H1.2 top features

Top feature 0 in H1.2: (feature 3399)

TOP ACTIVATIONS
MAX = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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 DFA by src position
MAX = 0.155

atre
Tokenatre
Feature activation-0.057
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
a
Token a
Feature activation-0.019
Top resid features:
former
Token former
Feature activation+0.039
Top resid features:
boss
Token boss
Feature activation-0.114
Top resid features:
of
Token of
Feature activation+0.155
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Defence
Token Defence
Feature activation+0.000
Top resid features:
Research
Token Research
Feature activation+0.000
Top resid features:
&
Token &
Feature activation+0.000
Top resid features:
Development
Token Development
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.086
Top resid features:
A
Token A
Feature activation-0.097
Top resid features:
atre
Tokenatre
Feature activation-0.065
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
former
Token former
Feature activation+0.124
Top resid features:
boss
Token boss
Feature activation-0.182
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Defence
Token Defence
Feature activation+0.000
Top resid features:
Research
Token Research
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.069
Top resid features:
K
TokenK
Feature activation-0.089
Top resid features:
.
Token.
Feature activation-0.079
Top resid features:
A
Token A
Feature activation-0.103
Top resid features:
atre
Tokenatre
Feature activation-0.054
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
boss
Token boss
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.071
Top resid features:
A
Token A
Feature activation-0.114
Top resid features:
atre
Tokenatre
Feature activation-0.067
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
former
Token former
Feature activation+0.099
Top resid features:
boss
Token boss
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:
Defence
Token Defence
Feature activation+0.000
Top resid features:
Research
Token Research
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.135
Top resid features:
rik
Tokenrik
Feature activation+0.084
Top resid features:
ar
Tokenar
Feature activation-0.007
Top resid features:
said
Token said
Feature activation-0.070
Top resid features:
Saturday
Token Saturday
Feature activation-0.063
Top resid features:
.
Token.
Feature activation-0.113
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.122
Top resid features:
rik
Tokenrik
Feature activation-0.002
Top resid features:
ar
Tokenar
Feature activation-0.058
Top resid features:
said
Token said
Feature activation-0.052
Top resid features:
Saturday
Token Saturday
Feature activation-0.112
Top resid features:
.
Token.
Feature activation-0.179
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.097
Top resid features:
rik
Tokenrik
Feature activation+0.095
Top resid features:
ar
Tokenar
Feature activation+0.014
Top resid features:
said
Token said
Feature activation-0.051
Top resid features:
Saturday
Token Saturday
Feature activation-0.037
Top resid features:
.
Token.
Feature activation-0.098
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.071
Top resid features:
rik
Tokenrik
Feature activation+0.064
Top resid features:
ar
Tokenar
Feature activation-0.005
Top resid features:
said
Token said
Feature activation-0.055
Top resid features:
Saturday
Token Saturday
Feature activation-0.087
Top resid features:
.
Token.
Feature activation-0.111
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.070
Top resid features:
rik
Tokenrik
Feature activation+0.064
Top resid features:
ar
Tokenar
Feature activation+0.025
Top resid features:
said
Token said
Feature activation-0.018
Top resid features:
Saturday
Token Saturday
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.054
Top resid features:
Ċ
TokenĊ
Feature activation-0.089
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.094
Top resid features:
rik
Tokenrik
Feature activation+0.034
Top resid features:
ar
Tokenar
Feature activation+0.008
Top resid features:
said
Token said
Feature activation-0.010
Top resid features:
Saturday
Token Saturday
Feature activation-0.022
Top resid features:
.
Token.
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.082
Top resid features:
The
TokenThe
Feature activation-0.050
Top resid features:
defence
Token defence
Feature activation-0.054
Top resid features:
ministry
Token ministry
Feature activation-0.134
Top resid features:
committee
Token committee
Feature activation-0.100
Top resid features:
headed
Token headed
Feature activation-0.112
Top resid features:
by
Token by
Feature activation+0.081
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.075
Top resid features:
rik
Tokenrik
Feature activation+0.116
Top resid features:
ar
Tokenar
Feature activation+0.005
Top resid features:
said
Token said
Feature activation-0.019
Top resid features:
Saturday
Token Saturday
Feature activation-0.032
Top resid features:
.
Token.
Feature activation-0.056
Top resid features:
Ċ
TokenĊ
Feature activation-0.115
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.140
Top resid features:
rik
Tokenrik
Feature activation+0.051
Top resid features:
ar
Tokenar
Feature activation+0.002
Top resid features:
said
Token said
Feature activation-0.010
Top resid features:
Saturday
Token Saturday
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.034
Top resid features:
Ċ
TokenĊ
Feature activation-0.072
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.134
Top resid features:
rik
Tokenrik
Feature activation+0.035
Top resid features:
ar
Tokenar
Feature activation+0.012
Top resid features:
said
Token said
Feature activation-0.010
Top resid features:
Saturday
Token Saturday
Feature activation-0.016
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation-0.070
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.113
Top resid features:
rik
Tokenrik
Feature activation+0.047
Top resid features:
ar
Tokenar
Feature activation+0.071
Top resid features:
said
Token said
Feature activation-0.013
Top resid features:
Saturday
Token Saturday
Feature activation-0.011
Top resid features:
.
Token.
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.060
Top resid features:
Ċ
TokenĊ
Feature activation-0.060
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.186
Top resid features:
rik
Tokenrik
Feature activation+0.034
Top resid features:
ar
Tokenar
Feature activation-0.001
Top resid features:
said
Token said
Feature activation-0.009
Top resid features:
Saturday
Token Saturday
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.048
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.027
Top resid features:
rik
Tokenrik
Feature activation+0.057
Top resid features:
ar
Tokenar
Feature activation-0.021
Top resid features:
said
Token said
Feature activation-0.019
Top resid features:
Saturday
Token Saturday
Feature activation-0.034
Top resid features:
.
Token.
Feature activation-0.074
Top resid features:
Ċ
TokenĊ
Feature activation-0.132
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.047
Top resid features:
rik
Tokenrik
Feature activation+0.089
Top resid features:
ar
Tokenar
Feature activation+0.048
Top resid features:
said
Token said
Feature activation-0.035
Top resid features:
Saturday
Token Saturday
Feature activation-0.042
Top resid features:
.
Token.
Feature activation-0.086
Top resid features:
Ċ
TokenĊ
Feature activation-0.149
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.079
Top resid features:
rik
Tokenrik
Feature activation+0.075
Top resid features:
ar
Tokenar
Feature activation+0.040
Top resid features:
said
Token said
Feature activation-0.063
Top resid features:
Saturday
Token Saturday
Feature activation-0.087
Top resid features:
.
Token.
Feature activation-0.137
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.010
Top resid features:
rik
Tokenrik
Feature activation+0.126
Top resid features:
ar
Tokenar
Feature activation+0.140
Top resid features:
said
Token said
Feature activation-0.054
Top resid features:
Saturday
Token Saturday
Feature activation-0.052
Top resid features:
.
Token.
Feature activation-0.078
Top resid features:
Ċ
TokenĊ
Feature activation-0.161
Top resid features:
Ċ
TokenĊ
Feature activation-0.153
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.09

Head 2: 0.18

Head 3: 0.05

Head 4: 0.14

Head 5: 0.04

Head 6: 0.09

Head 7: 0.07

Head 8: 0.04

Head 9: 0.03

Head 10: 0.17

Head 11: 0.06

Positive logits

inka0.92

duino0.92

sockets0.89

lasers0.88

receptors0.86

transmitter0.85

LEDs0.85

circuitry0.84

guessed0.84

orbs0.83

goggles0.83

joints0.81

transmissions0.81

wink0.80

objects0.80

gib0.80

objects0.79

teleportation0.79

Pixel0.78

itself0.78

Negative logits

secut-1.05

isode-1.00

wic-0.94

Fir-0.93

omy-0.93

ivo-0.93

ktop-0.89

oun-0.88

volunt-0.87

attrition-0.87

Mour-0.86

Celebr-0.86

ategory-0.85

ategor-0.85

Advent-0.85

iscopal-0.85

cludes-0.85

omic-0.84

herty-0.83

plet-0.83

INTERVAL 0.000 - 0.000
CONTAINS 100.000%

bunker
Token bunker
Feature activation+0.000
called
Token called
Feature activation+0.000
Iron
Token Iron
Feature activation+0.000
Mountain
Token Mountain
Feature activation+0.000
(
Token (
Feature activation+0.000
as
Tokenas
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
worldwide
Token worldwide
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
current
Token current
Feature activation+0.000
marriage
Token marriage
Feature activation+0.000
and
Token and
Feature activation+0.000
divorce
Token divorce
Feature activation+0.000
rate
Token rate
Feature activation+0.000
continues
Token continues
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
about
Token about
Feature activation+0.000
sense
Token sense
Feature activation+0.000
that
Token that
Feature activation+0.000
something
Token something
Feature activation+0.000
would
Token would
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.000
go
Token go
Feature activation+0.000
missing
Token missing
Feature activation+0.000
that
Token that
Feature activation+0.000
only
Token only
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
sourcing
Token sourcing
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.000
accurate
Token accurate
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
of
Token of
Feature activation+0.000
planned
Token planned
Feature activation+0.000
design
Token design
Feature activation+0.000
changes
Token changes
Feature activation+0.000
coming
Token coming
Feature activation+0.000
to
Token to
Feature activation+0.000
StarCraft
Token StarCraft
Feature activation+0.000
II
Token II
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
the
Token the
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 H1.2: (feature 12560)

TOP ACTIVATIONS
MAX = 1.326

workers
Tokenworkers
Feature activation+0.000
wore
Token wore
Feature activation+0.000
dirty
Token dirty
Feature activation+0.000
looks
Token looks
Feature activation+0.019
,
Token,
Feature activation+0.202
saying
Token saying
Feature activation+1.326
without
Token without
Feature activation+0.665
saying
Token saying
Feature activation+0.817
"
Token "
Feature activation+0.262
you
Tokenyou
Feature activation+0.000
broke
Token broke
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.104
old
Token old
Feature activation+1.083
men
Token men
Feature activation+0.941
,
Token,
Feature activation+0.392
heads
Token heads
Feature activation+1.310
held
Token held
Feature activation+0.961
high
Token high
Feature activation+0.765
,
Token,
Feature activation+0.288
marching
Token marching
Feature activation+0.791
past
Token past
Feature activation+0.730
more
Token more
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+0.000
,
Token,
Feature activation+0.224
however
Token however
Feature activation+1.303
.
Token.
Feature activation+0.101
âĢ
Token âĢ
Feature activation+0.131
ľ
Tokenľ
Feature activation+0.000
Feature
TokenFeature
Feature activation+0.000
production
Token production
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
political
Token political
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.170
frankly
Token frankly
Feature activation+1.227
,
Token,
Feature activation+0.248
âĢ
TokenâĢ
Feature activation+0.644
Ŀ
TokenĿ
Feature activation+0.309
Trump
Token Trump
Feature activation+0.379
told
Token told
Feature activation+0.240
bother
Token bother
Feature activation+0.000
some
Tokensome
Feature activation+0.000
health
Token health
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.107
including
Token including
Feature activation+1.226
eye
Token eye
Feature activation+0.530
issues
Token issues
Feature activation+0.673
.
Token.
Feature activation+0.037
Cham
Token Cham
Feature activation+0.045
om
Tokenom
Feature activation+0.299
by
Token by
Feature activation+0.000
Connecticut
Token Connecticut
Feature activation+0.000
,
Token,
Feature activation+0.075
Iowa
Token Iowa
Feature activation+0.951
,
Token,
Feature activation+0.343
Massachusetts
Token Massachusetts
Feature activation+1.225
,
Token,
Feature activation+0.403
New
Token New
Feature activation+1.039
Hampshire
Token Hampshire
Feature activation+1.029
and
Token and
Feature activation+0.336
Vermont
Token Vermont
Feature activation+0.242
own
Token own
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
election
Tokenelection
Feature activation+0.000
,
Token,
Feature activation+0.136
which
Token which
Feature activation+1.190
she
Token she
Feature activation+0.495
denies
Token denies
Feature activation+0.428
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
It
TokenIt
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
trail
Token trail
Feature activation+0.000
surface
Token surface
Feature activation+0.000
,
Token,
Feature activation+0.248
which
Token which
Feature activation+1.178
can
Token can
Feature activation+0.599
be
Token be
Feature activation+0.453
repaired
Token repaired
Feature activation+0.285
in
Token in
Feature activation+0.368
time
Token time
Feature activation+0.318
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
cocktails
Token cocktails
Feature activation+0.000
,
Token,
Feature activation+0.106
including
Token including
Feature activation+1.162
Nicholas
Token Nicholas
Feature activation+0.707
âĢ
TokenâĢ
Feature activation+0.283
Ļ
TokenĻ
Feature activation+0.102
favorite
Token favorite
Feature activation+0.430
,
Token,
Feature activation+0.039
taking
Token taking
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
habit
Token habit
Feature activation+0.000
,
Token,
Feature activation+0.131
including
Token including
Feature activation+1.152
bills
Token bills
Feature activation+0.528
requiring
Token requiring
Feature activation+0.560
all
Token all
Feature activation+0.165
California
Token California
Feature activation+0.177
schools
Token schools
Feature activation+0.054
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
storm
Token storm
Feature activation+0.000
relief
Token relief
Feature activation+0.000
,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+1.151
his
Token his
Feature activation+0.523
response
Token response
Feature activation+0.496
to
Token to
Feature activation+0.280
Hurricane
Token Hurricane
Feature activation+0.278
Maria
Token Maria
Feature activation+0.242
common
Token common
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
players
Token players
Feature activation+0.000
,
Token,
Feature activation+0.246
which
Token which
Feature activation+1.147
was
Token was
Feature activation+0.533
one
Token one
Feature activation+0.435
of
Token of
Feature activation+0.186
the
Token the
Feature activation+0.173
hardest
Token hardest
Feature activation+0.200
have
Token have
Feature activation+0.000
altered
Token altered
Feature activation+0.000
the
Token the
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
,
Token,
Feature activation+0.117
including
Token including
Feature activation+1.143
a
Token a
Feature activation+0.493
defensive
Token defensive
Feature activation+0.416
three
Token three
Feature activation+0.223
-
Token-
Feature activation+0.029
second
Tokensecond
Feature activation+0.000
turning
Token turning
Feature activation+0.012
over
Token over
Feature activation+0.002
the
Token the
Feature activation+0.000
finished
Token finished
Feature activation+0.000
,
Token,
Feature activation+0.174
high
Token high
Feature activation+1.142
-
Token-
Feature activation+0.848
quality
Tokenquality
Feature activation+0.650
files
Token files
Feature activation+0.699
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.026
litigation
Token litigation
Feature activation+0.000
over
Token over
Feature activation+0.000
other
Token other
Feature activation+0.000
trails
Token trails
Feature activation+0.000
,
Token,
Feature activation+0.196
including
Token including
Feature activation+1.139
compensation
Token compensation
Feature activation+0.524
claims
Token claims
Feature activation+0.629
filed
Token filed
Feature activation+0.650
by
Token by
Feature activation+0.264
landowners
Token landowners
Feature activation+0.258
at
Token at
Feature activation+0.988
least
Token least
Feature activation+0.946
not
Token not
Feature activation+0.859
immediately
Token immediately
Feature activation+0.624
,
Token,
Feature activation+0.437
since
Token since
Feature activation+1.138
it
Token it
Feature activation+0.608
remains
Token remains
Feature activation+0.453
closed
Token closed
Feature activation+0.462
to
Token to
Feature activation+0.188
women
Token women
Feature activation+0.227
world
Token world
Feature activation+0.000
is
Token is
Feature activation+0.000
banning
Token banning
Feature activation+0.038
GMOs
Token GMOs
Feature activation+0.000
,
Token,
Feature activation+0.367
which
Token which
Feature activation+1.136
shows
Token shows
Feature activation+0.611
public
Token public
Feature activation+0.616
outcry
Token outcry
Feature activation+0.529
is
Token is
Feature activation+0.316
growing
Token growing
Feature activation+0.241
open
Token open
Feature activation+0.069
the
Token the
Feature activation+0.000
discarded
Token discarded
Feature activation+0.000
cups
Token cups
Feature activation+0.053
,
Token,
Feature activation+0.420
turn
Token turn
Feature activation+1.135
the
Token the
Feature activation+0.748
leftover
Token leftover
Feature activation+0.711
coffee
Token coffee
Feature activation+0.546
grounds
Token grounds
Feature activation+0.439
into
Token into
Feature activation+0.319
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.204
each
Token each
Feature activation+0.964
,
Token,
Feature activation+0.467
on
Token on
Feature activation+1.130
the
Token the
Feature activation+0.708
Te
Token Te
Feature activation+0.629
ide
Tokenide
Feature activation+0.437
volcano
Token volcano
Feature activation+0.398
.
Token.
Feature activation+0.000
systems
Token systems
Feature activation+0.020
of
Token of
Feature activation+0.000
societal
Token societal
Feature activation+0.000
organization
Token organization
Feature activation+0.013
,
Token,
Feature activation+0.197
particularly
Token particularly
Feature activation+1.128
state
Token state
Feature activation+0.829
-
Token-
Feature activation+0.473
backed
Tokenbacked
Feature activation+0.253
money
Token money
Feature activation+0.414
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 1.993

-
Token-
Feature activation+0.020
Top resid features:
workers
Tokenworkers
Feature activation+0.049
Top resid features:
wore
Token wore
Feature activation+0.079
Top resid features:
dirty
Token dirty
Feature activation+0.034
Top resid features:
looks
Token looks
Feature activation+0.074
Top resid features:
,
Token,
Feature activation+1.793
Top resid features:
saying
Token saying
Feature activation+0.086
Top resid features:
without
Token without
Feature activation+0.000
Top resid features:
saying
Token saying
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
you
Tokenyou
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.032
Top resid features:
time
Token time
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.676
Top resid features:
old
Token old
Feature activation+0.103
Top resid features:
men
Token men
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+1.175
Top resid features:
heads
Token heads
Feature activation+0.069
Top resid features:
held
Token held
Feature activation+0.000
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
marching
Token marching
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.016
Top resid features:
more
Token more
Feature activation+0.034
Top resid features:
difficult
Token difficult
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.041
Top resid features:
determine
Token determine
Feature activation+0.063
Top resid features:
,
Token,
Feature activation+1.850
Top resid features:
however
Token however
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Feature
TokenFeature
Feature activation+0.000
Top resid features:
involved
Token involved
Feature activation+0.027
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
political
Token political
Feature activation+0.032
Top resid features:
campaign
Token campaign
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+1.792
Top resid features:
frankly
Token frankly
Feature activation+0.111
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.021
Top resid features:
bother
Token bother
Feature activation+0.014
Top resid features:
some
Tokensome
Feature activation+0.012
Top resid features:
health
Token health
Feature activation+0.026
Top resid features:
issues
Token issues
Feature activation+0.076
Top resid features:
,
Token,
Feature activation+1.993
Top resid features:
including
Token including
Feature activation+0.070
Top resid features:
eye
Token eye
Feature activation+0.000
Top resid features:
issues
Token issues
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Cham
Token Cham
Feature activation+0.000
Top resid features:
granted
Token granted
Feature activation+0.044
Top resid features:
by
Token by
Feature activation+0.039
Top resid features:
Connecticut
Token Connecticut
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.784
Top resid features:
Iowa
Token Iowa
Feature activation+0.063
Top resid features:
,
Token,
Feature activation+1.004
Top resid features:
Massachusetts
Token Massachusetts
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
Hampshire
Token Hampshire
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.022
Top resid features:
own
Token own
Feature activation+0.042
Top resid features:
re
Token re
Feature activation+0.026
Top resid features:
-
Token-
Feature activation+0.052
Top resid features:
election
Tokenelection
Feature activation+0.091
Top resid features:
,
Token,
Feature activation+1.754
Top resid features:
which
Token which
Feature activation+0.082
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
denies
Token denies
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
damage
Token damage
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
trail
Token trail
Feature activation+0.050
Top resid features:
surface
Token surface
Feature activation+0.073
Top resid features:
,
Token,
Feature activation+1.772
Top resid features:
which
Token which
Feature activation+0.067
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
repaired
Token repaired
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
learn
Token learn
Feature activation+0.023
Top resid features:
how
Token how
Feature activation+0.079
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
make
Token make
Feature activation+0.080
Top resid features:
cocktails
Token cocktails
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+1.756
Top resid features:
including
Token including
Feature activation+0.093
Top resid features:
Nicholas
Token Nicholas
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
favorite
Token favorite
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.015
Top resid features:
taking
Token taking
Feature activation+0.012
Top resid features:
up
Token up
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
habit
Token habit
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+1.776
Top resid features:
including
Token including
Feature activation+0.025
Top resid features:
bills
Token bills
Feature activation+0.000
Top resid features:
requiring
Token requiring
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
California
Token California
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.020
Top resid features:
comes
Token comes
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
storm
Token storm
Feature activation-0.009
Top resid features:
relief
Token relief
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+1.918
Top resid features:
saying
Token saying
Feature activation+0.118
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
response
Token response
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Hurricane
Token Hurricane
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
common
Token common
Feature activation+0.014
Top resid features:
group
Token group
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+0.098
Top resid features:
players
Token players
Feature activation+0.071
Top resid features:
,
Token,
Feature activation+1.628
Top resid features:
which
Token which
Feature activation+0.071
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
one
Token one
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:
may
Token may
Feature activation+0.012
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
altered
Token altered
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
outcome
Token outcome
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+1.792
Top resid features:
including
Token including
Feature activation-0.011
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
defensive
Token defensive
Feature activation+0.000
Top resid features:
three
Token three
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.038
Top resid features:
turning
Token turning
Feature activation+0.036
Top resid features:
over
Token over
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.082
Top resid features:
finished
Token finished
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+1.531
Top resid features:
high
Token high
Feature activation+0.093
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
quality
Tokenquality
Feature activation+0.000
Top resid features:
files
Token files
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
expensive
Token expensive
Feature activation+0.022
Top resid features:
litigation
Token litigation
Feature activation+0.014
Top resid features:
over
Token over
Feature activation+0.029
Top resid features:
other
Token other
Feature activation+0.028
Top resid features:
trails
Token trails
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+1.712
Top resid features:
including
Token including
Feature activation+0.041
Top resid features:
compensation
Token compensation
Feature activation+0.000
Top resid features:
claims
Token claims
Feature activation+0.000
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.381
Top resid features:
at
Token at
Feature activation+0.022
Top resid features:
least
Token least
Feature activation+0.106
Top resid features:
not
Token not
Feature activation+0.064
Top resid features:
immediately
Token immediately
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+1.228
Top resid features:
since
Token since
Feature activation+0.048
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
remains
Token remains
Feature activation+0.000
Top resid features:
closed
Token closed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
world
Token world
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.086
Top resid features:
banning
Token banning
Feature activation+0.069
Top resid features:
GMOs
Token GMOs
Feature activation+0.031
Top resid features:
,
Token,
Feature activation+1.580
Top resid features:
which
Token which
Feature activation+0.038
Top resid features:
shows
Token shows
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
outcry
Token outcry
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
break
Token break
Feature activation+0.032
Top resid features:
open
Token open
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
discarded
Token discarded
Feature activation+0.073
Top resid features:
cups
Token cups
Feature activation+0.105
Top resid features:
,
Token,
Feature activation+1.504
Top resid features:
turn
Token turn
Feature activation+0.061
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
leftover
Token leftover
Feature activation+0.000
Top resid features:
coffee
Token coffee
Feature activation+0.000
Top resid features:
grounds
Token grounds
Feature activation+0.000
Top resid features:
hours
Token hours
Feature activation+0.042
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
work
Token work
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+0.720
Top resid features:
each
Token each
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.988
Top resid features:
on
Token on
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Te
Token Te
Feature activation+0.000
Top resid features:
ide
Tokenide
Feature activation+0.000
Top resid features:
volcano
Token volcano
Feature activation+0.000
Top resid features:
foundational
Token foundational
Feature activation-0.000
Top resid features:
systems
Token systems
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.030
Top resid features:
societal
Token societal
Feature activation+0.019
Top resid features:
organization
Token organization
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+1.773
Top resid features:
particularly
Token particularly
Feature activation+0.027
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
backed
Tokenbacked
Feature activation+0.000
Top resid features:
money
Token money
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.19

Head 2: 0.18

Head 3: 0.07

Head 4: 0.11

Head 5: 0.02

Head 6: 0.02

Head 7: 0.04

Head 8: 0.05

Head 9: 0.04

Head 10: 0.17

Head 11: 0.05

Positive logits

netflix0.96

preferably0.90

0.84

apologies0.84

nonetheless0.84

reasoned0.82

notwithstanding0.81

Machina0.81

aside0.76

0.76

etheless0.75

conservancy0.75

orio0.74

unsus0.73

acquies0.72

majorities0.71

esides0.71

hypoc0.71

whe0.70

unsurprisingly0.70

Negative logits

Defin-0.84

ilege-0.78

awar-0.77

uminati-0.77

20439-0.77

tains-0.76

abor-0.73

ven-0.73

emade-0.72

toggle-0.71

iatus-0.71

latable-0.70

���-0.70

-0.70

enger-0.70

adies-0.70

umbn-0.70

igree-0.69

ammy-0.69

ocado-0.68

INTERVAL 1.193 - 1.326
CONTAINS 0.001%

workers
Tokenworkers
Feature activation+0.000
wore
Token wore
Feature activation+0.000
dirty
Token dirty
Feature activation+0.000
looks
Token looks
Feature activation+0.019
,
Token,
Feature activation+0.202
saying
Token saying
Feature activation+1.326
without
Token without
Feature activation+0.665
saying
Token saying
Feature activation+0.817
"
Token "
Feature activation+0.262
you
Tokenyou
Feature activation+0.000
broke
Token broke
Feature activation+0.000
more
Token more
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+0.000
,
Token,
Feature activation+0.224
however
Token however
Feature activation+1.303
.
Token.
Feature activation+0.101
âĢ
Token âĢ
Feature activation+0.131
ľ
Tokenľ
Feature activation+0.000
Feature
TokenFeature
Feature activation+0.000
production
Token production
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
political
Token political
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.170
frankly
Token frankly
Feature activation+1.227
,
Token,
Feature activation+0.248
âĢ
TokenâĢ
Feature activation+0.644
Ŀ
TokenĿ
Feature activation+0.309
Trump
Token Trump
Feature activation+0.379
told
Token told
Feature activation+0.240
bother
Token bother
Feature activation+0.000
some
Tokensome
Feature activation+0.000
health
Token health
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.107
including
Token including
Feature activation+1.226
eye
Token eye
Feature activation+0.530
issues
Token issues
Feature activation+0.673
.
Token.
Feature activation+0.037
Cham
Token Cham
Feature activation+0.045
om
Tokenom
Feature activation+0.299
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.104
old
Token old
Feature activation+1.083
men
Token men
Feature activation+0.941
,
Token,
Feature activation+0.392
heads
Token heads
Feature activation+1.310
held
Token held
Feature activation+0.961
high
Token high
Feature activation+0.765
,
Token,
Feature activation+0.288
marching
Token marching
Feature activation+0.791
past
Token past
Feature activation+0.730

INTERVAL 1.060 - 1.193
CONTAINS 0.006%

,
Token,
Feature activation+0.000
fruit
Token fruit
Feature activation+0.522
drinks
Token drinks
Feature activation+0.709
,
Token,
Feature activation+0.333
energy
Token energy
Feature activation+0.877
drinks
Token drinks
Feature activation+1.081
,
Token,
Feature activation+0.507
sweet
Token sweet
Feature activation+0.803
ened
Tokenened
Feature activation+0.932
Token
Feature activation+0.463
iced
Tokeniced
Feature activation+0.151
entry
Token entry
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
,
Token,
Feature activation+0.133
including
Token including
Feature activation+1.084
reviews
Token reviews
Feature activation+0.370
of
Token of
Feature activation+0.128
their
Token their
Feature activation+0.186
social
Token social
Feature activation+0.099
media
Token media
Feature activation+0.048
do
Token do
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
,
Token,
Feature activation+0.147
which
Token which
Feature activation+1.118
they
Token they
Feature activation+0.664
do
Token do
Feature activation+0.536
in
Token in
Feature activation+0.447
non
Token non
Feature activation+0.342
-
Token-
Feature activation+0.223
taking
Token taking
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
habit
Token habit
Feature activation+0.000
,
Token,
Feature activation+0.131
including
Token including
Feature activation+1.152
bills
Token bills
Feature activation+0.528
requiring
Token requiring
Feature activation+0.560
all
Token all
Feature activation+0.165
California
Token California
Feature activation+0.177
schools
Token schools
Feature activation+0.054
have
Token have
Feature activation+0.000
altered
Token altered
Feature activation+0.000
the
Token the
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
,
Token,
Feature activation+0.117
including
Token including
Feature activation+1.143
a
Token a
Feature activation+0.493
defensive
Token defensive
Feature activation+0.416
three
Token three
Feature activation+0.223
-
Token-
Feature activation+0.029
second
Tokensecond
Feature activation+0.000

INTERVAL 0.928 - 1.060
CONTAINS 0.028%

tackle
Token tackle
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
from
Token from
Feature activation+0.000
transport
Token transport
Feature activation+0.000
,
Token,
Feature activation+0.090
industry
Token industry
Feature activation+0.992
and
Token and
Feature activation+0.291
homes
Token homes
Feature activation+0.222
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
office
Token office
Feature activation+0.000
network
Token network
Feature activation+0.000
,
Token,
Feature activation+0.327
where
Token where
Feature activation+0.995
all
Token all
Feature activation+0.522
network
Token network
Feature activation+0.486
users
Token users
Feature activation+0.332
can
Token can
Feature activation+0.305
reach
Token reach
Feature activation+0.137
of
Token of
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
sensory
Token sensory
Feature activation+0.000
cues
Token cues
Feature activation+0.000
,
Token,
Feature activation+0.021
including
Token including
Feature activation+0.936
smell
Token smell
Feature activation+0.202
(
Token (
Feature activation+0.081
is
Tokenis
Feature activation+0.085
the
Token the
Feature activation+0.026
female
Token female
Feature activation+0.085
play
Token play
Feature activation+0.098
highly
Token highly
Feature activation+0.129
animated
Token animated
Feature activation+0.022
roles
Token roles
Feature activation+0.049
,
Token,
Feature activation+0.187
emphasizing
Token emphasizing
Feature activation+0.985
a
Token a
Feature activation+0.580
lack
Token lack
Feature activation+0.396
of
Token of
Feature activation+0.197
power
Token power
Feature activation+0.266
;
Token;
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
thermal
Token thermal
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.931
Google
Token Google
Feature activation+0.280
did
Token did
Feature activation+0.410
not
Token not
Feature activation+0.242
comment
Token comment
Feature activation+0.269
on
Token on
Feature activation+0.143

INTERVAL 0.795 - 0.928
CONTAINS 0.068%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
season
Token season
Feature activation+0.116
,
Token,
Feature activation+0.245
Howard
Token Howard
Feature activation+0.897
could
Token could
Feature activation+0.754
find
Token find
Feature activation+0.462
himself
Token himself
Feature activation+0.281
playing
Token playing
Feature activation+0.292
an
Token an
Feature activation+0.077
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
released
Token released
Feature activation+0.092
,
Token,
Feature activation+0.249
they
Token they
Feature activation+0.833
will
Token will
Feature activation+0.737
jump
Token jump
Feature activation+0.524
up
Token up
Feature activation+0.465
by
Token by
Feature activation+0.382
over
Token over
Feature activation+0.224
urban
Token urban
Feature activation+0.000
hip
Token hip
Feature activation+0.000
hang
Token hang
Feature activation+0.000
outs
Tokenouts
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.818
is
Token is
Feature activation+0.171
somehow
Token somehow
Feature activation+0.077
familiar
Token familiar
Feature activation+0.250
âĢ¦
TokenâĢ¦
Feature activation+0.110
Ċ
TokenĊ
Feature activation+0.000
atop
Token atop
Feature activation+0.000
a
Token a
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
roof
Token roof
Feature activation+0.000
,
Token,
Feature activation+0.000
trying
Token trying
Feature activation+0.834
desperately
Token desperately
Feature activation+0.657
to
Token to
Feature activation+0.320
come
Token come
Feature activation+0.391
up
Token up
Feature activation+0.247
with
Token with
Feature activation+0.205
released
Token released
Feature activation+0.000
while
Token while
Feature activation+0.000
navigating
Token navigating
Feature activation+0.000
fame
Token fame
Feature activation+0.000
,
Token,
Feature activation+0.124
romance
Token romance
Feature activation+0.912
,
Token,
Feature activation+0.427
and
Token and
Feature activation+0.688
a
Token a
Feature activation+0.500
music
Token music
Feature activation+0.419
industry
Token industry
Feature activation+0.579

INTERVAL 0.663 - 0.795
CONTAINS 0.145%

have
Token have
Feature activation+0.000
staged
Token staged
Feature activation+0.000
street
Token street
Feature activation+0.000
protests
Token protests
Feature activation+0.000
,
Token,
Feature activation+0.205
repeatedly
Token repeatedly
Feature activation+0.735
thrown
Token thrown
Feature activation+0.463
tear
Token tear
Feature activation+0.060
gas
Token gas
Feature activation+0.076
in
Token in
Feature activation+0.004
parliament
Token parliament
Feature activation+0.000
House
Token House
Feature activation+0.082
roof
Token roof
Feature activation+0.000
in
Token in
Feature activation+0.000
1979
Token 1979
Feature activation+0.000
,
Token,
Feature activation+0.119
solar
Token solar
Feature activation+0.782
remains
Token remains
Feature activation+0.349
barely
Token barely
Feature activation+0.000
a
Token a
Feature activation+0.000
bl
Token bl
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
in
Token in
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
,
Token,
Feature activation+0.032
D
Token D
Feature activation+0.756
.
Token.
Feature activation+0.342
C
TokenC
Feature activation+0.308
.,
Token.,
Feature activation+0.597
U
Token U
Feature activation+0.669
.
Token.
Feature activation+0.488
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
launch
Token launch
Feature activation+0.000
site
Token site
Feature activation+0.000
,
Token,
Feature activation+0.000
well
Token well
Feature activation+0.671
short
Token short
Feature activation+0.417
of
Token of
Feature activation+0.220
its
Token its
Feature activation+0.165
maximum
Token maximum
Feature activation+0.143
range
Token range
Feature activation+0.193
,
Token,
Feature activation+0.000
reckless
Token reckless
Feature activation+0.949
at
Token at
Feature activation+0.791
worst
Token worst
Feature activation+0.848
,
Token,
Feature activation+0.306
âĢ
TokenâĢ
Feature activation+0.683
Ŀ
TokenĿ
Feature activation+0.535
he
Token he
Feature activation+0.561
said
Token said
Feature activation+0.611
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.530 - 0.663
CONTAINS 0.243%

-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
student
Token student
Feature activation+0.000
,
Token,
Feature activation+0.000
Montreal
Token Montreal
Feature activation+0.534
police
Token police
Feature activation+0.237
told
Token told
Feature activation+0.108
the
Token the
Feature activation+0.000
BBC
Token BBC
Feature activation+0.000
.
Token.
Feature activation+0.000
rich
Token rich
Feature activation+0.000
in
Token in
Feature activation+0.000
amino
Token amino
Feature activation+0.000
acids
Token acids
Feature activation+0.000
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.548
pro
Token pro
Feature activation+0.202
line
Tokenline
Feature activation+0.399
which
Token which
Feature activation+0.377
promotes
Token promotes
Feature activation+0.155
skin
Token skin
Feature activation+0.084
learning
Token learning
Feature activation+0.167
disabilities
Token disabilities
Feature activation+0.111
,
Token,
Feature activation+0.324
only
Token only
Feature activation+1.053
24
Token 24
Feature activation+0.579
%
Token%
Feature activation+0.540
say
Token say
Feature activation+0.314
they
Token they
Feature activation+0.064
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
disabled
Token disabled
Feature activation+0.000
tablets
Token tablets
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
,
Token,
Feature activation+0.000
opening
Token opening
Feature activation+1.011
up
Token up
Feature activation+0.793
an
Token an
Feature activation+0.590
array
Token array
Feature activation+0.463
of
Token of
Feature activation+0.374
interactive
Token interactive
Feature activation+0.419
possibilities
Token possibilities
Feature activation+0.477
.
Token.
Feature activation+0.000
just
Token just
Feature activation+0.000
made
Token made
Feature activation+0.000
my
Token my
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.616
âĢ
TokenâĢ
Feature activation+0.252
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.398 - 0.530
CONTAINS 0.375%

the
Token the
Feature activation+0.000
TPP
Token TPP
Feature activation+0.000
,
Token,
Feature activation+0.129
opposed
Token opposed
Feature activation+0.834
by
Token by
Feature activation+0.647
many
Token many
Feature activation+0.487
voters
Token voters
Feature activation+0.336
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.639
absorbed
Token absorbed
Feature activation+0.550
and
Token and
Feature activation+0.243
assimil
Token assimil
Feature activation+0.183
ated
Tokenated
Feature activation+0.479
the
Token the
Feature activation+0.134
suggestions
Token suggestions
Feature activation+0.171
he
Token he
Feature activation+0.066
got
Token got
Feature activation+0.013
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
costume
Token costume
Feature activation+0.000
,
Token,
Feature activation+0.000
battling
Token battling
Feature activation+0.745
and
Token and
Feature activation+0.281
losing
Token losing
Feature activation+0.525
to
Token to
Feature activation+0.190
the
Token the
Feature activation+0.101
K
Token K
Feature activation+0.100
rav
Tokenrav
Feature activation+0.000
in
Tokenin
Feature activation+0.000
2015
Token 2015
Feature activation+0.740
).
Token).
Feature activation+0.000
And
Token And
Feature activation+0.000
,
Token,
Feature activation+0.053
just
Token just
Feature activation+0.646
as
Token as
Feature activation+0.417
was
Token was
Feature activation+0.127
the
Token the
Feature activation+0.049
case
Token case
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
our
Token our
Feature activation+0.000
officers
Token officers
Feature activation+0.000
,
Token,
Feature activation+0.000
honoring
Token honoring
Feature activation+0.837
our
Token our
Feature activation+0.648
officers
Token officers
Feature activation+0.458
,
Token,
Feature activation+0.193
making
Token making
Feature activation+0.988
sure
Token sure
Feature activation+0.634
that
Token that
Feature activation+0.365
they
Token they
Feature activation+0.191

INTERVAL 0.265 - 0.398
CONTAINS 0.557%

,
Token,
Feature activation+0.164
a
Token a
Feature activation+0.581
plus
Token plus
Feature activation+0.570
-
Token-
Feature activation+0.363
9
Token9
Feature activation+0.256
rating
Token rating
Feature activation+0.295
,
Token,
Feature activation+0.056
eight
Token eight
Feature activation+0.608
penalty
Token penalty
Feature activation+0.395
minutes
Token minutes
Feature activation+0.284
,
Token,
Feature activation+0.000
bitter
Token bitter
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.457
major
Token major
Feature activation+0.277
Democratic
Token Democratic
Feature activation+0.100
figures
Token figures
Feature activation+0.080
accusing
Token accusing
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
,
Token,
Feature activation+0.000
Texas
Token Texas
Feature activation+0.610
,
Token,
Feature activation+0.089
and
Token and
Feature activation+0.338
Kansas
Token Kansas
Feature activation+0.362
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
1860
Token 1860
Feature activation+0.000
he
Token he
Feature activation+0.000
achieved
Token achieved
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
we
Token we
Feature activation+0.000
athered
Tokenathered
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.279
lived
Token lived
Feature activation+0.371
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
B
Token B
Feature activation+0.000
ILL
TokenILL
Feature activation+0.000
S
TokenS
Feature activation+0.000
,
Token,
Feature activation+0.000
MAD
Token MAD
Feature activation+0.372
ISON
TokenISON
Feature activation+0.337
AV
Token AV
Feature activation+0.256
EN
TokenEN
Feature activation+0.252
UE
TokenUE
Feature activation+0.043
:
Token:
Feature activation+0.000

INTERVAL 0.133 - 0.265
CONTAINS 0.846%

-
Token-
Feature activation+0.000
memory
Tokenmemory
Feature activation+0.055
component
Token component
Feature activation+0.091
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.098
as
Tokenas
Feature activation+0.158
pl
Tokenpl
Feature activation+0.000
oit
Tokenoit
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
res
Tokenres
Feature activation+0.115
iding
Tokeniding
Feature activation+0.168
Russian
Token Russian
Feature activation+0.000
cities
Token cities
Feature activation+0.000
you
Token you
Feature activation+0.000
travel
Token travel
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.143
less
Token less
Feature activation+0.096
English
Token English
Feature activation+0.000
speakers
Token speakers
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
said
Token said
Feature activation+0.435
athletes
Token athletes
Feature activation+0.376
should
Token should
Feature activation+0.203
not
Token not
Feature activation+0.172
protest
Token protest
Feature activation+0.114
against
Token against
Feature activation+0.145
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
on
Token on
Feature activation+0.009
the
Token the
Feature activation+0.000
medal
Token medal
Feature activation+0.091
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000
office
Token office
Feature activation+0.000
employees
Token employees
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.192
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
.
Token.
Feature activation+0.000
we
Token we
Feature activation+0.478
know
Token know
Feature activation+0.290
many
Token many
Feature activation+0.372
of
Token of
Feature activation+0.101
our
Token our
Feature activation+0.287
bored
Token bored
Feature activation+0.158
pand
Token pand
Feature activation+0.000
as
Tokenas
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
consider
Token consider
Feature activation+0.000

INTERVAL 0.000 - 0.133
CONTAINS 97.732%

s
Tokens
Feature activation+0.000
no
Token no
Feature activation+0.000
bitterness
Token bitterness
Feature activation+0.000
towards
Token towards
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
team
Token team
Feature activation+0.000
guys
Token guys
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
wom
Token wom
Feature activation+0.000
bs
Tokenbs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
removed
Token removed
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
living
Token living
Feature activation+0.000
donors
Token donors
Feature activation+0.000
,
Token,
Feature activation+0.000
Chosen
Token Chosen
Feature activation+0.000
One
Token One
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
alone
Token alone
Feature activation+0.000
in
Token in
Feature activation+0.000
falling
Token falling
Feature activation+0.000
behind
Token behind
Feature activation+0.000
Kobe
Token Kobe
Feature activation+0.000
in
Token in
Feature activation+0.000
Jordan
Token Jordan
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
by
Token by
Feature activation+0.000
Dil
Token Dil
Feature activation+0.000
jit
Tokenjit
Feature activation+0.000
Dos
Token Dos
Feature activation+0.000
an
Tokenan
Feature activation+0.000
j
Tokenj
Feature activation+0.000
h
Tokenh
Feature activation+0.000
,
Token,
Feature activation+0.000
Nik
TokenNik
Feature activation+0.225
ku
Tokenku
Feature activation+0.142
ľ
Tokenľ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
you
Token you
Feature activation+0.000
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
eaten
Token eaten
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
while
Token while
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

Defence
Token Defence
Feature activation+0.001
Research
Token Research
Feature activation+0.094
&
Token &
Feature activation+0.041
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.410
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.001
Research
Token Research
Feature activation+0.094
&
Token &
Feature activation+0.041
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.410
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.486
former
Token former
Feature activation+0.316
boss
Token boss
Feature activation+0.220
of
Token of
Feature activation+0.059
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.001
Research
Token Research
Feature activation+0.094
&
Token &
Feature activation+0.041
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
of
Token of
Feature activation+0.059
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.001
Research
Token Research
Feature activation+0.094
&
Token &
Feature activation+0.041
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.410
is
Token is
Feature activation+0.000
to
Token to
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+0.486
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
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+0.486
former
Token former
Feature activation+0.316
boss
Token boss
Feature activation+0.220
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.486
former
Token former
Feature activation+0.316
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.486
former
Token former
Feature activation+0.316
boss
Token boss
Feature activation+0.220
of
Token of
Feature activation+0.059
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.486
former
Token former
Feature activation+0.316
boss
Token boss
Feature activation+0.220
of
Token of
Feature activation+0.059
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 H1.2: (feature 10497)

TOP ACTIVATIONS
MAX = 1.712

ride
Token ride
Feature activation+0.000
-
Token-
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ailing
Tokenailing
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+1.712
Additionally
Token Additionally
Feature activation+0.000
,
Token,
Feature activation+0.196
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
switched
Token switched
Feature activation+0.000
was
Token was
Feature activation+0.000
finally
Token finally
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
.
Token.
Feature activation+1.694
Ċ
TokenĊ
Feature activation+0.186
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
your
Token your
Feature activation+0.000
over
Token over
Feature activation+0.000
payments
Token payments
Feature activation+0.000
were
Token were
Feature activation+0.000
for
Token for
Feature activation+0.000
.
Token.
Feature activation+1.683
Ċ
TokenĊ
Feature activation+0.232
Ċ
TokenĊ
Feature activation+0.000
NOTE
TokenNOTE
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
floor
Token floor
Feature activation+0.000
.
Token.
Feature activation+1.667
These
Token These
Feature activation+0.070
are
Token are
Feature activation+0.000
committee
Token committee
Feature activation+0.000
people
Tokenpeople
Feature activation+0.000
.
Token.
Feature activation+0.743
a
Token a
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
Primary
Token Primary
Feature activation+0.000
fortress
Token fortress
Feature activation+0.000
.
Token.
Feature activation+1.635
Ċ
TokenĊ
Feature activation+0.188
Ċ
TokenĊ
Feature activation+0.000
U
TokenU
Feature activation+0.000
.
Token.
Feature activation+0.160
S
TokenS
Feature activation+0.000
every
Token every
Feature activation+0.000
room
Token room
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
house
Token house
Feature activation+0.000
.
Token.
Feature activation+1.626
Ċ
TokenĊ
Feature activation+0.336
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.033
new
Token new
Feature activation+0.109
Echo
Token Echo
Feature activation+0.000
prism
Token prism
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
subjective
Token subjective
Feature activation+0.000
experience
Token experience
Feature activation+0.000
.
Token.
Feature activation+1.622
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
of
Token of
Feature activation+0.000
some
Token some
Feature activation+0.000
dream
Token dream
Feature activation+0.000
career
Token career
Feature activation+0.000
resurrection
Token resurrection
Feature activation+0.000
.
Token.
Feature activation+1.617
It
Token It
Feature activation+0.013
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
independent
Token independent
Feature activation+0.000
games
Token games
Feature activation+0.000
studio
Token studio
Feature activation+0.000
.
Token.
Feature activation+1.613
Ċ
TokenĊ
Feature activation+0.126
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
Kickstarter
Token Kickstarter
Feature activation+0.000
project
Token project
Feature activation+0.000
remote
Token remote
Feature activation+0.000
north
Token north
Feature activation+0.000
-
Token-
Feature activation+0.000
western
Tokenwestern
Feature activation+0.000
region
Token region
Feature activation+0.000
.
Token.
Feature activation+1.601
Un
Token Un
Feature activation+0.000
named
Tokennamed
Feature activation+0.000
Pakistani
Token Pakistani
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
sources
Token sources
Feature activation+0.000
fine
Token fine
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
office
Token office
Feature activation+0.000
.
Token.
Feature activation+1.589
Ċ
TokenĊ
Feature activation+0.405
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
27
Token 27
Feature activation+0.000
-
Token-
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.000
in
Token in
Feature activation+0.000
history
Token history
Feature activation+0.000
.
Token.
Feature activation+1.588
And
Token And
Feature activation+0.000
why
Token why
Feature activation+0.000
would
Token would
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
regard
Token regard
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.018
own
Token own
Feature activation+0.000
safety
Token safety
Feature activation+0.000
.
Token.
Feature activation+1.586
Ċ
TokenĊ
Feature activation+0.039
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
of
Token of
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
in
Token in
Feature activation+0.000
Ecuador
Token Ecuador
Feature activation+0.000
.
Token.
Feature activation+1.581
In
Token In
Feature activation+0.266
the
Token the
Feature activation+0.000
late
Token late
Feature activation+0.000
1990
Token 1990
Feature activation+0.000
s
Tokens
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
September
Token September
Feature activation+0.000
.
Token.
Feature activation+1.575
Samsung
Token Samsung
Feature activation+0.000
's
Token's
Feature activation+0.116
lawyers
Token lawyers
Feature activation+0.000
initially
Token initially
Feature activation+0.000
challenged
Token challenged
Feature activation+0.000
there
Token there
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
testing
Token testing
Feature activation+0.000
period
Token period
Feature activation+0.000
.
Token.
Feature activation+1.575
Ċ
TokenĊ
Feature activation+0.287
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
staff
Token staff
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
tokens
Token tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
.
Token.
Feature activation+1.573
To
Token To
Feature activation+0.151
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.000
UN
Token UN
Feature activation+0.000
partnered
Token partnered
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
is
Token is
Feature activation+0.059
still
Token still
Feature activation+0.110
in
Token in
Feature activation+0.000
progress
Token progress
Feature activation+0.263
.
Token.
Feature activation+1.570
The
Token The
Feature activation+0.219
illegitimate
Token illegitimate
Feature activation+0.000
and
Token and
Feature activation+0.009
unjust
Token unjust
Feature activation+0.000
actions
Token actions
Feature activation+0.000
normal
Token normal
Feature activation+0.000
operation
Token operation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
mechanism
Token mechanism
Feature activation+0.000
.
Token.
Feature activation+1.570
Needless
Token Needless
Feature activation+0.000
to
Token to
Feature activation+0.052
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.039
removing
Token removing
Feature activation+0.000
reflect
Token reflect
Feature activation+0.000
well
Token well
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.083
sport
Token sport
Feature activation+0.000
.
Token.
Feature activation+1.570
The
Token The
Feature activation+0.199
typically
Token typically
Feature activation+0.000
quirky
Token quirky
Feature activation+0.000
Lotus
Token Lotus
Feature activation+0.000
social
Token social
Feature activation+0.000

Top DFA by src position
MAX = 0.142

the
Token the
Feature activation+0.031
Top resid features:
presence
Token presence
Feature activation+0.038
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
a
Token a
Feature activation-0.020
Top resid features:
major
Token major
Feature activation+0.006
Top resid features:
ride
Token ride
Feature activation+0.090
Top resid features:
-
Token-
Feature activation-0.047
Top resid features:
h
Tokenh
Feature activation-0.030
Top resid features:
ailing
Tokenailing
Feature activation+0.027
Top resid features:
service
Token service
Feature activation-0.036
Top resid features:
.
Token.
Feature activation-0.080
Top resid features:
sample
Token sample
Feature activation-0.000
Top resid features:
would
Token would
Feature activation+0.011
Top resid features:
be
Token be
Feature activation+0.032
Top resid features:
used
Token used
Feature activation+0.024
Top resid features:
for
Token for
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.142
Top resid features:
had
Token had
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.068
Top resid features:
refuse
Token refuse
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.057
Top resid features:
hand
Token hand
Feature activation+0.049
Top resid features:
survey
Token survey
Feature activation+0.040
Top resid features:
request
Token request
Feature activation+0.031
Top resid features:
or
Token or
Feature activation+0.063
Top resid features:
be
Token be
Feature activation+0.040
Top resid features:
directed
Token directed
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.078
Top resid features:
a
Token a
Feature activation+0.030
Top resid features:
site
Token site
Feature activation+0.047
Top resid features:
that
Token that
Feature activation+0.056
Top resid features:
will
Token will
Feature activation+0.041
Top resid features:
ask
Token ask
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
lobby
Token lobby
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
tower
Token tower
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.102
Top resid features:
cast
Token cast
Feature activation+0.026
Top resid features:
their
Token their
Feature activation+0.046
Top resid features:
ballots
Token ballots
Feature activation+0.053
Top resid features:
for
Token for
Feature activation+0.041
Top resid features:
individuals
Token individuals
Feature activation+0.036
Top resid features:
looked
Token looked
Feature activation-0.020
Top resid features:
like
Token like
Feature activation-0.008
Top resid features:
a
Token a
Feature activation+0.044
Top resid features:
rev
Token rev
Feature activation+0.001
Top resid features:
up
Token up
Feature activation-0.013
Top resid features:
of
Token of
Feature activation+0.064
Top resid features:
those
Token those
Feature activation+0.062
Top resid features:
erect
Token erect
Feature activation+0.013
Top resid features:
or
Tokenor
Feature activation+0.045
Top resid features:
set
Token set
Feature activation+0.039
Top resid features:
pieces
Token pieces
Feature activation+0.038
Top resid features:
consumers
Token consumers
Feature activation-0.024
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
embed
Token embed
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
Echo
Token Echo
Feature activation+0.068
Top resid features:
and
Token and
Feature activation+0.073
Top resid features:
its
Token its
Feature activation+0.051
Top resid features:
Alexa
Token Alexa
Feature activation+0.044
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
powered
Tokenpowered
Feature activation+0.027
Top resid features:
brain
Token brain
Feature activation+0.054
Top resid features:
we
Token we
Feature activation-0.016
Top resid features:
do
Token do
Feature activation-0.013
Top resid features:
hear
Token hear
Feature activation-0.007
Top resid features:
his
Token his
Feature activation+0.022
Top resid features:
thoughts
Token thoughts
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.081
Top resid features:
see
Token see
Feature activation+0.026
Top resid features:
and
Token and
Feature activation+0.065
Top resid features:
consider
Token consider
Feature activation+0.005
Top resid features:
what
Token what
Feature activation+0.012
Top resid features:
happens
Token happens
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.072
Top resid features:
give
Token give
Feature activation+0.020
Top resid features:
up
Token up
Feature activation+0.012
Top resid features:
travers
Token travers
Feature activation+0.070
Top resid features:
ing
Tokening
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
world
Token world
Feature activation+0.051
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
search
Token search
Feature activation+0.007
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
some
Token some
Feature activation-0.025
Top resid features:
are
Token are
Feature activation+0.064
Top resid features:
risking
Token risking
Feature activation+0.004
Top resid features:
their
Token their
Feature activation+0.025
Top resid features:
financial
Token financial
Feature activation+0.040
Top resid features:
security
Token security
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.091
Top resid features:
personal
Token personal
Feature activation+0.021
Top resid features:
relationships
Token relationships
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
achieve
Token achieve
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.052
Top resid features:
on
Token on
Feature activation+0.031
Top resid features:
Saturday
Token Saturday
Feature activation+0.051
Top resid features:
by
Token by
Feature activation+0.054
Top resid features:
a
Token a
Feature activation+0.034
Top resid features:
presumed
Token presumed
Feature activation+0.022
Top resid features:
US
Token US
Feature activation+0.127
Top resid features:
attack
Token attack
Feature activation+0.038
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
country
Token country
Feature activation+0.086
Top resid features:
's
Token's
Feature activation-0.007
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
fine
Token fine
Feature activation+0.072
Top resid features:
from
Token from
Feature activation-0.032
Top resid features:
the
Token the
Feature activation-0.035
Top resid features:
league
Token league
Feature activation-0.058
Top resid features:
office
Token office
Feature activation+0.098
Top resid features:
.
Token.
Feature activation-0.018
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:
27
Token 27
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.044
Top resid features:
one
Token one
Feature activation+0.005
Top resid features:
big
Token big
Feature activation-0.002
Top resid features:
lie
Token lie
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
and
Token and
Feature activation+0.092
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
should
Token should
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
truth
Token truth
Feature activation+0.018
Top resid features:
emerge
Token emerge
Feature activation+0.003
Top resid features:
truck
Token truck
Feature activation-0.029
Top resid features:
which
Token which
Feature activation-0.004
Top resid features:
had
Token had
Feature activation-0.013
Top resid features:
broken
Token broken
Feature activation+0.007
Top resid features:
down
Token down
Feature activation-0.016
Top resid features:
and
Token and
Feature activation+0.097
Top resid features:
it
Token it
Feature activation+0.038
Top resid features:
was
Token was
Feature activation+0.044
Top resid features:
critical
Token critical
Feature activation+0.020
Top resid features:
that
Token that
Feature activation+0.046
Top resid features:
they
Token they
Feature activation+0.045
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
discussion
Token discussion
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
pros
Token pros
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.086
Top resid features:
cons
Token cons
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
using
Token using
Feature activation+0.027
Top resid features:
dollars
Token dollars
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
version
Token version
Feature activation+0.019
Top resid features:
at
Token at
Feature activation-0.002
Top resid features:
least
Token least
Feature activation-0.009
Top resid features:
until
Token until
Feature activation-0.017
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
hearing
Token hearing
Feature activation+0.096
Top resid features:
can
Token can
Feature activation+0.017
Top resid features:
take
Token take
Feature activation+0.019
Top resid features:
place
Token place
Feature activation+0.061
Top resid features:
at
Token at
Feature activation-0.072
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
be
Token be
Feature activation+0.017
Top resid features:
placed
Token placed
Feature activation+0.005
Top resid features:
on
Token on
Feature activation+0.034
Top resid features:
top
Token top
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.075
Top resid features:
bank
Token bank
Feature activation+0.021
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
lock
Token lock
Feature activation+0.053
Top resid features:
ers
Tokeners
Feature activation+0.035
Top resid features:
with
Token with
Feature activation+0.066
Top resid features:
or
Token or
Feature activation+0.033
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
smartphone
Token smartphone
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
there
Token there
Feature activation+0.020
Top resid features:
was
Token was
Feature activation+0.073
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
need
Token need
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
devise
Token devise
Feature activation+0.042
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
he
Token he
Feature activation+0.034
Top resid features:
committed
Token committed
Feature activation-0.004
Top resid features:
while
Token while
Feature activation+0.046
Top resid features:
serving
Token serving
Feature activation+0.026
Top resid features:
as
Token as
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
Colombian
Token Colombian
Feature activation+0.035
Top resid features:
president
Token president
Feature activation+0.042
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
investigation
Token investigation
Feature activation+0.029
Top resid features:
any
Token any
Feature activation+0.005
Top resid features:
fresh
Token fresh
Feature activation-0.000
Top resid features:
C
Token C
Feature activation+0.019
Top resid features:
NC
TokenNC
Feature activation+0.041
Top resid features:
part
Token part
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
they
Token they
Feature activation+0.033
Top resid features:
must
Token must
Feature activation-0.016
Top resid features:
be
Token be
Feature activation+0.031
Top resid features:
smoot
Token smoot
Feature activation+0.012
Top resid features:
hed
Tokenhed
Feature activation+0.037
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.279
Top resid features:
touching
Token touching
Feature activation+0.004
Top resid features:
distance
Token distance
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
beating
Token beating
Feature activation-0.013
Top resid features:
Mercedes
Token Mercedes
Feature activation+0.089
Top resid features:
and
Token and
Feature activation+0.075
Top resid features:
Ferrari
Token Ferrari
Feature activation+0.026
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.041
Top resid features:
has
Token has
Feature activation+0.013
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.09

Head 2: 0.17

Head 3: 0.07

Head 4: 0.12

Head 5: 0.05

Head 6: 0.06

Head 7: 0.04

Head 8: 0.06

Head 9: 0.05

Head 10: 0.16

Head 11: 0.09

Positive logits

ğ0.89

sbm0.77

��0.75

Provided0.74

FANT0.72

Realms0.72

Immun0.71

Brill0.71

afety0.70

largeDownload0.68

Pigs0.66

diplom0.66

agre0.65

chool0.65

0.65

Carnage0.64

disapp0.64

Satisf0.64

0.64

Pros0.64

Negative logits

ogue-0.76

enum-0.75

ozo-0.74

abo-0.70

idden-0.70

UD-0.68

izon-0.67

eca-0.65

ggles-0.63

oker-0.61

ipes-0.60

UD-0.60

ines-0.60

pton-0.59

iterator-0.59

iest-0.59

unci-0.58

alloc-0.58

ithub-0.58

ipe-0.58

INTERVAL 1.541 - 1.712
CONTAINS 0.003%

more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.000
in
Token in
Feature activation+0.000
history
Token history
Feature activation+0.000
.
Token.
Feature activation+1.588
And
Token And
Feature activation+0.000
why
Token why
Feature activation+0.000
would
Token would
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
the
Token the
Feature activation+0.000
tokens
Token tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
.
Token.
Feature activation+1.573
To
Token To
Feature activation+0.151
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.000
UN
Token UN
Feature activation+0.000
partnered
Token partnered
Feature activation+0.000
a
Token a
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
Primary
Token Primary
Feature activation+0.000
fortress
Token fortress
Feature activation+0.000
.
Token.
Feature activation+1.635
Ċ
TokenĊ
Feature activation+0.188
Ċ
TokenĊ
Feature activation+0.000
U
TokenU
Feature activation+0.000
.
Token.
Feature activation+0.160
S
TokenS
Feature activation+0.000
your
Token your
Feature activation+0.000
over
Token over
Feature activation+0.000
payments
Token payments
Feature activation+0.000
were
Token were
Feature activation+0.000
for
Token for
Feature activation+0.000
.
Token.
Feature activation+1.683
Ċ
TokenĊ
Feature activation+0.232
Ċ
TokenĊ
Feature activation+0.000
NOTE
TokenNOTE
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
delayed
Token delayed
Feature activation+0.000
the
Token the
Feature activation+0.000
healing
Token healing
Feature activation+0.000
process
Token process
Feature activation+0.000
.
Token.
Feature activation+1.559
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Of
TokenOf
Feature activation+0.000

INTERVAL 1.370 - 1.541
CONTAINS 0.017%

such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
accounting
Token accounting
Feature activation+0.000
and
Token and
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
.
Token.
Feature activation+1.375
Ċ
TokenĊ
Feature activation+0.108
Ċ
TokenĊ
Feature activation+0.000
Mult
TokenMult
Feature activation+0.000
inational
Tokeninational
Feature activation+0.000
s
Tokens
Feature activation+0.000
can
Token can
Feature activation+0.000
actually
Token actually
Feature activation+0.000
dissolve
Token dissolve
Feature activation+0.000
the
Token the
Feature activation+0.000
town
Token town
Feature activation+0.000
.
Token.
Feature activation+1.455
Ċ
TokenĊ
Feature activation+0.138
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
show
Token show
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
unorthodox
Token unorthodox
Feature activation+0.000
arrangement
Token arrangement
Feature activation+0.000
himself
Token himself
Feature activation+0.000
.
Token.
Feature activation+1.464
Ċ
TokenĊ
Feature activation+0.045
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
account
Token account
Feature activation+0.000
since
Token since
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+1.383
Ċ
TokenĊ
Feature activation+0.050
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
ray
Tokenray
Feature activation+0.000
ing
Tokening
Feature activation+0.000
eliminated
Token eliminated
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
schedule
Token schedule
Feature activation+0.000
.
Token.
Feature activation+1.391
Ċ
TokenĊ
Feature activation+0.137
Ċ
TokenĊ
Feature activation+0.000
Fin
TokenFin
Feature activation+0.000
an
Tokenan
Feature activation+0.000
cially
Tokencially
Feature activation+0.000

INTERVAL 1.198 - 1.370
CONTAINS 0.046%

role
Token role
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
community
Token community
Feature activation+0.000
advocate
Token advocate
Feature activation+0.000
.
Token.
Feature activation+1.255
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.064
You
TokenYou
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Northwest
Token Northwest
Feature activation+0.000
Side
Token Side
Feature activation+0.000
.
Token.
Feature activation+1.302
He
Token He
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
other
Token other
Feature activation+0.000
people
Token people
Feature activation+0.000
-
Token-
Feature activation+0.000
west
Tokenwest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+1.204
AL
Token AL
Feature activation+0.000
LE
TokenLE
Feature activation+0.000
G
TokenG
Feature activation+0.000
ED
TokenED
Feature activation+0.000
LI
Token LI
Feature activation+0.000
ller
Tokenller
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
side
Token side
Feature activation+0.000
.
Token.
Feature activation+1.238
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
fle
Tokenfle
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
ed
Tokened
Feature activation+0.000
editor
Token editor
Feature activation+0.000
ials
Tokenials
Feature activation+0.000
.
Token.
Feature activation+1.317
The
Token The
Feature activation+0.000
Record
Token Record
Feature activation+0.000
got
Token got
Feature activation+0.000
caught
Token caught
Feature activation+0.000
red
Token red
Feature activation+0.000

INTERVAL 1.027 - 1.198
CONTAINS 0.069%

by
Token by
Feature activation+0.000
US
Token US
Feature activation+0.000
President
Token President
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+1.088
Ċ
TokenĊ
Feature activation+0.089
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
With
TokenWith
Feature activation+0.000
inputs
Token inputs
Feature activation+0.000
annual
Token annual
Feature activation+0.000
Tokyo
Token Tokyo
Feature activation+0.000
Toy
Token Toy
Feature activation+0.000
Show
Token Show
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
.
Token.
Feature activation+1.078
Tom
Token Tom
Feature activation+0.000
y
Tokeny
Feature activation+0.000
claims
Token claims
Feature activation+0.000
the
Token the
Feature activation+0.000
gadget
Token gadget
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
of
Token of
Feature activation+0.000
using
Token using
Feature activation+0.000
block
Token block
Feature activation+0.000
chains
Tokenchains
Feature activation+0.000
.
Token.
Feature activation+1.084
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
why
Token why
Feature activation+0.000
dominated
Token dominated
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
Tour
Token Tour
Feature activation+0.000
ing
Tokening
Feature activation+0.000
recently
Token recently
Feature activation+0.000
.
Token.
Feature activation+1.133
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
fair
Token fair
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
met
Token met
Feature activation+0.000
for
Token for
Feature activation+0.000
talks
Token talks
Feature activation+0.000
in
Token in
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
.
Token.
Feature activation+1.193
Ċ
TokenĊ
Feature activation+0.021
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000

INTERVAL 0.856 - 1.027
CONTAINS 0.088%

literally
Token literally
Feature activation+0.000
roll
Token roll
Feature activation+0.000
toward
Token toward
Feature activation+0.000
the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
.
Token.
Feature activation+0.881
Only
Token Only
Feature activation+0.000
their
Token their
Feature activation+0.000
sideways
Token sideways
Feature activation+0.000
motion
Token motion
Feature activation+0.000
or
Token or
Feature activation+0.000
salaries
Token salaries
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
regular
Token regular
Feature activation+0.000
basis
Token basis
Feature activation+0.000
.
Token.
Feature activation+0.929
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.582
2
Token2
Feature activation+0.000
innings
Token innings
Feature activation+0.000
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.951
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Agg
Token Agg
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
into
Token into
Feature activation+0.000
your
Token your
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
fusion
Token fusion
Feature activation+0.000
map
Token map
Feature activation+0.000
.
Token.
Feature activation+0.901
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
for
Token for
Feature activation+0.000
Fusion
Token Fusion
Feature activation+0.000
tips
Token tips
Feature activation+0.000
on
Token on
Feature activation+0.000
navigating
Token navigating
Feature activation+0.000
Content
Token Content
Feature activation+0.000
ID
TokenID
Feature activation+0.000
.
Token.
Feature activation+0.936
Ċ
TokenĊ
Feature activation+0.061
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
ef
Tokenef
Feature activation+0.000

INTERVAL 0.685 - 0.856
CONTAINS 0.094%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Season
Token Season
Feature activation+0.000
4
Token 4
Feature activation+0.000
finale
Token finale
Feature activation+0.000
.
Token.
Feature activation+0.854
Ċ
TokenĊ
Feature activation+0.218
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
is
Token is
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
the
Token the
Feature activation+0.000
worst
Token worst
Feature activation+0.000
option
Token option
Feature activation+0.000
.
Token.
Feature activation+0.697
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
myself
Token myself
Feature activation+0.000
up
Token up
Feature activation+0.000
white
Token white
Feature activation+0.000
noise
Token noise
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
thing
Token thing
Feature activation+0.000
.
Token.
Feature activation+0.761
To
Token To
Feature activation+0.000
be
Token be
Feature activation+0.000
honest
Token honest
Feature activation+0.000
,
Token,
Feature activation+0.027
I
Token I
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
V
Token V
Feature activation+0.000
FW
TokenFW
Feature activation+0.000
post
Token post
Feature activation+0.000
.
Token.
Feature activation+0.734
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
names
Token names
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
bikes
Token bikes
Feature activation+0.000
in
Token in
Feature activation+0.000
cities
Token cities
Feature activation+0.000
.
Token.
Feature activation+0.725
Some
Token Some
Feature activation+0.000
reports
Token reports
Feature activation+0.000
put
Token put
Feature activation+0.000
one
Token one
Feature activation+0.000
woman
Token woman
Feature activation+0.000

INTERVAL 0.514 - 0.685
CONTAINS 0.096%

port
Tokenport
Feature activation+0.000
USB
Token USB
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.448
0
Token0
Feature activation+0.000
.
Token.
Feature activation+0.673
While
Token While
Feature activation+0.000
reading
Token reading
Feature activation+0.000
the
Token the
Feature activation+0.186
repository
Token repository
Feature activation+0.000
reach
Token reach
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
thing
Token thing
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.526
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
in
Token in
Feature activation+0.000
town
Token town
Feature activation+0.000
where
Token where
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
any
Token any
Feature activation+0.000
specific
Token specific
Feature activation+0.000
person
Token person
Feature activation+0.000
.
Token.
Feature activation+0.670
I
Token I
Feature activation+0.000
simply
Token simply
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
Nation
Token Nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
objections
Token objections
Feature activation+0.000
.
Token.
Feature activation+0.546
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Di
TokenDi
Feature activation+0.000
Nat
Token Nat
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
,
Token,
Feature activation+0.092
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.566
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Eric
TokenEric
Feature activation+0.000
Schmidt
Token Schmidt
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.342 - 0.514
CONTAINS 0.104%

in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
release
Token release
Feature activation+0.000
.
Token.
Feature activation+0.434
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"'
Token"'
Feature activation+0.000
Year
TokenYear
Feature activation+0.000
Zero
Token Zero
Feature activation+0.000
food
Token food
Feature activation+0.000
prices
Token prices
Feature activation+0.000
by
Token by
Feature activation+0.000
various
Token various
Feature activation+0.000
foreigners
Token foreigners
Feature activation+0.000
.
Token.
Feature activation+0.364
By
Token By
Feature activation+0.000
News
Token News
Feature activation+0.000
.
Token.
Feature activation+0.000
co
Tokenco
Feature activation+0.000
.
Token.
Feature activation+0.000
17
Token 17
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
full
Token full
Feature activation+0.000
professors
Token professors
Feature activation+0.000
.
Token.
Feature activation+0.395
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
copper
Token copper
Feature activation+0.000
/
Token /
Feature activation+0.000
20
Token 20
Feature activation+0.000
%
Token%
Feature activation+0.000
tin
Token tin
Feature activation+0.000
).
Token).
Feature activation+0.355
This
Token This
Feature activation+0.000
is
Token is
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
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
act
Token act
Feature activation+0.000
inconsist
Token inconsist
Feature activation+0.000
ently
Tokenently
Feature activation+0.000
.
Token.
Feature activation+0.388
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ide
TokenIde
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.171 - 0.342
CONTAINS 0.146%

jet
Token jet
Feature activation+0.000
to
Token to
Feature activation+0.000
pick
Token pick
Feature activation+0.000
him
Token him
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.245
Marcus
Token Marcus
Feature activation+0.000
takes
Token takes
Feature activation+0.000
Billy
Token Billy
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
downloading
Token downloading
Feature activation+0.000
apps
Token apps
Feature activation+0.000
from
Token from
Feature activation+0.000
reputable
Token reputable
Feature activation+0.000
sites
Token sites
Feature activation+0.000
.
Token.
Feature activation+0.239
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bit
TokenBit
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ender
Tokenender
Feature activation+0.000
from
Token from
Feature activation+0.000
Libya
Token Libya
Feature activation+0.000
is
Token is
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
troubling
Token troubling
Feature activation+0.000
.
Token.
Feature activation+0.297
Libya
Token Libya
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
arsenal
Token arsenal
Feature activation+0.000
slavery
Token slavery
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
elite
Token elite
Feature activation+0.000
.
Token.
Feature activation+0.266
In
Token In
Feature activation+0.000
light
Token light
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Edward
Token Edward
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
structure
Token structure
Feature activation+0.000
.
Token.
Feature activation+0.175
A
Token A
Feature activation+0.000
Lisp
Token Lisp
Feature activation+0.000
program
Token program
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000

INTERVAL 0.000 - 0.171
CONTAINS 99.338%

Ļ
TokenĻ
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
military
Token military
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
an
Token an
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
,
Token,
Feature activation+0.000
H
Token H
Feature activation+0.000
yn
Tokenyn
Feature activation+0.000
ix
Tokenix
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
pleased
Token pleased
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
na
Tokenna
Feature activation+0.000
F
Token F
Feature activation+0.000
á
Tokená
Feature activation+0.000
il
Tokenil
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
headed
Token headed
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
taking
Token taking
Feature activation+0.000
shape
Token shape
Feature activation+0.000
,
Token,
Feature activation+0.000
Cort
Token Cort
Feature activation+0.000
esi
Tokenesi
Feature activation+0.000
highlights
Token highlights
Feature activation+0.000
various
Token various
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
forces
Token forces
Feature activation+0.000
are
Token are
Feature activation+0.000
capable
Token capable
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+0.000
military
Token military
Feature activation+0.000
operations
Token operations
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
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 H1.2: (feature 24575)

TOP ACTIVATIONS
MAX = 0.959

community
Token community
Feature activation+0.313
members
Token members
Feature activation+0.437
,
Token,
Feature activation+0.547
to
Token to
Feature activation+0.562
decide
Token decide
Feature activation+0.776
what
Token what
Feature activation+0.959
the
Token the
Feature activation+0.775
school
Token school
Feature activation+0.700
district
Token district
Feature activation+0.634
needs
Token needs
Feature activation+0.463
to
Token to
Feature activation+0.419
,
Token,
Feature activation+0.384
but
Token but
Feature activation+0.546
rather
Token rather
Feature activation+0.704
than
Token than
Feature activation+0.726
fret
Token fret
Feature activation+0.689
ting
Tokenting
Feature activation+0.956
about
Token about
Feature activation+0.823
inequality
Token inequality
Feature activation+0.525
,
Token,
Feature activation+0.603
perhaps
Token perhaps
Feature activation+0.679
we
Token we
Feature activation+0.643
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.090
sounds
Token sounds
Feature activation+0.291
,
Token,
Feature activation+0.437
while
Token while
Feature activation+0.740
others
Token others
Feature activation+0.920
are
Token are
Feature activation+0.835
artificial
Token artificial
Feature activation+0.651
can
Token can
Feature activation+0.683
als
Tokenals
Feature activation+0.735
.
Token.
Feature activation+0.294
for
Token for
Feature activation+0.261
an
Token an
Feature activation+0.561
as
Token as
Feature activation+0.583
yet
Token yet
Feature activation+0.652
unknown
Token unknown
Feature activation+0.764
reason
Token reason
Feature activation+0.862
,
Token,
Feature activation+0.712
allegedly
Token allegedly
Feature activation+0.595
fired
Token fired
Feature activation+0.652
his
Token his
Feature activation+0.715
gun
Token gun
Feature activation+0.658
and
Token and
Feature activation+0.428
much
Token much
Feature activation+0.521
more
Token more
Feature activation+0.639
,
Token,
Feature activation+0.650
try
Token try
Feature activation+0.684
an
Token an
Feature activation+0.854
All
Token All
Feature activation+0.661
Access
Token Access
Feature activation+0.554
Digital
Token Digital
Feature activation+0.358
subscription
Token subscription
Feature activation+0.317
:
Token:
Feature activation+0.005
and
Token and
Feature activation+0.159
biking
Token biking
Feature activation+0.152
,
Token,
Feature activation+0.285
and
Token and
Feature activation+0.488
roller
Token roller
Feature activation+0.501
bl
Tokenbl
Feature activation+0.848
ading
Tokenading
Feature activation+0.700
.
Token.
Feature activation+0.254
Each
Token Each
Feature activation+0.432
time
Token time
Feature activation+0.413
Met
Token Met
Feature activation+0.342
financial
Token financial
Feature activation+0.389
documents
Token documents
Feature activation+0.461
,
Token,
Feature activation+0.453
as
Token as
Feature activation+0.566
well
Token well
Feature activation+0.793
as
Token as
Feature activation+0.845
in
Token in
Feature activation+0.607
newspapers
Token newspapers
Feature activation+0.638
and
Token and
Feature activation+0.426
other
Token other
Feature activation+0.503
media
Token media
Feature activation+0.396
as
Token as
Feature activation+0.234
mentioned
Token mentioned
Feature activation+0.446
,
Token,
Feature activation+0.563
we
Token we
Feature activation+0.598
are
Token are
Feature activation+0.691
seeing
Token seeing
Feature activation+0.842
extremely
Token extremely
Feature activation+0.686
low
Token low
Feature activation+0.685
water
Token water
Feature activation+0.793
conditions
Token conditions
Feature activation+0.570
this
Token this
Feature activation+0.462
and
Token and
Feature activation+0.090
sounds
Token sounds
Feature activation+0.291
,
Token,
Feature activation+0.437
while
Token while
Feature activation+0.740
others
Token others
Feature activation+0.920
are
Token are
Feature activation+0.835
artificial
Token artificial
Feature activation+0.651
can
Token can
Feature activation+0.683
als
Tokenals
Feature activation+0.735
.
Token.
Feature activation+0.294
It
Token It
Feature activation+0.241
iz
Tokeniz
Feature activation+0.302
technology
Token technology
Feature activation+0.024
,
Token,
Feature activation+0.107
while
Token while
Feature activation+0.515
saying
Token saying
Feature activation+0.722
little
Token little
Feature activation+0.828
about
Token about
Feature activation+0.728
the
Token the
Feature activation+0.621
people
Token people
Feature activation+0.517
who
Token who
Feature activation+0.534
already
Token already
Feature activation+0.491
were
Token were
Feature activation+0.469
some
Token some
Feature activation+0.725
exceptions
Token exceptions
Feature activation+0.709
),
Token),
Feature activation+0.656
even
Token even
Feature activation+0.757
if
Token if
Feature activation+0.825
not
Token not
Feature activation+0.801
for
Token for
Feature activation+0.692
the
Token the
Feature activation+0.613
same
Token same
Feature activation+0.613
reasons
Token reasons
Feature activation+0.533
but
Token but
Feature activation+0.546
rather
Token rather
Feature activation+0.704
than
Token than
Feature activation+0.726
fret
Token fret
Feature activation+0.689
ting
Tokenting
Feature activation+0.956
about
Token about
Feature activation+0.823
inequality
Token inequality
Feature activation+0.525
,
Token,
Feature activation+0.603
perhaps
Token perhaps
Feature activation+0.679
we
Token we
Feature activation+0.643
should
Token should
Feature activation+0.640
is
Token is
Feature activation+0.697
the
Token the
Feature activation+0.761
involvement
Token involvement
Feature activation+0.638
of
Token of
Feature activation+0.706
bigger
Token bigger
Feature activation+0.766
-
Token-
Feature activation+0.820
than
Tokenthan
Feature activation+0.619
-
Token-
Feature activation+0.780
life
Tokenlife
Feature activation+0.637
Oprah
Token Oprah
Feature activation+0.541
Win
Token Win
Feature activation+0.437
individual
Token individual
Feature activation+0.153
,
Token,
Feature activation+0.255
as
Token as
Feature activation+0.418
well
Token well
Feature activation+0.576
as
Token as
Feature activation+0.800
up
Token up
Feature activation+0.812
to
Token to
Feature activation+0.610
five
Token five
Feature activation+0.652
years
Token years
Feature activation+0.551
behind
Token behind
Feature activation+0.567
bars
Token bars
Feature activation+0.606
are
Token are
Feature activation+0.678
privileged
Token privileged
Feature activation+0.791
can
Token can
Feature activation+0.772
access
Token access
Feature activation+0.738
the
Token the
Feature activation+0.763
same
Token same
Feature activation+0.808
.
Token.
Feature activation+0.524
E
Token E
Feature activation+0.462
DP
TokenDP
Feature activation+0.530
will
Token will
Feature activation+0.345
be
Token be
Feature activation+0.438
,
Token,
Feature activation+0.239
but
Token but
Feature activation+0.465
because
Token because
Feature activation+0.586
you
Token you
Feature activation+0.659
apparently
Token apparently
Feature activation+0.723
needed
Token needed
Feature activation+0.805
to
Token to
Feature activation+0.640
communicate
Token communicate
Feature activation+0.541
something
Token something
Feature activation+0.677
to
Token to
Feature activation+0.400
me
Token me
Feature activation+0.360
some
Token some
Feature activation+0.725
exceptions
Token exceptions
Feature activation+0.709
),
Token),
Feature activation+0.656
even
Token even
Feature activation+0.757
if
Token if
Feature activation+0.825
not
Token not
Feature activation+0.801
for
Token for
Feature activation+0.692
the
Token the
Feature activation+0.613
same
Token same
Feature activation+0.613
reasons
Token reasons
Feature activation+0.533
.
Token.
Feature activation+0.231
an
Token an
Feature activation+0.119
individual
Token individual
Feature activation+0.153
,
Token,
Feature activation+0.255
as
Token as
Feature activation+0.418
well
Token well
Feature activation+0.576
as
Token as
Feature activation+0.800
up
Token up
Feature activation+0.812
to
Token to
Feature activation+0.610
five
Token five
Feature activation+0.652
years
Token years
Feature activation+0.551
behind
Token behind
Feature activation+0.567
,
Token,
Feature activation+0.335
but
Token but
Feature activation+0.473
,
Token,
Feature activation+0.511
after
Token after
Feature activation+0.570
the
Token the
Feature activation+0.779
debate
Token debate
Feature activation+0.793
âĢ
TokenâĢ
Feature activation+0.531
Ļ
TokenĻ
Feature activation+0.580
s
Tokens
Feature activation+0.511
over
Token over
Feature activation+0.469
,
Token,
Feature activation+0.520
and
Token and
Feature activation+0.423
financial
Token financial
Feature activation+0.389
documents
Token documents
Feature activation+0.461
,
Token,
Feature activation+0.453
as
Token as
Feature activation+0.566
well
Token well
Feature activation+0.793
as
Token as
Feature activation+0.845
in
Token in
Feature activation+0.607
newspapers
Token newspapers
Feature activation+0.638
and
Token and
Feature activation+0.426
other
Token other
Feature activation+0.503

Top DFA by src position
MAX = 0.680

and
Token and
Feature activation+0.160
Top resid features:
community
Token community
Feature activation+0.146
Top resid features:
members
Token members
Feature activation+0.150
Top resid features:
,
Token,
Feature activation+0.301
Top resid features:
to
Token to
Feature activation+0.328
Top resid features:
decide
Token decide
Feature activation+0.351
Top resid features:
what
Token what
Feature activation+0.171
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
school
Token school
Feature activation+0.000
Top resid features:
district
Token district
Feature activation+0.000
Top resid features:
needs
Token needs
Feature activation+0.000
Top resid features:
level
Token level
Feature activation+0.074
Top resid features:
,
Token,
Feature activation+0.300
Top resid features:
but
Token but
Feature activation+0.313
Top resid features:
rather
Token rather
Feature activation+0.252
Top resid features:
than
Token than
Feature activation+0.268
Top resid features:
fret
Token fret
Feature activation+0.363
Top resid features:
ting
Tokenting
Feature activation+0.101
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
inequality
Token inequality
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
perhaps
Token perhaps
Feature activation+0.000
Top resid features:
ays
Tokenays
Feature activation+0.105
Top resid features:
,
Token,
Feature activation+0.154
Top resid features:
and
Token and
Feature activation+0.235
Top resid features:
sounds
Token sounds
Feature activation+0.270
Top resid features:
,
Token,
Feature activation+0.208
Top resid features:
while
Token while
Feature activation+0.680
Top resid features:
others
Token others
Feature activation+0.252
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
artificial
Token artificial
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
als
Tokenals
Feature activation+0.000
Top resid features:
point
Token point
Feature activation+0.076
Top resid features:
,
Token,
Feature activation+0.197
Top resid features:
and
Token and
Feature activation+0.224
Top resid features:
for
Token for
Feature activation+0.312
Top resid features:
an
Token an
Feature activation+0.210
Top resid features:
as
Token as
Feature activation+0.362
Top resid features:
yet
Token yet
Feature activation+0.252
Top resid features:
unknown
Token unknown
Feature activation+0.275
Top resid features:
reason
Token reason
Feature activation+0.125
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
allegedly
Token allegedly
Feature activation+0.000
Top resid features:
news
Token news
Feature activation+0.129
Top resid features:
and
Token and
Feature activation+0.170
Top resid features:
much
Token much
Feature activation+0.173
Top resid features:
more
Token more
Feature activation+0.184
Top resid features:
,
Token,
Feature activation+0.298
Top resid features:
try
Token try
Feature activation+0.323
Top resid features:
an
Token an
Feature activation+0.133
Top resid features:
All
Token All
Feature activation+0.000
Top resid features:
Access
Token Access
Feature activation+0.000
Top resid features:
Digital
Token Digital
Feature activation+0.000
Top resid features:
subscription
Token subscription
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.147
Top resid features:
skiing
Token skiing
Feature activation+0.125
Top resid features:
,
Token,
Feature activation+0.369
Top resid features:
and
Token and
Feature activation+0.216
Top resid features:
biking
Token biking
Feature activation+0.177
Top resid features:
,
Token,
Feature activation+0.424
Top resid features:
and
Token and
Feature activation+0.267
Top resid features:
roller
Token roller
Feature activation+0.330
Top resid features:
bl
Tokenbl
Feature activation+0.022
Top resid features:
ading
Tokenading
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.123
Top resid features:
financial
Token financial
Feature activation+0.104
Top resid features:
documents
Token documents
Feature activation+0.103
Top resid features:
,
Token,
Feature activation+0.295
Top resid features:
as
Token as
Feature activation+0.283
Top resid features:
well
Token well
Feature activation+0.350
Top resid features:
as
Token as
Feature activation+0.214
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
newspapers
Token newspapers
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.196
Top resid features:
as
Token as
Feature activation+0.249
Top resid features:
mentioned
Token mentioned
Feature activation+0.184
Top resid features:
,
Token,
Feature activation+0.301
Top resid features:
we
Token we
Feature activation+0.239
Top resid features:
are
Token are
Feature activation+0.408
Top resid features:
seeing
Token seeing
Feature activation+0.191
Top resid features:
extremely
Token extremely
Feature activation+0.000
Top resid features:
low
Token low
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
conditions
Token conditions
Feature activation+0.000
Top resid features:
ays
Tokenays
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.146
Top resid features:
and
Token and
Feature activation+0.195
Top resid features:
sounds
Token sounds
Feature activation+0.235
Top resid features:
,
Token,
Feature activation+0.205
Top resid features:
while
Token while
Feature activation+0.508
Top resid features:
others
Token others
Feature activation+0.342
Top resid features:
are
Token are
Feature activation+0.133
Top resid features:
artificial
Token artificial
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
als
Tokenals
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.088
Top resid features:
wh
Tokenwh
Feature activation+0.111
Top resid features:
iz
Tokeniz
Feature activation+0.097
Top resid features:
technology
Token technology
Feature activation+0.123
Top resid features:
,
Token,
Feature activation+0.310
Top resid features:
while
Token while
Feature activation+0.505
Top resid features:
saying
Token saying
Feature activation+0.466
Top resid features:
little
Token little
Feature activation+0.177
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.152
Top resid features:
there
Token there
Feature activation+0.237
Top resid features:
were
Token were
Feature activation+0.192
Top resid features:
some
Token some
Feature activation+0.162
Top resid features:
exceptions
Token exceptions
Feature activation+0.253
Top resid features:
),
Token),
Feature activation+0.487
Top resid features:
even
Token even
Feature activation+0.232
Top resid features:
if
Token if
Feature activation+0.187
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.138
Top resid features:
a
Token a
Feature activation+0.094
Top resid features:
higher
Token higher
Feature activation+0.109
Top resid features:
level
Token level
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.224
Top resid features:
but
Token but
Feature activation+0.274
Top resid features:
rather
Token rather
Feature activation+0.220
Top resid features:
than
Token than
Feature activation+0.188
Top resid features:
fret
Token fret
Feature activation+0.266
Top resid features:
ting
Tokenting
Feature activation+0.222
Top resid features:
about
Token about
Feature activation+0.114
Top resid features:
that
Token that
Feature activation+0.239
Top resid features:
is
Token is
Feature activation+0.260
Top resid features:
the
Token the
Feature activation+0.200
Top resid features:
involvement
Token involvement
Feature activation+0.175
Top resid features:
of
Token of
Feature activation+0.194
Top resid features:
bigger
Token bigger
Feature activation+0.279
Top resid features:
-
Token-
Feature activation+0.055
Top resid features:
than
Tokenthan
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
life
Tokenlife
Feature activation+0.000
Top resid features:
Oprah
Token Oprah
Feature activation+0.000
Top resid features:
000
Token000
Feature activation+0.122
Top resid features:
for
Token for
Feature activation+0.174
Top resid features:
an
Token an
Feature activation+0.144
Top resid features:
individual
Token individual
Feature activation+0.151
Top resid features:
,
Token,
Feature activation+0.252
Top resid features:
as
Token as
Feature activation+0.399
Top resid features:
well
Token well
Feature activation+0.261
Top resid features:
as
Token as
Feature activation+0.357
Top resid features:
up
Token up
Feature activation+0.158
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.195
Top resid features:
therefore
Token therefore
Feature activation+0.102
Top resid features:
,
Token,
Feature activation+0.193
Top resid features:
only
Token only
Feature activation+0.157
Top resid features:
apps
Token apps
Feature activation+0.154
Top resid features:
which
Token which
Feature activation+0.257
Top resid features:
are
Token are
Feature activation+0.207
Top resid features:
privileged
Token privileged
Feature activation+0.198
Top resid features:
can
Token can
Feature activation+0.216
Top resid features:
access
Token access
Feature activation+0.189
Top resid features:
the
Token the
Feature activation+0.200
Top resid features:
avoid
Token avoid
Feature activation+0.117
Top resid features:
hitting
Token hitting
Feature activation+0.136
Top resid features:
me
Token me
Feature activation+0.089
Top resid features:
,
Token,
Feature activation+0.241
Top resid features:
but
Token but
Feature activation+0.295
Top resid features:
because
Token because
Feature activation+0.453
Top resid features:
you
Token you
Feature activation+0.317
Top resid features:
apparently
Token apparently
Feature activation+0.180
Top resid features:
needed
Token needed
Feature activation+0.107
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
communicate
Token communicate
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.149
Top resid features:
there
Token there
Feature activation+0.204
Top resid features:
were
Token were
Feature activation+0.128
Top resid features:
some
Token some
Feature activation+0.147
Top resid features:
exceptions
Token exceptions
Feature activation+0.244
Top resid features:
),
Token),
Feature activation+0.429
Top resid features:
even
Token even
Feature activation+0.189
Top resid features:
if
Token if
Feature activation+0.325
Top resid features:
not
Token not
Feature activation+0.098
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.193
Top resid features:
an
Token an
Feature activation+0.169
Top resid features:
individual
Token individual
Feature activation+0.170
Top resid features:
,
Token,
Feature activation+0.291
Top resid features:
as
Token as
Feature activation+0.323
Top resid features:
well
Token well
Feature activation+0.392
Top resid features:
as
Token as
Feature activation+0.291
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.085
Top resid features:
indicated
Token indicated
Feature activation+0.139
Top resid features:
,
Token,
Feature activation+0.211
Top resid features:
but
Token but
Feature activation+0.232
Top resid features:
,
Token,
Feature activation+0.231
Top resid features:
after
Token after
Feature activation+0.500
Top resid features:
the
Token the
Feature activation+0.251
Top resid features:
debate
Token debate
Feature activation+0.153
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
care
Token care
Feature activation+0.079
Top resid features:
and
Token and
Feature activation+0.148
Top resid features:
financial
Token financial
Feature activation+0.118
Top resid features:
documents
Token documents
Feature activation+0.120
Top resid features:
,
Token,
Feature activation+0.364
Top resid features:
as
Token as
Feature activation+0.404
Top resid features:
well
Token well
Feature activation+0.119
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
newspapers
Token newspapers
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.11

Head 2: 0.17

Head 3: 0.10

Head 4: 0.13

Head 5: 0.05

Head 6: 0.04

Head 7: 0.06

Head 8: 0.06

Head 9: 0.06

Head 10: 0.14

Head 11: 0.04

Positive logits

geoning0.67

0.66

pocket0.62

uously0.61

isse0.61

astical0.61

pmwiki0.60

istani0.58

arc0.58

peria0.57

ELY0.56

ammed0.55

aldi0.55

separately0.55

iless0.55

ibly0.54

0.54

ively0.54

ationally0.54

lopp0.54

Negative logits

Pru-0.75

ramid-0.64

Lets-0.63

Hug-0.62

Lists-0.62

congr-0.61

disadvant-0.59

Murd-0.55

Kard-0.53

Recogn-0.53

plots-0.53

reciation-0.52

Replay-0.52

Defin-0.51

Christy-0.51

appre-0.51

Puzz-0.51

erva-0.51

Values-0.50

Topics-0.50

INTERVAL 0.863 - 0.959
CONTAINS 0.000%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.090
sounds
Token sounds
Feature activation+0.291
,
Token,
Feature activation+0.437
while
Token while
Feature activation+0.740
others
Token others
Feature activation+0.920
are
Token are
Feature activation+0.835
artificial
Token artificial
Feature activation+0.651
can
Token can
Feature activation+0.683
als
Tokenals
Feature activation+0.735
.
Token.
Feature activation+0.294
,
Token,
Feature activation+0.384
but
Token but
Feature activation+0.546
rather
Token rather
Feature activation+0.704
than
Token than
Feature activation+0.726
fret
Token fret
Feature activation+0.689
ting
Tokenting
Feature activation+0.956
about
Token about
Feature activation+0.823
inequality
Token inequality
Feature activation+0.525
,
Token,
Feature activation+0.603
perhaps
Token perhaps
Feature activation+0.679
we
Token we
Feature activation+0.643
community
Token community
Feature activation+0.313
members
Token members
Feature activation+0.437
,
Token,
Feature activation+0.547
to
Token to
Feature activation+0.562
decide
Token decide
Feature activation+0.776
what
Token what
Feature activation+0.959
the
Token the
Feature activation+0.775
school
Token school
Feature activation+0.700
district
Token district
Feature activation+0.634
needs
Token needs
Feature activation+0.463
to
Token to
Feature activation+0.419

INTERVAL 0.767 - 0.863
CONTAINS 0.003%

an
Token an
Feature activation+0.119
individual
Token individual
Feature activation+0.153
,
Token,
Feature activation+0.255
as
Token as
Feature activation+0.418
well
Token well
Feature activation+0.576
as
Token as
Feature activation+0.800
up
Token up
Feature activation+0.812
to
Token to
Feature activation+0.610
five
Token five
Feature activation+0.652
years
Token years
Feature activation+0.551
behind
Token behind
Feature activation+0.567
only
Token only
Feature activation+0.286
apps
Token apps
Feature activation+0.397
which
Token which
Feature activation+0.653
are
Token are
Feature activation+0.678
privileged
Token privileged
Feature activation+0.791
can
Token can
Feature activation+0.772
access
Token access
Feature activation+0.738
the
Token the
Feature activation+0.763
same
Token same
Feature activation+0.808
.
Token.
Feature activation+0.524
E
Token E
Feature activation+0.462
and
Token and
Feature activation+0.428
much
Token much
Feature activation+0.521
more
Token more
Feature activation+0.639
,
Token,
Feature activation+0.650
try
Token try
Feature activation+0.684
an
Token an
Feature activation+0.854
All
Token All
Feature activation+0.661
Access
Token Access
Feature activation+0.554
Digital
Token Digital
Feature activation+0.358
subscription
Token subscription
Feature activation+0.317
:
Token:
Feature activation+0.005
were
Token were
Feature activation+0.469
some
Token some
Feature activation+0.725
exceptions
Token exceptions
Feature activation+0.709
),
Token),
Feature activation+0.656
even
Token even
Feature activation+0.757
if
Token if
Feature activation+0.825
not
Token not
Feature activation+0.801
for
Token for
Feature activation+0.692
the
Token the
Feature activation+0.613
same
Token same
Feature activation+0.613
reasons
Token reasons
Feature activation+0.533
Hiroshima
Token Hiroshima
Feature activation+0.105
,
Token,
Feature activation+0.350
too
Token too
Feature activation+0.461
often
Token often
Feature activation+0.650
over
Token over
Feature activation+0.647
comes
Tokencomes
Feature activation+0.782
lesser
Token lesser
Feature activation+0.606
concerns
Token concerns
Feature activation+0.569
âĢĶ
Token âĢĶ
Feature activation+0.444
like
Token like
Feature activation+0.294
the
Token the
Feature activation+0.401

INTERVAL 0.671 - 0.767
CONTAINS 0.009%

,
Token,
Feature activation+0.210
finally
Token finally
Feature activation+0.296
,
Token,
Feature activation+0.459
the
Token the
Feature activation+0.581
ups
Token ups
Feature activation+0.568
and
Token and
Feature activation+0.746
downs
Token downs
Feature activation+0.554
of
Token of
Feature activation+0.622
their
Token their
Feature activation+0.525
lives
Token lives
Feature activation+0.522
after
Token after
Feature activation+0.472
of
Token of
Feature activation+0.245
1994
Token 1994
Feature activation+0.424
,
Token,
Feature activation+0.340
it
Token it
Feature activation+0.293
provided
Token provided
Feature activation+0.452
two
Token two
Feature activation+0.703
singles
Token singles
Feature activation+0.424
which
Token which
Feature activation+0.571
also
Token also
Feature activation+0.471
did
Token did
Feature activation+0.482
well
Token well
Feature activation+0.577
and
Token and
Feature activation+0.088
for
Token for
Feature activation+0.261
an
Token an
Feature activation+0.561
as
Token as
Feature activation+0.583
yet
Token yet
Feature activation+0.652
unknown
Token unknown
Feature activation+0.764
reason
Token reason
Feature activation+0.862
,
Token,
Feature activation+0.712
allegedly
Token allegedly
Feature activation+0.595
fired
Token fired
Feature activation+0.652
his
Token his
Feature activation+0.715
Mike
Token Mike
Feature activation+0.332
y
Tokeny
Feature activation+0.508
Weinstein
Token Weinstein
Feature activation+0.307
,
Token,
Feature activation+0.402
MR
Token MR
Feature activation+0.413
FF
TokenFF
Feature activation+0.759
Advisory
Token Advisory
Feature activation+0.427
Board
Token Board
Feature activation+0.356
member
Token member
Feature activation+0.197
and
Token and
Feature activation+0.298
Islam
Token Islam
Feature activation+0.245
,
Token,
Feature activation+0.341
and
Token and
Feature activation+0.482
with
Token with
Feature activation+0.453
enough
Token enough
Feature activation+0.713
in
Token in
Feature activation+0.612
poll
Token poll
Feature activation+0.685
numbers
Token numbers
Feature activation+0.614
they
Token they
Feature activation+0.420
see
Token see
Feature activation+0.352
to
Token to
Feature activation+0.243
keep
Token keep
Feature activation+0.292

INTERVAL 0.575 - 0.671
CONTAINS 0.026%

-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.014
learned
Token learned
Feature activation+0.066
more
Token more
Feature activation+0.239
,
Token,
Feature activation+0.373
but
Token but
Feature activation+0.584
not
Token not
Feature activation+0.627
much
Token much
Feature activation+0.724
more
Token more
Feature activation+0.745
.
Token.
Feature activation+0.338
The
Token The
Feature activation+0.305
and
Token and
Feature activation+0.482
with
Token with
Feature activation+0.453
enough
Token enough
Feature activation+0.713
in
Token in
Feature activation+0.612
poll
Token poll
Feature activation+0.685
numbers
Token numbers
Feature activation+0.614
they
Token they
Feature activation+0.420
see
Token see
Feature activation+0.352
to
Token to
Feature activation+0.243
keep
Token keep
Feature activation+0.292
them
Token them
Feature activation+0.243
is
Token is
Feature activation+0.514
divided
Token divided
Feature activation+0.558
on
Token on
Feature activation+0.591
the
Token the
Feature activation+0.638
issue
Token issue
Feature activation+0.466
,
Token,
Feature activation+0.578
and
Token and
Feature activation+0.495
did
Token did
Feature activation+0.407
not
Token not
Feature activation+0.661
impose
Token impose
Feature activation+0.477
a
Token a
Feature activation+0.442
,
Token,
Feature activation+0.057
after
Token after
Feature activation+0.192
all
Token all
Feature activation+0.500
,
Token,
Feature activation+0.464
has
Token has
Feature activation+0.422
an
Token an
Feature activation+0.616
iron
Token iron
Feature activation+0.402
-
Token-
Feature activation+0.509
like
Tokenlike
Feature activation+0.334
grip
Token grip
Feature activation+0.348
on
Token on
Feature activation+0.236
,
Token,
Feature activation+0.459
the
Token the
Feature activation+0.581
ups
Token ups
Feature activation+0.568
and
Token and
Feature activation+0.746
downs
Token downs
Feature activation+0.554
of
Token of
Feature activation+0.622
their
Token their
Feature activation+0.525
lives
Token lives
Feature activation+0.522
after
Token after
Feature activation+0.472
they
Token they
Feature activation+0.328
returned
Token returned
Feature activation+0.369

INTERVAL 0.479 - 0.575
CONTAINS 0.070%

enormous
Token enormous
Feature activation+0.346
amounts
Token amounts
Feature activation+0.471
of
Token of
Feature activation+0.419
precious
Token precious
Feature activation+0.505
fresh
Token fresh
Feature activation+0.457
water
Token water
Feature activation+0.492
and
Token and
Feature activation+0.328
releases
Token releases
Feature activation+0.190
massive
Token massive
Feature activation+0.285
amounts
Token amounts
Feature activation+0.347
of
Token of
Feature activation+0.192
and
Token and
Feature activation+0.309
media
Token media
Feature activation+0.273
school
Token school
Feature activation+0.266
,
Token,
Feature activation+0.414
and
Token and
Feature activation+0.469
met
Token met
Feature activation+0.487
a
Token a
Feature activation+0.656
book
Token book
Feature activation+0.534
pack
Token pack
Feature activation+0.429
ager
Tokenager
Feature activation+0.583
named
Token named
Feature activation+0.448
I
Token I
Feature activation+0.021
just
Token just
Feature activation+0.153
indicated
Token indicated
Feature activation+0.106
,
Token,
Feature activation+0.335
but
Token but
Feature activation+0.473
,
Token,
Feature activation+0.511
after
Token after
Feature activation+0.570
the
Token the
Feature activation+0.779
debate
Token debate
Feature activation+0.793
âĢ
TokenâĢ
Feature activation+0.531
Ļ
TokenĻ
Feature activation+0.580
and
Token and
Feature activation+0.293
that
Token that
Feature activation+0.370
his
Token his
Feature activation+0.521
remark
Token remark
Feature activation+0.488
on
Token on
Feature activation+0.431
Thursday
Token Thursday
Feature activation+0.508
wasn
Token wasn
Feature activation+0.458
't
Token't
Feature activation+0.574
"
Token "
Feature activation+0.312
a
Tokena
Feature activation+0.110
personal
Token personal
Feature activation+0.133
and
Token and
Feature activation+0.000
officials
Token officials
Feature activation+0.000
who
Token who
Feature activation+0.161
have
Token have
Feature activation+0.295
been
Token been
Feature activation+0.365
watching
Token watching
Feature activation+0.533
the
Token the
Feature activation+0.417
sport
Token sport
Feature activation+0.395
for
Token for
Feature activation+0.300
decades
Token decades
Feature activation+0.239
.
Token.
Feature activation+0.109

INTERVAL 0.383 - 0.479
CONTAINS 0.173%

of
Token of
Feature activation+0.381
Brexit
Token Brexit
Feature activation+0.232
,
Token,
Feature activation+0.557
the
Token the
Feature activation+0.547
UK
Token UK
Feature activation+0.485
will
Token will
Feature activation+0.469
no
Token no
Feature activation+0.654
longer
Token longer
Feature activation+0.651
have
Token have
Feature activation+0.567
a
Token a
Feature activation+0.479
say
Token say
Feature activation+0.415
the
Token the
Feature activation+0.143
launch
Token launch
Feature activation+0.120
site
Token site
Feature activation+0.093
,
Token,
Feature activation+0.183
well
Token well
Feature activation+0.270
short
Token short
Feature activation+0.419
of
Token of
Feature activation+0.312
its
Token its
Feature activation+0.335
maximum
Token maximum
Feature activation+0.250
range
Token range
Feature activation+0.244
.
Token.
Feature activation+0.000
permission
Token permission
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.139
might
Token might
Feature activation+0.228
guess
Token guess
Feature activation+0.472
,
Token,
Feature activation+0.298
is
Token is
Feature activation+0.197
bestowed
Token bestowed
Feature activation+0.223
by
Token by
Feature activation+0.364
the
Token the
Feature activation+0.342
,
Token,
Feature activation+0.200
killing
Token killing
Feature activation+0.132
animals
Token animals
Feature activation+0.067
and
Token and
Feature activation+0.235
allowing
Token allowing
Feature activation+0.286
others
Token others
Feature activation+0.468
to
Token to
Feature activation+0.379
escape
Token escape
Feature activation+0.280
.
Token.
Feature activation+0.189
Initially
Token Initially
Feature activation+0.161
,
Token,
Feature activation+0.229
turn
Token turn
Feature activation+0.499
of
Token of
Feature activation+0.386
the
Token the
Feature activation+0.442
story
Token story
Feature activation+0.427
of
Token of
Feature activation+0.319
Apollo
Token Apollo
Feature activation+0.427
13
Token 13
Feature activation+0.354
on
Token on
Feature activation+0.109
the
Token the
Feature activation+0.210
radio
Token radio
Feature activation+0.248
and
Token and
Feature activation+0.000

INTERVAL 0.288 - 0.383
CONTAINS 0.358%

press
Token press
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
virtually
Token virtually
Feature activation+0.021
indistinguishable
Token indistinguishable
Feature activation+0.000
from
Token from
Feature activation+0.349
freedom
Token freedom
Feature activation+0.216
of
Token of
Feature activation+0.195
speech
Token speech
Feature activation+0.171
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
four
Token four
Feature activation+0.032
,
Token,
Feature activation+0.060
was
Token was
Feature activation+0.227
shot
Token shot
Feature activation+0.449
and
Token and
Feature activation+0.408
killed
Token killed
Feature activation+0.334
by
Token by
Feature activation+0.335
Officer
Token Officer
Feature activation+0.201
Betty
Token Betty
Feature activation+0.240
Shelby
Token Shelby
Feature activation+0.081
as
Token as
Feature activation+0.120
,
Token,
Feature activation+0.254
to
Token to
Feature activation+0.204
deliver
Token deliver
Feature activation+0.263
a
Token a
Feature activation+0.401
higher
Token higher
Feature activation+0.311
level
Token level
Feature activation+0.347
of
Token of
Feature activation+0.195
security
Token security
Feature activation+0.024
from
Token from
Feature activation+0.147
the
Token the
Feature activation+0.183
start
Token start
Feature activation+0.004
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
can
Token can
Feature activation+0.000
now
Token now
Feature activation+0.000
confirm
Token confirm
Feature activation+0.160
that
Token that
Feature activation+0.309
Big
Token Big
Feature activation+0.399
E
Token E
Feature activation+0.355
suffered
Token suffered
Feature activation+0.261
a
Token a
Feature activation+0.312
cont
Token cont
Feature activation+0.104
what
Token what
Feature activation+0.417
actually
Token actually
Feature activation+0.355
is
Token is
Feature activation+0.220
,
Token,
Feature activation+0.222
which
Token which
Feature activation+0.216
might
Token might
Feature activation+0.296
be
Token be
Feature activation+0.360
called
Token called
Feature activation+0.095
n
Token n
Feature activation+0.010
own
Tokenown
Feature activation+0.074
ess
Tokeness
Feature activation+0.020

INTERVAL 0.192 - 0.288
CONTAINS 0.619%

which
Token which
Feature activation+0.180
will
Token will
Feature activation+0.268
continue
Token continue
Feature activation+0.393
to
Token to
Feature activation+0.437
threaten
Token threaten
Feature activation+0.211
PCs
Token PCs
Feature activation+0.255
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Apple
TokenApple
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
this
Token this
Feature activation+0.070
nexus
Token nexus
Feature activation+0.000
is
Token is
Feature activation+0.062
even
Token even
Feature activation+0.242
more
Token more
Feature activation+0.256
pronounced
Token pronounced
Feature activation+0.238
here
Token here
Feature activation+0.211
in
Token in
Feature activation+0.126
Texas
Token Texas
Feature activation+0.090
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
cycling
Token cycling
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.005
out
Token out
Feature activation+0.054
of
Token of
Feature activation+0.261
ket
Token ket
Feature activation+0.043
osis
Tokenosis
Feature activation+0.139
was
Token was
Feature activation+0.154
new
Token new
Feature activation+0.317
to
Token to
Feature activation+0.212
taken
Token taken
Feature activation+0.510
aback
Token aback
Feature activation+0.200
by
Token by
Feature activation+0.251
its
Token its
Feature activation+0.334
spectacle
Token spectacle
Feature activation+0.139
,
Token,
Feature activation+0.286
which
Token which
Feature activation+0.273
was
Token was
Feature activation+0.215
not
Token not
Feature activation+0.356
just
Token just
Feature activation+0.339
grand
Token grand
Feature activation+0.157
cr
Token cr
Feature activation+0.080
ick
Tokenick
Feature activation+0.354
eters
Tokeneters
Feature activation+0.016
and
Token and
Feature activation+0.000
others
Token others
Feature activation+0.027
whose
Token whose
Feature activation+0.268
genius
Token genius
Feature activation+0.128
bl
Token bl
Feature activation+0.160
ed
Tokened
Feature activation+0.131
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.096 - 0.192
CONTAINS 0.955%

flattened
Token flattened
Feature activation+0.000
inside
Token inside
Feature activation+0.013
for
Token for
Feature activation+0.137
a
Token a
Feature activation+0.168
big
Token big
Feature activation+0.110
gain
Token gain
Feature activation+0.120
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.090
middle
Token middle
Feature activation+0.000
.
Token.
Feature activation+0.000
King
Token King
Feature activation+0.000
,
Token,
Feature activation+0.183
neither
Token neither
Feature activation+0.340
does
Token does
Feature activation+0.468
the
Token the
Feature activation+0.453
prospect
Token prospect
Feature activation+0.399
.
Token.
Feature activation+0.155
You
Token You
Feature activation+0.199
can
Token can
Feature activation+0.109
feel
Token feel
Feature activation+0.257
a
Token a
Feature activation+0.155
little
Token little
Feature activation+0.149
,
Token,
Feature activation+0.405
which
Token which
Feature activation+0.508
they
Token they
Feature activation+0.456
gave
Token gave
Feature activation+0.412
.
Token.
Feature activation+0.273
Unfortunately
Token Unfortunately
Feature activation+0.162
,
Token,
Feature activation+0.297
the
Token the
Feature activation+0.235
Army
Token Army
Feature activation+0.137
made
Token made
Feature activation+0.109
an
Token an
Feature activation+0.153
,
Token,
Feature activation+0.000
respondents
Token respondents
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
witnesses
Token witnesses
Feature activation+0.000
speak
Token speak
Feature activation+0.123
to
Token to
Feature activation+0.129
investigators
Token investigators
Feature activation+0.149
,
Token,
Feature activation+0.306
no
Token no
Feature activation+0.383
recording
Token recording
Feature activation+0.173
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.130
been
Token been
Feature activation+0.271
largely
Token largely
Feature activation+0.416
immune
Token immune
Feature activation+0.454
from
Token from
Feature activation+0.548
criticism
Token criticism
Feature activation+0.436

INTERVAL 0.000 - 0.096
CONTAINS 97.787%

quite
Token quite
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
I
TokenI
Feature activation+0.000
've
Token've
Feature activation+0.000
known
Token known
Feature activation+0.000
S
Token S
Feature activation+0.000
atch
Tokenatch
Feature activation+0.000
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Wonder
Token Wonder
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
pre
Token pre
Feature activation+0.000
ppy
Tokenppy
Feature activation+0.000
retailer
Token retailer
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
hundred
Token hundred
Feature activation+0.000
with
Token with
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Nusra
TokenNusra
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
official
Token official
Feature activation+0.000
said
Token said
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Mori
Token Mori
Feature activation+0.000
arty
Tokenarty
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
go
Token go
Feature activation+0.000
after
Token after
Feature activation+0.000
any
Token any
Feature activation+0.000
ar
Token ar
Feature activation+0.000
re
Tokenre
Feature activation+0.000
ars
Tokenars
Feature activation+0.000
for
Token for
Feature activation+0.000
domestic
Token domestic
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 H1.2: (feature 11366)

TOP ACTIVATIONS
MAX = 1.726

âĢ
TokenâĢ
Feature activation+0.175
Ļ
TokenĻ
Feature activation+0.307
Brien
TokenBrien
Feature activation+0.883
âĢ
TokenâĢ
Feature activation+0.811
Ļ
TokenĻ
Feature activation+0.730
s
Tokens
Feature activation+1.726
desk
Token desk
Feature activation+1.332
.
Token.
Feature activation+1.178
<|endoftext|>
Token<|endoftext|>
Feature activation+0.017
Search
TokenSearch
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.266
what
Token what
Feature activation+1.033
âĢ
TokenâĢ
Feature activation+0.720
Ļ
TokenĻ
Feature activation+0.525
s
Tokens
Feature activation+1.640
happening
Token happening
Feature activation+1.383
with
Token with
Feature activation+1.253
the
Token the
Feature activation+0.990
DP
Token DP
Feature activation+0.480
W
TokenW
Feature activation+0.752
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
That
Token That
Feature activation+0.705
âĢ
TokenâĢ
Feature activation+0.456
Ļ
TokenĻ
Feature activation+0.422
s
Tokens
Feature activation+1.629
odd
Token odd
Feature activation+1.316
.
Token.
Feature activation+1.257
Only
Token Only
Feature activation+0.876
three
Token three
Feature activation+0.607
months
Token months
Feature activation+0.397
to
Token to
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.299
Ļ
TokenĻ
Feature activation+0.197
s
Tokens
Feature activation+1.620
meeting
Token meeting
Feature activation+1.450
.
Token.
Feature activation+1.198
Ċ
TokenĊ
Feature activation+0.373
Ċ
TokenĊ
Feature activation+0.167
Many
TokenMany
Feature activation+0.198
banks
Token banks
Feature activation+0.000
so
Token so
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.121
Ļ
TokenĻ
Feature activation+0.340
s
Tokens
Feature activation+1.609
decentral
Token decentral
Feature activation+1.057
ization
Tokenization
Feature activation+0.866
and
Token and
Feature activation+0.924
promise
Token promise
Feature activation+0.631
to
Token to
Feature activation+0.452
Standard
Token Standard
Feature activation+0.000
&
Token &
Feature activation+0.000
Poor
Token Poor
Feature activation+0.150
âĢ
TokenâĢ
Feature activation+0.238
Ļ
TokenĻ
Feature activation+0.356
s
Tokens
Feature activation+1.594
,
Token,
Feature activation+1.117
which
Token which
Feature activation+0.710
in
Token in
Feature activation+0.462
a
Token a
Feature activation+0.535
report
Token report
Feature activation+0.268
al
Tokenal
Feature activation+0.000
Bern
Token Bern
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.125
Ļ
TokenĻ
Feature activation+0.446
s
Tokens
Feature activation+1.592
revelation
Token revelation
Feature activation+1.137
that
Token that
Feature activation+0.788
federal
Token federal
Feature activation+0.364
authorities
Token authorities
Feature activation+0.196
already
Token already
Feature activation+0.356
ratings
Token ratings
Feature activation+0.000
to
Token to
Feature activation+0.000
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.354
Ļ
TokenĻ
Feature activation+0.308
s
Tokens
Feature activation+1.584
every
Token every
Feature activation+1.243
action
Token action
Feature activation+1.093
,
Token,
Feature activation+0.883
so
Token so
Feature activation+0.532
it
Token it
Feature activation+0.297
Mont
Token Mont
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Python
Token Python
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.273
Ļ
TokenĻ
Feature activation+0.343
s
Tokens
Feature activation+1.583
take
Token take
Feature activation+1.288
on
Token on
Feature activation+0.660
this
Token this
Feature activation+0.572
important
Token important
Feature activation+0.383
time
Token time
Feature activation+0.339
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
That
Token That
Feature activation+0.745
âĢ
TokenâĢ
Feature activation+0.355
Ļ
TokenĻ
Feature activation+0.433
s
Tokens
Feature activation+1.574
not
Token not
Feature activation+1.490
true
Token true
Feature activation+1.043
.
Token.
Feature activation+1.012
I
Token I
Feature activation+0.561
love
Token love
Feature activation+0.226
used
Token used
Feature activation+0.000
in
Token in
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.178
Ļ
TokenĻ
Feature activation+0.266
s
Tokens
Feature activation+1.567
handset
Token handset
Feature activation+1.026
.
Token.
Feature activation+0.964
Considering
Token Considering
Feature activation+0.399
the
Token the
Feature activation+0.235
memory
Token memory
Feature activation+0.222
good
Token good
Feature activation+0.000
for
Token for
Feature activation+0.000
women
Token women
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.347
Ļ
TokenĻ
Feature activation+0.129
s
Tokens
Feature activation+1.567
health
Token health
Feature activation+1.489
,
Token,
Feature activation+0.900
but
Token but
Feature activation+0.450
also
Token also
Feature activation+0.172
moral
Token moral
Feature activation+0.192
pleased
Token pleased
Feature activation+0.660
we
Token we
Feature activation+0.717
âĢ
TokenâĢ
Feature activation+0.603
Ļ
TokenĻ
Feature activation+0.393
re
Tokenre
Feature activation+1.367
bringing
Token bringing
Feature activation+1.566
him
Token him
Feature activation+1.173
in
Token in
Feature activation+0.785
.
Token.
Feature activation+0.891
âĢ
TokenâĢ
Feature activation+0.289
Ŀ
TokenĿ
Feature activation+0.000
evaluations
Token evaluations
Feature activation+0.000
since
Token since
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.356
Ļ
TokenĻ
Feature activation+0.207
s
Tokens
Feature activation+1.562
pal
Token pal
Feature activation+1.175
ates
Tokenates
Feature activation+0.845
are
Token are
Feature activation+1.142
different
Token different
Feature activation+0.864
.
Token.
Feature activation+0.705
limited
Token limited
Feature activation+0.009
its
Token its
Feature activation+0.109
occupant
Token occupant
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.452
Ļ
TokenĻ
Feature activation+0.383
s
Tokens
Feature activation+1.554
vision
Token vision
Feature activation+1.257
and
Token and
Feature activation+0.971
range
Token range
Feature activation+0.573
of
Token of
Feature activation+0.474
motion
Token motion
Feature activation+0.115
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.766
Ļ
TokenĻ
Feature activation+0.610
he
Token he
Feature activation+1.548
said
Token said
Feature activation+1.203
.
Token.
Feature activation+1.042
Ċ
TokenĊ
Feature activation+0.391
Ċ
TokenĊ
Feature activation+0.191
âĢ
TokenâĢ
Feature activation+0.010
ere
Tokenere
Feature activation+0.000
og
Tokenog
Feature activation+0.083
um
Tokenum
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.270
Ļ
TokenĻ
Feature activation+0.332
s
Tokens
Feature activation+1.511
list
Token list
Feature activation+1.232
of
Token of
Feature activation+1.065
the
Token the
Feature activation+0.778
best
Token best
Feature activation+0.661
albums
Token albums
Feature activation+0.383
of
Token of
Feature activation+0.000
Cle
Token Cle
Feature activation+0.000
ary
Tokenary
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.033
Ļ
TokenĻ
Feature activation+0.278
s
Tokens
Feature activation+1.508
2011
Token 2011
Feature activation+0.841
Grand
Token Grand
Feature activation+0.727
Final
Token Final
Feature activation+0.530
team
Token team
Feature activation+0.577
at
Token at
Feature activation+0.551
like
Token like
Feature activation+0.786
Grand
Token Grand
Feature activation+0.374
pa
Tokenpa
Feature activation+0.212
âĢ
TokenâĢ
Feature activation+0.290
Ļ
TokenĻ
Feature activation+0.308
s
Tokens
Feature activation+1.495
100
Token 100
Feature activation+1.033
-
Token-
Feature activation+0.710
year
Tokenyear
Feature activation+0.656
-
Token-
Feature activation+0.511
old
Tokenold
Feature activation+0.352
J
Token J
Feature activation+0.000
odor
Tokenodor
Feature activation+0.000
owsky
Tokenowsky
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.180
ĺ
Tokenĺ
Feature activation+0.339
s
Tokens
Feature activation+1.492
D
Token D
Feature activation+0.973
une
Tokenune
Feature activation+0.645
.
Token.
Feature activation+0.693
Ċ
TokenĊ
Feature activation+0.070
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 1.533

Conan
Token Conan
Feature activation+0.006
Top resid features:
O
Token O
Feature activation-0.020
Top resid features:
âĢ
TokenâĢ
Feature activation+0.476
Top resid features:
Ļ
TokenĻ
Feature activation+0.132
Top resid features:
Brien
TokenBrien
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.882
Top resid features:
Ļ
TokenĻ
Feature activation+0.233
Top resid features:
s
Tokens
Feature activation+0.032
Top resid features:
desk
Token desk
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
That
Token That
Feature activation-0.042
Top resid features:
âĢ
TokenâĢ
Feature activation+0.496
Top resid features:
Ļ
TokenĻ
Feature activation+0.153
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
what
Token what
Feature activation-0.052
Top resid features:
âĢ
TokenâĢ
Feature activation+1.028
Top resid features:
Ļ
TokenĻ
Feature activation+0.267
Top resid features:
s
Tokens
Feature activation+0.074
Top resid features:
happening
Token happening
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
decisions
Token decisions
Feature activation-0.045
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
âĢ
TokenâĢ
Feature activation+0.503
Top resid features:
Ŀ
TokenĿ
Feature activation+0.118
Top resid features:
That
Token That
Feature activation-0.049
Top resid features:
âĢ
TokenâĢ
Feature activation+1.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.325
Top resid features:
s
Tokens
Feature activation-0.013
Top resid features:
odd
Token odd
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Only
Token Only
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
communicated
Token communicated
Feature activation+0.005
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
last
Token last
Feature activation+0.010
Top resid features:
night
Token night
Feature activation-0.042
Top resid features:
âĢ
TokenâĢ
Feature activation+1.533
Top resid features:
Ļ
TokenĻ
Feature activation+0.353
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
meeting
Token meeting
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
big
Token big
Feature activation+0.007
Top resid features:
banks
Token banks
Feature activation-0.003
Top resid features:
so
Token so
Feature activation-0.019
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+1.488
Top resid features:
Ļ
TokenĻ
Feature activation+0.374
Top resid features:
s
Tokens
Feature activation+0.036
Top resid features:
decentral
Token decentral
Feature activation+0.000
Top resid features:
ization
Tokenization
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
ratings
Token ratings
Feature activation-0.009
Top resid features:
agency
Token agency
Feature activation-0.013
Top resid features:
Standard
Token Standard
Feature activation-0.010
Top resid features:
&
Token &
Feature activation+0.098
Top resid features:
Poor
Token Poor
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+1.358
Top resid features:
Ļ
TokenĻ
Feature activation+0.337
Top resid features:
s
Tokens
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ch
Token Ch
Feature activation-0.003
Top resid features:
ant
Tokenant
Feature activation+0.057
Top resid features:
al
Tokenal
Feature activation+0.048
Top resid features:
Bern
Token Bern
Feature activation+0.093
Top resid features:
ier
Tokenier
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+1.459
Top resid features:
Ļ
TokenĻ
Feature activation+0.301
Top resid features:
s
Tokens
Feature activation-0.010
Top resid features:
revelation
Token revelation
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
federal
Token federal
Feature activation+0.000
Top resid features:
assigning
Token assigning
Feature activation-0.008
Top resid features:
numerical
Token numerical
Feature activation+0.016
Top resid features:
ratings
Token ratings
Feature activation+0.013
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+1.473
Top resid features:
Ļ
TokenĻ
Feature activation+0.308
Top resid features:
s
Tokens
Feature activation+0.040
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
action
Token action
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
supplemented
Token supplemented
Feature activation-0.013
Top resid features:
by
Token by
Feature activation-0.006
Top resid features:
Mont
Token Mont
Feature activation+0.062
Top resid features:
y
Tokeny
Feature activation+0.006
Top resid features:
Python
Token Python
Feature activation-0.032
Top resid features:
âĢ
TokenâĢ
Feature activation+1.353
Top resid features:
Ļ
TokenĻ
Feature activation+0.302
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
accountable
Token accountable
Feature activation-0.033
Top resid features:
.
Token.
Feature activation+0.049
Top resid features:
âĢ
TokenâĢ
Feature activation+0.469
Top resid features:
Ļ
TokenĻ
Feature activation+0.177
Top resid features:
That
Token That
Feature activation-0.057
Top resid features:
âĢ
TokenâĢ
Feature activation+0.981
Top resid features:
Ļ
TokenĻ
Feature activation+0.314
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
true
Token true
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
AND
TokenAND
Feature activation+0.031
Top resid features:
memory
Token memory
Feature activation+0.021
Top resid features:
used
Token used
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
Apple
Token Apple
Feature activation-0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+1.445
Top resid features:
Ļ
TokenĻ
Feature activation+0.305
Top resid features:
s
Tokens
Feature activation+0.024
Top resid features:
handset
Token handset
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Considering
Token Considering
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
only
Token only
Feature activation+0.002
Top resid features:
good
Token good
Feature activation-0.019
Top resid features:
for
Token for
Feature activation-0.028
Top resid features:
women
Token women
Feature activation+0.042
Top resid features:
âĢ
TokenâĢ
Feature activation+1.385
Top resid features:
Ļ
TokenĻ
Feature activation+0.285
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
health
Token health
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:
Ļ
TokenĻ
Feature activation+0.106
Top resid features:
m
Tokenm
Feature activation+0.041
Top resid features:
really
Token really
Feature activation+0.009
Top resid features:
pleased
Token pleased
Feature activation+0.048
Top resid features:
we
Token we
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.767
Top resid features:
Ļ
TokenĻ
Feature activation+0.234
Top resid features:
re
Tokenre
Feature activation+0.085
Top resid features:
bringing
Token bringing
Feature activation+0.073
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.016
Top resid features:
own
Token own
Feature activation+0.014
Top resid features:
evaluations
Token evaluations
Feature activation+0.021
Top resid features:
since
Token since
Feature activation-0.039
Top resid features:
everyone
Token everyone
Feature activation-0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+1.457
Top resid features:
Ļ
TokenĻ
Feature activation+0.336
Top resid features:
s
Tokens
Feature activation+0.036
Top resid features:
pal
Token pal
Feature activation+0.000
Top resid features:
ates
Tokenates
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
severely
Token severely
Feature activation+0.021
Top resid features:
it
Token it
Feature activation-0.010
Top resid features:
limited
Token limited
Feature activation-0.001
Top resid features:
its
Token its
Feature activation+0.028
Top resid features:
occupant
Token occupant
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+1.410
Top resid features:
Ļ
TokenĻ
Feature activation+0.261
Top resid features:
s
Tokens
Feature activation-0.024
Top resid features:
vision
Token vision
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
range
Token range
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
knock
Token knock
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
âĢ
TokenâĢ
Feature activation+0.650
Top resid features:
Ļ
TokenĻ
Feature activation+0.245
Top resid features:
âĢ
TokenâĢ
Feature activation+0.695
Top resid features:
Ļ
TokenĻ
Feature activation+0.299
Top resid features:
he
Token he
Feature activation-0.111
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.011
Top resid features:
St
Token St
Feature activation+0.041
Top resid features:
ere
Tokenere
Feature activation+0.007
Top resid features:
og
Tokenog
Feature activation-0.005
Top resid features:
um
Tokenum
Feature activation+0.051
Top resid features:
âĢ
TokenâĢ
Feature activation+1.282
Top resid features:
Ļ
TokenĻ
Feature activation+0.282
Top resid features:
s
Tokens
Feature activation-0.020
Top resid features:
list
Token list
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:
major
Token major
Feature activation-0.008
Top resid features:
part
Token part
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
Cle
Token Cle
Feature activation+0.009
Top resid features:
ary
Tokenary
Feature activation+0.038
Top resid features:
âĢ
TokenâĢ
Feature activation+1.393
Top resid features:
Ļ
TokenĻ
Feature activation+0.311
Top resid features:
s
Tokens
Feature activation+0.028
Top resid features:
2011
Token 2011
Feature activation+0.000
Top resid features:
Grand
Token Grand
Feature activation+0.000
Top resid features:
Final
Token Final
Feature activation+0.000
Top resid features:
worked
Token worked
Feature activation+0.013
Top resid features:
just
Token just
Feature activation-0.013
Top resid features:
like
Token like
Feature activation-0.009
Top resid features:
Grand
Token Grand
Feature activation+0.011
Top resid features:
pa
Tokenpa
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+1.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.278
Top resid features:
s
Tokens
Feature activation-0.030
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
Ale
Token Ale
Feature activation+0.040
Top resid features:
jandro
Tokenjandro
Feature activation+0.044
Top resid features:
J
Token J
Feature activation+0.015
Top resid features:
odor
Tokenodor
Feature activation+0.044
Top resid features:
owsky
Tokenowsky
Feature activation+0.072
Top resid features:
âĢ
TokenâĢ
Feature activation+1.394
Top resid features:
ĺ
Tokenĺ
Feature activation+0.207
Top resid features:
s
Tokens
Feature activation-0.042
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
une
Tokenune
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.15

Head 2: 0.17

Head 3: 0.07

Head 4: 0.12

Head 5: 0.03

Head 6: 0.03

Head 7: 0.06

Head 8: 0.05

Head 9: 0.05

Head 10: 0.17

Head 11: 0.05

Positive logits

Chandra0.97

Tik0.89

0.86

0.85

rahim0.84

Shank0.84

Nik0.84

Chand0.84

0.83

ashtra0.83

Pradesh0.80

[/0.80

Shiv0.80

atoon0.80

Vish0.80

Tuls0.79

Foss0.79

0.79

(@0.79

anth0.79

Negative logits

catentry-0.96

ailability-0.94

reperc-0.93

rigging-0.93

relapse-0.92

ModLoader-0.89

scenery-0.89

surpr-0.87

outwe-0.86

enthusi-0.85

dilig-0.84

rouse-0.84

ende-0.81

partake-0.81

instruments-0.80

exerc-0.79

uncture-0.79

glers-0.78

overlook-0.78

footing-0.78

INTERVAL 1.553 - 1.726
CONTAINS 0.002%

used
Token used
Feature activation+0.000
in
Token in
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.178
Ļ
TokenĻ
Feature activation+0.266
s
Tokens
Feature activation+1.567
handset
Token handset
Feature activation+1.026
.
Token.
Feature activation+0.964
Considering
Token Considering
Feature activation+0.399
the
Token the
Feature activation+0.235
memory
Token memory
Feature activation+0.222
to
Token to
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.299
Ļ
TokenĻ
Feature activation+0.197
s
Tokens
Feature activation+1.620
meeting
Token meeting
Feature activation+1.450
.
Token.
Feature activation+1.198
Ċ
TokenĊ
Feature activation+0.373
Ċ
TokenĊ
Feature activation+0.167
Many
TokenMany
Feature activation+0.198
limited
Token limited
Feature activation+0.009
its
Token its
Feature activation+0.109
occupant
Token occupant
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.452
Ļ
TokenĻ
Feature activation+0.383
s
Tokens
Feature activation+1.554
vision
Token vision
Feature activation+1.257
and
Token and
Feature activation+0.971
range
Token range
Feature activation+0.573
of
Token of
Feature activation+0.474
motion
Token motion
Feature activation+0.115
âĢ
TokenâĢ
Feature activation+0.175
Ļ
TokenĻ
Feature activation+0.307
Brien
TokenBrien
Feature activation+0.883
âĢ
TokenâĢ
Feature activation+0.811
Ļ
TokenĻ
Feature activation+0.730
s
Tokens
Feature activation+1.726
desk
Token desk
Feature activation+1.332
.
Token.
Feature activation+1.178
<|endoftext|>
Token<|endoftext|>
Feature activation+0.017
Search
TokenSearch
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
pleased
Token pleased
Feature activation+0.660
we
Token we
Feature activation+0.717
âĢ
TokenâĢ
Feature activation+0.603
Ļ
TokenĻ
Feature activation+0.393
re
Tokenre
Feature activation+1.367
bringing
Token bringing
Feature activation+1.566
him
Token him
Feature activation+1.173
in
Token in
Feature activation+0.785
.
Token.
Feature activation+0.891
âĢ
TokenâĢ
Feature activation+0.289
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 1.381 - 1.553
CONTAINS 0.004%

s
Tokens
Feature activation+0.722
clear
Token clear
Feature activation+0.853
it
Token it
Feature activation+0.769
âĢ
TokenâĢ
Feature activation+0.357
Ļ
TokenĻ
Feature activation+0.347
s
Tokens
Feature activation+1.418
been
Token been
Feature activation+1.156
a
Token a
Feature activation+1.265
privilege
Token privilege
Feature activation+0.741
for
Token for
Feature activation+0.749
the
Token the
Feature activation+0.615
barely
Token barely
Feature activation+0.000
below
Token below
Feature activation+0.000
Nevada
Token Nevada
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.211
Ļ
TokenĻ
Feature activation+0.178
s
Tokens
Feature activation+1.453
12
Token 12
Feature activation+0.864
.
Token.
Feature activation+0.818
5
Token5
Feature activation+0.428
percent
Token percent
Feature activation+0.564
âĢĶ
Token âĢĶ
Feature activation+0.199
cities
Token cities
Feature activation+0.000
in
Token in
Feature activation+0.000
California
Token California
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.330
Ļ
TokenĻ
Feature activation+0.023
s
Tokens
Feature activation+1.400
Central
Token Central
Feature activation+0.771
Valley
Token Valley
Feature activation+0.679
âĢĶ
TokenâĢĶ
Feature activation+0.468
Sac
TokenSac
Feature activation+0.264
rament
Tokenrament
Feature activation+0.064
like
Token like
Feature activation+0.786
Grand
Token Grand
Feature activation+0.374
pa
Tokenpa
Feature activation+0.212
âĢ
TokenâĢ
Feature activation+0.290
Ļ
TokenĻ
Feature activation+0.308
s
Tokens
Feature activation+1.495
100
Token 100
Feature activation+1.033
-
Token-
Feature activation+0.710
year
Tokenyear
Feature activation+0.656
-
Token-
Feature activation+0.511
old
Tokenold
Feature activation+0.352
pler
Tokenpler
Feature activation+0.000
:
Token:
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.113
Ļ
TokenĻ
Feature activation+0.150
s
Tokens
Feature activation+1.439
a
Token a
Feature activation+1.224
sound
Token sound
Feature activation+0.961
that
Token that
Feature activation+0.844
means
Token means
Feature activation+0.586
work
Token work
Feature activation+0.340

INTERVAL 1.208 - 1.381
CONTAINS 0.019%

him
Token him
Feature activation+0.000
what
Token what
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.317
Ļ
TokenĻ
Feature activation+0.052
d
Tokend
Feature activation+1.307
like
Token like
Feature activation+1.049
to
Token to
Feature activation+0.610
drink
Token drink
Feature activation+0.371
.
Token.
Feature activation+0.658
He
Token He
Feature activation+0.135
when
Token when
Feature activation+0.000
assessing
Token assessing
Feature activation+0.000
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.221
personality
Token personality
Feature activation+0.727
traits
Token traits
Feature activation+0.680
.
Token.
Feature activation+0.500
For
Token For
Feature activation+0.032
example
Token example
Feature activation+0.000
what
Token what
Feature activation+1.033
âĢ
TokenâĢ
Feature activation+0.720
Ļ
TokenĻ
Feature activation+0.525
s
Tokens
Feature activation+1.640
happening
Token happening
Feature activation+1.383
with
Token with
Feature activation+1.253
the
Token the
Feature activation+0.990
DP
Token DP
Feature activation+0.480
W
TokenW
Feature activation+0.752
now
Token now
Feature activation+0.732
.
Token.
Feature activation+0.513
from
Token from
Feature activation+0.000
John
Token John
Feature activation+0.000
Oliver
Token Oliver
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.017
s
Tokens
Feature activation+1.228
show
Token show
Feature activation+0.985
,
Token,
Feature activation+0.791
which
Token which
Feature activation+0.453
lamp
Token lamp
Feature activation+0.401
oon
Tokenoon
Feature activation+0.129
exactly
Token exactly
Feature activation+0.625
?
Token?
Feature activation+0.627
She
Token She
Feature activation+0.518
âĢ
TokenâĢ
Feature activation+0.362
Ļ
TokenĻ
Feature activation+0.183
s
Tokens
Feature activation+1.351
essentially
Token essentially
Feature activation+1.236
a
Token a
Feature activation+1.095
house
Token house
Feature activation+0.746
plant
Tokenplant
Feature activation+0.487
.
Token.
Feature activation+0.493

INTERVAL 1.036 - 1.208
CONTAINS 0.040%

Norway
Token Norway
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.402
right
Token right
Feature activation+1.268
-
Token-
Feature activation+1.041
wing
Tokenwing
Feature activation+0.832
government
Token government
Feature activation+0.782
took
Token took
Feature activation+0.794
office
Token office
Feature activation+0.548
in
Token in
Feature activation+0.312
confirmed
Token confirmed
Feature activation+0.000
the
Token the
Feature activation+0.000
pastor
Token pastor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.126
arrest
Token arrest
Feature activation+0.865
.
Token.
Feature activation+0.788
Ċ
TokenĊ
Feature activation+0.135
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
It
TokenIt
Feature activation+0.608
âĢ
TokenâĢ
Feature activation+0.081
Ļ
TokenĻ
Feature activation+0.083
s
Tokens
Feature activation+1.269
a
Token a
Feature activation+1.207
very
Token very
Feature activation+1.111
challenging
Token challenging
Feature activation+0.830
collision
Token collision
Feature activation+0.505
in
Token in
Feature activation+0.306
that
Token that
Feature activation+0.253
there
Token there
Feature activation+0.066
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.511
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.025
s
Tokens
Feature activation+1.118
19
Token 19
Feature activation+0.811
th
Tokenth
Feature activation+0.730
century
Token century
Feature activation+0.563
technology
Token technology
Feature activation+0.484
being
Token being
Feature activation+0.397
but
Token but
Feature activation+0.000
Ne
Token Ne
Feature activation+0.000
uer
Tokenuer
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.134
Ļ
TokenĻ
Feature activation+0.053
s
Tokens
Feature activation+1.076
awareness
Token awareness
Feature activation+0.723
kept
Token kept
Feature activation+0.630
the
Token the
Feature activation+0.382
ball
Token ball
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 0.863 - 1.036
CONTAINS 0.078%

I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.546
take
Token take
Feature activation+0.911
back
Token back
Feature activation+0.796
anything
Token anything
Feature activation+0.708
,
Token,
Feature activation+0.452
I
Token I
Feature activation+0.104
love
Token love
Feature activation+0.000
compiling
Token compiling
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.171
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.201
own
Token own
Feature activation+0.874
decade
Token decade
Feature activation+0.523
lists
Token lists
Feature activation+0.349
,
Token,
Feature activation+0.244
we
Token we
Feature activation+0.000
felt
Token felt
Feature activation+0.000
style
Token style
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
she
Tokenshe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.012
s
Tokens
Feature activation+1.019
at
Token at
Feature activation+0.907
least
Token least
Feature activation+0.620
a
Token a
Feature activation+0.492
little
Token little
Feature activation+0.303
bit
Token bit
Feature activation+0.303
VC
TokenVC
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.364
Ļ
TokenĻ
Feature activation+0.518
t
Tokent
Feature activation+1.066
implement
Token implement
Feature activation+0.924
type
Token type
Feature activation+1.098
-
Token-
Feature activation+0.689
based
Tokenbased
Feature activation+0.707
alias
Token alias
Feature activation+0.410
analysis
Token analysis
Feature activation+0.418
ľ
Tokenľ
Feature activation+0.000
He
TokenHe
Feature activation+0.385
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.207
in
Token in
Feature activation+0.940
a
Token a
Feature activation+0.937
pretty
Token pretty
Feature activation+0.947
good
Token good
Feature activation+0.831
rhythm
Token rhythm
Feature activation+0.518
right
Token right
Feature activation+0.565

INTERVAL 0.690 - 0.863
CONTAINS 0.139%

.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.835
big
Token big
Feature activation+0.706
believers
Token believers
Feature activation+0.548
in
Token in
Feature activation+0.436
what
Token what
Feature activation+0.428
virtual
Token virtual
Feature activation+0.185
reality
Token reality
Feature activation+0.030
nothing
Token nothing
Feature activation+0.243
âĢ
TokenâĢ
Feature activation+0.227
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.122
personal
Token personal
Feature activation+0.898
about
Token about
Feature activation+0.823
this
Token this
Feature activation+0.500
.
Token.
Feature activation+0.442
I
Token I
Feature activation+0.000
hope
Token hope
Feature activation+0.000
that
Token that
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.424
haven
Token haven
Feature activation+0.247
âĢ
TokenâĢ
Feature activation+0.069
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.762
seen
Token seen
Feature activation+0.946
an
Token an
Feature activation+0.714
athlete
Token athlete
Feature activation+0.309
like
Token like
Feature activation+0.443
RG
Token RG
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.123
administration
Token administration
Feature activation+0.776
office
Token office
Feature activation+0.830
in
Token in
Feature activation+0.617
Gu
Token Gu
Feature activation+0.406
ern
Tokenern
Feature activation+0.395
sey
Tokensey
Feature activation+0.246
sets
Token sets
Feature activation+0.498
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.077
Ļ
TokenĻ
Feature activation+0.067
t
Tokent
Feature activation+0.804
want
Token want
Feature activation+1.036
to
Token to
Feature activation+0.727
answer
Token answer
Feature activation+0.772
his
Token his
Feature activation+0.761
questions
Token questions
Feature activation+0.676
,
Token,
Feature activation+0.472
he
Token he
Feature activation+0.219

INTERVAL 0.518 - 0.690
CONTAINS 0.189%

city
Token city
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Mah
Token Mah
Feature activation+0.323
oney
Tokenoney
Feature activation+0.526
explained
Token explained
Feature activation+0.531
.
Token.
Feature activation+0.426
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
Jerry
Token Jerry
Feature activation+0.000
Brown
Token Brown
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.936
administration
Token administration
Feature activation+0.627
released
Token released
Feature activation+0.426
GDP
Token GDP
Feature activation+0.169
figures
Token figures
Feature activation+0.000
in
Token in
Feature activation+0.000
June
Token June
Feature activation+0.000
Bell
Token Bell
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.984
pre
Token pre
Feature activation+0.718
-
Token-
Feature activation+0.666
orders
Tokenorders
Feature activation+0.535
soared
Token soared
Feature activation+0.358
and
Token and
Feature activation+0.090
many
Token many
Feature activation+0.000
rose
Token rose
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.228
culp
Token culp
Feature activation+0.960
ability
Tokenability
Feature activation+0.647
in
Token in
Feature activation+0.715
connection
Token connection
Feature activation+0.584
with
Token with
Feature activation+0.664
the
Token the
Feature activation+0.507
offense
Token offense
Feature activation+0.251
,
Token,
Feature activation+0.304
their
Token their
Feature activation+0.217
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.097
nothing
Token nothing
Feature activation+0.979
super
Token super
Feature activation+0.707
valuable
Token valuable
Feature activation+0.609
,
Token,
Feature activation+0.586
but
Token but
Feature activation+0.258
it
Token it
Feature activation+0.284
âĢ
TokenâĢ
Feature activation+0.150
Ļ
TokenĻ
Feature activation+0.080
s
Tokens
Feature activation+1.055

INTERVAL 0.345 - 0.518
CONTAINS 0.278%

Ŀ
TokenĿ
Feature activation+0.000
time
Token time
Feature activation+0.920
zone
Token zone
Feature activation+0.678
would
Token would
Feature activation+0.834
be
Token be
Feature activation+0.480
London
Token London
Feature activation+0.369
âĢ
TokenâĢ
Feature activation+0.168
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.132
time
Token time
Feature activation+0.852
zone
Token zone
Feature activation+0.552
s
Tokens
Feature activation+1.202
a
Token a
Feature activation+1.025
delay
Token delay
Feature activation+0.703
in
Token in
Feature activation+0.598
the
Token the
Feature activation+0.567
time
Token time
Feature activation+0.458
it
Token it
Feature activation+0.404
takes
Token takes
Feature activation+0.238
information
Token information
Feature activation+0.152
out
Token out
Feature activation+0.078
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.259
M
TokenM
Feature activation+0.191
EM
TokenEM
Feature activation+0.148
RI
TokenRI
Feature activation+0.246
also
Token also
Feature activation+0.471
cited
Token cited
Feature activation+0.365
the
Token the
Feature activation+0.174
writings
Token writings
Feature activation+0.056
of
Token of
Feature activation+0.000
Kar
Token Kar
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.300
clear
Token clear
Feature activation+0.475
that
Token that
Feature activation+0.407
this
Token this
Feature activation+0.133
will
Token will
Feature activation+0.073
not
Token not
Feature activation+0.248
be
Token be
Feature activation+0.047
good
Token good
Feature activation+0.100
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.747
said
Token said
Feature activation+0.485
.
Token.
Feature activation+0.411
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.353

INTERVAL 0.173 - 0.345
CONTAINS 0.462%

days
Token days
Feature activation+0.191
of
Token of
Feature activation+0.108
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Mad
TokenMad
Feature activation+0.572
Men
Token Men
Feature activation+0.300
âĢ
TokenâĢ
Feature activation+0.142
Ļ
TokenĻ
Feature activation+0.145
with
Token with
Feature activation+1.023
these
Token these
Feature activation+0.774
downtown
Token downtown
Feature activation+0.428
gas
Token gas
Feature activation+0.000
loading
Token loading
Feature activation+0.031
implies
Token implies
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.183
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.187
quite
Token quite
Feature activation+1.027
a
Token a
Feature activation+0.891
lot
Token lot
Feature activation+0.795
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
scenic
Token scenic
Feature activation+0.037
trail
Token trail
Feature activation+0.030
âĢ
TokenâĢ
Feature activation+0.393
Ļ
TokenĻ
Feature activation+0.259
s
Tokens
Feature activation+1.440
history
Token history
Feature activation+1.124
,
Token,
Feature activation+0.681
thanks
Token thanks
Feature activation+0.204
to
Token to
Feature activation+0.054
said
Token said
Feature activation+1.012
Bulldogs
Token Bulldogs
Feature activation+0.497
Medical
Token Medical
Feature activation+0.465
Services
Token Services
Feature activation+0.463
Manager
Token Manager
Feature activation+0.333
Chris
Token Chris
Feature activation+0.257
Bell
Token Bell
Feature activation+0.120
.
Token.
Feature activation+0.028
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.843
inex
Token inex
Feature activation+0.672
orable
Tokenorable
Feature activation+0.549
trend
Token trend
Feature activation+0.563
to
Token to
Feature activation+0.532
greater
Token greater
Feature activation+0.333
use
Token use
Feature activation+0.327
of
Token of
Feature activation+0.178
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
rob
Tokenrob
Feature activation+0.386

INTERVAL 0.000 - 0.173
CONTAINS 98.789%

home
Token home
Feature activation+0.406
to
Token to
Feature activation+0.352
perform
Token perform
Feature activation+0.275
half
Token half
Feature activation+0.168
the
Token the
Feature activation+0.072
tasks
Token tasks
Feature activation+0.143
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
office
Token office
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.000
image
Tokenimage
Feature activation+0.000
activist
Token activist
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
T
Token T
Feature activation+0.000
ress
Tokenress
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
consultant
Token consultant
Feature activation+0.000
for
Token for
Feature activation+0.000
gay
Token gay
Feature activation+0.000
men
Token men
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
killed
Token killed
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
area
Token area
Feature activation+0.000
and
Token and
Feature activation+0.000
outside
Token outside
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
fight
Token fight
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
hopeless
Token hopeless
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
devoted
Token devoted
Feature activation+0.000
to
Token to
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
tested
Token tested
Feature activation+0.000
,
Token,
Feature activation+0.000
changed
Token changed
Feature activation+0.000
performance
Token performance
Feature activation+0.000
to
Token to
Feature activation+0.000
improve
Token improve
Feature activation+0.000
results
Token results
Feature activation+0.000
.
Token.
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 5 in H1.2: (feature 20989)

TOP ACTIVATIONS
MAX = 1.726

Made
Token Made
Feature activation+1.145
to
Token to
Feature activation+0.642
hate
Token hate
Feature activation+0.834
themselves
Token themselves
Feature activation+0.518
.
Token.
Feature activation+0.404
Made
Token Made
Feature activation+1.726
to
Token to
Feature activation+1.171
wish
Token wish
Feature activation+1.251
that
Token that
Feature activation+0.781
they
Token they
Feature activation+0.557
were
Token were
Feature activation+0.390
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Change
Token Change
Feature activation+1.082
things
Token things
Feature activation+0.894
.
Token.
Feature activation+0.527
Keep
Token Keep
Feature activation+1.477
in
Token in
Feature activation+1.118
touch
Token touch
Feature activation+0.829
and
Token and
Feature activation+0.430
tell
Token tell
Feature activation+0.523
her
Token her
Feature activation+0.302
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
trial
Token trial
Feature activation+0.000
.
Token.
Feature activation+0.141
Particip
Token Particip
Feature activation+1.376
ating
Tokenating
Feature activation+1.468
required
Token required
Feature activation+1.161
surgery
Token surgery
Feature activation+0.994
and
Token and
Feature activation+0.262
about
Token about
Feature activation+0.425
12
Token 12
Feature activation+0.248
policy
Token policy
Feature activation+0.000
called
Token called
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
.
Token.
Feature activation+0.169
Federal
Token Federal
Feature activation+1.455
ism
Tokenism
Feature activation+1.004
is
Token is
Feature activation+0.802
one
Token one
Feature activation+0.347
of
Token of
Feature activation+0.208
the
Token the
Feature activation+0.121
with
Token with
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
power
Token power
Feature activation+0.000
sources
Token sources
Feature activation+0.000
.
Token.
Feature activation+0.068
Key
Token Key
Feature activation+1.445
clean
Token clean
Feature activation+1.046
energy
Token energy
Feature activation+1.006
stock
Token stock
Feature activation+0.736
indexes
Token indexes
Feature activation+0.449
rose
Token rose
Feature activation+0.459
private
Token private
Feature activation+0.000
insurance
Token insurance
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.038
Still
Token Still
Feature activation+1.440
others
Token others
Feature activation+1.147
are
Token are
Feature activation+0.796
leaving
Token leaving
Feature activation+0.604
the
Token the
Feature activation+0.458
practice
Token practice
Feature activation+0.360
else
Token else
Feature activation+0.000
can
Token can
Feature activation+0.000
repair
Token repair
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.176
Or
Token Or
Feature activation+1.438
Apple
Token Apple
Feature activation+1.050
says
Token says
Feature activation+0.744
only
Token only
Feature activation+0.548
they
Token they
Feature activation+0.447
should
Token should
Feature activation+0.401
from
Token from
Feature activation+0.317
such
Token such
Feature activation+0.402
a
Token a
Feature activation+0.346
debate
Token debate
Feature activation+0.261
.
Token.
Feature activation+0.383
There
Token There
Feature activation+1.434
are
Token are
Feature activation+1.054
other
Token other
Feature activation+0.767
points
Token points
Feature activation+0.537
worth
Token worth
Feature activation+0.419
discussing
Token discussing
Feature activation+0.211
himself
Token himself
Feature activation+0.000
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
endeavor
Token endeavor
Feature activation+0.000
.
Token.
Feature activation+0.234
Heads
Token Heads
Feature activation+1.393
will
Token will
Feature activation+1.176
need
Token need
Feature activation+0.775
to
Token to
Feature activation+0.555
roll
Token roll
Feature activation+0.389
!
Token!
Feature activation+0.138
on
Token on
Feature activation+0.000
directly
Token directly
Feature activation+0.000
to
Token to
Feature activation+0.000
councils
Token councils
Feature activation+0.000
.
Token.
Feature activation+0.000
Council
Token Council
Feature activation+1.388
s
Tokens
Feature activation+1.111
have
Token have
Feature activation+0.972
been
Token been
Feature activation+0.808
seriously
Token seriously
Feature activation+0.717
disadvantaged
Token disadvantaged
Feature activation+0.545
and
Token and
Feature activation+0.000
declining
Token declining
Feature activation+0.000
living
Token living
Feature activation+0.000
standards
Token standards
Feature activation+0.000
.
Token.
Feature activation+0.046
Public
Token Public
Feature activation+1.386
opinion
Token opinion
Feature activation+1.065
is
Token is
Feature activation+0.692
generally
Token generally
Feature activation+0.604
favorable
Token favorable
Feature activation+0.293
toward
Token toward
Feature activation+0.177
as
Token as
Feature activation+0.114
a
Token a
Feature activation+0.135
young
Token young
Feature activation+0.152
boy
Token boy
Feature activation+0.209
.
Token.
Feature activation+0.334
Very
Token Very
Feature activation+1.378
predatory
Token predatory
Feature activation+0.942
;
Token;
Feature activation+0.576
a
Token a
Feature activation+0.677
hunt
Token hunt
Feature activation+0.449
.
Token.
Feature activation+0.252
approval
Token approval
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
trial
Token trial
Feature activation+0.000
.
Token.
Feature activation+0.141
Particip
Token Particip
Feature activation+1.376
ating
Tokenating
Feature activation+1.468
required
Token required
Feature activation+1.161
surgery
Token surgery
Feature activation+0.994
and
Token and
Feature activation+0.262
about
Token about
Feature activation+0.425
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
.
Token.
Feature activation+0.075
Fear
Token Fear
Feature activation+1.375
had
Token had
Feature activation+1.221
done
Token done
Feature activation+1.116
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
owner
Token owner
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+0.000
.
Token.
Feature activation+0.021
Bell
Token Bell
Feature activation+1.300
ing
Tokening
Feature activation+1.356
cat
Tokencat
Feature activation+0.841
has
Token has
Feature activation+0.788
published
Token published
Feature activation+0.383
several
Token several
Feature activation+0.363
how
Token how
Feature activation+0.105
can
Token can
Feature activation+1.051
't
Token't
Feature activation+1.042
agree
Token agree
Feature activation+0.738
either
Token either
Feature activation+0.779
.
Token.
Feature activation+0.463
Seems
Token Seems
Feature activation+1.354
it
Token it
Feature activation+0.892
's
Token's
Feature activation+0.705
all
Token all
Feature activation+0.418
open
Token open
Feature activation+0.368
to
Token to
Feature activation+0.196
of
Token of
Feature activation+0.000
TV
Token TV
Feature activation+0.000
advertising
Token advertising
Feature activation+0.000
.
Token.
Feature activation+0.093
TV
Token TV
Feature activation+1.292
ads
Token ads
Feature activation+1.348
are
Token are
Feature activation+0.850
known
Token known
Feature activation+0.573
to
Token to
Feature activation+0.393
drive
Token drive
Feature activation+0.360
search
Token search
Feature activation+0.219
to
Token to
Feature activation+0.031
the
Token the
Feature activation+0.053
Prime
Token Prime
Feature activation+0.158
Minister
Token Minister
Feature activation+0.173
.
Token.
Feature activation+0.130
Officials
Token Officials
Feature activation+1.347
must
Token must
Feature activation+0.861
ensure
Token ensure
Feature activation+0.437
that
Token that
Feature activation+0.067
confidential
Token confidential
Feature activation+0.000
information
Token information
Feature activation+0.015
Airbus
Token Airbus
Feature activation+0.000
Helic
Token Helic
Feature activation+0.000
op
Tokenop
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
.
Token.
Feature activation+0.090
One
Token One
Feature activation+1.346
of
Token of
Feature activation+0.887
the
Token the
Feature activation+0.714
Airbus
Token Airbus
Feature activation+0.688
pilots
Token pilots
Feature activation+0.556
was
Token was
Feature activation+0.493
much
Token much
Feature activation+0.000
later
Token later
Feature activation+0.000
than
Token than
Feature activation+0.088
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.230
There
Token There
Feature activation+1.337
is
Token is
Feature activation+0.992
also
Token also
Feature activation+0.865
a
Token a
Feature activation+0.451
tradition
Token tradition
Feature activation+0.359
of
Token of
Feature activation+0.176

Top DFA by src position
MAX = 1.882

.
Token.
Feature activation+0.558
Top resid features:
Made
Token Made
Feature activation+0.102
Top resid features:
to
Token to
Feature activation+0.190
Top resid features:
hate
Token hate
Feature activation+0.145
Top resid features:
themselves
Token themselves
Feature activation+0.146
Top resid features:
.
Token.
Feature activation+1.705
Top resid features:
Made
Token Made
Feature activation+0.219
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
wish
Token wish
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.082
Top resid features:
in
Token in
Feature activation+0.096
Top resid features:
.
Token.
Feature activation+0.550
Top resid features:
Change
Token Change
Feature activation+0.192
Top resid features:
things
Token things
Feature activation+0.127
Top resid features:
.
Token.
Feature activation+1.326
Top resid features:
Keep
Token Keep
Feature activation+0.179
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
touch
Token touch
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
tell
Token tell
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation+0.152
Top resid features:
approval
Token approval
Feature activation+0.120
Top resid features:
for
Token for
Feature activation+0.157
Top resid features:
the
Token the
Feature activation+0.118
Top resid features:
trial
Token trial
Feature activation+0.135
Top resid features:
.
Token.
Feature activation+1.585
Top resid features:
Particip
Token Particip
Feature activation+0.306
Top resid features:
ating
Tokenating
Feature activation+0.131
Top resid features:
required
Token required
Feature activation+0.000
Top resid features:
surgery
Token surgery
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.060
Top resid features:
policy
Token policy
Feature activation+0.099
Top resid features:
called
Token called
Feature activation+0.147
Top resid features:
Federal
Token Federal
Feature activation+0.092
Top resid features:
ism
Tokenism
Feature activation+0.120
Top resid features:
.
Token.
Feature activation+1.760
Top resid features:
Federal
Token Federal
Feature activation+0.188
Top resid features:
ism
Tokenism
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
competitive
Token competitive
Feature activation+0.068
Top resid features:
with
Token with
Feature activation+0.179
Top resid features:
conventional
Token conventional
Feature activation+0.069
Top resid features:
power
Token power
Feature activation+0.144
Top resid features:
sources
Token sources
Feature activation+0.094
Top resid features:
.
Token.
Feature activation+1.781
Top resid features:
Key
Token Key
Feature activation+0.245
Top resid features:
clean
Token clean
Feature activation+0.000
Top resid features:
energy
Token energy
Feature activation+0.000
Top resid features:
stock
Token stock
Feature activation+0.000
Top resid features:
indexes
Token indexes
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.109
Top resid features:
private
Token private
Feature activation+0.075
Top resid features:
insurance
Token insurance
Feature activation+0.142
Top resid features:
as
Token as
Feature activation+0.200
Top resid features:
well
Token well
Feature activation+0.161
Top resid features:
.
Token.
Feature activation+1.882
Top resid features:
Still
Token Still
Feature activation+0.155
Top resid features:
others
Token others
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
leaving
Token leaving
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.090
Top resid features:
else
Token else
Feature activation+0.135
Top resid features:
can
Token can
Feature activation+0.172
Top resid features:
repair
Token repair
Feature activation+0.136
Top resid features:
it
Token it
Feature activation+0.109
Top resid features:
.
Token.
Feature activation+1.816
Top resid features:
Or
Token Or
Feature activation+0.170
Top resid features:
Apple
Token Apple
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
benefit
Token benefit
Feature activation+0.119
Top resid features:
from
Token from
Feature activation+0.121
Top resid features:
such
Token such
Feature activation+0.109
Top resid features:
a
Token a
Feature activation+0.110
Top resid features:
debate
Token debate
Feature activation+0.126
Top resid features:
.
Token.
Feature activation+1.628
Top resid features:
There
Token There
Feature activation+0.129
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
worth
Token worth
Feature activation+0.000
Top resid features:
use
Tokenuse
Feature activation+0.123
Top resid features:
himself
Token himself
Feature activation+0.097
Top resid features:
from
Token from
Feature activation+0.159
Top resid features:
this
Token this
Feature activation+0.098
Top resid features:
endeavor
Token endeavor
Feature activation+0.078
Top resid features:
.
Token.
Feature activation+1.712
Top resid features:
Heads
Token Heads
Feature activation+0.203
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
need
Token need
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
roll
Token roll
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.095
Top resid features:
on
Token on
Feature activation+0.149
Top resid features:
directly
Token directly
Feature activation+0.070
Top resid features:
to
Token to
Feature activation+0.204
Top resid features:
councils
Token councils
Feature activation+0.194
Top resid features:
.
Token.
Feature activation+1.823
Top resid features:
Council
Token Council
Feature activation+0.329
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
seriously
Token seriously
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.155
Top resid features:
and
Token and
Feature activation+0.149
Top resid features:
declining
Token declining
Feature activation+0.090
Top resid features:
living
Token living
Feature activation+0.151
Top resid features:
standards
Token standards
Feature activation+0.130
Top resid features:
.
Token.
Feature activation+1.725
Top resid features:
Public
Token Public
Feature activation+0.215
Top resid features:
opinion
Token opinion
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
generally
Token generally
Feature activation+0.000
Top resid features:
favorable
Token favorable
Feature activation+0.000
Top resid features:
especially
Token especially
Feature activation+0.094
Top resid features:
as
Token as
Feature activation+0.138
Top resid features:
a
Token a
Feature activation+0.098
Top resid features:
young
Token young
Feature activation+0.060
Top resid features:
boy
Token boy
Feature activation+0.098
Top resid features:
.
Token.
Feature activation+1.708
Top resid features:
Very
Token Very
Feature activation+0.118
Top resid features:
predatory
Token predatory
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
hunt
Token hunt
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation+0.153
Top resid features:
approval
Token approval
Feature activation+0.147
Top resid features:
for
Token for
Feature activation+0.177
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
trial
Token trial
Feature activation+0.147
Top resid features:
.
Token.
Feature activation+1.739
Top resid features:
Particip
Token Particip
Feature activation+0.102
Top resid features:
ating
Tokenating
Feature activation+0.000
Top resid features:
required
Token required
Feature activation+0.000
Top resid features:
surgery
Token surgery
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
put
Token put
Feature activation+0.109
Top resid features:
it
Token it
Feature activation+0.097
Top resid features:
to
Token to
Feature activation+0.143
Top resid features:
a
Token a
Feature activation+0.119
Top resid features:
vote
Token vote
Feature activation+0.141
Top resid features:
.
Token.
Feature activation+1.792
Top resid features:
Fear
Token Fear
Feature activation+0.205
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.082
Top resid features:
date
Token date
Feature activation+0.067
Top resid features:
of
Token of
Feature activation+0.091
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
attack
Token attack
Feature activation+0.114
Top resid features:
.
Token.
Feature activation+1.579
Top resid features:
Bell
Token Bell
Feature activation+0.333
Top resid features:
ing
Tokening
Feature activation+0.150
Top resid features:
cat
Tokencat
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
published
Token published
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.120
Top resid features:
can
Token can
Feature activation+0.161
Top resid features:
't
Token't
Feature activation+0.137
Top resid features:
agree
Token agree
Feature activation+0.165
Top resid features:
either
Token either
Feature activation+0.090
Top resid features:
.
Token.
Feature activation+1.336
Top resid features:
Seems
Token Seems
Feature activation+0.118
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.118
Top resid features:
lot
Token lot
Feature activation+0.108
Top resid features:
of
Token of
Feature activation+0.125
Top resid features:
TV
Token TV
Feature activation+0.166
Top resid features:
advertising
Token advertising
Feature activation+0.191
Top resid features:
.
Token.
Feature activation+1.653
Top resid features:
TV
Token TV
Feature activation+0.225
Top resid features:
ads
Token ads
Feature activation+0.168
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
known
Token known
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
directly
Token directly
Feature activation+0.037
Top resid features:
to
Token to
Feature activation+0.094
Top resid features:
the
Token the
Feature activation+0.064
Top resid features:
Prime
Token Prime
Feature activation+0.072
Top resid features:
Minister
Token Minister
Feature activation+0.079
Top resid features:
.
Token.
Feature activation+1.607
Top resid features:
Officials
Token Officials
Feature activation+0.094
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
ensure
Token ensure
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
confidential
Token confidential
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.192
Top resid features:
Airbus
Token Airbus
Feature activation+0.128
Top resid features:
Helic
Token Helic
Feature activation+0.094
Top resid features:
op
Tokenop
Feature activation+0.064
Top resid features:
ters
Tokenters
Feature activation+0.194
Top resid features:
.
Token.
Feature activation+1.816
Top resid features:
One
Token One
Feature activation+0.231
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Airbus
Token Airbus
Feature activation+0.000
Top resid features:
pilots
Token pilots
Feature activation+0.000
Top resid features:
appears
Token appears
Feature activation+0.143
Top resid features:
much
Token much
Feature activation+0.110
Top resid features:
later
Token later
Feature activation+0.120
Top resid features:
than
Token than
Feature activation+0.147
Top resid features:
that
Token that
Feature activation+0.193
Top resid features:
.
Token.
Feature activation+1.700
Top resid features:
There
Token There
Feature activation+0.115
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
tradition
Token tradition
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.15

Head 2: 0.17

Head 3: 0.10

Head 4: 0.12

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.06

Head 9: 0.06

Head 10: 0.14

Head 11: 0.05

Positive logits

however1.16

meanwhile0.94

therefore0.86

Saunders0.84

furthermore0.84

---------0.83

anwhile0.79

though0.79

Shuttle0.79

Nurse0.76

haw0.75

moreover0.75

Cosponsors0.74

Hitchcock0.74

utenberg0.73

Hague0.73

Rasmussen0.72

Muse0.71

Hawks0.69

miah0.69

Negative logits

$.-0.80

".[-0.80

],"-0.77

".-0.77

'.-0.76

behalf-0.75

tains-0.75

)),-0.73

guiActiveUnfocused-0.73

)).-0.73

)",-0.72

��-0.72

fame-0.72

vagina-0.71

yond-0.71

existent-0.70

thereof-0.70

tnc-0.69

SPONSORED-0.69

*.-0.68

INTERVAL 1.553 - 1.726
CONTAINS 0.000%

Made
Token Made
Feature activation+1.145
to
Token to
Feature activation+0.642
hate
Token hate
Feature activation+0.834
themselves
Token themselves
Feature activation+0.518
.
Token.
Feature activation+0.404
Made
Token Made
Feature activation+1.726
to
Token to
Feature activation+1.171
wish
Token wish
Feature activation+1.251
that
Token that
Feature activation+0.781
they
Token they
Feature activation+0.557
were
Token were
Feature activation+0.390

INTERVAL 1.381 - 1.553
CONTAINS 0.001%

else
Token else
Feature activation+0.000
can
Token can
Feature activation+0.000
repair
Token repair
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.176
Or
Token Or
Feature activation+1.438
Apple
Token Apple
Feature activation+1.050
says
Token says
Feature activation+0.744
only
Token only
Feature activation+0.548
they
Token they
Feature activation+0.447
should
Token should
Feature activation+0.401
and
Token and
Feature activation+0.000
declining
Token declining
Feature activation+0.000
living
Token living
Feature activation+0.000
standards
Token standards
Feature activation+0.000
.
Token.
Feature activation+0.046
Public
Token Public
Feature activation+1.386
opinion
Token opinion
Feature activation+1.065
is
Token is
Feature activation+0.692
generally
Token generally
Feature activation+0.604
favorable
Token favorable
Feature activation+0.293
toward
Token toward
Feature activation+0.177
private
Token private
Feature activation+0.000
insurance
Token insurance
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.038
Still
Token Still
Feature activation+1.440
others
Token others
Feature activation+1.147
are
Token are
Feature activation+0.796
leaving
Token leaving
Feature activation+0.604
the
Token the
Feature activation+0.458
practice
Token practice
Feature activation+0.360
policy
Token policy
Feature activation+0.000
called
Token called
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
.
Token.
Feature activation+0.169
Federal
Token Federal
Feature activation+1.455
ism
Tokenism
Feature activation+1.004
is
Token is
Feature activation+0.802
one
Token one
Feature activation+0.347
of
Token of
Feature activation+0.208
the
Token the
Feature activation+0.121
on
Token on
Feature activation+0.000
directly
Token directly
Feature activation+0.000
to
Token to
Feature activation+0.000
councils
Token councils
Feature activation+0.000
.
Token.
Feature activation+0.000
Council
Token Council
Feature activation+1.388
s
Tokens
Feature activation+1.111
have
Token have
Feature activation+0.972
been
Token been
Feature activation+0.808
seriously
Token seriously
Feature activation+0.717
disadvantaged
Token disadvantaged
Feature activation+0.545

INTERVAL 1.208 - 1.381
CONTAINS 0.010%

as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.181
He
Token He
Feature activation+1.263
would
Token would
Feature activation+1.213
abhor
Token abhor
Feature activation+0.967
the
Token the
Feature activation+0.655
physical
Token physical
Feature activation+0.657
union
Token union
Feature activation+0.532
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
religious
Token religious
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+1.241
's
Token's
Feature activation+0.871
own
Token own
Feature activation+0.826
views
Token views
Feature activation+0.721
should
Token should
Feature activation+0.753
not
Token not
Feature activation+0.573
ambush
Token ambush
Feature activation+0.000
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.078
evening
Token evening
Feature activation+0.140
.
Token.
Feature activation+0.268
Meanwhile
Token Meanwhile
Feature activation+1.310
,
Token,
Feature activation+0.716
Israeli
Token Israeli
Feature activation+0.735
top
Token top
Feature activation+0.673
brass
Token brass
Feature activation+0.424
convened
Token convened
Feature activation+0.428
heastern
Tokenheastern
Feature activation+0.000
states
Token states
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.187
Home
Token Home
Feature activation+1.224
heating
Token heating
Feature activation+1.191
oil
Token oil
Feature activation+0.997
in
Token in
Feature activation+0.720
Maine
Token Maine
Feature activation+0.656
is
Token is
Feature activation+0.396
could
Token could
Feature activation+0.000
come
Token come
Feature activation+0.000
up
Token up
Feature activation+0.000
with
Token with
Feature activation+0.000
.
Token.
Feature activation+0.166
Including
Token Including
Feature activation+1.210
âĢ¦
TokenâĢ¦
Feature activation+0.736
(
Token(
Feature activation+0.399
d
Tokend
Feature activation+0.479
rum
Tokenrum
Feature activation+0.288
roll
Token roll
Feature activation+0.237

INTERVAL 1.036 - 1.208
CONTAINS 0.042%

the
Token the
Feature activation+0.000
door
Token door
Feature activation+0.021
knock
Token knock
Feature activation+0.122
ers
Tokeners
Feature activation+0.062
.
Token.
Feature activation+0.081
Pull
Token Pull
Feature activation+1.049
down
Token down
Feature activation+1.037
the
Token the
Feature activation+0.648
shut
Token shut
Feature activation+0.721
ters
Tokenters
Feature activation+0.520
.
Token.
Feature activation+0.290
up
Token up
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
.
Token.
Feature activation+0.068
Tal
Token Tal
Feature activation+1.125
ley
Tokenley
Feature activation+1.116
Mae
Token Mae
Feature activation+0.724
brings
Token brings
Feature activation+0.785
the
Token the
Feature activation+0.448
"
Token "
Feature activation+0.270
declining
Token declining
Feature activation+0.000
living
Token living
Feature activation+0.000
standards
Token standards
Feature activation+0.000
.
Token.
Feature activation+0.046
Public
Token Public
Feature activation+1.386
opinion
Token opinion
Feature activation+1.065
is
Token is
Feature activation+0.692
generally
Token generally
Feature activation+0.604
favorable
Token favorable
Feature activation+0.293
toward
Token toward
Feature activation+0.177
greater
Token greater
Feature activation+0.140
el
Tokenel
Feature activation+0.000
blue
Token blue
Feature activation+0.000
or
Token or
Feature activation+0.000
mint
Token mint
Feature activation+0.000
.
Token.
Feature activation+0.025
For
Token For
Feature activation+1.036
condition
Token condition
Feature activation+0.955
er
Tokener
Feature activation+0.634
,
Token,
Feature activation+0.273
almost
Token almost
Feature activation+0.479
any
Token any
Feature activation+0.187
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
security
Token security
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.067
A
Token A
Feature activation+1.148
number
Token number
Feature activation+1.039
of
Token of
Feature activation+0.643
International
Token International
Feature activation+0.665
Organization
Token Organization
Feature activation+0.618
for
Token for
Feature activation+0.217

INTERVAL 0.863 - 1.036
CONTAINS 0.097%

have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.961
of
Token of
Feature activation+0.791
those
Token those
Feature activation+0.550
are
Token are
Feature activation+0.630
tough
Token tough
Feature activation+0.520
decisions
Token decisions
Feature activation+0.402
known
Token known
Feature activation+0.000
to
Token to
Feature activation+0.000
man
Token man
Feature activation+0.000
.
Token.
Feature activation+0.184
Over
Token Over
Feature activation+1.023
many
Token many
Feature activation+0.865
years
Token years
Feature activation+0.802
,
Token,
Feature activation+0.227
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
Great
Token Great
Feature activation+0.000
Recession
Token Recession
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.899
Republican
Token Republican
Feature activation+0.902
Party
Token Party
Feature activation+0.995
has
Token has
Feature activation+0.717
blocked
Token blocked
Feature activation+0.398
any
Token any
Feature activation+0.421
taxation
Token taxation
Feature activation+0.398
is
Token is
Feature activation+0.000
unbelievably
Token unbelievably
Feature activation+0.000
untrue
Token untrue
Feature activation+0.000
.
Token.
Feature activation+0.000
Ass
Token Ass
Feature activation+0.888
essing
Tokenessing
Feature activation+0.946
custody
Token custody
Feature activation+0.673
battles
Token battles
Feature activation+0.733
on
Token on
Feature activation+0.651
a
Token a
Feature activation+0.515
case
Token case
Feature activation+0.475
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Near
Token Near
Feature activation+1.146
the
Token the
Feature activation+0.699
city
Token city
Feature activation+0.828
limits
Token limits
Feature activation+0.945
,
Token,
Feature activation+0.463
a
Token a
Feature activation+0.414
tall
Token tall
Feature activation+0.437
,
Token,
Feature activation+0.226
bull
Token bull
Feature activation+0.157

INTERVAL 0.690 - 0.863
CONTAINS 0.161%

comment
Token comment
Feature activation+0.000
.
Token.
Feature activation+0.121
In
Token In
Feature activation+1.062
a
Token a
Feature activation+0.912
press
Token press
Feature activation+0.868
release
Token release
Feature activation+0.692
,
Token,
Feature activation+0.262
it
Token it
Feature activation+0.230
wrote
Token wrote
Feature activation+0.041
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
come
Token come
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
.
Token.
Feature activation+0.000
None
Token None
Feature activation+0.855
of
Token of
Feature activation+0.491
that
Token that
Feature activation+0.370
would
Token would
Feature activation+0.491
have
Token have
Feature activation+0.342
happened
Token happened
Feature activation+0.314
season
Token season
Feature activation+0.000
it
Token it
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
volumes
Token volumes
Feature activation+0.000
.
Token.
Feature activation+0.076
But
Token But
Feature activation+0.755
I
Token I
Feature activation+0.361
think
Token think
Feature activation+0.125
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
done
Token done
Feature activation+0.000
the
Token the
Feature activation+0.000
Marvel
Token Marvel
Feature activation+0.000
Universe
Token Universe
Feature activation+0.000
.
Token.
Feature activation+0.000
Iron
Token Iron
Feature activation+0.792
Man
Token Man
Feature activation+0.754
,
Token,
Feature activation+0.119
genius
Token genius
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
solvent
Token solvent
Feature activation+0.000
are
Token are
Feature activation+0.000
produced
Token produced
Feature activation+0.000
.
Token.
Feature activation+0.132
Polar
Token Polar
Feature activation+1.129
compounds
Token compounds
Feature activation+0.828
that
Token that
Feature activation+0.300
are
Token are
Feature activation+0.123
deposited
Token deposited
Feature activation+0.071
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.518 - 0.690
CONTAINS 0.238%

till
Token till
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.720
unin
Token unin
Feature activation+0.762
hab
Tokenhab
Feature activation+0.541
ited
Tokenited
Feature activation+0.618
island
Token island
Feature activation+0.653
is
Token is
Feature activation+0.358
rich
Token rich
Feature activation+0.217
in
Token in
Feature activation+0.068
r
Token r
Feature activation+0.000
ipples
Tokenipples
Feature activation+0.000
and
Token and
Feature activation+0.000
waves
Token waves
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.665
as
Token as
Feature activation+0.325
a
Token a
Feature activation+0.068
navig
Token navig
Feature activation+0.363
able
Tokenable
Feature activation+0.000
water
Token water
Feature activation+0.000
.
Token.
Feature activation+0.021
A
Token A
Feature activation+1.157
Senate
Token Senate
Feature activation+1.099
working
Token working
Feature activation+0.920
group
Token group
Feature activation+0.990
continues
Token continues
Feature activation+0.690
to
Token to
Feature activation+0.237
limp
Token limp
Feature activation+0.122
forward
Token forward
Feature activation+0.086
on
Token on
Feature activation+0.000
complex
Token complex
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.802
Cas
Token Cas
Feature activation+0.677
ley
Tokenley
Feature activation+0.714
declared
Token declared
Feature activation+0.704
himself
Token himself
Feature activation+0.583
"
Token "
Feature activation+0.440
Prince
TokenPrince
Feature activation+0.344
",
Token",
Feature activation+0.078
the
Token the
Feature activation+0.119
administration
Token administration
Feature activation+0.180
way
Token way
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
operation
Token operation
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.662
fighters
Token fighters
Feature activation+0.437
began
Token began
Feature activation+0.444
to
Token to
Feature activation+0.000
train
Token train
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.345 - 0.518
CONTAINS 0.395%

specific
Token specific
Feature activation+0.000
points
Token points
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.224
good
Token good
Feature activation+0.496
news
Token news
Feature activation+0.465
:
Token:
Feature activation+0.262
with
Token with
Feature activation+0.375
a
Token a
Feature activation+0.386
few
Token few
Feature activation+0.430
plan
Token plan
Feature activation+0.360
Pyrrha
Token Pyrrha
Feature activation+0.307
nodded
Token nodded
Feature activation+0.306
.
Token.
Feature activation+0.124
"
Token "
Feature activation+0.750
Complete
TokenComplete
Feature activation+0.449
ly
Tokenly
Feature activation+0.447
?"
Token?"
Feature activation+0.287
Pyrrha
Token Pyrrha
Feature activation+0.505
nodded
Token nodded
Feature activation+0.238
again
Token again
Feature activation+0.111
.
Token.
Feature activation+0.000
it
Token it
Feature activation+0.000
really
Token really
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.362
didn
Token didn
Feature activation+0.362
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.090
plan
Token plan
Feature activation+0.206
to
Token to
Feature activation+0.219
ins
Tokenins
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.656
.
Token.
Feature activation+0.083
See
Token See
Feature activation+0.538
our
Token our
Feature activation+0.443
website
Token website
Feature activation+0.364
www
Token www
Feature activation+0.190
.
Token.
Feature activation+0.000
in
Tokenin
Feature activation+0.000
4
Token4
Feature activation+0.000
an
Token an
Feature activation+0.000
overall
Token overall
Feature activation+0.000
view
Token view
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.953
âĢ
TokenâĢ
Feature activation+0.395
Ļ
TokenĻ
Feature activation+0.319
ll
Tokenll
Feature activation+0.433
break
Token break
Feature activation+0.657
it
Token it
Feature activation+0.419
into
Token into
Feature activation+0.400

INTERVAL 0.173 - 0.345
CONTAINS 0.700%

uge
Tokenuge
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
deck
Token deck
Feature activation+0.000
.
Token.
Feature activation+0.176
The
Token The
Feature activation+0.922
5
Token 5
Feature activation+0.828
cost
Token cost
Feature activation+0.687
5
Token 5
Feature activation+0.517
attack
Token attack
Feature activation+0.427
fled
Token fled
Feature activation+0.000
.
Token.
Feature activation+0.077
At
Token At
Feature activation+0.970
least
Token least
Feature activation+0.894
one
Token one
Feature activation+0.369
of
Token of
Feature activation+0.267
the
Token the
Feature activation+0.035
victims
Token victims
Feature activation+0.184
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
major
Token major
Feature activation+0.000
league
Token league
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.338
while
Token while
Feature activation+0.056
organizations
Token organizations
Feature activation+0.503
desperate
Token desperate
Feature activation+0.304
for
Token for
Feature activation+0.177
near
Token near
Feature activation+0.184
racial
Token racial
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Building
TokenBuilding
Feature activation+0.000
a
Token a
Feature activation+0.185
startup
Token startup
Feature activation+0.013
is
Token is
Feature activation+0.116
marathon
Token marathon
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
and
Token and
Feature activation+0.000
Oakland
Token Oakland
Feature activation+0.000
,
Token,
Feature activation+0.000
California
Token California
Feature activation+0.076
.
Token.
Feature activation+0.216
A
Token A
Feature activation+1.160
part
Token part
Feature activation+0.919
of
Token of
Feature activation+0.573
the
Token the
Feature activation+0.402
anti
Token anti
Feature activation+0.404

INTERVAL 0.000 - 0.173
CONTAINS 98.356%

tr
Token tr
Feature activation+0.000
uces
Tokenuces
Feature activation+0.000
,
Token,
Feature activation+0.000
Hamas
Token Hamas
Feature activation+0.000
has
Token has
Feature activation+0.000
observed
Token observed
Feature activation+0.000
the
Token the
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
.
Token.
Feature activation+0.120
On
Token On
Feature activation+1.113
the
Token the
Feature activation+0.908
fire
Token fire
Feature activation+0.000
up
Token up
Feature activation+0.000
that
Token that
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
Matrix
Token Matrix
Feature activation+0.000
as
Token as
Feature activation+0.000
reality
Token reality
Feature activation+0.000
is
Token is
Feature activation+0.000
scoff
Token scoff
Feature activation+0.000
.
Token.
Feature activation+0.000
99
Token99
Feature activation+0.000
âĤ¬
TokenâĤ¬
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Remember
TokenRemember
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
either
Token either
Feature activation+0.000
way
Token way
Feature activation+0.000
people
Token people
Feature activation+0.000
ruin
Token ruin
Feature activation+0.000
everything
Token everything
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Phillip
Token Phillip
Feature activation+0.000
Van
Token Van
Feature activation+0.000
De
Token De
Feature activation+0.000
Kamp
Token Kamp
Feature activation+0.000
(@
Token (@
Feature activation+0.000
Major
TokenMajor
Feature activation+0.000
Ph
TokenPh
Feature activation+0.000
THE
Token THE
Feature activation+0.000
READ
Token READ
Feature activation+0.000
ING
TokenING
Feature activation+0.000
RO
Token RO
Feature activation+0.000
OM
TokenOM
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FOR
TokenFOR
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
INFORMATION
Token INFORMATION
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
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+0.107
<|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+0.107
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+0.107
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.254
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
a
Token a
Feature 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
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.254
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.107
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.254
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.107
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.254
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
a
Token a
Feature 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
K
TokenK
Feature activation+0.254
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
a
Token a
Feature 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
A
Token A
Feature activation+0.360
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
atre
Tokenatre
Feature activation+0.237
,
Token,
Feature activation+0.000
a
Token a
Feature 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
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.107
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.254
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.360
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.107
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.254
.
Token.
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+0.107
headed
Token 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+0.107
headed
Token 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 H1.2: (feature 7092)

TOP ACTIVATIONS
MAX = 1.148

town
Token town
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bet
TokenBet
Feature activation+0.347
ty
Tokenty
Feature activation+1.148
Martinez
Token Martinez
Feature activation+0.727
said
Token said
Feature activation+0.442
her
Token her
Feature activation+0.460
daughter
Token daughter
Feature activation+0.721
had
Token had
Feature activation+0.194
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.019
Ly
TokenLy
Feature activation+0.498
ne
Tokenne
Feature activation+1.113
Mor
Token Mor
Feature activation+0.695
iss
Tokeniss
Feature activation+0.837
ette
Tokenette
Feature activation+0.777
,
Token,
Feature activation+0.426
a
Token a
Feature activation+0.312
appearance
Token appearance
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.048
Sc
TokenSc
Feature activation+0.455
rol
Tokenrol
Feature activation+1.084
l
Token l
Feature activation+0.723
down
Token down
Feature activation+0.641
for
Token for
Feature activation+0.672
video
Token video
Feature activation+0.520
Ċ
TokenĊ
Feature activation+0.081
control
Token control
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.465
ala
Tokenala
Feature activation+1.078
began
Token began
Feature activation+0.466
developing
Token developing
Feature activation+0.497
ha
Token ha
Feature activation+0.380
ptic
Tokenptic
Feature activation+0.469
technology
Token technology
Feature activation+0.413
cases
Token cases
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SP
TokenSP
Feature activation+0.442
C
TokenC
Feature activation+1.070
spokesman
Token spokesman
Feature activation+0.683
Sun
Token Sun
Feature activation+0.478
Jung
Token Jung
Feature activation+0.371
ong
Tokenong
Feature activation+0.388
said
Token said
Feature activation+0.268
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.024
[
Token[
Feature activation+0.168
B
TokenB
Feature activation+0.343
yr
Tokenyr
Feature activation+1.053
um
Tokenum
Feature activation+0.837
photo
Token photo
Feature activation+0.245
credit
Token credit
Feature activation+0.421
:
Token:
Feature activation+0.205
Anne
Token Anne
Feature activation+0.159
assassin
Token assassin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.316
inger
Tokeninger
Feature activation+1.046
-
Token-
Feature activation+0.672
actor
Tokenactor
Feature activation+0.682
George
Token George
Feature activation+0.359
Lewis
Token Lewis
Feature activation+0.259
Jr
Token Jr
Feature activation+0.294
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.478
rock
Tokenrock
Feature activation+1.045
âĢ
TokenâĢ
Feature activation+0.405
Ļ
TokenĻ
Feature activation+0.474
s
Tokens
Feature activation+0.664
speech
Token speech
Feature activation+0.409
does
Token does
Feature activation+0.300
reach
Tokenreach
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.104
Mc
TokenMc
Feature activation+0.425
Cr
TokenCr
Feature activation+1.040
ory
Tokenory
Feature activation+1.017
's
Token's
Feature activation+0.854
lawyers
Token lawyers
Feature activation+0.649
also
Token also
Feature activation+0.641
say
Token say
Feature activation+0.467
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.127
Though
TokenThough
Feature activation+0.303
North
Token North
Feature activation+0.913
Korean
Token Korean
Feature activation+1.035
artillery
Token artillery
Feature activation+0.429
âĢĵ
Token âĢĵ
Feature activation+0.450
both
Token both
Feature activation+0.353
on
Token on
Feature activation+0.221
other
Token other
Feature activation+0.295
downtown
Token downtown
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Step
TokenStep
Feature activation+0.414
han
Tokenhan
Feature activation+1.032
ie
Tokenie
Feature activation+1.013
Vand
Token Vand
Feature activation+0.511
ep
Tokenep
Feature activation+0.686
ut
Tokenut
Feature activation+0.460
te
Tokente
Feature activation+0.502
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.104
Mc
TokenMc
Feature activation+0.425
Cr
TokenCr
Feature activation+1.040
ory
Tokenory
Feature activation+1.017
's
Token's
Feature activation+0.854
lawyers
Token lawyers
Feature activation+0.649
also
Token also
Feature activation+0.641
say
Token say
Feature activation+0.467
there
Token there
Feature activation+0.202
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Step
TokenStep
Feature activation+0.414
han
Tokenhan
Feature activation+1.032
ie
Tokenie
Feature activation+1.013
Vand
Token Vand
Feature activation+0.511
ep
Tokenep
Feature activation+0.686
ut
Tokenut
Feature activation+0.460
te
Tokente
Feature activation+0.502
,
Token,
Feature activation+0.375
angers
Tokenangers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.260
angers
Tokenangers
Feature activation+1.009
were
Token were
Feature activation+0.537
small
Token small
Feature activation+0.317
tubes
Token tubes
Feature activation+0.501
of
Token of
Feature activation+0.252
gun
Token gun
Feature activation+0.321
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.004
P
TokenP
Feature activation+0.361
ray
Tokenray
Feature activation+0.995
ing
Tokening
Feature activation+0.734
For
Token For
Feature activation+0.540
my
Token my
Feature activation+0.511
lil
Token lil
Feature activation+0.401
cousin
Token cousin
Feature activation+0.438
drug
Token drug
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Gear
TokenGear
Feature activation+0.474
y
Tokeny
Feature activation+0.993
found
Token found
Feature activation+0.669
big
Token big
Feature activation+0.582
pharmaceutical
Token pharmaceutical
Feature activation+0.473
s
Tokens
Feature activation+0.506
gave
Token gave
Feature activation+0.338
kids
Token kids
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mc
TokenMc
Feature activation+0.389
Donald
TokenDonald
Feature activation+0.986
's
Token's
Feature activation+0.769
and
Token and
Feature activation+0.641
the
Token the
Feature activation+0.550
restaurant
Token restaurant
Feature activation+0.439
industry
Token industry
Feature activation+0.453
it
Token it
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.089
B
TokenB
Feature activation+0.534
arr
Tokenarr
Feature activation+0.981
was
Token was
Feature activation+0.550
the
Token the
Feature activation+0.449
Libertarian
Token Libertarian
Feature activation+0.258
Party
Token Party
Feature activation+0.281
's
Token's
Feature activation+0.206
scheduled
Token scheduled
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.120
Getting
TokenGetting
Feature activation+0.463
back
Token back
Feature activation+0.979
to
Token to
Feature activation+0.684
normal
Token normal
Feature activation+0.578
Ċ
TokenĊ
Feature activation+0.304
Ċ
TokenĊ
Feature activation+0.335
If
TokenIf
Feature activation+0.304
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Christ
TokenChrist
Feature activation+0.272
ine
Tokenine
Feature activation+0.978
El
Token El
Feature activation+0.758
-
Token-
Feature activation+0.762
K
TokenK
Feature activation+0.466
hour
Tokenhour
Feature activation+0.868
y
Tokeny
Feature activation+0.760

Top DFA by src position
MAX = 0.630

of
Token of
Feature activation+0.034
Top resid features:
town
Token town
Feature activation+0.031
Top resid features:
."
Token."
Feature activation+0.187
Top resid features:
Ċ
TokenĊ
Feature activation+0.454
Top resid features:
Ċ
TokenĊ
Feature activation+0.463
Top resid features:
Bet
TokenBet
Feature activation+0.528
Top resid features:
ty
Tokenty
Feature activation+0.068
Top resid features:
Martinez
Token Martinez
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
daughter
Token daughter
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.031
Top resid features:
yet
Token yet
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.174
Top resid features:
Ċ
TokenĊ
Feature activation+0.405
Top resid features:
Ċ
TokenĊ
Feature activation+0.391
Top resid features:
Ly
TokenLy
Feature activation+0.535
Top resid features:
ne
Tokenne
Feature activation+0.125
Top resid features:
Mor
Token Mor
Feature activation+0.000
Top resid features:
iss
Tokeniss
Feature activation+0.000
Top resid features:
ette
Tokenette
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.044
Top resid features:
appearance
Token appearance
Feature activation+0.057
Top resid features:
.
Token.
Feature activation+0.172
Top resid features:
Ċ
TokenĊ
Feature activation+0.428
Top resid features:
Ċ
TokenĊ
Feature activation+0.367
Top resid features:
Sc
TokenSc
Feature activation+0.467
Top resid features:
rol
Tokenrol
Feature activation+0.179
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
video
Token video
Feature activation+0.000
Top resid features:
gesture
Token gesture
Feature activation+0.060
Top resid features:
control
Token control
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.171
Top resid features:
Ċ
TokenĊ
Feature activation+0.396
Top resid features:
Ċ
TokenĊ
Feature activation+0.379
Top resid features:
B
TokenB
Feature activation+0.616
Top resid features:
ala
Tokenala
Feature activation+0.085
Top resid features:
began
Token began
Feature activation+0.000
Top resid features:
developing
Token developing
Feature activation+0.000
Top resid features:
ha
Token ha
Feature activation+0.000
Top resid features:
ptic
Tokenptic
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.053
Top resid features:
environmental
Token environmental
Feature activation+0.019
Top resid features:
cases
Token cases
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.192
Top resid features:
Ċ
TokenĊ
Feature activation+0.454
Top resid features:
Ċ
TokenĊ
Feature activation+0.457
Top resid features:
SP
TokenSP
Feature activation+0.454
Top resid features:
C
TokenC
Feature activation+0.066
Top resid features:
spokesman
Token spokesman
Feature activation+0.000
Top resid features:
Sun
Token Sun
Feature activation+0.000
Top resid features:
Jung
Token Jung
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ŀ
TokenĿ
Feature activation+0.063
Top resid features:
Ċ
TokenĊ
Feature activation+0.412
Top resid features:
Ċ
TokenĊ
Feature activation+0.387
Top resid features:
[
Token[
Feature activation+0.050
Top resid features:
B
TokenB
Feature activation+0.555
Top resid features:
yr
Tokenyr
Feature activation+0.096
Top resid features:
um
Tokenum
Feature activation+0.000
Top resid features:
photo
Token photo
Feature activation+0.000
Top resid features:
credit
Token credit
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.013
Top resid features:
like
Tokenlike
Feature activation+0.032
Top resid features:
robot
Token robot
Feature activation+0.010
Top resid features:
assassin
Token assassin
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.198
Top resid features:
Ċ
TokenĊ
Feature activation+0.446
Top resid features:
Ċ
TokenĊ
Feature activation+0.407
Top resid features:
S
TokenS
Feature activation+0.241
Top resid features:
inger
Tokeninger
Feature activation+0.155
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
actor
Tokenactor
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.045
Top resid features:
level
Token level
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.204
Top resid features:
Ċ
TokenĊ
Feature activation+0.436
Top resid features:
Ċ
TokenĊ
Feature activation+0.424
Top resid features:
B
TokenB
Feature activation+0.493
Top resid features:
rock
Tokenrock
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
speech
Token speech
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
blatant
Token blatant
Feature activation+0.025
Top resid features:
over
Token over
Feature activation+0.032
Top resid features:
reach
Tokenreach
Feature activation+0.046
Top resid features:
."
Token."
Feature activation+0.137
Top resid features:
Ċ
TokenĊ
Feature activation+0.481
Top resid features:
Ċ
TokenĊ
Feature activation+0.470
Top resid features:
Mc
TokenMc
Feature activation+0.419
Top resid features:
Cr
TokenCr
Feature activation+0.103
Top resid features:
ory
Tokenory
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
North
Token North
Feature activation+0.021
Top resid features:
Korean
Token Korean
Feature activation+0.040
Top resid features:
military
Token military
Feature activation+0.005
Top resid features:
facility
Token facility
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.284
Top resid features:
Ċ
TokenĊ
Feature activation+0.431
Top resid features:
Ċ
TokenĊ
Feature activation+0.370
Top resid features:
Though
TokenThough
Feature activation+0.211
Top resid features:
North
Token North
Feature activation+0.175
Top resid features:
Korean
Token Korean
Feature activation+0.052
Top resid features:
artillery
Token artillery
Feature activation+0.000
Top resid features:
bring
Token bring
Feature activation+0.018
Top resid features:
downtown
Token downtown
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.179
Top resid features:
Ċ
TokenĊ
Feature activation+0.446
Top resid features:
Ċ
TokenĊ
Feature activation+0.452
Top resid features:
Step
TokenStep
Feature activation+0.525
Top resid features:
han
Tokenhan
Feature activation+0.091
Top resid features:
ie
Tokenie
Feature activation+0.000
Top resid features:
Vand
Token Vand
Feature activation+0.000
Top resid features:
ep
Tokenep
Feature activation+0.000
Top resid features:
ut
Tokenut
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
blatant
Token blatant
Feature activation+0.016
Top resid features:
over
Token over
Feature activation+0.025
Top resid features:
reach
Tokenreach
Feature activation+0.043
Top resid features:
."
Token."
Feature activation+0.147
Top resid features:
Ċ
TokenĊ
Feature activation+0.422
Top resid features:
Ċ
TokenĊ
Feature activation+0.399
Top resid features:
Mc
TokenMc
Feature activation+0.299
Top resid features:
Cr
TokenCr
Feature activation+0.295
Top resid features:
ory
Tokenory
Feature activation-0.018
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
bring
Token bring
Feature activation+0.016
Top resid features:
downtown
Token downtown
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.163
Top resid features:
Ċ
TokenĊ
Feature activation+0.382
Top resid features:
Ċ
TokenĊ
Feature activation+0.366
Top resid features:
Step
TokenStep
Feature activation+0.418
Top resid features:
han
Tokenhan
Feature activation+0.180
Top resid features:
ie
Tokenie
Feature activation+0.134
Top resid features:
Vand
Token Vand
Feature activation+0.000
Top resid features:
ep
Tokenep
Feature activation+0.000
Top resid features:
ut
Tokenut
Feature activation+0.000
Top resid features:
b
Token b
Feature activation+0.044
Top resid features:
angers
Tokenangers
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.188
Top resid features:
Ċ
TokenĊ
Feature activation+0.405
Top resid features:
Ċ
TokenĊ
Feature activation+0.400
Top resid features:
B
TokenB
Feature activation+0.600
Top resid features:
angers
Tokenangers
Feature activation+0.125
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
tubes
Token tubes
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
account
Token account
Feature activation+0.017
Top resid features:
since
Token since
Feature activation+0.014
Top resid features:
last
Token last
Feature activation+0.009
Top resid features:
night
Token night
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.157
Top resid features:
Ċ
TokenĊ
Feature activation+0.494
Top resid features:
Ċ
TokenĊ
Feature activation+0.461
Top resid features:
P
TokenP
Feature activation+0.396
Top resid features:
ray
Tokenray
Feature activation+0.026
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
For
Token For
Feature activation+0.000
Top resid features:
marijuana
Token marijuana
Feature activation+0.037
Top resid features:
drug
Token drug
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.126
Top resid features:
Ċ
TokenĊ
Feature activation+0.422
Top resid features:
Ċ
TokenĊ
Feature activation+0.373
Top resid features:
Gear
TokenGear
Feature activation+0.516
Top resid features:
y
Tokeny
Feature activation+0.014
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
big
Token big
Feature activation+0.000
Top resid features:
pharmaceutical
Token pharmaceutical
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.015
Top resid features:
nutritious
Token nutritious
Feature activation+0.019
Top resid features:
for
Token for
Feature activation+0.048
Top resid features:
kids
Token kids
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.199
Top resid features:
Ċ
TokenĊ
Feature activation+0.433
Top resid features:
Ċ
TokenĊ
Feature activation+0.406
Top resid features:
Mc
TokenMc
Feature activation+0.367
Top resid features:
Donald
TokenDonald
Feature activation+0.149
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.038
Top resid features:
it
Token it
Feature activation+0.019
Top resid features:
."
Token."
Feature activation+0.154
Top resid features:
Ċ
TokenĊ
Feature activation+0.358
Top resid features:
Ċ
TokenĊ
Feature activation+0.384
Top resid features:
B
TokenB
Feature activation+0.630
Top resid features:
arr
Tokenarr
Feature activation-0.073
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Libertarian
Token Libertarian
Feature activation+0.000
Top resid features:
Party
Token Party
Feature activation+0.000
Top resid features:
originally
Token originally
Feature activation+0.014
Top resid features:
scheduled
Token scheduled
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.153
Top resid features:
Ċ
TokenĊ
Feature activation+0.383
Top resid features:
Ċ
TokenĊ
Feature activation+0.341
Top resid features:
Getting
TokenGetting
Feature activation+0.477
Top resid features:
back
Token back
Feature activation+0.100
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
normal
Token normal
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:
doubt
Token doubt
Feature activation+0.023
Top resid features:
about
Token about
Feature activation+0.040
Top resid features:
that
Token that
Feature activation+0.053
Top resid features:
.
Token.
Feature activation+0.190
Top resid features:
Ċ
TokenĊ
Feature activation+0.439
Top resid features:
Ċ
TokenĊ
Feature activation+0.469
Top resid features:
Christ
TokenChrist
Feature activation+0.446
Top resid features:
ine
Tokenine
Feature activation+0.061
Top resid features:
El
Token El
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.16

Head 2: 0.17

Head 3: 0.07

Head 4: 0.13

Head 5: 0.03

Head 6: 0.03

Head 7: 0.05

Head 8: 0.06

Head 9: 0.04

Head 10: 0.16

Head 11: 0.04

Positive logits

endum1.02

meanwhile0.93

Edit0.91

plom0.84

quickShipAvailable0.83

hatt0.82

cerpt0.81

question0.81

':0.80

Expand0.80

surprisingly0.79

unsurprisingly0.78

mosp0.75

Originally0.75

largeDownload0.75

spokesman0.74

arten0.74

resa0.74

disclaimer0.73

Lavrov0.73

Negative logits

]."-1.20

%.-1.00

..."-1.00

$.-0.96

.).-0.95

)."-0.93

".-0.93

thereof-0.92

respectively-0.90

."-0.90

.�-0.89

."-0.87

therein-0.87

].-0.87

."[-0.86

!".-0.86

).-0.84

?).-0.84

}.-0.83

%).-0.82

INTERVAL 1.033 - 1.148
CONTAINS 0.001%

town
Token town
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bet
TokenBet
Feature activation+0.347
ty
Tokenty
Feature activation+1.148
Martinez
Token Martinez
Feature activation+0.727
said
Token said
Feature activation+0.442
her
Token her
Feature activation+0.460
daughter
Token daughter
Feature activation+0.721
had
Token had
Feature activation+0.194
appearance
Token appearance
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.048
Sc
TokenSc
Feature activation+0.455
rol
Tokenrol
Feature activation+1.084
l
Token l
Feature activation+0.723
down
Token down
Feature activation+0.641
for
Token for
Feature activation+0.672
video
Token video
Feature activation+0.520
Ċ
TokenĊ
Feature activation+0.081
cases
Token cases
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SP
TokenSP
Feature activation+0.442
C
TokenC
Feature activation+1.070
spokesman
Token spokesman
Feature activation+0.683
Sun
Token Sun
Feature activation+0.478
Jung
Token Jung
Feature activation+0.371
ong
Tokenong
Feature activation+0.388
said
Token said
Feature activation+0.268
reach
Tokenreach
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.104
Mc
TokenMc
Feature activation+0.425
Cr
TokenCr
Feature activation+1.040
ory
Tokenory
Feature activation+1.017
's
Token's
Feature activation+0.854
lawyers
Token lawyers
Feature activation+0.649
also
Token also
Feature activation+0.641
say
Token say
Feature activation+0.467
control
Token control
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.465
ala
Tokenala
Feature activation+1.078
began
Token began
Feature activation+0.466
developing
Token developing
Feature activation+0.497
ha
Token ha
Feature activation+0.380
ptic
Tokenptic
Feature activation+0.469
technology
Token technology
Feature activation+0.413

INTERVAL 0.918 - 1.033
CONTAINS 0.003%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.021
Thomas
TokenThomas
Feature activation+0.475
K
Token K
Feature activation+0.683
up
Tokenup
Feature activation+0.943
fer
Tokenfer
Feature activation+0.878
,
Token,
Feature activation+0.528
Hol
Token Hol
Feature activation+0.197
ger
Tokenger
Feature activation+0.147
Bra
Token Bra
Feature activation+0.131
downtown
Token downtown
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Step
TokenStep
Feature activation+0.414
han
Tokenhan
Feature activation+1.032
ie
Tokenie
Feature activation+1.013
Vand
Token Vand
Feature activation+0.511
ep
Tokenep
Feature activation+0.686
ut
Tokenut
Feature activation+0.460
te
Tokente
Feature activation+0.502
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.094
Cu
TokenCu
Feature activation+0.397
omo
Tokenomo
Feature activation+0.941
then
Token then
Feature activation+0.608
dismissed
Token dismissed
Feature activation+0.386
the
Token the
Feature activation+0.431
idea
Token idea
Feature activation+0.369
of
Token of
Feature activation+0.215
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Roberts
TokenRoberts
Feature activation+0.335
on
Tokenon
Feature activation+0.649
handed
Token handed
Feature activation+0.588
out
Token out
Feature activation+0.930
printed
Token printed
Feature activation+0.645
photos
Token photos
Feature activation+0.563
of
Token of
Feature activation+0.381
a
Token a
Feature activation+0.413
new
Token new
Feature activation+0.336
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.337
am
Tokenam
Feature activation+0.935
ilies
Tokenilies
Feature activation+0.648
started
Token started
Feature activation+0.487
to
Token to
Feature activation+0.402
collect
Token collect
Feature activation+0.355
wood
Token wood
Feature activation+0.315

INTERVAL 0.803 - 0.918
CONTAINS 0.013%

Court
Token Court
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.012
Read
TokenRead
Feature activation+0.285
more
Token more
Feature activation+0.853
:
Token:
Feature activation+0.665
Ċ
TokenĊ
Feature activation+0.215
Ċ
TokenĊ
Feature activation+0.246
Read
TokenRead
Feature activation+0.157
or
Token or
Feature activation+0.592
threat
Token threat
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ab
TokenAb
Feature activation+0.223
d
Tokend
Feature activation+0.833
ul
Tokenul
Feature activation+0.824
Ham
Token Ham
Feature activation+0.725
id
Tokenid
Feature activation+0.617
confirmed
Token confirmed
Feature activation+0.387
the
Token the
Feature activation+0.362
peers
Token peers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
E
TokenE
Feature activation+0.198
akin
Tokenakin
Feature activation+0.879
,
Token,
Feature activation+0.522
67
Token 67
Feature activation+0.533
,
Token,
Feature activation+0.442
a
Token a
Feature activation+0.473
Republican
Token Republican
Feature activation+0.363
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
St
TokenSt
Feature activation+0.326
P
Token P
Feature activation+0.836
addy
Tokenaddy
Feature activation+0.899
âĢ
TokenâĢ
Feature activation+0.434
Ļ
TokenĻ
Feature activation+0.416
s
Tokens
Feature activation+0.678
Day
Token Day
Feature activation+0.502
Ċ
TokenĊ
Feature activation+0.138
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.063
Kim
TokenKim
Feature activation+0.431
P
Token P
Feature activation+0.905
ind
Tokenind
Feature activation+0.804
ak
Tokenak
Feature activation+0.694
and
Token and
Feature activation+0.544
Sam
Token Sam
Feature activation+0.482
Phillips
Token Phillips
Feature activation+0.357
claim
Token claim
Feature activation+0.125

INTERVAL 0.689 - 0.803
CONTAINS 0.031%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Current
TokenCurrent
Feature activation+0.319
NFL
Token NFL
Feature activation+0.560
players
Token players
Feature activation+0.754
who
Token who
Feature activation+0.511
were
Token were
Feature activation+0.430
also
Token also
Feature activation+0.305
two
Token two
Feature activation+0.323
-
Token-
Feature activation+0.175
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Y
TokenY
Feature activation+0.361
ves
Tokenves
Feature activation+0.857
M
Token M
Feature activation+0.575
ers
Tokeners
Feature activation+0.782
ch
Tokench
Feature activation+0.597
image
Token image
Feature activation+0.336
via
Token via
Feature activation+0.346
Coin
Token Coin
Feature activation+0.253
Desk
TokenDesk
Feature activation+0.117
House
Token House
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.081
Once
TokenOnce
Feature activation+0.346
inside
Token inside
Feature activation+0.723
the
Token the
Feature activation+0.596
base
Token base
Feature activation+0.476
of
Token of
Feature activation+0.380
the
Token the
Feature activation+0.334
tower
Token tower
Feature activation+0.372
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Many
TokenMany
Feature activation+0.284
Spanish
Token Spanish
Feature activation+0.463
em
Token em
Feature activation+0.565
ig
Tokenig
Feature activation+0.740
res
Tokenres
Feature activation+0.691
and
Token and
Feature activation+0.360
corporations
Token corporations
Feature activation+0.383
from
Token from
Feature activation+0.236
telecom
Token telecom
Feature activation+0.191
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.043
For
TokenFor
Feature activation+0.410
the
Token the
Feature activation+0.726
eminent
Token eminent
Feature activation+0.595
political
Token political
Feature activation+0.700
scientist
Token scientist
Feature activation+0.846
Samuel
Token Samuel
Feature activation+0.456
Huntington
Token Huntington
Feature activation+0.480
,
Token,
Feature activation+0.219
writing
Token writing
Feature activation+0.117

INTERVAL 0.574 - 0.689
CONTAINS 0.080%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.055
Watch
TokenWatch
Feature activation+0.466
video
Token video
Feature activation+0.687
02
Token 02
Feature activation+0.668
:
Token:
Feature activation+0.562
12
Token12
Feature activation+0.300
30
Token 30
Feature activation+0.378
Years
Token Years
Feature activation+0.394
of
Token of
Feature activation+0.212
Image
TokenImage
Feature activation+0.407
caption
Token caption
Feature activation+0.533
M
Token M
Feature activation+0.469
anna
Tokenanna
Feature activation+0.774
De
Token De
Feature activation+0.542
y
Tokeny
Feature activation+0.651
won
Token won
Feature activation+0.264
several
Token several
Feature activation+0.095
awards
Token awards
Feature activation+0.114
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.073
Court
TokenCourt
Feature activation+0.356
records
Token records
Feature activation+0.681
and
Token and
Feature activation+0.555
documents
Token documents
Feature activation+0.540
show
Token show
Feature activation+0.458
that
Token that
Feature activation+0.168
Banks
Token Banks
Feature activation+0.129
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.152
m
Token m
Feature activation+0.377
ong
Tokenong
Feature activation+0.782
ore
Tokenore
Feature activation+0.654
store
Tokenstore
Feature activation+0.521
we
Token we
Feature activation+0.278
should
Token should
Feature activation+0.129
only
Token only
Feature activation+0.138
need
Token need
Feature activation+0.121
Enough
TokenEnough
Feature activation+0.193
.
Token.
Feature activation+0.359
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.012
R
TokenR
Feature activation+0.117
ond
Tokenond
Feature activation+0.653
ini
Tokenini
Feature activation+0.441
's
Token's
Feature activation+0.249
the
Token the
Feature activation+0.027
woman
Token woman
Feature activation+0.000
who
Token who
Feature activation+0.000

INTERVAL 0.459 - 0.574
CONTAINS 0.160%

behind
Token behind
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.236
may
Token may
Feature activation+0.467
even
Token even
Feature activation+0.471
spring
Token spring
Feature activation+0.394
to
Token to
Feature activation+0.223
mind
Token mind
Feature activation+0.317
that
Token that
Feature activation+0.165
West
TokenWest
Feature activation+0.071
Region
Token Region
Feature activation+0.461
Ċ
TokenĊ
Feature activation+0.037
Ċ
TokenĊ
Feature activation+0.060
#
Token#
Feature activation+0.153
1
Token1
Feature activation+0.488
)
Token)
Feature activation+0.419
Wisconsin
Token Wisconsin
Feature activation+0.333
:
Token:
Feature activation+0.322
Ron
Token Ron
Feature activation+0.116
Rivera
Token Rivera
Feature activation+0.213
office
Token office
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Inter
TokenInter
Feature activation+0.109
views
Tokenviews
Feature activation+0.476
were
Token were
Feature activation+0.317
conducted
Token conducted
Feature activation+0.088
in
Token in
Feature activation+0.140
July
Token July
Feature activation+0.152
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Samsung
TokenSamsung
Feature activation+0.391
announced
Token announced
Feature activation+0.478
the
Token the
Feature activation+0.493
Gear
Token Gear
Feature activation+0.510
VR
Token VR
Feature activation+0.523
in
Token in
Feature activation+0.287
September
Token September
Feature activation+0.307
2014
Token 2014
Feature activation+0.303
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.049
he
Token he
Feature activation+0.550
and
Token and
Feature activation+0.425
his
Token his
Feature activation+0.523
friends
Token friends
Feature activation+0.557
return
Token return
Feature activation+0.408
to
Token to
Feature activation+0.149
Earth
Token Earth
Feature activation+0.265
,
Token,
Feature activation+0.011

INTERVAL 0.344 - 0.459
CONTAINS 0.283%

military
Token military
Feature activation+0.000
voters
Token voters
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.088
interesting
Token interesting
Feature activation+0.450
sub
Token sub
Feature activation+0.378
text
Tokentext
Feature activation+0.346
to
Token to
Feature activation+0.146
John
Token John
Feature activation+0.147
McCain
Token McCain
Feature activation+0.075
Fer
Token Fer
Feature activation+0.282
din
Tokendin
Feature activation+0.428
ando
Tokenando
Feature activation+0.530
Armen
Token Armen
Feature activation+0.363
i
Tokeni
Feature activation+0.457
bowed
Token bowed
Feature activation+0.453
to
Token to
Feature activation+0.231
pressure
Token pressure
Feature activation+0.414
and
Token and
Feature activation+0.080
resigned
Token resigned
Feature activation+0.228
before
Token before
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.014
A
TokenA
Feature activation+0.272
freedom
Token freedom
Feature activation+0.938
fighter
Token fighter
Feature activation+0.814
he
Token he
Feature activation+0.489
definitely
Token definitely
Feature activation+0.365
was
Token was
Feature activation+0.280
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
certain
Token certain
Feature activation+0.000
edition
Token edition
Feature activation+0.466
of
Token of
Feature activation+0.294
the
Token the
Feature activation+0.279
Cor
Token Cor
Feature activation+0.340
ri
Tokenri
Feature activation+0.379
ere
Tokenere
Feature activation+0.364
D
Token D
Feature activation+0.259
ella
Tokenella
Feature activation+0.215
Ser
Token Ser
Feature activation+0.047
a
Tokena
Feature activation+0.000
,
Token,
Feature activation+0.000
sheet
Token sheet
Feature activation+0.520
?
Token?
Feature activation+0.200
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.134
beat
Token beat
Feature activation+0.457
sheet
Token sheet
Feature activation+0.478
is
Token is
Feature activation+0.064
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.230 - 0.344
CONTAINS 0.431%

âĢ
TokenâĢ
Feature activation+0.305
Ļ
TokenĻ
Feature activation+0.182
t
Tokent
Feature activation+0.234
know
Token know
Feature activation+0.177
how
Token how
Feature activation+0.223
you
Token you
Feature activation+0.279
can
Token can
Feature activation+0.181
view
Token view
Feature activation+0.000
[
Token [
Feature activation+0.000
Wednesday
TokenWednesday
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.152
the
Token the
Feature activation+0.522
designated
Token designated
Feature activation+0.328
day
Token day
Feature activation+0.357
,
Token,
Feature activation+0.246
âĢ
Token âĢ
Feature activation+0.029
ľ
Tokenľ
Feature activation+0.000
D
TokenD
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
In
TokenIn
Feature activation+0.163
addition
Token addition
Feature activation+0.577
to
Token to
Feature activation+0.628
the
Token the
Feature activation+0.562
expansion
Token expansion
Feature activation+0.468
,
Token,
Feature activation+0.334
Westminster
Token Westminster
Feature activation+0.228
plans
Token plans
Feature activation+0.340
to
Token to
Feature activation+0.082
renov
Token renov
Feature activation+0.328
ate
Tokenate
Feature activation+0.064
"
Token"
Feature activation+0.000
instead
Token instead
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dat
TokenDat
Feature activation+0.258
ab
Tokenab
Feature activation+0.588
inding
Tokeninding
Feature activation+0.572
Hub
Token Hub
Feature activation+0.461
Tile
TokenTile
Feature activation+0.411
Step
Token Step
Feature activation+0.344
Cont
TokenCont
Feature activation+0.022
iguous
Tokeniguous
Feature activation+0.233
territory
Token territory
Feature activation+0.288
'
Token'
Feature activation+0.139
Ċ
TokenĊ
Feature activation+0.154
Ċ
TokenĊ
Feature activation+0.269
The
TokenThe
Feature activation+0.105
US
Token US
Feature activation+0.262
president
Token president
Feature activation+0.438
said
Token said
Feature activation+0.199
that
Token that
Feature activation+0.000

INTERVAL 0.115 - 0.230
CONTAINS 0.594%

FC
TokenFC
Feature activation+0.385
Ċ
TokenĊ
Feature activation+0.123
Ċ
TokenĊ
Feature activation+0.092
Display
TokenDisplay
Feature activation+0.000
Port
TokenPort
Feature activation+0.340
Ċ
TokenĊ
Feature activation+0.208
Ċ
TokenĊ
Feature activation+0.105
DN
TokenDN
Feature activation+0.000
LA
TokenLA
Feature activation+0.236
Ċ
TokenĊ
Feature activation+0.086
Ċ
TokenĊ
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
overseas
Token overseas
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Just
TokenJust
Feature activation+0.201
food
Token food
Feature activation+0.551
for
Token for
Feature activation+0.453
thought
Token thought
Feature activation+0.439
.
Token.
Feature activation+0.377
Ċ
TokenĊ
Feature activation+0.072
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
V
TokenV
Feature activation+0.000
ander
Tokenander
Feature activation+0.308
Pl
Token Pl
Feature activation+0.118
a
Tokena
Feature activation+0.137
ats
Tokenats
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
driving
Token driving
Feature activation+0.283
near
Token near
Feature activation+0.252
Sher
Token Sher
Feature activation+0.338
brook
Tokenbrook
Feature activation+0.194
Street
Token Street
Feature activation+0.217
and
Token and
Feature activation+0.116
Notre
Token Notre
Feature activation+0.154
Dame
Token Dame
Feature activation+0.118
Avenue
Token Avenue
Feature activation+0.000
when
Token when
Feature activation+0.000
his
Token his
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
Kay
Token Kay
Feature activation+0.000
Mel
Token Mel
Feature activation+0.025
ch
Tokench
Feature activation+0.164
ior
Tokenior
Feature activation+0.116
reports
Token reports
Feature activation+0.131
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.000 - 0.115
CONTAINS 98.404%

.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
Pew
Token Pew
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
research
Token research
Feature activation+0.000
since
Token since
Feature activation+0.000
1985
Token 1985
Feature activation+0.000
,
Token,
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
rapid
Token rapid
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.000
extent
Token extent
Feature activation+0.000
of
Token of
Feature activation+0.000
fracturing
Token fracturing
Feature activation+0.000
this
Token this
Feature activation+0.000
spring
Token spring
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
L
TokenL
Feature activation+0.000
oyd
Tokenoyd
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
represents
Token represents
Feature activation+0.000
former
Token former
Feature activation+0.000
Ole
Token Ole
Feature activation+0.000
's
Token's
Feature activation+0.000
market
Token market
Feature activation+0.000
price
Token price
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
insisted
Token insisted
Feature activation+0.000
that
Token that
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
drafts
Token drafts
Feature activation+0.000
EU
Token EU
Feature activation+0.000
laws
Token laws
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
originally
Token originally
Feature activation+0.000
called
Token called
Feature activation+0.000
for
Token for
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 H1.2: (feature 7470)

TOP ACTIVATIONS
MAX = 1.545

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
sp
Token sp
Feature activation+0.000
ied
Tokenied
Feature activation+1.545
on
Token on
Feature activation+0.051
and
Token and
Feature activation+0.000
unm
Token unm
Feature activation+0.000
ask
Tokenask
Feature activation+0.706
ed
Tokened
Feature activation+0.351
will
Token will
Feature activation+0.000
feel
Token feel
Feature activation+0.000
compelled
Token compelled
Feature activation+0.000
to
Token to
Feature activation+0.000
pl
Token pl
Feature activation+0.000
unk
Tokenunk
Feature activation+1.453
down
Token down
Feature activation+0.000
several
Token several
Feature activation+0.000
million
Token million
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
toward
Token toward
Feature activation+0.000
qu
Token qu
Feature activation+0.000
elling
Tokenelling
Feature activation+1.421
the
Token the
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
squ
Token squ
Feature activation+0.000
irt
Tokenirt
Feature activation+1.417
bottle
Token bottle
Feature activation+0.000
or
Token or
Feature activation+0.000
else
Token else
Feature activation+0.000
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.000
It
Token It
Feature activation+0.000
wins
Token wins
Feature activation+0.000
votes
Token votes
Feature activation+0.000
by
Token by
Feature activation+0.000
sc
Token sc
Feature activation+0.000
aring
Tokenaring
Feature activation+1.409
the
Token the
Feature activation+0.009
public
Token public
Feature activation+0.000
and
Token and
Feature activation+0.000
painting
Token painting
Feature activation+0.000
himself
Token himself
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
qu
Token qu
Feature activation+0.000
ivers
Tokenivers
Feature activation+1.399
we
Token we
Feature activation+0.000
currently
Token currently
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+0.000
-
Token-
Feature activation+0.000
been
Token been
Feature activation+0.000
stalk
Token stalk
Feature activation+0.000
ed
Tokened
Feature activation+0.335
and
Token and
Feature activation+0.000
sp
Token sp
Feature activation+0.000
ied
Tokenied
Feature activation+1.387
upon
Token upon
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
mo
Token mo
Feature activation+0.000
vers
Tokenvers
Feature activation+1.182
and
Token and
Feature activation+0.000
sh
Token sh
Feature activation+0.000
akers
Tokenakers
Feature activation+1.376
to
Token to
Feature activation+0.000
shake
Token shake
Feature activation+0.000
off
Token off
Feature activation+0.383
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
GM
Token GM
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
pl
Token pl
Feature activation+0.000
ucking
Tokenucking
Feature activation+1.361
Guer
Token Guer
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
waiver
Token waiver
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
these
Tokenthese
Feature activation+0.000
dusty
Token dusty
Feature activation+0.028
treasures
Token treasures
Feature activation+0.000
pl
Token pl
Feature activation+0.000
ucked
Tokenucked
Feature activation+1.354
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+0.000
even
Token even
Feature activation+0.000
see
Token see
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
sc
Token sc
Feature activation+0.000
outed
Tokenouted
Feature activation+1.345
a
Token a
Feature activation+0.000
player
Token player
Feature activation+0.000
every
Token every
Feature activation+0.000
single
Token single
Feature activation+0.000
day
Token day
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
tr
Token tr
Feature activation+0.000
amp
Tokenamp
Feature activation+1.337
is
Token is
Feature activation+0.000
dead
Token dead
Feature activation+0.000
,
Token,
Feature activation+0.107
long
Token long
Feature activation+0.000
live
Token live
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
"
Token "
Feature activation+0.000
how
Tokenhow
Feature activation+0.000
many
Token many
Feature activation+0.000
sm
Token sm
Feature activation+0.000
acks
Tokenacks
Feature activation+1.320
could
Token could
Feature activation+0.000
he
Token he
Feature activation+0.000
take
Token take
Feature activation+0.000
?"
Token?"
Feature activation+0.000
But
Token But
Feature activation+0.000
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
sc
Token sc
Feature activation+0.000
aring
Tokenaring
Feature activation+1.317
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
b
Token b
Feature activation+0.000
****
Token****
Feature activation+0.477
!
Token!
Feature activation+0.000
original
Token original
Feature activation+0.000
kid
Token kid
Feature activation+0.000
gloves
Token gloves
Feature activation+0.000
,
Token,
Feature activation+0.000
sp
Token sp
Feature activation+0.000
urs
Tokenurs
Feature activation+1.313
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
ammunition
Token ammunition
Feature activation+0.000
band
Token band
Feature activation+0.000
ol
Tokenol
Feature activation+0.405
oul
Tokenoul
Feature activation+0.000
i
Tokeni
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
hon
Token hon
Feature activation+0.000
ours
Tokenours
Feature activation+1.304
at
Token at
Feature activation+0.241
the
Token the
Feature activation+0.098
awards
Token awards
Feature activation+0.000
which
Token which
Feature activation+0.016
were
Token were
Feature activation+0.000
of
Token of
Feature activation+0.085
coffee
Token coffee
Feature activation+0.000
amidst
Token amidst
Feature activation+0.000
a
Token a
Feature activation+0.000
ver
Token ver
Feature activation+0.042
itable
Tokenitable
Feature activation+1.299
snake
Token snake
Feature activation+0.000
pit
Token pit
Feature activation+0.208
of
Token of
Feature activation+0.000
cables
Token cables
Feature activation+0.000
.
Token.
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
gone
Token gone
Feature activation+0.000
gu
Token gu
Feature activation+0.000
er
Tokener
Feature activation+0.860
illa
Tokenilla
Feature activation+1.281
and
Token and
Feature activation+0.000
headed
Token headed
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
bush
Token bush
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
conceal
Token conceal
Feature activation+0.000
their
Token their
Feature activation+0.000
g
Token g
Feature activation+0.000
lee
Tokenlee
Feature activation+1.281
at
Token at
Feature activation+0.000
Lew
Token Lew
Feature activation+0.016
and
Tokenand
Feature activation+0.000
ow
Tokenow
Feature activation+0.011
ki
Tokenki
Feature activation+0.006
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
mon
Token mon
Feature activation+0.000
ied
Tokenied
Feature activation+1.277
elite
Token elite
Feature activation+0.048
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 1.377

Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.069
Top resid features:
The
TokenThe
Feature activation+0.165
Top resid features:
Obama
Token Obama
Feature activation+0.045
Top resid features:
administration
Token administration
Feature activation+0.043
Top resid features:
sp
Token sp
Feature activation+1.251
Top resid features:
ied
Tokenied
Feature activation+0.617
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
unm
Token unm
Feature activation+0.000
Top resid features:
ask
Tokenask
Feature activation+0.000
Top resid features:
production
Token production
Feature activation+0.061
Top resid features:
will
Token will
Feature activation+0.101
Top resid features:
feel
Token feel
Feature activation+0.058
Top resid features:
compelled
Token compelled
Feature activation+0.105
Top resid features:
to
Token to
Feature activation+0.153
Top resid features:
pl
Token pl
Feature activation+1.303
Top resid features:
unk
Tokenunk
Feature activation+0.466
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
several
Token several
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.000
Top resid features:
dollars
Token dollars
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.040
Top resid features:
a
Token a
Feature activation+0.123
Top resid features:
long
Token long
Feature activation+0.024
Top resid features:
way
Token way
Feature activation+0.071
Top resid features:
toward
Token toward
Feature activation+0.207
Top resid features:
qu
Token qu
Feature activation+1.293
Top resid features:
elling
Tokenelling
Feature activation+0.459
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
outrage
Token outrage
Feature activation+0.000
Top resid features:
surrounding
Token surrounding
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
easiest
Token easiest
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.088
Top resid features:
use
Token use
Feature activation+0.032
Top resid features:
with
Token with
Feature activation+0.158
Top resid features:
a
Token a
Feature activation+0.254
Top resid features:
squ
Token squ
Feature activation+1.175
Top resid features:
irt
Tokenirt
Feature activation+0.534
Top resid features:
bottle
Token bottle
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
else
Token else
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.114
Top resid features:
It
Token It
Feature activation+0.073
Top resid features:
wins
Token wins
Feature activation+0.069
Top resid features:
votes
Token votes
Feature activation+0.124
Top resid features:
by
Token by
Feature activation+0.195
Top resid features:
sc
Token sc
Feature activation+1.320
Top resid features:
aring
Tokenaring
Feature activation+0.438
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
painting
Token painting
Feature activation+0.000
Top resid features:
can
Token can
Feature activation-0.031
Top resid features:
we
Token we
Feature activation-0.005
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
all
Token all
Feature activation+0.086
Top resid features:
the
Token the
Feature activation+0.218
Top resid features:
qu
Token qu
Feature activation+1.221
Top resid features:
ivers
Tokenivers
Feature activation+0.460
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
currently
Token currently
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.040
Top resid features:
been
Token been
Feature activation+0.019
Top resid features:
stalk
Token stalk
Feature activation+0.056
Top resid features:
ed
Tokened
Feature activation+0.106
Top resid features:
and
Token and
Feature activation+0.134
Top resid features:
sp
Token sp
Feature activation+1.293
Top resid features:
ied
Tokenied
Feature activation+0.507
Top resid features:
upon
Token upon
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.044
Top resid features:
fellow
Token fellow
Feature activation+0.048
Top resid features:
mo
Token mo
Feature activation+0.120
Top resid features:
vers
Tokenvers
Feature activation+0.053
Top resid features:
and
Token and
Feature activation+0.224
Top resid features:
sh
Token sh
Feature activation+1.237
Top resid features:
akers
Tokenakers
Feature activation+0.404
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
shake
Token shake
Feature activation+0.000
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
move
Token move
Feature activation+0.065
Top resid features:
as
Token as
Feature activation+0.071
Top resid features:
a
Token a
Feature activation+0.136
Top resid features:
GM
Token GM
Feature activation+0.060
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.117
Top resid features:
pl
Token pl
Feature activation+1.328
Top resid features:
ucking
Tokenucking
Feature activation+0.322
Top resid features:
Guer
Token Guer
Feature activation+0.000
Top resid features:
ra
Tokenra
Feature activation+0.000
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
quotes
Token quotes
Feature activation+0.021
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.103
Top resid features:
these
Tokenthese
Feature activation+0.096
Top resid features:
dusty
Token dusty
Feature activation+0.116
Top resid features:
treasures
Token treasures
Feature activation+0.121
Top resid features:
pl
Token pl
Feature activation+1.343
Top resid features:
ucked
Tokenucked
Feature activation+0.337
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
consciousness
Token consciousness
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.007
Top resid features:
even
Token even
Feature activation+0.033
Top resid features:
see
Token see
Feature activation+0.097
Top resid features:
if
Token if
Feature activation+0.170
Top resid features:
you
Token you
Feature activation+0.090
Top resid features:
sc
Token sc
Feature activation+1.252
Top resid features:
outed
Tokenouted
Feature activation+0.522
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
player
Token player
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
single
Token single
Feature activation+0.000
Top resid features:
1973
Token 1973
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.086
Top resid features:
"
Token"
Feature activation+0.062
Top resid features:
The
TokenThe
Feature activation+0.309
Top resid features:
tr
Token tr
Feature activation+1.255
Top resid features:
amp
Tokenamp
Feature activation+0.420
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.032
Top resid features:
thinking
Token thinking
Feature activation-0.002
Top resid features:
"
Token "
Feature activation+0.052
Top resid features:
how
Tokenhow
Feature activation+0.179
Top resid features:
many
Token many
Feature activation+0.145
Top resid features:
sm
Token sm
Feature activation+1.198
Top resid features:
acks
Tokenacks
Feature activation+0.412
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
?"
Token?"
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.129
Top resid features:
You
Token You
Feature activation+0.096
Top resid features:
âĢ
TokenâĢ
Feature activation+0.049
Top resid features:
Ļ
TokenĻ
Feature activation+0.050
Top resid features:
re
Tokenre
Feature activation+0.014
Top resid features:
sc
Token sc
Feature activation+1.377
Top resid features:
aring
Tokenaring
Feature activation+0.401
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
b
Token b
Feature activation+0.000
Top resid features:
****
Token****
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
original
Token original
Feature activation+0.045
Top resid features:
kid
Token kid
Feature activation+0.067
Top resid features:
gloves
Token gloves
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.254
Top resid features:
sp
Token sp
Feature activation+1.221
Top resid features:
urs
Tokenurs
Feature activation+0.278
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ammunition
Token ammunition
Feature activation+0.000
Top resid features:
band
Token band
Feature activation+0.000
Top resid features:
am
Tokenam
Feature activation+0.000
Top resid features:
oul
Tokenoul
Feature activation+0.011
Top resid features:
i
Tokeni
Feature activation+0.077
Top resid features:
won
Token won
Feature activation+0.054
Top resid features:
the
Token the
Feature activation+0.322
Top resid features:
hon
Token hon
Feature activation+1.163
Top resid features:
ours
Tokenours
Feature activation+0.440
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
awards
Token awards
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
lake
Token lake
Feature activation+0.078
Top resid features:
of
Token of
Feature activation+0.125
Top resid features:
coffee
Token coffee
Feature activation+0.045
Top resid features:
amidst
Token amidst
Feature activation+0.162
Top resid features:
a
Token a
Feature activation+0.218
Top resid features:
ver
Token ver
Feature activation+0.886
Top resid features:
itable
Tokenitable
Feature activation+0.445
Top resid features:
snake
Token snake
Feature activation+0.000
Top resid features:
pit
Token pit
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
cables
Token cables
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
fact
Token fact
Feature activation+0.064
Top resid features:
she
Token she
Feature activation+0.063
Top resid features:
had
Token had
Feature activation+0.085
Top resid features:
gone
Token gone
Feature activation+0.009
Top resid features:
gu
Token gu
Feature activation+1.344
Top resid features:
er
Tokener
Feature activation+0.064
Top resid features:
illa
Tokenilla
Feature activation+0.301
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
others
Token others
Feature activation+0.080
Top resid features:
could
Token could
Feature activation+0.068
Top resid features:
not
Token not
Feature activation+0.027
Top resid features:
conceal
Token conceal
Feature activation+0.030
Top resid features:
their
Token their
Feature activation+0.090
Top resid features:
g
Token g
Feature activation+1.255
Top resid features:
lee
Tokenlee
Feature activation+0.441
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Lew
Token Lew
Feature activation+0.000
Top resid features:
and
Tokenand
Feature activation+0.000
Top resid features:
ow
Tokenow
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.021
Top resid features:
as
Token as
Feature activation+0.105
Top resid features:
those
Token those
Feature activation+0.161
Top resid features:
of
Token of
Feature activation+0.220
Top resid features:
a
Token a
Feature activation+0.337
Top resid features:
mon
Token mon
Feature activation+0.770
Top resid features:
ied
Tokenied
Feature activation+0.502
Top resid features:
elite
Token elite
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
So
Token So
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.08

Head 2: 0.17

Head 3: 0.08

Head 4: 0.10

Head 5: 0.03

Head 6: 0.06

Head 7: 0.06

Head 8: 0.05

Head 9: 0.06

Head 10: 0.15

Head 11: 0.06

Positive logits

gery0.81

spread0.79

ded0.78

syn0.77

geoning0.75

enary0.75

gian0.75

convention0.75

syn0.72

sync0.71

relic0.69

asses0.69

iously0.69

vested0.68

discs0.68

onite0.68

disposal0.67

cord0.67

arial0.66

unity0.66

Negative logits

Lines-0.86

Citiz-0.86

Reincarn-0.82

chwitz-0.81

Novel-0.80

Fey-0.79

zsche-0.77

Yon-0.77

Bus-0.77

Aging-0.75

Jihad-0.75

Month-0.74

Tsukuyomi-0.74

Leilan-0.72

Niet-0.71

Payments-0.71

Salary-0.71

Uriel-0.71

-0.71

ivia-0.71

INTERVAL 1.390 - 1.545
CONTAINS 0.001%

It
Token It
Feature activation+0.000
wins
Token wins
Feature activation+0.000
votes
Token votes
Feature activation+0.000
by
Token by
Feature activation+0.000
sc
Token sc
Feature activation+0.000
aring
Tokenaring
Feature activation+1.409
the
Token the
Feature activation+0.009
public
Token public
Feature activation+0.000
and
Token and
Feature activation+0.000
painting
Token painting
Feature activation+0.000
himself
Token himself
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
squ
Token squ
Feature activation+0.000
irt
Tokenirt
Feature activation+1.417
bottle
Token bottle
Feature activation+0.000
or
Token or
Feature activation+0.000
else
Token else
Feature activation+0.000
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
qu
Token qu
Feature activation+0.000
ivers
Tokenivers
Feature activation+1.399
we
Token we
Feature activation+0.000
currently
Token currently
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
toward
Token toward
Feature activation+0.000
qu
Token qu
Feature activation+0.000
elling
Tokenelling
Feature activation+1.421
the
Token the
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
decision
Token decision
Feature activation+0.000
will
Token will
Feature activation+0.000
feel
Token feel
Feature activation+0.000
compelled
Token compelled
Feature activation+0.000
to
Token to
Feature activation+0.000
pl
Token pl
Feature activation+0.000
unk
Tokenunk
Feature activation+1.453
down
Token down
Feature activation+0.000
several
Token several
Feature activation+0.000
million
Token million
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 1.236 - 1.390
CONTAINS 0.002%

as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
GM
Token GM
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
pl
Token pl
Feature activation+0.000
ucking
Tokenucking
Feature activation+1.361
Guer
Token Guer
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
waiver
Token waiver
Feature activation+0.000
oul
Tokenoul
Feature activation+0.000
i
Tokeni
Feature activation+0.000
won
Token won
Feature activation+0.000
the
Token the
Feature activation+0.000
hon
Token hon
Feature activation+0.000
ours
Tokenours
Feature activation+1.304
at
Token at
Feature activation+0.241
the
Token the
Feature activation+0.098
awards
Token awards
Feature activation+0.000
which
Token which
Feature activation+0.016
were
Token were
Feature activation+0.000
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
sc
Token sc
Feature activation+0.000
aring
Tokenaring
Feature activation+1.317
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
b
Token b
Feature activation+0.000
****
Token****
Feature activation+0.477
!
Token!
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
mo
Token mo
Feature activation+0.000
vers
Tokenvers
Feature activation+1.182
and
Token and
Feature activation+0.000
sh
Token sh
Feature activation+0.000
akers
Tokenakers
Feature activation+1.376
to
Token to
Feature activation+0.000
shake
Token shake
Feature activation+0.000
off
Token off
Feature activation+0.383
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
of
Token of
Feature activation+0.085
coffee
Token coffee
Feature activation+0.000
amidst
Token amidst
Feature activation+0.000
a
Token a
Feature activation+0.000
ver
Token ver
Feature activation+0.042
itable
Tokenitable
Feature activation+1.299
snake
Token snake
Feature activation+0.000
pit
Token pit
Feature activation+0.208
of
Token of
Feature activation+0.000
cables
Token cables
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.081 - 1.236
CONTAINS 0.005%

,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
l
Token l
Feature activation+0.000
uster
Tokenuster
Feature activation+1.153
faded
Token faded
Feature activation+0.033
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
job
Token job
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
aff
Token aff
Feature activation+0.000
lict
Tokenlict
Feature activation+1.135
the
Token the
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
The
Token The
Feature activation+0.000
Russians
Token Russians
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
tam
Token tam
Feature activation+0.000
per
Tokenper
Feature activation+1.114
with
Token with
Feature activation+0.064
the
Token the
Feature activation+0.000
vote
Token vote
Feature activation+0.000
totals
Token totals
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
h
Token h
Feature activation+0.000
odge
Tokenodge
Feature activation+1.155
-
Token-
Feature activation+0.084
p
Tokenp
Feature activation+0.000
odge
Tokenodge
Feature activation+0.422
of
Token of
Feature activation+0.000
shape
Token shape
Feature activation+0.000
for
Token for
Feature activation+0.000
restoration
Token restoration
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fac
Token fac
Feature activation+0.000
ades
Tokenades
Feature activation+1.187
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
along
Token along
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.927 - 1.081
CONTAINS 0.011%

jazz
Token jazz
Feature activation+0.000
fusion
Token fusion
Feature activation+0.000
and
Token and
Feature activation+0.000
br
Token br
Feature activation+0.000
anc
Tokenanc
Feature activation+0.770
hed
Tokenhed
Feature activation+0.927
out
Token out
Feature activation+0.000
from
Token from
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
bo
Token bo
Feature activation+0.000
omer
Tokenomer
Feature activation+1.051
angs
Tokenangs
Feature activation+0.966
are
Token are
Feature activation+0.000
coming
Token coming
Feature activation+0.000
back
Token back
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
goes
Token goes
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
tir
Token tir
Feature activation+0.000
ade
Tokenade
Feature activation+0.927
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
importance
Token importance
Feature activation+0.000
of
Token of
Feature activation+0.000
shareholders
Token shareholders
Feature activation+0.000
these
Token these
Feature activation+0.000
mechanisms
Token mechanisms
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
cause
Token cause
Feature activation+0.000
cr
Token cr
Feature activation+0.000
amping
Tokenamping
Feature activation+0.962
,
Token,
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
in
Token in
Feature activation+0.000
combination
Token combination
Feature activation+0.000
.
Token.
Feature activation+0.000
man
Token man
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
red
Token red
Feature activation+0.000
tur
Token tur
Feature activation+0.145
ban
Tokenban
Feature activation+0.995
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
kicked
Token kicked
Feature activation+0.000
out
Token out
Feature activation+0.138
of
Token of
Feature activation+0.000

INTERVAL 0.772 - 0.927
CONTAINS 0.021%

've
Token've
Feature activation+0.000
got
Token got
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
the
Token the
Feature activation+0.000
m
Token m
Feature activation+0.000
akings
Tokenakings
Feature activation+0.779
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
for
Token for
Feature activation+0.000
corporations
Token corporations
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
posting
Token posting
Feature activation+0.000
emotional
Token emotional
Feature activation+0.000
t
Token t
Feature activation+0.000
ributes
Tokenributes
Feature activation+0.821
to
Token to
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
man
Tokenman
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lind
TokenLind
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
fer
Token fer
Feature activation+0.000
ments
Tokenments
Feature activation+0.870
whole
Token whole
Feature activation+0.000
cher
Token cher
Feature activation+0.000
ries
Tokenries
Feature activation+0.692
in
Token in
Feature activation+0.000
lamb
Token lamb
Feature activation+0.000
the
Token the
Feature activation+0.000
ways
Token ways
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
n
Token n
Feature activation+0.000
atal
Tokenatal
Feature activation+0.779
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
girls
Token girls
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
he
Token he
Feature activation+0.000
br
Token br
Feature activation+0.000
agged
Tokenagged
Feature activation+0.924
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.618 - 0.772
CONTAINS 0.033%

),
Token),
Feature activation+0.000
heat
Token heat
Feature activation+0.000
2
Token 2
Feature activation+0.000
t
Token t
Feature activation+0.000
bs
Tokenbs
Feature activation+0.339
ps
Tokenps
Feature activation+0.658
of
Token of
Feature activation+0.000
vegetables
Token vegetables
Feature activation+0.000
and
Token and
Feature activation+0.000
cook
Token cook
Feature activation+0.000
the
Token the
Feature activation+0.000
display
Token display
Feature activation+0.000
,
Token,
Feature activation+0.000
sab
Token sab
Feature activation+0.000
ine
Tokenine
Feature activation+0.686
l
Token l
Feature activation+0.073
iew
Tokeniew
Feature activation+0.722
ald
Tokenald
Feature activation+0.503
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Companies
TokenCompanies
Feature activation+0.000
:
Token:
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
is
Token is
Feature activation+0.000
dist
Token dist
Feature activation+0.000
antly
Tokenantly
Feature activation+0.745
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.000
East
Token East
Feature activation+0.000
Euras
Token Euras
Feature activation+0.000
encountered
Token encountered
Feature activation+0.000
a
Token a
Feature activation+0.000
specimen
Token specimen
Feature activation+0.000
as
Token as
Feature activation+0.000
mush
Token mush
Feature activation+0.000
y
Tokeny
Feature activation+0.661
,
Token,
Feature activation+0.000
un
Token un
Feature activation+0.000
season
Tokenseason
Feature activation+0.000
ed
Tokened
Feature activation+0.076
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
cock
Token cock
Feature activation+0.000
y
Tokeny
Feature activation+0.642
enough
Token enough
Feature activation+0.000
jerk
Token jerk
Feature activation+0.000
to
Token to
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.463 - 0.618
CONTAINS 0.052%

What
Token What
Feature activation+0.000
it
Token it
Feature activation+0.000
takes
Token takes
Feature activation+0.000
is
Token is
Feature activation+0.000
des
Token des
Feature activation+0.000
ens
Tokenens
Feature activation+0.467
it
Tokenit
Feature activation+0.000
ization
Tokenization
Feature activation+0.278
and
Token and
Feature activation+0.000
conditioning
Token conditioning
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
were
Token were
Feature activation+0.000
being
Token being
Feature activation+0.000
pel
Token pel
Feature activation+0.000
ted
Tokented
Feature activation+0.581
with
Token with
Feature activation+0.000
ash
Token ash
Feature activation+0.000
and
Token and
Feature activation+0.000
acid
Token acid
Feature activation+0.000
rain
Token rain
Feature activation+0.017
changes
Token changes
Feature activation+0.000
had
Token had
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
ker
Token ker
Feature activation+0.000
bs
Tokenbs
Feature activation+0.529
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
better
Tokenbetter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
rep
Token rep
Feature activation+0.000
urch
Tokenurch
Feature activation+0.468
ased
Tokenased
Feature activation+0.007
its
Token its
Feature activation+0.000
warrants
Token warrants
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000
4
Token4
Feature activation+0.000
teaspoon
Token teaspoon
Feature activation+0.000
cor
Token cor
Feature activation+0.000
i
Tokeni
Feature activation+0.516
ander
Tokenander
Feature activation+0.352
Ċ
TokenĊ
Feature activation+0.024
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
/
Token/
Feature activation+0.000

INTERVAL 0.309 - 0.463
CONTAINS 0.083%

areas
Token areas
Feature activation+0.000
)
Token)
Feature activation+0.000
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
con
Token con
Feature activation+0.000
undrum
Tokenundrum
Feature activation+0.418
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
Thailand
Token Thailand
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Imp
TokenImp
Feature activation+0.000
ending
Tokenending
Feature activation+0.431
Thai
Token Thai
Feature activation+0.000
auto
Token auto
Feature activation+0.000
subsidies
Token subsidies
Feature activation+0.000
have
Token have
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
int
Token int
Feature activation+0.000
ents
Tokenents
Feature activation+0.413
and
Token and
Feature activation+0.000
purposes
Token purposes
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
amina
Tokenamina
Feature activation+0.000
D
TokenD
Feature activation+0.000
rain
Tokenrain
Feature activation+0.000
Mult
TokenMult
Feature activation+0.000
ipl
Tokenipl
Feature activation+0.146
ier
Tokenier
Feature activation+0.408
Spec
Token Spec
Feature activation+0.138
ifies
Tokenifies
Feature activation+0.279
the
Token the
Feature activation+0.021
scaling
Token scaling
Feature activation+0.030
factor
Token factor
Feature activation+0.162
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
of
Token of
Feature activation+0.000
m
Token m
Feature activation+0.000
ong
Tokenong
Feature activation+0.360
rel
Tokenrel
Feature activation+0.038
s
Tokens
Feature activation+0.131
and
Token and
Feature activation+0.000
without
Token without
Feature activation+0.000
Follow
Token Follow
Feature activation+0.000

INTERVAL 0.154 - 0.309
CONTAINS 0.119%

16
Token 16
Feature activation+0.000
Warning
Token Warning
Feature activation+0.000
:
Token:
Feature activation+0.000
impl
Token impl
Feature activation+0.000
ode
Tokenode
Feature activation+0.629
():
Token():
Feature activation+0.282
Argument
Token Argument
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.074
an
Token an
Feature activation+0.000
array
Token array
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
Pett
Token Pett
Feature activation+0.000
itte
Tokenitte
Feature activation+0.261
is
Token is
Feature activation+0.000
coming
Token coming
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
retirement
Token retirement
Feature activation+0.000
vol
Token vol
Feature activation+0.000
to
Tokento
Feature activation+0.000
inc
Token inc
Feature activation+0.000
app
Tokenapp
Feature activation+0.133
ucc
Tokenucc
Feature activation+0.203
iat
Tokeniat
Feature activation+0.259
o
Tokeno
Feature activation+0.090
o
Token o
Feature activation+0.000
n
Token n
Feature activation+0.000
asc
Tokenasc
Feature activation+0.224
ost
Tokenost
Feature activation+0.139
to
Token to
Feature activation+0.000
breaches
Token breaches
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.000
Ric
Token Ric
Feature activation+0.000
ochet
Tokenochet
Feature activation+0.268
client
Token client
Feature activation+0.000
works
Token works
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
self
Token self
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
quest
Token quest
Feature activation+0.000
for
Token for
Feature activation+0.000
market
Token market
Feature activation+0.000
able
Tokenable
Feature activation+0.157
credentials
Token credentials
Feature activation+0.000
eclipse
Token eclipse
Feature activation+0.000
real
Token real
Feature activation+0.000
learning
Token learning
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.154
CONTAINS 99.674%

N
TokenN
Feature activation+0.000
X
TokenX
Feature activation+0.000
chose
Token chose
Feature activation+0.000
chip
Token chip
Feature activation+0.000
-
Token-
Feature activation+0.000
maker
Tokenmaker
Feature activation+0.000
Qualcomm
Token Qualcomm
Feature activation+0.000
to
Token to
Feature activation+0.000
partner
Token partner
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+0.000
and
Token and
Feature activation+0.000
world
Token world
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
in
Token in
Feature activation+0.000
VR
Token VR
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
AMD
Token AMD
Feature activation+0.000
,
Token,
Feature activation+0.000
HTC
Token HTC
Feature activation+0.000
pop
Token pop
Feature activation+0.000
bottles
Token bottles
Feature activation+0.000
and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
go
Token go
Feature activation+0.000
really
Token really
Feature activation+0.000
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
service
Token service
Feature activation+0.000
to
Token to
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.000
and
Token and
Feature activation+0.000
Portland
Token Portland
Feature activation+0.000
several
Token several
Feature activation+0.000
stint
Token stint
Feature activation+0.000
s
Tokens
Feature activation+0.000
on
Token on
Feature activation+0.000
Broadway
Token Broadway
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
pretty
Token pretty
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 H1.2: (feature 16729)

TOP ACTIVATIONS
MAX = 1.243

donate
Token donate
Feature activation+0.000
your
Token your
Feature activation+0.000
cash
Token cash
Feature activation+0.000
to
Token to
Feature activation+0.000
qu
Token qu
Feature activation+0.000
acks
Tokenacks
Feature activation+1.243
,
Token,
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.033
as
Tokenas
Feature activation+0.717
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
the
Token the
Feature activation+0.000
le
Token le
Feature activation+0.000
aching
Tokenaching
Feature activation+1.232
being
Token being
Feature activation+0.000
mild
Token mild
Feature activation+0.000
.
Token.
Feature activation+0.000
Five
Token Five
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
qu
Token qu
Feature activation+0.000
irk
Tokenirk
Feature activation+1.184
of
Token of
Feature activation+0.000
cinema
Token cinema
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
,
Token,
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
authority
Token authority
Feature activation+0.000
to
Token to
Feature activation+0.000
investigate
Token investigate
Feature activation+0.000
every
Token every
Feature activation+0.000
sal
Token sal
Feature activation+0.000
acious
Tokenacious
Feature activation+1.158
claim
Token claim
Feature activation+0.000
or
Token or
Feature activation+0.000
rumor
Token rumor
Feature activation+0.000
about
Token about
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
James
Token James
Feature activation+0.000
Hodg
Token Hodg
Feature activation+0.000
kinson
Tokenkinson
Feature activation+0.000
r
Token r
Feature activation+0.000
ailed
Tokenailed
Feature activation+1.142
in
Token in
Feature activation+0.013
numerous
Token numerous
Feature activation+0.000
public
Token public
Feature activation+0.000
letters
Token letters
Feature activation+0.126
to
Token to
Feature activation+0.000
Her
Token Her
Feature activation+0.000
fing
Token fing
Feature activation+0.000
ern
Tokenern
Feature activation+0.852
ails
Tokenails
Feature activation+0.508
gn
Token gn
Feature activation+0.219
awed
Tokenawed
Feature activation+1.116
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
quick
Token quick
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
d
Token d
Feature activation+0.000
ail
Tokenail
Feature activation+0.930
ies
Tokenies
Feature activation+1.098
were
Token were
Feature activation+0.000
reviewed
Token reviewed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
studio
Token studio
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
seen
Token seen
Feature activation+0.000
its
Token its
Feature activation+0.000
l
Token l
Feature activation+0.000
uster
Tokenuster
Feature activation+1.004
dim
Token dim
Feature activation+0.000
med
Tokenmed
Feature activation+0.841
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
globe
Token globe
Feature activation+0.000
can
Token can
Feature activation+0.000
qu
Token qu
Feature activation+0.000
iver
Tokeniver
Feature activation+0.993
."[
Token."[
Feature activation+0.000
21
Token21
Feature activation+0.000
][
Token][
Feature activation+0.000
22
Token22
Feature activation+0.000
]
Token]
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
sprink
Token sprink
Feature activation+0.000
ler
Tokenler
Feature activation+0.990
system
Token system
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
pet
Token pet
Feature activation+0.000
store
Token store
Feature activation+0.000
's
Token's
Feature activation+0.000
too
Token too
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
del
Token del
Feature activation+0.000
ude
Tokenude
Feature activation+0.985
ourselves
Token ourselves
Feature activation+0.004
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
found
Token found
Feature activation+0.000
her
Token her
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
uses
Token uses
Feature activation+0.000
ins
Token ins
Feature activation+0.000
ince
Tokenince
Feature activation+0.980
re
Tokenre
Feature activation+0.444
,
Token,
Feature activation+0.000
shallow
Token shallow
Feature activation+0.000
affection
Token affection
Feature activation+0.000
to
Token to
Feature activation+0.000
)
Token)
Feature activation+0.000
that
Token that
Feature activation+0.000
receives
Token receives
Feature activation+0.000
the
Token the
Feature activation+0.000
vent
Token vent
Feature activation+0.000
ral
Tokenral
Feature activation+0.978
te
Token te
Feature activation+0.036
gment
Tokengment
Feature activation+0.548
al
Tokenal
Feature activation+0.782
area
Token area
Feature activation+0.000
dopamine
Token dopamine
Feature activation+0.000
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+0.973
so
Token so
Feature activation+0.000
hard
Token hard
Feature activation+0.000
in
Token in
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
that
Token that
Feature activation+0.000
an
Token an
Feature activation+0.000
insidious
Token insidious
Feature activation+0.000
drug
Token drug
Feature activation+0.000
that
Token that
Feature activation+0.000
ro
Token ro
Feature activation+0.000
bs
Tokenbs
Feature activation+0.965
addicts
Token addicts
Feature activation+0.000
of
Token of
Feature activation+0.000
true
Token true
Feature activation+0.000
happiness
Token happiness
Feature activation+0.000
."
Token."
Feature activation+0.000
service
Token service
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
ev
Token ev
Feature activation+0.000
ading
Tokenading
Feature activation+0.960
it
Token it
Feature activation+0.000
through
Token through
Feature activation+0.000
inaction
Token inaction
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
America
Token America
Feature activation+0.000
will
Token will
Feature activation+0.000
start
Token start
Feature activation+0.000
to
Token to
Feature activation+0.000
d
Token d
Feature activation+0.000
uke
Tokenuke
Feature activation+0.959
it
Token it
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
were
Token were
Feature activation+0.000
just
Token just
Feature activation+0.000
d
Token d
Feature activation+0.000
renched
Tokenrenched
Feature activation+0.958
in
Token in
Feature activation+0.000
bat
Token bat
Feature activation+0.000
pee
Token pee
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
gor
Token gor
Feature activation+0.000
illas
Tokenillas
Feature activation+0.333
are
Token are
Feature activation+0.000
ent
Token ent
Feature activation+0.000
ang
Tokenang
Feature activation+0.715
lement
Tokenlement
Feature activation+0.951
in
Token in
Feature activation+0.000
hunting
Token hunting
Feature activation+0.000
s
Token s
Feature activation+0.000
na
Tokenna
Feature activation+0.438
res
Tokenres
Feature activation+0.479
sticks
Token sticks
Feature activation+0.000
and
Token and
Feature activation+0.000
rocks
Token rocks
Feature activation+0.000
trump
Token trump
Feature activation+0.027
bl
Token bl
Feature activation+0.028
asters
Tokenasters
Feature activation+0.951
and
Token and
Feature activation+0.000
speed
Token speed
Feature activation+0.000
er
Tokener
Feature activation+0.213
bikes
Token bikes
Feature activation+0.000
?
Token?
Feature activation+0.000

Top DFA by src position
MAX = 1.173

to
Token to
Feature activation+0.057
Top resid features:
donate
Token donate
Feature activation+0.083
Top resid features:
your
Token your
Feature activation+0.125
Top resid features:
cash
Token cash
Feature activation+0.095
Top resid features:
to
Token to
Feature activation+0.179
Top resid features:
qu
Token qu
Feature activation+1.132
Top resid features:
acks
Tokenacks
Feature activation+0.400
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
fle
Token fle
Feature activation+0.116
Top resid features:
as
Tokenas
Feature activation+0.088
Top resid features:
,
Token,
Feature activation+0.246
Top resid features:
despite
Token despite
Feature activation+0.212
Top resid features:
the
Token the
Feature activation+0.167
Top resid features:
le
Token le
Feature activation+1.041
Top resid features:
aching
Tokenaching
Feature activation+0.382
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
mild
Token mild
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Five
Token Five
Feature activation+0.000
Top resid features:
Rush
Token Rush
Feature activation+0.059
Top resid features:
,
Token,
Feature activation+0.136
Top resid features:
thanks
Token thanks
Feature activation+0.119
Top resid features:
to
Token to
Feature activation+0.176
Top resid features:
a
Token a
Feature activation+0.177
Top resid features:
qu
Token qu
Feature activation+1.119
Top resid features:
irk
Tokenirk
Feature activation+0.421
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
cinema
Token cinema
Feature activation+0.000
Top resid features:
distribution
Token distribution
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
forensic
Token forensic
Feature activation+0.075
Top resid features:
authority
Token authority
Feature activation+0.083
Top resid features:
to
Token to
Feature activation+0.120
Top resid features:
investigate
Token investigate
Feature activation+0.186
Top resid features:
every
Token every
Feature activation+0.137
Top resid features:
sal
Token sal
Feature activation+1.088
Top resid features:
acious
Tokenacious
Feature activation+0.400
Top resid features:
claim
Token claim
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
rumor
Token rumor
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.153
Top resid features:
,
Token,
Feature activation+0.176
Top resid features:
James
Token James
Feature activation+0.084
Top resid features:
Hodg
Token Hodg
Feature activation+0.111
Top resid features:
kinson
Tokenkinson
Feature activation+0.225
Top resid features:
r
Token r
Feature activation+0.966
Top resid features:
ailed
Tokenailed
Feature activation+0.425
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
numerous
Token numerous
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
letters
Token letters
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.190
Top resid features:
Her
Token Her
Feature activation+0.142
Top resid features:
fing
Token fing
Feature activation+0.279
Top resid features:
ern
Tokenern
Feature activation+0.100
Top resid features:
ails
Tokenails
Feature activation+0.176
Top resid features:
gn
Token gn
Feature activation+0.781
Top resid features:
awed
Tokenawed
Feature activation+0.357
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
quick
Token quick
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.089
Top resid features:
shooting
Token shooting
Feature activation+0.125
Top resid features:
âĢ
TokenâĢ
Feature activation+0.052
Top resid features:
Ļ
TokenĻ
Feature activation+0.082
Top resid features:
s
Tokens
Feature activation+0.115
Top resid features:
d
Token d
Feature activation+1.037
Top resid features:
ail
Tokenail
Feature activation+0.159
Top resid features:
ies
Tokenies
Feature activation+0.452
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
reviewed
Token reviewed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
lake
Token lake
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.176
Top resid features:
has
Token has
Feature activation+0.152
Top resid features:
seen
Token seen
Feature activation+0.195
Top resid features:
its
Token its
Feature activation+0.244
Top resid features:
l
Token l
Feature activation+0.995
Top resid features:
uster
Tokenuster
Feature activation+0.324
Top resid features:
dim
Token dim
Feature activation+0.000
Top resid features:
med
Tokenmed
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
recent
Token recent
Feature activation+0.000
Top resid features:
whole
Token whole
Feature activation+0.051
Top resid features:
of
Token of
Feature activation+0.085
Top resid features:
this
Token this
Feature activation+0.108
Top resid features:
globe
Token globe
Feature activation+0.064
Top resid features:
can
Token can
Feature activation+0.149
Top resid features:
qu
Token qu
Feature activation+1.130
Top resid features:
iver
Tokeniver
Feature activation+0.472
Top resid features:
."[
Token."[
Feature activation+0.000
Top resid features:
21
Token21
Feature activation+0.000
Top resid features:
][
Token][
Feature activation+0.000
Top resid features:
22
Token22
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.053
Top resid features:
not
Token not
Feature activation+0.055
Top resid features:
been
Token been
Feature activation+0.105
Top resid features:
for
Token for
Feature activation+0.205
Top resid features:
the
Token the
Feature activation+0.229
Top resid features:
sprink
Token sprink
Feature activation+1.060
Top resid features:
ler
Tokenler
Feature activation+0.222
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
inside
Token inside
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pet
Token pet
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.065
Top resid features:
's
Token's
Feature activation+0.095
Top resid features:
too
Token too
Feature activation+0.081
Top resid features:
easy
Token easy
Feature activation+0.129
Top resid features:
to
Token to
Feature activation+0.226
Top resid features:
del
Token del
Feature activation+0.728
Top resid features:
ude
Tokenude
Feature activation+0.300
Top resid features:
ourselves
Token ourselves
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
serve
Token serve
Feature activation+0.058
Top resid features:
her
Token her
Feature activation+0.079
Top resid features:
.
Token.
Feature activation+0.235
Top resid features:
She
Token She
Feature activation+0.156
Top resid features:
uses
Token uses
Feature activation+0.236
Top resid features:
ins
Token ins
Feature activation+0.861
Top resid features:
ince
Tokenince
Feature activation+0.496
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
shallow
Token shallow
Feature activation+0.000
Top resid features:
affection
Token affection
Feature activation+0.000
Top resid features:
c
Tokenc
Feature activation+0.035
Top resid features:
)
Token)
Feature activation+0.114
Top resid features:
that
Token that
Feature activation+0.162
Top resid features:
receives
Token receives
Feature activation+0.161
Top resid features:
the
Token the
Feature activation+0.202
Top resid features:
vent
Token vent
Feature activation+0.622
Top resid features:
ral
Tokenral
Feature activation+0.531
Top resid features:
te
Token te
Feature activation+0.000
Top resid features:
gment
Tokengment
Feature activation+0.000
Top resid features:
al
Tokenal
Feature activation+0.000
Top resid features:
area
Token area
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.125
Top resid features:
And
Token And
Feature activation+0.124
Top resid features:
now
Token now
Feature activation+0.100
Top resid features:
,
Token,
Feature activation+0.223
Top resid features:
it
Token it
Feature activation+0.120
Top resid features:
r
Token r
Feature activation+0.991
Top resid features:
ained
Tokenained
Feature activation+0.420
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:
Florida
Token Florida
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.095
Top resid features:
an
Token an
Feature activation+0.062
Top resid features:
insidious
Token insidious
Feature activation+0.103
Top resid features:
drug
Token drug
Feature activation+0.056
Top resid features:
that
Token that
Feature activation+0.238
Top resid features:
ro
Token ro
Feature activation+1.039
Top resid features:
bs
Tokenbs
Feature activation+0.223
Top resid features:
addicts
Token addicts
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
true
Token true
Feature activation+0.000
Top resid features:
happiness
Token happiness
Feature activation+0.000
Top resid features:
military
Token military
Feature activation+0.053
Top resid features:
service
Token service
Feature activation+0.065
Top resid features:
,
Token,
Feature activation+0.221
Top resid features:
he
Token he
Feature activation+0.137
Top resid features:
is
Token is
Feature activation+0.217
Top resid features:
ev
Token ev
Feature activation+0.892
Top resid features:
ading
Tokenading
Feature activation+0.365
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
inaction
Token inaction
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.067
Top resid features:
America
Token America
Feature activation+0.062
Top resid features:
will
Token will
Feature activation+0.136
Top resid features:
start
Token start
Feature activation+0.138
Top resid features:
to
Token to
Feature activation+0.161
Top resid features:
d
Token d
Feature activation+1.151
Top resid features:
uke
Tokenuke
Feature activation+0.265
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Virginia
Token Virginia
Feature activation+0.000
Top resid features:
bats
Token bats
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.153
Top resid features:
We
Token We
Feature activation+0.146
Top resid features:
were
Token were
Feature activation+0.200
Top resid features:
just
Token just
Feature activation+0.087
Top resid features:
d
Token d
Feature activation+1.173
Top resid features:
renched
Tokenrenched
Feature activation+0.368
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
bat
Token bat
Feature activation+0.000
Top resid features:
pee
Token pee
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.069
Top resid features:
mountain
Token mountain
Feature activation+0.039
Top resid features:
gor
Token gor
Feature activation+0.095
Top resid features:
illas
Tokenillas
Feature activation+0.110
Top resid features:
are
Token are
Feature activation+0.244
Top resid features:
ent
Token ent
Feature activation+0.838
Top resid features:
ang
Tokenang
Feature activation+0.156
Top resid features:
lement
Tokenlement
Feature activation+0.561
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
hunting
Token hunting
Feature activation+0.000
Top resid features:
s
Token s
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.079
Top resid features:
sticks
Token sticks
Feature activation+0.069
Top resid features:
and
Token and
Feature activation+0.159
Top resid features:
rocks
Token rocks
Feature activation+0.085
Top resid features:
trump
Token trump
Feature activation+0.225
Top resid features:
bl
Token bl
Feature activation+0.811
Top resid features:
asters
Tokenasters
Feature activation+0.459
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
speed
Token speed
Feature activation+0.000
Top resid features:
er
Tokener
Feature activation+0.000
Top resid features:
bikes
Token bikes
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.14

Head 1: 0.08

Head 2: 0.17

Head 3: 0.05

Head 4: 0.13

Head 5: 0.03

Head 6: 0.05

Head 7: 0.05

Head 8: 0.06

Head 9: 0.04

Head 10: 0.14

Head 11: 0.06

Positive logits

geoning0.86

pear0.82

vested0.79

fever0.78

afore0.77

iously0.77

disc0.76

lic0.76

ass0.75

material0.75

enc0.75

cord0.73

arial0.72

perfection0.72

asses0.71

nerves0.71

peat0.71

cing0.70

sep0.70

decomp0.70

Negative logits

Citiz-0.96

inav-0.94

chwitz-0.91

Lines-0.89

Hobby-0.86

Month-0.85

Crimes-0.83

Charity-0.83

imir-0.82

Chau-0.82

Choi-0.81

Funding-0.81

ornings-0.81

Areas-0.81

Seas-0.81

Salary-0.80

Rica-0.80

Bus-0.80

Niet-0.80

Reincarn-0.80

INTERVAL 1.119 - 1.243
CONTAINS 0.001%

,
Token,
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
qu
Token qu
Feature activation+0.000
irk
Tokenirk
Feature activation+1.184
of
Token of
Feature activation+0.000
cinema
Token cinema
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
,
Token,
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
,
Token,
Feature activation+0.000
James
Token James
Feature activation+0.000
Hodg
Token Hodg
Feature activation+0.000
kinson
Tokenkinson
Feature activation+0.000
r
Token r
Feature activation+0.000
ailed
Tokenailed
Feature activation+1.142
in
Token in
Feature activation+0.013
numerous
Token numerous
Feature activation+0.000
public
Token public
Feature activation+0.000
letters
Token letters
Feature activation+0.126
to
Token to
Feature activation+0.000
authority
Token authority
Feature activation+0.000
to
Token to
Feature activation+0.000
investigate
Token investigate
Feature activation+0.000
every
Token every
Feature activation+0.000
sal
Token sal
Feature activation+0.000
acious
Tokenacious
Feature activation+1.158
claim
Token claim
Feature activation+0.000
or
Token or
Feature activation+0.000
rumor
Token rumor
Feature activation+0.000
about
Token about
Feature activation+0.000
him
Token him
Feature activation+0.000
as
Tokenas
Feature activation+0.717
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
the
Token the
Feature activation+0.000
le
Token le
Feature activation+0.000
aching
Tokenaching
Feature activation+1.232
being
Token being
Feature activation+0.000
mild
Token mild
Feature activation+0.000
.
Token.
Feature activation+0.000
Five
Token Five
Feature activation+0.000
out
Token out
Feature activation+0.000
donate
Token donate
Feature activation+0.000
your
Token your
Feature activation+0.000
cash
Token cash
Feature activation+0.000
to
Token to
Feature activation+0.000
qu
Token qu
Feature activation+0.000
acks
Tokenacks
Feature activation+1.243
,
Token,
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.033

INTERVAL 0.994 - 1.119
CONTAINS 0.000%

,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
seen
Token seen
Feature activation+0.000
its
Token its
Feature activation+0.000
l
Token l
Feature activation+0.000
uster
Tokenuster
Feature activation+1.004
dim
Token dim
Feature activation+0.000
med
Tokenmed
Feature activation+0.841
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
d
Token d
Feature activation+0.000
ail
Tokenail
Feature activation+0.930
ies
Tokenies
Feature activation+1.098
were
Token were
Feature activation+0.000
reviewed
Token reviewed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
studio
Token studio
Feature activation+0.000
Her
Token Her
Feature activation+0.000
fing
Token fing
Feature activation+0.000
ern
Tokenern
Feature activation+0.852
ails
Tokenails
Feature activation+0.508
gn
Token gn
Feature activation+0.219
awed
Tokenawed
Feature activation+1.116
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
quick
Token quick
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000

INTERVAL 0.870 - 0.994
CONTAINS 0.005%

surrounded
Token surrounded
Feature activation+0.000
by
Token by
Feature activation+0.000
manic
Token manic
Feature activation+0.000
ured
Tokenured
Feature activation+0.600
hed
Token hed
Feature activation+0.000
ges
Tokenges
Feature activation+0.882
,
Token,
Feature activation+0.000
lawn
Token lawn
Feature activation+0.000
s
Tokens
Feature activation+0.570
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
sprink
Token sprink
Feature activation+0.000
ler
Tokenler
Feature activation+0.990
system
Token system
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
pet
Token pet
Feature activation+0.000
store
Token store
Feature activation+0.000
friends
Token friends
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
heart
Token heart
Feature activation+0.000
p
Token p
Feature activation+0.000
ours
Tokenours
Feature activation+0.948
out
Token out
Feature activation+0.007
to
Token to
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
and
Token and
Feature activation+0.000
hack
Token hack
Feature activation+0.000
les
Tokenles
Feature activation+0.317
were
Token were
Feature activation+0.000
r
Token r
Feature activation+0.000
uff
Tokenuff
Feature activation+0.907
led
Tokenled
Feature activation+0.887
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000
overheard
Token overheard
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
which
Token which
Feature activation+0.000
frequently
Token frequently
Feature activation+0.000
end
Token end
Feature activation+0.000
with
Token with
Feature activation+0.000
pl
Token pl
Feature activation+0.000
umes
Tokenumes
Feature activation+0.880
of
Token of
Feature activation+0.000
tear
Token tear
Feature activation+0.000
gas
Token gas
Feature activation+0.253
and
Token and
Feature activation+0.000
shots
Token shots
Feature activation+0.000

INTERVAL 0.746 - 0.870
CONTAINS 0.011%

gone
Token gone
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
tall
Token tall
Feature activation+0.000
p
Token p
Feature activation+0.000
ines
Tokenines
Feature activation+0.772
grow
Token grow
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
fl
Token fl
Feature activation+0.000
or
Tokenor
Feature activation+0.546
ists
Tokenists
Feature activation+0.610
,
Token,
Feature activation+0.000
baker
Token baker
Feature activation+0.000
ies
Tokenies
Feature activation+0.849
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
photographers
Token photographers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
flowers
Token flowers
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
da
Token da
Feature activation+0.000
isy
Tokenisy
Feature activation+0.867
chain
Token chain
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Most
TokenMost
Feature activation+0.000
Guard
Token Guard
Feature activation+0.000
dies
Token dies
Feature activation+0.000
but
Token but
Feature activation+0.000
never
Token never
Feature activation+0.000
sur
Token sur
Feature activation+0.000
rend
Tokenrend
Feature activation+0.852
ers
Tokeners
Feature activation+0.390
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
knee
Token knee
Feature activation+0.000
fem
Token fem
Feature activation+0.000
oral
Tokenoral
Feature activation+0.523
ch
Token ch
Feature activation+0.000
ond
Tokenond
Feature activation+0.595
ral
Tokenral
Feature activation+0.769
defect
Token defect
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
tro
Token tro
Feature activation+0.000
ch
Tokench
Feature activation+0.217

INTERVAL 0.622 - 0.746
CONTAINS 0.020%

,
Token,
Feature activation+0.000
seem
Token seem
Feature activation+0.000
like
Token like
Feature activation+0.000
a
Token a
Feature activation+0.000
tr
Token tr
Feature activation+0.000
ifle
Tokenifle
Feature activation+0.650
to
Token to
Feature activation+0.000
workers
Token workers
Feature activation+0.000
all
Token all
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
others
Token others
Feature activation+0.000
whose
Token whose
Feature activation+0.000
genius
Token genius
Feature activation+0.000
bl
Token bl
Feature activation+0.000
ed
Tokened
Feature activation+0.626
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
trenches
Token trenches
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
run
Token run
Feature activation+0.000
large
Token large
Feature activation+0.000
trade
Token trade
Feature activation+0.000
sur
Token sur
Feature activation+0.000
pl
Tokenpl
Feature activation+0.604
uses
Tokenuses
Feature activation+0.634
or
Token or
Feature activation+0.000
deficits
Token deficits
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
would
Token would
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.000
his
Token his
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
sw
Token sw
Feature activation+0.000
ells
Tokenells
Feature activation+0.646
onboard
Token onboard
Feature activation+0.000
the
Token the
Feature activation+0.000
cruise
Token cruise
Feature activation+0.000
liner
Token liner
Feature activation+0.074
to
Token to
Feature activation+0.000
babies
Token babies
Feature activation+0.000
opt
Token opt
Feature activation+0.035
for
Token for
Feature activation+0.034
ca
Token ca
Feature activation+0.023
es
Tokenes
Feature activation+0.668
are
Tokenare
Feature activation+0.704
an
Tokenan
Feature activation+0.287
sections
Token sections
Feature activation+0.000
.
Token.
Feature activation+0.000
Gene
Token Gene
Feature activation+0.000
trait
Token trait
Feature activation+0.000

INTERVAL 0.497 - 0.622
CONTAINS 0.037%

e
Tokene
Feature activation+0.000
ered
Tokenered
Feature activation+0.203
an
Token an
Feature activation+0.000
Army
Token Army
Feature activation+0.000
je
Token je
Feature activation+0.000
ep
Tokenep
Feature activation+0.554
and
Token and
Feature activation+0.000
returned
Token returned
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
front
Token front
Feature activation+0.000
the
Token the
Feature activation+0.000
Liga
Token Liga
Feature activation+0.000
MX
Token MX
Feature activation+0.000
top
Token top
Feature activation+0.000
f
Token f
Feature activation+0.000
ives
Tokenives
Feature activation+0.553
in
Token in
Feature activation+0.000
certain
Token certain
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
their
Token their
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
of
Token of
Feature activation+0.000
tink
Token tink
Feature activation+0.000
ering
Tokenering
Feature activation+0.565
,
Token,
Feature activation+0.000
driving
Token driving
Feature activation+0.000
,
Token,
Feature activation+0.000
modifying
Token modifying
Feature activation+0.000
,
Token,
Feature activation+0.000
me
Token me
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
is
Token is
Feature activation+0.000
br
Token br
Feature activation+0.000
agg
Tokenagg
Feature activation+0.514
ot
Tokenot
Feature activation+0.540
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
anything
Token anything
Feature activation+0.000
that
Token that
Feature activation+0.000
rh
Token rh
Feature activation+0.000
hardly
Token hardly
Feature activation+0.000
any
Token any
Feature activation+0.000
ling
Token ling
Feature activation+0.000
ua
Tokenua
Feature activation+0.743
fr
Token fr
Feature activation+0.127
anca
Tokenanca
Feature activation+0.538
could
Token could
Feature activation+0.000
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

INTERVAL 0.373 - 0.497
CONTAINS 0.053%

federal
Token federal
Feature activation+0.000
funding
Token funding
Feature activation+0.000
must
Token must
Feature activation+0.000
'
Token '
Feature activation+0.000
t
Tokent
Feature activation+0.000
reat
Tokenreat
Feature activation+0.430
a
Token a
Feature activation+0.000
student
Token student
Feature activation+0.000
's
Token's
Feature activation+0.000
gender
Token gender
Feature activation+0.000
identity
Token identity
Feature activation+0.000
specializes
Token specializes
Feature activation+0.000
in
Token in
Feature activation+0.000
kale
Token kale
Feature activation+0.000
h
Tokenh
Feature activation+0.356
p
Token p
Feature activation+0.000
ache
Tokenache
Feature activation+0.479
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
"
Token "
Feature activation+0.000
heads
Tokenheads
Feature activation+0.002
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Moreover
Token Moreover
Feature activation+0.000
,
Token,
Feature activation+0.000
its
Token its
Feature activation+0.000
antiqu
Token antiqu
Feature activation+0.000
ated
Tokenated
Feature activation+0.414
power
Token power
Feature activation+0.000
plants
Token plants
Feature activation+0.000
burn
Token burn
Feature activation+0.000
the
Token the
Feature activation+0.000
oil
Token oil
Feature activation+0.000
the
Token the
Feature activation+0.000
month
Token month
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
empt
Token empt
Feature activation+0.000
ies
Tokenies
Feature activation+0.377
out
Token out
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
residents
Token residents
Feature activation+0.000
head
Token head
Feature activation+0.000
head
Token head
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
debris
Token debris
Feature activation+0.000
ric
Token ric
Feature activation+0.000
oche
Tokenoche
Feature activation+0.405
ted
Tokented
Feature activation+0.155
high
Token high
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000

INTERVAL 0.249 - 0.373
CONTAINS 0.074%

he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
,
Token,
Feature activation+0.000
qu
Token qu
Feature activation+0.000
en
Tokenen
Feature activation+0.134
ches
Tokenches
Feature activation+0.311
the
Token the
Feature activation+0.000
thirst
Token thirst
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
many
Token many
Feature activation+0.000
vas
Token vas
Feature activation+0.000
ect
Tokenect
Feature activation+0.580
om
Tokenom
Feature activation+0.321
ies
Tokenies
Feature activation+0.661
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
performed
Token performed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
23
Token 23
Feature activation+0.000
nucle
Token nucle
Feature activation+0.000
otide
Tokenotide
Feature activation+0.155
pl
Token pl
Feature activation+0.000
asm
Tokenasm
Feature activation+0.272
id
Tokenid
Feature activation+0.146
target
Token target
Feature activation+0.000
sequence
Token sequence
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
before
Token before
Feature activation+0.000
someone
Token someone
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
her
Token her
Feature activation+0.000
skim
Token skim
Feature activation+0.000
py
Tokenpy
Feature activation+0.357
tank
Token tank
Feature activation+0.000
top
Token top
Feature activation+0.000
and
Token and
Feature activation+0.000
tight
Token tight
Feature activation+0.000
,
Token,
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
feelings
Token feelings
Feature activation+0.000
for
Token for
Feature activation+0.000
anthrop
Token anthrop
Feature activation+0.000
omorph
Tokenomorph
Feature activation+0.074
ized
Tokenized
Feature activation+0.321
animals
Token animals
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

INTERVAL 0.124 - 0.249
CONTAINS 0.102%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
col
Tokencol
Feature activation+0.000
on
Tokenon
Feature activation+0.206
els
Tokenels
Feature activation+0.162
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
iment
Tokeniment
Feature activation+0.182
in
Token in
Feature activation+0.000
hyper
Token hyper
Feature activation+0.000
liter
Tokenliter
Feature activation+0.179
ary
Tokenary
Feature activation+0.458
comedy
Token comedy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
filled
Token filled
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
,
Token,
Feature activation+0.000
Rudy
Token Rudy
Feature activation+0.000
Hu
Token Hu
Feature activation+0.000
xt
Tokenxt
Feature activation+0.000
able
Tokenable
Feature activation+0.190
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
landmark
Token landmark
Feature activation+0.000
television
Token television
Feature activation+0.000
cad
Token cad
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
is
Token is
Feature activation+0.000
recogn
Token recogn
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
ably
Tokenably
Feature activation+0.147
his
Token his
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
a
Token a
Feature activation+0.000
subsequent
Token subsequent
Feature activation+0.000
co
Tokenco
Feature activation+0.000
wine
Token wine
Feature activation+0.000
barrels
Token barrels
Feature activation+0.000
with
Token with
Feature activation+0.000
bre
Token bre
Feature activation+0.000
tt
Tokentt
Feature activation+0.225
an
Tokenan
Feature activation+0.000
omy
Tokenomy
Feature activation+0.000
ces
Tokences
Feature activation+0.063
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 0.000 - 0.124
CONTAINS 99.697%

inventions
Token inventions
Feature activation+0.000
'
Token '
Feature activation+0.000
ideal
Token ideal
Feature activation+0.000
'.
Token '.
Feature activation+0.000
He
Token He
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
'
Token '
Feature activation+0.000
we
Token we
Feature activation+0.000
.
Token.
Feature activation+0.000
Grimoire
Token Grimoire
Feature activation+0.000
of
Token of
Feature activation+0.000
Sup
Token Sup
Feature activation+0.000
rem
Tokenrem
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
effect
Token effect
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
-
Token-
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
WAR
Token WAR
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
three
Token three
Feature activation+0.000
,
Token,
Feature activation+0.000
Issa
Token Issa
Feature activation+0.000
is
Token is
Feature activation+0.000
getting
Token getting
Feature activation+0.000
his
Token his
Feature activation+0.000
cue
Token cue
Feature activation+0.000
from
Token from
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
voice
Token voice
Feature activation+0.000
to
Token to
Feature activation+0.000
]
Token]
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
elected
Token elected
Feature activation+0.000
a
Token a
Feature activation+0.000
Fellow
Token Fellow
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Royal
Token Royal
Feature activation+0.000
Society
Token Society
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H1.2: (feature 3987)

TOP ACTIVATIONS
MAX = 1.516

."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.101
Ċ
TokenĊ
Feature activation+0.391
A
TokenA
Feature activation+0.903
new
Token new
Feature activation+1.348
exhibition
Token exhibition
Feature activation+1.516
commemor
Token commemor
Feature activation+1.066
ating
Tokenating
Feature activation+1.107
the
Token the
Feature activation+0.752
ill
Token ill
Feature activation+0.724
-
Token-
Feature activation+0.631
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.012
Ċ
TokenĊ
Feature activation+0.296
Each
TokenEach
Feature activation+0.966
round
Token round
Feature activation+1.494
will
Token will
Feature activation+1.135
have
Token have
Feature activation+1.061
a
Token a
Feature activation+0.862
set
Token set
Feature activation+0.733
date
Token date
Feature activation+0.732
problem
Token problem
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
His
TokenHis
Feature activation+0.901
father
Token father
Feature activation+1.417
,
Token,
Feature activation+0.785
who
Token who
Feature activation+0.831
shares
Token shares
Feature activation+0.795
the
Token the
Feature activation+0.697
same
Token same
Feature activation+0.683
forward
Token forward
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
Ar
TokenAr
Feature activation+0.797
n
Tokenn
Feature activation+1.375
old
Tokenold
Feature activation+1.367
Pl
Token Pl
Feature activation+1.247
ick
Tokenick
Feature activation+1.096
ert
Tokenert
Feature activation+1.148
,
Token,
Feature activation+0.779
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.362
Plan
TokenPlan
Feature activation+0.809
ets
Tokenets
Feature activation+1.374
in
Token in
Feature activation+1.075
other
Token other
Feature activation+0.938
systems
Token systems
Feature activation+0.965
,
Token,
Feature activation+0.434
including
Token including
Feature activation+0.428
.
Token.
Feature activation+0.785
io
Tokenio
Feature activation+0.982
Ċ
TokenĊ
Feature activation+0.561
Ċ
TokenĊ
Feature activation+0.734
Create
TokenCreate
Feature activation+1.225
a
Token a
Feature activation+1.371
simple
Token simple
Feature activation+1.197
web
Token web
Feature activation+1.154
chat
Token chat
Feature activation+1.136
to
Token to
Feature activation+0.673
share
Token share
Feature activation+0.684
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.005
Ċ
TokenĊ
Feature activation+0.330
An
TokenAn
Feature activation+0.900
O
Token O
Feature activation+1.137
SC
TokenSC
Feature activation+1.368
R
TokenR
Feature activation+1.266
spokesman
Token spokesman
Feature activation+1.015
yesterday
Token yesterday
Feature activation+0.988
said
Token said
Feature activation+0.513
any
Token any
Feature activation+0.180
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
Ar
TokenAr
Feature activation+0.797
n
Tokenn
Feature activation+1.375
old
Tokenold
Feature activation+1.367
Pl
Token Pl
Feature activation+1.247
ick
Tokenick
Feature activation+1.096
ert
Tokenert
Feature activation+1.148
,
Token,
Feature activation+0.779
head
Token head
Feature activation+0.854
consequences
Token consequences
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.129
North
TokenNorth
Feature activation+0.856
land
Tokenland
Feature activation+1.351
Forest
Token Forest
Feature activation+1.289
Products
Token Products
Feature activation+1.110
chief
Token chief
Feature activation+1.091
executive
Token executive
Feature activation+0.904
James
Token James
Feature activation+0.747
back
Token back
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.101
Ċ
TokenĊ
Feature activation+0.391
A
TokenA
Feature activation+0.903
new
Token new
Feature activation+1.348
exhibition
Token exhibition
Feature activation+1.516
commemor
Token commemor
Feature activation+1.066
ating
Tokenating
Feature activation+1.107
the
Token the
Feature activation+0.752
ill
Token ill
Feature activation+0.724
moves
Token moves
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.185
Ċ
TokenĊ
Feature activation+0.463
South
TokenSouth
Feature activation+1.079
Dakota
Token Dakota
Feature activation+1.332
had
Token had
Feature activation+0.939
the
Token the
Feature activation+0.832
highest
Token highest
Feature activation+0.787
share
Token share
Feature activation+0.956
of
Token of
Feature activation+0.676
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.004
Ċ
TokenĊ
Feature activation+0.345
Over
TokenOver
Feature activation+0.852
the
Token the
Feature activation+1.328
last
Token last
Feature activation+1.274
year
Token year
Feature activation+1.155
many
Token many
Feature activation+0.979
Americans
Token Americans
Feature activation+0.816
have
Token have
Feature activation+0.672
much
Token much
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.083
Latin
TokenLatin
Feature activation+1.074
America
Token America
Feature activation+1.323
's
Token's
Feature activation+1.012
biggest
Token biggest
Feature activation+0.960
detention
Token detention
Feature activation+0.843
centre
Token centre
Feature activation+0.747
Ċ
TokenĊ
Feature activation+0.000
still
Tokenstill
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.345
Mat
TokenMat
Feature activation+0.799
u
Tokenu
Feature activation+1.317
idi
Tokenidi
Feature activation+1.120
is
Token is
Feature activation+1.092
to
Token to
Feature activation+0.785
marry
Token marry
Feature activation+1.018
the
Token the
Feature activation+0.815
number
Token number
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.350
Only
TokenOnly
Feature activation+0.947
20
Token 20
Feature activation+1.316
percent
Token percent
Feature activation+1.312
strongly
Token strongly
Feature activation+1.261
approved
Token approved
Feature activation+0.970
of
Token of
Feature activation+0.801
the
Token the
Feature activation+0.734
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.350
Only
TokenOnly
Feature activation+0.947
20
Token 20
Feature activation+1.316
percent
Token percent
Feature activation+1.312
strongly
Token strongly
Feature activation+1.261
approved
Token approved
Feature activation+0.970
of
Token of
Feature activation+0.801
the
Token the
Feature activation+0.734
job
Token job
Feature activation+0.671
victory
Token victory
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.257
A
TokenA
Feature activation+0.859
brief
Token brief
Feature activation+1.305
scene
Token scene
Feature activation+1.151
in
Token in
Feature activation+0.997
an
Token an
Feature activation+1.011
almost
Token almost
Feature activation+1.074
empty
Token empty
Feature activation+0.886
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.176
Rep
TokenRep
Feature activation+0.633
orted
Tokenorted
Feature activation+1.300
by
Token by
Feature activation+1.094
a
Token a
Feature activation+0.932
Hert
Token Hert
Feature activation+0.803
ford
Tokenford
Feature activation+0.901
College
Token College
Feature activation+0.797
awareness
Token awareness
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.071
Ċ
TokenĊ
Feature activation+0.425
Live
TokenLive
Feature activation+0.954
in
Token in
Feature activation+1.300
the
Token the
Feature activation+1.128
moment
Token moment
Feature activation+1.248
.
Token.
Feature activation+0.915
Ċ
TokenĊ
Feature activation+0.557
Ċ
TokenĊ
Feature activation+0.680
2019
Token 2019
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.139
South
TokenSouth
Feature activation+0.722
Africa
Token Africa
Feature activation+1.298
has
Token has
Feature activation+0.754
struggled
Token struggled
Feature activation+0.876
to
Token to
Feature activation+0.768
deliver
Token deliver
Feature activation+0.751
growth
Token growth
Feature activation+0.707

Top DFA by src position
MAX = 0.838

quickly
Token quickly
Feature activation+0.049
Top resid features:
brings
Token brings
Feature activation+0.108
Top resid features:
them
Token them
Feature activation+0.076
Top resid features:
back
Token back
Feature activation+0.099
Top resid features:
."
Token."
Feature activation+0.293
Top resid features:
Ċ
TokenĊ
Feature activation+0.632
Top resid features:
Ċ
TokenĊ
Feature activation+0.557
Top resid features:
A
TokenA
Feature activation+0.476
Top resid features:
new
Token new
Feature activation+0.325
Top resid features:
exhibition
Token exhibition
Feature activation+0.096
Top resid features:
commemor
Token commemor
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.065
Top resid features:
events
Token events
Feature activation+0.063
Top resid features:
like
Token like
Feature activation+0.125
Top resid features:
this
Token this
Feature activation+0.068
Top resid features:
.
Token.
Feature activation+0.326
Top resid features:
Ċ
TokenĊ
Feature activation+0.666
Top resid features:
Ċ
TokenĊ
Feature activation+0.637
Top resid features:
Each
TokenEach
Feature activation+0.588
Top resid features:
round
Token round
Feature activation+0.171
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
part
Token part
Feature activation+0.079
Top resid features:
of
Token of
Feature activation+0.114
Top resid features:
the
Token the
Feature activation+0.107
Top resid features:
problem
Token problem
Feature activation+0.089
Top resid features:
.
Token.
Feature activation+0.372
Top resid features:
Ċ
TokenĊ
Feature activation+0.774
Top resid features:
Ċ
TokenĊ
Feature activation+0.756
Top resid features:
His
TokenHis
Feature activation+0.494
Top resid features:
father
Token father
Feature activation+0.183
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.110
Top resid features:
come
Token come
Feature activation+0.092
Top resid features:
forward
Token forward
Feature activation+0.117
Top resid features:
.
Token.
Feature activation+0.303
Top resid features:
Ċ
TokenĊ
Feature activation+0.820
Top resid features:
Ċ
TokenĊ
Feature activation+0.838
Top resid features:
Ar
TokenAr
Feature activation+0.467
Top resid features:
n
Tokenn
Feature activation+0.149
Top resid features:
old
Tokenold
Feature activation+0.000
Top resid features:
Pl
Token Pl
Feature activation+0.000
Top resid features:
ick
Tokenick
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.085
Top resid features:
peanuts
Token peanuts
Feature activation+0.070
Top resid features:
.
Token.
Feature activation+0.233
Top resid features:
âĢ
TokenâĢ
Feature activation+0.111
Top resid features:
Ŀ
TokenĿ
Feature activation+0.119
Top resid features:
Ċ
TokenĊ
Feature activation+0.787
Top resid features:
Ċ
TokenĊ
Feature activation+0.765
Top resid features:
Plan
TokenPlan
Feature activation+0.395
Top resid features:
ets
Tokenets
Feature activation+0.145
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
l
Tokenl
Feature activation+0.082
Top resid features:
k
Tokenk
Feature activation+0.099
Top resid features:
.
Token.
Feature activation+0.129
Top resid features:
io
Tokenio
Feature activation+0.124
Top resid features:
Ċ
TokenĊ
Feature activation+0.501
Top resid features:
Ċ
TokenĊ
Feature activation+0.515
Top resid features:
Create
TokenCreate
Feature activation+0.405
Top resid features:
a
Token a
Feature activation+0.162
Top resid features:
simple
Token simple
Feature activation+0.000
Top resid features:
web
Token web
Feature activation+0.000
Top resid features:
chat
Token chat
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.096
Top resid features:
their
Token their
Feature activation+0.058
Top resid features:
ruling
Token ruling
Feature activation+0.071
Top resid features:
committees
Token committees
Feature activation+0.058
Top resid features:
.
Token.
Feature activation+0.323
Top resid features:
Ċ
TokenĊ
Feature activation+0.694
Top resid features:
Ċ
TokenĊ
Feature activation+0.691
Top resid features:
An
TokenAn
Feature activation+0.349
Top resid features:
O
Token O
Feature activation+0.208
Top resid features:
SC
TokenSC
Feature activation+0.111
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.096
Top resid features:
come
Token come
Feature activation+0.086
Top resid features:
forward
Token forward
Feature activation+0.097
Top resid features:
.
Token.
Feature activation+0.304
Top resid features:
Ċ
TokenĊ
Feature activation+0.743
Top resid features:
Ċ
TokenĊ
Feature activation+0.800
Top resid features:
Ar
TokenAr
Feature activation+0.387
Top resid features:
n
Tokenn
Feature activation+0.238
Top resid features:
old
Tokenold
Feature activation+0.153
Top resid features:
Pl
Token Pl
Feature activation+0.000
Top resid features:
ick
Tokenick
Feature activation+0.000
Top resid features:
economic
Token economic
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.097
Top resid features:
ecological
Token ecological
Feature activation+0.082
Top resid features:
consequences
Token consequences
Feature activation+0.099
Top resid features:
.
Token.
Feature activation+0.353
Top resid features:
Ċ
TokenĊ
Feature activation+0.807
Top resid features:
Ċ
TokenĊ
Feature activation+0.792
Top resid features:
North
TokenNorth
Feature activation+0.444
Top resid features:
land
Tokenland
Feature activation+0.231
Top resid features:
Forest
Token Forest
Feature activation+0.000
Top resid features:
Products
Token Products
Feature activation+0.000
Top resid features:
quickly
Token quickly
Feature activation+0.066
Top resid features:
brings
Token brings
Feature activation+0.118
Top resid features:
them
Token them
Feature activation+0.082
Top resid features:
back
Token back
Feature activation+0.122
Top resid features:
."
Token."
Feature activation+0.289
Top resid features:
Ċ
TokenĊ
Feature activation+0.675
Top resid features:
Ċ
TokenĊ
Feature activation+0.630
Top resid features:
A
TokenA
Feature activation+0.376
Top resid features:
new
Token new
Feature activation+0.157
Top resid features:
exhibition
Token exhibition
Feature activation+0.000
Top resid features:
commemor
Token commemor
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.099
Top resid features:
in
Token in
Feature activation+0.133
Top resid features:
bound
Tokenbound
Feature activation+0.098
Top resid features:
moves
Token moves
Feature activation+0.082
Top resid features:
.
Token.
Feature activation+0.283
Top resid features:
Ċ
TokenĊ
Feature activation+0.689
Top resid features:
Ċ
TokenĊ
Feature activation+0.632
Top resid features:
South
TokenSouth
Feature activation+0.333
Top resid features:
Dakota
Token Dakota
Feature activation+0.210
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.119
Top resid features:
talking
Token talking
Feature activation+0.095
Top resid features:
about
Token about
Feature activation+0.126
Top resid features:
it
Token it
Feature activation+0.082
Top resid features:
.
Token.
Feature activation+0.313
Top resid features:
Ċ
TokenĊ
Feature activation+0.684
Top resid features:
Ċ
TokenĊ
Feature activation+0.657
Top resid features:
Over
TokenOver
Feature activation+0.482
Top resid features:
the
Token the
Feature activation+0.208
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
10
Token 10
Feature activation+0.091
Top resid features:
times
Token times
Feature activation+0.043
Top resid features:
as
Token as
Feature activation+0.100
Top resid features:
much
Token much
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.307
Top resid features:
Ċ
TokenĊ
Feature activation+0.771
Top resid features:
Ċ
TokenĊ
Feature activation+0.737
Top resid features:
Latin
TokenLatin
Feature activation+0.366
Top resid features:
America
Token America
Feature activation+0.129
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
biggest
Token biggest
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.088
Top resid features:
a
Token a
Feature activation+0.088
Top resid features:
stand
Token stand
Feature activation+0.080
Top resid features:
still
Tokenstill
Feature activation+0.108
Top resid features:
.
Token.
Feature activation+0.287
Top resid features:
Ċ
TokenĊ
Feature activation+0.807
Top resid features:
Ċ
TokenĊ
Feature activation+0.804
Top resid features:
Mat
TokenMat
Feature activation+0.449
Top resid features:
u
Tokenu
Feature activation+0.065
Top resid features:
idi
Tokenidi
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
ness
Tokenness
Feature activation+0.062
Top resid features:
in
Token in
Feature activation+0.121
Top resid features:
that
Token that
Feature activation+0.098
Top resid features:
number
Token number
Feature activation+0.045
Top resid features:
.
Token.
Feature activation+0.317
Top resid features:
Ċ
TokenĊ
Feature activation+0.795
Top resid features:
Ċ
TokenĊ
Feature activation+0.724
Top resid features:
Only
TokenOnly
Feature activation+0.346
Top resid features:
20
Token 20
Feature activation+0.207
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
strongly
Token strongly
Feature activation+0.000
Top resid features:
ness
Tokenness
Feature activation+0.062
Top resid features:
in
Token in
Feature activation+0.130
Top resid features:
that
Token that
Feature activation+0.109
Top resid features:
number
Token number
Feature activation+0.079
Top resid features:
.
Token.
Feature activation+0.342
Top resid features:
Ċ
TokenĊ
Feature activation+0.751
Top resid features:
Ċ
TokenĊ
Feature activation+0.707
Top resid features:
Only
TokenOnly
Feature activation+0.306
Top resid features:
20
Token 20
Feature activation+0.209
Top resid features:
percent
Token percent
Feature activation+0.072
Top resid features:
strongly
Token strongly
Feature activation+0.000
Top resid features:
enjoying
Token enjoying
Feature activation+0.081
Top resid features:
a
Token a
Feature activation+0.084
Top resid features:
sweet
Token sweet
Feature activation+0.104
Top resid features:
victory
Token victory
Feature activation+0.074
Top resid features:
.
Token.
Feature activation+0.312
Top resid features:
Ċ
TokenĊ
Feature activation+0.782
Top resid features:
Ċ
TokenĊ
Feature activation+0.731
Top resid features:
A
TokenA
Feature activation+0.542
Top resid features:
brief
Token brief
Feature activation+0.105
Top resid features:
scene
Token scene
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
White
Token White
Feature activation+0.077
Top resid features:
head
Tokenhead
Feature activation+0.126
Top resid features:
says
Token says
Feature activation+0.083
Top resid features:
.
Token.
Feature activation+0.292
Top resid features:
Ċ
TokenĊ
Feature activation+0.746
Top resid features:
Ċ
TokenĊ
Feature activation+0.737
Top resid features:
Rep
TokenRep
Feature activation+0.288
Top resid features:
orted
Tokenorted
Feature activation+0.218
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.072
Top resid features:
moment
Token moment
Feature activation+0.087
Top resid features:
with
Token with
Feature activation+0.136
Top resid features:
awareness
Token awareness
Feature activation+0.058
Top resid features:
.
Token.
Feature activation+0.310
Top resid features:
Ċ
TokenĊ
Feature activation+0.717
Top resid features:
Ċ
TokenĊ
Feature activation+0.713
Top resid features:
Live
TokenLive
Feature activation+0.403
Top resid features:
in
Token in
Feature activation+0.242
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
moment
Token moment
Feature activation+0.000
Top resid features:
lo
Token lo
Feature activation+0.060
Top resid features:
om
Tokenom
Feature activation+0.060
Top resid features:
in
Token in
Feature activation+0.152
Top resid features:
2019
Token 2019
Feature activation+0.096
Top resid features:
.
Token.
Feature activation+0.312
Top resid features:
Ċ
TokenĊ
Feature activation+0.797
Top resid features:
Ċ
TokenĊ
Feature activation+0.735
Top resid features:
South
TokenSouth
Feature activation+0.357
Top resid features:
Africa
Token Africa
Feature activation+0.298
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
struggled
Token struggled
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.13

Head 2: 0.17

Head 3: 0.10

Head 4: 0.12

Head 5: 0.04

Head 6: 0.02

Head 7: 0.06

Head 8: 0.07

Head 9: 0.06

Head 10: 0.15

Head 11: 0.04

Positive logits

disclaimer0.64

endum0.62

resa0.59

DragonMagazine0.59

iple0.59

question0.59

QUEST0.58

however0.57

Courier0.57

misunderstand0.55

escription0.55

Horus0.55

Profile0.55

Banner0.54

aside0.54

Explan0.53

Pathfinder0.53

:=0.53

undrum0.53

iologist0.53

Negative logits

respectively-0.79

$.-0.78

%.-0.71

]."-0.71

.).-0.67

$$-0.66

..."-0.65

].-0.64

."[-0.63

().-0.61

thereof-0.61

SPONSORED-0.60

?).-0.59

!.-0.59

Establishment-0.59

).[-0.57

#$-0.57

".[-0.57

zona-0.57

rouse-0.57

INTERVAL 1.364 - 1.516
CONTAINS 0.001%

forward
Token forward
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
Ar
TokenAr
Feature activation+0.797
n
Tokenn
Feature activation+1.375
old
Tokenold
Feature activation+1.367
Pl
Token Pl
Feature activation+1.247
ick
Tokenick
Feature activation+1.096
ert
Tokenert
Feature activation+1.148
,
Token,
Feature activation+0.779
problem
Token problem
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.335
His
TokenHis
Feature activation+0.901
father
Token father
Feature activation+1.417
,
Token,
Feature activation+0.785
who
Token who
Feature activation+0.831
shares
Token shares
Feature activation+0.795
the
Token the
Feature activation+0.697
same
Token same
Feature activation+0.683
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.101
Ċ
TokenĊ
Feature activation+0.391
A
TokenA
Feature activation+0.903
new
Token new
Feature activation+1.348
exhibition
Token exhibition
Feature activation+1.516
commemor
Token commemor
Feature activation+1.066
ating
Tokenating
Feature activation+1.107
the
Token the
Feature activation+0.752
ill
Token ill
Feature activation+0.724
-
Token-
Feature activation+0.631
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.289
Ar
TokenAr
Feature activation+0.797
n
Tokenn
Feature activation+1.375
old
Tokenold
Feature activation+1.367
Pl
Token Pl
Feature activation+1.247
ick
Tokenick
Feature activation+1.096
ert
Tokenert
Feature activation+1.148
,
Token,
Feature activation+0.779
head
Token head
Feature activation+0.854
.
Token.
Feature activation+0.785
io
Tokenio
Feature activation+0.982
Ċ
TokenĊ
Feature activation+0.561
Ċ
TokenĊ
Feature activation+0.734
Create
TokenCreate
Feature activation+1.225
a
Token a
Feature activation+1.371
simple
Token simple
Feature activation+1.197
web
Token web
Feature activation+1.154
chat
Token chat
Feature activation+1.136
to
Token to
Feature activation+0.673
share
Token share
Feature activation+0.684

INTERVAL 1.212 - 1.364
CONTAINS 0.008%

others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.116
Scroll
TokenScroll
Feature activation+0.775
down
Token down
Feature activation+1.215
for
Token for
Feature activation+1.064
video
Token video
Feature activation+1.023
Ċ
TokenĊ
Feature activation+0.407
Ċ
TokenĊ
Feature activation+0.482
Em
TokenEm
Feature activation+0.660
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.170
The
TokenThe
Feature activation+0.836
number
Token number
Feature activation+1.260
of
Token of
Feature activation+1.053
House
Token House
Feature activation+1.090
rank
Token rank
Feature activation+1.018
-
Token-
Feature activation+0.824
and
Tokenand
Feature activation+0.790
history
Token history
Feature activation+1.201
Ċ
TokenĊ
Feature activation+0.651
Ċ
TokenĊ
Feature activation+0.763
Wikipedia
TokenWikipedia
Feature activation+0.950
officially
Token officially
Feature activation+1.140
launched
Token launched
Feature activation+1.240
on
Token on
Feature activation+1.015
15
Token 15
Feature activation+0.717
January
Token January
Feature activation+0.733
2001
Token 2001
Feature activation+0.523
,
Token,
Feature activation+0.246
charge
Token charge
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.155
District
TokenDistrict
Feature activation+1.003
Court
Token Court
Feature activation+1.257
records
Token records
Feature activation+1.167
indicate
Token indicate
Feature activation+0.782
that
Token that
Feature activation+0.393
Den
Token Den
Feature activation+0.356
ne
Tokenne
Feature activation+0.443
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.001
Ċ
TokenĊ
Feature activation+0.287
You
TokenYou
Feature activation+0.867
may
Token may
Feature activation+1.070
already
Token already
Feature activation+1.240
extend
Token extend
Feature activation+0.945
your
Token your
Feature activation+0.905
game
Token game
Feature activation+0.757
time
Token time
Feature activation+0.528
by
Token by
Feature activation+0.255

INTERVAL 1.061 - 1.212
CONTAINS 0.036%

say
Token say
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.231
In
TokenIn
Feature activation+0.703
order
Token order
Feature activation+1.071
to
Token to
Feature activation+0.793
st
Token st
Feature activation+0.902
oke
Tokenoke
Feature activation+1.176
the
Token the
Feature activation+0.749
conspiracy
Token conspiracy
Feature activation+0.846
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.071
Ċ
TokenĊ
Feature activation+0.425
Live
TokenLive
Feature activation+0.954
in
Token in
Feature activation+1.300
the
Token the
Feature activation+1.128
moment
Token moment
Feature activation+1.248
.
Token.
Feature activation+0.915
Ċ
TokenĊ
Feature activation+0.557
Ċ
TokenĊ
Feature activation+0.680
I
TokenI
Feature activation+0.987
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.017
Ċ
TokenĊ
Feature activation+0.378
4
Token4
Feature activation+0.977
.
Token.
Feature activation+0.997
Press
Token Press
Feature activation+1.142
urized
Tokenurized
Feature activation+0.945
Air
Token Air
Feature activation+1.158
Ċ
TokenĊ
Feature activation+0.536
Ċ
TokenĊ
Feature activation+0.616
As
TokenAs
Feature activation+1.001
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.194
On
TokenOn
Feature activation+0.702
the
Token the
Feature activation+1.094
30
Token 30
Feature activation+1.115
th
Tokenth
Feature activation+1.142
June
Token June
Feature activation+1.178
,
Token,
Feature activation+0.653
Ess
Token Ess
Feature activation+0.650
am
Tokenam
Feature activation+0.731
threat
Token threat
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.108
The
TokenThe
Feature activation+0.763
London
Token London
Feature activation+1.084
Knights
Token Knights
Feature activation+0.974
have
Token have
Feature activation+0.767
had
Token had
Feature activation+0.634
many
Token many
Feature activation+0.582
players
Token players
Feature activation+0.394

INTERVAL 0.909 - 1.061
CONTAINS 0.084%

over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.258
Psych
TokenPsych
Feature activation+0.832
ic
Tokenic
Feature activation+1.010
Library
Token Library
Feature activation+1.060
end
Token end
Feature activation+1.071
orses
Tokenorses
Feature activation+0.684
all
Token all
Feature activation+0.594
true
Token true
Feature activation+0.513
edit
Token edit
Feature activation+0.585
]
Token ]
Feature activation+0.507
Ċ
TokenĊ
Feature activation+0.216
Ċ
TokenĊ
Feature activation+0.291
The
TokenThe
Feature activation+0.762
expression
Token expression
Feature activation+0.937
for
Token for
Feature activation+0.832
adding
Token adding
Feature activation+0.658
the
Token the
Feature activation+0.370
numbers
Token numbers
Feature activation+0.325
1
Token 1
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.086
A
TokenA
Feature activation+0.591
productive
Token productive
Feature activation+1.008
relationship
Token relationship
Feature activation+1.124
is
Token is
Feature activation+0.963
expected
Token expected
Feature activation+0.841
to
Token to
Feature activation+0.710
prevail
Token prevail
Feature activation+0.612
for
Token for
Feature activation+0.582
the
Token the
Feature activation+0.489
bonus
Token bonus
Feature activation+0.000
tasks
Token tasks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.063
St
TokenSt
Feature activation+0.349
unning
Tokenunning
Feature activation+0.918
visual
Token visual
Feature activation+0.679
effects
Token effects
Feature activation+0.696
and
Token and
Feature activation+0.365
fantastic
Token fantastic
Feature activation+0.323
bonuses
Token bonuses
Feature activation+0.231
adds
Token adds
Feature activation+0.466
:
Token:
Feature activation+0.403
Ċ
TokenĊ
Feature activation+0.094
Ċ
TokenĊ
Feature activation+0.288
Govern
TokenGovern
Feature activation+0.646
or
Tokenor
Feature activation+0.923
Jindal
Token Jindal
Feature activation+0.601
said
Token said
Feature activation+0.642
,
Token,
Feature activation+0.210
âĢ
Token âĢ
Feature activation+0.025
ľ
Tokenľ
Feature activation+0.043

INTERVAL 0.758 - 0.909
CONTAINS 0.171%

general
Token general
Feature activation+1.061
we
Token we
Feature activation+0.875
are
Token are
Feature activation+0.799
happy
Token happy
Feature activation+0.804
with
Token with
Feature activation+0.782
our
Token our
Feature activation+0.803
velocity
Token velocity
Feature activation+0.665
.
Token.
Feature activation+0.361
We
Token We
Feature activation+0.380
did
Token did
Feature activation+0.151
a
Token a
Feature activation+0.130
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.030
For
TokenFor
Feature activation+0.574
Johnson
Token Johnson
Feature activation+0.855
,
Token,
Feature activation+0.511
there
Token there
Feature activation+0.525
's
Token's
Feature activation+0.478
also
Token also
Feature activation+0.392
something
Token something
Feature activation+0.171
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.263
But
TokenBut
Feature activation+0.558
the
Token the
Feature activation+0.784
benefits
Token benefits
Feature activation+0.878
of
Token of
Feature activation+0.801
participating
Token participating
Feature activation+0.794
outwe
Token outwe
Feature activation+0.723
ighed
Tokenighed
Feature activation+0.632
any
Token any
Feature activation+0.573
ich
Tokenich
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.541
executive
Token executive
Feature activation+0.870
experience
Token experience
Feature activation+0.733
,
Token,
Feature activation+0.354
though
Token though
Feature activation+0.288
praised
Token praised
Feature activation+0.302
as
Token as
Feature activation+0.103
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.133
Five
TokenFive
Feature activation+0.745
Sent
Token Sent
Feature activation+0.949
in
Tokenin
Feature activation+0.866
els
Tokenels
Feature activation+0.650
are
Token are
Feature activation+0.538
already
Token already
Feature activation+0.661
flying
Token flying
Feature activation+0.274
.
Token.
Feature activation+0.054

INTERVAL 0.606 - 0.758
CONTAINS 0.273%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.075
V
TokenV
Feature activation+0.683
iola
Tokeniola
Feature activation+0.965
Beach
Token Beach
Feature activation+1.047
had
Token had
Feature activation+0.714
been
Token been
Feature activation+0.813
championed
Token championed
Feature activation+0.621
by
Token by
Feature activation+0.592
BBC
Token BBC
Feature activation+0.531
Introdu
Token Introdu
Feature activation+0.478
cleaning
Token cleaning
Feature activation+0.000
oven
Token oven
Feature activation+0.000
.'
Token.'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.209
In
TokenIn
Feature activation+0.636
her
Token her
Feature activation+0.962
recent
Token recent
Feature activation+0.932
post
Token post
Feature activation+1.048
she
Token she
Feature activation+0.698
explained
Token explained
Feature activation+0.606
Ċ
TokenĊ
Feature activation+0.132
âĢ
TokenâĢ
Feature activation+0.453
ľ
Tokenľ
Feature activation+0.578
Go
TokenGo
Feature activation+0.790
home
Token home
Feature activation+1.103
and
Token and
Feature activation+0.709
take
Token take
Feature activation+0.773
your
Token your
Feature activation+0.616
mind
Token mind
Feature activation+0.539
off
Token off
Feature activation+0.377
things
Token things
Feature activation+0.343
's
Token's
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.098
3
Token3
Feature activation+0.613
Lith
Token Lith
Feature activation+0.707
ium
Tokenium
Feature activation+1.037
Li
Token Li
Feature activation+0.574
Greek
Token Greek
Feature activation+0.521
Î
Token Î
Feature activation+0.287
than
Token than
Feature activation+0.415
others
Token others
Feature activation+0.346
.
Token.
Feature activation+0.217
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.096
These
TokenThese
Feature activation+0.654
headaches
Token headaches
Feature activation+0.730
can
Token can
Feature activation+0.516
occur
Token occur
Feature activation+0.439
like
Token like
Feature activation+0.268
clock
Token clock
Feature activation+0.190

INTERVAL 0.455 - 0.606
CONTAINS 0.359%

Registry
Token Registry
Feature activation+0.000
value
Token value
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Added
TokenAdded
Feature activation+0.456
.
Token .
Feature activation+0.492
NET
TokenNET
Feature activation+0.232
detection
Token detection
Feature activation+0.419
-
Token -
Feature activation+0.196
When
Token When
Feature activation+0.000
to
Token to
Feature activation+0.833
transfer
Token transfer
Feature activation+0.901
characters
Token characters
Feature activation+0.769
to
Token to
Feature activation+0.489
new
Token new
Feature activation+0.639
factions
Token factions
Feature activation+0.533
(
Token (
Feature activation+0.126
when
Tokenwhen
Feature activation+0.000
they
Token they
Feature activation+0.000
become
Token become
Feature activation+0.002
fully
Token fully
Feature activation+0.000
left
Token left
Feature activation+0.745
.
Token.
Feature activation+0.512
She
Token She
Feature activation+0.546
was
Token was
Feature activation+0.567
later
Token later
Feature activation+0.640
found
Token found
Feature activation+0.577
dead
Token dead
Feature activation+0.615
in
Token in
Feature activation+0.293
her
Token her
Feature activation+0.291
apartment
Token apartment
Feature activation+0.246
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.190
Unfortunately
TokenUnfortunately
Feature activation+0.802
,
Token,
Feature activation+0.620
they
Token they
Feature activation+0.520
got
Token got
Feature activation+0.527
a
Token a
Feature activation+0.494
little
Token little
Feature activation+0.413
too
Token too
Feature activation+0.308
creative
Token creative
Feature activation+0.214
tuning
Token tuning
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.214
are
Token are
Feature activation+0.567
your
Token your
Feature activation+0.430
goals
Token goals
Feature activation+0.220
as
Token as
Feature activation+0.142
an
Token an
Feature activation+0.000
indie
Token indie
Feature activation+0.000

INTERVAL 0.303 - 0.455
CONTAINS 0.431%

-
Token-
Feature activation+1.102
school
Tokenschool
Feature activation+1.123
,
Token,
Feature activation+0.505
early
Token early
Feature activation+0.610
sw
Token sw
Feature activation+0.470
immers
Tokenimmers
Feature activation+0.432
had
Token had
Feature activation+0.204
better
Token better
Feature activation+0.000
visual
Token visual
Feature activation+0.000
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Soul
TokenSoul
Feature activation+0.119
Society
Token Society
Feature activation+0.391
-
Token -
Feature activation+0.322
K
Token K
Feature activation+0.319
iz
Tokeniz
Feature activation+0.348
ok
Tokenok
Feature activation+0.415
ug
Tokenug
Feature activation+0.323
ai
Tokenai
Feature activation+0.370
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
John
TokenJohn
Feature activation+0.713
Wesley
Token Wesley
Feature activation+0.664
Jones
Token Jones
Feature activation+0.539
,
Token,
Feature activation+0.270
also
Token also
Feature activation+0.392
known
Token known
Feature activation+0.330
as
Token as
Feature activation+0.243
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Face
TokenFace
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.588
in
Token in
Feature activation+0.550
line
Token line
Feature activation+0.659
to
Token to
Feature activation+0.397
the
Token the
Feature activation+0.453
throne
Token throne
Feature activation+0.416
,
Token,
Feature activation+0.153
as
Token as
Feature activation+0.142
a
Token a
Feature activation+0.052
1947
Token 1947
Feature activation+0.111
succession
Token succession
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ge
TokenGe
Feature activation+0.000
ffen
Tokenffen
Feature activation+0.250
was
Token was
Feature activation+0.478
no
Token no
Feature activation+0.452
fan
Token fan
Feature activation+0.471
of
Token of
Feature activation+0.378
the
Token the
Feature activation+0.388
Clintons
Token Clintons
Feature activation+0.264
back
Token back
Feature activation+0.272

INTERVAL 0.152 - 0.303
CONTAINS 0.592%

brown
Token brown
Feature activation+0.438
leather
Token leather
Feature activation+0.329
.
Token.
Feature activation+0.084
Dark
Token Dark
Feature activation+0.247
brown
Token brown
Feature activation+0.478
can
Token can
Feature activation+0.217
work
Token work
Feature activation+0.172
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
tan
Token tan
Feature activation+0.000
living
Token living
Feature activation+0.000
standards
Token standards
Feature activation+0.000
.
Token.
Feature activation+0.000
Public
Token Public
Feature activation+0.082
opinion
Token opinion
Feature activation+0.152
is
Token is
Feature activation+0.169
generally
Token generally
Feature activation+0.128
favorable
Token favorable
Feature activation+0.000
toward
Token toward
Feature activation+0.024
greater
Token greater
Feature activation+0.059
government
Token government
Feature activation+0.032
âĢ
TokenâĢ
Feature activation+0.544
Ļ
TokenĻ
Feature activation+0.569
s
Tokens
Feature activation+0.708
assassination
Token assassination
Feature activation+0.577
of
Token of
Feature activation+0.287
an
Token an
Feature activation+0.250
Iranian
Token Iranian
Feature activation+0.143
nuclear
Token nuclear
Feature activation+0.085
scientist
Token scientist
Feature activation+0.000
has
Token has
Feature activation+0.000
aroused
Token aroused
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
leaks
Token leaks
Feature activation+0.206
also
Token also
Feature activation+0.199
include
Token include
Feature activation+0.001
forums
Token forums
Feature activation+0.000
for
Token for
Feature activation+0.000
improving
Token improving
Feature activation+0.000
hacking
Token hacking
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
with
Token with
Feature activation+0.000
plans
Token plans
Feature activation+0.084
starting
Token starting
Feature activation+0.236
at
Token at
Feature activation+0.181
low
Token low
Feature activation+0.224
rates
Token rates
Feature activation+0.298
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.076
which
Token which
Feature activation+0.032

INTERVAL 0.000 - 0.152
CONTAINS 98.046%

along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
Afghan
Token Afghan
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+0.000
football
Token football
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
grown
Token grown
Feature activation+0.000
up
Token up
Feature activation+0.000
since
Token since
Feature activation+0.000
The
TokenThe
Feature activation+0.070
incident
Token incident
Feature activation+0.169
was
Token was
Feature activation+0.015
caught
Token caught
Feature activation+0.000
on
Token on
Feature activation+0.000
CCTV
Token CCTV
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
gone
Token gone
Feature activation+0.000
viral
Token viral
Feature activation+0.000
on
Token on
Feature activation+0.000
glass
Token glass
Feature activation+0.000
and
Token and
Feature activation+0.000
chrome
Token chrome
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
and
Token and
Feature activation+0.000
g
Token g
Feature activation+0.000
ee
Tokenee
Feature activation+0.000
-
Token-
Feature activation+0.000
wh
Tokenwh
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
charges
Token charges
Feature activation+0.000
on
Token on
Feature activation+0.000
firms
Token firms
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
new
Token new
Feature activation+0.000
rules
Token rules
Feature activation+0.000
or
Token or
Feature activation+0.000
laws
Token laws
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
growth
Token growth
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
a
Token a
Feature activation+0.000
depression
Token depression
Feature activation+0.000
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+0.000
that
Token that
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
six
Token six
Feature activation+0.000
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
file
Token file
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
six
Token six
Feature activation+0.000
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
six
Token six
Feature activation+0.000
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
six
Token six
Feature activation+0.000
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.113
defence
Token defence
Feature activation+0.462
ministry
Token ministry
Feature activation+0.469
committee
Token committee
Feature activation+0.521
<|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+0.113
defence
Token defence
Feature activation+0.462
ministry
Token ministry
Feature activation+0.469
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+0.113
defence
Token defence
Feature activation+0.462
ministry
Token ministry
Feature activation+0.469
committee
Token committee
Feature activation+0.521
headed
Token headed
Feature activation+0.381
.
Token.
Feature activation+0.146
K
TokenK
Feature activation+0.251
.
Token.
Feature activation+0.184
A
Token A
Feature activation+0.300
atre
Tokenatre
Feature activation+0.199
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.023
former
Token former
Feature activation+0.033
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
former
Token former
Feature activation+0.033
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
six
Token six
Feature activation+0.000
a
Token a
Feature activation+0.023
former
Token former
Feature activation+0.033
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.023
former
Token former
Feature activation+0.033
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
A
Token A
Feature activation+0.300
atre
Tokenatre
Feature activation+0.199
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.023
former
Token former
Feature activation+0.033
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
atre
Tokenatre
Feature activation+0.199
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.023
former
Token former
Feature activation+0.033
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