
Token a
Feature activation+0.822
lot
Token lot
Feature activation+0.089
of
Token of
Feature activation+0.441
ATE
TokenATE
Feature activation+0.000
END
Token END
Feature activation+0.602
ORS
TokenORS
Feature activation+0.558
ER
TokenER
Feature activation+0.211
POS
Token POS
Feature activation+0.781
ITION
TokenITION
Feature activation+1.155
PTS
Token PTS
Feature activation+0.000
.
Token.
Feature activation+1.606
>>
Token >>
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.901
Clinton
Token Clinton
Feature activation+0.743
cause
Tokencause
Feature activation+0.000
()
Token()
Feature activation+0.000
`
Token`
Feature activation+0.000
//
Token //
Feature activation+0.000
syntax
Token syntax
Feature activation+0.807
is
Token is
Feature activation+1.083
not
Token not
Feature activation+1.078
supported
Token supported
Feature activation+0.936
.
Token.
Feature activation+0.578
errors
Token errors
Feature activation+0.000
{
Token {
Feature activation+0.000

INTERVAL 0.649 - 0.973
CONTAINS 0.014%

but
Token but
Feature activation+1.388
I
Token I
Feature activation+1.671
prefer
Token prefer
Feature activation+1.381
to
Token to
Feature activation+1.551
enter
Token enter
Feature activation+0.834
the
Token the
Feature activation+0.769
math
Token math
Feature activation+0.000
as
Token as
Feature activation+0.430
a
Token a
Feature activation+0.468
reminder
Token reminder
Feature activation+0.000
of
Token of
Feature activation+0.000
M
TokenM
Feature activation+0.000
.)
Token.)
Feature activation+0.000
1
Token 1
Feature activation+0.000
>>
Token >>
Feature activation+0.000
2
Token 2
Feature activation+0.198
/
Token/
Feature activation+0.698
24
Token24
Feature activation+0.002
Harry
Token Harry
Feature activation+0.631
Reid
Token Reid
Feature activation+0.138
SEN
Token SEN
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+1.606
>>
Token >>
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.901
Clinton
Token Clinton
Feature activation+0.743
2
Token 2
Feature activation+0.490
/
Token/
Feature activation+0.660
26
Token26
Feature activation+0.059
/
Token/
Feature activation+0.780
16
Token16
Feature activation+0.019
Ben
Token Ben
Feature activation+1.322
R
Token R
Feature activation+0.000
Some
TokenSome
Feature activation+0.508
protesters
Token protesters
Feature activation+0.974
were
Token were
Feature activation+0.866
heard
Token heard
Feature activation+0.620
yelling
Token yelling
Feature activation+0.595
'
Token '
Feature activation+0.649
Black
TokenBlack
Feature activation+0.000
Lives
Token Lives
Feature activation+0.000
Matter
Token Matter
Feature activation+0.000
,'
Token,'
Feature activation+0.000
and
Token and
Feature activation+0.376
In
Token In
Feature activation+0.510
fact
Token fact
Feature activation+0.746
,
Token,
Feature activation+0.996
I
Token I
Feature activation+0.878
see
Token see
Feature activation+0.834
a
Token a
Feature activation+0.822
lot
Token lot
Feature activation+0.089
of
Token of
Feature activation+0.441
them
Token them
Feature activation+0.374
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.324 - 0.649
CONTAINS 0.035%

TER
TokenTER
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.046
industry
Token industry
Feature activation+0.595
doesn
Token doesn
Feature activation+0.907
't
Token't
Feature activation+0.854
want
Token want
Feature activation+0.418
to
Token to
Feature activation+0.597
have
Token have
Feature activation+0.566
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
My
TokenMy
Feature activation+0.675
husband
Token husband
Feature activation+0.586
was
Token was
Feature activation+0.483
a
Token a
Feature activation+0.355
Sidd
Token Sidd
Feature activation+0.000
ha
Tokenha
Feature activation+0.000
practitioner
Token practitioner
Feature activation+0.018
and
Token and
Feature activation+0.091
problems
Token problems
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.412
updated
Token updated
Feature activation+0.561
Open
Token Open
Feature activation+0.415
B
TokenB
Feature activation+0.075
azaar
Tokenazaar
Feature activation+0.515
logo
Token logo
Feature activation+0.431
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
background
Token background
Feature activation+0.000
color
Token color
Feature activation+0.000
//
Token //
Feature activation+0.000
to
Token to
Feature activation+0.717
red
Token red
Feature activation+0.556
and
Token and
Feature activation+0.963
the
Token the
Feature activation+0.924
x
Token x
Feature activation+0.198
-
Token-
Feature activation+0.031
position
Tokenposition
Feature activation+0.000
streets
Token streets
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Here
TokenHere
Feature activation+0.000
they
Token they
Feature activation+0.365
can
Token can
Feature activation+0.076
be
Token be
Feature activation+0.000
seen
Token seen
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.000 - 0.324
CONTAINS 99.933%

see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
future
Token future
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
decision
Token decision
Feature activation+0.000
,
Token,
Feature activation+0.000
NBC
Token NBC
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
scrutiny
Token scrutiny
Feature activation+0.000
for
Token for
Feature activation+0.000
pand
Token pand
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
his
Token his
Feature activation+0.000
entire
Token entire
Feature activation+0.000
fanbase
Token fanbase
Feature activation+0.000
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
idea
Token idea
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
behind
Token behind
Feature activation+0.000
what
Token what
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
talent
Token talent
Feature activation+0.000
is
Token is
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000
to
Token to
Feature activation+0.000
climb
Token climb
Feature activation+0.000
the
Token the
Feature activation+0.000
Look
Token Look
Feature activation+0.000
Forward
Token Forward
Feature activation+0.000
To
Token To
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Dark
Token Dark
Feature activation+0.000
Matter
Token Matter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
TWO
Token TWO
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H3.1: (feature 3697)

TOP ACTIVATIONS
MAX = 4.837

role
Token role
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.043
in
Token in
Feature activation+2.466
reward
Token reward
Feature activation+1.291
and
Token and
Feature activation+4.837
addiction
Token addiction
Feature activation+0.483
but
Token but
Feature activation+0.039
also
Token also
Feature activation+0.000
in
Token in
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
to
Token to
Feature activation+2.557
the
Token the
Feature activation+1.506
wars
Token wars
Feature activation+0.799
in
Token in
Feature activation+0.482
Afghanistan
Token Afghanistan
Feature activation+1.527
and
Token and
Feature activation+4.243
Iraq
Token Iraq
Feature activation+0.164
,
Token,
Feature activation+0.662
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+1.569
established
Token established
Feature activation+1.223
treatment
Token treatment
Feature activation+0.642
for
Token for
Feature activation+2.122
anxiety
Token anxiety
Feature activation+0.519
and
Token and
Feature activation+3.816
depression
Token depression
Feature activation+0.000
,
Token,
Feature activation+0.358
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.295
way
Token way
Feature activation+1.831
to
Token to
Feature activation+1.798
get
Token get
Feature activation+1.972
more
Token more
Feature activation+3.794
readers
Token readers
Feature activation+0.393
but
Token but
Feature activation+0.164
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
,
Token,
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+1.654
violence
Token violence
Feature activation+1.023
and
Token and
Feature activation+3.790
nudity
Token nudity
Feature activation+0.195
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
political
Token political
Feature activation+0.000
sensitivity
Token sensitivity
Feature activation+0.000
an
Token an
Feature activation+1.322
attack
Token attack
Feature activation+1.479
on
Token on
Feature activation+1.290
Wisconsin
Token Wisconsin
Feature activation+1.080
families
Token families
Feature activation+0.792
and
Token and
Feature activation+3.681
public
Token public
Feature activation+0.000
education
Token education
Feature activation+0.000
but
Token but
Feature activation+0.000
on
Token on
Feature activation+0.000
democracy
Token democracy
Feature activation+0.000
title
Token title
Feature activation+0.000
marks
Token marks
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+2.158
first
Token first
Feature activation+3.559
creator
Token creator
Feature activation+2.708
owned
Token owned
Feature activation+1.692
book
Token book
Feature activation+0.859
from
Token from
Feature activation+1.031
team
Token team
Feature activation+0.251
Swift
Token Swift
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
more
Token more
Feature activation+3.316
powerful
Token powerful
Feature activation+1.433
,
Token,
Feature activation+1.024
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
has
Token has
Feature activation+0.000
Not
Token Not
Feature activation+0.000
only
Token only
Feature activation+0.000
are
Token are
Feature activation+0.000
city
Token city
Feature activation+0.064
police
Token police
Feature activation+0.267
more
Token more
Feature activation+3.310
involved
Token involved
Feature activation+0.328
,
Token,
Feature activation+1.294
she
Token she
Feature activation+0.000
observes
Token observes
Feature activation+0.441
,
Token,
Feature activation+0.092
ish
Tokenish
Feature activation+0.000
an
Tokenan
Feature activation+0.000
then
Token then
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
apologized
Token apologized
Feature activation+3.293
but
Token but
Feature activation+0.146
turned
Token turned
Feature activation+0.456
the
Token the
Feature activation+0.091
lines
Token lines
Feature activation+0.000
into
Token into
Feature activation+0.331
Range
Token Range
Feature activation+0.000
Rover
Token Rover
Feature activation+0.000
a
Token a
Feature activation+0.212
new
Token new
Feature activation+1.772
vehicle
Token vehicle
Feature activation+0.000
and
Token and
Feature activation+3.119
brand
Token brand
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.786
sequel
Token sequel
Feature activation+2.951
to
Token to
Feature activation+2.997
Out
Token Out
Feature activation+0.009
Run
Token Run
Feature activation+0.000
but
Token but
Feature activation+0.700
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
ineffective
Token ineffective
Feature activation+2.479
at
Token at
Feature activation+0.898
preventing
Token preventing
Feature activation+2.989
teenage
Token teenage
Feature activation+0.177
pregnancy
Token pregnancy
Feature activation+0.728
,
Token,
Feature activation+1.187
it
Token it
Feature activation+0.000
contributes
Token contributes
Feature activation+0.325
by
Token by
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.786
sequel
Token sequel
Feature activation+2.951
to
Token to
Feature activation+2.997
Out
Token Out
Feature activation+0.009
Run
Token Run
Feature activation+0.000
but
Token but
Feature activation+0.700
also
Token also
Feature activation+0.000
entitled
Token entitled
Feature activation+0.450
to
Token to
Feature activation+1.040
inspect
Token inspect
Feature activation+1.753
the
Token the
Feature activation+0.922
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+2.888
videos
Token videos
Feature activation+0.000
,
Token,
Feature activation+0.141
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
poor
Token poor
Feature activation+0.000
performance
Token performance
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
ruined
Token ruined
Feature activation+2.882
its
Token its
Feature activation+2.221
own
Token own
Feature activation+2.374
balance
Token balance
Feature activation+0.582
sheet
Token sheet
Feature activation+0.670
but
Token but
Feature activation+0.166
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.669
cheap
Token cheap
Feature activation+2.838
,
Token,
Feature activation+2.854
but
Token but
Feature activation+0.076
have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
service
Token service
Feature activation+0.000
time
Token time
Feature activation+0.000
far
Token far
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.669
cheap
Token cheap
Feature activation+2.838
,
Token,
Feature activation+2.854
but
Token but
Feature activation+0.076
have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
service
Token service
Feature activation+0.000
Mr
Token Mr
Feature activation+0.475
.
Token.
Feature activation+0.000
Hert
Token Hert
Feature activation+0.000
z
Tokenz
Feature activation+0.000
og
Tokenog
Feature activation+0.000
and
Token and
Feature activation+2.775
Proxy
Token Proxy
Feature activation+0.000
Card
Token Card
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
an
Token an
Feature activation+0.000
marks
Token marks
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+2.158
first
Token first
Feature activation+3.559
creator
Token creator
Feature activation+2.708
owned
Token owned
Feature activation+1.692
book
Token book
Feature activation+0.859
from
Token from
Feature activation+1.031
team
Token team
Feature activation+0.251
Santos
Token Santos
Feature activation+0.000

Top DFA by src position
MAX = 5.075

play
Token play
Feature activation+0.003
Top resid features:
an
Token an
Feature activation+0.007
Top resid features:
important
Token important
Feature activation+0.003
Top resid features:
role
Token role
Feature activation+0.013
Top resid features:
not
Token not
Feature activation+0.110
Top resid features:
only
Token only
Feature activation+5.075
Top resid features:
in
Token in
Feature activation+0.165
Top resid features:
reward
Token reward
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
addiction
Token addiction
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
ann
Tokenann
Feature activation-0.002
Top resid features:
elled
Tokenelled
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
opposition
Token opposition
Feature activation+0.010
Top resid features:
not
Token not
Feature activation+0.125
Top resid features:
only
Token only
Feature activation+4.475
Top resid features:
to
Token to
Feature activation+0.089
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
wars
Token wars
Feature activation+0.033
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
Afghanistan
Token Afghanistan
Feature activation+0.076
Top resid features:
C
TokenC
Feature activation-0.000
Top resid features:
BT
TokenBT
Feature activation-0.002
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
not
Token not
Feature activation+0.087
Top resid features:
only
Token only
Feature activation+4.153
Top resid features:
an
Token an
Feature activation+0.033
Top resid features:
established
Token established
Feature activation-0.010
Top resid features:
treatment
Token treatment
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.071
Top resid features:
anxiety
Token anxiety
Feature activation+0.123
Top resid features:
widening
Token widening
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
audience
Token audience
Feature activation+0.008
Top resid features:
was
Token was
Feature activation-0.010
Top resid features:
not
Token not
Feature activation+0.056
Top resid features:
only
Token only
Feature activation+4.175
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
way
Token way
Feature activation+0.045
Top resid features:
to
Token to
Feature activation+0.081
Top resid features:
get
Token get
Feature activation+0.055
Top resid features:
more
Token more
Feature activation-0.053
Top resid features:
who
Token who
Feature activation+0.043
Top resid features:
often
Token often
Feature activation-0.017
Top resid features:
flag
Token flag
Feature activation+0.024
Top resid features:
scenes
Token scenes
Feature activation-0.001
Top resid features:
not
Token not
Feature activation+0.051
Top resid features:
only
Token only
Feature activation+4.029
Top resid features:
for
Token for
Feature activation+0.105
Top resid features:
violence
Token violence
Feature activation+0.076
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
nudity
Token nudity
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
This
Token This
Feature activation+0.003
Top resid features:
bill
Token bill
Feature activation+0.004
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
not
Token not
Feature activation+0.084
Top resid features:
only
Token only
Feature activation+4.010
Top resid features:
an
Token an
Feature activation+0.045
Top resid features:
attack
Token attack
Feature activation+0.037
Top resid features:
on
Token on
Feature activation+0.060
Top resid features:
Wisconsin
Token Wisconsin
Feature activation+0.023
Top resid features:
families
Token families
Feature activation+0.038
Top resid features:
Dark
Token Dark
Feature activation-0.002
Top resid features:
Horse
Token Horse
Feature activation-0.001
Top resid features:
title
Token title
Feature activation+0.000
Top resid features:
marks
Token marks
Feature activation+0.043
Top resid features:
not
Token not
Feature activation-0.017
Top resid features:
only
Token only
Feature activation+4.098
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
first
Token first
Feature activation+0.014
Top resid features:
creator
Token creator
Feature activation+0.000
Top resid features:
owned
Token owned
Feature activation+0.000
Top resid features:
book
Token book
Feature activation+0.000
Top resid features:
called
Token called
Feature activation-0.003
Top resid features:
Swift
Token Swift
Feature activation+0.002
Top resid features:
that
Token that
Feature activation-0.039
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
not
Token not
Feature activation-0.070
Top resid features:
only
Token only
Feature activation+4.009
Top resid features:
more
Token more
Feature activation+0.009
Top resid features:
powerful
Token powerful
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.063
Top resid features:
ig
Tokenig
Feature activation-0.014
Top resid features:
ler
Tokenler
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Not
Token Not
Feature activation+0.056
Top resid features:
only
Token only
Feature activation+3.859
Top resid features:
are
Token are
Feature activation-0.042
Top resid features:
city
Token city
Feature activation+0.091
Top resid features:
police
Token police
Feature activation+0.062
Top resid features:
more
Token more
Feature activation-0.023
Top resid features:
involved
Token involved
Feature activation+0.000
Top resid features:
ik
Tokenik
Feature activation+0.011
Top resid features:
ish
Tokenish
Feature activation+0.045
Top resid features:
an
Tokenan
Feature activation+0.019
Top resid features:
then
Token then
Feature activation-0.138
Top resid features:
not
Token not
Feature activation-0.081
Top resid features:
only
Token only
Feature activation+4.001
Top resid features:
apologized
Token apologized
Feature activation+0.073
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
turned
Token turned
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
lines
Token lines
Feature activation+0.000
Top resid features:
Rover
Token Rover
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Not
TokenNot
Feature activation+0.076
Top resid features:
only
Token only
Feature activation+3.619
Top resid features:
was
Token was
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.053
Top resid features:
Range
Token Range
Feature activation-0.005
Top resid features:
Rover
Token Rover
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
had
Token had
Feature activation-0.005
Top resid features:
it
Token it
Feature activation-0.006
Top resid features:
by
Token by
Feature activation+0.009
Top resid features:
releasing
Token releasing
Feature activation+0.102
Top resid features:
not
Token not
Feature activation+0.058
Top resid features:
only
Token only
Feature activation+3.073
Top resid features:
a
Token a
Feature activation+0.088
Top resid features:
sequel
Token sequel
Feature activation+0.257
Top resid features:
to
Token to
Feature activation+0.094
Top resid features:
Out
Token Out
Feature activation+0.000
Top resid features:
Run
Token Run
Feature activation+0.000
Top resid features:
sex
Token sex
Feature activation+0.008
Top resid features:
education
Token education
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
is
Token is
Feature activation-0.015
Top resid features:
not
Token not
Feature activation+0.063
Top resid features:
only
Token only
Feature activation+2.936
Top resid features:
ineffective
Token ineffective
Feature activation+0.276
Top resid features:
at
Token at
Feature activation+0.146
Top resid features:
preventing
Token preventing
Feature activation+0.131
Top resid features:
teenage
Token teenage
Feature activation+0.000
Top resid features:
pregnancy
Token pregnancy
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
by
Token by
Feature activation+0.014
Top resid features:
releasing
Token releasing
Feature activation+0.127
Top resid features:
not
Token not
Feature activation+0.092
Top resid features:
only
Token only
Feature activation+3.090
Top resid features:
a
Token a
Feature activation+0.174
Top resid features:
sequel
Token sequel
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Out
Token Out
Feature activation+0.000
Top resid features:
Run
Token Run
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.016
Top resid features:
The
TokenThe
Feature activation+0.007
Top resid features:
defense
Token defense
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
not
Token not
Feature activation+0.107
Top resid features:
only
Token only
Feature activation+3.189
Top resid features:
entitled
Token entitled
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.079
Top resid features:
inspect
Token inspect
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
photographs
Token photographs
Feature activation+0.090
Top resid features:
Ļ
TokenĻ
Feature activation-0.008
Top resid features:
s
Tokens
Feature activation+0.028
Top resid features:
poor
Token poor
Feature activation+0.006
Top resid features:
performance
Token performance
Feature activation+0.086
Top resid features:
not
Token not
Feature activation-0.115
Top resid features:
only
Token only
Feature activation+3.466
Top resid features:
ruined
Token ruined
Feature activation+0.079
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
balance
Token balance
Feature activation+0.000
Top resid features:
sheet
Token sheet
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.007
Top resid features:
thus
Token thus
Feature activation+0.015
Top resid features:
far
Token far
Feature activation-0.006
Top resid features:
have
Token have
Feature activation+0.021
Top resid features:
not
Token not
Feature activation+0.045
Top resid features:
only
Token only
Feature activation+3.064
Top resid features:
been
Token been
Feature activation+0.072
Top resid features:
cheap
Token cheap
Feature activation+0.079
Top resid features:
,
Token,
Feature activation+0.120
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.001
Top resid features:
thus
Token thus
Feature activation-0.005
Top resid features:
far
Token far
Feature activation-0.002
Top resid features:
have
Token have
Feature activation+0.025
Top resid features:
not
Token not
Feature activation+0.024
Top resid features:
only
Token only
Feature activation+3.235
Top resid features:
been
Token been
Feature activation+0.094
Top resid features:
cheap
Token cheap
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.006
Top resid features:
incredible
Token incredible
Feature activation-0.001
Top resid features:
partnership
Token partnership
Feature activation+0.022
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.017
Top resid features:
not
Token not
Feature activation+0.179
Top resid features:
only
Token only
Feature activation+3.179
Top resid features:
between
Token between
Feature activation-0.047
Top resid features:
Mr
Token Mr
Feature activation+0.078
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Hert
Token Hert
Feature activation+0.015
Top resid features:
z
Tokenz
Feature activation+0.007
Top resid features:
Dark
Token Dark
Feature activation-0.006
Top resid features:
Horse
Token Horse
Feature activation-0.015
Top resid features:
title
Token title
Feature activation-0.008
Top resid features:
marks
Token marks
Feature activation+0.029
Top resid features:
not
Token not
Feature activation+0.066
Top resid features:
only
Token only
Feature activation+2.961
Top resid features:
the
Token the
Feature activation+0.194
Top resid features:
first
Token first
Feature activation-0.019
Top resid features:
creator
Token creator
Feature activation+0.093
Top resid features:
owned
Token owned
Feature activation+0.000
Top resid features:
book
Token book
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.45

Head 2: 0.05

Head 3: 0.02

Head 4: 0.02

Head 5: 0.06

Head 6: 0.04

Head 7: 0.04

Head 8: 0.07

Head 9: 0.05

Head 10: 0.07

Head 11: 0.12

Positive logits

inev1.25

PsyNetMessage1.23

Titanic1.20

Ware1.20

oku1.18

retrospective1.17

¯¯¯¯¯¯¯¯1.15

degrade1.13

idal1.13

wards1.12

1.09

cruise1.09

Emer1.08

RFC1.08

gard1.07

nursery1.07

obs1.07

pian1.07

ishable1.06

1.05

Negative logits

EVA-1.56

ombat-1.42

cock-1.28

anwhile-1.27

Answer-1.26

brainer-1.22

Lastly-1.21

Fed-1.21

attRot-1.21

Mutant-1.19

Also-1.19

chev-1.18

aho-1.17

!".-1.16

heng-1.16

alien-1.14

Mub-1.14

hawk-1.13

.",-1.12

Additionally-1.12

INTERVAL 4.353 - 4.837
CONTAINS 0.000%

role
Token role
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.043
in
Token in
Feature activation+2.466
reward
Token reward
Feature activation+1.291
and
Token and
Feature activation+4.837
addiction
Token addiction
Feature activation+0.483
but
Token but
Feature activation+0.039
also
Token also
Feature activation+0.000
in
Token in
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000

INTERVAL 3.870 - 4.353
CONTAINS 0.000%

to
Token to
Feature activation+2.557
the
Token the
Feature activation+1.506
wars
Token wars
Feature activation+0.799
in
Token in
Feature activation+0.482
Afghanistan
Token Afghanistan
Feature activation+1.527
and
Token and
Feature activation+4.243
Iraq
Token Iraq
Feature activation+0.164
,
Token,
Feature activation+0.662
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 3.386 - 3.870
CONTAINS 0.001%

only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.295
way
Token way
Feature activation+1.831
to
Token to
Feature activation+1.798
get
Token get
Feature activation+1.972
more
Token more
Feature activation+3.794
readers
Token readers
Feature activation+0.393
but
Token but
Feature activation+0.164
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+1.569
established
Token established
Feature activation+1.223
treatment
Token treatment
Feature activation+0.642
for
Token for
Feature activation+2.122
anxiety
Token anxiety
Feature activation+0.519
and
Token and
Feature activation+3.816
depression
Token depression
Feature activation+0.000
,
Token,
Feature activation+0.358
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
title
Token title
Feature activation+0.000
marks
Token marks
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+2.158
first
Token first
Feature activation+3.559
creator
Token creator
Feature activation+2.708
owned
Token owned
Feature activation+1.692
book
Token book
Feature activation+0.859
from
Token from
Feature activation+1.031
team
Token team
Feature activation+0.251
an
Token an
Feature activation+1.322
attack
Token attack
Feature activation+1.479
on
Token on
Feature activation+1.290
Wisconsin
Token Wisconsin
Feature activation+1.080
families
Token families
Feature activation+0.792
and
Token and
Feature activation+3.681
public
Token public
Feature activation+0.000
education
Token education
Feature activation+0.000
but
Token but
Feature activation+0.000
on
Token on
Feature activation+0.000
democracy
Token democracy
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+1.654
violence
Token violence
Feature activation+1.023
and
Token and
Feature activation+3.790
nudity
Token nudity
Feature activation+0.195
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
political
Token political
Feature activation+0.000
sensitivity
Token sensitivity
Feature activation+0.000

INTERVAL 2.902 - 3.386
CONTAINS 0.001%

Range
Token Range
Feature activation+0.000
Rover
Token Rover
Feature activation+0.000
a
Token a
Feature activation+0.212
new
Token new
Feature activation+1.772
vehicle
Token vehicle
Feature activation+0.000
and
Token and
Feature activation+3.119
brand
Token brand
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
only
Token only
Feature activation+0.000
are
Token are
Feature activation+0.000
city
Token city
Feature activation+0.064
police
Token police
Feature activation+0.267
more
Token more
Feature activation+3.310
involved
Token involved
Feature activation+0.328
,
Token,
Feature activation+1.294
she
Token she
Feature activation+0.000
observes
Token observes
Feature activation+0.441
,
Token,
Feature activation+0.092
releasing
Token releasing
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.786
sequel
Token sequel
Feature activation+2.951
to
Token to
Feature activation+2.997
Out
Token Out
Feature activation+0.009
Run
Token Run
Feature activation+0.000
but
Token but
Feature activation+0.700
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
by
Token by
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.786
sequel
Token sequel
Feature activation+2.951
to
Token to
Feature activation+2.997
Out
Token Out
Feature activation+0.009
Run
Token Run
Feature activation+0.000
but
Token but
Feature activation+0.700
also
Token also
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
an
Tokenan
Feature activation+0.000
then
Token then
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
apologized
Token apologized
Feature activation+3.293
but
Token but
Feature activation+0.146
turned
Token turned
Feature activation+0.456
the
Token the
Feature activation+0.091
lines
Token lines
Feature activation+0.000
into
Token into
Feature activation+0.331

INTERVAL 2.419 - 2.902
CONTAINS 0.002%

far
Token far
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.669
cheap
Token cheap
Feature activation+2.838
,
Token,
Feature activation+2.854
but
Token but
Feature activation+0.076
have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
service
Token service
Feature activation+0.000
U
Token U
Feature activation+0.000
H
TokenH
Feature activation+0.000
West
Token West
Feature activation+0.000
O
Token O
Feature activation+0.000
ahu
Tokenahu
Feature activation+0.000
and
Token and
Feature activation+2.652
U
Token U
Feature activation+0.000
H
TokenH
Feature activation+0.000
H
Token H
Feature activation+0.000
ilo
Tokenilo
Feature activation+0.000
,
Token,
Feature activation+0.003
s
Tokens
Feature activation+0.000
poor
Token poor
Feature activation+0.000
performance
Token performance
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
ruined
Token ruined
Feature activation+2.882
its
Token its
Feature activation+2.221
own
Token own
Feature activation+2.374
balance
Token balance
Feature activation+0.582
sheet
Token sheet
Feature activation+0.670
but
Token but
Feature activation+0.166
entitled
Token entitled
Feature activation+0.450
to
Token to
Feature activation+1.040
inspect
Token inspect
Feature activation+1.753
the
Token the
Feature activation+0.922
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+2.888
videos
Token videos
Feature activation+0.000
,
Token,
Feature activation+0.141
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
to
Token to
Feature activation+0.000
he
Token he
Feature activation+0.000
able
Token able
Feature activation+0.287
to
Token to
Feature activation+0.000
skip
Token skip
Feature activation+0.838
work
Token work
Feature activation+0.000
and
Token and
Feature activation+2.467
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 1.935 - 2.419
CONTAINS 0.003%

ainer
Tokenainer
Feature activation+0.000
usage
Token usage
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
peaked
Token peaked
Feature activation+2.670
early
Token early
Feature activation+2.270
in
Token in
Feature activation+0.322
the
Token the
Feature activation+0.573
Obama
Token Obama
Feature activation+0.384
years
Token years
Feature activation+0.250
,
Token,
Feature activation+1.422
stripes
Token stripes
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
environmentalists
Token environmentalists
Feature activation+0.427
and
Token and
Feature activation+2.180
climate
Token climate
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
but
Token but
Feature activation+0.000
many
Token many
Feature activation+0.000
conservatives
Token conservatives
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
in
Token in
Feature activation+0.399
our
Token our
Feature activation+0.587
economy
Token economy
Feature activation+1.736
,
Token,
Feature activation+2.121
but
Token but
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
democracy
Token democracy
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
feds
Token feds
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
promised
Token promised
Feature activation+2.393
not
Token not
Feature activation+1.111
to
Token to
Feature activation+0.277
ring
Token ring
Feature activation+1.048
him
Token him
Feature activation+0.796
up
Token up
Feature activation+0.352
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.295
way
Token way
Feature activation+1.831
to
Token to
Feature activation+1.798
get
Token get
Feature activation+1.972
more
Token more
Feature activation+3.794
readers
Token readers
Feature activation+0.393
but
Token but
Feature activation+0.164
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000

INTERVAL 1.451 - 1.935
CONTAINS 0.005%

often
Token often
Feature activation+0.000
flag
Token flag
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+1.654
violence
Token violence
Feature activation+1.023
and
Token and
Feature activation+3.790
nudity
Token nudity
Feature activation+0.195
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
the
Token the
Feature activation+1.116
story
Token story
Feature activation+0.223
buffs
Token buffs
Feature activation+0.917
,
Token,
Feature activation+1.720
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
experience
Token experience
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
by
Token by
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+1.786
sequel
Token sequel
Feature activation+2.951
to
Token to
Feature activation+2.997
Out
Token Out
Feature activation+0.009
Run
Token Run
Feature activation+0.000
but
Token but
Feature activation+0.700
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
entitled
Token entitled
Feature activation+0.450
to
Token to
Feature activation+1.040
inspect
Token inspect
Feature activation+1.753
the
Token the
Feature activation+0.922
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+2.888
videos
Token videos
Feature activation+0.000
,
Token,
Feature activation+0.141
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
sounds
Token sounds
Feature activation+0.170
like
Token like
Feature activation+0.738
a
Token a
Feature activation+0.052
lot
Token lot
Feature activation+1.463
âĢĶ
Token âĢĶ
Feature activation+1.221
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000

INTERVAL 0.967 - 1.451
CONTAINS 0.009%

not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
wasn
Token wasn
Feature activation+0.982
't
Token't
Feature activation+2.013
his
Token his
Feature activation+0.610
MVP
Token MVP
Feature activation+1.182
self
Token self
Feature activation+1.128
,
Token,
Feature activation+1.759
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
extract
Token extract
Feature activation+1.040
oil
Token oil
Feature activation+0.981
âĢĶ
Token âĢĶ
Feature activation+0.930
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
also
Token also
Feature activation+0.000
be
Token be
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Rod
TokenRod
Feature activation+0.000
gers
Tokengers
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
wasn
Token wasn
Feature activation+0.982
't
Token't
Feature activation+2.013
his
Token his
Feature activation+0.610
MVP
Token MVP
Feature activation+1.182
self
Token self
Feature activation+1.128
,
Token,
Feature activation+1.759
only
Token only
Feature activation+0.000
sounds
Token sounds
Feature activation+0.170
like
Token like
Feature activation+0.738
a
Token a
Feature activation+0.052
lot
Token lot
Feature activation+1.463
âĢĶ
Token âĢĶ
Feature activation+1.221
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
.
Token.
Feature activation+0.000
defense
Token defense
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
entitled
Token entitled
Feature activation+0.450
to
Token to
Feature activation+1.040
inspect
Token inspect
Feature activation+1.753
the
Token the
Feature activation+0.922
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+2.888
videos
Token videos
Feature activation+0.000

INTERVAL 0.484 - 0.967
CONTAINS 0.016%

Not
Token Not
Feature activation+0.000
only
Token only
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.395
negativity
Token negativity
Feature activation+0.062
unw
Token unw
Feature activation+0.954
arranted
Tokenarranted
Feature activation+0.501
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.086
position
Token position
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
Miami
Token Miami
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
clinging
Token clinging
Feature activation+0.565
to
Token to
Feature activation+0.949
the
Token the
Feature activation+0.683
faint
Token faint
Feature activation+0.076
hope
Token hope
Feature activation+0.468
of
Token of
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
go
Token go
Feature activation+0.097
there
Token there
Feature activation+0.221
for
Token for
Feature activation+0.279
an
Token an
Feature activation+0.850
hour
Token hour
Feature activation+0.298
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
'll
Token'll
Feature activation+0.000
be
Token be
Feature activation+0.000
1
Token 1
Feature activation+0.100
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
bring
Token bring
Feature activation+1.421
bug
Token bug
Feature activation+0.191
fixes
Token fixes
Feature activation+0.778
and
Token and
Feature activation+2.288
optimizations
Token optimizations
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
also
Token also
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.493
is
Token is
Feature activation+0.000
morally
Token morally
Feature activation+0.189
and
Token and
Feature activation+1.570
eth
Token eth
Feature activation+0.000
ically
Tokenically
Feature activation+0.000

INTERVAL 0.000 - 0.484
CONTAINS 99.964%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.000
safety
Token safety
Feature activation+0.000
article
Token article
Feature activation+0.000
,
Token,
Feature activation+0.000
Letter
Token Letter
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
Bad
Token Bad
Feature activation+0.000
New
Token New
Feature activation+0.000
z
Tokenz
Feature activation+0.000
Girl
Token Girl
Feature activation+0.000
:
Token:
Feature activation+0.000
5
Token 5
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Cook
TokenCook
Feature activation+0.000
ing
Tokening
Feature activation+0.000
with
Token with
Feature activation+0.000
Ell
Token Ell
Feature activation+0.000
a
Tokena
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
or
Token or
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Walters
Token Walters
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
why
Token why
Feature activation+0.000
a
Token a
Feature activation+0.000
previous
Token previous
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
detect
Token detect
Feature activation+0.000
new
Token new
Feature activation+0.000
diesel
Token diesel
Feature activation+0.000
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
rapid
Token rapid
Feature activation+0.000
dec
Token dec
Feature activation+0.000
arbon
Tokenarbon
Feature activation+0.000
isation
Tokenisation
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 3 in H3.1: (feature 3472)

TOP ACTIVATIONS
MAX = 3.795

Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.531
John
Token John
Feature activation+1.635
Boehner
Token Boehner
Feature activation+2.238
Claims
Token Claims
Feature activation+3.187
He
Token He
Feature activation+1.680
Was
Token Was
Feature activation+1.340
âĢ
Token âĢ
Feature activation+1.525
ĺ
Tokenĺ
Feature activation+0.198
Fl
TokenFl
Feature activation+0.000
attacks
Token attacks
Feature activation+2.961
Trump
Token Trump
Feature activation+2.124
for
Token for
Feature activation+1.884
transgender
Token transgender
Feature activation+0.845
bathroom
Token bathroom
Feature activation+1.046
comments
Token comments
Feature activation+3.049
Ċ
TokenĊ
Feature activation+1.426
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
then
Token then
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.600
Cruz
Token Cruz
Feature activation+1.616
attacks
Token attacks
Feature activation+2.961
Trump
Token Trump
Feature activation+2.124
for
Token for
Feature activation+1.884
transgender
Token transgender
Feature activation+0.845
bathroom
Token bathroom
Feature activation+1.046
comments
Token comments
Feature activation+3.049
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Mass
Token Mass
Feature activation+1.804
shooting
Token shooting
Feature activation+2.351
at
Token at
Feature activation+1.793
Orlando
Token Orlando
Feature activation+2.877
gay
Token gay
Feature activation+2.120
nightclub
Token nightclub
Feature activation+2.219
Ċ
TokenĊ
Feature activation+0.865
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
North
Token North
Feature activation+1.832
Van
Token Van
Feature activation+2.077
developer
Token developer
Feature activation+2.461
says
Token says
Feature activation+2.847
the
Token the
Feature activation+1.891
industry
Token industry
Feature activation+0.423
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.371
do
Token do
Feature activation+1.061
Read
TokenRead
Feature activation+0.000
:
Token:
Feature activation+0.000
Frozen
Token Frozen
Feature activation+1.543
in
Token in
Feature activation+1.168
Time
Token Time
Feature activation+2.508
--
Token --
Feature activation+2.825
7
Token 7
Feature activation+2.277
of
Token of
Feature activation+1.125
the
Token the
Feature activation+1.107
Worst
Token Worst
Feature activation+1.783
Blizz
Token Blizz
Feature activation+0.074
B
Token B
Feature activation+1.270
.
Token.
Feature activation+1.383
C
TokenC
Feature activation+0.062
.
Token.
Feature activation+1.089
photographer
Token photographer
Feature activation+2.121
captures
Token captures
Feature activation+2.628
rescue
Token rescue
Feature activation+1.460
of
Token of
Feature activation+1.220
bald
Token bald
Feature activation+0.123
eagle
Token eagle
Feature activation+0.241
trapped
Token trapped
Feature activation+1.189
:
Token:
Feature activation+0.000
Russia
Token Russia
Feature activation+1.418
and
Token and
Feature activation+2.114
Europe
Token Europe
Feature activation+1.793
to
Token to
Feature activation+2.278
launch
Token launch
Feature activation+2.576
joint
Token joint
Feature activation+1.693
mission
Token mission
Feature activation+1.916
to
Token to
Feature activation+1.667
dark
Token dark
Feature activation+1.173
side
Token side
Feature activation+0.321
deal
Token deal
Feature activation+0.757
with
Token with
Feature activation+0.386
refugee
Token refugee
Feature activation+0.828
health
Token health
Feature activation+0.814
care
Token care
Feature activation+0.537
?
Token?
Feature activation+2.541
Ċ
TokenĊ
Feature activation+0.317
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.167
Navy
Token Navy
Feature activation+1.734
pitches
Token pitches
Feature activation+2.528
for
Token for
Feature activation+2.057
women
Token women
Feature activation+1.192
pilots
Token pilots
Feature activation+1.381
but
Token but
Feature activation+2.409
no
Token no
Feature activation+1.024
Ċ
TokenĊ
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
:
Token:
Feature activation+0.000
Frozen
Token Frozen
Feature activation+1.543
in
Token in
Feature activation+1.168
Time
Token Time
Feature activation+2.508
--
Token --
Feature activation+2.825
7
Token 7
Feature activation+2.277
of
Token of
Feature activation+1.125
the
Token the
Feature activation+1.107
Worst
Token Worst
Feature activation+1.783
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
Donald
Token Donald
Feature activation+1.194
Trump
Token Trump
Feature activation+1.764
Makes
Token Makes
Feature activation+2.484
History
Token History
Feature activation+1.303
With
Token With
Feature activation+1.854
Zero
Token Zero
Feature activation+0.739
Major
Token Major
Feature activation+0.898
Newspaper
Token Newspaper
Feature activation+1.488
READ
TokenREAD
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
North
Token North
Feature activation+1.832
Van
Token Van
Feature activation+2.077
developer
Token developer
Feature activation+2.461
says
Token says
Feature activation+2.847
the
Token the
Feature activation+1.891
industry
Token industry
Feature activation+0.423
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.371
Latest
Token Latest
Feature activation+1.242
on
Token on
Feature activation+0.715
Turkey
Token Turkey
Feature activation+1.974
's
Token's
Feature activation+1.555
corruption
Token corruption
Feature activation+1.840
probe
Token probe
Feature activation+2.441
Ċ
TokenĊ
Feature activation+0.947
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
wide
Token wide
Feature activation+0.000
-
Token-
Feature activation+0.000
Navy
Token Navy
Feature activation+1.734
pitches
Token pitches
Feature activation+2.528
for
Token for
Feature activation+2.057
women
Token women
Feature activation+1.192
pilots
Token pilots
Feature activation+1.381
but
Token but
Feature activation+2.409
no
Token no
Feature activation+1.024
combat
Token combat
Feature activation+0.000
role
Token role
Feature activation+0.000
yet
Token yet
Feature activation+1.592
Ċ
TokenĊ
Feature activation+1.468
:
Token:
Feature activation+0.000
Net
Token Net
Feature activation+1.247
an
Tokenan
Feature activation+0.705
jah
Tokenjah
Feature activation+0.792
i
Tokeni
Feature activation+0.761
says
Token says
Feature activation+2.405
Israel
Token Israel
Feature activation+1.436
will
Token will
Feature activation+1.781
not
Token not
Feature activation+1.106
accept
Token accept
Feature activation+0.700
'
Token '
Feature activation+1.797
Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.000
NCAA
Token NCAA
Feature activation+1.488
Regional
Token Regional
Feature activation+2.230
rankings
Token rankings
Feature activation+2.360
|
Token |
Feature activation+1.220
United
Token United
Feature activation+0.466
Soccer
Token Soccer
Feature activation+0.412
Co
Token Co
Feature activation+0.767
aches
Tokenaches
Feature activation+0.862
Ċ
TokenĊ
Feature activation+0.000
READ
TokenREAD
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Mass
Token Mass
Feature activation+1.804
shooting
Token shooting
Feature activation+2.351
at
Token at
Feature activation+1.793
Orlando
Token Orlando
Feature activation+2.877
gay
Token gay
Feature activation+2.120
nightclub
Token nightclub
Feature activation+2.219
Ċ
TokenĊ
Feature activation+0.865
Related
TokenRelated
Feature activation+0.000
:
Token:
Feature activation+0.000
Host
Token Host
Feature activation+1.818
ess
Tokeness
Feature activation+1.311
jobs
Token jobs
Feature activation+2.051
-
Token -
Feature activation+2.344
'
Token '
Feature activation+1.513
Great
TokenGreat
Feature activation+0.000
'
Token'
Feature activation+0.070
to
Token to
Feature activation+1.091
'
Token '
Feature activation+1.376
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
:
Token:
Feature activation+0.358
White
Token White
Feature activation+1.198
House
Token House
Feature activation+1.590
,
Token,
Feature activation+2.337
GOP
Token GOP
Feature activation+2.036
Intel
Token Intel
Feature activation+1.349
Committee
Token Committee
Feature activation+1.780
Heads
Token Heads
Feature activation+1.315
Push
Token Push
Feature activation+2.218

Top DFA by src position
MAX = 2.906

like
Token like
Feature activation+0.002
Top resid features:
children
Token children
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.050
Top resid features:
Ċ
TokenĊ
Feature activation-0.067
Top resid features:
Ċ
TokenĊ
Feature activation-0.070
Top resid features:
RELATED
TokenRELATED
Feature activation+2.583
Top resid features:
:
Token:
Feature activation+0.872
Top resid features:
John
Token John
Feature activation+0.082
Top resid features:
Boehner
Token Boehner
Feature activation+0.084
Top resid features:
Claims
Token Claims
Feature activation+0.037
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
horror
Token horror
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
RELATED
TokenRELATED
Feature activation+1.779
Top resid features:
:
Token:
Feature activation+1.182
Top resid features:
Cruz
Token Cruz
Feature activation+0.013
Top resid features:
attacks
Token attacks
Feature activation+0.001
Top resid features:
Trump
Token Trump
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.047
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
horror
Token horror
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.040
Top resid features:
Ċ
TokenĊ
Feature activation-0.052
Top resid features:
Ċ
TokenĊ
Feature activation-0.059
Top resid features:
RELATED
TokenRELATED
Feature activation+2.089
Top resid features:
:
Token:
Feature activation+1.035
Top resid features:
Cruz
Token Cruz
Feature activation+0.142
Top resid features:
attacks
Token attacks
Feature activation+0.100
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
READ
TokenREAD
Feature activation+0.860
Top resid features:
MORE
Token MORE
Feature activation+0.518
Top resid features:
:
Token:
Feature activation+1.371
Top resid features:
Mass
Token Mass
Feature activation+0.033
Top resid features:
shooting
Token shooting
Feature activation+0.076
Top resid features:
at
Token at
Feature activation+0.066
Top resid features:
Orlando
Token Orlando
Feature activation+0.128
Top resid features:
gay
Token gay
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
READ
TokenREAD
Feature activation+0.564
Top resid features:
MORE
Token MORE
Feature activation+0.331
Top resid features:
:
Token:
Feature activation+1.806
Top resid features:
North
Token North
Feature activation+0.057
Top resid features:
Van
Token Van
Feature activation+0.089
Top resid features:
developer
Token developer
Feature activation+0.229
Top resid features:
says
Token says
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
see
Token see
Feature activation-0.000
Top resid features:
!"
Token!"
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.075
Top resid features:
Ċ
TokenĊ
Feature activation-0.060
Top resid features:
Read
TokenRead
Feature activation+0.082
Top resid features:
:
Token:
Feature activation+2.906
Top resid features:
Frozen
Token Frozen
Feature activation+0.116
Top resid features:
in
Token in
Feature activation+0.112
Top resid features:
Time
Token Time
Feature activation+0.096
Top resid features:
--
Token --
Feature activation-0.102
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.027
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
READ
TokenREAD
Feature activation+0.297
Top resid features:
MORE
Token MORE
Feature activation+0.381
Top resid features:
:
Token:
Feature activation+1.947
Top resid features:
B
Token B
Feature activation+0.067
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
C
TokenC
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
photographer
Token photographer
Feature activation+0.198
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
READ
TokenREAD
Feature activation+0.284
Top resid features:
MORE
Token MORE
Feature activation+0.368
Top resid features:
:
Token:
Feature activation+1.723
Top resid features:
Russia
Token Russia
Feature activation+0.110
Top resid features:
and
Token and
Feature activation+0.031
Top resid features:
Europe
Token Europe
Feature activation-0.052
Top resid features:
to
Token to
Feature activation+0.128
Top resid features:
launch
Token launch
Feature activation+0.144
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
Ċ
TokenĊ
Feature activation-0.027
Top resid features:
READ
TokenREAD
Feature activation+0.643
Top resid features:
MORE
Token MORE
Feature activation+0.021
Top resid features:
:
Token:
Feature activation+2.413
Top resid features:
What
Token What
Feature activation+0.052
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation-0.042
Top resid features:
s
Tokens
Feature activation-0.018
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation-0.040
Top resid features:
Ċ
TokenĊ
Feature activation-0.049
Top resid features:
Also
TokenAlso
Feature activation-0.013
Top resid features:
Read
Token Read
Feature activation+1.000
Top resid features:
:
Token:
Feature activation+1.557
Top resid features:
Navy
Token Navy
Feature activation+0.126
Top resid features:
pitches
Token pitches
Feature activation+0.137
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
pilots
Token pilots
Feature activation+0.000
Top resid features:
see
Token see
Feature activation-0.000
Top resid features:
!"
Token!"
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.037
Top resid features:
Ċ
TokenĊ
Feature activation-0.029
Top resid features:
Read
TokenRead
Feature activation+0.282
Top resid features:
:
Token:
Feature activation+2.185
Top resid features:
Frozen
Token Frozen
Feature activation+0.040
Top resid features:
in
Token in
Feature activation+0.077
Top resid features:
Time
Token Time
Feature activation+0.149
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.044
Top resid features:
Also
TokenAlso
Feature activation+0.124
Top resid features:
Read
Token Read
Feature activation+1.004
Top resid features:
:
Token:
Feature activation+1.372
Top resid features:
Donald
Token Donald
Feature activation+0.086
Top resid features:
Trump
Token Trump
Feature activation+0.138
Top resid features:
Makes
Token Makes
Feature activation+0.058
Top resid features:
History
Token History
Feature activation+0.000
Top resid features:
With
Token With
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
READ
TokenREAD
Feature activation+0.627
Top resid features:
MORE
Token MORE
Feature activation+0.667
Top resid features:
:
Token:
Feature activation+1.187
Top resid features:
North
Token North
Feature activation+0.085
Top resid features:
Van
Token Van
Feature activation+0.122
Top resid features:
developer
Token developer
Feature activation+0.081
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.000
Top resid features:
year
Token year
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation-0.044
Top resid features:
Ċ
TokenĊ
Feature activation-0.042
Top resid features:
Related
TokenRelated
Feature activation+1.219
Top resid features:
:
Token:
Feature activation+1.055
Top resid features:
Latest
Token Latest
Feature activation+0.201
Top resid features:
on
Token on
Feature activation-0.030
Top resid features:
Turkey
Token Turkey
Feature activation+0.076
Top resid features:
's
Token's
Feature activation+0.106
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Also
TokenAlso
Feature activation-0.171
Top resid features:
Read
Token Read
Feature activation+0.474
Top resid features:
:
Token:
Feature activation+2.273
Top resid features:
Navy
Token Navy
Feature activation+0.053
Top resid features:
pitches
Token pitches
Feature activation+0.048
Top resid features:
for
Token for
Feature activation+0.078
Top resid features:
women
Token women
Feature activation+0.046
Top resid features:
pilots
Token pilots
Feature activation+0.058
Top resid features:
."
Token."
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation-0.108
Top resid features:
Ċ
TokenĊ
Feature activation-0.105
Top resid features:
Read
TokenRead
Feature activation+0.248
Top resid features:
more
Token more
Feature activation+0.173
Top resid features:
:
Token:
Feature activation+2.235
Top resid features:
Net
Token Net
Feature activation+0.085
Top resid features:
an
Tokenan
Feature activation+0.012
Top resid features:
jah
Tokenjah
Feature activation+0.066
Top resid features:
i
Tokeni
Feature activation+0.002
Top resid features:
says
Token says
Feature activation+0.042
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
championship
Token championship
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.125
Top resid features:
Ċ
TokenĊ
Feature activation-0.082
Top resid features:
Ċ
TokenĊ
Feature activation-0.079
Top resid features:
RELATED
TokenRELATED
Feature activation+1.384
Top resid features:
:
Token:
Feature activation+1.011
Top resid features:
NCAA
Token NCAA
Feature activation+0.112
Top resid features:
Regional
Token Regional
Feature activation+0.161
Top resid features:
rankings
Token rankings
Feature activation+0.191
Top resid features:
|
Token |
Feature activation+0.000
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
added
Token added
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation-0.029
Top resid features:
Ċ
TokenĊ
Feature activation-0.038
Top resid features:
READ
TokenREAD
Feature activation+0.968
Top resid features:
MORE
Token MORE
Feature activation+0.583
Top resid features:
:
Token:
Feature activation+0.787
Top resid features:
Mass
Token Mass
Feature activation+0.025
Top resid features:
shooting
Token shooting
Feature activation+0.136
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
ess
Tokeness
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation-0.083
Top resid features:
Ċ
TokenĊ
Feature activation-0.072
Top resid features:
Related
TokenRelated
Feature activation+0.387
Top resid features:
:
Token:
Feature activation+2.360
Top resid features:
Host
Token Host
Feature activation+0.025
Top resid features:
ess
Tokeness
Feature activation-0.006
Top resid features:
jobs
Token jobs
Feature activation+0.086
Top resid features:
-
Token -
Feature activation-0.152
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.043
Top resid features:
Ċ
TokenĊ
Feature activation-0.063
Top resid features:
Ċ
TokenĊ
Feature activation-0.058
Top resid features:
Related
TokenRelated
Feature activation+1.013
Top resid features:
:
Token:
Feature activation+1.572
Top resid features:
White
Token White
Feature activation+0.040
Top resid features:
House
Token House
Feature activation+0.193
Top resid features:
,
Token,
Feature activation-0.103
Top resid features:
GOP
Token GOP
Feature activation+0.000
Top resid features:
Intel
Token Intel
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.45

Head 2: 0.06

Head 3: 0.02

Head 4: 0.03

Head 5: 0.09

Head 6: 0.06

Head 7: 0.05

Head 8: 0.06

Head 9: 0.04

Head 10: 0.05

Head 11: 0.06

Positive logits

?]2.83

!]2.35

']2.18

Replay2.12

').2.11

!'"2.01

)2.00

.)1.98

.")1.98

?).1.96

.]1.94

?)1.93

…]1.92

}}1.88

});1.87

})1.83

]'1.82

]."1.82

.'"1.82

!'1.81

Negative logits

NetMessage-2.03

nown-1.74

":[{"-1.70

龍喚士-1.70

classes-1.66

theless-1.59

sbm-1.58

-1.57

POSE-1.56

wark-1.55

daq-1.53

byss-1.51

-1.50

behavi-1.48

ODUCT-1.48

CONCLUS-1.48

attRot-1.47

SourceFile-1.47

Stain-1.46

trak-1.46

INTERVAL 3.415 - 3.795
CONTAINS 0.000%

INTERVAL 3.036 - 3.415
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.531
John
Token John
Feature activation+1.635
Boehner
Token Boehner
Feature activation+2.238
Claims
Token Claims
Feature activation+3.187
He
Token He
Feature activation+1.680
Was
Token Was
Feature activation+1.340
âĢ
Token âĢ
Feature activation+1.525
ĺ
Tokenĺ
Feature activation+0.198
Fl
TokenFl
Feature activation+0.000
attacks
Token attacks
Feature activation+2.961
Trump
Token Trump
Feature activation+2.124
for
Token for
Feature activation+1.884
transgender
Token transgender
Feature activation+0.845
bathroom
Token bathroom
Feature activation+1.046
comments
Token comments
Feature activation+3.049
Ċ
TokenĊ
Feature activation+1.426
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
then
Token then
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000

INTERVAL 2.656 - 3.036
CONTAINS 0.000%

MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
North
Token North
Feature activation+1.832
Van
Token Van
Feature activation+2.077
developer
Token developer
Feature activation+2.461
says
Token says
Feature activation+2.847
the
Token the
Feature activation+1.891
industry
Token industry
Feature activation+0.423
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.371
do
Token do
Feature activation+1.061
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Mass
Token Mass
Feature activation+1.804
shooting
Token shooting
Feature activation+2.351
at
Token at
Feature activation+1.793
Orlando
Token Orlando
Feature activation+2.877
gay
Token gay
Feature activation+2.120
nightclub
Token nightclub
Feature activation+2.219
Ċ
TokenĊ
Feature activation+0.865
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
:
Token:
Feature activation+0.000
Frozen
Token Frozen
Feature activation+1.543
in
Token in
Feature activation+1.168
Time
Token Time
Feature activation+2.508
--
Token --
Feature activation+2.825
7
Token 7
Feature activation+2.277
of
Token of
Feature activation+1.125
the
Token the
Feature activation+1.107
Worst
Token Worst
Feature activation+1.783
Blizz
Token Blizz
Feature activation+0.074
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.600
Cruz
Token Cruz
Feature activation+1.616
attacks
Token attacks
Feature activation+2.961
Trump
Token Trump
Feature activation+2.124
for
Token for
Feature activation+1.884
transgender
Token transgender
Feature activation+0.845
bathroom
Token bathroom
Feature activation+1.046
comments
Token comments
Feature activation+3.049

INTERVAL 2.277 - 2.656
CONTAINS 0.002%

Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
Donald
Token Donald
Feature activation+1.194
Trump
Token Trump
Feature activation+1.764
Makes
Token Makes
Feature activation+2.484
History
Token History
Feature activation+1.303
With
Token With
Feature activation+1.854
Zero
Token Zero
Feature activation+0.739
Major
Token Major
Feature activation+0.898
Newspaper
Token Newspaper
Feature activation+1.488
B
Token B
Feature activation+1.270
.
Token.
Feature activation+1.383
C
TokenC
Feature activation+0.062
.
Token.
Feature activation+1.089
photographer
Token photographer
Feature activation+2.121
captures
Token captures
Feature activation+2.628
rescue
Token rescue
Feature activation+1.460
of
Token of
Feature activation+1.220
bald
Token bald
Feature activation+0.123
eagle
Token eagle
Feature activation+0.241
trapped
Token trapped
Feature activation+1.189
Ċ
TokenĊ
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
:
Token:
Feature activation+0.000
Frozen
Token Frozen
Feature activation+1.543
in
Token in
Feature activation+1.168
Time
Token Time
Feature activation+2.508
--
Token --
Feature activation+2.825
7
Token 7
Feature activation+2.277
of
Token of
Feature activation+1.125
the
Token the
Feature activation+1.107
Worst
Token Worst
Feature activation+1.783
Ċ
TokenĊ
Feature activation+0.000
READ
TokenREAD
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Mass
Token Mass
Feature activation+1.804
shooting
Token shooting
Feature activation+2.351
at
Token at
Feature activation+1.793
Orlando
Token Orlando
Feature activation+2.877
gay
Token gay
Feature activation+2.120
nightclub
Token nightclub
Feature activation+2.219
Ċ
TokenĊ
Feature activation+0.865
Latest
Token Latest
Feature activation+1.242
on
Token on
Feature activation+0.715
Turkey
Token Turkey
Feature activation+1.974
's
Token's
Feature activation+1.555
corruption
Token corruption
Feature activation+1.840
probe
Token probe
Feature activation+2.441
Ċ
TokenĊ
Feature activation+0.947
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
wide
Token wide
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.897 - 2.277
CONTAINS 0.005%

Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.600
Cruz
Token Cruz
Feature activation+1.616
attacks
Token attacks
Feature activation+2.961
Trump
Token Trump
Feature activation+2.124
for
Token for
Feature activation+1.884
transgender
Token transgender
Feature activation+0.845
bathroom
Token bathroom
Feature activation+1.046
comments
Token comments
Feature activation+3.049
Ċ
TokenĊ
Feature activation+1.426
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
Coverage
Token Coverage
Feature activation+0.000
Aden
Token Aden
Feature activation+0.816
governor
Token governor
Feature activation+1.588
accuses
Token accuses
Feature activation+2.163
Yemen
Token Yemen
Feature activation+1.334
's
Token's
Feature activation+0.490
Houth
Token Houth
Feature activation+0.491
is
Tokenis
Feature activation+0.439
of
Token of
Feature activation+0.653
Read
TokenRead
Feature activation+0.000
next
Token next
Feature activation+0.000
:
Token:
Feature activation+0.000
Storm
Token Storm
Feature activation+1.002
Fly
TokenFly
Feature activation+0.544
hits
Token hits
Feature activation+2.235
$
Token $
Feature activation+2.137
100
Token100
Feature activation+1.119
k
Tokenk
Feature activation+0.648
Kickstarter
Token Kickstarter
Feature activation+1.582
funding
Token funding
Feature activation+1.448
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000
B
Token B
Feature activation+1.320
itter
Tokenitter
Feature activation+1.580
dispute
Token dispute
Feature activation+2.301
|
Token |
Feature activation+1.900
Cobb
Token Cobb
Feature activation+1.057
reports
Token reports
Feature activation+1.361
theft
Token theft
Feature activation+1.229
Ċ
TokenĊ
Feature activation+1.413
Ċ
TokenĊ
Feature activation+0.292
Mass
Token Mass
Feature activation+1.804
shooting
Token shooting
Feature activation+2.351
at
Token at
Feature activation+1.793
Orlando
Token Orlando
Feature activation+2.877
gay
Token gay
Feature activation+2.120
nightclub
Token nightclub
Feature activation+2.219
Ċ
TokenĊ
Feature activation+0.865
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000
much
Token much
Feature activation+0.000

INTERVAL 1.518 - 1.897
CONTAINS 0.010%

I
TokenI
Feature activation+0.275
Am
Token Am
Feature activation+1.213
Trap
Token Trap
Feature activation+1.206
âĢ
TokenâĢ
Feature activation+1.156
Ŀ
TokenĿ
Feature activation+1.126
Release
Token Release
Feature activation+1.872
Date
Token Date
Feature activation+1.727
,
Token,
Feature activation+1.298
Cover
Token Cover
Feature activation+0.946
Art
Token Art
Feature activation+0.421
,
Token,
Feature activation+0.736
Fly
TokenFly
Feature activation+0.544
hits
Token hits
Feature activation+2.235
$
Token $
Feature activation+2.137
100
Token100
Feature activation+1.119
k
Tokenk
Feature activation+0.648
Kickstarter
Token Kickstarter
Feature activation+1.582
funding
Token funding
Feature activation+1.448
goal
Token goal
Feature activation+1.842
,
Token,
Feature activation+1.974
hopes
Token hopes
Feature activation+0.979
you
Token you
Feature activation+0.331
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.000
SQU
Token SQU
Feature activation+0.265
IR
TokenIR
Feature activation+0.000
REL
TokenREL
Feature activation+0.409
T
Token T
Feature activation+1.680
OU
TokenOU
Feature activation+0.000
CH
TokenCH
Feature activation+0.000
DOWN
TokenDOWN
Feature activation+0.806
Ċ
TokenĊ
Feature activation+0.459
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.000
Students
Token Students
Feature activation+0.845
fear
Token fear
Feature activation+1.872
âĢ
Token âĢ
Feature activation+1.414
ĺ
Tokenĺ
Feature activation+0.588
m
Tokenm
Feature activation+0.093
ilit
Tokenilit
Feature activation+0.000
ar
Tokenar
Feature activation+0.004
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.148
:
Token:
Feature activation+0.653
Trump
Token Trump
Feature activation+1.367
Jo
Token Jo
Feature activation+1.523
ins
Tokenins
Feature activation+2.173
List
Token List
Feature activation+2.216
of
Token of
Feature activation+1.591
Polit
Token Polit
Feature activation+0.765
icians
Tokenicians
Feature activation+1.106

INTERVAL 1.138 - 1.518
CONTAINS 0.014%

Ċ
TokenĊ
Feature activation+0.000
SEE
TokenSEE
Feature activation+0.000
ALSO
Token ALSO
Feature activation+0.000
:
Token:
Feature activation+0.000
I
Token I
Feature activation+1.062
tried
Token tried
Feature activation+1.484
to
Token to
Feature activation+0.988
find
Token find
Feature activation+1.247
a
Token a
Feature activation+0.854
new
Token new
Feature activation+0.521
B
Token B
Feature activation+0.249
ulse
Tokenulse
Feature activation+0.451
and
Token and
Feature activation+0.766
Monica
Token Monica
Feature activation+0.221
Dave
Token Dave
Feature activation+0.462
y
Tokeny
Feature activation+0.255
.
Token.
Feature activation+1.440
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Minnesota
Token Minnesota
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
Art
Token Art
Feature activation+1.437
of
Token of
Feature activation+1.663
Living
Token Living
Feature activation+1.427
âĢ
TokenâĢ
Feature activation+1.165
Ļ
TokenĻ
Feature activation+1.219
s
Tokens
Feature activation+1.178
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
:
Token:
Feature activation+0.000
Diablo
Token Diablo
Feature activation+0.780
4
Token 4
Feature activation+1.221
âĢĵ
Token âĢĵ
Feature activation+2.170
everything
Token everything
Feature activation+0.572
you
Token you
Feature activation+0.420
need
Token need
Feature activation+0.133
to
Token to
Feature activation+0.090
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.000
NCAA
Token NCAA
Feature activation+1.488
Regional
Token Regional
Feature activation+2.230
rankings
Token rankings
Feature activation+2.360
|
Token |
Feature activation+1.220
United
Token United
Feature activation+0.466
Soccer
Token Soccer
Feature activation+0.412

INTERVAL 0.759 - 1.138
CONTAINS 0.017%

Cruz
Token Cruz
Feature activation+1.616
attacks
Token attacks
Feature activation+2.961
Trump
Token Trump
Feature activation+2.124
for
Token for
Feature activation+1.884
transgender
Token transgender
Feature activation+0.845
bathroom
Token bathroom
Feature activation+1.046
comments
Token comments
Feature activation+3.049
Ċ
TokenĊ
Feature activation+1.426
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
then
Token then
Feature activation+0.000
'
Token'
Feature activation+0.000
Is
Token Is
Feature activation+1.214
Sn
Token Sn
Feature activation+0.053
ub
Tokenub
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.043
Ċ
TokenĊ
Feature activation+0.083
Smith
TokenSmith
Feature activation+0.000
clarified
Token clarified
Feature activation+0.000
that
Token that
Feature activation+0.000
while
Token while
Feature activation+0.000
Korea
Token Korea
Feature activation+1.065
just
Token just
Feature activation+1.900
built
Token built
Feature activation+1.438
a
Token a
Feature activation+0.655
really
Token really
Feature activation+0.502
stunning
Token stunning
Feature activation+1.033
new
Token new
Feature activation+0.141
airport
Token airport
Feature activation+0.328
which
Token which
Feature activation+1.609
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.496
Ċ
TokenĊ
Feature activation+0.000
READ
TokenREAD
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.869
fight
Token fight
Feature activation+0.857
over
Token over
Feature activation+1.032
Confederate
Token Confederate
Feature activation+1.136
statues
Token statues
Feature activation+1.090
could
Token could
Feature activation+1.879
make
Token make
Feature activation+0.928
or
Token or
Feature activation+0.200
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
:
Token:
Feature activation+0.000
4
Token 4
Feature activation+0.868
Ways
Token Ways
Feature activation+2.138
That
Token That
Feature activation+1.243
Democrats
Token Democrats
Feature activation+1.512
Want
Token Want
Feature activation+1.096
to
Token to
Feature activation+0.607

INTERVAL 0.379 - 0.759
CONTAINS 0.024%

led
Tokenled
Feature activation+0.075
With
Token With
Feature activation+0.000
Religious
Token Religious
Feature activation+0.208
Leaders
Token Leaders
Feature activation+0.640
Ċ
TokenĊ
Feature activation+1.855
Ċ
TokenĊ
Feature activation+0.594
Flying
TokenFlying
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
from
Token from
Feature activation+0.000
Story
Token Story
Feature activation+0.000
Smart
Token Smart
Feature activation+1.015
cities
Token cities
Feature activation+1.486
,
Token,
Feature activation+1.940
smoother
Token smoother
Feature activation+0.854
lives
Token lives
Feature activation+0.528
through
Token through
Feature activation+0.359
digital
Token digital
Feature activation+0.139
connectivity
Token connectivity
Feature activation+0.187
Ċ
TokenĊ
Feature activation+0.635
Ċ
TokenĊ
Feature activation+0.000
building
Token building
Feature activation+1.190
in
Token in
Feature activation+1.081
Detroit
Token Detroit
Feature activation+1.254
to
Token to
Feature activation+1.041
house
Token house
Feature activation+1.041
restaurant
Token restaurant
Feature activation+0.458
,
Token,
Feature activation+1.228
foundation
Token foundation
Feature activation+0.009
HQ
Token HQ
Feature activation+0.022
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
WATCHED
Token WATCHED
Feature activation+0.000
Booker
Token Booker
Feature activation+0.000
on
Token on
Feature activation+0.000
GOP
Token GOP
Feature activation+0.406
health
Token health
Feature activation+0.270
strategy
Token strategy
Feature activation+0.439
:
Token:
Feature activation+0.003
'
Token '
Feature activation+0.101
this
Tokenthis
Feature activation+0.000
is
Token is
Feature activation+0.000
cra
Token cra
Feature activation+0.000
in
Token in
Feature activation+0.527
multinational
Token multinational
Feature activation+0.901
tax
Token tax
Feature activation+0.642
battle
Token battle
Feature activation+1.573
but
Token but
Feature activation+1.478
NZ
Token NZ
Feature activation+0.626
may
Token may
Feature activation+0.726
not
Token not
Feature activation+0.000
get
Token get
Feature activation+0.000
the
Token the
Feature activation+0.000
spo
Token spo
Feature activation+0.000

INTERVAL 0.000 - 0.379
CONTAINS 99.927%

bit
Token bit
Feature activation+0.000
is
Token is
Feature activation+0.000
flipped
Token flipped
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
word
Token word
Feature activation+0.000
?
Token?
Feature activation+0.000
A
Token A
Feature activation+0.000
log
Token log
Feature activation+0.000
message
Token message
Feature activation+0.000
might
Token might
Feature activation+0.000
als
Tokenals
Feature activation+0.000
and
Token and
Feature activation+0.000
water
Token water
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
and
Token and
Feature activation+0.000
un
Token un
Feature activation+0.000
cl
Tokencl
Feature activation+0.000
ogging
Tokenogging
Feature activation+0.000
storm
Token storm
Feature activation+0.000
water
Token water
Feature activation+0.000
drains
Token drains
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
roll
Token roll
Feature activation+0.000
with
Token with
Feature activation+0.000
LeBron
Token LeBron
Feature activation+0.000
over
Token over
Feature activation+0.000
Jordan
Token Jordan
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
bridge
Token bridge
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
is
Token is
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
bard
Tokenbard
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
college
Token college
Feature activation+0.000
's
Token's
Feature activation+0.000
associate
Token associate
Feature activation+0.000
vice
Token vice
Feature activation+0.000
president
Token president
Feature activation+0.000
of
Token of
Feature activation+0.000
Student
Token Student
Feature activation+0.000
Health
Token Health
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 H3.1: (feature 21345)

TOP ACTIVATIONS
MAX = 2.692

."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Like
TokenLike
Feature activation+1.082
going
Token going
Feature activation+2.692
into
Token into
Feature activation+2.145
a
Token a
Feature activation+0.934
time
Token time
Feature activation+1.057
machine
Token machine
Feature activation+0.854
'
Token'
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
Important
TokenImportant
Feature activation+0.833
defeat
Token defeat
Feature activation+2.381
for
Token for
Feature activation+1.179
the
Token the
Feature activation+0.925
tobacco
Token tobacco
Feature activation+1.133
industry
Token industry
Feature activation+1.351
'
Token'
Feature activation+0.040
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Like
TokenLike
Feature activation+1.082
going
Token going
Feature activation+2.692
into
Token into
Feature activation+2.145
a
Token a
Feature activation+0.934
time
Token time
Feature activation+1.057
machine
Token machine
Feature activation+0.854
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.965
acy
Tokenacy
Feature activation+1.874
lives
Token lives
Feature activation+1.953
on
Token on
Feature activation+0.947
'
Token'
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
cing
Tokencing
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.965
acy
Tokenacy
Feature activation+1.874
lives
Token lives
Feature activation+1.953
on
Token on
Feature activation+0.947
'
Token'
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
break
Token break
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
'
Token'
Feature activation+0.000
New
TokenNew
Feature activation+1.219
Yorker
Token Yorker
Feature activation+1.756
'
Token'
Feature activation+0.406
cover
Token cover
Feature activation+0.000
ang
Token ang
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
Obama
Token Obama
Feature activation+0.406
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Un
TokenUn
Feature activation+0.670
break
Tokenbreak
Feature activation+1.749
able
Tokenable
Feature activation+1.516
bond
Token bond
Feature activation+1.219
'
Token'
Feature activation+0.265
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
C
TokenC
Feature activation+0.902
ultural
Tokenultural
Feature activation+0.537
genocide
Token genocide
Feature activation+1.707
'
Token'
Feature activation+0.361
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
new
Token new
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
Mad
TokenMad
Feature activation+0.826
Men
Token Men
Feature activation+1.693
'
Token'
Feature activation+0.480
recap
Token recap
Feature activation+0.000
:
Token:
Feature activation+0.000
Out
Token Out
Feature activation+0.000
with
Token with
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
Experts
TokenExperts
Feature activation+1.081
say
Token say
Feature activation+1.672
it
Token it
Feature activation+1.058
's
Token's
Feature activation+0.240
increasingly
Token increasingly
Feature activation+0.000
clear
Token clear
Feature activation+0.000
that
Token that
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
Pretty
TokenPretty
Feature activation+1.292
tense
Token tense
Feature activation+1.634
'
Token'
Feature activation+0.398
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ms
TokenMs
Feature activation+0.000
T
Token T
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
'
Token'
Feature activation+0.000
Give
TokenGive
Feature activation+0.629
It
Token It
Feature activation+1.536
To
Token To
Feature activation+1.615
Your
Token Your
Feature activation+1.303
Woman
Token Woman
Feature activation+1.465
,
Token,
Feature activation+1.058
It
Token It
Feature activation+0.542
's
Token's
Feature activation+0.666
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Deep
TokenDeep
Feature activation+1.453
and
Token and
Feature activation+1.394
profound
Token profound
Feature activation+1.038
issues
Token issues
Feature activation+1.602
'
Token'
Feature activation+0.001
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token'
Feature activation+0.000
Living
TokenLiving
Feature activation+0.904
in
Token in
Feature activation+1.288
An
Token An
Feature activation+0.882
caster
Tokencaster
Feature activation+1.038
,
Token,
Feature activation+1.556
water
Token water
Feature activation+0.826
my
Token my
Feature activation+0.669
garden
Token garden
Feature activation+0.125
every
Token every
Feature activation+0.000
morning
Token morning
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
'
Token'
Feature activation+0.000
Give
TokenGive
Feature activation+0.629
It
Token It
Feature activation+1.536
To
Token To
Feature activation+1.615
Your
Token Your
Feature activation+1.303
Woman
Token Woman
Feature activation+1.465
,
Token,
Feature activation+1.058
It
Token It
Feature activation+0.542
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Un
TokenUn
Feature activation+0.670
break
Tokenbreak
Feature activation+1.749
able
Tokenable
Feature activation+1.516
bond
Token bond
Feature activation+1.219
'
Token'
Feature activation+0.265
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
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
Every
TokenEvery
Feature activation+0.907
ward
Token ward
Feature activation+1.515
full
Token full
Feature activation+0.444
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mike
TokenMike
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
The
TokenThe
Feature activation+0.025
L
Token L
Feature activation+1.373
UFC
TokenUFC
Feature activation+1.310
academy
Token academy
Feature activation+1.489
is
Token is
Feature activation+0.662
now
Token now
Feature activation+0.199
regarded
Token regarded
Feature activation+0.553
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
'
Token'
Feature activation+0.000
Give
TokenGive
Feature activation+0.629
It
Token It
Feature activation+1.536
To
Token To
Feature activation+1.615
Your
Token Your
Feature activation+1.303
Woman
Token Woman
Feature activation+1.465
,
Token,
Feature activation+1.058
It
Token It
Feature activation+0.542
's
Token's
Feature activation+0.666
Her
Token Her
Feature activation+0.000
Job
Token Job
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
Cont
TokenCont
Feature activation+0.865
iguous
Tokeniguous
Feature activation+1.459
territory
Token territory
Feature activation+1.086
'
Token'
Feature activation+0.353
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

Top DFA by src position
MAX = 3.331

quite
Token quite
Feature activation+0.002
Top resid features:
interesting
Token interesting
Feature activation-0.002
Top resid features:
."
Token."
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
'
Token'
Feature activation+3.237
Top resid features:
Like
TokenLike
Feature activation+0.183
Top resid features:
going
Token going
Feature activation+0.075
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
successful
Token successful
Feature activation+0.004
Top resid features:
there
Token there
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.037
Top resid features:
Ċ
TokenĊ
Feature activation-0.043
Top resid features:
'
Token'
Feature activation+3.331
Top resid features:
Important
TokenImportant
Feature activation-0.119
Top resid features:
defeat
Token defeat
Feature activation+0.039
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
tobacco
Token tobacco
Feature activation+0.000
Top resid features:
quite
Token quite
Feature activation+0.000
Top resid features:
interesting
Token interesting
Feature activation+0.000
Top resid features:
."
Token."
Feature activation-0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
'
Token'
Feature activation+2.719
Top resid features:
Like
TokenLike
Feature activation+0.051
Top resid features:
going
Token going
Feature activation+0.092
Top resid features:
into
Token into
Feature activation+0.115
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
BBC
Token BBC
Feature activation-0.000
Top resid features:
Introdu
Token Introdu
Feature activation+0.003
Top resid features:
cing
Tokencing
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
'
Token'
Feature activation+2.416
Top resid features:
Leg
TokenLeg
Feature activation+0.020
Top resid features:
acy
Tokenacy
Feature activation+0.103
Top resid features:
lives
Token lives
Feature activation+0.057
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
BBC
Token BBC
Feature activation+0.000
Top resid features:
Introdu
Token Introdu
Feature activation+0.003
Top resid features:
cing
Tokencing
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
'
Token'
Feature activation+2.671
Top resid features:
Leg
TokenLeg
Feature activation-0.026
Top resid features:
acy
Tokenacy
Feature activation+0.024
Top resid features:
lives
Token lives
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
bond
Token bond
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
break
Token break
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.112
Top resid features:
'
Token'
Feature activation+2.600
Top resid features:
New
TokenNew
Feature activation-0.040
Top resid features:
Yorker
Token Yorker
Feature activation+0.087
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
ang
Token ang
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.005
Top resid features:
around
Token around
Feature activation+0.008
Top resid features:
".
Token".
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
'
Token'
Feature activation+2.167
Top resid features:
Un
TokenUn
Feature activation+0.064
Top resid features:
break
Tokenbreak
Feature activation+0.128
Top resid features:
able
Tokenable
Feature activation+0.000
Top resid features:
bond
Token bond
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.002
Top resid features:
words
Token words
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+0.006
Top resid features:
'
Token'
Feature activation+2.389
Top resid features:
C
TokenC
Feature activation+0.069
Top resid features:
ultural
Tokenultural
Feature activation-0.055
Top resid features:
genocide
Token genocide
Feature activation+0.051
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
AL
TokenAL
Feature activation+0.006
Top resid features:
SO
TokenSO
Feature activation+0.008
Top resid features:
:
Token:
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
'
Token'
Feature activation+2.359
Top resid features:
Mad
TokenMad
Feature activation-0.038
Top resid features:
Men
Token Men
Feature activation+0.083
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
recap
Token recap
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:
network
Token network
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
'
Token'
Feature activation+2.128
Top resid features:
Experts
TokenExperts
Feature activation+0.151
Top resid features:
say
Token say
Feature activation+0.046
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
increasingly
Token increasingly
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
them
Token them
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
'
Token'
Feature activation+1.899
Top resid features:
Pretty
TokenPretty
Feature activation+0.190
Top resid features:
tense
Token tense
Feature activation+0.224
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:
on
Token on
Feature activation+0.001
Top resid features:
May
Token May
Feature activation-0.007
Top resid features:
1
Token 1
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.034
Top resid features:
'
Token'
Feature activation+1.989
Top resid features:
Give
TokenGive
Feature activation+0.106
Top resid features:
It
Token It
Feature activation+0.160
Top resid features:
To
Token To
Feature activation+0.136
Top resid features:
Your
Token Your
Feature activation+0.000
Top resid features:
Woman
Token Woman
Feature activation+0.000
Top resid features:
he
Token he
Feature activation-0.005
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
'
Token'
Feature activation+2.054
Top resid features:
Deep
TokenDeep
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+0.125
Top resid features:
profound
Token profound
Feature activation+0.005
Top resid features:
issues
Token issues
Feature activation+0.060
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
same
Token same
Feature activation-0.004
Top resid features:
again
Token again
Feature activation+0.007
Top resid features:
."
Token."
Feature activation-0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
'
Token'
Feature activation+2.200
Top resid features:
Living
TokenLiving
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.094
Top resid features:
An
Token An
Feature activation-0.060
Top resid features:
caster
Tokencaster
Feature activation-0.030
Top resid features:
,
Token,
Feature activation+0.107
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
May
Token May
Feature activation-0.014
Top resid features:
1
Token 1
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.072
Top resid features:
'
Token'
Feature activation+1.959
Top resid features:
Give
TokenGive
Feature activation+0.281
Top resid features:
It
Token It
Feature activation+0.120
Top resid features:
To
Token To
Feature activation+0.000
Top resid features:
Your
Token Your
Feature activation+0.000
Top resid features:
Woman
Token Woman
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.004
Top resid features:
around
Token around
Feature activation+0.004
Top resid features:
".
Token".
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
'
Token'
Feature activation+1.699
Top resid features:
Un
TokenUn
Feature activation+0.029
Top resid features:
break
Tokenbreak
Feature activation+0.327
Top resid features:
able
Tokenable
Feature activation+0.034
Top resid features:
bond
Token bond
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.001
Top resid features:
can
Token can
Feature activation+0.001
Top resid features:
."
Token."
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation-0.027
Top resid features:
'
Token'
Feature activation+2.216
Top resid features:
Every
TokenEvery
Feature activation+0.036
Top resid features:
ward
Token ward
Feature activation+0.075
Top resid features:
full
Token full
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
six
Token six
Feature activation-0.000
Top resid features:
years
Token years
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
'
Token'
Feature activation+2.168
Top resid features:
The
TokenThe
Feature activation+0.046
Top resid features:
L
Token L
Feature activation-0.011
Top resid features:
UFC
TokenUFC
Feature activation+0.005
Top resid features:
academy
Token academy
Feature activation+0.042
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
May
Token May
Feature activation-0.006
Top resid features:
1
Token 1
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.008
Top resid features:
'
Token'
Feature activation+1.996
Top resid features:
Give
TokenGive
Feature activation+0.047
Top resid features:
It
Token It
Feature activation+0.071
Top resid features:
To
Token To
Feature activation+0.080
Top resid features:
Your
Token Your
Feature activation-0.010
Top resid features:
Woman
Token Woman
Feature activation+0.060
Top resid features:
peace
Token peace
Feature activation-0.001
Top resid features:
talks
Token talks
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
'
Token'
Feature activation+2.036
Top resid features:
Cont
TokenCont
Feature activation+0.027
Top resid features:
iguous
Tokeniguous
Feature activation+0.025
Top resid features:
territory
Token territory
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.43

Head 2: 0.07

Head 3: 0.03

Head 4: 0.03

Head 5: 0.06

Head 6: 0.08

Head 7: 0.05

Head 8: 0.07

Head 9: 0.05

Head 10: 0.05

Head 11: 0.06

Positive logits

"]2.56

':2.56

'?2.55

)'2.49

?'2.49

')2.46

').2.46

,'"2.42

"?2.40

,'2.39

',"2.38

)",2.31

",2.30

'),2.29

"2.29

)"2.26

''2.25

]'2.25

".2.21

")2.19

Negative logits

Oracle-1.71

arnaev-1.69

hetti-1.65

uala-1.62

WAR-1.59

etheless-1.54

ospons-1.50

ustomed-1.49

xtap-1.47

osponsors-1.46

aleb-1.45

icipated-1.41

utenberg-1.40

Cosponsors-1.39

upon-1.38

lain-1.38

ullivan-1.38

lamented-1.38

utterstock-1.37

NPR-1.37

INTERVAL 2.423 - 2.692
CONTAINS 0.000%

."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Like
TokenLike
Feature activation+1.082
going
Token going
Feature activation+2.692
into
Token into
Feature activation+2.145
a
Token a
Feature activation+0.934
time
Token time
Feature activation+1.057
machine
Token machine
Feature activation+0.854
'
Token'
Feature activation+0.000

INTERVAL 2.154 - 2.423
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Important
TokenImportant
Feature activation+0.833
defeat
Token defeat
Feature activation+2.381
for
Token for
Feature activation+1.179
the
Token the
Feature activation+0.925
tobacco
Token tobacco
Feature activation+1.133
industry
Token industry
Feature activation+1.351
'
Token'
Feature activation+0.040

INTERVAL 1.885 - 2.154
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.965
acy
Tokenacy
Feature activation+1.874
lives
Token lives
Feature activation+1.953
on
Token on
Feature activation+0.947
'
Token'
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
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
Like
TokenLike
Feature activation+1.082
going
Token going
Feature activation+2.692
into
Token into
Feature activation+2.145
a
Token a
Feature activation+0.934
time
Token time
Feature activation+1.057
machine
Token machine
Feature activation+0.854
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.615 - 1.885
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Experts
TokenExperts
Feature activation+1.081
say
Token say
Feature activation+1.672
it
Token it
Feature activation+1.058
's
Token's
Feature activation+0.240
increasingly
Token increasingly
Feature activation+0.000
clear
Token clear
Feature activation+0.000
that
Token that
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
Mad
TokenMad
Feature activation+0.826
Men
Token Men
Feature activation+1.693
'
Token'
Feature activation+0.480
recap
Token recap
Feature activation+0.000
:
Token:
Feature activation+0.000
Out
Token Out
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
C
TokenC
Feature activation+0.902
ultural
Tokenultural
Feature activation+0.537
genocide
Token genocide
Feature activation+1.707
'
Token'
Feature activation+0.361
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
new
Token new
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
Pretty
TokenPretty
Feature activation+1.292
tense
Token tense
Feature activation+1.634
'
Token'
Feature activation+0.398
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ms
TokenMs
Feature activation+0.000
T
Token T
Feature activation+0.000
cing
Tokencing
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.965
acy
Tokenacy
Feature activation+1.874
lives
Token lives
Feature activation+1.953
on
Token on
Feature activation+0.947
'
Token'
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.346 - 1.615
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Cont
TokenCont
Feature activation+0.865
iguous
Tokeniguous
Feature activation+1.459
territory
Token territory
Feature activation+1.086
'
Token'
Feature activation+0.353
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Deep
TokenDeep
Feature activation+1.453
and
Token and
Feature activation+1.394
profound
Token profound
Feature activation+1.038
issues
Token issues
Feature activation+1.602
'
Token'
Feature activation+0.001
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token'
Feature activation+0.000
Living
TokenLiving
Feature activation+0.904
in
Token in
Feature activation+1.288
An
Token An
Feature activation+0.882
caster
Tokencaster
Feature activation+1.038
,
Token,
Feature activation+1.556
water
Token water
Feature activation+0.826
my
Token my
Feature activation+0.669
garden
Token garden
Feature activation+0.125
every
Token every
Feature activation+0.000
morning
Token morning
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Deep
TokenDeep
Feature activation+1.453
and
Token and
Feature activation+1.394
profound
Token profound
Feature activation+1.038
issues
Token issues
Feature activation+1.602
'
Token'
Feature activation+0.001
Ċ
TokenĊ
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
'
Token'
Feature activation+0.000
Give
TokenGive
Feature activation+0.629
It
Token It
Feature activation+1.536
To
Token To
Feature activation+1.615
Your
Token Your
Feature activation+1.303
Woman
Token Woman
Feature activation+1.465
,
Token,
Feature activation+1.058
It
Token It
Feature activation+0.542

INTERVAL 1.077 - 1.346
CONTAINS 0.003%

'
Token'
Feature activation+0.000
Sign
TokenSign
Feature activation+0.651
ificant
Tokenificant
Feature activation+1.282
'
Token'
Feature activation+0.793
arrest
Token arrest
Feature activation+0.430
:
Token:
Feature activation+1.129
RCMP
Token RCMP
Feature activation+1.108
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Un
TokenUn
Feature activation+0.711
pleasant
Tokenpleasant
Feature activation+1.290
condition
Token condition
Feature activation+1.304
'
Token'
Feature activation+0.236
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
diabetes
Token diabetes
Feature activation+0.000
interesting
Token interesting
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
Like
TokenLike
Feature activation+1.082
going
Token going
Feature activation+2.692
into
Token into
Feature activation+2.145
a
Token a
Feature activation+0.934
time
Token time
Feature activation+1.057
machine
Token machine
Feature activation+0.854
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
I
TokenI
Feature activation+0.934
thought
Token thought
Feature activation+1.153
you
Token you
Feature activation+1.332
wanted
Token wanted
Feature activation+0.776
to
Token to
Feature activation+0.416
do
Token do
Feature activation+0.239
this
Token this
Feature activation+0.492
network
Token network
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
Experts
TokenExperts
Feature activation+1.081
say
Token say
Feature activation+1.672
it
Token it
Feature activation+1.058
's
Token's
Feature activation+0.240
increasingly
Token increasingly
Feature activation+0.000
clear
Token clear
Feature activation+0.000

INTERVAL 0.808 - 1.077
CONTAINS 0.004%

partners
Token partners
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
Make
TokenMake
Feature activation+0.821
the
Token the
Feature activation+1.113
first
Token first
Feature activation+0.829
year
Token year
Feature activation+0.496
of
Token of
Feature activation+0.152
tert
Token tert
Feature activation+0.651
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Academy
Token Academy
Feature activation+1.010
Philosophy
Token Philosophy
Feature activation+1.096
and
Token and
Feature activation+0.328
Co
Token Co
Feature activation+0.173
aching
Tokenaching
Feature activation+0.476
programme
Token programme
Feature activation+0.063
Introdu
Token Introdu
Feature activation+0.000
cing
Tokencing
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Leg
TokenLeg
Feature activation+0.965
acy
Tokenacy
Feature activation+1.874
lives
Token lives
Feature activation+1.953
on
Token on
Feature activation+0.947
'
Token'
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
prosperity
Token prosperity
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
Menu
TokenMenu
Feature activation+1.059
of
Token of
Feature activation+1.440
options
Token options
Feature activation+1.374
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Like
TokenLike
Feature activation+1.082
going
Token going
Feature activation+2.692
into
Token into
Feature activation+2.145
a
Token a
Feature activation+0.934
time
Token time
Feature activation+1.057
machine
Token machine
Feature activation+0.854
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dr
TokenDr
Feature activation+0.000
illing
Tokenilling
Feature activation+0.000

INTERVAL 0.538 - 0.808
CONTAINS 0.005%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.568
Ļ
TokenĻ
Feature activation+0.215
s
Tokens
Feature activation+0.210
no
Token no
Feature activation+0.000
big
Token big
Feature activation+0.000
secret
Token secret
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Sign
TokenSign
Feature activation+0.651
ificant
Tokenificant
Feature activation+1.282
'
Token'
Feature activation+0.793
arrest
Token arrest
Feature activation+0.430
:
Token:
Feature activation+1.129
RCMP
Token RCMP
Feature activation+1.108
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Care
TokenCare
Feature activation+1.268
ful
Tokenful
Feature activation+1.458
with
Token with
Feature activation+0.707
language
Token language
Feature activation+0.759
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
defended
Token defended
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Increase
TokenIncrease
Feature activation+0.338
student
Token student
Feature activation+1.288
allowances
Token allowances
Feature activation+0.560
and
Token and
Feature activation+0.585
living
Token living
Feature activation+0.138
cost
Token cost
Feature activation+0.190
loans
Token loans
Feature activation+0.000
by
Token by
Feature activation+0.161
$
Token $
Feature activation+0.000
refugees
Token refugees
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
T
TokenT
Feature activation+0.768
otally
Tokenotally
Feature activation+1.186
disconnected
Token disconnected
Feature activation+1.210
'
Token'
Feature activation+0.410
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.269 - 0.538
CONTAINS 0.008%

wanted
Token wanted
Feature activation+0.776
to
Token to
Feature activation+0.416
do
Token do
Feature activation+0.239
this
Token this
Feature activation+0.492
.
Token.
Feature activation+1.031
The
Token The
Feature activation+0.329
time
Token time
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
says
Token says
Feature activation+0.000
she
Token she
Feature activation+0.000
'll
Token'll
Feature activation+0.000
'
Token '
Feature activation+0.000
look
Tokenlook
Feature activation+0.059
into
Token into
Feature activation+0.421
'
Token'
Feature activation+0.000
releasing
Token releasing
Feature activation+0.000
paid
Token paid
Feature activation+0.000
speech
Token speech
Feature activation+0.000
transcripts
Token transcripts
Feature activation+0.000
spend
Token spend
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
Increase
TokenIncrease
Feature activation+0.338
student
Token student
Feature activation+1.288
allowances
Token allowances
Feature activation+0.560
and
Token and
Feature activation+0.585
living
Token living
Feature activation+0.138
cost
Token cost
Feature activation+0.190
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
'
Token'
Feature activation+0.000
VE
TokenVE
Feature activation+0.076
EVER
Token EVER
Feature activation+0.479
H
Token H
Feature activation+0.000
AD
TokenAD
Feature activation+0.313
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
DW
TokenDW
Feature activation+0.000
'
Token '
Feature activation+0.000
blown
Tokenblown
Feature activation+0.000
hugely
Token hugely
Feature activation+0.602
out
Token out
Feature activation+0.084
of
Token of
Feature activation+0.081
proportion
Token proportion
Feature activation+0.300
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000

INTERVAL 0.000 - 0.269
CONTAINS 99.976%

that
Token that
Feature activation+0.000
tries
Token tries
Feature activation+0.000
to
Token to
Feature activation+0.000
replicate
Token replicate
Feature activation+0.000
the
Token the
Feature activation+0.000
digital
Token digital
Feature activation+0.000
genre
Token genre
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
tabletop
Token tabletop
Feature activation+0.000
.
Token.
Feature activation+0.000
jury
Token jury
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
presence
Token presence
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
going
Token going
Feature activation+0.000
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
sell
Token sell
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
by
Token by
Feature activation+0.000
ilt
Tokenilt
Feature activation+0.000
U
Token U
Feature activation+0.000
class
Token class
Feature activation+0.000
(
Token (
Feature activation+0.000
details
Tokendetails
Feature activation+0.000
below
Token below
Feature activation+0.000
),
Token),
Feature activation+0.000
Kath
Token Kath
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
will
Token will
Feature activation+0.000
present
Token present
Feature activation+0.000
questioned
Token questioned
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ver
Token ver
Feature activation+0.000
acity
Tokenacity
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Cap
Token Cap
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 H3.1: (feature 12189)

TOP ACTIVATIONS
MAX = 1.925

Ċ
TokenĊ
Feature activation+0.000
Upon
TokenUpon
Feature activation+0.000
reading
Token reading
Feature activation+0.000
Open
Token Open
Feature activation+1.366
Source
Token Source
Feature activation+0.720
Application
Token Application
Feature activation+1.925
of
Token of
Feature activation+1.489
the
Token the
Feature activation+0.214
Week
Token Week
Feature activation+0.156
:
Token:
Feature activation+0.745
Op
Token Op
Feature activation+0.005
en
Tokenen
Feature activation+0.000
into
Token into
Feature activation+0.000
Spurs
Token Spurs
Feature activation+0.000
midfield
Token midfield
Feature activation+0.000
role
Token role
Feature activation+0.000
Read
Token Read
Feature activation+1.503
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.212
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Upon
TokenUpon
Feature activation+0.000
reading
Token reading
Feature activation+0.000
Open
Token Open
Feature activation+1.366
Source
Token Source
Feature activation+0.720
Application
Token Application
Feature activation+1.925
of
Token of
Feature activation+1.489
the
Token the
Feature activation+0.214
Week
Token Week
Feature activation+0.156
:
Token:
Feature activation+0.745
Op
Token Op
Feature activation+0.005
ens
Tokenens
Feature activation+0.000
(
Token (
Feature activation+0.000
PDF
TokenPDF
Feature activation+0.000
,
Token,
Feature activation+0.000
372
Token 372
Feature activation+0.236
KB
TokenKB
Feature activation+0.000
)
Token)
Feature activation+1.401
Ċ
TokenĊ
Feature activation+0.398
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
more
Token more
Feature activation+0.000
of
Token of
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Upon
TokenUpon
Feature activation+0.000
reading
Token reading
Feature activation+0.000
Open
Token Open
Feature activation+1.366
Source
Token Source
Feature activation+0.720
Application
Token Application
Feature activation+1.925
of
Token of
Feature activation+1.489
the
Token the
Feature activation+0.214
Week
Token Week
Feature activation+0.156
Read
TokenRead
Feature activation+0.000
IGN
Token IGN
Feature activation+0.765
's
Token's
Feature activation+0.000
Fallout
Token Fallout
Feature activation+0.349
4
Token 4
Feature activation+0.000
review
Token review
Feature activation+1.351
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
Editing
Token Editing
Feature activation+0.523
and
Token and
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
up
Tokenup
Feature activation+0.000
:
Token:
Feature activation+0.169
Paul
Token Paul
Feature activation+1.292
Sab
Token Sab
Feature activation+0.000
a
Tokena
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Copyright
TokenCopyright
Feature activation+0.000
oria
Tokenoria
Feature activation+0.112
Contemporary
Token Contemporary
Feature activation+0.937
Art
Token Art
Feature activation+0.245
Museum
Token Museum
Feature activation+0.457
stories
Token stories
Feature activation+0.418
.)
Token.)
Feature activation+1.244
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
push
Token push
Feature activation+0.000
back
Tokenback
Feature activation+0.000
from
Token from
Feature activation+0.000
'
Token '
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
brother
Token brother
Feature activation+0.000
'
Token'
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
Read
Token Read
Feature activation+1.140
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.094
Ċ
TokenĊ
Feature activation+0.000
Nation
TokenNation
Feature activation+0.000
wide
Tokenwide
Feature activation+0.000
EDIT
TokenEDIT
Feature activation+0.000
BEL
Token BEL
Feature activation+0.000
ON
TokenON
Feature activation+0.000
GS
TokenGS
Feature activation+0.000
TO
Token TO
Feature activation+0.000
Michael
Token Michael
Feature activation+1.102
Dante
Token Dante
Feature activation+0.000
Di
Token Di
Feature activation+0.114
Mart
TokenMart
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
,
Token,
Feature activation+0.761
but
Token but
Feature activation+0.000
no
Token no
Feature activation+0.000
combat
Token combat
Feature activation+0.000
role
Token role
Feature activation+0.000
yet
Token yet
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.098
Ċ
TokenĊ
Feature activation+0.297
Par
TokenPar
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
window
Token window
Feature activation+0.000
Read
Token Read
Feature activation+1.054
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
it
Token it
Feature activation+0.000
(
Token (
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
more
Token more
Feature activation+0.000
Cas
Token Cas
Feature activation+0.775
oria
Tokenoria
Feature activation+0.112
Contemporary
Token Contemporary
Feature activation+0.937
Art
Token Art
Feature activation+0.245
Museum
Token Museum
Feature activation+0.457
stories
Token stories
Feature activation+0.418
.)
Token.)
Feature activation+1.244
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
ï
Tokenï
Feature activation+0.000
»
Token»
Feature activation+0.000
¿
Token¿
Feature activation+0.000
Read
Token Read
Feature activation+0.000
Tracy
Token Tracy
Feature activation+0.887
's
Token's
Feature activation+0.446
books
Token books
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
option
Token option
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
think
Token think
Feature activation+0.000
tank
Tokentank
Feature activation+0.000
Read
Token Read
Feature activation+0.852
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.752
Ċ
TokenĊ
Feature activation+0.384
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
as
Token as
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
slows
Token slows
Feature activation+0.000
Read
Token Read
Feature activation+0.846
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.000
to
Token to
Feature activation+0.000
Diane
Token Diane
Feature activation+0.496
Ts
Token Ts
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
at
Token at
Feature activation+0.000
d
Token d
Feature activation+0.821
iane
Tokeniane
Feature activation+0.141
.
Token.
Feature activation+0.556
ts
Tokents
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
@
Token@
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.105
:
Token:
Feature activation+0.789
BMW
Token BMW
Feature activation+0.728
Concept
Token Concept
Feature activation+0.079
X
Token X
Feature activation+0.000
7
Token7
Feature activation+0.447
i
Token i
Feature activation+0.586
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
more
Token more
Feature activation+0.000
Cas
Token Cas
Feature activation+0.775
oria
Tokenoria
Feature activation+0.112
Contemporary
Token Contemporary
Feature activation+0.937
Art
Token Art
Feature activation+0.245
Museum
Token Museum
Feature activation+0.457
stories
Token stories
Feature activation+0.418
Michael
Token Michael
Feature activation+1.102
Dante
Token Dante
Feature activation+0.000
Di
Token Di
Feature activation+0.114
Mart
TokenMart
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
,
Token,
Feature activation+0.761
Bryan
Token Bryan
Feature activation+0.407
Kon
Token Kon
Feature activation+0.000
iet
Tokeniet
Feature activation+0.000
z
Tokenz
Feature activation+0.000
ko
Tokenko
Feature activation+0.000

Top DFA by src position
MAX = 3.201

,
Token,
Feature activation-0.005
Top resid features:
2017
Token 2017
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Upon
TokenUpon
Feature activation-0.016
Top resid features:
reading
Token reading
Feature activation+3.201
Top resid features:
Open
Token Open
Feature activation-0.109
Top resid features:
Source
Token Source
Feature activation-0.316
Top resid features:
Application
Token Application
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation-0.002
Top resid features:
into
Token into
Feature activation+0.030
Top resid features:
Spurs
Token Spurs
Feature activation-0.003
Top resid features:
midfield
Token midfield
Feature activation+0.003
Top resid features:
role
Token role
Feature activation+0.017
Top resid features:
Read
Token Read
Feature activation+2.049
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
2017
Token 2017
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Upon
TokenUpon
Feature activation-0.022
Top resid features:
reading
Token reading
Feature activation+2.175
Top resid features:
Open
Token Open
Feature activation+0.053
Top resid features:
Source
Token Source
Feature activation+0.016
Top resid features:
Application
Token Application
Feature activation-0.034
Top resid features:
of
Token of
Feature activation+0.121
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
professional
Token professional
Feature activation-0.000
Top resid features:
drones
Token drones
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Download
TokenDownload
Feature activation+2.042
Top resid features:
(
Token (
Feature activation+0.002
Top resid features:
PDF
TokenPDF
Feature activation+0.182
Top resid features:
,
Token,
Feature activation+0.057
Top resid features:
372
Token 372
Feature activation+0.016
Top resid features:
KB
TokenKB
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
2017
Token 2017
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Upon
TokenUpon
Feature activation-0.011
Top resid features:
reading
Token reading
Feature activation+2.255
Top resid features:
Open
Token Open
Feature activation+0.006
Top resid features:
Source
Token Source
Feature activation+0.000
Top resid features:
Application
Token Application
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.268
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Read
TokenRead
Feature activation+2.065
Top resid features:
IGN
Token IGN
Feature activation+0.039
Top resid features:
's
Token's
Feature activation+0.204
Top resid features:
Fallout
Token Fallout
Feature activation-0.115
Top resid features:
4
Token 4
Feature activation-0.119
Top resid features:
review
Token review
Feature activation+0.066
Top resid features:
1981
Token 1981
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Trans
TokenTrans
Feature activation+0.008
Top resid features:
cription
Tokencription
Feature activation+2.081
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
Editing
Token Editing
Feature activation+0.134
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
Mark
Token Mark
Feature activation-0.003
Top resid features:
up
Tokenup
Feature activation-0.056
Top resid features:
,"
Token,"
Feature activation+0.037
Top resid features:
he
Token he
Feature activation-0.001
Top resid features:
said
Token said
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.061
Top resid features:
(
Token (
Feature activation+0.048
Top resid features:
Read
TokenRead
Feature activation+1.817
Top resid features:
more
Token more
Feature activation+0.174
Top resid features:
Cas
Token Cas
Feature activation+0.010
Top resid features:
oria
Tokenoria
Feature activation-0.010
Top resid features:
Contemporary
Token Contemporary
Feature activation+0.002
Top resid features:
Art
Token Art
Feature activation+0.009
Top resid features:
'
Token '
Feature activation+0.007
Top resid features:
big
Tokenbig
Feature activation+0.000
Top resid features:
brother
Token brother
Feature activation-0.013
Top resid features:
'
Token'
Feature activation+0.033
Top resid features:
concerns
Token concerns
Feature activation-0.039
Top resid features:
Read
Token Read
Feature activation+1.742
Top resid features:
more
Token more
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:
Nation
TokenNation
Feature activation+0.000
Top resid features:
wide
Tokenwide
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
ALL
TokenALL
Feature activation+0.032
Top resid features:
CR
Token CR
Feature activation+0.011
Top resid features:
EDIT
TokenEDIT
Feature activation+1.907
Top resid features:
BEL
Token BEL
Feature activation+0.012
Top resid features:
ON
TokenON
Feature activation-0.007
Top resid features:
GS
TokenGS
Feature activation+0.067
Top resid features:
TO
Token TO
Feature activation+0.027
Top resid features:
Michael
Token Michael
Feature activation-0.047
Top resid features:
regard
Token regard
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Also
TokenAlso
Feature activation+0.005
Top resid features:
Read
Token Read
Feature activation+1.603
Top resid features:
:
Token:
Feature activation+0.369
Top resid features:
Navy
Token Navy
Feature activation-0.000
Top resid features:
pitches
Token pitches
Feature activation-0.010
Top resid features:
for
Token for
Feature activation+0.006
Top resid features:
women
Token women
Feature activation+0.001
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
Arsenal
Token Arsenal
Feature activation-0.008
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
January
Token January
Feature activation+0.017
Top resid features:
window
Token window
Feature activation-0.027
Top resid features:
Read
Token Read
Feature activation+1.874
Top resid features:
more
Token more
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:
But
TokenBut
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.018
Top resid features:
he
Token he
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.070
Top resid features:
(
Token (
Feature activation+0.106
Top resid features:
Read
TokenRead
Feature activation+1.730
Top resid features:
more
Token more
Feature activation+0.087
Top resid features:
Cas
Token Cas
Feature activation-0.021
Top resid features:
oria
Tokenoria
Feature activation-0.264
Top resid features:
Contemporary
Token Contemporary
Feature activation+0.097
Top resid features:
Art
Token Art
Feature activation+0.000
Top resid features:
Series
Token Series
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
ï
Tokenï
Feature activation+0.001
Top resid features:
»
Token»
Feature activation+0.016
Top resid features:
¿
Token¿
Feature activation+0.126
Top resid features:
Read
Token Read
Feature activation+1.470
Top resid features:
Tracy
Token Tracy
Feature activation+0.032
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
books
Token books
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
option
Token option
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
says
Token says
Feature activation+0.037
Top resid features:
think
Token think
Feature activation+0.025
Top resid features:
tank
Tokentank
Feature activation-0.142
Top resid features:
Read
Token Read
Feature activation+1.604
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
2018
Token 2018
Feature activation-0.043
Top resid features:
as
Token as
Feature activation+0.025
Top resid features:
Earth
Token Earth
Feature activation-0.045
Top resid features:
rotation
Token rotation
Feature activation-0.005
Top resid features:
slows
Token slows
Feature activation-0.052
Top resid features:
Read
Token Read
Feature activation+1.619
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
000
Token000
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
Write
TokenWrite
Feature activation+1.401
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
Diane
Token Diane
Feature activation+0.002
Top resid features:
Ts
Token Ts
Feature activation+0.013
Top resid features:
ai
Tokenai
Feature activation-0.015
Top resid features:
at
Token at
Feature activation+0.096
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
Also
TokenAlso
Feature activation+0.218
Top resid features:
Read
Token Read
Feature activation+1.314
Top resid features:
:
Token:
Feature activation+0.015
Top resid features:
BMW
Token BMW
Feature activation+0.000
Top resid features:
Concept
Token Concept
Feature activation+0.000
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
7
Token7
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.022
Top resid features:
he
Token he
Feature activation-0.000
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
(
Token (
Feature activation+0.062
Top resid features:
Read
TokenRead
Feature activation+1.552
Top resid features:
more
Token more
Feature activation-0.041
Top resid features:
Cas
Token Cas
Feature activation-0.003
Top resid features:
oria
Tokenoria
Feature activation+0.000
Top resid features:
Contemporary
Token Contemporary
Feature activation+0.000
Top resid features:
Art
Token Art
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
ALL
TokenALL
Feature activation+0.099
Top resid features:
CR
Token CR
Feature activation+0.006
Top resid features:
EDIT
TokenEDIT
Feature activation+1.254
Top resid features:
BEL
Token BEL
Feature activation+0.016
Top resid features:
ON
TokenON
Feature activation+0.001
Top resid features:
GS
TokenGS
Feature activation+0.040
Top resid features:
TO
Token TO
Feature activation+0.107
Top resid features:
Michael
Token Michael
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.43

Head 2: 0.05

Head 3: 0.03

Head 4: 0.05

Head 5: 0.07

Head 6: 0.05

Head 7: 0.05

Head 8: 0.06

Head 9: 0.07

Head 10: 0.06

Head 11: 0.07

Positive logits

.)2.02

').1.73

!]1.72

Replay1.67

!)1.66

OTOS1.65

!'1.58

diary1.58

bernatorial1.54

!'"1.50

-)1.49

')1.49

]'1.48

)'1.48

'."1.47

.)1.47

';1.46

Topics1.45

.'"1.45

irection1.45

Negative logits

exha-1.72

nown-1.63

btn-1.63

srfAttach-1.56

conservancy-1.55

bably-1.42

Ashe-1.42

byss-1.37

ortunately-1.34

mbuds-1.33

Roses-1.32

roth-1.29

atever-1.29

sshd-1.28

raltar-1.28

profits-1.28

Corps-1.27

Magicka-1.27

represented-1.27

��-1.26

INTERVAL 1.732 - 1.925
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Upon
TokenUpon
Feature activation+0.000
reading
Token reading
Feature activation+0.000
Open
Token Open
Feature activation+1.366
Source
Token Source
Feature activation+0.720
Application
Token Application
Feature activation+1.925
of
Token of
Feature activation+1.489
the
Token the
Feature activation+0.214
Week
Token Week
Feature activation+0.156
:
Token:
Feature activation+0.745
Op
Token Op
Feature activation+0.005

INTERVAL 1.540 - 1.732
CONTAINS 0.000%

INTERVAL 1.347 - 1.540
CONTAINS 0.001%

Read
TokenRead
Feature activation+0.000
IGN
Token IGN
Feature activation+0.765
's
Token's
Feature activation+0.000
Fallout
Token Fallout
Feature activation+0.349
4
Token 4
Feature activation+0.000
review
Token review
Feature activation+1.351
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
(
Token (
Feature activation+0.000
PDF
TokenPDF
Feature activation+0.000
,
Token,
Feature activation+0.000
372
Token 372
Feature activation+0.236
KB
TokenKB
Feature activation+0.000
)
Token)
Feature activation+1.401
Ċ
TokenĊ
Feature activation+0.398
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
more
Token more
Feature activation+0.000
of
Token of
Feature activation+0.000
en
Tokenen
Feature activation+0.000
into
Token into
Feature activation+0.000
Spurs
Token Spurs
Feature activation+0.000
midfield
Token midfield
Feature activation+0.000
role
Token role
Feature activation+0.000
Read
Token Read
Feature activation+1.503
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.212
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Upon
TokenUpon
Feature activation+0.000
reading
Token reading
Feature activation+0.000
Open
Token Open
Feature activation+1.366
Source
Token Source
Feature activation+0.720
Application
Token Application
Feature activation+1.925
of
Token of
Feature activation+1.489
the
Token the
Feature activation+0.214
Week
Token Week
Feature activation+0.156
Upon
TokenUpon
Feature activation+0.000
reading
Token reading
Feature activation+0.000
Open
Token Open
Feature activation+1.366
Source
Token Source
Feature activation+0.720
Application
Token Application
Feature activation+1.925
of
Token of
Feature activation+1.489
the
Token the
Feature activation+0.214
Week
Token Week
Feature activation+0.156
:
Token:
Feature activation+0.745
Op
Token Op
Feature activation+0.005
ens
Tokenens
Feature activation+0.000

INTERVAL 1.155 - 1.347
CONTAINS 0.000%

oria
Tokenoria
Feature activation+0.112
Contemporary
Token Contemporary
Feature activation+0.937
Art
Token Art
Feature activation+0.245
Museum
Token Museum
Feature activation+0.457
stories
Token stories
Feature activation+0.418
.)
Token.)
Feature activation+1.244
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
push
Token push
Feature activation+0.000
back
Tokenback
Feature activation+0.000
from
Token from
Feature activation+0.000
Editing
Token Editing
Feature activation+0.523
and
Token and
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
up
Tokenup
Feature activation+0.000
:
Token:
Feature activation+0.169
Paul
Token Paul
Feature activation+1.292
Sab
Token Sab
Feature activation+0.000
a
Tokena
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Copyright
TokenCopyright
Feature activation+0.000

INTERVAL 0.962 - 1.155
CONTAINS 0.000%

'
Token '
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
brother
Token brother
Feature activation+0.000
'
Token'
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
Read
Token Read
Feature activation+1.140
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.094
Ċ
TokenĊ
Feature activation+0.000
Nation
TokenNation
Feature activation+0.000
wide
Tokenwide
Feature activation+0.000
but
Token but
Feature activation+0.000
no
Token no
Feature activation+0.000
combat
Token combat
Feature activation+0.000
role
Token role
Feature activation+0.000
yet
Token yet
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.098
Ċ
TokenĊ
Feature activation+0.297
Par
TokenPar
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
Arsenal
Token Arsenal
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
window
Token window
Feature activation+0.000
Read
Token Read
Feature activation+1.054
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
it
Token it
Feature activation+0.000
EDIT
TokenEDIT
Feature activation+0.000
BEL
Token BEL
Feature activation+0.000
ON
TokenON
Feature activation+0.000
GS
TokenGS
Feature activation+0.000
TO
Token TO
Feature activation+0.000
Michael
Token Michael
Feature activation+1.102
Dante
Token Dante
Feature activation+0.000
Di
Token Di
Feature activation+0.114
Mart
TokenMart
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
,
Token,
Feature activation+0.761

INTERVAL 0.770 - 0.962
CONTAINS 0.001%

to
Token to
Feature activation+0.000
Diane
Token Diane
Feature activation+0.496
Ts
Token Ts
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
at
Token at
Feature activation+0.000
d
Token d
Feature activation+0.821
iane
Tokeniane
Feature activation+0.141
.
Token.
Feature activation+0.556
ts
Tokents
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
@
Token@
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
more
Token more
Feature activation+0.000
Cas
Token Cas
Feature activation+0.775
oria
Tokenoria
Feature activation+0.112
Contemporary
Token Contemporary
Feature activation+0.937
Art
Token Art
Feature activation+0.245
Museum
Token Museum
Feature activation+0.457
stories
Token stories
Feature activation+0.418
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.105
:
Token:
Feature activation+0.789
BMW
Token BMW
Feature activation+0.728
Concept
Token Concept
Feature activation+0.079
X
Token X
Feature activation+0.000
7
Token7
Feature activation+0.447
i
Token i
Feature activation+0.586
(
Token (
Feature activation+0.000
Read
TokenRead
Feature activation+0.000
more
Token more
Feature activation+0.000
Cas
Token Cas
Feature activation+0.775
oria
Tokenoria
Feature activation+0.112
Contemporary
Token Contemporary
Feature activation+0.937
Art
Token Art
Feature activation+0.245
Museum
Token Museum
Feature activation+0.457
stories
Token stories
Feature activation+0.418
.)
Token.)
Feature activation+1.244
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
option
Token option
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
think
Token think
Feature activation+0.000
tank
Tokentank
Feature activation+0.000
Read
Token Read
Feature activation+0.852
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.752
Ċ
TokenĊ
Feature activation+0.384
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 0.577 - 0.770
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.105
:
Token:
Feature activation+0.789
BMW
Token BMW
Feature activation+0.728
Concept
Token Concept
Feature activation+0.079
X
Token X
Feature activation+0.000
7
Token7
Feature activation+0.447
i
Token i
Feature activation+0.586
Performance
TokenPerformance
Feature activation+0.000
/
Token/
Feature activation+0.000
s
Tokens
Feature activation+0.000
Read
Token Read
Feature activation+0.142
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
311
Token 311
Feature activation+0.604
37
Token37
Feature activation+0.390
MB
Token MB
Feature activation+0.000
/
Token/
Feature activation+0.000
s
Tokens
Feature activation+0.000
Writ
Token Writ
Feature activation+0.000
Michael
Token Michael
Feature activation+1.102
Dante
Token Dante
Feature activation+0.000
Di
Token Di
Feature activation+0.114
Mart
TokenMart
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
,
Token,
Feature activation+0.761
Bryan
Token Bryan
Feature activation+0.407
Kon
Token Kon
Feature activation+0.000
iet
Tokeniet
Feature activation+0.000
z
Tokenz
Feature activation+0.000
ko
Tokenko
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.004
Donald
Token Donald
Feature activation+0.668
Trump
Token Trump
Feature activation+0.658
Makes
Token Makes
Feature activation+0.465
History
Token History
Feature activation+0.000
With
Token With
Feature activation+0.000
Zero
Token Zero
Feature activation+0.000
Major
Token Major
Feature activation+0.000
.
Token.
Feature activation+0.000
Better
Token Better
Feature activation+0.000
yet
Token yet
Feature activation+0.000
,
Token,
Feature activation+0.000
read
Token read
Feature activation+0.000
P
Token P
Feature activation+0.595
FF
TokenFF
Feature activation+0.288
's
Token's
Feature activation+0.465
detailed
Token detailed
Feature activation+0.000
FAQ
Token FAQ
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.385 - 0.577
CONTAINS 0.004%

1
Token 1
Feature activation+0.475
,
Token,
Feature activation+0.027
000
Token000
Feature activation+0.186
miles
Token miles
Feature activation+0.000
from
Token from
Feature activation+0.000
POL
Token POL
Feature activation+0.436
AND
TokenAND
Feature activation+0.000
to
Token to
Feature activation+0.000
London
Token London
Feature activation+0.000
because
Token because
Feature activation+0.281
it
Token it
Feature activation+0.000
ï
Tokenï
Feature activation+0.000
»
Token»
Feature activation+0.000
¿
Token¿
Feature activation+0.000
Read
Token Read
Feature activation+0.000
Tracy
Token Tracy
Feature activation+0.887
's
Token's
Feature activation+0.446
books
Token books
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
.
Token.
Feature activation+0.000
Read
Token Read
Feature activation+0.000
erotic
Token erotic
Feature activation+0.000
poetry
Token poetry
Feature activation+0.000
of
Token of
Feature activation+0.000
Jay
Token Jay
Feature activation+0.484
ade
Tokenade
Feature activation+0.000
va
Tokenva
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.264
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Rainbow
Token Rainbow
Feature activation+0.071
host
Token host
Feature activation+0.524
Le
Token Le
Feature activation+0.099
Var
TokenVar
Feature activation+0.000
Burton
Token Burton
Feature activation+0.380
,
Token,
Feature activation+0.437
winner
Token winner
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
1989
Token 1989
Feature activation+0.000
Help
Token Help
Feature activation+0.000
smoother
Token smoother
Feature activation+0.000
lives
Token lives
Feature activation+0.000
through
Token through
Feature activation+0.000
digital
Token digital
Feature activation+0.000
connectivity
Token connectivity
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.385
Ċ
TokenĊ
Feature activation+0.000
Since
TokenSince
Feature activation+0.000
last
Token last
Feature activation+0.000
July
Token July
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.192 - 0.385
CONTAINS 0.005%

Time
Token Time
Feature activation+0.252
--
Token --
Feature activation+0.139
7
Token 7
Feature activation+0.147
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Worst
Token Worst
Feature activation+0.223
Blizz
Token Blizz
Feature activation+0.000
ards
Tokenards
Feature activation+0.000
To
Token To
Feature activation+0.000
Ever
Token Ever
Feature activation+0.000
Hit
Token Hit
Feature activation+0.000
tap
Token tap
Feature activation+0.000
here
Token here
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
SB
Token SB
Feature activation+0.322
140
Token140
Feature activation+0.356
.
Token.
Feature activation+0.102
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
Copyright
TokenCopyright
Feature activation+0.000
full
Token full
Feature activation+0.000
report
Token report
Feature activation+0.000
at
Token at
Feature activation+0.000
Climate
Token Climate
Feature activation+0.569
Audit
Token Audit
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.353
Ċ
TokenĊ
Feature activation+0.000
================================
Token================================
Feature activation+0.000
================
Token================
Feature activation+0.000
========
Token========
Feature activation+0.000
===
Token===
Feature activation+0.000
Reading
Token Reading
Feature activation+0.297
Rainbow
Token Rainbow
Feature activation+0.071
host
Token host
Feature activation+0.524
Le
Token Le
Feature activation+0.099
Var
TokenVar
Feature activation+0.000
Burton
Token Burton
Feature activation+0.380
,
Token,
Feature activation+0.437
winner
Token winner
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
1989
Token 1989
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
READ
TokenREAD
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Mass
Token Mass
Feature activation+0.000
shooting
Token shooting
Feature activation+0.219
at
Token at
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.286
gay
Token gay
Feature activation+0.000
nightclub
Token nightclub
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.192
CONTAINS 99.987%

the
Token the
Feature activation+0.000
relevant
Token relevant
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
spec
Token spec
Feature activation+0.000
,
Token,
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
can
Token can
Feature activation+0.000
the
Token the
Feature activation+0.000
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.000
pediatric
Token pediatric
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
and
Token and
Feature activation+0.000
neon
Token neon
Feature activation+0.000
atal
Tokenatal
Feature activation+0.000
specialist
Token specialist
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
[
Token [
Feature activation+0.000
out
Tokenout
Feature activation+0.000
in
Token in
Feature activation+0.000
hex
Token hex
Feature activation+0.000
es
Tokenes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Honestly
TokenHonestly
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
KA
TokenKA
Feature activation+0.000
Designs
Token Designs
Feature activation+0.000
claims
Token claims
Feature activation+0.000
that
Token that
Feature activation+0.000
their
Token their
Feature activation+0.000
intention
Token intention
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
skill
Token skill
Feature activation+0.000
and
Token and
Feature activation+0.000
flexibility
Token flexibility
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
human
Token human
Feature activation+0.000
limb
Token limb
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H3.1: (feature 17279)

TOP ACTIVATIONS
MAX = 4.635

,
Token,
Feature activation+0.000
Gim
Token Gim
Feature activation+1.875
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
Gim
Token Gim
Feature activation+1.875
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
sters
Tokensters
Feature activation+2.979
his
Token his
Feature activation+0.000
book
Token book
Feature activation+0.000
W
Token W
Feature activation+1.438
aking
Tokenaking
Feature activation+2.255
Up
Token Up
Feature activation+2.646
:
Token:
Feature activation+4.312
A
Token A
Feature activation+4.083
Guide
Token Guide
Feature activation+2.974
to
Token to
Feature activation+1.588
Spirit
Token Spirit
Feature activation+1.871
uality
Tokenuality
Feature activation+3.303
his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
Oxford
Token Oxford
Feature activation+1.547
book
Token book
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.203
ľ
Tokenľ
Feature activation+0.000
Block
TokenBlock
Feature activation+2.619
chain
Tokenchain
Feature activation+2.750
:
Token:
Feature activation+4.162
Blueprint
Token Blueprint
Feature activation+4.138
for
Token for
Feature activation+2.322
a
Token a
Feature activation+0.810
New
Token New
Feature activation+1.506
Economy
Token Economy
Feature activation+1.660
âĢ
Token âĢ
Feature activation+0.203
ľ
Tokenľ
Feature activation+0.000
Block
TokenBlock
Feature activation+2.619
chain
Tokenchain
Feature activation+2.750
:
Token:
Feature activation+4.162
Blueprint
Token Blueprint
Feature activation+4.138
for
Token for
Feature activation+2.322
a
Token a
Feature activation+0.810
New
Token New
Feature activation+1.506
Economy
Token Economy
Feature activation+1.660
,
Token,
Feature activation+0.981
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.142
ľ
Tokenľ
Feature activation+0.000
Who
TokenWho
Feature activation+1.305
Are
Token Are
Feature activation+4.115
We
Token We
Feature activation+3.319
?
Token?
Feature activation+3.217
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
book
Token book
Feature activation+0.000
W
Token W
Feature activation+1.438
aking
Tokenaking
Feature activation+2.255
Up
Token Up
Feature activation+2.646
:
Token:
Feature activation+4.312
A
Token A
Feature activation+4.083
Guide
Token Guide
Feature activation+2.974
to
Token to
Feature activation+1.588
Spirit
Token Spirit
Feature activation+1.871
uality
Tokenuality
Feature activation+3.303
without
Token without
Feature activation+0.481
2010
Token 2010
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
Oxford
Token Oxford
Feature activation+1.547
-
Token-
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.270
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.627
Closing
Token Closing
Feature activation+4.033
of
Token of
Feature activation+2.141
the
Token the
Feature activation+1.190
Liberal
Token Liberal
Feature activation+0.716
Mind
Token Mind
Feature activation+2.767
âĢ
TokenâĢ
Feature activation+0.035
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Gim
Token Gim
Feature activation+1.875
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
er
Tokener
Feature activation+0.000
's
Token's
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
book
Token book
Feature activation+0.000
The
Token The
Feature activation+2.406
Better
Token Better
Feature activation+3.982
Angels
Token Angels
Feature activation+2.352
of
Token of
Feature activation+2.642
Our
Token Our
Feature activation+3.546
Nature
Token Nature
Feature activation+2.615
,
Token,
Feature activation+0.734
,
Token,
Feature activation+0.000
Evangel
Token Evangel
Feature activation+3.069
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
Semin
Token Semin
Feature activation+1.699
arians
Tokenarians
Feature activation+2.367
and
Token and
Feature activation+0.780
Their
Token Their
Feature activation+1.929
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
Oxford
Token Oxford
Feature activation+1.547
-
Token-
Feature activation+0.000
educated
Tokeneducated
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Evangel
Token Evangel
Feature activation+3.069
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
Semin
Token Semin
Feature activation+1.699
arians
Tokenarians
Feature activation+2.367
and
Token and
Feature activation+0.780
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
sters
Tokensters
Feature activation+2.979
,
Token,
Feature activation+1.129
book
Token book
Feature activation+0.000
The
Token The
Feature activation+2.406
Better
Token Better
Feature activation+3.982
Angels
Token Angels
Feature activation+2.352
of
Token of
Feature activation+2.642
Our
Token Our
Feature activation+3.546
Nature
Token Nature
Feature activation+2.615
,
Token,
Feature activation+0.734
I
Token I
Feature activation+0.947
wrote
Token wrote
Feature activation+0.000
:
Token:
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Dis
Token Dis
Feature activation+2.645
pir
Tokenpir
Feature activation+1.235
ited
Tokenited
Feature activation+2.915
:
Token:
Feature activation+3.516
How
Token How
Feature activation+3.312
Contemporary
Token Contemporary
Feature activation+1.043
Spirit
Token Spirit
Feature activation+0.694
uality
Tokenuality
Feature activation+2.234
Makes
Token Makes
Feature activation+0.562
,
Token,
Feature activation+0.000
The
Token The
Feature activation+2.338
Low
Token Low
Feature activation+2.297
down
Tokendown
Feature activation+3.353
on
Token on
Feature activation+2.481
Witches
Token Witches
Feature activation+3.396
.
Token.
Feature activation+0.159
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Leon
TokenLeon
Feature activation+0.000
ard
Tokenard
Feature activation+0.000

Top DFA by src position
MAX = 5.362

2003
Token 2003
Feature activation-0.021
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
published
Token published
Feature activation+0.027
Top resid features:
his
Token his
Feature activation+0.043
Top resid features:
first
Token first
Feature activation-0.051
Top resid features:
book
Token book
Feature activation+5.235
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
Gim
Token Gim
Feature activation+0.038
Top resid features:
me
Tokenme
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.152
Top resid features:
Break
Token Break
Feature activation-0.017
Top resid features:
2003
Token 2003
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
published
Token published
Feature activation+0.044
Top resid features:
his
Token his
Feature activation+0.022
Top resid features:
first
Token first
Feature activation-0.018
Top resid features:
book
Token book
Feature activation+5.362
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
Gim
Token Gim
Feature activation+0.029
Top resid features:
me
Tokenme
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
Break
Token Break
Feature activation+0.009
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.475
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
his
Token his
Feature activation+0.052
Top resid features:
book
Token book
Feature activation+4.889
Top resid features:
W
Token W
Feature activation+0.154
Top resid features:
aking
Tokenaking
Feature activation-0.058
Top resid features:
Up
Token Up
Feature activation+0.087
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
In
Token In
Feature activation-0.002
Top resid features:
his
Token his
Feature activation+0.061
Top resid features:
2010
Token 2010
Feature activation-0.028
Top resid features:
book
Token book
Feature activation+4.893
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
Million
Token Million
Feature activation+0.086
Top resid features:
aire
Tokenaire
Feature activation+0.033
Top resid features:
M
Token M
Feature activation+0.000
Top resid features:
igrants
Tokenigrants
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
In
TokenIn
Feature activation-0.001
Top resid features:
her
Token her
Feature activation+0.086
Top resid features:
2015
Token 2015
Feature activation-0.044
Top resid features:
book
Token book
Feature activation+4.812
Top resid features:
âĢ
Token âĢ
Feature activation+0.033
Top resid features:
ľ
Tokenľ
Feature activation-0.003
Top resid features:
Block
TokenBlock
Feature activation+0.034
Top resid features:
chain
Tokenchain
Feature activation+0.039
Top resid features:
:
Token:
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
In
TokenIn
Feature activation+0.001
Top resid features:
her
Token her
Feature activation+0.062
Top resid features:
2015
Token 2015
Feature activation+0.003
Top resid features:
book
Token book
Feature activation+4.878
Top resid features:
âĢ
Token âĢ
Feature activation+0.005
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Block
TokenBlock
Feature activation+0.008
Top resid features:
chain
Tokenchain
Feature activation-0.017
Top resid features:
:
Token:
Feature activation+0.120
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
writing
Token writing
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
his
Token his
Feature activation+0.030
Top resid features:
last
Token last
Feature activation-0.010
Top resid features:
book
Token book
Feature activation+4.632
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
âĢ
Token âĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.015
Top resid features:
Who
TokenWho
Feature activation+0.190
Top resid features:
Are
Token Are
Feature activation+0.043
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.438
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
his
Token his
Feature activation+0.025
Top resid features:
book
Token book
Feature activation+4.938
Top resid features:
W
Token W
Feature activation+0.045
Top resid features:
aking
Tokenaking
Feature activation-0.056
Top resid features:
Up
Token Up
Feature activation+0.048
Top resid features:
:
Token:
Feature activation-0.070
Top resid features:
A
Token A
Feature activation+0.002
Top resid features:
there
Token there
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
In
Token In
Feature activation+0.006
Top resid features:
his
Token his
Feature activation+0.066
Top resid features:
2010
Token 2010
Feature activation+0.012
Top resid features:
book
Token book
Feature activation+4.648
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
Million
Token Million
Feature activation+0.027
Top resid features:
aire
Tokenaire
Feature activation-0.029
Top resid features:
M
Token M
Feature activation+0.047
Top resid features:
igrants
Tokenigrants
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
explain
Token explain
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
my
Token my
Feature activation+0.036
Top resid features:
forthcoming
Token forthcoming
Feature activation+0.047
Top resid features:
book
Token book
Feature activation+4.519
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
âĢ
Token âĢ
Feature activation+0.033
Top resid features:
ľ
Tokenľ
Feature activation-0.004
Top resid features:
The
TokenThe
Feature activation+0.162
Top resid features:
Closing
Token Closing
Feature activation+0.026
Top resid features:
2003
Token 2003
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
published
Token published
Feature activation+0.042
Top resid features:
his
Token his
Feature activation+0.041
Top resid features:
first
Token first
Feature activation-0.012
Top resid features:
book
Token book
Feature activation+4.390
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
Gim
Token Gim
Feature activation+0.130
Top resid features:
me
Tokenme
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.192
Top resid features:
Break
Token Break
Feature activation+0.041
Top resid features:
there
Token there
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
In
Token In
Feature activation+0.003
Top resid features:
his
Token his
Feature activation+0.053
Top resid features:
2010
Token 2010
Feature activation-0.031
Top resid features:
book
Token book
Feature activation+4.658
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
Million
Token Million
Feature activation+0.101
Top resid features:
aire
Tokenaire
Feature activation+0.000
Top resid features:
M
Token M
Feature activation+0.000
Top resid features:
igrants
Tokenigrants
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.451
Top resid features:
Pink
Token Pink
Feature activation-0.016
Top resid features:
er
Tokener
Feature activation+0.006
Top resid features:
's
Token's
Feature activation+0.016
Top resid features:
2011
Token 2011
Feature activation-0.001
Top resid features:
book
Token book
Feature activation+4.681
Top resid features:
The
Token The
Feature activation+0.008
Top resid features:
Better
Token Better
Feature activation+0.122
Top resid features:
Angels
Token Angels
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Our
Token Our
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.030
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
new
Token new
Feature activation+0.010
Top resid features:
book
Token book
Feature activation+4.555
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
Evangel
Token Evangel
Feature activation+0.086
Top resid features:
ical
Tokenical
Feature activation-0.022
Top resid features:
Exodus
Token Exodus
Feature activation+0.010
Top resid features:
:
Token:
Feature activation-0.023
Top resid features:
there
Token there
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
In
Token In
Feature activation+0.012
Top resid features:
his
Token his
Feature activation+0.041
Top resid features:
2010
Token 2010
Feature activation-0.040
Top resid features:
book
Token book
Feature activation+4.673
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
Million
Token Million
Feature activation-0.174
Top resid features:
aire
Tokenaire
Feature activation-0.034
Top resid features:
M
Token M
Feature activation+0.043
Top resid features:
igrants
Tokenigrants
Feature activation-0.014
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.023
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
new
Token new
Feature activation+0.009
Top resid features:
book
Token book
Feature activation+4.347
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
Evangel
Token Evangel
Feature activation+0.016
Top resid features:
ical
Tokenical
Feature activation-0.005
Top resid features:
Exodus
Token Exodus
Feature activation+0.069
Top resid features:
:
Token:
Feature activation-0.008
Top resid features:
2003
Token 2003
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
published
Token published
Feature activation+0.055
Top resid features:
his
Token his
Feature activation+0.050
Top resid features:
first
Token first
Feature activation-0.001
Top resid features:
book
Token book
Feature activation+4.102
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
Gim
Token Gim
Feature activation+0.032
Top resid features:
me
Tokenme
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.032
Top resid features:
Break
Token Break
Feature activation+0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.481
Top resid features:
Pink
Token Pink
Feature activation+0.000
Top resid features:
er
Tokener
Feature activation+0.003
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
2011
Token 2011
Feature activation+0.053
Top resid features:
book
Token book
Feature activation+4.076
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
Better
Token Better
Feature activation-0.038
Top resid features:
Angels
Token Angels
Feature activation+0.055
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
Our
Token Our
Feature activation+0.136
Top resid features:
religion
Token religion
Feature activation-0.012
Top resid features:
David
Token David
Feature activation+0.000
Top resid features:
Webster
Token Webster
Feature activation-0.022
Top resid features:
in
Token in
Feature activation+0.051
Top resid features:
his
Token his
Feature activation+0.049
Top resid features:
book
Token book
Feature activation+4.149
Top resid features:
,
Token,
Feature activation+0.072
Top resid features:
Dis
Token Dis
Feature activation+0.162
Top resid features:
pir
Tokenpir
Feature activation-0.007
Top resid features:
ited
Tokenited
Feature activation-0.036
Top resid features:
:
Token:
Feature activation+0.040
Top resid features:
out
Token out
Feature activation+0.010
Top resid features:
research
Token research
Feature activation+0.021
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
his
Token his
Feature activation+0.014
Top resid features:
next
Token next
Feature activation+0.009
Top resid features:
book
Token book
Feature activation+3.586
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
The
Token The
Feature activation+0.032
Top resid features:
Low
Token Low
Feature activation+0.031
Top resid features:
down
Tokendown
Feature activation+0.063
Top resid features:
on
Token on
Feature activation+0.225
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.43

Head 2: 0.08

Head 3: 0.04

Head 4: 0.02

Head 5: 0.04

Head 6: 0.06

Head 7: 0.07

Head 8: 0.06

Head 9: 0.05

Head 10: 0.06

Head 11: 0.07

Positive logits

.)1.86

Volume1.68

Manifest1.63

."1.62

Agent1.55

Handbook1.54

Haunted1.53

.")1.52

Relationship1.52

Agents1.51

Diary1.48

].1.45

copy1.45

Concert1.44

)]1.44

Therapy1.42

').1.41

"]1.40

").1.39

 1.38

Negative logits

srfAttach-1.67

=\"-1.64

INO-1.51

capped-1.46

Downloadha-1.45

ire-1.45

punct-1.45

ForgeModLoader-1.38

rupt-1.37

testers-1.36

bably-1.35

elsius-1.34

inently-1.33

luaj-1.33

���-1.32

respondents-1.30

roughly-1.28

uay-1.28

breached-1.27

pse-1.27

INTERVAL 4.171 - 4.635
CONTAINS 0.000%

his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
Oxford
Token Oxford
Feature activation+1.547
his
Token his
Feature activation+0.000
book
Token book
Feature activation+0.000
W
Token W
Feature activation+1.438
aking
Tokenaking
Feature activation+2.255
Up
Token Up
Feature activation+2.646
:
Token:
Feature activation+4.312
A
Token A
Feature activation+4.083
Guide
Token Guide
Feature activation+2.974
to
Token to
Feature activation+1.588
Spirit
Token Spirit
Feature activation+1.871
uality
Tokenuality
Feature activation+3.303
,
Token,
Feature activation+0.000
Gim
Token Gim
Feature activation+1.875
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
Gim
Token Gim
Feature activation+1.875
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
sters
Tokensters
Feature activation+2.979

INTERVAL 3.708 - 4.171
CONTAINS 0.001%

book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
Oxford
Token Oxford
Feature activation+1.547
-
Token-
Feature activation+0.000
educated
Tokeneducated
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.203
ľ
Tokenľ
Feature activation+0.000
Block
TokenBlock
Feature activation+2.619
chain
Tokenchain
Feature activation+2.750
:
Token:
Feature activation+4.162
Blueprint
Token Blueprint
Feature activation+4.138
for
Token for
Feature activation+2.322
a
Token a
Feature activation+0.810
New
Token New
Feature activation+1.506
Economy
Token Economy
Feature activation+1.660
,
Token,
Feature activation+0.981
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Million
Token Million
Feature activation+3.990
aire
Tokenaire
Feature activation+4.311
M
Token M
Feature activation+4.069
igrants
Tokenigrants
Feature activation+3.787
,
Token,
Feature activation+2.906
the
Token the
Feature activation+1.711
,
Token,
Feature activation+0.000
Evangel
Token Evangel
Feature activation+3.069
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
Semin
Token Semin
Feature activation+1.699
arians
Tokenarians
Feature activation+2.367
and
Token and
Feature activation+0.780
Their
Token Their
Feature activation+1.929
er
Tokener
Feature activation+0.000
's
Token's
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
book
Token book
Feature activation+0.000
The
Token The
Feature activation+2.406
Better
Token Better
Feature activation+3.982
Angels
Token Angels
Feature activation+2.352
of
Token of
Feature activation+2.642
Our
Token Our
Feature activation+3.546
Nature
Token Nature
Feature activation+2.615
,
Token,
Feature activation+0.734

INTERVAL 3.244 - 3.708
CONTAINS 0.001%

,
Token,
Feature activation+0.000
Dis
Token Dis
Feature activation+2.645
pir
Tokenpir
Feature activation+1.235
ited
Tokenited
Feature activation+2.915
:
Token:
Feature activation+3.516
How
Token How
Feature activation+3.312
Contemporary
Token Contemporary
Feature activation+1.043
Spirit
Token Spirit
Feature activation+0.694
uality
Tokenuality
Feature activation+2.234
Makes
Token Makes
Feature activation+0.562
Us
Token Us
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Evangel
Token Evangel
Feature activation+3.069
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
Semin
Token Semin
Feature activation+1.699
arians
Tokenarians
Feature activation+2.367
and
Token and
Feature activation+0.780
next
Token next
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+2.338
Low
Token Low
Feature activation+2.297
down
Tokendown
Feature activation+3.353
on
Token on
Feature activation+2.481
Witches
Token Witches
Feature activation+3.396
.
Token.
Feature activation+0.159
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+2.338
Low
Token Low
Feature activation+2.297
down
Tokendown
Feature activation+3.353
on
Token on
Feature activation+2.481
Witches
Token Witches
Feature activation+3.396
.
Token.
Feature activation+0.159
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Leon
TokenLeon
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
sters
Tokensters
Feature activation+2.979
,
Token,
Feature activation+1.129

INTERVAL 2.781 - 3.244
CONTAINS 0.001%

'
Token'
Feature activation+0.000
Brien
TokenBrien
Feature activation+0.000
's
Token's
Feature activation+0.000
book
Token book
Feature activation+0.061
Christian
Token Christian
Feature activation+1.069
Social
Token Social
Feature activation+2.975
Principles
Token Principles
Feature activation+2.940
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
follows
Token follows
Feature activation+0.000
Brien
TokenBrien
Feature activation+0.000
's
Token's
Feature activation+0.000
book
Token book
Feature activation+0.061
Christian
Token Christian
Feature activation+1.069
Social
Token Social
Feature activation+2.975
Principles
Token Principles
Feature activation+2.940
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
follows
Token follows
Feature activation+0.000
:
Token:
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Evangel
Token Evangel
Feature activation+3.069
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
How
Token How
Feature activation+4.617
I
Token I
Feature activation+3.574
Exp
Token Exp
Feature activation+2.730
osed
Tokenosed
Feature activation+2.006
Huck
Token Huck
Feature activation+1.250
sters
Tokensters
Feature activation+2.979
,
Token,
Feature activation+1.129
Che
Token Che
Feature activation+1.289
ats
Tokenats
Feature activation+1.125
,
Token,
Feature activation+1.593
and
Token and
Feature activation+0.476
based
Tokenbased
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
book
Token book
Feature activation+0.000
The
Token The
Feature activation+1.958
Roots
Token Roots
Feature activation+3.071
of
Token of
Feature activation+2.712
Obama
Token Obama
Feature activation+1.824
âĢ
TokenâĢ
Feature activation+0.923
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.151

INTERVAL 2.317 - 2.781
CONTAINS 0.004%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Pat
TokenPat
Feature activation+0.522
riot
Tokenriot
Feature activation+1.253
ism
Tokenism
Feature activation+0.595
Is
Token Is
Feature activation+2.407
Not
Token Not
Feature activation+0.726
Enough
Token Enough
Feature activation+1.928
:
Token:
Feature activation+1.980
Harry
Token Harry
Feature activation+0.000
J
Token J
Feature activation+0.000
Me
Token Me
Feature activation+0.429
Medicine
Token Medicine
Feature activation+1.994
vs
Token vs
Feature activation+1.784
.
Token.
Feature activation+0.992
We
Token We
Feature activation+1.169
Medicine
Token Medicine
Feature activation+2.643
,
Token,
Feature activation+0.871
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+2.712
Obama
Token Obama
Feature activation+1.824
âĢ
TokenâĢ
Feature activation+0.923
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.151
Rage
Token Rage
Feature activation+2.713
)
Token)
Feature activation+0.000
with
Token with
Feature activation+0.000
my
Token my
Feature activation+0.000
19
Token 19
Feature activation+0.000
-
Token-
Feature activation+0.000
The
Token The
Feature activation+2.406
Better
Token Better
Feature activation+3.982
Angels
Token Angels
Feature activation+2.352
of
Token of
Feature activation+2.642
Our
Token Our
Feature activation+3.546
Nature
Token Nature
Feature activation+2.615
,
Token,
Feature activation+0.734
I
Token I
Feature activation+0.947
wrote
Token wrote
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.627
Closing
Token Closing
Feature activation+4.033
of
Token of
Feature activation+2.141
the
Token the
Feature activation+1.190
Liberal
Token Liberal
Feature activation+0.716
Mind
Token Mind
Feature activation+2.767
âĢ
TokenâĢ
Feature activation+0.035
Ŀ
TokenĿ
Feature activation+0.000
:
Token:
Feature activation+3.318
Ċ
TokenĊ
Feature activation+0.288
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.854 - 2.317
CONTAINS 0.002%

new
Token new
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Evangel
Token Evangel
Feature activation+3.069
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
Semin
Token Semin
Feature activation+1.699
arians
Tokenarians
Feature activation+2.367
Up
Token Up
Feature activation+2.646
:
Token:
Feature activation+4.312
A
Token A
Feature activation+4.083
Guide
Token Guide
Feature activation+2.974
to
Token to
Feature activation+1.588
Spirit
Token Spirit
Feature activation+1.871
uality
Tokenuality
Feature activation+3.303
without
Token without
Feature activation+0.481
Religion
Token Religion
Feature activation+0.974
.
Token.
Feature activation+0.073
Ċ
TokenĊ
Feature activation+0.000
published
Token published
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
Gim
Token Gim
Feature activation+1.875
me
Tokenme
Feature activation+0.500
a
Token a
Feature activation+2.429
Break
Token Break
Feature activation+3.997
:
Token:
Feature activation+4.635
How
Token How
Feature activation+4.617
riot
Tokenriot
Feature activation+1.253
ism
Tokenism
Feature activation+0.595
Is
Token Is
Feature activation+2.407
Not
Token Not
Feature activation+0.726
Enough
Token Enough
Feature activation+1.928
:
Token:
Feature activation+1.980
Harry
Token Harry
Feature activation+0.000
J
Token J
Feature activation+0.000
aff
Tokenaff
Feature activation+0.000
a
Tokena
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
book
Token book
Feature activation+0.000
W
Token W
Feature activation+1.438
aking
Tokenaking
Feature activation+2.255
Up
Token Up
Feature activation+2.646
:
Token:
Feature activation+4.312
A
Token A
Feature activation+4.083
Guide
Token Guide
Feature activation+2.974
to
Token to
Feature activation+1.588

INTERVAL 1.390 - 1.854
CONTAINS 0.004%

chain
Tokenchain
Feature activation+2.750
:
Token:
Feature activation+4.162
Blueprint
Token Blueprint
Feature activation+4.138
for
Token for
Feature activation+2.322
a
Token a
Feature activation+0.810
New
Token New
Feature activation+1.506
Economy
Token Economy
Feature activation+1.660
,
Token,
Feature activation+0.981
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
ical
Tokenical
Feature activation+1.196
Exodus
Token Exodus
Feature activation+2.221
:
Token:
Feature activation+3.675
Evangel
Token Evangel
Feature activation+3.850
ical
Tokenical
Feature activation+1.507
Semin
Token Semin
Feature activation+1.699
arians
Tokenarians
Feature activation+2.367
and
Token and
Feature activation+0.780
Their
Token Their
Feature activation+1.929
Path
Token Path
Feature activation+1.179
s
Tokens
Feature activation+0.221
1898
Token 1898
Feature activation+0.000
book
Token book
Feature activation+0.000
titled
Token titled
Feature activation+0.000
"
Token "
Feature activation+0.000
A
TokenA
Feature activation+0.721
Century
Token Century
Feature activation+1.708
of
Token of
Feature activation+0.606
Vacc
Token Vacc
Feature activation+1.835
ination
Tokenination
Feature activation+1.382
":
Token":
Feature activation+0.322
Other
TokenOther
Feature activation+1.047
recent
Token recent
Feature activation+0.000
books
Token books
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.397
Fall
Token Fall
Feature activation+0.935
acy
Tokenacy
Feature activation+1.793
of
Token of
Feature activation+1.589
Fine
Token Fine
Feature activation+0.426
-
Token-
Feature activation+0.200
T
TokenT
Feature activation+0.231
uning
Tokenuning
Feature activation+0.747
2004
Token 2004
Feature activation+0.000
film
Token film
Feature activation+0.000
Team
Token Team
Feature activation+0.000
America
Token America
Feature activation+0.465
:
Token:
Feature activation+0.574
World
Token World
Feature activation+1.489
Police
Token Police
Feature activation+0.708
for
Token for
Feature activation+0.000
one
Token one
Feature activation+0.000
free
Token free
Feature activation+0.000
screening
Token screening
Feature activation+0.000

INTERVAL 0.927 - 1.390
CONTAINS 0.006%

Blueprint
Token Blueprint
Feature activation+4.138
for
Token for
Feature activation+2.322
a
Token a
Feature activation+0.810
New
Token New
Feature activation+1.506
Economy
Token Economy
Feature activation+1.660
,
Token,
Feature activation+0.981
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
to
Token to
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Brien
TokenBrien
Feature activation+0.000
's
Token's
Feature activation+0.000
book
Token book
Feature activation+0.061
Christian
Token Christian
Feature activation+1.069
Social
Token Social
Feature activation+2.975
Principles
Token Principles
Feature activation+2.940
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
Andy
TokenAndy
Feature activation+0.000
Murray
Token Murray
Feature activation+0.000
:
Token:
Feature activation+1.051
The
Token The
Feature activation+0.677
Man
Token Man
Feature activation+0.732
Behind
Token Behind
Feature activation+1.374
the
Token the
Feature activation+0.005
Rac
Token Rac
Feature activation+0.251
quet
Tokenquet
Feature activation+0.000
'.
Token'.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
White
Token White
Feature activation+0.000
and
Token and
Feature activation+0.000
Blue
Token Blue
Feature activation+0.000
:
Token:
Feature activation+1.055
The
Token The
Feature activation+1.069
Nug
Token Nug
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
Manifest
Token Manifest
Feature activation+0.000
o
Tokeno
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.950
Vatican
Token Vatican
Feature activation+0.212
:
Token:
Feature activation+2.462
Population
Token Population
Feature activation+2.322
Growth
Token Growth
Feature activation+2.769
and
Token and
Feature activation+0.930
National
Token National
Feature activation+0.222
Security
Token Security
Feature activation+0.405
(
Token (
Feature activation+0.130
1984
Token1984
Feature activation+0.000
).
Token).
Feature activation+0.000

INTERVAL 0.463 - 0.927
CONTAINS 0.012%

2012
Token 2012
Feature activation+0.000
Brookings
Token Brookings
Feature activation+0.000
Institution
Token Institution
Feature activation+0.000
report
Token report
Feature activation+0.000
entitled
Token entitled
Feature activation+0.000
Saving
Token Saving
Feature activation+0.487
Syria
Token Syria
Feature activation+0.817
:
Token:
Feature activation+1.057
Ass
Token Ass
Feature activation+0.806
essing
Tokenessing
Feature activation+0.696
Options
Token Options
Feature activation+0.640
ensemble
Token ensemble
Feature activation+0.000
dram
Token dram
Feature activation+0.000
edy
Tokenedy
Feature activation+0.000
Men
Token Men
Feature activation+0.000
,
Token,
Feature activation+0.000
Women
Token Women
Feature activation+0.514
&
Token &
Feature activation+0.706
Children
Token Children
Feature activation+0.301
also
Token also
Feature activation+0.000
stalled
Token stalled
Feature activation+0.000
,
Token,
Feature activation+0.000
sym
Token sym
Feature activation+0.000
posium
Tokenposium
Feature activation+0.000
,
Token,
Feature activation+0.000
Hegel
Token Hegel
Feature activation+0.000
and
Token and
Feature activation+0.289
Legal
Token Legal
Feature activation+0.774
Theory
Token Theory
Feature activation+1.073
,
Token,
Feature activation+0.313
a
Token a
Feature activation+0.100
British
Token British
Feature activation+0.000
academic
Token academic
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
nonprofit
Token nonprofit
Feature activation+0.000
Data
Token Data
Feature activation+0.287
and
Token and
Feature activation+0.000
Society
Token Society
Feature activation+0.761
Research
Token Research
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+0.000
,
Token,
Feature activation+0.000
author
Token author
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ISIS
TokenISIS
Feature activation+0.000
:
Token:
Feature activation+0.671
A
Token A
Feature activation+0.728
History
Token History
Feature activation+0.688
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 0.000 - 0.463
CONTAINS 99.969%

in
Tokenin
Feature activation+0.000
Cor
Token Cor
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
20
Token 20
Feature activation+0.000
on
Token on
Feature activation+0.000
July
Token July
Feature activation+0.000
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
Qatar
Token Qatar
Feature activation+0.000
and
Token and
Feature activation+0.000
down
Token down
Feature activation+0.000
grading
Tokengrading
Feature activation+0.000
ties
Token ties
Feature activation+0.000
with
Token with
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
an
Token an
Feature activation+0.000
has
Token has
Feature activation+0.000
now
Token now
Feature activation+0.000
gone
Token gone
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
seems
Token seems
Feature activation+0.000
industry
Token industry
Feature activation+0.000
experts
Token experts
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bitcoin
TokenBitcoin
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
reached
Token reached
Feature activation+0.000
out
Token out
Feature activation+0.000
to
Token to
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
founders
Token founders
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
."
Token."
Feature activation+0.000
Their
TokenTheir
Feature activation+0.000
theatrical
Token theatrical
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
was
Token was
Feature activation+0.000
something
Token something
Feature activation+0.000
else
Token else
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
played
Token played
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 H3.1: (feature 10650)

TOP ACTIVATIONS
MAX = 2.502

saying
Token saying
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.030
their
Token their
Feature activation+0.364
interest
Token interest
Feature activation+2.502
to
Token to
Feature activation+1.744
treat
Token treat
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.000
well
Token well
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.108
make
Token make
Feature activation+0.330
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
sense
Token sense
Feature activation+2.436
to
Token to
Feature activation+1.536
discuss
Token discuss
Feature activation+0.162
how
Token how
Feature activation+0.000
economies
Token economies
Feature activation+0.000
could
Token could
Feature activation+0.000
Shah
Token Shah
Feature activation+0.838
b
Tokenb
Feature activation+0.054
az
Tokenaz
Feature activation+0.000
's
Token's
Feature activation+1.789
friend
Token friend
Feature activation+1.399
who
Token who
Feature activation+2.429
offered
Token offered
Feature activation+0.000
the
Token the
Feature activation+0.000
huge
Token huge
Feature activation+0.000
sum
Token sum
Feature activation+0.000
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
at
Token at
Feature activation+0.384
all
Token all
Feature activation+0.407
obnoxious
Token obnoxious
Feature activation+0.507
to
Token to
Feature activation+2.317
allow
Token allow
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
concealed
Token concealed
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
in
Token in
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.028
the
Token the
Feature activation+0.043
government
Token government
Feature activation+0.047
's
Token's
Feature activation+0.629
interest
Token interest
Feature activation+2.257
to
Token to
Feature activation+1.624
get
Token get
Feature activation+0.432
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.674
'
Token '
Feature activation+0.000
mist
Tokenmist
Feature activation+0.949
ake
Tokenake
Feature activation+2.240
'
Token'
Feature activation+1.636
for
Token for
Feature activation+1.714
Leave
Token Leave
Feature activation+0.000
to
Token to
Feature activation+0.940
claim
Token claim
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
illegal
Token illegal
Feature activation+0.953
for
Token for
Feature activation+2.198
protesters
Token protesters
Feature activation+0.000
to
Token to
Feature activation+0.942
cover
Token cover
Feature activation+0.000
their
Token their
Feature activation+0.000
faces
Token faces
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
common
Token common
Feature activation+0.308
and
Token and
Feature activation+0.127
legal
Token legal
Feature activation+0.739
for
Token for
Feature activation+2.129
private
Token private
Feature activation+0.000
universities
Token universities
Feature activation+0.000
to
Token to
Feature activation+1.788
not
Token not
Feature activation+0.000
record
Token record
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.578
huge
Token huge
Feature activation+0.325
surprise
Token surprise
Feature activation+2.102
if
Token if
Feature activation+1.046
they
Token they
Feature activation+0.178
put
Token put
Feature activation+0.000
N
Token N
Feature activation+0.000
uke
Tokenuke
Feature activation+0.000
and
Token and
Feature activation+0.000
overall
Token overall
Feature activation+0.000
it
Token it
Feature activation+0.057
appears
Token appears
Feature activation+0.074
as
Token as
Feature activation+0.224
though
Token though
Feature activation+2.086
he
Token he
Feature activation+0.673
was
Token was
Feature activation+0.104
never
Token never
Feature activation+0.134
the
Token the
Feature activation+0.422
right
Token right
Feature activation+0.471
And
Token And
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
r
Token r
Feature activation+0.000
ained
Tokenained
Feature activation+2.084
so
Token so
Feature activation+0.000
hard
Token hard
Feature activation+0.219
in
Token in
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
that
Token that
Feature activation+1.178
added
Token added
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.402
task
Token task
Feature activation+2.045
of
Token of
Feature activation+0.507
naval
Token naval
Feature activation+0.000
personnel
Token personnel
Feature activation+0.000
to
Token to
Feature activation+1.700
protect
Token protect
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.302
late
Token late
Feature activation+2.037
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
existence
Token existence
Feature activation+0.000
of
Token of
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
crime
Token crime
Feature activation+2.014
,
Token,
Feature activation+0.000
punishable
Token punishable
Feature activation+0.052
by
Token by
Feature activation+0.000
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.000
Associated
Token Associated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.115
early
Token early
Feature activation+1.988
to
Token to
Feature activation+0.998
tell
Token tell
Feature activation+0.761
but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.113
public
Token public
Feature activation+0.000
safety
Token safety
Feature activation+0.000
challenge
Token challenge
Feature activation+1.980
of
Token of
Feature activation+0.306
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
order
Token order
Feature activation+0.000
.
Token.
Feature activation+0.000
it
Token it
Feature activation+0.031
was
Token was
Feature activation+0.000
the
Token the
Feature activation+1.038
Republican
Token Republican
Feature activation+0.000
candidate
Token candidate
Feature activation+0.049
who
Token who
Feature activation+1.954
had
Token had
Feature activation+0.000
avoided
Token avoided
Feature activation+0.000
serving
Token serving
Feature activation+0.000
in
Token in
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
the
Token the
Feature activation+0.000
race
Token race
Feature activation+0.000
once
Token once
Feature activation+0.000
it
Token it
Feature activation+0.000
became
Token became
Feature activation+0.406
clear
Token clear
Feature activation+1.952
she
Token she
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.159
early
Token early
Feature activation+1.944
to
Token to
Feature activation+1.157
say
Token say
Feature activation+0.086
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
Germany
Token Germany
Feature activation+0.971
's
Token's
Feature activation+0.576
intention
Token intention
Feature activation+1.931
to
Token to
Feature activation+0.663
become
Token become
Feature activation+0.987
a
Token a
Feature activation+0.105
leader
Token leader
Feature activation+0.000
in
Token in
Feature activation+0.000

Top DFA by src position
MAX = 3.158

treatment
Tokentreatment
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.008
Top resid features:
mothers
Token mothers
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
saying
Token saying
Feature activation+0.007
Top resid features:
it
Token it
Feature activation+3.158
Top resid features:
is
Token is
Feature activation-0.075
Top resid features:
in
Token in
Feature activation-0.055
Top resid features:
their
Token their
Feature activation-0.038
Top resid features:
interest
Token interest
Feature activation+0.077
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Instead
Token Instead
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
financial
Token financial
Feature activation-0.000
Top resid features:
repression
Token repression
Feature activation-0.005
Top resid features:
it
Token it
Feature activation+2.992
Top resid features:
would
Token would
Feature activation-0.135
Top resid features:
make
Token make
Feature activation-0.035
Top resid features:
much
Token much
Feature activation+0.002
Top resid features:
more
Token more
Feature activation+0.125
Top resid features:
sense
Token sense
Feature activation+0.074
Top resid features:
while
Token while
Feature activation-0.005
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
others
Token others
Feature activation-0.004
Top resid features:
he
Token he
Feature activation-0.009
Top resid features:
says
Token says
Feature activation+0.008
Top resid features:
it
Token it
Feature activation+3.142
Top resid features:
was
Token was
Feature activation-0.177
Top resid features:
Ham
Token Ham
Feature activation+0.040
Top resid features:
za
Tokenza
Feature activation+0.012
Top resid features:
Shah
Token Shah
Feature activation+0.002
Top resid features:
b
Tokenb
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
Texas
Token Texas
Feature activation+0.008
Top resid features:
has
Token has
Feature activation-0.000
Top resid features:
decided
Token decided
Feature activation-0.017
Top resid features:
that
Token that
Feature activation+0.022
Top resid features:
it
Token it
Feature activation+2.745
Top resid features:
is
Token is
Feature activation-0.011
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.011
Top resid features:
all
Token all
Feature activation+0.003
Top resid features:
obnoxious
Token obnoxious
Feature activation+0.145
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
And
Token And
Feature activation+0.002
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
think
Token think
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.046
Top resid features:
it
Token it
Feature activation+2.549
Top resid features:
's
Token's
Feature activation-0.034
Top resid features:
in
Token in
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
government
Token government
Feature activation+0.164
Top resid features:
's
Token's
Feature activation+0.021
Top resid features:
us
Tokenus
Feature activation+0.000
Top resid features:
ann
Tokenann
Feature activation+0.000
Top resid features:
are
Tokenare
Feature activation-0.000
Top resid features:
id
Tokenid
Feature activation+0.000
Top resid features:
100
Token100
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+2.879
Top resid features:
was
Token was
Feature activation-0.171
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
'
Token '
Feature activation+0.012
Top resid features:
mist
Tokenmist
Feature activation+0.060
Top resid features:
ake
Tokenake
Feature activation+0.049
Top resid features:
proposed
Token proposed
Feature activation-0.007
Top resid features:
law
Token law
Feature activation+0.020
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
would
Token would
Feature activation+0.001
Top resid features:
make
Token make
Feature activation-0.027
Top resid features:
it
Token it
Feature activation+2.992
Top resid features:
illegal
Token illegal
Feature activation-0.158
Top resid features:
for
Token for
Feature activation-0.070
Top resid features:
protesters
Token protesters
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
Columbia
Token Columbia
Feature activation+0.000
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
policy
Token policy
Feature activation-0.002
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
it
Token it
Feature activation+2.710
Top resid features:
is
Token is
Feature activation-0.039
Top resid features:
common
Token common
Feature activation-0.031
Top resid features:
and
Token and
Feature activation+0.035
Top resid features:
legal
Token legal
Feature activation+0.002
Top resid features:
for
Token for
Feature activation-0.030
Top resid features:
said
Token said
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
my
Token my
Feature activation-0.004
Top resid features:
team
Token team
Feature activation-0.003
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
it
Token it
Feature activation+2.661
Top resid features:
would
Token would
Feature activation-0.143
Top resid features:
be
Token be
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
huge
Token huge
Feature activation+0.030
Top resid features:
surprise
Token surprise
Feature activation+0.034
Top resid features:
built
Token built
Feature activation+0.001
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
Guardiola
Token Guardiola
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
overall
Token overall
Feature activation-0.002
Top resid features:
it
Token it
Feature activation+2.577
Top resid features:
appears
Token appears
Feature activation+0.011
Top resid features:
as
Token as
Feature activation-0.006
Top resid features:
though
Token though
Feature activation-0.014
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
early
Token early
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
And
Token And
Feature activation-0.005
Top resid features:
now
Token now
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
it
Token it
Feature activation+2.575
Top resid features:
r
Token r
Feature activation+0.013
Top resid features:
ained
Tokenained
Feature activation-0.009
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
hard
Token hard
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
nation
Token nation
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.017
Top resid features:
He
Token He
Feature activation-0.015
Top resid features:
added
Token added
Feature activation-0.008
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
it
Token it
Feature activation+2.674
Top resid features:
is
Token is
Feature activation-0.092
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
task
Token task
Feature activation+0.066
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
naval
Token naval
Feature activation+0.000
Top resid features:
wake
Token wake
Feature activation-0.006
Top resid features:
up
Token up
Feature activation+0.007
Top resid features:
now
Token now
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
before
Token before
Feature activation+0.015
Top resid features:
it
Token it
Feature activation+2.507
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.035
Top resid features:
too
Token too
Feature activation-0.046
Top resid features:
late
Token late
Feature activation+0.040
Top resid features:
Ohio
Token Ohio
Feature activation+0.012
Top resid features:
election
Token election
Feature activation-0.008
Top resid features:
law
Token law
Feature activation+0.042
Top resid features:
that
Token that
Feature activation-0.038
Top resid features:
makes
Token makes
Feature activation-0.052
Top resid features:
it
Token it
Feature activation+2.539
Top resid features:
a
Token a
Feature activation-0.062
Top resid features:
crime
Token crime
Feature activation+0.099
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
punishable
Token punishable
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
told
Token told
Feature activation-0.039
Top resid features:
The
Token The
Feature activation-0.006
Top resid features:
Associated
Token Associated
Feature activation-0.000
Top resid features:
Press
Token Press
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+2.869
Top resid features:
was
Token was
Feature activation-0.217
Top resid features:
too
Token too
Feature activation-0.131
Top resid features:
early
Token early
Feature activation+0.085
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
tell
Token tell
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
university
Token university
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
it
Token it
Feature activation+2.467
Top resid features:
is
Token is
Feature activation-0.061
Top resid features:
a
Token a
Feature activation-0.029
Top resid features:
public
Token public
Feature activation+0.037
Top resid features:
safety
Token safety
Feature activation+0.032
Top resid features:
challenge
Token challenge
Feature activation+0.012
Top resid features:
Gore
Token Gore
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
John
Token John
Feature activation-0.000
Top resid features:
Kerry
Token Kerry
Feature activation-0.004
Top resid features:
when
Token when
Feature activation+0.008
Top resid features:
it
Token it
Feature activation+2.497
Top resid features:
was
Token was
Feature activation-0.087
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Republican
Token Republican
Feature activation+0.034
Top resid features:
candidate
Token candidate
Feature activation+0.047
Top resid features:
who
Token who
Feature activation-0.040
Top resid features:
out
Token out
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
race
Token race
Feature activation-0.004
Top resid features:
once
Token once
Feature activation+0.063
Top resid features:
it
Token it
Feature activation+2.500
Top resid features:
became
Token became
Feature activation-0.022
Top resid features:
clear
Token clear
Feature activation-0.029
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Austin
Token Austin
Feature activation+0.010
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Har
Token Har
Feature activation+0.001
Top resid features:
oon
Tokenoon
Feature activation-0.000
Top resid features:
said
Token said
Feature activation-0.015
Top resid features:
it
Token it
Feature activation+2.619
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
s
Tokens
Feature activation-0.030
Top resid features:
too
Token too
Feature activation-0.128
Top resid features:
early
Token early
Feature activation+0.016
Top resid features:
Chancellor
Token Chancellor
Feature activation-0.010
Top resid features:
Angela
Token Angela
Feature activation-0.002
Top resid features:
Merkel
Token Merkel
Feature activation-0.002
Top resid features:
said
Token said
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+0.076
Top resid features:
it
Token it
Feature activation+2.402
Top resid features:
was
Token was
Feature activation-0.124
Top resid features:
Germany
Token Germany
Feature activation+0.065
Top resid features:
's
Token's
Feature activation-0.022
Top resid features:
intention
Token intention
Feature activation+0.059
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.43

Head 2: 0.09

Head 3: 0.02

Head 4: 0.02

Head 5: 0.03

Head 6: 0.06

Head 7: 0.05

Head 8: 0.05

Head 9: 0.10

Head 10: 0.07

Head 11: 0.05

Positive logits

Governments1.73

Poles1.65

frogs1.58

Bulgar1.57

sew1.54

raining1.47

tigers1.41

Regulations1.36

frog1.33

uphill1.32

Germans1.32

Russians1.31

Stephens1.31

".1.30

hops1.29

Engels1.29

Afghans1.29

paran1.28

Ukrainians1.28

Count1.26

Negative logits

-1.62

lio-1.49

-1.48

Library-1.42

pione-1.41

-1.39

シャ-1.37

CHA-1.33

Globe-1.33

ukemia-1.31

>]-1.30

pton-1.29

-1.28

luster-1.28

itage-1.28

-1.27

vertisement-1.27

scorer-1.26

BN-1.26

iano-1.25

INTERVAL 2.252 - 2.502
CONTAINS 0.001%

Shah
Token Shah
Feature activation+0.838
b
Tokenb
Feature activation+0.054
az
Tokenaz
Feature activation+0.000
's
Token's
Feature activation+1.789
friend
Token friend
Feature activation+1.399
who
Token who
Feature activation+2.429
offered
Token offered
Feature activation+0.000
the
Token the
Feature activation+0.000
huge
Token huge
Feature activation+0.000
sum
Token sum
Feature activation+0.000
to
Token to
Feature activation+0.000
saying
Token saying
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.030
their
Token their
Feature activation+0.364
interest
Token interest
Feature activation+2.502
to
Token to
Feature activation+1.744
treat
Token treat
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.000
well
Token well
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.108
make
Token make
Feature activation+0.330
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
sense
Token sense
Feature activation+2.436
to
Token to
Feature activation+1.536
discuss
Token discuss
Feature activation+0.162
how
Token how
Feature activation+0.000
economies
Token economies
Feature activation+0.000
could
Token could
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.028
the
Token the
Feature activation+0.043
government
Token government
Feature activation+0.047
's
Token's
Feature activation+0.629
interest
Token interest
Feature activation+2.257
to
Token to
Feature activation+1.624
get
Token get
Feature activation+0.432
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
in
Token in
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
at
Token at
Feature activation+0.384
all
Token all
Feature activation+0.407
obnoxious
Token obnoxious
Feature activation+0.507
to
Token to
Feature activation+2.317
allow
Token allow
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
concealed
Token concealed
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.001 - 2.252
CONTAINS 0.001%

and
Token and
Feature activation+0.000
overall
Token overall
Feature activation+0.000
it
Token it
Feature activation+0.057
appears
Token appears
Feature activation+0.074
as
Token as
Feature activation+0.224
though
Token though
Feature activation+2.086
he
Token he
Feature activation+0.673
was
Token was
Feature activation+0.104
never
Token never
Feature activation+0.134
the
Token the
Feature activation+0.422
right
Token right
Feature activation+0.471
And
Token And
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
r
Token r
Feature activation+0.000
ained
Tokenained
Feature activation+2.084
so
Token so
Feature activation+0.000
hard
Token hard
Feature activation+0.219
in
Token in
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
that
Token that
Feature activation+1.178
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.578
huge
Token huge
Feature activation+0.325
surprise
Token surprise
Feature activation+2.102
if
Token if
Feature activation+1.046
they
Token they
Feature activation+0.178
put
Token put
Feature activation+0.000
N
Token N
Feature activation+0.000
uke
Tokenuke
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.302
late
Token late
Feature activation+2.037
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
existence
Token existence
Feature activation+0.000
of
Token of
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
crime
Token crime
Feature activation+2.014
,
Token,
Feature activation+0.000
punishable
Token punishable
Feature activation+0.052
by
Token by
Feature activation+0.000
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.000

INTERVAL 1.751 - 2.001
CONTAINS 0.002%

s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.210
ground
Token ground
Feature activation+0.439
less
Tokenless
Feature activation+0.000
assumption
Token assumption
Feature activation+1.931
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
omew
Tokenomew
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
Germany
Token Germany
Feature activation+0.971
's
Token's
Feature activation+0.576
intention
Token intention
Feature activation+1.931
to
Token to
Feature activation+0.663
become
Token become
Feature activation+0.987
a
Token a
Feature activation+0.105
leader
Token leader
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.031
was
Token was
Feature activation+0.000
the
Token the
Feature activation+1.038
Republican
Token Republican
Feature activation+0.000
candidate
Token candidate
Feature activation+0.049
who
Token who
Feature activation+1.954
had
Token had
Feature activation+0.000
avoided
Token avoided
Feature activation+0.000
serving
Token serving
Feature activation+0.000
in
Token in
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
efficient
Token efficient
Feature activation+0.832
and
Token and
Feature activation+0.202
cheaper
Token cheaper
Feature activation+1.229
to
Token to
Feature activation+1.783
run
Token run
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
his
Token his
Feature activation+1.019
place
Token place
Feature activation+1.911
"
Token "
Feature activation+0.000
to
Tokento
Feature activation+1.388
judge
Token judge
Feature activation+0.272
our
Token our
Feature activation+0.000
current
Token current
Feature activation+0.000

INTERVAL 1.501 - 1.751
CONTAINS 0.005%

and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
heart
Token heart
Feature activation+0.434
warming
Tokenwarming
Feature activation+1.607
,
Token,
Feature activation+0.078
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
Center
Token Center
Feature activation+0.000
the
Token the
Feature activation+0.000
feast
Token feast
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
difficult
Token difficult
Feature activation+0.094
to
Token to
Feature activation+1.523
move
Token move
Feature activation+0.000
.
Token.
Feature activation+0.000
Wilson
Token Wilson
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
slaves
Token slaves
Feature activation+0.000
.
Token.
Feature activation+0.000
Is
Token Is
Feature activation+0.000
it
Token it
Feature activation+0.000
acceptable
Token acceptable
Feature activation+0.000
to
Token to
Feature activation+1.502
ensl
Token ensl
Feature activation+0.000
ave
Tokenave
Feature activation+0.020
your
Token your
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
human
Token human
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
for
Token for
Feature activation+1.007
Mrs
Token Mrs
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
to
Token to
Feature activation+1.619
claim
Token claim
Feature activation+0.006
victory
Token victory
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
based
Token based
Feature activation+0.000
about
Token about
Feature activation+0.000
10
Token 10
Feature activation+0.000
times
Token times
Feature activation+0.465
as
Token as
Feature activation+0.455
much
Token much
Feature activation+0.325
to
Token to
Feature activation+1.637
bury
Token bury
Feature activation+0.000
wire
Token wire
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
string
Token string
Feature activation+0.000

INTERVAL 1.251 - 1.501
CONTAINS 0.009%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.204
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.201
stretch
Token stretch
Feature activation+1.268
to
Token to
Feature activation+0.264
imagine
Token imagine
Feature activation+0.000
Life
Token Life
Feature activation+0.000
is
Token is
Feature activation+0.000
Strange
Token Strange
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.000
admit
Token admit
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.253
mistake
Token mistake
Feature activation+1.400
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.385
be
Token be
Feature activation+0.293
an
Token an
Feature activation+1.183
issue
Token issue
Feature activation+1.517
that
Token that
Feature activation+1.492
turns
Token turns
Feature activation+0.149
teams
Token teams
Feature activation+0.000
off
Token off
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
it
Token it
Feature activation+0.050
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
helpful
Token helpful
Feature activation+0.000
to
Token to
Feature activation+1.433
look
Token look
Feature activation+0.300
at
Token at
Feature activation+0.000
charities
Token charities
Feature activation+0.000
as
Token as
Feature activation+0.000
products
Token products
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.008
from
Token from
Feature activation+0.084
far
Token far
Feature activation+0.000
away
Tokenaway
Feature activation+0.000
lands
Token lands
Feature activation+0.000
that
Token that
Feature activation+1.261
had
Token had
Feature activation+0.000
little
Token little
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 1.001 - 1.251
CONTAINS 0.017%

of
Token of
Feature activation+0.000
progress
Token progress
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
possible
Token possible
Feature activation+0.184
for
Token for
Feature activation+1.117
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.597
human
Token human
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.195
until
Token until
Feature activation+0.397
1900
Token 1900
Feature activation+0.692
that
Token that
Feature activation+1.123
design
Token design
Feature activation+0.000
submissions
Token submissions
Feature activation+0.000
were
Token were
Feature activation+0.000
actually
Token actually
Feature activation+0.000
invited
Token invited
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
an
Token an
Feature activation+0.000
obst
Token obst
Feature activation+0.000
inate
Tokeninate
Feature activation+0.514
belief
Token belief
Feature activation+1.147
that
Token that
Feature activation+0.045
the
Token the
Feature activation+0.000
religion
Token religion
Feature activation+0.000
of
Token of
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
so
Token so
Feature activation+0.000
it
Token it
Feature activation+0.000
responds
Token responds
Feature activation+0.000
more
Token more
Feature activation+0.000
readily
Token readily
Feature activation+0.193
to
Token to
Feature activation+1.010
winds
Token winds
Feature activation+0.241
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
easily
Token easily
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
car
Token car
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.156
tricky
Token tricky
Feature activation+1.213
to
Token to
Feature activation+1.393
do
Token do
Feature activation+0.694
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 0.751 - 1.001
CONTAINS 0.030%

it
Token it
Feature activation+0.000
became
Token became
Feature activation+0.044
best
Token best
Feature activation+0.000
-
Token-
Feature activation+0.000
known
Tokenknown
Feature activation+0.524
for
Token for
Feature activation+0.865
its
Token its
Feature activation+0.000
participation
Token participation
Feature activation+0.000
in
Token in
Feature activation+0.000
Blizzard
Token Blizzard
Feature activation+0.000
titles
Token titles
Feature activation+0.000
only
Token only
Feature activation+0.000
country
Token country
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
that
Token that
Feature activation+0.820
bans
Token bans
Feature activation+0.000
women
Token women
Feature activation+0.000
from
Token from
Feature activation+0.000
driving
Token driving
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
falling
Token falling
Feature activation+0.000
it
Token it
Feature activation+0.155
is
Token is
Feature activation+0.247
difficult
Token difficult
Feature activation+0.059
to
Token to
Feature activation+0.956
service
Token service
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
begun
Token begun
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.821
until
Token until
Feature activation+0.576
later
Token later
Feature activation+0.048
that
Token that
Feature activation+0.814
you
Token you
Feature activation+0.000
realize
Token realize
Feature activation+0.000
this
Token this
Feature activation+0.000
has
Token has
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.019
destabil
Token destabil
Feature activation+0.070
ising
Tokenising
Feature activation+0.757
politically
Token politically
Feature activation+0.000
if
Token if
Feature activation+0.762
we
Token we
Feature activation+0.000
get
Token get
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.500 - 0.751
CONTAINS 0.058%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
it
Token it
Feature activation+0.109
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
uncommon
Token uncommon
Feature activation+0.757
for
Token for
Feature activation+0.627
a
Token a
Feature activation+0.000
worker
Token worker
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
Vi
Token Vi
Feature activation+0.000
ess
Tokeness
Feature activation+0.000
mann
Tokenmann
Feature activation+0.000
Group
Token Group
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.556
integrate
Token integrate
Feature activation+0.000
an
Token an
Feature activation+0.000
aer
Tokenaer
Feature activation+0.000
obic
Tokenobic
Feature activation+0.000
digestion
Token digestion
Feature activation+0.000
Under
Token Under
Feature activation+0.000
no
Token no
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
is
Token is
Feature activation+0.000
it
Token it
Feature activation+0.134
ok
Token ok
Feature activation+0.546
to
Token to
Feature activation+0.540
shoot
Token shoot
Feature activation+0.000
a
Token a
Feature activation+0.000
green
Token green
Feature activation+0.000
tank
Token tank
Feature activation+0.000
comfort
Token comfort
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
believed
Token believed
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.230
be
Token be
Feature activation+0.688
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.144
the
Token the
Feature activation+0.724
turn
Token turn
Feature activation+0.624
of
Token of
Feature activation+0.000
And
Token And
Feature activation+0.000
hra
Tokenhra
Feature activation+0.000
Pradesh
Token Pradesh
Feature activation+0.000
to
Token to
Feature activation+0.846

INTERVAL 0.250 - 0.500
CONTAINS 0.117%

it
Token it
Feature activation+0.000
wins
Token wins
Feature activation+0.000
this
Token this
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
's
Token's
Feature activation+0.000
election
Token election
Feature activation+0.380
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
reflex
Token reflex
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
response
Token response
Feature activation+0.119
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.291
point
Token point
Feature activation+0.000
to
Token to
Feature activation+0.307
find
Token find
Feature activation+0.000
somebody
Token somebody
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
major
Token major
Feature activation+0.406
,''
Token,''
Feature activation+0.000
a
Token a
Feature activation+0.000
source
Token source
Feature activation+0.000
told
Token told
Feature activation+0.000
NW
Token NW
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
fun
Token fun
Feature activation+1.233
as
Token as
Feature activation+0.273
playing
Token playing
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
proved
Token proved
Feature activation+0.120
to
Token to
Feature activation+0.257
be
Token be
Feature activation+0.515
a
Token a
Feature activation+0.503
ca
Token ca
Feature activation+0.000
pper
Tokenpper
Feature activation+0.000
for
Token for
Feature activation+0.257

INTERVAL 0.000 - 0.250
CONTAINS 99.761%

this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
symbolic
Token symbolic
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
taken
Token taken
Feature activation+0.000
from
Token from
Feature activation+0.000
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
picking
Token picking
Feature activation+0.000
on
Token on
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
staff
Token staff
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
left
Token left
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Port
Token Port
Feature activation+0.000
-
Token-
Feature activation+0.000
au
Tokenau
Feature activation+0.000
-
Token-
Feature activation+0.000
Prince
TokenPrince
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
center
Token center
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
first
Token first
Feature activation+0.000
thing
Token thing
Feature activation+0.000
I
Token I
Feature activation+0.000
noticed
Token noticed
Feature activation+0.000
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
Redemption
Token Redemption
Feature activation+0.000
for
Token for
Feature activation+0.000
Louisville
Token Louisville
Feature activation+0.000
and
Token and
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H3.1: (feature 16261)

TOP ACTIVATIONS
MAX = 2.212

wars
Token wars
Feature activation+0.000
against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.647
and
Token and
Feature activation+0.913
China
Token China
Feature activation+0.790
,
Token,
Feature activation+2.212
and
Token and
Feature activation+1.787
a
Token a
Feature activation+0.515
half
Token half
Feature activation+0.000
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
mum
Token mum
Feature activation+0.620
and
Token and
Feature activation+1.462
father
Token father
Feature activation+0.663
less
Tokenless
Feature activation+0.501
children
Token children
Feature activation+1.509
,
Token,
Feature activation+2.139
all
Token all
Feature activation+1.353
expecting
Token expecting
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.411
gay
Token gay
Feature activation+0.154
and
Token and
Feature activation+0.343
lesbian
Token lesbian
Feature activation+0.457
characters
Token characters
Feature activation+1.574
,
Token,
Feature activation+1.856
and
Token and
Feature activation+1.676
people
Token people
Feature activation+0.035
and
Token and
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
of
Token of
Feature activation+0.000
ki
Tokenki
Feature activation+0.358
this
Token this
Feature activation+1.632
past
Token past
Feature activation+0.851
August
Token August
Feature activation+0.950
,
Token,
Feature activation+1.791
and
Token and
Feature activation+1.802
the
Token the
Feature activation+0.244
Braves
Token Braves
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
filing
Token filing
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
TC
TokenTC
Feature activation+0.000
,
Token,
Feature activation+1.793
which
Token which
Feature activation+1.385
means
Token means
Feature activation+0.239
Apple
Token Apple
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
rows
Tokenrows
Feature activation+0.000
ki
Tokenki
Feature activation+0.358
this
Token this
Feature activation+1.632
past
Token past
Feature activation+0.851
August
Token August
Feature activation+0.950
,
Token,
Feature activation+1.791
and
Token and
Feature activation+1.802
the
Token the
Feature activation+0.244
Braves
Token Braves
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.647
and
Token and
Feature activation+0.913
China
Token China
Feature activation+0.790
,
Token,
Feature activation+2.212
and
Token and
Feature activation+1.787
a
Token a
Feature activation+0.515
half
Token half
Feature activation+0.000
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
,
Token,
Feature activation+0.186
or
Token or
Feature activation+0.218
EG
Token EG
Feature activation+0.000
TR
TokenTR
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
)
Token)
Feature activation+1.757
and
Token and
Feature activation+1.205
2003
Token 2003
Feature activation+0.143
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+0.000
the
Token the
Feature activation+0.000
shipping
Token shipping
Feature activation+0.232
until
Token until
Feature activation+0.387
later
Token later
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+1.727
and
Token and
Feature activation+1.106
if
Token if
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.000
follows
Token follows
Feature activation+0.000
its
Token its
Feature activation+0.000
gay
Token gay
Feature activation+0.154
and
Token and
Feature activation+0.343
lesbian
Token lesbian
Feature activation+0.457
characters
Token characters
Feature activation+1.574
,
Token,
Feature activation+1.856
and
Token and
Feature activation+1.676
people
Token people
Feature activation+0.035
and
Token and
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
ĵ
Tokenĵ
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
á
Tokená
Feature activation+0.000
da
Tokenda
Feature activation+0.000
,
Token,
Feature activation+1.645
and
Token and
Feature activation+1.556
Alex
Token Alex
Feature activation+0.000
de
Token de
Feature activation+0.000
Wa
Token Wa
Feature activation+0.000
al
Tokenal
Feature activation+0.000
Dave
Token Dave
Feature activation+0.022
D
Token D
Feature activation+0.000
omb
Tokenomb
Feature activation+0.000
rows
Tokenrows
Feature activation+0.000
ki
Tokenki
Feature activation+0.358
this
Token this
Feature activation+1.632
past
Token past
Feature activation+0.851
August
Token August
Feature activation+0.950
,
Token,
Feature activation+1.791
and
Token and
Feature activation+1.802
the
Token the
Feature activation+0.244
farmers
Token farmers
Feature activation+0.478
and
Token and
Feature activation+0.480
Co
Token Co
Feature activation+0.000
hesion
Tokenhesion
Feature activation+0.000
Funds
Token Funds
Feature activation+0.000
,
Token,
Feature activation+1.630
a
Token a
Feature activation+0.759
crucial
Token crucial
Feature activation+0.167
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.148
them
Token them
Feature activation+0.000
Am
Token Am
Feature activation+0.245
art
Tokenart
Feature activation+0.000
ya
Tokenya
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
,
Token,
Feature activation+1.619
Corm
Token Corm
Feature activation+0.096
ac
Tokenac
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
ĵ
Tokenĵ
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
span
Token span
Feature activation+0.567
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.000
,
Token,
Feature activation+1.491
and
Token and
Feature activation+1.606
one
Token one
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
predictable
Token predictable
Feature activation+0.000
but
Token but
Feature activation+0.000
information
Token information
Feature activation+0.027
in
Token in
Feature activation+0.276
a
Token a
Feature activation+0.263
quantum
Token quantum
Feature activation+0.004
computer
Token computer
Feature activation+0.356
,
Token,
Feature activation+1.596
Ċ
TokenĊ
Feature activation+0.456
Ċ
TokenĊ
Feature activation+0.053
In
TokenIn
Feature activation+0.000
current
Token current
Feature activation+0.000
computers
Token computers
Feature activation+0.000
pre
Token pre
Feature activation+0.000
achers
Tokenachers
Feature activation+0.075
from
Token from
Feature activation+0.158
rival
Token rival
Feature activation+0.446
sects
Token sects
Feature activation+0.068
were
Token were
Feature activation+1.590
harassed
Token harassed
Feature activation+1.013
and
Token and
Feature activation+0.221
h
Token h
Feature activation+0.000
ounded
Tokenounded
Feature activation+0.000
out
Token out
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
his
Tokenhis
Feature activation+0.000
brothers
Token brothers
Feature activation+0.000
and
Token and
Feature activation+0.000
sisters
Token sisters
Feature activation+0.062
,
Token,
Feature activation+1.585
all
Token all
Feature activation+0.833
his
Token his
Feature activation+0.000
West
Token West
Feature activation+0.000
Coast
Token Coast
Feature activation+0.000
friends
Token friends
Feature activation+0.270
fifth
Tokenfifth
Feature activation+0.000
of
Token of
Feature activation+0.378
Bush
Token Bush
Feature activation+1.021
's
Token's
Feature activation+0.395
time
Token time
Feature activation+0.158
,
Token,
Feature activation+1.583
or
Token or
Feature activation+1.062
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
enth
Tokenenth
Feature activation+0.000
from
Token from
Feature activation+0.027
years
Token years
Feature activation+0.344
of
Token of
Feature activation+0.295
international
Token international
Feature activation+0.486
alienation
Token alienation
Feature activation+0.471
,
Token,
Feature activation+1.580
fear
Token fear
Feature activation+0.580
of
Token of
Feature activation+0.073
the
Token the
Feature activation+0.042
uncertainty
Token uncertainty
Feature activation+0.011
to
Token to
Feature activation+0.016

Top DFA by src position
MAX = 2.421

-
Token-
Feature activation+0.001
Top resid features:
a
Tokena
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
half
Tokenhalf
Feature activation-0.001
Top resid features:
wars
Token wars
Feature activation+0.004
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.421
Top resid features:
big
Tokenbig
Feature activation+0.021
Top resid features:
wars
Token wars
Feature activation+0.008
Top resid features:
against
Token against
Feature activation+0.032
Top resid features:
Russia
Token Russia
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.109
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
man
Token man
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
house
Token house
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.337
Top resid features:
lone
Token lone
Feature activation+0.037
Top resid features:
gr
Token gr
Feature activation+0.004
Top resid features:
anny
Tokenanny
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
lone
Token lone
Feature activation+0.028
Top resid features:
multicultural
Token multicultural
Feature activation+0.001
Top resid features:
makeup
Token makeup
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
Hugo
Token Hugo
Feature activation+0.001
Top resid features:
winners
Token winners
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.969
Top resid features:
books
Tokenbooks
Feature activation-0.006
Top resid features:
featuring
Token featuring
Feature activation+0.048
Top resid features:
women
Token women
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
gay
Token gay
Feature activation+0.095
Top resid features:
have
Token have
Feature activation+0.036
Top resid features:
since
Token since
Feature activation+0.017
Top resid features:
lost
Token lost
Feature activation+0.002
Top resid features:
their
Token their
Feature activation+0.004
Top resid features:
jobs
Token jobs
Feature activation+0.003
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.064
Top resid features:
the
Token the
Feature activation+0.060
Top resid features:
Tigers
Token Tigers
Feature activation+0.005
Top resid features:
dismissed
Token dismissed
Feature activation+0.025
Top resid features:
Dave
Token Dave
Feature activation+0.014
Top resid features:
D
Token D
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Apple
TokenApple
Feature activation-0.005
Top resid features:
now
Token now
Feature activation-0.004
Top resid features:
asserts
Token asserts
Feature activation-0.028
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.114
Top resid features:
in
Tokenin
Feature activation+0.080
Top resid features:
a
Token a
Feature activation+0.041
Top resid features:
filing
Token filing
Feature activation+0.018
Top resid features:
with
Token with
Feature activation+0.056
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
have
Token have
Feature activation+0.017
Top resid features:
since
Token since
Feature activation+0.012
Top resid features:
lost
Token lost
Feature activation+0.001
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
jobs
Token jobs
Feature activation+0.008
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.023
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
Tigers
Token Tigers
Feature activation+0.012
Top resid features:
dismissed
Token dismissed
Feature activation+0.019
Top resid features:
Dave
Token Dave
Feature activation+0.017
Top resid features:
D
Token D
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
a
Tokena
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
half
Tokenhalf
Feature activation-0.002
Top resid features:
wars
Token wars
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.145
Top resid features:
big
Tokenbig
Feature activation+0.010
Top resid features:
wars
Token wars
Feature activation+0.006
Top resid features:
against
Token against
Feature activation+0.012
Top resid features:
Russia
Token Russia
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
affecting
Token affecting
Feature activation+0.012
Top resid features:
high
Token high
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
income
Tokenincome
Feature activation+0.001
Top resid features:
taxpayers
Token taxpayers
Feature activation+0.011
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.158
Top resid features:
orig
Tokenorig
Feature activation-0.003
Top resid features:
inally
Tokeninally
Feature activation+0.022
Top resid features:
enacted
Token enacted
Feature activation+0.021
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
2001
Token 2001
Feature activation+0.006
Top resid features:
still
Token still
Feature activation+0.001
Top resid features:
off
Token off
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
distance
Token distance
Feature activation+0.003
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.132
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
new
Token new
Feature activation+0.018
Top resid features:
Xbox
Token Xbox
Feature activation+0.004
Top resid features:
One
Token One
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
multicultural
Token multicultural
Feature activation+0.001
Top resid features:
makeup
Token makeup
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
Hugo
Token Hugo
Feature activation-0.000
Top resid features:
winners
Token winners
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.784
Top resid features:
books
Tokenbooks
Feature activation-0.001
Top resid features:
featuring
Token featuring
Feature activation+0.035
Top resid features:
women
Token women
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
gay
Token gay
Feature activation+0.083
Top resid features:
great
Token great
Feature activation+0.008
Top resid features:
contemporary
Token contemporary
Feature activation+0.010
Top resid features:
authorities
Token authorities
Feature activation+0.003
Top resid features:
on
Token on
Feature activation+0.017
Top resid features:
famine
Token famine
Feature activation-0.005
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.866
Top resid features:
among
Tokenamong
Feature activation+0.106
Top resid features:
them
Token them
Feature activation+0.117
Top resid features:
Am
Token Am
Feature activation-0.004
Top resid features:
art
Tokenart
Feature activation-0.003
Top resid features:
ya
Tokenya
Feature activation-0.000
Top resid features:
have
Token have
Feature activation+0.007
Top resid features:
since
Token since
Feature activation+0.014
Top resid features:
lost
Token lost
Feature activation+0.003
Top resid features:
their
Token their
Feature activation-0.002
Top resid features:
jobs
Token jobs
Feature activation+0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.870
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
Tigers
Token Tigers
Feature activation+0.006
Top resid features:
dismissed
Token dismissed
Feature activation+0.074
Top resid features:
Dave
Token Dave
Feature activation+0.040
Top resid features:
D
Token D
Feature activation+0.034
Top resid features:
draft
Token draft
Feature activation-0.004
Top resid features:
showed
Token showed
Feature activation-0.054
Top resid features:
key
Token key
Feature activation-0.000
Top resid features:
budget
Token budget
Feature activation-0.001
Top resid features:
areas
Token areas
Feature activation-0.002
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.047
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
Common
Token Common
Feature activation+0.001
Top resid features:
Agricultural
Token Agricultural
Feature activation+0.002
Top resid features:
Policy
Token Policy
Feature activation+0.001
Top resid features:
support
Token support
Feature activation-0.002
Top resid features:
great
Token great
Feature activation+0.010
Top resid features:
contemporary
Token contemporary
Feature activation+0.013
Top resid features:
authorities
Token authorities
Feature activation+0.004
Top resid features:
on
Token on
Feature activation+0.017
Top resid features:
famine
Token famine
Feature activation-0.009
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.735
Top resid features:
among
Tokenamong
Feature activation+0.139
Top resid features:
them
Token them
Feature activation+0.214
Top resid features:
Am
Token Am
Feature activation+0.007
Top resid features:
art
Tokenart
Feature activation+0.002
Top resid features:
ya
Tokenya
Feature activation+0.043
Top resid features:
from
Token from
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
DS
Token DS
Feature activation-0.000
Top resid features:
9
Token9
Feature activation+0.000
Top resid features:
universe
Token universe
Feature activation-0.001
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.879
Top resid features:
one
Token one
Feature activation+0.036
Top resid features:
that
Token that
Feature activation+0.101
Top resid features:
was
Token was
Feature activation+0.021
Top resid features:
unpredictable
Token unpredictable
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
bit
Token bit
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
or
Token or
Feature activation+0.005
Top resid features:
qu
Token qu
Feature activation+0.002
Top resid features:
bit
Tokenbit
Feature activation+0.003
Top resid features:
--
Token--
Feature activation+1.796
Top resid features:
the
Tokenthe
Feature activation+0.114
Top resid features:
basic
Token basic
Feature activation+0.021
Top resid features:
unit
Token unit
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
information
Token information
Feature activation+0.015
Top resid features:
olic
Tokenolic
Feature activation+0.001
Top resid features:
Church
Token Church
Feature activation+0.001
Top resid features:
were
Token were
Feature activation+0.002
Top resid features:
effectively
Token effectively
Feature activation-0.002
Top resid features:
banned
Token banned
Feature activation-0.015
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.030
Top resid features:
visiting
Token visiting
Feature activation+0.022
Top resid features:
pre
Token pre
Feature activation+0.004
Top resid features:
achers
Tokenachers
Feature activation+0.044
Top resid features:
from
Token from
Feature activation+0.048
Top resid features:
rival
Token rival
Feature activation+0.022
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
second
Tokensecond
Feature activation-0.000
Top resid features:
Street
Token Street
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Everyone
Token Everyone
Feature activation+0.016
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.964
Top resid features:
his
Tokenhis
Feature activation+0.055
Top resid features:
brothers
Token brothers
Feature activation+0.081
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
sisters
Token sisters
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+0.081
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
eight
Token eight
Feature activation-0.002
Top resid features:
minutes
Token minutes
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
coverage
Token coverage
Feature activation-0.010
Top resid features:
--
Token --
Feature activation+1.858
Top resid features:
one
Token one
Feature activation+0.068
Top resid features:
-
Token-
Feature activation+0.050
Top resid features:
fifth
Tokenfifth
Feature activation+0.037
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
Bush
Token Bush
Feature activation+0.049
Top resid features:
contrast
Token contrast
Feature activation+0.080
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
Taiwanese
Token Taiwanese
Feature activation+0.013
Top resid features:
political
Token political
Feature activation+0.014
Top resid features:
emotions
Token emotions
Feature activation+0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.771
Top resid features:
indignation
Token indignation
Feature activation+0.040
Top resid features:
from
Token from
Feature activation+0.035
Top resid features:
years
Token years
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.070
Top resid features:
international
Token international
Feature activation+0.042
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.43

Head 2: 0.06

Head 3: 0.03

Head 4: 0.03

Head 5: 0.08

Head 6: 0.05

Head 7: 0.05

Head 8: 0.06

Head 9: 0.08

Head 10: 0.07

Head 11: 0.05

Positive logits

*)3.66

?)3.62

!)3.59

?).3.51

!).3.33

-)3.28

!),3.26

*)3.26

)?3.21

?),3.19

)3.13

)*3.00

)2.97

)}2.95

).2.88

)/2.86

?)2.78

…)2.76

});2.72

)!2.72

Negative logits

":[{"-1.88

orget-1.79

":[-1.78

Dialogue-1.76

ubis-1.76

ielding-1.74

venants-1.68

ACTIONS-1.67

raltar-1.66

reth-1.62

ospel-1.61

"""-1.59

gobl-1.57

owship-1.57

orsi-1.56

agascar-1.56

farious-1.53

orah-1.53

risome-1.53

ciplinary-1.53

INTERVAL 1.991 - 2.212
CONTAINS 0.000%

mum
Token mum
Feature activation+0.620
and
Token and
Feature activation+1.462
father
Token father
Feature activation+0.663
less
Tokenless
Feature activation+0.501
children
Token children
Feature activation+1.509
,
Token,
Feature activation+2.139
all
Token all
Feature activation+1.353
expecting
Token expecting
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
wars
Token wars
Feature activation+0.000
against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.647
and
Token and
Feature activation+0.913
China
Token China
Feature activation+0.790
,
Token,
Feature activation+2.212
and
Token and
Feature activation+1.787
a
Token a
Feature activation+0.515
half
Token half
Feature activation+0.000
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.770 - 1.991
CONTAINS 0.001%

rows
Tokenrows
Feature activation+0.000
ki
Tokenki
Feature activation+0.358
this
Token this
Feature activation+1.632
past
Token past
Feature activation+0.851
August
Token August
Feature activation+0.950
,
Token,
Feature activation+1.791
and
Token and
Feature activation+1.802
the
Token the
Feature activation+0.244
Braves
Token Braves
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
ki
Tokenki
Feature activation+0.358
this
Token this
Feature activation+1.632
past
Token past
Feature activation+0.851
August
Token August
Feature activation+0.950
,
Token,
Feature activation+1.791
and
Token and
Feature activation+1.802
the
Token the
Feature activation+0.244
Braves
Token Braves
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
,
Token,
Feature activation+0.411
gay
Token gay
Feature activation+0.154
and
Token and
Feature activation+0.343
lesbian
Token lesbian
Feature activation+0.457
characters
Token characters
Feature activation+1.574
,
Token,
Feature activation+1.856
and
Token and
Feature activation+1.676
people
Token people
Feature activation+0.035
and
Token and
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
of
Token of
Feature activation+0.000
against
Token against
Feature activation+0.000
Russia
Token Russia
Feature activation+0.647
and
Token and
Feature activation+0.913
China
Token China
Feature activation+0.790
,
Token,
Feature activation+2.212
and
Token and
Feature activation+1.787
a
Token a
Feature activation+0.515
half
Token half
Feature activation+0.000
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
filing
Token filing
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
TC
TokenTC
Feature activation+0.000
,
Token,
Feature activation+1.793
which
Token which
Feature activation+1.385
means
Token means
Feature activation+0.239
Apple
Token Apple
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.549 - 1.770
CONTAINS 0.002%

Ã
Token Ã
Feature activation+0.000
ĵ
Tokenĵ
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
á
Tokená
Feature activation+0.000
da
Tokenda
Feature activation+0.000
,
Token,
Feature activation+1.645
and
Token and
Feature activation+1.556
Alex
Token Alex
Feature activation+0.000
de
Token de
Feature activation+0.000
Wa
Token Wa
Feature activation+0.000
al
Tokenal
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
you
Token you
Feature activation+0.000
believe
Token believe
Feature activation+0.000
it
Token it
Feature activation+0.682
,
Token,
Feature activation+1.551
a
Token a
Feature activation+0.335
Michael
Token Michael
Feature activation+0.000
Is
Token Is
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
Dave
Token Dave
Feature activation+0.022
D
Token D
Feature activation+0.000
omb
Tokenomb
Feature activation+0.000
rows
Tokenrows
Feature activation+0.000
ki
Tokenki
Feature activation+0.358
this
Token this
Feature activation+1.632
past
Token past
Feature activation+0.851
August
Token August
Feature activation+0.950
,
Token,
Feature activation+1.791
and
Token and
Feature activation+1.802
the
Token the
Feature activation+0.244
women
Token women
Feature activation+0.074
,
Token,
Feature activation+0.411
gay
Token gay
Feature activation+0.154
and
Token and
Feature activation+0.343
lesbian
Token lesbian
Feature activation+0.457
characters
Token characters
Feature activation+1.574
,
Token,
Feature activation+1.856
and
Token and
Feature activation+1.676
people
Token people
Feature activation+0.035
and
Token and
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
gay
Token gay
Feature activation+0.154
and
Token and
Feature activation+0.343
lesbian
Token lesbian
Feature activation+0.457
characters
Token characters
Feature activation+1.574
,
Token,
Feature activation+1.856
and
Token and
Feature activation+1.676
people
Token people
Feature activation+0.035
and
Token and
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000

INTERVAL 1.327 - 1.549
CONTAINS 0.003%

and
Token and
Feature activation+1.462
father
Token father
Feature activation+0.663
less
Tokenless
Feature activation+0.501
children
Token children
Feature activation+1.509
,
Token,
Feature activation+2.139
all
Token all
Feature activation+1.353
expecting
Token expecting
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
stand
Token stand
Feature activation+0.000
to
Token to
Feature activation+0.009
his
Token his
Feature activation+0.246
seizure
Token seizure
Feature activation+0.000
problem
Token problem
Feature activation+0.131
,
Token,
Feature activation+1.426
and
Token and
Feature activation+1.441
stress
Token stress
Feature activation+0.000
.
Token.
Feature activation+0.000
"[
Token "[
Feature activation+0.000
T
TokenT
Feature activation+0.000
]
Token]
Feature activation+0.000
series
Token series
Feature activation+0.154
of
Token of
Feature activation+0.208
ambitious
Token ambitious
Feature activation+0.179
performance
Token performance
Feature activation+0.032
requirements
Token requirements
Feature activation+0.408
,
Token,
Feature activation+1.434
including
Token including
Feature activation+0.336
net
Token net
Feature activation+0.000
zero
Token zero
Feature activation+0.000
energy
Token energy
Feature activation+0.000
,
Token,
Feature activation+0.335
chief
Token chief
Feature activation+0.000
of
Token of
Feature activation+0.000
staff
Token staff
Feature activation+0.369
Katie
Token Katie
Feature activation+0.044
Walsh
Token Walsh
Feature activation+0.949
and
Token and
Feature activation+1.460
former
Token former
Feature activation+0.613
communications
Token communications
Feature activation+0.234
director
Token director
Feature activation+0.291
Mike
Token Mike
Feature activation+0.000
Dub
Token Dub
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
no
Token no
Feature activation+0.213
LinkedIn
Token LinkedIn
Feature activation+0.419
employment
Token employment
Feature activation+0.189
changes
Token changes
Feature activation+0.469
,
Token,
Feature activation+1.544
no
Token no
Feature activation+1.138
announcements
Token announcements
Feature activation+0.307
to
Token to
Feature activation+0.000
Ott
Token Ott
Feature activation+0.224
oc
Tokenoc
Feature activation+0.000

INTERVAL 1.106 - 1.327
CONTAINS 0.007%

part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.033
the
Token the
Feature activation+0.104
story
Token story
Feature activation+0.516
,
Token,
Feature activation+0.934
and
Token and
Feature activation+1.290
a
Token a
Feature activation+0.230
designation
Token designation
Feature activation+0.407
Jane
Token Jane
Feature activation+0.261
doesn
Token doesn
Feature activation+0.402
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.623
2
Token 2
Feature activation+0.111
,
Token,
Feature activation+0.572
000
Token000
Feature activation+0.516
yuan
Token yuan
Feature activation+0.864
more
Token more
Feature activation+1.300
than
Token than
Feature activation+0.706
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
previously
Token previously
Feature activation+0.000
have
Token have
Feature activation+0.000
Abby
Token Abby
Feature activation+0.000
Er
Token Er
Feature activation+0.000
ce
Tokence
Feature activation+0.000
g
Tokeng
Feature activation+0.000
after
Token after
Feature activation+1.149
her
Token her
Feature activation+0.011
red
Token red
Feature activation+0.000
card
Token card
Feature activation+0.000
was
Token was
Feature activation+0.496
overturned
Token overturned
Feature activation+0.000
ior
Tokenior
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
featured
Token featured
Feature activation+0.000
)
Token)
Feature activation+1.310
and
Token and
Feature activation+0.841
newer
Token newer
Feature activation+0.000
names
Token names
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
when
Token when
Feature activation+0.353
you
Token you
Feature activation+0.296
overcome
Token overcome
Feature activation+0.000
a
Token a
Feature activation+0.000
challenge
Token challenge
Feature activation+0.000
,
Token,
Feature activation+1.180
the
Token the
Feature activation+0.742
joy
Token joy
Feature activation+0.000
of
Token of
Feature activation+0.000
discovery
Token discovery
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 0.885 - 1.106
CONTAINS 0.016%

âĢĶ
Token âĢĶ
Feature activation+0.091
brilliant
Token brilliant
Feature activation+0.000
,
Token,
Feature activation+0.000
cold
Token cold
Feature activation+0.126
,
Token,
Feature activation+0.188
and
Token and
Feature activation+1.048
calculating
Token calculating
Feature activation+0.676
,
Token,
Feature activation+0.772
but
Token but
Feature activation+0.899
prone
Token prone
Feature activation+0.000
to
Token to
Feature activation+0.000
character
Token character
Feature activation+0.000
-
Token -
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
stage
Token stage
Feature activation+0.000
,
Token,
Feature activation+0.956
working
Token working
Feature activation+0.645
without
Token without
Feature activation+0.037
a
Token a
Feature activation+0.000
name
Token name
Feature activation+0.066
-
Token -
Feature activation+0.000
all
Token all
Feature activation+0.266
usions
Tokenusions
Feature activation+0.884
to
Token to
Feature activation+0.277
Sanders
Token Sanders
Feature activation+0.436
,
Token,
Feature activation+1.200
the
Token the
Feature activation+0.970
Vermont
Token Vermont
Feature activation+0.000
socialist
Token socialist
Feature activation+0.000
polling
Token polling
Feature activation+0.001
competitive
Token competitive
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
Java
Token Java
Feature activation+0.318
lets
Token lets
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.472
,
Token,
Feature activation+1.041
and
Token and
Feature activation+0.393
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
encouraged
Token encouraged
Feature activation+0.000
back
Token back
Feature activation+0.000
current
Token current
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
public
Token public
Feature activation+0.000
health
Token health
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.389
say
Token say
Feature activation+1.060
men
Token men
Feature activation+0.593
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
travelled
Token travelled
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.664 - 0.885
CONTAINS 0.026%

brilliant
Token brilliant
Feature activation+0.000
,
Token,
Feature activation+0.000
cold
Token cold
Feature activation+0.126
,
Token,
Feature activation+0.188
and
Token and
Feature activation+1.048
calculating
Token calculating
Feature activation+0.676
,
Token,
Feature activation+0.772
but
Token but
Feature activation+0.899
prone
Token prone
Feature activation+0.000
to
Token to
Feature activation+0.000
fits
Token fits
Feature activation+0.000
0
Token 0
Feature activation+0.000
to
Token to
Feature activation+0.000
about
Token about
Feature activation+0.046
40
Token 40
Feature activation+0.296
percent
Token percent
Feature activation+0.259
in
Token in
Feature activation+0.867
an
Token an
Feature activation+0.229
hour
Token hour
Feature activation+0.078
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
includes
Token includes
Feature activation+0.000
-
Token-
Feature activation+0.080
b
Tokenb
Feature activation+0.000
ashing
Tokenashing
Feature activation+0.000
in
Token in
Feature activation+0.244
general
Token general
Feature activation+0.284
,
Token,
Feature activation+0.665
rev
Token rev
Feature activation+0.201
s
Tokens
Feature activation+0.492
up
Token up
Feature activation+0.000
its
Token its
Feature activation+0.000
base
Token base
Feature activation+0.000
adult
Token adult
Feature activation+0.000
in
Token in
Feature activation+0.183
the
Token the
Feature activation+0.210
room
Token room
Feature activation+0.157
he
Token he
Feature activation+0.648
was
Token was
Feature activation+0.718
trying
Token trying
Feature activation+0.467
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
bigotry
Token bigotry
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.696
knowing
Token knowing
Feature activation+0.000
lies
Token lies
Feature activation+0.000
,
Token,
Feature activation+0.433
the
Token the
Feature activation+0.332
attempted
Token attempted
Feature activation+0.000

INTERVAL 0.442 - 0.664
CONTAINS 0.061%

.
Token.
Feature activation+0.000
M
TokenM
Feature activation+0.000
.
Token.
Feature activation+0.319
âĢ
TokenâĢ
Feature activation+0.468
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.443
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Sh
TokenSh
Feature activation+0.000
iny
Tokeniny
Feature activation+0.000
Happy
Token Happy
Feature activation+0.000
covered
Token covered
Feature activation+0.098
by
Token by
Feature activation+0.099
Federal
Token Federal
Feature activation+0.000
Regulations
Token Regulations
Feature activation+0.000
,
Token,
Feature activation+0.944
viz
Token viz
Feature activation+0.512
:
Token:
Feature activation+0.000
IT
Token IT
Feature activation+0.000
AR
TokenAR
Feature activation+0.000
(
Token (
Feature activation+0.000
International
TokenInternational
Feature activation+0.000
decision
Token decision
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.452
made
Token made
Feature activation+0.274
fifteen
Token fifteen
Feature activation+0.282
years
Token years
Feature activation+0.491
earlier
Token earlier
Feature activation+0.793
âĢĶ
TokenâĢĶ
Feature activation+0.000
me
Tokenme
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
verge
Token verge
Feature activation+0.000
of
Token of
Feature activation+0.000
graduating
Token graduating
Feature activation+0.689
high
Token high
Feature activation+0.184
school
Token school
Feature activation+0.546
no
Token no
Feature activation+1.085
less
Token less
Feature activation+0.000
--
Token --
Feature activation+0.000
be
Token be
Feature activation+0.000
unable
Token unable
Feature activation+0.000
and
Token and
Feature activation+0.000
decisive
Token decisive
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.006
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.631
times
Token times
Feature activation+0.160
,
Token,
Feature activation+0.302
attacked
Token attacked
Feature activation+0.547
Romney
Token Romney
Feature activation+0.596
and
Token and
Feature activation+0.020

INTERVAL 0.221 - 0.442
CONTAINS 0.119%

Internet
Token Internet
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
book
Token book
Feature activation+0.333
came
Token came
Feature activation+0.291
within
Token within
Feature activation+0.244
one
Token one
Feature activation+0.398
tick
Token tick
Feature activation+0.000
mark
Token mark
Feature activation+0.262
of
Token of
Feature activation+0.000
making
Token making
Feature activation+0.039
ucked
Tokenucked
Feature activation+0.159
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
consciousness
Token consciousness
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.229
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
renowned
Token renowned
Feature activation+0.000
gen
Token gen
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.034
Trevor
Token Trevor
Feature activation+0.014
Stanley
Token Stanley
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.117
he
Tokenhe
Feature activation+0.000
decided
Token decided
Feature activation+0.282
that
Token that
Feature activation+0.172
the
Token the
Feature activation+0.000
ballot
Token ballot
Feature activation+0.000
expressed
Token expressed
Feature activation+0.000
an
Token an
Feature activation+0.000
asure
Tokenasure
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
by
Tokenby
Feature activation+0.000
approving
Token approving
Feature activation+0.846
an
Token an
Feature activation+0.000
interpretation
Token interpretation
Feature activation+0.358
of
Token of
Feature activation+0.054
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ind
Tokenind
Feature activation+0.000
ec
Tokenec
Feature activation+0.000
was
Token was
Feature activation+0.000
outlawed
Token outlawed
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
never
Token never
Feature activation+0.213
mind
Token mind
Feature activation+0.208
that
Token that
Feature activation+0.248
it
Token it
Feature activation+0.607
wasn
Token wasn
Feature activation+0.231
âĢ
TokenâĢ
Feature activation+0.190
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000

INTERVAL 0.000 - 0.221
CONTAINS 99.766%

season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
procedure
Token procedure
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
complicated
Token complicated
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
medical
Token medical
Feature activation+0.000
staff
Token staff
Feature activation+0.000
Law
Token Law
Feature activation+0.000
School
Token School
Feature activation+0.000
professor
Token professor
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
it
Tokenit
Feature activation+0.000
Berger
Token Berger
Feature activation+0.000
uttered
Token uttered
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Personally
TokenPersonally
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
more
Token more
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
create
Token create
Feature activation+0.000
that
Token that
Feature activation+0.000
many
Token many
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
or
Token or
Feature activation+0.000
finance
Token finance
Feature activation+0.000
existing
Token existing
Feature activation+0.000
,
Token,
Feature activation+0.000
crumbling
Token crumbling
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 H3.1: (feature 23769)

TOP ACTIVATIONS
MAX = 3.540

fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
other
Token other
Feature activation+2.436
credible
Token credible
Feature activation+1.803
,
Token,
Feature activation+0.000
serious
Token serious
Feature activation+3.540
choices
Token choices
Feature activation+2.645
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Comments
TokenComments
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
scientist
Token scientist
Feature activation+1.122
,
Token,
Feature activation+0.127
of
Token of
Feature activation+0.368
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
than
Token than
Feature activation+3.474
collecting
Token collecting
Feature activation+0.171
and
Token and
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
data
Token data
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
every
Token every
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
)
Token)
Feature activation+0.027
to
Token to
Feature activation+3.439
go
Token go
Feature activation+2.229
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
are
Token are
Feature activation+0.000
few
Token few
Feature activation+0.436
prominent
Token prominent
Feature activation+0.720
Republican
Token Republican
Feature activation+0.052
leaders
Token leaders
Feature activation+0.234
left
Token left
Feature activation+3.191
with
Token with
Feature activation+0.000
military
Token military
Feature activation+0.000
bona
Token bona
Feature activation+0.000
f
Token f
Feature activation+0.000
ides
Tokenides
Feature activation+0.725
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+3.181
very
Token very
Feature activation+2.186
pronounced
Token pronounced
Feature activation+0.389
ethos
Token ethos
Feature activation+0.371
of
Token of
Feature activation+0.740
ant
Token ant
Feature activation+0.000
there
Token there
Feature activation+0.377
's
Token's
Feature activation+0.095
something
Token something
Feature activation+0.000
to
Token to
Feature activation+0.991
be
Token be
Feature activation+0.151
said
Token said
Feature activation+3.091
for
Token for
Feature activation+0.000
being
Token being
Feature activation+0.000
proud
Token proud
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
something
Token something
Feature activation+0.000
to
Token to
Feature activation+1.683
be
Token be
Feature activation+0.449
said
Token said
Feature activation+3.063
for
Token for
Feature activation+0.177
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.259
of
Token of
Feature activation+0.260
nice
Token nice
Feature activation+0.836
mathematics
Token mathematics
Feature activation+1.462
that
Token that
Feature activation+3.020
can
Token can
Feature activation+1.502
be
Token be
Feature activation+0.433
glean
Token glean
Feature activation+0.071
ed
Tokened
Feature activation+0.229
from
Token from
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.762
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
significant
Token significant
Feature activation+3.016
practical
Token practical
Feature activation+1.032
reasons
Token reasons
Feature activation+0.917
why
Token why
Feature activation+0.495
government
Token government
Feature activation+0.000
aff
Token aff
Feature activation+0.000
loosen
Token loosen
Feature activation+0.000
ess
Tokeness
Feature activation+0.000
and
Token and
Feature activation+0.131
play
Token play
Feature activation+0.379
fulness
Tokenfulness
Feature activation+0.177
that
Token that
Feature activation+2.854
is
Token is
Feature activation+0.461
pretty
Token pretty
Feature activation+0.000
unique
Token unique
Feature activation+1.183
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
much
Token much
Feature activation+0.000
money
Token money
Feature activation+1.961
to
Token to
Feature activation+2.854
collect
Token collect
Feature activation+0.000
:
Token:
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
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.136
be
Token be
Feature activation+0.269
the
Token the
Feature activation+1.694
proletariat
Token proletariat
Feature activation+0.000
left
Token left
Feature activation+2.835
in
Token in
Feature activation+0.123
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
sights
Token sights
Feature activation+0.000
and
Token and
Feature activation+0.000
prices
Token prices
Feature activation+0.424
are
Token are
Feature activation+1.095
significantly
Token significantly
Feature activation+0.000
cheaper
Token cheaper
Feature activation+2.818
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
for
Token for
Feature activation+0.000
hotels
Token hotels
Feature activation+0.000
and
Token and
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.099
always
Token always
Feature activation+0.000
something
Token something
Feature activation+2.335
interesting
Token interesting
Feature activation+2.714
to
Token to
Feature activation+2.780
do
Token do
Feature activation+1.653
in
Token in
Feature activation+0.206
R
Token R
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
G
TokenG
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.099
always
Token always
Feature activation+0.000
something
Token something
Feature activation+2.335
interesting
Token interesting
Feature activation+2.714
to
Token to
Feature activation+2.780
do
Token do
Feature activation+1.653
in
Token in
Feature activation+0.206
R
Token R
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
money
Token money
Feature activation+2.341
to
Token to
Feature activation+2.707
let
Token let
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
lucrative
Token lucrative
Feature activation+0.097
practice
Token practice
Feature activation+0.000
are
Token are
Feature activation+0.000
desp
Token desp
Feature activation+0.000
ots
Tokenots
Feature activation+0.238
and
Token and
Feature activation+0.818
murderers
Token murderers
Feature activation+1.282
out
Token out
Feature activation+2.687
there
Token there
Feature activation+0.000
who
Token who
Feature activation+0.959
have
Token have
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
less
Token less
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
enough
Token enough
Feature activation+0.000
money
Token money
Feature activation+0.856
left
Token left
Feature activation+2.665
over
Token over
Feature activation+0.000
for
Token for
Feature activation+0.000
renovations
Token renovations
Feature activation+0.000
,
Token,
Feature activation+0.000
along
Token along
Feature activation+0.000
,
Token,
Feature activation+0.000
other
Token other
Feature activation+2.436
credible
Token credible
Feature activation+1.803
,
Token,
Feature activation+0.000
serious
Token serious
Feature activation+3.540
choices
Token choices
Feature activation+2.645
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Comments
TokenComments
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
about
Token about
Feature activation+0.014
7
Token 7
Feature activation+0.551
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
billion
Token billion
Feature activation+2.017
people
Token people
Feature activation+2.644
out
Token out
Feature activation+2.310
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000

Top DFA by src position
MAX = 4.460

to
Token to
Feature activation+0.007
Top resid features:
see
Token see
Feature activation-0.033
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
hear
Token hear
Feature activation-0.003
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
there
Token there
Feature activation+4.460
Top resid features:
are
Token are
Feature activation-0.429
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
fact
Token fact
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
caught
Token caught
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
consumed
Token consumed
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
But
Token But
Feature activation+0.015
Top resid features:
there
Token there
Feature activation+4.008
Top resid features:
is
Token is
Feature activation-0.089
Top resid features:
more
Token more
Feature activation-0.020
Top resid features:
to
Token to
Feature activation+0.046
Top resid features:
being
Token being
Feature activation-0.023
Top resid features:
a
Token a
Feature activation-0.014
Top resid features:
NOT
Token NOT
Feature activation+0.003
Top resid features:
shoot
Token shoot
Feature activation-0.001
Top resid features:
green
Token green
Feature activation-0.001
Top resid features:
tanks
Token tanks
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
There
Token There
Feature activation+4.167
Top resid features:
are
Token are
Feature activation-0.364
Top resid features:
plenty
Token plenty
Feature activation+0.090
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
red
Token red
Feature activation+0.030
Top resid features:
ones
Token ones
Feature activation+0.029
Top resid features:
retiring
Token retiring
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Senate
Token Senate
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
there
Token there
Feature activation+3.769
Top resid features:
are
Token are
Feature activation-0.202
Top resid features:
few
Token few
Feature activation-0.034
Top resid features:
prominent
Token prominent
Feature activation+0.013
Top resid features:
Republican
Token Republican
Feature activation+0.021
Top resid features:
leaders
Token leaders
Feature activation+0.084
Top resid features:
free
Token free
Feature activation-0.000
Top resid features:
exchange
Token exchange
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ideas
Token ideas
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
There
Token There
Feature activation+4.253
Top resid features:
was
Token was
Feature activation-0.626
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
however
Token however
Feature activation+0.026
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
some
Token some
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
including
Token including
Feature activation+0.009
Top resid features:
me
Token me
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
there
Token there
Feature activation+3.961
Top resid features:
's
Token's
Feature activation-0.048
Top resid features:
something
Token something
Feature activation-0.170
Top resid features:
to
Token to
Feature activation-0.035
Top resid features:
be
Token be
Feature activation-0.181
Top resid features:
said
Token said
Feature activation+0.049
Top resid features:
however
Token however
Feature activation+0.001
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.013
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
There
Token There
Feature activation+3.797
Top resid features:
âĢ
TokenâĢ
Feature activation-0.009
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
s
Tokens
Feature activation-0.016
Top resid features:
something
Token something
Feature activation-0.083
Top resid features:
to
Token to
Feature activation-0.028
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
explored
Token explored
Feature activation+0.006
Top resid features:
:
Token:
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
There
TokenThere
Feature activation+3.272
Top resid features:
is
Token is
Feature activation-0.100
Top resid features:
quite
Token quite
Feature activation+0.015
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
lot
Token lot
Feature activation-0.026
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
IONS
TokenIONS
Feature activation-0.002
Top resid features:
OF
Token OF
Feature activation+0.002
Top resid features:
MOR
Token MOR
Feature activation+0.007
Top resid features:
AL
TokenAL
Feature activation+0.001
Top resid features:
ITY
TokenITY
Feature activation+0.005
Top resid features:
There
Token There
Feature activation+4.133
Top resid features:
are
Token are
Feature activation-0.652
Top resid features:
,
Token,
Feature activation+0.084
Top resid features:
then
Token then
Feature activation-0.074
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
significant
Token significant
Feature activation+0.054
Top resid features:
Wash
Token Wash
Feature activation+0.001
Top resid features:
burn
Tokenburn
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
âĢ
Token âĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.005
Top resid features:
There
TokenThere
Feature activation+3.615
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.020
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.324
Top resid features:
loosen
Token loosen
Feature activation+0.011
Top resid features:
though
Token though
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
hope
Token hope
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.015
Top resid features:
there
Token there
Feature activation+3.392
Top resid features:
won
Token won
Feature activation-0.037
Top resid features:
't
Token't
Feature activation-0.010
Top resid features:
be
Token be
Feature activation-0.081
Top resid features:
much
Token much
Feature activation-0.000
Top resid features:
money
Token money
Feature activation+0.085
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
destroy
Token destroy
Feature activation+0.003
Top resid features:
each
Token each
Feature activation+0.002
Top resid features:
other
Token other
Feature activation+0.001
Top resid features:
so
Token so
Feature activation+0.003
Top resid features:
there
Token there
Feature activation+3.599
Top resid features:
will
Token will
Feature activation-0.039
Top resid features:
only
Token only
Feature activation+0.042
Top resid features:
be
Token be
Feature activation-0.142
Top resid features:
the
Token the
Feature activation-0.091
Top resid features:
proletariat
Token proletariat
Feature activation+0.014
Top resid features:
aspect
Token aspect
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
this
Token this
Feature activation-0.005
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.035
Top resid features:
there
Token there
Feature activation+3.149
Top resid features:
are
Token are
Feature activation-0.012
Top resid features:
no
Token no
Feature activation+0.008
Top resid features:
lines
Token lines
Feature activation+0.014
Top resid features:
at
Token at
Feature activation+0.005
Top resid features:
any
Token any
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
There
Token There
Feature activation+3.407
Top resid features:
is
Token is
Feature activation-0.040
Top resid features:
always
Token always
Feature activation+0.020
Top resid features:
something
Token something
Feature activation-0.238
Top resid features:
interesting
Token interesting
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+0.108
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.017
Top resid features:
There
Token There
Feature activation+3.575
Top resid features:
is
Token is
Feature activation-0.059
Top resid features:
always
Token always
Feature activation+0.127
Top resid features:
something
Token something
Feature activation-0.517
Top resid features:
interesting
Token interesting
Feature activation+0.134
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
real
Tokenreal
Feature activation-0.001
Top resid features:
crimes
Token crimes
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
there
Token there
Feature activation+3.128
Top resid features:
âĢ
TokenâĢ
Feature activation-0.018
Top resid features:
Ļ
TokenĻ
Feature activation-0.042
Top resid features:
s
Tokens
Feature activation-0.028
Top resid features:
too
Token too
Feature activation+0.080
Top resid features:
much
Token much
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
he
Token he
Feature activation+0.005
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
done
Token done
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
there
Token there
Feature activation+3.277
Top resid features:
are
Token are
Feature activation-0.290
Top resid features:
desp
Token desp
Feature activation+0.016
Top resid features:
ots
Tokenots
Feature activation+0.036
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
murderers
Token murderers
Feature activation+0.088
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
000
Token000
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
so
Token so
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
there
Token there
Feature activation+3.266
Top resid features:
was
Token was
Feature activation-0.137
Top resid features:
enough
Token enough
Feature activation+0.009
Top resid features:
money
Token money
Feature activation+0.058
Top resid features:
left
Token left
Feature activation+0.001
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
see
Token see
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
hear
Token hear
Feature activation-0.008
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
there
Token there
Feature activation+3.328
Top resid features:
are
Token are
Feature activation-0.332
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
fact
Token fact
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
But
Token But
Feature activation+0.001
Top resid features:
you
Token you
Feature activation+0.016
Top resid features:
know
Token know
Feature activation+0.002
Top resid features:
what
Token what
Feature activation-0.004
Top resid features:
?
Token?
Feature activation+0.028
Top resid features:
There
Token There
Feature activation+3.409
Top resid features:
are
Token are
Feature activation-0.371
Top resid features:
about
Token about
Feature activation-0.008
Top resid features:
7
Token 7
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.43

Head 2: 0.10

Head 3: 0.02

Head 4: 0.01

Head 5: 0.05

Head 6: 0.04

Head 7: 0.05

Head 8: 0.05

Head 9: 0.11

Head 10: 0.06

Head 11: 0.06

Positive logits

overlap1.97

lurking1.75

shortage1.63

discrepancy1.57

unaccount1.57

rez1.55

lingering1.54

ambiguity1.54

Shroud1.53

unanim1.51

variance1.45

discrepancies1.42

similarities1.41

disagreement1.39

validity1.38

mismatch1.38

TTL1.38

recurring1.37

Vand1.36

temptation1.36

Negative logits

srfAttach-1.80

cedes-1.66

bian-1.64

friend-1.59

alf-1.56

venture-1.54

aukee-1.53

oxide-1.45

gypt-1.44

ector-1.44

Lie-1.43

Analy-1.42

quickShipAvailable-1.40

inth-1.39

eper-1.37

サーティワン-1.37

independent-1.37

ison-1.36

Avg-1.36

-1.36

INTERVAL 3.186 - 3.540
CONTAINS 0.000%

fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
other
Token other
Feature activation+2.436
credible
Token credible
Feature activation+1.803
,
Token,
Feature activation+0.000
serious
Token serious
Feature activation+3.540
choices
Token choices
Feature activation+2.645
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Comments
TokenComments
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
every
Token every
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
)
Token)
Feature activation+0.027
to
Token to
Feature activation+3.439
go
Token go
Feature activation+2.229
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
are
Token are
Feature activation+0.000
few
Token few
Feature activation+0.436
prominent
Token prominent
Feature activation+0.720
Republican
Token Republican
Feature activation+0.052
leaders
Token leaders
Feature activation+0.234
left
Token left
Feature activation+3.191
with
Token with
Feature activation+0.000
military
Token military
Feature activation+0.000
bona
Token bona
Feature activation+0.000
f
Token f
Feature activation+0.000
ides
Tokenides
Feature activation+0.725
scientist
Token scientist
Feature activation+1.122
,
Token,
Feature activation+0.127
of
Token of
Feature activation+0.368
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
than
Token than
Feature activation+3.474
collecting
Token collecting
Feature activation+0.171
and
Token and
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
data
Token data
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000

INTERVAL 2.832 - 3.186
CONTAINS 0.001%

there
Token there
Feature activation+0.377
's
Token's
Feature activation+0.095
something
Token something
Feature activation+0.000
to
Token to
Feature activation+0.991
be
Token be
Feature activation+0.151
said
Token said
Feature activation+3.091
for
Token for
Feature activation+0.000
being
Token being
Feature activation+0.000
proud
Token proud
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.136
be
Token be
Feature activation+0.269
the
Token the
Feature activation+1.694
proletariat
Token proletariat
Feature activation+0.000
left
Token left
Feature activation+2.835
in
Token in
Feature activation+0.123
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
much
Token much
Feature activation+0.000
money
Token money
Feature activation+1.961
to
Token to
Feature activation+2.854
collect
Token collect
Feature activation+0.000
:
Token:
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
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.259
of
Token of
Feature activation+0.260
nice
Token nice
Feature activation+0.836
mathematics
Token mathematics
Feature activation+1.462
that
Token that
Feature activation+3.020
can
Token can
Feature activation+1.502
be
Token be
Feature activation+0.433
glean
Token glean
Feature activation+0.071
ed
Tokened
Feature activation+0.229
from
Token from
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
something
Token something
Feature activation+0.000
to
Token to
Feature activation+1.683
be
Token be
Feature activation+0.449
said
Token said
Feature activation+3.063
for
Token for
Feature activation+0.177
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 2.478 - 2.832
CONTAINS 0.002%

,
Token,
Feature activation+0.000
other
Token other
Feature activation+2.436
credible
Token credible
Feature activation+1.803
,
Token,
Feature activation+0.000
serious
Token serious
Feature activation+3.540
choices
Token choices
Feature activation+2.645
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Comments
TokenComments
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.099
of
Token of
Feature activation+0.168
sports
Token sports
Feature activation+1.757
you
Token you
Feature activation+1.933
can
Token can
Feature activation+2.642
do
Token do
Feature activation+1.238
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.209
a
Token a
Feature activation+0.000
limited
Token limited
Feature activation+0.000
sights
Token sights
Feature activation+0.000
and
Token and
Feature activation+0.000
prices
Token prices
Feature activation+0.424
are
Token are
Feature activation+1.095
significantly
Token significantly
Feature activation+0.000
cheaper
Token cheaper
Feature activation+2.818
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
for
Token for
Feature activation+0.000
hotels
Token hotels
Feature activation+0.000
and
Token and
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.099
always
Token always
Feature activation+0.000
something
Token something
Feature activation+2.335
interesting
Token interesting
Feature activation+2.714
to
Token to
Feature activation+2.780
do
Token do
Feature activation+1.653
in
Token in
Feature activation+0.206
R
Token R
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.099
always
Token always
Feature activation+0.000
something
Token something
Feature activation+2.335
interesting
Token interesting
Feature activation+2.714
to
Token to
Feature activation+2.780
do
Token do
Feature activation+1.653
in
Token in
Feature activation+0.206
R
Token R
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
G
TokenG
Feature activation+0.000

INTERVAL 2.124 - 2.478
CONTAINS 0.004%

was
Token was
Feature activation+0.000
unfortunately
Token unfortunately
Feature activation+0.000
no
Token no
Feature activation+0.898
true
Token true
Feature activation+1.342
goal
Token goal
Feature activation+1.759
to
Token to
Feature activation+2.454
the
Token the
Feature activation+0.074
entire
Token entire
Feature activation+0.000
endeavor
Token endeavor
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
side
Token side
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
something
Token something
Feature activation+0.297
absent
Token absent
Feature activation+2.248
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
-
Token -
Feature activation+0.000
a
Token a
Feature activation+0.023
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+3.181
very
Token very
Feature activation+2.186
pronounced
Token pronounced
Feature activation+0.389
ethos
Token ethos
Feature activation+0.371
of
Token of
Feature activation+0.740
ant
Token ant
Feature activation+0.000
inational
Tokeninational
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
dream
Token dream
Feature activation+0.234
like
Tokenlike
Feature activation+0.000
quality
Token quality
Feature activation+0.934
to
Token to
Feature activation+2.135
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
ride
Token ride
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
in
Token in
Feature activation+0.029
the
Token the
Feature activation+0.000
middle
Token middle
Feature activation+0.000
names
Token names
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+2.440
how
Token how
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.770 - 2.124
CONTAINS 0.009%

There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
two
Token two
Feature activation+0.000
universal
Token universal
Feature activation+0.000
languages
Token languages
Feature activation+0.468
in
Token in
Feature activation+2.089
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
:
Token:
Feature activation+0.000
mathematics
Token mathematics
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.055
are
Token are
Feature activation+0.000
so
Token so
Feature activation+0.448
many
Token many
Feature activation+1.040
toys
Token toys
Feature activation+1.251
involved
Token involved
Feature activation+2.019
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
fun
Token fun
Feature activation+0.000
for
Token for
Feature activation+0.111
s
Tokens
Feature activation+0.000
little
Token little
Feature activation+0.000
any
Token any
Feature activation+0.000
economic
Token economic
Feature activation+0.000
doctor
Token doctor
Feature activation+0.540
can
Token can
Feature activation+1.833
do
Token do
Feature activation+0.650
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
our
Token our
Feature activation+0.000
$
Token $
Feature activation+0.000
are
Token are
Feature activation+0.000
some
Token some
Feature activation+0.000
great
Token great
Feature activation+0.000
ways
Token ways
Feature activation+0.297
you
Token you
Feature activation+0.747
can
Token can
Feature activation+1.955
help
Token help
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
How
TokenHow
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.214
more
Token more
Feature activation+0.162
to
Token to
Feature activation+2.074
share
Token share
Feature activation+0.320
amongst
Token amongst
Feature activation+0.486
the
Token the
Feature activation+0.000
parties
Token parties
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.416 - 1.770
CONTAINS 0.016%

that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
so
Token so
Feature activation+0.019
little
Token little
Feature activation+0.674
to
Token to
Feature activation+1.593
say
Token say
Feature activation+0.950
."[
Token."[
Feature activation+0.000
15
Token15
Feature activation+0.000
][
Token][
Feature activation+0.000
17
Token17
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
all
Token all
Feature activation+0.570
ure
Tokenure
Feature activation+0.026
to
Token to
Feature activation+1.591
finding
Token finding
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
treasure
Token treasure
Feature activation+0.000
chest
Token chest
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.095
velocity
Token velocity
Feature activation+0.185
involved
Token involved
Feature activation+1.501
with
Token with
Feature activation+0.000
anything
Token anything
Feature activation+0.055
that
Token that
Feature activation+0.362
goes
Token goes
Feature activation+0.000
into
Token into
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+1.448
it
Token it
Feature activation+0.601
than
Token than
Feature activation+0.958
sleeping
Token sleeping
Feature activation+0.346
and
Token and
Feature activation+0.241
drinking
Token drinking
Feature activation+0.382
bound
Token bound
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.625
a
Token a
Feature activation+1.808
few
Token few
Feature activation+2.020
accidents
Token accidents
Feature activation+1.488
.
Token.
Feature activation+0.000
Laun
Token Laun
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
this
Token this
Feature activation+0.000
summer
Token summer
Feature activation+0.000

INTERVAL 1.062 - 1.416
CONTAINS 0.028%

would
Token would
Feature activation+0.000
've
Token've
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.133
celebr
Token celebr
Feature activation+0.559
atory
Tokenatory
Feature activation+1.297
riot
Token riot
Feature activation+0.855
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
riot
Token riot
Feature activation+0.000
really
Token really
Feature activation+0.411
good
Token good
Feature activation+1.899
ho
Token ho
Feature activation+0.000
ppy
Tokenppy
Feature activation+0.352
beers
Token beers
Feature activation+1.483
at
Token at
Feature activation+1.201
Bore
Token Bore
Feature activation+0.000
fts
Tokenfts
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
two
Token two
Feature activation+0.000
punch
Token punch
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
a
Token a
Feature activation+1.065
market
Token market
Feature activation+0.054
for
Token for
Feature activation+1.133
him
Token him
Feature activation+0.003
.
Token.
Feature activation+0.000
Rum
Token Rum
Feature activation+0.000
if
Token if
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
real
Token real
Feature activation+0.653
catastrophe
Token catastrophe
Feature activation+1.116
?
Token?
Feature activation+0.550
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
think
Token think
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.572
amount
Token amount
Feature activation+1.164
of
Token of
Feature activation+0.579
time
Token time
Feature activation+1.781
to
Token to
Feature activation+2.432
start
Token start
Feature activation+0.000
tread
Token tread
Feature activation+0.000

INTERVAL 0.708 - 1.062
CONTAINS 0.048%

of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.010
many
Token many
Feature activation+0.000
like
Token like
Feature activation+0.887
it
Token it
Feature activation+0.374
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Finally
TokenFinally
Feature activation+0.000
"
Token "
Feature activation+0.000
There
TokenThere
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
whole
Token whole
Feature activation+0.846
two
Token two
Feature activation+0.833
days
Token days
Feature activation+1.775
where
Token where
Feature activation+1.597
we
Token we
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
that
Token that
Feature activation+0.769
big
Token big
Feature activation+0.000
,
Token,
Feature activation+0.000
wide
Token wide
Feature activation+0.000
,
Token,
Feature activation+0.000
ugly
Token ugly
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
labeling
Token labeling
Feature activation+0.000
or
Token or
Feature activation+0.000
external
Token external
Feature activation+0.000
indication
Token indication
Feature activation+0.786
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
which
Token which
Feature activation+0.000
.
Token.
Feature activation+0.000
obvious
Token obvious
Feature activation+0.920
par
Token par
Feature activation+0.186
abolic
Tokenabolic
Feature activation+0.000
shaped
Token shaped
Feature activation+0.138
structure
Token structure
Feature activation+0.872
in
Token in
Feature activation+0.891
the
Token the
Feature activation+0.000
rear
Token rear
Feature activation+0.000
wall
Token wall
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.354 - 0.708
CONTAINS 0.092%

There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
96
Token 96
Feature activation+0.266
teaspoons
Token teaspoons
Feature activation+1.382
in
Token in
Feature activation+1.636
this
Token this
Feature activation+0.390
bottle
Token bottle
Feature activation+0.000
of
Token of
Feature activation+0.000
gelatin
Token gelatin
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
two
Token two
Feature activation+0.416
spam
Token spam
Feature activation+0.609
emails
Token emails
Feature activation+0.605
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
would
Token would
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
sub
Token sub
Feature activation+0.753
genre
Tokengenre
Feature activation+0.691
looking
Token looking
Feature activation+1.055
at
Token at
Feature activation+0.230
them
Token them
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
But
Token But
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
side
Token side
Feature activation+1.004
currency
Token currency
Feature activation+0.502
pact
Token pact
Feature activation+0.263
in
Token in
Feature activation+1.081
which
Token which
Feature activation+0.000
countries
Token countries
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
any
Token any
Feature activation+0.008
ling
Token ling
Feature activation+0.000
ua
Tokenua
Feature activation+0.000
fr
Token fr
Feature activation+0.000
anca
Tokenanca
Feature activation+0.000
could
Token could
Feature activation+0.428
develop
Token develop
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.545

INTERVAL 0.000 - 0.354
CONTAINS 99.800%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
erg
Tokenerg
Feature activation+0.000
d
Tokend
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
pleaded
Token pleaded
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Big
TokenBig
Feature activation+0.000
business
Token business
Feature activation+0.000
has
Token has
Feature activation+0.000
already
Token already
Feature activation+0.000
recognized
Token recognized
Feature activation+0.000
the
Token the
Feature activation+0.000
potential
Token potential
Feature activation+0.000
in
Token in
Feature activation+0.000
these
Token these
Feature activation+0.000
new
Token new
Feature activation+0.000
autistic
Token autistic
Feature activation+0.000
traits
Token traits
Feature activation+0.000
questionnaire
Token questionnaire
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Social
Token Social
Feature activation+0.000
Respons
Token Respons
Feature activation+0.000
iveness
Tokeniveness
Feature activation+0.000
Scale
Token Scale
Feature activation+0.000
).
Token).
Feature activation+0.000
We
Token We
Feature activation+0.000
text
Token text
Feature activation+0.000
systems
Token systems
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
defeat
Token defeat
Feature activation+0.000
automatic
Token automatic
Feature activation+0.000
sign
Token sign
Feature activation+0.000
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
are
Token are
Feature activation+0.000
known
Token known
Feature activation+0.000
just
Token just
Feature activation+0.000
know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
desp
Token desp
Feature activation+0.000
ises
Tokenises
Feature activation+0.000
Hell
Token Hell
Feature activation+0.000
and
Token and
Feature activation+0.000
everything
Token everything
Feature activation+0.000
involved
Token involved
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