H2.3 top features

Top feature 0 in H2.3: (feature 20066)

TOP ACTIVATIONS
MAX = 3.592

European
Token European
Feature activation+0.000
mindset
Token mindset
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
both
Token both
Feature activation+0.000
wars
Token wars
Feature activation+3.592
,
Token,
Feature activation+1.271
the
Token the
Feature activation+0.625
notion
Token notion
Feature activation+0.000
of
Token of
Feature activation+0.260
remembrance
Token remembrance
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.000
neighbors
Token neighbors
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.000
communities
Token communities
Feature activation+2.966
together
Token together
Feature activation+1.065
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
would
Token would
Feature activation+0.000
want
Token want
Feature activation+0.000
:
Token:
Feature activation+0.000
both
Token both
Feature activation+0.345
players
Token players
Feature activation+2.957
at
Token at
Feature activation+1.062
the
Token the
Feature activation+0.866
club
Token club
Feature activation+0.270
and
Token and
Feature activation+0.000
rotating
Token rotating
Feature activation+0.000
the
Token the
Feature activation+0.000
bubbles
Token bubbles
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
candidates
Token candidates
Feature activation+2.905
,
Token,
Feature activation+0.871
but
Token but
Feature activation+0.210
placed
Token placed
Feature activation+0.000
a
Token a
Feature activation+0.000
strike
Token strike
Feature activation+0.000
(
Token (
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
can
Token can
Feature activation+0.000
hear
Token hear
Feature activation+0.000
both
Token both
Feature activation+0.000
tracks
Token tracks
Feature activation+2.880
below
Token below
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
step
Tokenstep
Feature activation+0.000
guides
Token guides
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
wallet
Token wallet
Feature activation+1.376
types
Token types
Feature activation+2.865
.
Token.
Feature activation+0.267
Getting
Token Getting
Feature activation+0.000
control
Token control
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
locked
Tokenlocked
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.280
sides
Token sides
Feature activation+2.807
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.335
Greek
Token Greek
Feature activation+0.019
captain
Token captain
Feature activation+0.000
manage
Token manage
Feature activation+0.000
challenges
Token challenges
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.160
countries
Token countries
Feature activation+2.734
have
Token have
Feature activation+1.650
taken
Token taken
Feature activation+0.395
positive
Token positive
Feature activation+0.000
steps
Token steps
Feature activation+0.028
in
Token in
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.000
that
Token that
Feature activation+0.000
both
Token both
Feature activation+0.000
mechanisms
Token mechanisms
Feature activation+2.724
probably
Token probably
Feature activation+0.464
played
Token played
Feature activation+0.331
a
Token a
Feature activation+0.000
role
Token role
Feature activation+0.000
,
Token,
Feature activation+0.000
One
Token One
Feature activation+0.000
Year
Token Year
Feature activation+0.000
Later
Token Later
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
specials
Token specials
Feature activation+2.717
received
Token received
Feature activation+1.338
high
Token high
Feature activation+0.000
Nielsen
Token Nielsen
Feature activation+0.000
ratings
Token ratings
Feature activation+0.360
,
Token,
Feature activation+0.000
After
Token After
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
casualties
Token casualties
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+2.716
,
Token,
Feature activation+0.455
the
Token the
Feature activation+0.273
Nazis
Token Nazis
Feature activation+0.000
withdrew
Token withdrew
Feature activation+0.000
in
Token in
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
back
Token back
Feature activation+0.000
both
Token both
Feature activation+0.000
creatures
Token creatures
Feature activation+2.714
,
Token,
Feature activation+0.751
Force
Token Force
Feature activation+0.000
pitching
Token pitching
Feature activation+0.000
Coun
Token Coun
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
couples
Token couples
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
both
Tokenboth
Feature activation+0.000
men
Token men
Feature activation+2.690
and
Token and
Feature activation+0.847
women
Token women
Feature activation+2.591
!
Token!
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
be
Token be
Feature activation+0.000
on
Token on
Feature activation+0.000
sale
Token sale
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
continents
Token continents
Feature activation+2.641
by
Token by
Feature activation+0.865
the
Token the
Feature activation+0.406
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
instruct
Token instruct
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
that
Token that
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
cases
Token cases
Feature activation+2.636
,
Token,
Feature activation+0.023
it
Token it
Feature activation+0.531
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.004
means
Token means
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
both
Token both
Feature activation+0.000
types
Token types
Feature activation+2.630
of
Token of
Feature activation+2.285
flashes
Token flashes
Feature activation+1.228
in
Token in
Feature activation+0.000
conjunction
Token conjunction
Feature activation+0.000
if
Token if
Feature activation+0.000
heard
Token heard
Feature activation+0.000
the
Token the
Feature activation+0.000
arguments
Token arguments
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+2.600
on
Token on
Feature activation+0.964
Jan
Token Jan
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token 6
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
armed
Token armed
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
both
Tokenboth
Feature activation+0.092
officers
Token officers
Feature activation+2.595
fired
Token fired
Feature activation+0.714
,
Token,
Feature activation+0.316
he
Token he
Feature activation+0.407
went
Token went
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
by
Token by
Feature activation+0.000
both
Token both
Feature activation+0.000
countries
Token countries
Feature activation+2.593
,
Token,
Feature activation+0.270
with
Token with
Feature activation+0.823
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
spat
Token spat
Feature activation+0.000
couples
Token couples
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
both
Tokenboth
Feature activation+0.000
men
Token men
Feature activation+2.690
and
Token and
Feature activation+0.847
women
Token women
Feature activation+2.591
!
Token!
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
urned
Tokenurned
Feature activation+0.000
watching
Token watching
Feature activation+0.000

Top DFA by src position
MAX = 4.978

the
Token the
Feature activation+0.005
Top resid features:
European
Token European
Feature activation-0.015
Top resid features:
mindset
Token mindset
Feature activation-0.015
Top resid features:
.
Token.
Feature activation-0.125
Top resid features:
For
Token For
Feature activation-0.007
Top resid features:
both
Token both
Feature activation+4.978
Top resid features:
wars
Token wars
Feature activation+0.066
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
notion
Token notion
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
relationship
Token relationship
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.175
Top resid features:
bring
Token bring
Feature activation+0.005
Top resid features:
neighbors
Token neighbors
Feature activation+0.030
Top resid features:
from
Token from
Feature activation-0.030
Top resid features:
both
Token both
Feature activation+4.484
Top resid features:
communities
Token communities
Feature activation+0.062
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.008
Top resid features:
everyone
Token everyone
Feature activation+0.063
Top resid features:
would
Token would
Feature activation+0.030
Top resid features:
want
Token want
Feature activation+0.107
Top resid features:
:
Token:
Feature activation-0.134
Top resid features:
both
Token both
Feature activation+4.110
Top resid features:
players
Token players
Feature activation+0.125
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
club
Token club
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.030
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
bubbles
Token bubbles
Feature activation+0.019
Top resid features:
next
Token next
Feature activation+0.050
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
both
Token both
Feature activation+3.851
Top resid features:
candidates
Token candidates
Feature activation+0.163
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
placed
Token placed
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Bo
Token Bo
Feature activation-0.041
Top resid features:
(
Token (
Feature activation-0.055
Top resid features:
you
Tokenyou
Feature activation-0.037
Top resid features:
can
Token can
Feature activation+0.060
Top resid features:
hear
Token hear
Feature activation+0.230
Top resid features:
both
Token both
Feature activation+4.199
Top resid features:
tracks
Token tracks
Feature activation+0.061
Top resid features:
below
Token below
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
by
Tokenby
Feature activation-0.049
Top resid features:
-
Token-
Feature activation-0.036
Top resid features:
step
Tokenstep
Feature activation-0.064
Top resid features:
guides
Token guides
Feature activation-0.012
Top resid features:
for
Token for
Feature activation+0.145
Top resid features:
both
Token both
Feature activation+4.304
Top resid features:
wallet
Token wallet
Feature activation-0.106
Top resid features:
types
Token types
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Getting
Token Getting
Feature activation+0.000
Top resid features:
control
Token control
Feature activation+0.000
Top resid features:
un
Tokenun
Feature activation-0.030
Top resid features:
locked
Tokenlocked
Feature activation+0.015
Top resid features:
âĢ
TokenâĢ
Feature activation-0.019
Top resid features:
Ļ
TokenĻ
Feature activation-0.072
Top resid features:
on
Token on
Feature activation+0.200
Top resid features:
both
Token both
Feature activation+4.024
Top resid features:
sides
Token sides
Feature activation-0.084
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Greek
Token Greek
Feature activation+0.000
Top resid features:
captain
Token captain
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
challenges
Token challenges
Feature activation-0.020
Top resid features:
may
Token may
Feature activation+0.004
Top resid features:
be
Token be
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.097
Top resid features:
Both
Token Both
Feature activation+3.922
Top resid features:
countries
Token countries
Feature activation+0.118
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
taken
Token taken
Feature activation+0.000
Top resid features:
positive
Token positive
Feature activation+0.000
Top resid features:
steps
Token steps
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.027
Top resid features:
but
Token but
Feature activation-0.100
Top resid features:
it
Token it
Feature activation+0.036
Top resid features:
seems
Token seems
Feature activation+0.017
Top resid features:
that
Token that
Feature activation-0.039
Top resid features:
both
Token both
Feature activation+3.966
Top resid features:
mechanisms
Token mechanisms
Feature activation+0.048
Top resid features:
probably
Token probably
Feature activation+0.000
Top resid features:
played
Token played
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
role
Token role
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.042
Top resid features:
One
Token One
Feature activation-0.033
Top resid features:
Year
Token Year
Feature activation-0.020
Top resid features:
Later
Token Later
Feature activation-0.037
Top resid features:
.
Token.
Feature activation-0.075
Top resid features:
Both
Token Both
Feature activation+4.252
Top resid features:
specials
Token specials
Feature activation+0.110
Top resid features:
received
Token received
Feature activation+0.000
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
Nielsen
Token Nielsen
Feature activation+0.000
Top resid features:
ratings
Token ratings
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
After
Token After
Feature activation-0.129
Top resid features:
heavy
Token heavy
Feature activation+0.019
Top resid features:
casualties
Token casualties
Feature activation-0.058
Top resid features:
on
Token on
Feature activation+0.106
Top resid features:
both
Token both
Feature activation+4.164
Top resid features:
sides
Token sides
Feature activation-0.084
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Nazis
Token Nazis
Feature activation+0.000
Top resid features:
withdrew
Token withdrew
Feature activation+0.000
Top resid features:
play
Token play
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.054
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
put
Token put
Feature activation+0.037
Top resid features:
back
Token back
Feature activation-0.112
Top resid features:
both
Token both
Feature activation+3.994
Top resid features:
creatures
Token creatures
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Force
Token Force
Feature activation+0.000
Top resid features:
pitching
Token pitching
Feature activation+0.000
Top resid features:
Coun
Token Coun
Feature activation+0.000
Top resid features:
Researchers
Token Researchers
Feature activation-0.037
Top resid features:
found
Token found
Feature activation+0.005
Top resid features:
that
Token that
Feature activation-0.040
Top resid features:
couples
Token couples
Feature activation+0.096
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.103
Top resid features:
both
Tokenboth
Feature activation+4.197
Top resid features:
men
Token men
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.000
Top resid features:
will
Token will
Feature activation-0.000
Top resid features:
be
Token be
Feature activation+0.008
Top resid features:
on
Token on
Feature activation-0.027
Top resid features:
sale
Token sale
Feature activation+0.038
Top resid features:
on
Token on
Feature activation+0.034
Top resid features:
both
Token both
Feature activation+4.005
Top resid features:
continents
Token continents
Feature activation+0.072
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.039
Top resid features:
instruct
Token instruct
Feature activation-0.052
Top resid features:
ive
Tokenive
Feature activation-0.055
Top resid features:
that
Token that
Feature activation-0.039
Top resid features:
in
Token in
Feature activation+0.158
Top resid features:
both
Token both
Feature activation+4.113
Top resid features:
cases
Token cases
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
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:
it
Token it
Feature activation-0.001
Top resid features:
means
Token means
Feature activation-0.080
Top resid features:
you
Token you
Feature activation-0.016
Top resid features:
can
Token can
Feature activation+0.069
Top resid features:
use
Token use
Feature activation+0.056
Top resid features:
both
Token both
Feature activation+3.979
Top resid features:
types
Token types
Feature activation-0.007
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
flashes
Token flashes
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
conjunction
Token conjunction
Feature activation+0.000
Top resid features:
ie
Tokenie
Feature activation-0.020
Top resid features:
heard
Token heard
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
arguments
Token arguments
Feature activation+0.073
Top resid features:
from
Token from
Feature activation+0.089
Top resid features:
both
Token both
Feature activation+3.815
Top resid features:
sides
Token sides
Feature activation-0.045
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Jan
Token Jan
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
6
Token 6
Feature activation+0.000
Top resid features:
suspect
Token suspect
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.141
Top resid features:
armed
Token armed
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.155
Top resid features:
"
Token "
Feature activation+0.063
Top resid features:
both
Tokenboth
Feature activation+3.918
Top resid features:
officers
Token officers
Feature activation-0.029
Top resid features:
fired
Token fired
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
went
Token went
Feature activation+0.000
Top resid features:
Japan
Token Japan
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.034
Top resid features:
and
Token and
Feature activation-0.199
Top resid features:
claimed
Token claimed
Feature activation+0.007
Top resid features:
by
Token by
Feature activation-0.045
Top resid features:
both
Token both
Feature activation+4.334
Top resid features:
countries
Token countries
Feature activation+0.139
Top resid features:
,
Token,
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:
latest
Token latest
Feature activation+0.000
Top resid features:
Researchers
Token Researchers
Feature activation-0.037
Top resid features:
found
Token found
Feature activation+0.008
Top resid features:
that
Token that
Feature activation-0.005
Top resid features:
couples
Token couples
Feature activation+0.053
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.101
Top resid features:
both
Tokenboth
Feature activation+4.505
Top resid features:
men
Token men
Feature activation-0.013
Top resid features:
and
Token and
Feature activation-0.476
Top resid features:
women
Token women
Feature activation+0.099
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.03

Head 2: 0.07

Head 3: 0.50

Head 4: 0.05

Head 5: 0.05

Head 6: 0.03

Head 7: 0.03

Head 8: 0.03

Head 9: 0.07

Head 10: 0.06

Head 11: 0.03

Positive logits

odder1.46

sexes1.42

igers1.41

ibraries1.33

ighth1.33

enders1.28

"]=>1.27

orts1.26

icians1.26

KS1.23

GH1.23

ounge1.22

Unloaded1.22

halves1.21

ggie1.20

idges1.20

alde1.19

UME1.18

ource1.18

ttes1.17

Negative logits

Collider-1.51

Ratio-1.41

smugg-1.18

Tess-1.18

Ratings-1.18

Petition-1.18

Beir-1.18

iqueness-1.17

Name-1.17

��-1.16

-1.14

Plot-1.14

Purg-1.14

Ranking-1.14

Appearance-1.14

draft-1.13

-1.13

Cay-1.13

Rat-1.13

arah-1.13

INTERVAL 3.233 - 3.592
CONTAINS 0.000%

European
Token European
Feature activation+0.000
mindset
Token mindset
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
both
Token both
Feature activation+0.000
wars
Token wars
Feature activation+3.592
,
Token,
Feature activation+1.271
the
Token the
Feature activation+0.625
notion
Token notion
Feature activation+0.000
of
Token of
Feature activation+0.260
remembrance
Token remembrance
Feature activation+0.000

INTERVAL 2.874 - 3.233
CONTAINS 0.000%

everyone
Token everyone
Feature activation+0.000
would
Token would
Feature activation+0.000
want
Token want
Feature activation+0.000
:
Token:
Feature activation+0.000
both
Token both
Feature activation+0.345
players
Token players
Feature activation+2.957
at
Token at
Feature activation+1.062
the
Token the
Feature activation+0.866
club
Token club
Feature activation+0.270
and
Token and
Feature activation+0.000
rotating
Token rotating
Feature activation+0.000
(
Token (
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
can
Token can
Feature activation+0.000
hear
Token hear
Feature activation+0.000
both
Token both
Feature activation+0.000
tracks
Token tracks
Feature activation+2.880
below
Token below
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
the
Token the
Feature activation+0.000
bubbles
Token bubbles
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
candidates
Token candidates
Feature activation+2.905
,
Token,
Feature activation+0.871
but
Token but
Feature activation+0.210
placed
Token placed
Feature activation+0.000
a
Token a
Feature activation+0.000
strike
Token strike
Feature activation+0.000
and
Token and
Feature activation+0.000
bring
Token bring
Feature activation+0.000
neighbors
Token neighbors
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.000
communities
Token communities
Feature activation+2.966
together
Token together
Feature activation+1.065
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.515 - 2.874
CONTAINS 0.002%

was
Token was
Feature activation+0.000
armed
Token armed
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
both
Tokenboth
Feature activation+0.092
officers
Token officers
Feature activation+2.595
fired
Token fired
Feature activation+0.714
,
Token,
Feature activation+0.316
he
Token he
Feature activation+0.407
went
Token went
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+0.323
us
Token us
Feature activation+2.570
.
Token.
Feature activation+0.097
Of
Token Of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
be
Token be
Feature activation+0.000
on
Token on
Feature activation+0.000
sale
Token sale
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
continents
Token continents
Feature activation+2.641
by
Token by
Feature activation+0.865
the
Token the
Feature activation+0.406
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
back
Token back
Feature activation+0.000
both
Token both
Feature activation+0.000
creatures
Token creatures
Feature activation+2.714
,
Token,
Feature activation+0.751
Force
Token Force
Feature activation+0.000
pitching
Token pitching
Feature activation+0.000
Coun
Token Coun
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
parties
Token parties
Feature activation+2.226
.
Token.
Feature activation+0.000
Especially
Token Especially
Feature activation+0.000
now
Token now
Feature activation+0.000
both
Token both
Feature activation+0.031
companies
Token companies
Feature activation+2.518
are
Token are
Feature activation+1.747
looking
Token looking
Feature activation+0.360
at
Token at
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 2.155 - 2.515
CONTAINS 0.005%

would
Token would
Feature activation+0.000
urge
Token urge
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.144
critics
Token critics
Feature activation+2.369
and
Token and
Feature activation+1.032
supporters
Token supporters
Feature activation+0.907
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
6
Token6
Feature activation+0.000
so
Token so
Feature activation+0.000
sad
Token sad
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.250
players
Token players
Feature activation+2.402
from
Token from
Feature activation+0.948
the
Token the
Feature activation+0.430
greatest
Token greatest
Feature activation+0.000
GSL
Token GSL
Feature activation+0.000
finals
Token finals
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
scene
Token scene
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
incidents
Token incidents
Feature activation+2.225
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
report
Token report
Feature activation+0.000
incomplete
Token incomplete
Feature activation+0.000
,
Token,
Feature activation+0.000
attorneys
Token attorneys
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+2.414
have
Token have
Feature activation+1.072
already
Token already
Feature activation+0.926
armored
Token armored
Feature activation+0.123
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
in
Token in
Feature activation+0.000
July
Token July
Feature activation+0.000
with
Token with
Feature activation+0.000
both
Token both
Feature activation+0.000
girls
Token girls
Feature activation+2.241
who
Token who
Feature activation+0.417
confirmed
Token confirmed
Feature activation+0.000
what
Token what
Feature activation+0.000
their
Token their
Feature activation+0.000
parents
Token parents
Feature activation+0.000

INTERVAL 1.796 - 2.155
CONTAINS 0.005%

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
parties
Token parties
Feature activation+2.117
âĢĵ
Token âĢĵ
Feature activation+1.161
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
truth
Token truth
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
Bern
Token Bern
Feature activation+0.000
anke
Tokenanke
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.166
mixed
Token mixed
Feature activation+1.897
bags
Token bags
Feature activation+0.432
.
Token.
Feature activation+0.000
Obviously
Token Obviously
Feature activation+0.000
Greens
Token Greens
Feature activation+0.000
pan
Tokenpan
Feature activation+0.000
functional
Token functional
Feature activation+0.000
languages
Token languages
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
both
Token both
Feature activation+0.000
cases
Token cases
Feature activation+1.898
comprehens
Token comprehens
Feature activation+0.000
ions
Tokenions
Feature activation+1.616
are
Token are
Feature activation+0.724
deep
Token deep
Feature activation+0.000
and
Token and
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
unique
Token unique
Feature activation+0.000
approach
Token approach
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
motorcycles
Token motorcycles
Feature activation+2.041
and
Token and
Feature activation+0.245
motorcycle
Token motorcycle
Feature activation+0.000
gear
Token gear
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
Kennedy
Token Kennedy
Feature activation+0.000
were
Token were
Feature activation+0.000
both
Token both
Feature activation+0.380
sons
Token sons
Feature activation+1.956
of
Token of
Feature activation+1.313
privileged
Token privileged
Feature activation+0.578
,
Token,
Feature activation+0.244
politically
Token politically
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.437 - 1.796
CONTAINS 0.005%

Eve
Token Eve
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
both
Token both
Feature activation+0.000
been
Token been
Feature activation+0.858
developed
Token developed
Feature activation+1.586
for
Token for
Feature activation+0.094
Virgin
Token Virgin
Feature activation+0.000
Galactic
Token Galactic
Feature activation+0.000
by
Token by
Feature activation+0.000
Moj
Token Moj
Feature activation+0.000
Both
Token Both
Feature activation+0.001
comments
Token comments
Feature activation+1.794
and
Token and
Feature activation+0.878
p
Token p
Feature activation+0.000
ings
Tokenings
Feature activation+1.360
are
Token are
Feature activation+1.753
currently
Token currently
Feature activation+0.041
closed
Token closed
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
Tin
Token Tin
Feature activation+0.000
Star
Token Star
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
both
Tokenboth
Feature activation+0.000
of
Token of
Feature activation+0.294
which
Token which
Feature activation+1.452
starred
Token starred
Feature activation+0.003
Henry
Token Henry
Feature activation+0.000
F
Token F
Feature activation+0.000
onda
Tokenonda
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
poetry
Token poetry
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
fears
Token fears
Feature activation+0.000
both
Token both
Feature activation+0.000
may
Token may
Feature activation+1.721
disappear
Token disappear
Feature activation+0.738
if
Token if
Feature activation+0.324
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
left
Token left
Feature activation+0.000
field
Token field
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.174
minors
Token minors
Feature activation+1.642
and
Token and
Feature activation+0.280
majors
Token majors
Feature activation+1.206
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.078 - 1.437
CONTAINS 0.007%

in
Token in
Feature activation+0.000
May
Token May
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
Europe
Token Europe
Feature activation+1.244
and
Token and
Feature activation+0.348
Asia
Token Asia
Feature activation+0.125
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
miracle
Token miracle
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
parties
Token parties
Feature activation+1.943
to
Token to
Feature activation+1.152
show
Token show
Feature activation+0.577
a
Token a
Feature activation+0.000
willingness
Token willingness
Feature activation+0.000
to
Token to
Feature activation+0.000
cooperate
Token cooperate
Feature activation+0.000
and
Token and
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
Japanese
Token Japanese
Feature activation+1.287
audio
Token audio
Feature activation+0.245
with
Token with
Feature activation+0.642
English
Token English
Feature activation+0.000
subtitles
Token subtitles
Feature activation+0.206
,
Token,
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
arian
Tokenarian
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
officers
Token officers
Feature activation+1.463
were
Token were
Feature activation+1.343
members
Token members
Feature activation+0.344
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
both
Token both
Feature activation+0.000
early
Token early
Feature activation+0.201
examples
Token examples
Feature activation+0.942
of
Token of
Feature activation+1.195
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
had
Token had
Feature activation+0.000

INTERVAL 0.718 - 1.078
CONTAINS 0.014%

possible
Token possible
Feature activation+0.000
to
Token to
Feature activation+0.000
achieve
Token achieve
Feature activation+0.000
both
Token both
Feature activation+0.000
,
Token,
Feature activation+0.122
and
Token and
Feature activation+0.771
quickly
Token quickly
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
isn
Token isn
Feature activation+0.000
45
Token 45
Feature activation+0.000
%
Token%
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
diseases
Token diseases
Feature activation+2.237
even
Token even
Feature activation+0.862
though
Token though
Feature activation+0.000
we
Token we
Feature activation+0.201
distributed
Token distributed
Feature activation+0.000
medicine
Token medicine
Feature activation+0.000
to
Token to
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
both
Token both
Feature activation+0.000
have
Token have
Feature activation+1.330
to
Token to
Feature activation+0.919
look
Token look
Feature activation+0.106
for
Token for
Feature activation+0.000
new
Token new
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
if
Token if
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+0.281
Cer
Token Cer
Feature activation+1.433
imag
Tokenimag
Feature activation+0.309
ics
Tokenics
Feature activation+1.329
claimed
Token claimed
Feature activation+0.968
the
Token the
Feature activation+0.000
6
Token 6
Feature activation+0.000
200
Token200
Feature activation+0.000
block
Token block
Feature activation+0.000
of
Token of
Feature activation+0.000
on
Token on
Feature activation+0.000
sale
Token sale
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
continents
Token continents
Feature activation+2.641
by
Token by
Feature activation+0.865
the
Token the
Feature activation+0.406
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.000

INTERVAL 0.359 - 0.718
CONTAINS 0.024%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
F
TokenF
Feature activation+0.000
)
Token)
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.220
common
Token common
Feature activation+0.481
and
Token and
Feature activation+0.000
very
Token very
Feature activation+0.000
costly
Token costly
Feature activation+0.000
.
Token.
Feature activation+0.000
Studies
Token Studies
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+1.843
of
Token of
Feature activation+1.647
the
Token the
Feature activation+0.508
debate
Token debate
Feature activation+0.000
have
Token have
Feature activation+0.588
suspended
Token suspended
Feature activation+0.000
their
Token their
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Both
TokenBoth
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.767
reactions
Token reactions
Feature activation+0.658
fundamentally
Token fundamentally
Feature activation+0.461
see
Token see
Feature activation+0.000
infertility
Token infertility
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
both
Token both
Feature activation+0.000
political
Token political
Feature activation+0.613
parties
Token parties
Feature activation+2.137
might
Token might
Feature activation+0.364
be
Token be
Feature activation+0.096
prepared
Token prepared
Feature activation+0.629
to
Token to
Feature activation+0.000
embrace
Token embrace
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+2.553
,
Token,
Feature activation+0.560
we
Token we
Feature activation+0.606
're
Token're
Feature activation+0.048
looking
Token looking
Feature activation+0.009
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.000 - 0.359
CONTAINS 99.939%

.
Token .
Feature activation+0.000
NET
TokenNET
Feature activation+0.000
core
Token core
Feature activation+0.000
d
Token d
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
(
Token (
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
core
Tokencore
Feature activation+0.000
e
Tokene
Feature activation+0.000
.
Token.
Feature activation+0.000
dll
Tokendll
Feature activation+0.000
say
Token say
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
st
Token st
Feature activation+0.000
oke
Tokenoke
Feature activation+0.000
the
Token the
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+0.000
titled
Token titled
Feature activation+0.000
Se
Token Se
Feature activation+0.000
xt
Tokenxt
Feature activation+0.000
up
Tokenup
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
and
Token and
Feature activation+0.000
Twins
Token Twins
Feature activation+0.000
:
Token:
Feature activation+0.000
One
Token One
Feature activation+0.000
Year
Token Year
Feature activation+0.000
Later
Token Later
Feature activation+0.000
the
Token the
Feature activation+0.000
run
Token run
Feature activation+0.000
from
Token from
Feature activation+0.000
Union
Token Union
Feature activation+0.000
militia
Token militia
Feature activation+0.000
and
Token and
Feature activation+0.000
bounty
Token bounty
Feature activation+0.000
hunters
Token hunters
Feature activation+0.000
.
Token.
Feature activation+0.000
Along
Token Along
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
losing
Token losing
Feature activation+0.000
continues
Token continues
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Johnson
TokenJohnson
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H2.3: (feature 6721)

TOP ACTIVATIONS
MAX = 1.804

,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.030
we
Token we
Feature activation+0.616
can
Token can
Feature activation+1.738
really
Token really
Feature activation+0.976
ask
Token ask
Feature activation+0.582
from
Token from
Feature activation+0.000
monetary
Token monetary
Feature activation+0.000
policy
Token policy
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
Trump
Token Trump
Feature activation+0.281
could
Token could
Feature activation+1.307
do
Token do
Feature activation+1.732
is
Token is
Feature activation+0.034
talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
"
Token "
Feature activation+0.000
all
Tokenall
Feature activation+0.000
options
Token options
Feature activation+0.625
are
Token are
Feature activation+1.726
on
Token on
Feature activation+1.100
the
Token the
Feature activation+0.169
table
Token table
Feature activation+0.000
to
Token to
Feature activation+0.000
achieve
Token achieve
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
relationships
Token relationships
Feature activation+0.269
are
Token are
Feature activation+1.715
doomed
Token doomed
Feature activation+0.116
,
Token,
Feature activation+0.342
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
click
Token click
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token .
Feature activation+0.000
All
Token All
Feature activation+0.000
files
Token files
Feature activation+1.015
are
Token are
Feature activation+1.706
for
Token for
Feature activation+0.880
personal
Token personal
Feature activation+0.000
use
Token use
Feature activation+0.000
only
Token only
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
All
TokenAll
Feature activation+0.000
I
Token I
Feature activation+0.289
saw
Token saw
Feature activation+1.700
was
Token was
Feature activation+0.172
a
Token a
Feature activation+0.142
photo
Token photo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
manager
Token manager
Feature activation+0.000
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
all
Token all
Feature activation+0.000
accounts
Token accounts
Feature activation+1.665
,
Token,
Feature activation+0.392
he
Token he
Feature activation+0.131
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
states
Token states
Feature activation+0.740
,
Token,
Feature activation+0.407
including
Token including
Feature activation+1.632
Israel
Token Israel
Feature activation+0.000
,
Token,
Feature activation+0.000
should
Token should
Feature activation+0.000
become
Token become
Feature activation+0.000
accessories
Token accessories
Feature activation+0.000
time
Token time
Feature activation+0.000
zones
Token zones
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
places
Token places
Feature activation+0.245
within
Token within
Feature activation+1.590
one
Token one
Feature activation+0.118
time
Token time
Feature activation+0.000
zone
Token zone
Feature activation+0.000
have
Token have
Feature activation+0.219
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+0.596
have
Token have
Feature activation+1.586
to
Token to
Feature activation+1.102
do
Token do
Feature activation+1.433
is
Token is
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
her
Token her
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
she
Token she
Feature activation+0.100
wanted
Token wanted
Feature activation+1.575
was
Token was
Feature activation+0.345
to
Token to
Feature activation+0.395
enjoy
Token enjoy
Feature activation+0.453
herself
Token herself
Feature activation+0.000
,
Token,
Feature activation+0.000
back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
all
Token all
Feature activation+0.000
worth
Token worth
Feature activation+1.570
it
Token it
Feature activation+0.440
-
Token -
Feature activation+0.349
they
Token they
Feature activation+0.129
say
Token say
Feature activation+0.150
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
all
Token all
Feature activation+0.000
accounts
Token accounts
Feature activation+1.565
,
Token,
Feature activation+0.318
the
Token the
Feature activation+0.000
initial
Token initial
Feature activation+0.000
land
Token land
Feature activation+0.000
mine
Token mine
Feature activation+0.000
plates
Tokenplates
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
templates
Token templates
Feature activation+0.729
are
Token are
Feature activation+1.551
double
Token double
Feature activation+0.217
-
Token-
Feature activation+0.000
sided
Tokensided
Feature activation+0.000
and
Token and
Feature activation+0.000
waterproof
Token waterproof
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+0.440
have
Token have
Feature activation+1.537
to
Token to
Feature activation+1.116
do
Token do
Feature activation+1.539
is
Token is
Feature activation+0.000
tap
Token tap
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
correct
Token correct
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
will
Token will
Feature activation+1.323
be
Token be
Feature activation+1.538
on
Token on
Feature activation+0.918
Comey
Token Comey
Feature activation+0.023
Thursday
Token Thursday
Feature activation+0.163
when
Token when
Feature activation+0.099
he
Token he
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+0.440
have
Token have
Feature activation+1.537
to
Token to
Feature activation+1.116
do
Token do
Feature activation+1.539
is
Token is
Feature activation+0.000
tap
Token tap
Feature activation+0.000
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
television
Token television
Feature activation+0.000
programs
Token programs
Feature activation+0.000
all
Token all
Feature activation+0.000
costumes
Token costumes
Feature activation+1.518
are
Token are
Feature activation+1.245
kept
Token kept
Feature activation+0.056
until
Token until
Feature activation+0.086
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
ops
Token ops
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
all
Token all
Feature activation+0.000
byte
Token byte
Feature activation+0.000
values
Token values
Feature activation+1.516
need
Token need
Feature activation+0.704
to
Token to
Feature activation+0.604
be
Token be
Feature activation+0.554
widened
Token widened
Feature activation+0.000
to
Token to
Feature activation+0.000
weight
Token weight
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
livestock
Token livestock
Feature activation+0.515
orders
Token orders
Feature activation+1.085
are
Token are
Feature activation+1.514
shipped
Token shipped
Feature activation+0.191
via
Token via
Feature activation+0.000
Next
Token Next
Feature activation+0.000
Day
Token Day
Feature activation+0.039
Air
Token Air
Feature activation+0.000

Top DFA by src position
MAX = 2.035

low
Token low
Feature activation-0.016
Top resid features:
inflation
Token inflation
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
which
Token which
Feature activation-0.030
Top resid features:
is
Token is
Feature activation+0.105
Top resid features:
all
Token all
Feature activation+1.806
Top resid features:
we
Token we
Feature activation+0.089
Top resid features:
can
Token can
Feature activation+0.080
Top resid features:
really
Token really
Feature activation+0.000
Top resid features:
ask
Token ask
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
discussing
Token discussing
Feature activation+0.008
Top resid features:
business
Token business
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
Meanwhile
Token Meanwhile
Feature activation-0.050
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
all
Token all
Feature activation+2.035
Top resid features:
Trump
Token Trump
Feature activation-0.006
Top resid features:
could
Token could
Feature activation+0.198
Top resid features:
do
Token do
Feature activation-0.038
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.024
Top resid features:
saying
Token saying
Feature activation+0.028
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
"
Token "
Feature activation-0.018
Top resid features:
all
Tokenall
Feature activation+1.815
Top resid features:
options
Token options
Feature activation+0.172
Top resid features:
are
Token are
Feature activation+0.068
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
table
Token table
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ŀ
TokenĿ
Feature activation-0.028
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
âĢ
Token âĢ
Feature activation-0.012
Top resid features:
ľ
Tokenľ
Feature activation-0.059
Top resid features:
All
TokenAll
Feature activation+1.858
Top resid features:
relationships
Token relationships
Feature activation+0.182
Top resid features:
are
Token are
Feature activation+0.108
Top resid features:
doomed
Token doomed
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
techniques
Token techniques
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
click
Token click
Feature activation+0.041
Top resid features:
here
Token here
Feature activation-0.014
Top resid features:
.
Token .
Feature activation-0.118
Top resid features:
All
Token All
Feature activation+2.004
Top resid features:
files
Token files
Feature activation+0.111
Top resid features:
are
Token are
Feature activation+0.065
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
personal
Token personal
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
owners
Token owners
Feature activation-0.024
Top resid features:
.
Token.
Feature activation-0.043
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
"
Token"
Feature activation-0.045
Top resid features:
All
TokenAll
Feature activation+2.000
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
saw
Token saw
Feature activation+0.052
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
photo
Token photo
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.015
Top resid features:
game
Token game
Feature activation+0.003
Top resid features:
manager
Token manager
Feature activation-0.018
Top resid features:
.
Token.
Feature activation-0.130
Top resid features:
By
Token By
Feature activation+0.307
Top resid features:
all
Token all
Feature activation+1.894
Top resid features:
accounts
Token accounts
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
persu
Token persu
Feature activation-0.005
Top resid features:
asions
Tokenasions
Feature activation-0.016
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
Australia
Token Australia
Feature activation-0.010
Top resid features:
that
Token that
Feature activation+0.042
Top resid features:
all
Token all
Feature activation+1.812
Top resid features:
states
Token states
Feature activation+0.146
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
including
Token including
Feature activation+0.029
Top resid features:
Israel
Token Israel
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.049
Top resid features:
time
Token time
Feature activation-0.012
Top resid features:
zones
Token zones
Feature activation-0.018
Top resid features:
.
Token.
Feature activation-0.140
Top resid features:
All
Token All
Feature activation+1.939
Top resid features:
places
Token places
Feature activation+0.214
Top resid features:
within
Token within
Feature activation-0.002
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
zone
Token zone
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
ľ
Tokenľ
Feature activation-0.066
Top resid features:
All
TokenAll
Feature activation+1.823
Top resid features:
you
Token you
Feature activation+0.053
Top resid features:
have
Token have
Feature activation+0.112
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
fault
Token fault
Feature activation-0.005
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
her
Token her
Feature activation-0.016
Top resid features:
own
Token own
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.052
Top resid features:
All
Token All
Feature activation+1.911
Top resid features:
she
Token she
Feature activation+0.018
Top resid features:
wanted
Token wanted
Feature activation+0.049
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
enjoy
Token enjoy
Feature activation+0.000
Top resid features:
look
Token look
Feature activation+0.030
Top resid features:
back
Token back
Feature activation-0.026
Top resid features:
,
Token,
Feature activation-0.044
Top resid features:
it
Token it
Feature activation+0.012
Top resid features:
's
Token's
Feature activation+0.097
Top resid features:
all
Token all
Feature activation+1.930
Top resid features:
worth
Token worth
Feature activation-0.034
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
administration
Token administration
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.070
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
By
TokenBy
Feature activation+0.182
Top resid features:
all
Token all
Feature activation+1.783
Top resid features:
accounts
Token accounts
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
initial
Token initial
Feature activation+0.000
Top resid features:
land
Token land
Feature activation+0.000
Top resid features:
Quality
TokenQuality
Feature activation-0.014
Top resid features:
Tem
Token Tem
Feature activation-0.013
Top resid features:
plates
Tokenplates
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
All
TokenAll
Feature activation+1.681
Top resid features:
templates
Token templates
Feature activation+0.157
Top resid features:
are
Token are
Feature activation+0.083
Top resid features:
double
Token double
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
sided
Tokensided
Feature activation+0.000
Top resid features:
factor
Token factor
Feature activation-0.003
Top resid features:
ization
Tokenization
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.035
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
All
TokenAll
Feature activation+1.681
Top resid features:
you
Token you
Feature activation+0.019
Top resid features:
have
Token have
Feature activation+0.292
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
do
Token do
Feature activation-0.023
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Come
TokenCome
Feature activation+0.014
Top resid features:
y
Tokeny
Feature activation-0.011
Top resid features:
speaks
Token speaks
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
All
TokenAll
Feature activation+1.574
Top resid features:
eyes
Token eyes
Feature activation+0.078
Top resid features:
will
Token will
Feature activation+0.173
Top resid features:
be
Token be
Feature activation+0.052
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Comey
Token Comey
Feature activation+0.000
Top resid features:
factor
Token factor
Feature activation-0.001
Top resid features:
ization
Tokenization
Feature activation-0.010
Top resid features:
.
Token.
Feature activation-0.045
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
All
TokenAll
Feature activation+1.818
Top resid features:
you
Token you
Feature activation+0.014
Top resid features:
have
Token have
Feature activation+0.086
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
For
TokenFor
Feature activation+0.084
Top resid features:
television
Token television
Feature activation+0.017
Top resid features:
programs
Token programs
Feature activation+0.094
Top resid features:
all
Token all
Feature activation+1.550
Top resid features:
costumes
Token costumes
Feature activation+0.099
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
kept
Token kept
Feature activation+0.000
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.015
Top resid features:
store
Tokenstore
Feature activation-0.004
Top resid features:
ops
Token ops
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
so
Token so
Feature activation+0.099
Top resid features:
all
Token all
Feature activation+1.647
Top resid features:
byte
Token byte
Feature activation+0.062
Top resid features:
values
Token values
Feature activation+0.040
Top resid features:
need
Token need
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
actual
Token actual
Feature activation+0.005
Top resid features:
shipping
Token shipping
Feature activation-0.001
Top resid features:
weight
Token weight
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.064
Top resid features:
All
Token All
Feature activation+1.640
Top resid features:
livestock
Token livestock
Feature activation+0.016
Top resid features:
orders
Token orders
Feature activation+0.102
Top resid features:
are
Token are
Feature activation+0.085
Top resid features:
shipped
Token shipped
Feature activation+0.000
Top resid features:
via
Token via
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.05

Head 3: 0.49

Head 4: 0.09

Head 5: 0.05

Head 6: 0.05

Head 7: 0.02

Head 8: 0.04

Head 9: 0.07

Head 10: 0.05

Head 11: 0.02

Positive logits

except2.45

except1.96

imaginable1.83

alike1.72

thereafter1.63

irrespective1.62

ynes1.61

soever1.59

therein1.59

equally1.58

whatsoever1.58

odder1.54

besides1.54

Muslims1.48

Except1.40

regardless1.40

agree1.38

individually1.37

including1.37

Including1.36

Negative logits

odore-1.43

uca-1.38

Lithuania-1.32

Zur-1.32

Spiegel-1.28

Collider-1.26

ierre-1.25

Rein-1.22

ounter-1.20

Rivals-1.20

ainment-1.19

manuel-1.19

Sz-1.19

Carnegie-1.19

Slov-1.18

berus-1.17

seq-1.17

artz-1.16

ifax-1.16

cliff-1.16

INTERVAL 1.624 - 1.804
CONTAINS 0.001%

Australia
Token Australia
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
states
Token states
Feature activation+0.740
,
Token,
Feature activation+0.407
including
Token including
Feature activation+1.632
Israel
Token Israel
Feature activation+0.000
,
Token,
Feature activation+0.000
should
Token should
Feature activation+0.000
become
Token become
Feature activation+0.000
accessories
Token accessories
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
relationships
Token relationships
Feature activation+0.269
are
Token are
Feature activation+1.715
doomed
Token doomed
Feature activation+0.116
,
Token,
Feature activation+0.342
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
"
Token "
Feature activation+0.000
all
Tokenall
Feature activation+0.000
options
Token options
Feature activation+0.625
are
Token are
Feature activation+1.726
on
Token on
Feature activation+1.100
the
Token the
Feature activation+0.169
table
Token table
Feature activation+0.000
to
Token to
Feature activation+0.000
achieve
Token achieve
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.030
we
Token we
Feature activation+0.616
can
Token can
Feature activation+1.738
really
Token really
Feature activation+0.976
ask
Token ask
Feature activation+0.582
from
Token from
Feature activation+0.000
monetary
Token monetary
Feature activation+0.000
policy
Token policy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
All
TokenAll
Feature activation+0.000
I
Token I
Feature activation+0.289
saw
Token saw
Feature activation+1.700
was
Token was
Feature activation+0.172
a
Token a
Feature activation+0.142
photo
Token photo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.444 - 1.624
CONTAINS 0.002%

back
Token back
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
all
Token all
Feature activation+0.000
worth
Token worth
Feature activation+1.570
it
Token it
Feature activation+0.440
-
Token -
Feature activation+0.349
they
Token they
Feature activation+0.129
say
Token say
Feature activation+0.150
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+0.596
have
Token have
Feature activation+1.586
to
Token to
Feature activation+1.102
do
Token do
Feature activation+1.433
is
Token is
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
television
Token television
Feature activation+0.000
programs
Token programs
Feature activation+0.000
all
Token all
Feature activation+0.000
costumes
Token costumes
Feature activation+1.518
are
Token are
Feature activation+1.245
kept
Token kept
Feature activation+0.056
until
Token until
Feature activation+0.086
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
will
Token will
Feature activation+1.323
be
Token be
Feature activation+1.538
on
Token on
Feature activation+0.918
Comey
Token Comey
Feature activation+0.023
Thursday
Token Thursday
Feature activation+0.163
when
Token when
Feature activation+0.099
he
Token he
Feature activation+0.000
that
Token that
Feature activation+0.000
investigators
Token investigators
Feature activation+0.000
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
states
Token states
Feature activation+0.822
could
Token could
Feature activation+1.501
use
Token use
Feature activation+0.293
to
Token to
Feature activation+0.188
track
Token track
Feature activation+0.000
the
Token the
Feature activation+0.000
disappeared
Token disappeared
Feature activation+0.000

INTERVAL 1.263 - 1.444
CONTAINS 0.004%

"
Token "
Feature activation+0.000
First
TokenFirst
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+0.101
can
Token can
Feature activation+1.269
look
Token look
Feature activation+0.350
at
Token at
Feature activation+0.059
previous
Token previous
Feature activation+0.000
records
Token records
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
tubes
Token tubes
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
I
Token I
Feature activation+0.194
could
Token could
Feature activation+1.347
see
Token see
Feature activation+0.832
was
Token was
Feature activation+0.000
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
three
Token three
Feature activation+1.044
carriers
Token carriers
Feature activation+0.000
are
Token are
Feature activation+1.326
also
Token also
Feature activation+0.425
offering
Token offering
Feature activation+0.259
to
Token to
Feature activation+0.000
throw
Token throw
Feature activation+0.000
in
Token in
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
claim
Token claim
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
nations
Token nations
Feature activation+0.673
have
Token have
Feature activation+1.268
âĢ
Token âĢ
Feature activation+0.755
ĺ
Tokenĺ
Feature activation+0.255
access
Tokenaccess
Feature activation+0.195
âĢ
TokenâĢ
Feature activation+0.164
Ļ
TokenĻ
Feature activation+0.000
land
Tokenland
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
on
Token on
Feature activation+0.000
all
Token all
Feature activation+0.000
seven
Token seven
Feature activation+0.860
counts
Token counts
Feature activation+1.320
in
Token in
Feature activation+0.564
a
Token a
Feature activation+0.007
campaign
Token campaign
Feature activation+0.000
finance
Token finance
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+0.000

INTERVAL 1.083 - 1.263
CONTAINS 0.006%

him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
miss
Token miss
Feature activation+0.000
all
Token all
Feature activation+0.000
but
Token but
Feature activation+0.000
four
Token four
Feature activation+1.093
games
Token games
Feature activation+0.241
last
Token last
Feature activation+0.000
season
Token season
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
shipping
Token shipping
Feature activation+0.000
weight
Token weight
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
livestock
Token livestock
Feature activation+0.515
orders
Token orders
Feature activation+1.085
are
Token are
Feature activation+1.514
shipped
Token shipped
Feature activation+0.191
via
Token via
Feature activation+0.000
Next
Token Next
Feature activation+0.000
Day
Token Day
Feature activation+0.039
Board
Token Board
Feature activation+0.000
as
Token as
Feature activation+0.000
saying
Token saying
Feature activation+0.000
all
Token all
Feature activation+0.000
players
Token players
Feature activation+0.987
were
Token were
Feature activation+1.234
safe
Token safe
Feature activation+0.721
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
is
Tokenis
Feature activation+0.000
it
Token it
Feature activation+0.000
?).
Token?).
Feature activation+0.000
All
Token All
Feature activation+0.000
you
Token you
Feature activation+0.510
need
Token need
Feature activation+1.129
now
Token now
Feature activation+0.921
is
Token is
Feature activation+0.530
to
Token to
Feature activation+0.265
write
Token write
Feature activation+0.000
some
Token some
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
,
Token,
Feature activation+1.191
a
Token a
Feature activation+0.796
four
Token four
Feature activation+0.157
-
Token-
Feature activation+0.000
star
Tokenstar
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.902 - 1.083
CONTAINS 0.014%

asset
Token asset
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
all
Token all
Feature activation+0.000
see
Token see
Feature activation+0.981
people
Token people
Feature activation+0.016
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
pull
Token pull
Feature activation+0.000
out
Tokenout
Feature activation+0.000
,
Token,
Feature activation+0.000
using
Token using
Feature activation+0.000
all
Token all
Feature activation+0.000
necessary
Token necessary
Feature activation+0.908
technical
Token technical
Feature activation+0.001
means
Token means
Feature activation+0.431
such
Token such
Feature activation+0.215
as
Token as
Feature activation+0.000
satellites
Token satellites
Feature activation+0.000
duo
Token duo
Feature activation+0.000
would
Token would
Feature activation+0.000
write
Token write
Feature activation+0.000
all
Token all
Feature activation+0.000
10
Token 10
Feature activation+0.316
episodes
Token episodes
Feature activation+0.947
before
Token before
Feature activation+0.294
production
Token production
Feature activation+0.093
begins
Token begins
Feature activation+0.000
on
Token on
Feature activation+0.000
season
Token season
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
ages
Token ages
Feature activation+1.089
and
Token and
Feature activation+0.250
skill
Token skill
Feature activation+0.030
levels
Token levels
Feature activation+0.924
,"
Token,"
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
Rex
Token Rex
Feature activation+0.000
St
Token St
Feature activation+0.000
be
Token be
Feature activation+0.000
avoiding
Token avoiding
Feature activation+0.000
Lewis
Token Lewis
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
costs
Token costs
Feature activation+0.976
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000

INTERVAL 0.722 - 0.902
CONTAINS 0.021%

III
Token III
Feature activation+0.000
).
Token ).
Feature activation+0.000
Surprisingly
Token Surprisingly
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
four
Token four
Feature activation+0.889
3
Token 3
Feature activation+0.355
âĢ²
TokenâĢ²
Feature activation+0.000
junction
Token junction
Feature activation+0.000
sequences
Token sequences
Feature activation+0.251
from
Token from
Feature activation+0.000
,
Token,
Feature activation+0.000
concluded
Token concluded
Feature activation+0.000
only
Token only
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
nine
Token nine
Feature activation+0.895
deaths
Token deaths
Feature activation+0.227
had
Token had
Feature activation+0.428
been
Token been
Feature activation+0.677
caused
Token caused
Feature activation+0.317
by
Token by
Feature activation+0.000
All
Token All
Feature activation+0.000
the
Token the
Feature activation+0.000
mechanically
Token mechanically
Feature activation+0.000
critical
Token critical
Feature activation+0.000
parts
Token parts
Feature activation+0.474
are
Token are
Feature activation+0.726
made
Token made
Feature activation+0.393
of
Token of
Feature activation+0.000
metal
Token metal
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
)
Token)
Feature activation+0.000
handles
Token handles
Feature activation+0.000
all
Token all
Feature activation+0.000
cryptographic
Token cryptographic
Feature activation+0.584
operations
Token operations
Feature activation+0.711
for
Token for
Feature activation+0.739
the
Token the
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
Watch
Token Watch
Feature activation+0.000
Series
Token Series
Feature activation+0.000
2
Token 2
Feature activation+0.000
network
Token network
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
all
Token all
Feature activation+0.000
network
Token network
Feature activation+0.000
users
Token users
Feature activation+0.774
can
Token can
Feature activation+0.986
reach
Token reach
Feature activation+0.086
it
Token it
Feature activation+0.103
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.541 - 0.722
CONTAINS 0.027%

half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
marriages
Token marriages
Feature activation+0.411
end
Token end
Feature activation+0.532
in
Token in
Feature activation+0.578
divorce
Token divorce
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
humans
Token humans
Feature activation+0.581
exist
Token exist
Feature activation+1.088
with
Token with
Feature activation+0.499
basic
Token basic
Feature activation+0.072
rights
Token rights
Feature activation+0.000
enshr
Token enshr
Feature activation+0.000
This
TokenThis
Feature activation+0.000
says
Token says
Feature activation+0.000
all
Token all
Feature activation+0.000
we
Token we
Feature activation+0.417
need
Token need
Feature activation+0.767
to
Token to
Feature activation+0.664
know
Token know
Feature activation+1.022
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
mov
Token mov
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
-
Token-
Feature activation+0.000
Mobile
TokenMobile
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Token all
Feature activation+0.000
already
Token already
Feature activation+0.871
implemented
Token implemented
Feature activation+0.560
Wi
Token Wi
Feature activation+0.000
-
Token-
Feature activation+0.000
Fi
TokenFi
Feature activation+0.000
calling
Token calling
Feature activation+0.000
,
Token,
Feature activation+0.000
capability
Token capability
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+0.569
need
Token need
Feature activation+1.315
to
Token to
Feature activation+0.996
do
Token do
Feature activation+1.388
is
Token is
Feature activation+0.060
to
Token to
Feature activation+0.000

INTERVAL 0.361 - 0.541
CONTAINS 0.042%

about
Token about
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
things
Token things
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.365
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
the
Token the
Feature activation+0.000
bourgeoisie
Token bourgeoisie
Feature activation+0.000
has
Token has
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
times
Token times
Feature activation+0.492
attributed
Token attributed
Feature activation+0.000
all
Token all
Feature activation+0.000
violent
Token violent
Feature activation+0.000
demonstrations
Token demonstrations
Feature activation+0.422
of
Token of
Feature activation+0.180
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
can
Token can
Feature activation+0.694
be
Token be
Feature activation+0.389
easily
Token easily
Feature activation+0.007
confirmed
Token confirmed
Feature activation+0.000
through
Token through
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
searches
Token searches
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
resistant
Token resistant
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
available
Token available
Feature activation+0.492
antibiotics
Token antibiotics
Feature activation+0.323
."
Token."
Feature activation+0.000
The
Token The
Feature activation+0.000
researchers
Token researchers
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
bully
Token bully
Feature activation+0.000
others
Token others
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
lose
Token lose
Feature activation+0.412
"
Token"
Feature activation+0.000
thank
Token thank
Feature activation+0.000
you
Token you
Feature activation+0.000
#
Token #
Feature activation+0.000
M
TokenM
Feature activation+0.000

INTERVAL 0.180 - 0.361
CONTAINS 0.068%

problems
Token problems
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
form
Token form
Feature activation+0.000
libraries
Token libraries
Feature activation+0.277
I
Token I
Feature activation+0.260
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.044
looked
Token looked
Feature activation+0.000
to
Token to
Feature activation+0.000
miss
Token miss
Feature activation+0.000
all
Token all
Feature activation+0.000
but
Token but
Feature activation+0.000
four
Token four
Feature activation+1.093
games
Token games
Feature activation+0.241
last
Token last
Feature activation+0.000
season
Token season
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
primary
Token primary
Feature activation+0.000
was
Token was
Feature activation+0.000
resistant
Token resistant
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
known
Token known
Feature activation+0.335
antibiotics
Token antibiotics
Feature activation+0.304
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
researchers
Token researchers
Feature activation+0.000
cultivated
Token cultivated
Feature activation+0.000
it
Token it
Feature activation+0.000
but
Token but
Feature activation+0.000
all
Token all
Feature activation+0.000
it
Token it
Feature activation+0.245
has
Token has
Feature activation+0.786
done
Token done
Feature activation+0.938
is
Token is
Feature activation+0.238
attack
Token attack
Feature activation+0.000
the
Token the
Feature activation+0.000
BJP
Token BJP
Feature activation+0.000
through
Token through
Feature activation+0.000
an
Token an
Feature activation+0.000
I
Token I
Feature activation+0.000
love
Token love
Feature activation+0.000
him
Token him
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
my
Token my
Feature activation+0.186
heart
Token heart
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000

INTERVAL 0.000 - 0.180
CONTAINS 99.816%

the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
you
Token you
Feature activation+0.000
believe
Token believe
Feature activation+0.000
it
Token it
Feature activation+0.000
eight
Token eight
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
climb
Token climb
Feature activation+0.000
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000
5
Token5
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+0.000
annual
Token annual
Feature activation+0.000
spending
Token spending
Feature activation+0.000
take
Token take
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
masses
Token masses
Feature activation+0.000
than
Token than
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
large
Token large
Feature activation+0.000
political
Token political
Feature activation+0.000
separatists
Token separatists
Feature activation+0.000
,
Token,
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
from
Token from
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Bal
Token Bal
Feature activation+0.000
uch
Tokenuch
Feature activation+0.000
istan
Tokenistan
Feature activation+0.000
GAM
Token GAM
Feature activation+0.000
ET
TokenET
Feature activation+0.000
IME
TokenIME
Feature activation+0.000
LIVE
Token LIVE
Feature activation+0.000
2
Token 2
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
-
Token-
Feature activation+0.000
TV
TokenTV
Feature activation+0.000
8
Token 8
Feature activation+0.000
:
Token:
Feature activation+0.000
22
Token22
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H2.3: (feature 21759)

TOP ACTIVATIONS
MAX = 2.769

.
Token.
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
every
Token every
Feature activation+0.000
nation
Token nation
Feature activation+0.658
that
Token that
Feature activation+2.769
America
Token America
Feature activation+0.711
conqu
Token conqu
Feature activation+0.075
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.474
is
Token is
Feature activation+0.149
affordable
Token affordable
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
at
Token at
Feature activation+0.000
every
Token every
Feature activation+0.000
stage
Token stage
Feature activation+2.766
of
Token of
Feature activation+1.389
life
Token life
Feature activation+0.937
,
Token,
Feature activation+0.682
from
Token from
Feature activation+0.000
birth
Token birth
Feature activation+0.000
personally
Token personally
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
every
Token every
Feature activation+0.000
word
Token word
Feature activation+1.010
you
Token you
Feature activation+2.627
say
Token say
Feature activation+2.197
.
Token.
Feature activation+0.476
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
120
Token 120
Feature activation+0.000
.
Token.
Feature activation+0.000
Every
Token Every
Feature activation+0.055
character
Token character
Feature activation+1.465
could
Token could
Feature activation+1.871
have
Token have
Feature activation+2.623
a
Token a
Feature activation+1.398
grand
Token grand
Feature activation+0.000
total
Token total
Feature activation+0.000
of
Token of
Feature activation+0.000
700
Token 700
Feature activation+0.000
News
Token News
Feature activation+0.000
in
Token in
Feature activation+0.000
every
Token every
Feature activation+0.098
bar
Token bar
Feature activation+0.895
and
Token and
Feature activation+1.211
restaurant
Token restaurant
Feature activation+2.608
in
Token in
Feature activation+1.781
big
Token big
Feature activation+0.218
chunks
Token chunks
Feature activation+0.406
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
team
Token team
Feature activation+1.072
he
Token he
Feature activation+2.598
âĢ
TokenâĢ
Feature activation+0.013
Ļ
TokenĻ
Feature activation+0.003
s
Tokens
Feature activation+0.363
known
Token known
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+0.000
making
Token making
Feature activation+0.000
sure
Token sure
Feature activation+0.000
at
Token at
Feature activation+0.000
every
Token every
Feature activation+0.000
stage
Token stage
Feature activation+2.475
along
Token along
Feature activation+0.000
the
Token the
Feature activation+0.576
line
Token line
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
time
Token time
Feature activation+0.000
he
Token he
Feature activation+2.458
sees
Token sees
Feature activation+0.742
me
Token me
Feature activation+0.319
,
Token,
Feature activation+0.507
he
Token he
Feature activation+0.418
says
Token says
Feature activation+0.000
a
Token a
Feature activation+0.000
moistur
Token moistur
Feature activation+0.000
izer
Tokenizer
Feature activation+0.000
every
Token every
Feature activation+0.000
time
Token time
Feature activation+0.064
you
Token you
Feature activation+2.449
wash
Token wash
Feature activation+2.063
your
Token your
Feature activation+1.089
hair
Token hair
Feature activation+0.000
.
Token.
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
item
Token item
Feature activation+1.027
I
Token I
Feature activation+2.213
can
Token can
Feature activation+2.441
give
Token give
Feature activation+1.308
a
Token a
Feature activation+0.241
new
Token new
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
to
Token to
Feature activation+0.103
every
Token every
Feature activation+0.028
single
Token single
Feature activation+0.177
African
Token African
Feature activation+0.717
-
Token-
Feature activation+0.330
American
TokenAmerican
Feature activation+0.989
citizen
Token citizen
Feature activation+2.440
in
Token in
Feature activation+1.241
this
Token this
Feature activation+0.408
country
Token country
Feature activation+0.000
who
Token who
Feature activation+0.136
wants
Token wants
Feature activation+0.000
Podcast
Token Podcast
Feature activation+0.000
rec
Token rec
Feature activation+0.000
aps
Tokenaps
Feature activation+0.000
every
Token every
Feature activation+0.000
Wild
Token Wild
Feature activation+0.000
Card
Token Card
Feature activation+2.436
game
Token game
Feature activation+1.531
and
Token and
Feature activation+1.370
looks
Token looks
Feature activation+0.644
ahead
Token ahead
Feature activation+0.000
to
Token to
Feature activation+0.000
will
Token will
Feature activation+0.000
win
Token win
Feature activation+0.000
every
Token every
Feature activation+0.000
press
Token press
Feature activation+0.370
conference
Token conference
Feature activation+2.085
he
Token he
Feature activation+2.406
holds
Token holds
Feature activation+0.399
.
Token.
Feature activation+0.330
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jim
TokenJim
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
every
Token every
Feature activation+0.000
chance
Token chance
Feature activation+0.498
he
Token he
Feature activation+2.404
gets
Token gets
Feature activation+1.475
.
Token.
Feature activation+0.595
The
Token The
Feature activation+0.000
MSM
Token MSM
Feature activation+0.000
is
Token is
Feature activation+0.000
gives
Token gives
Feature activation+0.000
away
Token away
Feature activation+0.000
every
Token every
Feature activation+0.000
major
Token major
Feature activation+0.000
action
Token action
Feature activation+1.347
beat
Token beat
Feature activation+2.373
).
Token).
Feature activation+0.000
Trail
Token Trail
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
uses
Token uses
Feature activation+0.000
in
Token in
Feature activation+0.000
every
Token every
Feature activation+0.000
damn
Token damn
Feature activation+0.000
movie
Token movie
Feature activation+1.250
he
Token he
Feature activation+2.347
makes
Token makes
Feature activation+0.907
.
Token.
Feature activation+0.000
Anyway
Token Anyway
Feature activation+0.000
,
Token,
Feature activation+0.000
old
Token old
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
country
Token country
Feature activation+0.247
in
Token in
Feature activation+2.318
Europe
Token Europe
Feature activation+0.628
should
Token should
Feature activation+0.785
contribute
Token contribute
Feature activation+0.105
to
Token to
Feature activation+0.000
strengthening
Token strengthening
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
five
Token five
Feature activation+0.462
numbers
Token numbers
Feature activation+0.301
you
Token you
Feature activation+2.248
reach
Token reach
Feature activation+0.808
the
Token the
Feature activation+0.369
next
Token next
Feature activation+0.000
stage
Token stage
Feature activation+0.000
,
Token,
Feature activation+0.000
every
Token every
Feature activation+0.515
magazine
Token magazine
Feature activation+1.541
and
Token and
Feature activation+1.543
every
Token every
Feature activation+0.600
TV
Token TV
Feature activation+0.569
anchor
Token anchor
Feature activation+2.247
screamed
Token screamed
Feature activation+1.402
for
Token for
Feature activation+1.261
gun
Token gun
Feature activation+0.000
owners
Token owners
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.145
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
just
Tokenjust
Feature activation+0.000
every
Token every
Feature activation+0.000
time
Token time
Feature activation+0.000
you
Token you
Feature activation+2.235
use
Token use
Feature activation+1.358
the
Token the
Feature activation+0.307
headphones
Token headphones
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token 3
Feature activation+0.000

Top DFA by src position
MAX = 3.639

for
Token for
Feature activation+0.012
Top resid features:
water
Token water
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.082
Top resid features:
Meanwhile
Token Meanwhile
Feature activation+0.068
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
every
Token every
Feature activation+3.228
Top resid features:
nation
Token nation
Feature activation+0.357
Top resid features:
that
Token that
Feature activation+0.089
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
conqu
Token conqu
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
affordable
Token affordable
Feature activation+0.089
Top resid features:
health
Token health
Feature activation+0.021
Top resid features:
care
Token care
Feature activation+0.038
Top resid features:
at
Token at
Feature activation+0.025
Top resid features:
every
Token every
Feature activation+3.639
Top resid features:
stage
Token stage
Feature activation-0.006
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.033
Top resid features:
you
Token you
Feature activation+0.019
Top resid features:
personally
Token personally
Feature activation+0.004
Top resid features:
thinking
Token thinking
Feature activation-0.052
Top resid features:
about
Token about
Feature activation-0.044
Top resid features:
every
Token every
Feature activation+3.060
Top resid features:
word
Token word
Feature activation+0.508
Top resid features:
you
Token you
Feature activation+0.073
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
5
Token 5
Feature activation+0.018
Top resid features:
until
Token until
Feature activation+0.047
Top resid features:
120
Token 120
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
Every
Token Every
Feature activation+3.057
Top resid features:
character
Token character
Feature activation+0.412
Top resid features:
could
Token could
Feature activation+0.227
Top resid features:
have
Token have
Feature activation-0.033
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
grand
Token grand
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.055
Top resid features:
is
Tokenis
Feature activation+0.094
Top resid features:
Fox
Token Fox
Feature activation-0.017
Top resid features:
News
Token News
Feature activation-0.022
Top resid features:
in
Token in
Feature activation+0.057
Top resid features:
every
Token every
Feature activation+3.140
Top resid features:
bar
Token bar
Feature activation+0.184
Top resid features:
and
Token and
Feature activation+0.102
Top resid features:
restaurant
Token restaurant
Feature activation-0.008
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
big
Token big
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
He
TokenHe
Feature activation+0.081
Top resid features:
said
Token said
Feature activation-0.055
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
every
Token every
Feature activation+3.135
Top resid features:
ultimate
Token ultimate
Feature activation+0.124
Top resid features:
team
Token team
Feature activation+0.355
Top resid features:
he
Token he
Feature activation+0.226
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
Scotland
Token Scotland
Feature activation-0.010
Top resid features:
about
Token about
Feature activation+0.017
Top resid features:
making
Token making
Feature activation-0.013
Top resid features:
sure
Token sure
Feature activation-0.059
Top resid features:
at
Token at
Feature activation+0.131
Top resid features:
every
Token every
Feature activation+3.440
Top resid features:
stage
Token stage
Feature activation-0.014
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
line
Token line
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
false
Token false
Feature activation-0.023
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
"
Token"
Feature activation+0.014
Top resid features:
Every
TokenEvery
Feature activation+3.110
Top resid features:
time
Token time
Feature activation+0.169
Top resid features:
he
Token he
Feature activation+0.181
Top resid features:
sees
Token sees
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
as
Token as
Feature activation+0.036
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
moistur
Token moistur
Feature activation+0.028
Top resid features:
izer
Tokenizer
Feature activation-0.008
Top resid features:
every
Token every
Feature activation+2.997
Top resid features:
time
Token time
Feature activation+0.344
Top resid features:
you
Token you
Feature activation+0.098
Top resid features:
wash
Token wash
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
hair
Token hair
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.037
Top resid features:
mmm
Tokenmmm
Feature activation-0.012
Top resid features:
...
Token...
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
Every
TokenEvery
Feature activation+2.801
Top resid features:
item
Token item
Feature activation+0.220
Top resid features:
I
Token I
Feature activation+0.333
Top resid features:
can
Token can
Feature activation+0.047
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
asking
Token asking
Feature activation-0.007
Top resid features:
for
Token for
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
vote
Token vote
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
every
Token every
Feature activation+3.270
Top resid features:
single
Token single
Feature activation+0.050
Top resid features:
African
Token African
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.011
Top resid features:
American
TokenAmerican
Feature activation-0.002
Top resid features:
citizen
Token citizen
Feature activation+0.006
Top resid features:
The
Token The
Feature activation+0.013
Top resid features:
NFL
Token NFL
Feature activation+0.032
Top resid features:
Podcast
Token Podcast
Feature activation-0.009
Top resid features:
rec
Token rec
Feature activation+0.020
Top resid features:
aps
Tokenaps
Feature activation-0.002
Top resid features:
every
Token every
Feature activation+2.671
Top resid features:
Wild
Token Wild
Feature activation+0.624
Top resid features:
Card
Token Card
Feature activation+0.064
Top resid features:
game
Token game
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
looks
Token looks
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.067
Top resid features:
He
Token He
Feature activation+0.089
Top resid features:
will
Token will
Feature activation+0.030
Top resid features:
win
Token win
Feature activation+0.020
Top resid features:
every
Token every
Feature activation+3.010
Top resid features:
press
Token press
Feature activation+0.187
Top resid features:
conference
Token conference
Feature activation-0.045
Top resid features:
he
Token he
Feature activation+0.104
Top resid features:
holds
Token holds
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.011
Top resid features:
the
Tokenthe
Feature activation-0.009
Top resid features:
enemy
Token enemy
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation+0.078
Top resid features:
Ŀ
TokenĿ
Feature activation+0.013
Top resid features:
every
Token every
Feature activation+2.735
Top resid features:
chance
Token chance
Feature activation+0.332
Top resid features:
he
Token he
Feature activation+0.156
Top resid features:
gets
Token gets
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
6
Token 6
Feature activation+0.050
Top resid features:
(
Token (
Feature activation+0.057
Top resid features:
which
Tokenwhich
Feature activation-0.003
Top resid features:
gives
Token gives
Feature activation+0.069
Top resid features:
away
Token away
Feature activation-0.056
Top resid features:
every
Token every
Feature activation+2.761
Top resid features:
major
Token major
Feature activation+0.185
Top resid features:
action
Token action
Feature activation+0.555
Top resid features:
beat
Token beat
Feature activation+0.067
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
Trail
Token Trail
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
he
Token he
Feature activation+0.020
Top resid features:
always
Token always
Feature activation+0.009
Top resid features:
uses
Token uses
Feature activation+0.044
Top resid features:
in
Token in
Feature activation+0.060
Top resid features:
every
Token every
Feature activation+2.993
Top resid features:
damn
Token damn
Feature activation+0.068
Top resid features:
movie
Token movie
Feature activation+0.320
Top resid features:
he
Token he
Feature activation+0.105
Top resid features:
makes
Token makes
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
ľ
Tokenľ
Feature activation-0.020
Top resid features:
Every
TokenEvery
Feature activation+2.898
Top resid features:
country
Token country
Feature activation+0.307
Top resid features:
in
Token in
Feature activation+0.190
Top resid features:
Europe
Token Europe
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:
contribute
Token contribute
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
1
Token 1
Feature activation+0.041
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
Ċ
TokenĊ
Feature activation+0.087
Top resid features:
Every
TokenEvery
Feature activation+2.766
Top resid features:
five
Token five
Feature activation-0.079
Top resid features:
numbers
Token numbers
Feature activation+0.342
Top resid features:
you
Token you
Feature activation+0.086
Top resid features:
reach
Token reach
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
newspaper
Token newspaper
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.075
Top resid features:
every
Token every
Feature activation+0.969
Top resid features:
magazine
Token magazine
Feature activation+0.040
Top resid features:
and
Token and
Feature activation+0.102
Top resid features:
every
Token every
Feature activation+1.947
Top resid features:
TV
Token TV
Feature activation-0.026
Top resid features:
anchor
Token anchor
Feature activation+0.044
Top resid features:
screamed
Token screamed
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
gun
Token gun
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.043
Top resid features:
need
Token need
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
read
Token read
Feature activation-0.028
Top resid features:
just
Tokenjust
Feature activation+0.027
Top resid features:
every
Token every
Feature activation+2.866
Top resid features:
time
Token time
Feature activation+0.282
Top resid features:
you
Token you
Feature activation+0.049
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
headphones
Token headphones
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.02

Head 2: 0.05

Head 3: 0.46

Head 4: 0.05

Head 5: 0.06

Head 6: 0.04

Head 7: 0.03

Head 8: 0.05

Head 9: 0.07

Head 10: 0.06

Head 11: 0.03

Positive logits

imaginable1.82

except1.55

omnia1.49

acca1.49

conceivable1.44

oso1.42

except1.37

inery1.35

perty1.34

ixt1.30

concess1.28

nut1.28

respect1.26

necessary1.26

Hallow1.25

foss1.24

Tes1.24

ifice1.24

adder1.24

Jew1.23

Negative logits

ilies-1.35

Zur-1.28

favorites-1.21

Supplemental-1.20

STA-1.19

cousins-1.18

aters-1.18

prevailed-1.17

Compliance-1.16

Cance-1.16

igans-1.16

tongues-1.13

iers-1.13

ainment-1.12

repositories-1.11

Vir-1.10

Motors-1.09

arty-1.09

bable-1.08

iere-1.08

INTERVAL 2.492 - 2.769
CONTAINS 0.001%

said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
team
Token team
Feature activation+1.072
he
Token he
Feature activation+2.598
âĢ
TokenâĢ
Feature activation+0.013
Ļ
TokenĻ
Feature activation+0.003
s
Tokens
Feature activation+0.363
known
Token known
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Meanwhile
Token Meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
every
Token every
Feature activation+0.000
nation
Token nation
Feature activation+0.658
that
Token that
Feature activation+2.769
America
Token America
Feature activation+0.711
conqu
Token conqu
Feature activation+0.075
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.474
is
Token is
Feature activation+0.149
affordable
Token affordable
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
at
Token at
Feature activation+0.000
every
Token every
Feature activation+0.000
stage
Token stage
Feature activation+2.766
of
Token of
Feature activation+1.389
life
Token life
Feature activation+0.937
,
Token,
Feature activation+0.682
from
Token from
Feature activation+0.000
birth
Token birth
Feature activation+0.000
120
Token 120
Feature activation+0.000
.
Token.
Feature activation+0.000
Every
Token Every
Feature activation+0.055
character
Token character
Feature activation+1.465
could
Token could
Feature activation+1.871
have
Token have
Feature activation+2.623
a
Token a
Feature activation+1.398
grand
Token grand
Feature activation+0.000
total
Token total
Feature activation+0.000
of
Token of
Feature activation+0.000
700
Token 700
Feature activation+0.000
personally
Token personally
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
every
Token every
Feature activation+0.000
word
Token word
Feature activation+1.010
you
Token you
Feature activation+2.627
say
Token say
Feature activation+2.197
.
Token.
Feature activation+0.476
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 2.215 - 2.492
CONTAINS 0.002%

blue
Token blue
Feature activation+0.000
ones
Token ones
Feature activation+0.000
every
Token every
Feature activation+0.000
now
Token now
Feature activation+0.525
and
Token and
Feature activation+0.588
then
Token then
Feature activation+2.216
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.045
go
Token go
Feature activation+0.049
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Every
TokenEvery
Feature activation+0.000
item
Token item
Feature activation+1.027
I
Token I
Feature activation+2.213
can
Token can
Feature activation+2.441
give
Token give
Feature activation+1.308
a
Token a
Feature activation+0.241
new
Token new
Feature activation+0.000
purpose
Token purpose
Feature activation+0.000
to
Token to
Feature activation+0.103
enemy
Token enemy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
every
Token every
Feature activation+0.000
chance
Token chance
Feature activation+0.498
he
Token he
Feature activation+2.404
gets
Token gets
Feature activation+1.475
.
Token.
Feature activation+0.595
The
Token The
Feature activation+0.000
MSM
Token MSM
Feature activation+0.000
is
Token is
Feature activation+0.000
uses
Token uses
Feature activation+0.000
in
Token in
Feature activation+0.000
every
Token every
Feature activation+0.000
damn
Token damn
Feature activation+0.000
movie
Token movie
Feature activation+1.250
he
Token he
Feature activation+2.347
makes
Token makes
Feature activation+0.907
.
Token.
Feature activation+0.000
Anyway
Token Anyway
Feature activation+0.000
,
Token,
Feature activation+0.000
old
Token old
Feature activation+0.000
will
Token will
Feature activation+0.000
win
Token win
Feature activation+0.000
every
Token every
Feature activation+0.000
press
Token press
Feature activation+0.370
conference
Token conference
Feature activation+2.085
he
Token he
Feature activation+2.406
holds
Token holds
Feature activation+0.399
.
Token.
Feature activation+0.330
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jim
TokenJim
Feature activation+0.000

INTERVAL 1.938 - 2.215
CONTAINS 0.003%

contest
Token contest
Feature activation+0.000
where
Token where
Feature activation+0.000
every
Token every
Feature activation+0.000
fight
Token fight
Feature activation+1.152
matters
Token matters
Feature activation+1.211
in
Token in
Feature activation+2.065
a
Token a
Feature activation+1.558
global
Token global
Feature activation+0.000
battle
Token battle
Feature activation+0.000
for
Token for
Feature activation+0.228
supremacy
Token supremacy
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
Every
Token Every
Feature activation+0.000
chance
Token chance
Feature activation+0.602
we
Token we
Feature activation+1.929
get
Token get
Feature activation+2.167
,
Token,
Feature activation+0.910
we
Token we
Feature activation+0.839
document
Token document
Feature activation+0.412
the
Token the
Feature activation+0.000
elders
Token elders
Feature activation+0.000
,
Token,
Feature activation+0.000
examining
Token examining
Feature activation+0.000
every
Token every
Feature activation+0.000
twist
Token twist
Feature activation+0.705
and
Token and
Feature activation+0.960
turn
Token turn
Feature activation+2.140
of
Token of
Feature activation+0.356
a
Token a
Feature activation+0.527
race
Token race
Feature activation+0.000
that
Token that
Feature activation+0.001
has
Token has
Feature activation+0.000
every
Token every
Feature activation+0.000
voter
Token voter
Feature activation+0.477
âĢ
TokenâĢ
Feature activation+0.309
Ļ
TokenĻ
Feature activation+0.582
s
Tokens
Feature activation+0.679
access
Token access
Feature activation+2.023
to
Token to
Feature activation+0.075
the
Token the
Feature activation+0.000
ballot
Token ballot
Feature activation+0.000
box
Token box
Feature activation+0.000
,
Token,
Feature activation+0.000
about
Token about
Feature activation+0.000
hanging
Token hanging
Feature activation+0.000
on
Token on
Feature activation+0.000
every
Token every
Feature activation+0.000
word
Token word
Feature activation+0.668
of
Token of
Feature activation+2.138
a
Token a
Feature activation+1.923
19
Token 19
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.662 - 1.938
CONTAINS 0.005%

your
Token your
Feature activation+0.000
writing
Token writing
Feature activation+0.000
.
Token.
Feature activation+0.000
Every
Token Every
Feature activation+0.000
entry
Token entry
Feature activation+1.602
is
Token is
Feature activation+1.770
a
Token a
Feature activation+2.168
pleasure
Token pleasure
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
.
Token.
Feature activation+0.000
all
Token all
Feature activation+0.000
topics
Token topics
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
every
Token every
Feature activation+0.000
form
Token form
Feature activation+1.693
,
Token,
Feature activation+0.752
in
Token in
Feature activation+1.165
accordance
Token accordance
Feature activation+0.295
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
every
Token every
Feature activation+0.000
major
Token major
Feature activation+0.000
international
Token international
Feature activation+0.000
conservation
Token conservation
Feature activation+0.000
group
Token group
Feature activation+1.666
has
Token has
Feature activation+1.838
established
Token established
Feature activation+0.074
a
Token a
Feature activation+0.000
China
Token China
Feature activation+0.000
office
Token office
Feature activation+0.000
to
Token to
Feature activation+0.000
ried
Tokenried
Feature activation+0.000
by
Token by
Feature activation+0.000
every
Token every
Feature activation+0.000
media
Token media
Feature activation+0.352
outlet
Token outlet
Feature activation+2.059
in
Token in
Feature activation+1.671
the
Token the
Feature activation+0.764
country
Token country
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
this
Token this
Feature activation+0.000
birth
Token birth
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
song
Token song
Feature activation+0.381
I
Token I
Feature activation+1.727
ended
Token ended
Feature activation+0.261
up
Token up
Feature activation+0.060
making
Token making
Feature activation+0.834
after
Token after
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.385 - 1.662
CONTAINS 0.009%

earn
Token earn
Feature activation+0.000
77
Token 77
Feature activation+0.000
¢
Token¢
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.288
dollar
Token dollar
Feature activation+1.550
men
Token men
Feature activation+0.467
earn
Token earn
Feature activation+1.628
).
Token).
Feature activation+0.173
This
Token This
Feature activation+0.000
national
Token national
Feature activation+0.000
investigate
Token investigate
Feature activation+0.000
every
Token every
Feature activation+0.000
sal
Token sal
Feature activation+0.735
acious
Tokenacious
Feature activation+0.789
claim
Token claim
Feature activation+1.422
or
Token or
Feature activation+1.444
rumor
Token rumor
Feature activation+0.719
about
Token about
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
Included
Token Included
Feature activation+0.000
rec
Token rec
Feature activation+0.000
aps
Tokenaps
Feature activation+0.000
every
Token every
Feature activation+0.000
Wild
Token Wild
Feature activation+0.000
Card
Token Card
Feature activation+2.436
game
Token game
Feature activation+1.531
and
Token and
Feature activation+1.370
looks
Token looks
Feature activation+0.644
ahead
Token ahead
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+0.000
every
Token every
Feature activation+0.000
form
Token form
Feature activation+0.696
of
Token of
Feature activation+1.737
comedy
Token comedy
Feature activation+1.456
from
Token from
Feature activation+0.472
the
Token the
Feature activation+0.221
small
Token small
Feature activation+0.000
stage
Token stage
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
every
Token every
Feature activation+0.000
chance
Token chance
Feature activation+0.498
he
Token he
Feature activation+2.404
gets
Token gets
Feature activation+1.475
.
Token.
Feature activation+0.595
The
Token The
Feature activation+0.000
MSM
Token MSM
Feature activation+0.000
is
Token is
Feature activation+0.000
going
Token going
Feature activation+0.000

INTERVAL 1.108 - 1.385
CONTAINS 0.013%

and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
effort
Token effort
Feature activation+0.074
will
Token will
Feature activation+0.491
be
Token be
Feature activation+0.336
made
Token made
Feature activation+1.377
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
che
Tokenche
Feature activation+0.000
dule
Tokendule
Feature activation+0.000
their
Token their
Feature activation+0.000
list
Tokenlist
Feature activation+0.000
every
Token every
Feature activation+0.000
Monday
Token Monday
Feature activation+0.329
morning
Token morning
Feature activation+0.000
,
Token,
Feature activation+0.249
once
Token once
Feature activation+1.345
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
stamps
Token stamps
Feature activation+0.000
and
Token and
Feature activation+0.000
placed
Token placed
Feature activation+0.000
into
Token into
Feature activation+0.000
every
Token every
Feature activation+0.000
electronic
Token electronic
Feature activation+1.110
device
Token device
Feature activation+1.556
on
Token on
Feature activation+1.117
the
Token the
Feature activation+0.683
planet
Token planet
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
answering
Token answering
Feature activation+0.000
every
Token every
Feature activation+0.000
single
Token single
Feature activation+0.000
question
Token question
Feature activation+0.418
put
Token put
Feature activation+1.322
to
Token to
Feature activation+0.443
him
Token him
Feature activation+0.101
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
every
Token every
Feature activation+0.000
mountains
Token mountains
Feature activation+0.000
ide
Tokenide
Feature activation+1.291
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000
ring
Token ring
Feature activation+0.000

INTERVAL 0.831 - 1.108
CONTAINS 0.018%

50
Token 50
Feature activation+0.000
¢
Token¢
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
dollar
Token dollar
Feature activation+1.416
contributed
Token contributed
Feature activation+0.942
by
Token by
Feature activation+0.650
an
Token an
Feature activation+0.000
employee
Token employee
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
scenarios
Token scenarios
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
every
Tokenevery
Feature activation+0.000
where
Tokenwhere
Feature activation+0.000
outside
Token outside
Feature activation+0.000
of
Token of
Feature activation+0.856
repressive
Token repressive
Feature activation+0.263
governments
Token governments
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.107
an
Tokenan
Feature activation+0.000
onym
Tokenonym
Feature activation+0.000
8
Token8
Feature activation+0.000
in
Token in
Feature activation+0.000
almost
Token almost
Feature activation+0.000
every
Token every
Feature activation+0.000
aspect
Token aspect
Feature activation+1.643
till
Token till
Feature activation+0.941
the
Token the
Feature activation+0.472
last
Token last
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
in
Token in
Feature activation+0.000
almost
Token almost
Feature activation+0.000
every
Token every
Feature activation+0.000
city
Token city
Feature activation+0.898
,
Token,
Feature activation+1.139
attracting
Token attracting
Feature activation+0.841
175
Token 175
Feature activation+0.088
million
Token million
Feature activation+0.000
visitors
Token visitors
Feature activation+0.000
per
Token per
Feature activation+0.000
year
Token year
Feature activation+0.000
hope
Token hope
Feature activation+0.000
you
Token you
Feature activation+0.000
spend
Token spend
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.030
in
Token in
Feature activation+0.908
prison
Token prison
Feature activation+0.946
thinking
Token thinking
Feature activation+0.174
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
life
Token life
Feature activation+0.000

INTERVAL 0.554 - 0.831
CONTAINS 0.022%

show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
election
Token election
Feature activation+1.147
are
Token are
Feature activation+0.722
finding
Token finding
Feature activation+1.447
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
every
Token every
Feature activation+0.000
year
Token year
Feature activation+0.000
for
Token for
Feature activation+2.117
free
Token free
Feature activation+0.549
.
Token.
Feature activation+0.627
Under
Token Under
Feature activation+0.000
new
Token new
Feature activation+0.000
provincial
Token provincial
Feature activation+0.000
rules
Token rules
Feature activation+0.000
,
Token,
Feature activation+0.000
been
Token been
Feature activation+0.000
shared
Token shared
Feature activation+0.000
by
Token by
Feature activation+0.000
every
Token every
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.242
of
Token of
Feature activation+0.747
the
Token the
Feature activation+1.235
Treasury
Token Treasury
Feature activation+0.000
,
Token,
Feature activation+0.014
regardless
Token regardless
Feature activation+0.000
of
Token of
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
not
Token not
Feature activation+0.000
bring
Token bring
Feature activation+0.000
every
Token every
Feature activation+0.000
offender
Token offender
Feature activation+1.142
to
Token to
Feature activation+0.611
justice
Token justice
Feature activation+1.190
,
Token,
Feature activation+0.421
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
every
Token every
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.059
I
TokenI
Feature activation+0.742
need
Token need
Feature activation+1.406
you
Token you
Feature activation+1.362
to
Token to
Feature activation+0.000
sell
Token sell
Feature activation+0.446
this
Token this
Feature activation+0.000

INTERVAL 0.277 - 0.554
CONTAINS 0.030%

down
Token down
Feature activation+0.000
barriers
Token barriers
Feature activation+0.000
at
Token at
Feature activation+0.000
every
Token every
Feature activation+0.000
interval
Token interval
Feature activation+1.899
and
Token and
Feature activation+0.364
showed
Token showed
Feature activation+0.054
the
Token the
Feature activation+0.032
company
Token company
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
pret
Token pret
Feature activation+0.307
ense
Tokenense
Feature activation+1.081
of
Token of
Feature activation+1.413
international
Token international
Feature activation+0.381
order
Token order
Feature activation+1.072
or
Token or
Feature activation+0.065
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+0.000
doctrine
Token doctrine
Feature activation+0.000
catch
Token catch
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.396
three
Token three
Feature activation+0.000
rushing
Token rushing
Feature activation+0.000
attempts
Token attempts
Feature activation+0.382
in
Token in
Feature activation+0.987
his
Token his
Feature activation+0.540
career
Token career
Feature activation+0.000
.
Token.
Feature activation+0.000
Cliff
Token Cliff
Feature activation+0.000
every
Token every
Feature activation+0.000
nation
Token nation
Feature activation+0.630
should
Token should
Feature activation+1.003
have
Token have
Feature activation+1.731
an
Token an
Feature activation+0.294
opportunity
Token opportunity
Feature activation+0.550
to
Token to
Feature activation+0.006
participate
Token participate
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
qualification
Token qualification
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Each
TokenEach
Feature activation+0.000
character
Token character
Feature activation+0.000
has
Token has
Feature activation+0.363
triggers
Token triggers
Feature activation+0.000
dependent
Token dependent
Feature activation+0.000
on
Token on
Feature activation+0.000
Harmony
Token Harmony
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.277
CONTAINS 99.897%

,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
uniformly
Token uniformly
Feature activation+0.000
support
Token support
Feature activation+0.000
women
Token women
Feature activation+0.000
's
Token's
Feature activation+0.000
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
choose
Token choose
Feature activation+0.000
,
Token,
Feature activation+0.000
joined
Token joined
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nice
Token nice
Feature activation+0.000
view
Token view
Feature activation+0.000
showing
Token showing
Feature activation+0.000
spacecraft
Token spacecraft
Feature activation+0.000
directions
Token directions
Feature activation+0.000
(
Token (
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
option
Token option
Feature activation+0.000
is
Token is
Feature activation+0.000
maintained
Token maintained
Feature activation+0.000
for
Token for
Feature activation+0.000
legacy
Token legacy
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
only
Token only
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
purchaser
Token purchaser
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
an
Token an
Feature activation+0.000
informed
Token informed
Feature activation+0.000
choice
Token choice
Feature activation+0.000
with
Token with
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
)
Token)
Feature activation+0.000
deeply
Token deeply
Feature activation+0.000
interconnected
Token interconnected
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
I
Token I
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H2.3: (feature 15052)

TOP ACTIVATIONS
MAX = 3.142

doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.896
were
Token were
Feature activation+2.683
still
Token still
Feature activation+3.142
together
Token together
Feature activation+0.612
and
Token and
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
her
Token her
Feature activation+0.000
in
Token in
Feature activation+0.000
s
Tokens
Feature activation+0.000
email
Token email
Feature activation+0.000
server
Token server
Feature activation+0.000
while
Token while
Feature activation+0.000
she
Token she
Feature activation+1.499
was
Token was
Feature activation+3.018
secretary
Token secretary
Feature activation+1.439
of
Token of
Feature activation+0.008
state
Token state
Feature activation+0.150
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Management
Token Management
Feature activation+0.000
that
Token that
Feature activation+0.000
while
Token while
Feature activation+0.000
plans
Token plans
Feature activation+0.000
were
Token were
Feature activation+2.566
still
Token still
Feature activation+2.984
in
Token in
Feature activation+1.031
the
Token the
Feature activation+0.110
very
Token very
Feature activation+0.000
early
Token early
Feature activation+0.000
stages
Token stages
Feature activation+0.000
supported
Token supported
Feature activation+0.000
her
Token her
Feature activation+0.000
partner
Token partner
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.929
was
Token was
Feature activation+2.927
in
Token in
Feature activation+1.863
jail
Token jail
Feature activation+1.262
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
sent
Token sent
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.344
was
Token was
Feature activation+2.705
on
Token on
Feature activation+2.432
vacation
Token vacation
Feature activation+0.533
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
I
Token I
Feature activation+0.000
I
Token I
Feature activation+0.000
met
Token met
Feature activation+0.000
her
Token her
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.231
was
Token was
Feature activation+2.692
campaigning
Token campaigning
Feature activation+2.262
for
Token for
Feature activation+0.000
John
Token John
Feature activation+0.000
Kerry
Token Kerry
Feature activation+0.000
.
Token.
Feature activation+0.000
or
Token or
Feature activation+0.000
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.896
were
Token were
Feature activation+2.683
still
Token still
Feature activation+3.142
together
Token together
Feature activation+0.612
and
Token and
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
her
Token her
Feature activation+0.000
,"
Token,"
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
PCs
Token PCs
Feature activation+0.324
will
Token will
Feature activation+0.533
still
Token still
Feature activation+2.642
be
Token be
Feature activation+0.621
able
Token able
Feature activation+0.822
to
Token to
Feature activation+0.000
run
Token run
Feature activation+0.000
"
Token "
Feature activation+0.000
Sports
Token Sports
Feature activation+0.000
Management
Token Management
Feature activation+0.000
that
Token that
Feature activation+0.000
while
Token while
Feature activation+0.000
plans
Token plans
Feature activation+0.000
were
Token were
Feature activation+2.566
still
Token still
Feature activation+2.984
in
Token in
Feature activation+1.031
the
Token the
Feature activation+0.110
very
Token very
Feature activation+0.000
early
Token early
Feature activation+0.000
beans
Tokenbeans
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
while
Token while
Feature activation+0.000
it
Token it
Feature activation+0.542
waits
Token waits
Feature activation+2.559
for
Token for
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
was
Token was
Feature activation+0.269
clear
Token clear
Feature activation+0.000
that
Token that
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+1.274
was
Token was
Feature activation+2.557
there
Token there
Feature activation+1.593
to
Token to
Feature activation+0.400
soak
Token soak
Feature activation+0.006
in
Token in
Feature activation+0.032
the
Token the
Feature activation+0.000
change
Token change
Feature activation+0.000
was
Token was
Feature activation+0.000
implemented
Token implemented
Feature activation+0.000
while
Token while
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
slept
Token slept
Feature activation+2.547
.
Token.
Feature activation+0.000
Like
Token Like
Feature activation+0.000
other
Token other
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
actions
Token actions
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
comment
Token comment
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.490
was
Token was
Feature activation+2.534
being
Token being
Feature activation+1.556
recorded
Token recorded
Feature activation+0.000
on
Token on
Feature activation+0.251
the
Token the
Feature activation+0.000
livestream
Token livestream
Feature activation+0.000
lost
Token lost
Feature activation+0.000
my
Token my
Feature activation+0.000
vision
Token vision
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.417
was
Token was
Feature activation+2.532
young
Token young
Feature activation+1.381
.
Token.
Feature activation+0.051
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
kind
Token kind
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
she
Token she
Feature activation+1.224
was
Token was
Feature activation+2.504
on
Token on
Feature activation+2.099
the
Token the
Feature activation+0.482
spot
Token spot
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
projects
Token projects
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
founders
Token founders
Feature activation+0.000
are
Token are
Feature activation+1.504
still
Token still
Feature activation+2.447
working
Token working
Feature activation+0.648
full
Token full
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
.
Token.
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.344
was
Token was
Feature activation+2.705
on
Token on
Feature activation+2.432
vacation
Token vacation
Feature activation+0.533
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
I
Token I
Feature activation+0.000
returned
Token returned
Feature activation+0.000
Bale
Token Bale
Feature activation+0.000
,
Token,
Feature activation+0.000
signed
Token signed
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.711
was
Token was
Feature activation+2.428
director
Token director
Feature activation+0.332
of
Token of
Feature activation+0.000
football
Token football
Feature activation+0.000
at
Token at
Feature activation+0.382
Tottenham
Token Tottenham
Feature activation+0.000
discussions
Token discussions
Feature activation+0.000
were
Token were
Feature activation+0.000
happening
Token happening
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.204
was
Token was
Feature activation+2.417
filming
Token filming
Feature activation+0.745
The
Token The
Feature activation+0.000
Rend
Token Rend
Feature activation+0.000
ezvous
Tokenezvous
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
are
Token are
Feature activation+2.398
attempting
Token attempting
Feature activation+1.334
to
Token to
Feature activation+0.261
put
Token put
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
on
Token on
Feature activation+0.000

Top DFA by src position
MAX = 3.932

it
Token it
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
or
Token or
Feature activation+0.007
Top resid features:
doing
Token doing
Feature activation+0.016
Top resid features:
it
Token it
Feature activation+0.044
Top resid features:
while
Token while
Feature activation+3.932
Top resid features:
we
Token we
Feature activation+0.250
Top resid features:
were
Token were
Feature activation+0.329
Top resid features:
still
Token still
Feature activation+0.028
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.074
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation-0.019
Top resid features:
email
Token email
Feature activation-0.001
Top resid features:
server
Token server
Feature activation-0.002
Top resid features:
while
Token while
Feature activation+3.732
Top resid features:
she
Token she
Feature activation+0.369
Top resid features:
was
Token was
Feature activation+0.217
Top resid features:
secretary
Token secretary
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
Armstrong
Token Armstrong
Feature activation-0.028
Top resid features:
told
Token told
Feature activation+0.030
Top resid features:
Sports
Token Sports
Feature activation-0.021
Top resid features:
Management
Token Management
Feature activation-0.030
Top resid features:
that
Token that
Feature activation-0.020
Top resid features:
while
Token while
Feature activation+3.920
Top resid features:
plans
Token plans
Feature activation+0.234
Top resid features:
were
Token were
Feature activation+0.299
Top resid features:
still
Token still
Feature activation+0.014
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
She
TokenShe
Feature activation+0.003
Top resid features:
also
Token also
Feature activation+0.007
Top resid features:
supported
Token supported
Feature activation+0.040
Top resid features:
her
Token her
Feature activation+0.005
Top resid features:
partner
Token partner
Feature activation+0.042
Top resid features:
while
Token while
Feature activation+3.556
Top resid features:
he
Token he
Feature activation+0.402
Top resid features:
was
Token was
Feature activation+0.207
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
jail
Token jail
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation-0.017
Top resid features:
circulated
Token circulated
Feature activation+0.060
Top resid features:
last
Token last
Feature activation+0.053
Top resid features:
week
Token week
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
while
Token while
Feature activation+3.394
Top resid features:
I
Token I
Feature activation+0.413
Top resid features:
was
Token was
Feature activation+0.153
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
vacation
Token vacation
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Senate
Token Senate
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.061
Top resid features:
I
Token I
Feature activation-0.009
Top resid features:
met
Token met
Feature activation+0.108
Top resid features:
her
Token her
Feature activation+0.043
Top resid features:
while
Token while
Feature activation+3.454
Top resid features:
I
Token I
Feature activation+0.306
Top resid features:
was
Token was
Feature activation+0.211
Top resid features:
campaigning
Token campaigning
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
or
Token or
Feature activation-0.008
Top resid features:
doing
Token doing
Feature activation+0.048
Top resid features:
it
Token it
Feature activation+0.058
Top resid features:
while
Token while
Feature activation+3.394
Top resid features:
we
Token we
Feature activation+0.455
Top resid features:
were
Token were
Feature activation+0.134
Top resid features:
still
Token still
Feature activation+0.000
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.004
Top resid features:
met
Tokenmet
Feature activation-0.014
Top resid features:
ro
Tokenro
Feature activation-0.022
Top resid features:
,"
Token,"
Feature activation+0.016
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
while
Token while
Feature activation+3.886
Top resid features:
PCs
Token PCs
Feature activation+0.152
Top resid features:
will
Token will
Feature activation+0.134
Top resid features:
still
Token still
Feature activation+0.010
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
Armstrong
Token Armstrong
Feature activation-0.026
Top resid features:
told
Token told
Feature activation+0.054
Top resid features:
Sports
Token Sports
Feature activation-0.023
Top resid features:
Management
Token Management
Feature activation-0.035
Top resid features:
that
Token that
Feature activation-0.040
Top resid features:
while
Token while
Feature activation+3.491
Top resid features:
plans
Token plans
Feature activation+0.356
Top resid features:
were
Token were
Feature activation+0.163
Top resid features:
still
Token still
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
soy
Token soy
Feature activation-0.017
Top resid features:
beans
Tokenbeans
Feature activation-0.051
Top resid features:
next
Token next
Feature activation+0.067
Top resid features:
year
Token year
Feature activation+0.063
Top resid features:
while
Token while
Feature activation+3.488
Top resid features:
it
Token it
Feature activation+0.352
Top resid features:
waits
Token waits
Feature activation+0.055
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
China
Token China
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
although
Token although
Feature activation+0.039
Top resid features:
it
Token it
Feature activation+0.033
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
clear
Token clear
Feature activation-0.006
Top resid features:
that
Token that
Feature activation-0.008
Top resid features:
while
Token while
Feature activation+3.178
Top resid features:
he
Token he
Feature activation+0.434
Top resid features:
was
Token was
Feature activation+0.252
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
soak
Token soak
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.008
Top resid features:
radical
Token radical
Feature activation+0.004
Top resid features:
change
Token change
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+0.089
Top resid features:
implemented
Token implemented
Feature activation-0.013
Top resid features:
while
Token while
Feature activation+3.368
Top resid features:
Congress
Token Congress
Feature activation+0.265
Top resid features:
slept
Token slept
Feature activation+0.186
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Like
Token Like
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
abb
Tokenabb
Feature activation-0.026
Top resid features:
ie
Tokenie
Feature activation-0.016
Top resid features:
made
Token made
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
comment
Token comment
Feature activation+0.146
Top resid features:
while
Token while
Feature activation+3.192
Top resid features:
he
Token he
Feature activation+0.361
Top resid features:
was
Token was
Feature activation+0.203
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
recorded
Token recorded
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.057
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
lost
Token lost
Feature activation+0.100
Top resid features:
my
Token my
Feature activation+0.005
Top resid features:
vision
Token vision
Feature activation+0.035
Top resid features:
while
Token while
Feature activation+3.302
Top resid features:
I
Token I
Feature activation+0.344
Top resid features:
was
Token was
Feature activation+0.183
Top resid features:
young
Token young
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:
by
Token by
Feature activation+0.031
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
fact
Token fact
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
while
Token while
Feature activation+3.194
Top resid features:
she
Token she
Feature activation+0.377
Top resid features:
was
Token was
Feature activation+0.205
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
spot
Token spot
Feature activation+0.000
Top resid features:
part
Token part
Feature activation+0.003
Top resid features:
-
Token-
Feature activation-0.014
Top resid features:
time
Tokentime
Feature activation-0.011
Top resid features:
weekend
Token weekend
Feature activation+0.002
Top resid features:
projects
Token projects
Feature activation-0.021
Top resid features:
while
Token while
Feature activation+3.548
Top resid features:
the
Token the
Feature activation+0.101
Top resid features:
founders
Token founders
Feature activation+0.050
Top resid features:
are
Token are
Feature activation+0.160
Top resid features:
still
Token still
Feature activation+0.042
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation-0.009
Top resid features:
circulated
Token circulated
Feature activation+0.078
Top resid features:
last
Token last
Feature activation+0.026
Top resid features:
week
Token week
Feature activation+0.017
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
while
Token while
Feature activation+3.060
Top resid features:
I
Token I
Feature activation+0.240
Top resid features:
was
Token was
Feature activation+0.344
Top resid features:
on
Token on
Feature activation+0.118
Top resid features:
vacation
Token vacation
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
Gareth
Token Gareth
Feature activation-0.041
Top resid features:
Bale
Token Bale
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
signed
Token signed
Feature activation+0.160
Top resid features:
while
Token while
Feature activation+3.168
Top resid features:
he
Token he
Feature activation+0.357
Top resid features:
was
Token was
Feature activation+0.181
Top resid features:
director
Token director
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
football
Token football
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
discussions
Token discussions
Feature activation+0.014
Top resid features:
were
Token were
Feature activation+0.042
Top resid features:
happening
Token happening
Feature activation+0.111
Top resid features:
while
Token while
Feature activation+3.110
Top resid features:
I
Token I
Feature activation+0.298
Top resid features:
was
Token was
Feature activation+0.208
Top resid features:
filming
Token filming
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Rend
Token Rend
Feature activation+0.000
Top resid features:
facing
Token facing
Feature activation+0.025
Top resid features:
them
Token them
Feature activation-0.001
Top resid features:
on
Token on
Feature activation+0.054
Top resid features:
Thursday
Token Thursday
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
while
Token while
Feature activation+3.182
Top resid features:
Labour
Token Labour
Feature activation+0.471
Top resid features:
are
Token are
Feature activation+0.131
Top resid features:
attempting
Token attempting
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.05

Head 3: 0.45

Head 4: 0.06

Head 5: 0.08

Head 6: 0.07

Head 7: 0.03

Head 8: 0.07

Head 9: 0.04

Head 10: 0.06

Head 11: 0.03

Positive logits

hyde1.53

phthal1.45

azeera1.37

ength1.35

berra1.35

uberty1.34

assic1.28

ensibly1.28

rir1.27

filming1.24

una1.24

leaf1.23

icult1.23

arella1.22

rehend1.20

uble1.20

owered1.19

unin1.19

ripe1.18

Bay1.18

Negative logits

Shap-1.47

PLUS-1.39

NG-1.37

pts-1.36

Laurent-1.33

Recommend-1.23

Blueprint-1.22

Lak-1.22

SOS-1.21

Weeks-1.20

Wis-1.19

++++++++-1.19

Indra-1.18

LESS-1.17

Yao-1.17

Rout-1.16

Loren-1.16

Demons-1.15

Sem-1.14

Christy-1.14

INTERVAL 2.828 - 3.142
CONTAINS 0.000%

supported
Token supported
Feature activation+0.000
her
Token her
Feature activation+0.000
partner
Token partner
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.929
was
Token was
Feature activation+2.927
in
Token in
Feature activation+1.863
jail
Token jail
Feature activation+1.262
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
sent
Token sent
Feature activation+0.000
s
Tokens
Feature activation+0.000
email
Token email
Feature activation+0.000
server
Token server
Feature activation+0.000
while
Token while
Feature activation+0.000
she
Token she
Feature activation+1.499
was
Token was
Feature activation+3.018
secretary
Token secretary
Feature activation+1.439
of
Token of
Feature activation+0.008
state
Token state
Feature activation+0.150
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Management
Token Management
Feature activation+0.000
that
Token that
Feature activation+0.000
while
Token while
Feature activation+0.000
plans
Token plans
Feature activation+0.000
were
Token were
Feature activation+2.566
still
Token still
Feature activation+2.984
in
Token in
Feature activation+1.031
the
Token the
Feature activation+0.110
very
Token very
Feature activation+0.000
early
Token early
Feature activation+0.000
stages
Token stages
Feature activation+0.000
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.896
were
Token were
Feature activation+2.683
still
Token still
Feature activation+3.142
together
Token together
Feature activation+0.612
and
Token and
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
her
Token her
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.514 - 2.828
CONTAINS 0.001%

change
Token change
Feature activation+0.000
was
Token was
Feature activation+0.000
implemented
Token implemented
Feature activation+0.000
while
Token while
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
slept
Token slept
Feature activation+2.547
.
Token.
Feature activation+0.000
Like
Token Like
Feature activation+0.000
other
Token other
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
actions
Token actions
Feature activation+0.000
beans
Tokenbeans
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
while
Token while
Feature activation+0.000
it
Token it
Feature activation+0.542
waits
Token waits
Feature activation+2.559
for
Token for
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
I
Token I
Feature activation+0.000
met
Token met
Feature activation+0.000
her
Token her
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.231
was
Token was
Feature activation+2.692
campaigning
Token campaigning
Feature activation+2.262
for
Token for
Feature activation+0.000
John
Token John
Feature activation+0.000
Kerry
Token Kerry
Feature activation+0.000
.
Token.
Feature activation+0.000
,"
Token,"
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
PCs
Token PCs
Feature activation+0.324
will
Token will
Feature activation+0.533
still
Token still
Feature activation+2.642
be
Token be
Feature activation+0.621
able
Token able
Feature activation+0.822
to
Token to
Feature activation+0.000
run
Token run
Feature activation+0.000
"
Token "
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
comment
Token comment
Feature activation+0.000
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.490
was
Token was
Feature activation+2.534
being
Token being
Feature activation+1.556
recorded
Token recorded
Feature activation+0.000
on
Token on
Feature activation+0.251
the
Token the
Feature activation+0.000
livestream
Token livestream
Feature activation+0.000

INTERVAL 2.200 - 2.514
CONTAINS 0.001%

here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
while
Token while
Feature activation+0.000
you
Token you
Feature activation+0.871
're
Token're
Feature activation+2.254
on
Token on
Feature activation+1.907
this
Token this
Feature activation+0.424
side
Token side
Feature activation+0.000
of
Token of
Feature activation+0.000
town
Token town
Feature activation+0.000
discussions
Token discussions
Feature activation+0.000
were
Token were
Feature activation+0.000
happening
Token happening
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.204
was
Token was
Feature activation+2.417
filming
Token filming
Feature activation+0.745
The
Token The
Feature activation+0.000
Rend
Token Rend
Feature activation+0.000
ezvous
Tokenezvous
Feature activation+0.000
,
Token,
Feature activation+0.000
met
Token met
Feature activation+0.000
her
Token her
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.231
was
Token was
Feature activation+2.692
campaigning
Token campaigning
Feature activation+2.262
for
Token for
Feature activation+0.000
John
Token John
Feature activation+0.000
Kerry
Token Kerry
Feature activation+0.000
.
Token.
Feature activation+0.000
Always
Token Always
Feature activation+0.000
generations
Token generations
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.393
were
Token were
Feature activation+2.305
thinking
Token thinking
Feature activation+1.704
about
Token about
Feature activation+0.041
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
fill
Token fill
Feature activation+0.000
projects
Token projects
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
founders
Token founders
Feature activation+0.000
are
Token are
Feature activation+1.504
still
Token still
Feature activation+2.447
working
Token working
Feature activation+0.648
full
Token full
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.885 - 2.200
CONTAINS 0.002%

worked
Token worked
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
while
Token while
Feature activation+0.000
I
Token I
Feature activation+0.079
was
Token was
Feature activation+2.080
there
Token there
Feature activation+1.388
,
Token,
Feature activation+0.586
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
distracting
Token distracting
Feature activation+0.000
even
Token even
Feature activation+0.000
while
Token while
Feature activation+0.000
standing
Token standing
Feature activation+0.358
perfectly
Token perfectly
Feature activation+0.085
still
Token still
Feature activation+1.895
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
a
Token a
Feature activation+0.000
something
Token something
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
animation
Token animation
Feature activation+0.000
is
Token is
Feature activation+1.187
still
Token still
Feature activation+2.041
doing
Token doing
Feature activation+0.000
its
Token its
Feature activation+0.000
thing
Token thing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
button
Token button
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
it
Token it
Feature activation+0.730
's
Token's
Feature activation+2.083
on
Token on
Feature activation+1.647
the
Token the
Feature activation+0.079
back
Token back
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
their
Token their
Feature activation+0.000
families
Token families
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
was
Token was
Feature activation+2.157
at
Token at
Feature activation+1.494
war
Token war
Feature activation+0.215
.
Token.
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.571 - 1.885
CONTAINS 0.003%

should
Token should
Feature activation+0.000
enjoy
Token enjoy
Feature activation+0.000
it
Token it
Feature activation+0.000
while
Token while
Feature activation+0.000
they
Token they
Feature activation+1.332
can
Token can
Feature activation+1.597
for
Token for
Feature activation+0.319
the
Token the
Feature activation+0.000
World
Token World
Feature activation+0.000
Cups
Token Cups
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
art
Token art
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
also
Token also
Feature activation+1.602
pulling
Token pulling
Feature activation+0.066
on
Token on
Feature activation+1.157
Japanese
Token Japanese
Feature activation+0.000
influences
Token influences
Feature activation+0.000
,
Token,
Feature activation+0.029
mix
Token mix
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
food
Token food
Feature activation+0.000
whilst
Token whilst
Feature activation+0.000
still
Token still
Feature activation+1.630
in
Token in
Feature activation+0.812
your
Token your
Feature activation+0.247
mouth
Token mouth
Feature activation+0.000
,
Token,
Feature activation+0.367
particularly
Token particularly
Feature activation+0.000
N
Token N
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ut
Tokenut
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
waiting
Token waiting
Feature activation+1.853
for
Token for
Feature activation+0.146
his
Token his
Feature activation+0.000
plane
Token plane
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.393
were
Token were
Feature activation+2.305
thinking
Token thinking
Feature activation+1.704
about
Token about
Feature activation+0.041
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
fill
Token fill
Feature activation+0.000
those
Token those
Feature activation+0.000

INTERVAL 1.257 - 1.571
CONTAINS 0.005%

star
Token star
Feature activation+0.000
goalkeeper
Token goalkeeper
Feature activation+0.000
Manuel
Token Manuel
Feature activation+0.000
Ne
Token Ne
Feature activation+0.000
uer
Tokenuer
Feature activation+0.000
is
Token is
Feature activation+1.427
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
action
Token action
Feature activation+0.000
until
Token until
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
in
Token in
Feature activation+0.000
detention
Token detention
Feature activation+0.000
while
Token while
Feature activation+0.000
awaiting
Token awaiting
Feature activation+1.334
completion
Token completion
Feature activation+0.000
of
Token of
Feature activation+0.000
deportation
Token deportation
Feature activation+0.000
proceedings
Token proceedings
Feature activation+0.000
have
Token have
Feature activation+0.000
profit
Token profit
Feature activation+0.000
while
Token while
Feature activation+0.000
British
Token British
Feature activation+0.000
Columb
Token Columb
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
are
Token are
Feature activation+1.376
asked
Token asked
Feature activation+0.526
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
water
Token water
Feature activation+0.000
our
Token our
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
are
Token are
Feature activation+2.398
attempting
Token attempting
Feature activation+1.334
to
Token to
Feature activation+0.261
put
Token put
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
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
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
was
Token was
Feature activation+1.317
immensely
Token immensely
Feature activation+0.126
rich
Token rich
Feature activation+0.000
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
given
Token given
Feature activation+0.000

INTERVAL 0.943 - 1.257
CONTAINS 0.010%

by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
bus
Token bus
Feature activation+0.000
while
Token while
Feature activation+0.000
still
Token still
Feature activation+1.878
on
Token on
Feature activation+1.170
the
Token the
Feature activation+0.264
ground
Token ground
Feature activation+0.076
.
Token.
Feature activation+0.000
Related
Token Related
Feature activation+0.000
Articles
Token Articles
Feature activation+0.000
imagery
Token imagery
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+0.000
Sic
Token Sic
Feature activation+0.000
ario
Tokenario
Feature activation+0.000
is
Token is
Feature activation+1.006
an
Token an
Feature activation+0.000
action
Token action
Feature activation+0.000
thriller
Token thriller
Feature activation+0.000
.
Token.
Feature activation+0.000
Whether
Token Whether
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
she
Token she
Feature activation+1.224
was
Token was
Feature activation+2.504
on
Token on
Feature activation+2.099
the
Token the
Feature activation+0.482
spot
Token spot
Feature activation+0.000
with
Token with
Feature activation+0.000
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
while
Token while
Feature activation+0.000
we
Token we
Feature activation+0.635
in
Token in
Feature activation+1.242
other
Token other
Feature activation+0.000
parts
Token parts
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
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
conviction
Token conviction
Feature activation+0.000
while
Token while
Feature activation+0.000
also
Token also
Feature activation+1.094
feeling
Token feeling
Feature activation+0.000
like
Token like
Feature activation+0.038
a
Token a
Feature activation+0.000
race
Token race
Feature activation+0.000
traitor
Token traitor
Feature activation+0.000

INTERVAL 0.628 - 0.943
CONTAINS 0.016%

a
Token a
Feature activation+0.000
win
Token win
Feature activation+0.000
over
Token over
Feature activation+0.000
Denver
Token Denver
Feature activation+0.000
while
Token while
Feature activation+0.000
also
Token also
Feature activation+0.752
recording
Token recording
Feature activation+0.000
a
Token a
Feature activation+0.000
sack
Token sack
Feature activation+0.000
and
Token and
Feature activation+0.000
forced
Token forced
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.000
are
Token are
Feature activation+1.219
questioning
Token questioning
Feature activation+0.825
how
Token how
Feature activation+0.350
the
Token the
Feature activation+0.000
model
Token model
Feature activation+0.000
where
Token where
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Big
Token Big
Feature activation+0.000
Oil
Token Oil
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
demanding
Token demanding
Feature activation+0.249
that
Token that
Feature activation+0.935
programs
Token programs
Feature activation+0.000
to
Token to
Feature activation+0.000
aid
Token aid
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
will
Token will
Feature activation+0.607
mostly
Token mostly
Feature activation+0.633
be
Token be
Feature activation+0.333
on
Token on
Feature activation+0.684
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
fire
Token fire
Feature activation+0.000
me
Token me
Feature activation+0.000
while
Token while
Feature activation+0.000
wearing
Token wearing
Feature activation+0.663
only
Token only
Feature activation+0.000
her
Token her
Feature activation+0.000
linger
Token linger
Feature activation+0.186
ie
Tokenie
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.314 - 0.628
CONTAINS 0.026%

dispatched
Token dispatched
Feature activation+0.000
while
Token while
Feature activation+0.000
doing
Token doing
Feature activation+0.527
a
Token a
Feature activation+0.584
dance
Token dance
Feature activation+0.462
trying
Token trying
Feature activation+0.328
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
certain
Token certain
Feature activation+0.000
,
Token,
Feature activation+0.000
shall
Token shall
Feature activation+0.000
defender
Token defender
Feature activation+0.000
Chris
Token Chris
Feature activation+0.000
Sam
Token Sam
Feature activation+0.000
ba
Tokenba
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.503
been
Token been
Feature activation+0.000
training
Token training
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
squad
Token squad
Feature activation+0.000
lawmaker
Token lawmaker
Feature activation+0.000
was
Token was
Feature activation+0.000
filmed
Token filmed
Feature activation+0.000
saying
Token saying
Feature activation+0.000
while
Token while
Feature activation+0.000
advocating
Token advocating
Feature activation+0.355
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
bill
Token bill
Feature activation+0.000
at
Token at
Feature activation+0.164
the
Token the
Feature activation+0.000
days
Token days
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
Irish
Token Irish
Feature activation+0.000
were
Token were
Feature activation+1.685
the
Token the
Feature activation+0.467
ultimate
Token ultimate
Feature activation+0.000
am
Token am
Feature activation+0.000
ateurs
Tokenateurs
Feature activation+0.000
-
Token -
Feature activation+0.000
with
Token with
Feature activation+0.000
politician
Token politician
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
dispatched
Token dispatched
Feature activation+0.000
while
Token while
Feature activation+0.000
doing
Token doing
Feature activation+0.527
a
Token a
Feature activation+0.584
dance
Token dance
Feature activation+0.462
trying
Token trying
Feature activation+0.328
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000

INTERVAL 0.000 - 0.314
CONTAINS 99.935%

ric
Tokenric
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.000
$
Token $
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
99
Token99
Feature activation+0.000
USD
Token USD
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Star
Token Star
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
careful
Token careful
Feature activation+0.000
about
Token about
Feature activation+0.000
contamination
Token contamination
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
if
Token if
Feature activation+0.000
I
Token I
Feature activation+0.000
read
Token read
Feature activation+0.000
one
Token one
Feature activation+0.000
more
Token more
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
hex
Tokenhex
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
website
Token website
Feature activation+0.000
had
Token had
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
signatures
Token signatures
Feature activation+0.000
.
Token.
Feature activation+0.000
or
Token or
Feature activation+0.000
heroic
Token heroic
Feature activation+0.000
survivor
Token survivor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
one
Token one
Feature activation+0.000
minute
Token minute
Feature activation+0.000
past
Token past
Feature activation+0.000
midnight
Token midnight
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H2.3: (feature 7443)

TOP ACTIVATIONS
MAX = 3.110

the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
step
Token step
Feature activation+0.000
after
Token after
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
has
Token has
Feature activation+3.110
signed
Token signed
Feature activation+1.028
a
Token a
Feature activation+0.000
defence
Token defence
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
Lieutenant
Token Lieutenant
Feature activation+0.000
Had
Token Had
Feature activation+1.643
ar
Tokenar
Feature activation+0.208
Gold
Token Gold
Feature activation+0.508
in
Tokenin
Feature activation+0.000
was
Token was
Feature activation+3.094
captured
Token captured
Feature activation+0.974
,
Token,
Feature activation+0.218
Israeli
Token Israeli
Feature activation+0.000
forces
Token forces
Feature activation+0.000
appear
Token appear
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.031
has
Token has
Feature activation+3.071
been
Token been
Feature activation+2.157
sprayed
Token sprayed
Feature activation+0.939
,
Token,
Feature activation+0.221
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
Red
Token Red
Feature activation+1.070
kn
Tokenkn
Feature activation+0.000
app
Tokenapp
Feature activation+0.000
had
Token had
Feature activation+2.958
asked
Token asked
Feature activation+0.466
for
Token for
Feature activation+0.000
£
Token £
Feature activation+0.000
100
Token100
Feature activation+0.000
,
Token,
Feature activation+0.000
beans
Token beans
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
this
Token this
Feature activation+0.057
is
Token is
Feature activation+2.414
done
Token done
Feature activation+2.937
,
Token,
Feature activation+1.009
the
Token the
Feature activation+0.000
villagers
Token villagers
Feature activation+0.000
have
Token have
Feature activation+0.728
no
Token no
Feature activation+0.000
reported
Token reported
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token ,
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.965
had
Token had
Feature activation+2.932
his
Token his
Feature activation+0.826
class
Token class
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
clip
Token clip
Feature activation+0.000
sol
Token sol
Feature activation+0.000
ids
Tokenids
Feature activation+0.000
after
Token after
Feature activation+0.000
cotton
Token cotton
Feature activation+0.245
seeds
Token seeds
Feature activation+0.836
have
Token have
Feature activation+2.929
been
Token been
Feature activation+2.411
pressed
Token pressed
Feature activation+1.690
for
Token for
Feature activation+0.000
oil
Token oil
Feature activation+0.000
act
Token act
Feature activation+0.000
After
Token After
Feature activation+0.000
sufficient
Token sufficient
Feature activation+0.000
F
Token F
Feature activation+0.000
BR
TokenBR
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
has
Token has
Feature activation+2.905
been
Token been
Feature activation+2.244
built
Token built
Feature activation+0.709
up
Token up
Feature activation+0.000
via
Token via
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
Oxy
Token Oxy
Feature activation+0.000
contin
Tokencontin
Feature activation+0.000
was
Token was
Feature activation+2.859
de
Token de
Feature activation+0.154
-
Token-
Feature activation+0.000
listed
Tokenlisted
Feature activation+0.063
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
premise
Token premise
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
dispensary
Token dispensary
Feature activation+0.000
has
Token has
Feature activation+2.830
paid
Token paid
Feature activation+0.482
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.000
145
Token145
Feature activation+0.000
China
Token China
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
all
Token all
Feature activation+0.673
,
Token,
Feature activation+0.608
has
Token has
Feature activation+2.810
an
Token an
Feature activation+0.531
iron
Token iron
Feature activation+0.000
-
Token-
Feature activation+0.000
like
Tokenlike
Feature activation+0.000
grip
Token grip
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.598
was
Token was
Feature activation+2.740
published
Token published
Feature activation+2.142
.
Token.
Feature activation+0.406
But
Token But
Feature activation+0.000
its
Token its
Feature activation+0.000
very
Token very
Feature activation+0.000
you
Token you
Feature activation+0.000
start
Token start
Feature activation+0.000
Firefox
Token Firefox
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.659
has
Token has
Feature activation+2.709
downloaded
Token downloaded
Feature activation+0.900
an
Token an
Feature activation+0.000
update
Token update
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.618
tests
Token tests
Feature activation+0.000
were
Token were
Feature activation+2.559
completed
Token completed
Feature activation+2.708
,
Token,
Feature activation+0.865
AT
Token AT
Feature activation+0.000
&
Token&
Feature activation+0.000
T
TokenT
Feature activation+0.000
decided
Token decided
Feature activation+0.000
in
Token in
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
after
Token after
Feature activation+0.000
W
Token W
Feature activation+0.174
had
Token had
Feature activation+2.641
led
Token led
Feature activation+0.136
America
Token America
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Hurricane
Token Hurricane
Feature activation+0.000
her
Token her
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
well
Token well
Feature activation+0.000
after
Token after
Feature activation+0.000
school
Token school
Feature activation+0.055
had
Token had
Feature activation+2.603
let
Token let
Feature activation+1.189
out
Token out
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
day
Token day
Feature activation+0.000
the
Token the
Feature activation+0.358
appropriate
Token appropriate
Feature activation+0.000
"
Token "
Feature activation+0.415
duration
Tokenduration
Feature activation+0.000
"
Token"
Feature activation+0.000
has
Token has
Feature activation+2.599
expired
Token expired
Feature activation+0.571
,
Token,
Feature activation+0.124
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
betting
Token betting
Feature activation+0.000
note
Token note
Feature activation+0.000
:
Token:
Feature activation+0.000
After
Token After
Feature activation+0.086
this
Token this
Feature activation+0.244
interview
Token interview
Feature activation+0.000
was
Token was
Feature activation+2.571
conducted
Token conducted
Feature activation+1.881
,
Token,
Feature activation+0.961
Az
Token Az
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
wrote
Token wrote
Feature activation+0.208
Unfortunately
Token Unfortunately
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.618
tests
Token tests
Feature activation+0.000
were
Token were
Feature activation+2.559
completed
Token completed
Feature activation+2.708
,
Token,
Feature activation+0.865
AT
Token AT
Feature activation+0.000
&
Token&
Feature activation+0.000
T
TokenT
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Long
Token Long
Feature activation+0.000
after
Token after
Feature activation+0.000
his
Token his
Feature activation+0.000
teammates
Token teammates
Feature activation+0.000
have
Token have
Feature activation+2.552
finished
Token finished
Feature activation+1.385
answering
Token answering
Feature activation+0.000
trade
Token trade
Feature activation+0.000
-
Token-
Feature activation+0.000
related
Tokenrelated
Feature activation+0.000

Top DFA by src position
MAX = 3.783

and
Token and
Feature activation+0.088
Top resid features:
traditionally
Token traditionally
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
next
Token next
Feature activation+0.010
Top resid features:
step
Token step
Feature activation-0.024
Top resid features:
after
Token after
Feature activation+3.734
Top resid features:
Canada
Token Canada
Feature activation-0.001
Top resid features:
has
Token has
Feature activation+0.070
Top resid features:
signed
Token signed
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
ľ
Tokenľ
Feature activation+0.021
Top resid features:
After
TokenAfter
Feature activation+3.553
Top resid features:
Lieutenant
Token Lieutenant
Feature activation+0.013
Top resid features:
Had
Token Had
Feature activation+0.023
Top resid features:
ar
Tokenar
Feature activation-0.001
Top resid features:
Gold
Token Gold
Feature activation+0.020
Top resid features:
in
Tokenin
Feature activation+0.021
Top resid features:
water
Token water
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.099
Top resid features:
in
Token in
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
air
Token air
Feature activation-0.079
Top resid features:
after
Token after
Feature activation+3.655
Top resid features:
it
Token it
Feature activation+0.226
Top resid features:
has
Token has
Feature activation+0.018
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
sprayed
Token sprayed
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
November
Token November
Feature activation+0.002
Top resid features:
2007
Token 2007
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.080
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
After
TokenAfter
Feature activation+3.546
Top resid features:
Red
Token Red
Feature activation-0.040
Top resid features:
kn
Tokenkn
Feature activation+0.020
Top resid features:
app
Tokenapp
Feature activation-0.001
Top resid features:
had
Token had
Feature activation+0.128
Top resid features:
asked
Token asked
Feature activation+0.000
Top resid features:
whom
Token whom
Feature activation+0.018
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
100
Token 100
Feature activation-0.017
Top resid features:
beans
Token beans
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
After
Token After
Feature activation+3.732
Top resid features:
this
Token this
Feature activation-0.090
Top resid features:
is
Token is
Feature activation+0.314
Top resid features:
done
Token done
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
York
Token York
Feature activation-0.014
Top resid features:
Post
Token Post
Feature activation-0.005
Top resid features:
reported
Token reported
Feature activation+0.029
Top resid features:
Friday
Token Friday
Feature activation-0.069
Top resid features:
,
Token ,
Feature activation+0.114
Top resid features:
after
Token after
Feature activation+3.757
Top resid features:
he
Token he
Feature activation+0.121
Top resid features:
had
Token had
Feature activation+0.081
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
class
Token class
Feature activation+0.000
Top resid features:
watch
Token watch
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
remaining
Token remaining
Feature activation+0.013
Top resid features:
sol
Token sol
Feature activation+0.004
Top resid features:
ids
Tokenids
Feature activation-0.005
Top resid features:
after
Token after
Feature activation+3.783
Top resid features:
cotton
Token cotton
Feature activation-0.039
Top resid features:
seeds
Token seeds
Feature activation-0.065
Top resid features:
have
Token have
Feature activation+0.096
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
pressed
Token pressed
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.010
Top resid features:
stage
Token stage
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.034
Top resid features:
fuel
Token fuel
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.122
Top resid features:
After
Token After
Feature activation+3.636
Top resid features:
sufficient
Token sufficient
Feature activation+0.068
Top resid features:
F
Token F
Feature activation+0.027
Top resid features:
BR
TokenBR
Feature activation-0.011
Top resid features:
capacity
Token capacity
Feature activation-0.167
Top resid features:
has
Token has
Feature activation+0.093
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.146
Top resid features:
.
Token.
Feature activation+0.092
Top resid features:
After
Token After
Feature activation+3.576
Top resid features:
Oxy
Token Oxy
Feature activation+0.076
Top resid features:
contin
Tokencontin
Feature activation-0.082
Top resid features:
was
Token was
Feature activation+0.245
Top resid features:
de
Token de
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
refusal
Token refusal
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.024
Top resid features:
lease
Token lease
Feature activation-0.038
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
premise
Token premise
Feature activation-0.044
Top resid features:
after
Token after
Feature activation+3.697
Top resid features:
the
Token the
Feature activation+0.158
Top resid features:
dispensary
Token dispensary
Feature activation-0.112
Top resid features:
has
Token has
Feature activation+0.092
Top resid features:
paid
Token paid
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.011
Top resid features:
so
Token so
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.063
Top resid features:
China
Token China
Feature activation-0.083
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
after
Token after
Feature activation+3.779
Top resid features:
all
Token all
Feature activation-0.285
Top resid features:
,
Token,
Feature activation+0.210
Top resid features:
has
Token has
Feature activation+0.043
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
iron
Token iron
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.030
Top resid features:
such
Token such
Feature activation-0.005
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.049
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
year
Token year
Feature activation-0.096
Top resid features:
after
Token after
Feature activation+3.365
Top resid features:
it
Token it
Feature activation+0.243
Top resid features:
was
Token was
Feature activation+0.080
Top resid features:
published
Token published
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:
appears
Token appears
Feature activation+0.003
Top resid features:
when
Token when
Feature activation+0.069
Top resid features:
you
Token you
Feature activation+0.051
Top resid features:
start
Token start
Feature activation+0.041
Top resid features:
Firefox
Token Firefox
Feature activation+0.015
Top resid features:
after
Token after
Feature activation+3.302
Top resid features:
it
Token it
Feature activation+0.192
Top resid features:
has
Token has
Feature activation+0.022
Top resid features:
downloaded
Token downloaded
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
update
Token update
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation-0.018
Top resid features:
cities
Token cities
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
Unfortunately
Token Unfortunately
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.092
Top resid features:
after
Token after
Feature activation+3.482
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
tests
Token tests
Feature activation-0.226
Top resid features:
were
Token were
Feature activation+0.270
Top resid features:
completed
Token completed
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Bush
Token Bush
Feature activation+0.008
Top resid features:
in
Token in
Feature activation+0.041
Top resid features:
2008
Token 2008
Feature activation-0.047
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.110
Top resid features:
after
Token after
Feature activation+3.340
Top resid features:
W
Token W
Feature activation+0.077
Top resid features:
had
Token had
Feature activation+0.047
Top resid features:
led
Token led
Feature activation+0.000
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
pick
Token pick
Feature activation+0.024
Top resid features:
up
Token up
Feature activation+0.029
Top resid features:
her
Token her
Feature activation-0.011
Top resid features:
daughter
Token daughter
Feature activation-0.019
Top resid features:
well
Token well
Feature activation+0.068
Top resid features:
after
Token after
Feature activation+3.238
Top resid features:
school
Token school
Feature activation+0.066
Top resid features:
had
Token had
Feature activation+0.130
Top resid features:
let
Token let
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Xbox
Token Xbox
Feature activation-0.000
Top resid features:
One
Token One
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.098
Top resid features:
After
Token After
Feature activation+3.174
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
appropriate
Token appropriate
Feature activation+0.076
Top resid features:
"
Token "
Feature activation+0.117
Top resid features:
duration
Tokenduration
Feature activation-0.093
Top resid features:
"
Token"
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
note
Token note
Feature activation-0.000
Top resid features:
:
Token:
Feature activation+0.052
Top resid features:
After
Token After
Feature activation+3.136
Top resid features:
this
Token this
Feature activation+0.130
Top resid features:
interview
Token interview
Feature activation-0.053
Top resid features:
was
Token was
Feature activation+0.151
Top resid features:
conducted
Token conducted
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation-0.029
Top resid features:
cities
Token cities
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Unfortunately
Token Unfortunately
Feature activation+0.082
Top resid features:
,
Token,
Feature activation+0.094
Top resid features:
after
Token after
Feature activation+3.353
Top resid features:
the
Token the
Feature activation+0.120
Top resid features:
tests
Token tests
Feature activation-0.144
Top resid features:
were
Token were
Feature activation+0.142
Top resid features:
completed
Token completed
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
TOR
TokenTOR
Feature activation+0.001
Top resid features:
ON
TokenON
Feature activation+0.003
Top resid features:
TO
TokenTO
Feature activation+0.002
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.128
Top resid features:
Long
Token Long
Feature activation-0.009
Top resid features:
after
Token after
Feature activation+3.269
Top resid features:
his
Token his
Feature activation+0.037
Top resid features:
teammates
Token teammates
Feature activation-0.055
Top resid features:
have
Token have
Feature activation+0.043
Top resid features:
finished
Token finished
Feature activation+0.000
Top resid features:
answering
Token answering
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.02

Head 2: 0.04

Head 3: 0.44

Head 4: 0.03

Head 5: 0.06

Head 6: 0.07

Head 7: 0.02

Head 8: 0.08

Head 9: 0.04

Head 10: 0.06

Head 11: 0.02

Positive logits

haul1.46

ournal1.34

uberty1.32

rosis1.31

disband1.28

Completed1.27

recess1.26

icult1.26

akia1.24

iversary1.24

alyses1.24

ascript1.24

ushima1.24

ourning1.24

agate1.24

aundering1.22

iltration1.22

untu1.21

pection1.21

disbanded1.20

Negative logits

WER-1.41

Cosponsors-1.38

":"/-1.29

Ng-1.25

Neh-1.21

-1.20

IVERS-1.19

★★-1.18

envy-1.17

Yad-1.17

Gems-1.15

OND-1.15

enthusi-1.14

Hend-1.13

soever-1.13

pts-1.13

Guerrero-1.12

YPG-1.11

Sor-1.11

highlights-1.10

INTERVAL 2.799 - 3.110
CONTAINS 0.001%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.031
has
Token has
Feature activation+3.071
been
Token been
Feature activation+2.157
sprayed
Token sprayed
Feature activation+0.939
,
Token,
Feature activation+0.221
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
reported
Token reported
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token ,
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.965
had
Token had
Feature activation+2.932
his
Token his
Feature activation+0.826
class
Token class
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
clip
Token clip
Feature activation+0.000
After
Token After
Feature activation+0.000
sufficient
Token sufficient
Feature activation+0.000
F
Token F
Feature activation+0.000
BR
TokenBR
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
has
Token has
Feature activation+2.905
been
Token been
Feature activation+2.244
built
Token built
Feature activation+0.709
up
Token up
Feature activation+0.000
via
Token via
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
premise
Token premise
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
dispensary
Token dispensary
Feature activation+0.000
has
Token has
Feature activation+2.830
paid
Token paid
Feature activation+0.482
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.000
145
Token145
Feature activation+0.000
China
Token China
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
all
Token all
Feature activation+0.673
,
Token,
Feature activation+0.608
has
Token has
Feature activation+2.810
an
Token an
Feature activation+0.531
iron
Token iron
Feature activation+0.000
-
Token-
Feature activation+0.000
like
Tokenlike
Feature activation+0.000
grip
Token grip
Feature activation+0.000

INTERVAL 2.488 - 2.799
CONTAINS 0.001%

wall
Token wall
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
De
Token De
Feature activation+0.379
bo
Tokenbo
Feature activation+0.000
was
Token was
Feature activation+2.539
hit
Token hit
Feature activation+1.288
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
the
Token the
Feature activation+0.358
appropriate
Token appropriate
Feature activation+0.000
"
Token "
Feature activation+0.415
duration
Tokenduration
Feature activation+0.000
"
Token"
Feature activation+0.000
has
Token has
Feature activation+2.599
expired
Token expired
Feature activation+0.571
,
Token,
Feature activation+0.124
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
betting
Token betting
Feature activation+0.000
you
Token you
Feature activation+0.000
start
Token start
Feature activation+0.000
Firefox
Token Firefox
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.659
has
Token has
Feature activation+2.709
downloaded
Token downloaded
Feature activation+0.900
an
Token an
Feature activation+0.000
update
Token update
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.598
was
Token was
Feature activation+2.740
published
Token published
Feature activation+2.142
.
Token.
Feature activation+0.406
But
Token But
Feature activation+0.000
its
Token its
Feature activation+0.000
very
Token very
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Long
Token Long
Feature activation+0.000
after
Token after
Feature activation+0.000
his
Token his
Feature activation+0.000
teammates
Token teammates
Feature activation+0.000
have
Token have
Feature activation+2.552
finished
Token finished
Feature activation+1.385
answering
Token answering
Feature activation+0.000
trade
Token trade
Feature activation+0.000
-
Token-
Feature activation+0.000
related
Tokenrelated
Feature activation+0.000

INTERVAL 2.177 - 2.488
CONTAINS 0.003%

onda
Tokenonda
Feature activation+0.000
soon
Token soon
Feature activation+0.000
after
Token after
Feature activation+0.000
I
Token I
Feature activation+0.608
was
Token was
Feature activation+2.237
released
Token released
Feature activation+2.284
.
Token.
Feature activation+0.188
I
Token I
Feature activation+0.000
asked
Token asked
Feature activation+0.000
her
Token her
Feature activation+0.000
if
Token if
Feature activation+0.000
hit
Token hit
Feature activation+0.000
back
Token back
Feature activation+0.000
today
Token today
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.130
was
Token was
Feature activation+2.197
accused
Token accused
Feature activation+0.519
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
leading
Token leading
Feature activation+0.000
left
Token left
Feature activation+0.000
:
Token:
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+0.000
manifesto
Token manifesto
Feature activation+0.000
was
Token was
Feature activation+2.367
released
Token released
Feature activation+1.167
we
Token we
Feature activation+0.000
received
Token received
Feature activation+0.101
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
from
Token from
Feature activation+0.000
Weiner
Token Weiner
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.015
he
Token he
Feature activation+0.954
was
Token was
Feature activation+2.418
caught
Token caught
Feature activation+2.129
sending
Token sending
Feature activation+0.352
a
Token a
Feature activation+0.000
suggestive
Token suggestive
Feature activation+0.000
photo
Token photo
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
,
Token,
Feature activation+0.000
shortly
Token shortly
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.306
was
Token was
Feature activation+2.235
signed
Token signed
Feature activation+1.140
into
Token into
Feature activation+0.000
law
Token law
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.866 - 2.177
CONTAINS 0.003%

killed
Token killed
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
after
Token after
Feature activation+0.000
they
Token they
Feature activation+0.689
were
Token were
Feature activation+1.962
thwarted
Token thwarted
Feature activation+0.465
in
Token in
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
travel
Token travel
Feature activation+0.000
:
Token:
Feature activation+0.000
After
Token After
Feature activation+0.086
this
Token this
Feature activation+0.244
interview
Token interview
Feature activation+0.000
was
Token was
Feature activation+2.571
conducted
Token conducted
Feature activation+1.881
,
Token,
Feature activation+0.961
Az
Token Az
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
wrote
Token wrote
Feature activation+0.208
an
Token an
Feature activation+0.000
evacuate
Token evacuate
Feature activation+0.000
the
Token the
Feature activation+0.000
site
Token site
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+2.016
attacked
Token attacked
Feature activation+1.073
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Analysis
TokenAnalysis
Feature activation+0.000
September
Token September
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
prominent
Token prominent
Feature activation+0.000
businessman
Token businessman
Feature activation+0.000
was
Token was
Feature activation+2.063
murdered
Token murdered
Feature activation+0.769
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lead
TokenLead
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
boom
Token boom
Feature activation+0.000
after
Token after
Feature activation+0.000
World
Token World
Feature activation+0.406
War
Token War
Feature activation+0.887
II
Token II
Feature activation+0.233
was
Token was
Feature activation+1.926
turning
Token turning
Feature activation+0.389
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
widespread
Token widespread
Feature activation+0.000
use
Token use
Feature activation+0.000

INTERVAL 1.555 - 1.866
CONTAINS 0.005%

was
Token was
Feature activation+0.000
pronounced
Token pronounced
Feature activation+0.000
dead
Token dead
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.588
was
Token was
Feature activation+1.775
found
Token found
Feature activation+1.093
hanged
Token hanged
Feature activation+0.794
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
bathroom
Token bathroom
Feature activation+0.000
After
Token After
Feature activation+0.000
you
Token you
Feature activation+0.916
âĢ
TokenâĢ
Feature activation+0.557
Ļ
TokenĻ
Feature activation+0.850
ve
Tokenve
Feature activation+0.141
gotten
Token gotten
Feature activation+1.676
those
Token those
Feature activation+0.000
first
Token first
Feature activation+0.000
bits
Token bits
Feature activation+0.000
of
Token of
Feature activation+0.000
press
Token press
Feature activation+0.000
hours
Token hours
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+0.000
,
Token,
Feature activation+0.596
was
Token was
Feature activation+1.613
dead
Token dead
Feature activation+0.692
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
help
Token help
Feature activation+0.000
that
Token that
Feature activation+0.000
after
Token after
Feature activation+0.000
lighting
Token lighting
Feature activation+0.340
,
Token,
Feature activation+0.568
were
Token were
Feature activation+1.616
thrown
Token thrown
Feature activation+1.724
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
to
Token to
Feature activation+0.000
explode
Token explode
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
the
Token the
Feature activation+0.156
war
Token war
Feature activation+0.000
ended
Token ended
Feature activation+1.675
,
Token,
Feature activation+0.631
the
Token the
Feature activation+0.000
industrial
Token industrial
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
was
Token was
Feature activation+0.397

INTERVAL 1.244 - 1.555
CONTAINS 0.007%

.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
De
Token De
Feature activation+0.379
bo
Tokenbo
Feature activation+0.000
was
Token was
Feature activation+2.539
hit
Token hit
Feature activation+1.288
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
itch
Tokenitch
Feature activation+0.000
or
Token or
Feature activation+0.000
so
Token so
Feature activation+0.000
days
Token days
Feature activation+0.000
after
Token after
Feature activation+0.000
it
Token it
Feature activation+0.637
left
Token left
Feature activation+1.414
Cape
Token Cape
Feature activation+0.000
Canaveral
Token Canaveral
Feature activation+0.000
,
Token,
Feature activation+0.193
unfortunately
Token unfortunately
Feature activation+0.000
what
Token what
Feature activation+0.000
16
Token 16
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
execution
Token execution
Feature activation+0.000
began
Token began
Feature activation+1.280
,
Token,
Feature activation+0.358
and
Token and
Feature activation+0.000
without
Token without
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
ett
Tokenett
Feature activation+0.000
Then
Token Then
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
they
Token they
Feature activation+1.434
're
Token're
Feature activation+1.717
all
Token all
Feature activation+1.481
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
words
Token words
Feature activation+0.000
,
Token,
Feature activation+0.334
ask
Token ask
Feature activation+0.000
):
Token):
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
its
Token its
Feature activation+0.104
dried
Token dried
Feature activation+1.278
,
Token,
Feature activation+0.645
its
Token its
Feature activation+0.103
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
fit
Token fit
Feature activation+0.000

INTERVAL 0.933 - 1.244
CONTAINS 0.012%

rate
Token rate
Feature activation+0.000
of
Token of
Feature activation+0.000
TB
Token TB
Feature activation+0.000
after
Token after
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
,
Token,
Feature activation+0.988
with
Token with
Feature activation+0.640
almost
Token almost
Feature activation+0.000
48
Token 48
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
heard
Token heard
Feature activation+0.000
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
after
Token after
Feature activation+0.000
,
Token,
Feature activation+1.215
approving
Token approving
Feature activation+0.798
the
Token the
Feature activation+0.286
2005
Token 2005
Feature activation+0.030
legislative
Token legislative
Feature activation+0.000
decree
Token decree
Feature activation+0.000
s
Tokens
Feature activation+0.000
armed
Token armed
Feature activation+0.000
forces
Token forces
Feature activation+0.000
after
Token after
Feature activation+0.000
they
Token they
Feature activation+0.869
ret
Token ret
Feature activation+1.000
ook
Tokenook
Feature activation+0.233
the
Token the
Feature activation+0.000
western
Token western
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
security
Token security
Feature activation+0.000
contract
Token contract
Feature activation+0.000
after
Token after
Feature activation+0.000
residents
Token residents
Feature activation+0.335
protested
Token protested
Feature activation+1.123
the
Token the
Feature activation+0.000
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
privat
Token privat
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.124
those
Token those
Feature activation+0.000
sites
Token sites
Feature activation+0.000
began
Token began
Feature activation+0.965
working
Token working
Feature activation+0.000
with
Token with
Feature activation+0.000
large
Token large
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
service
Token service
Feature activation+0.000

INTERVAL 0.622 - 0.933
CONTAINS 0.027%

Ċ
TokenĊ
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
comments
Token comments
Feature activation+0.000
come
Token come
Feature activation+0.000
after
Token after
Feature activation+0.000
Liberal
Token Liberal
Feature activation+0.851
Party
Token Party
Feature activation+1.053
back
Token back
Feature activation+0.000
ben
Tokenben
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
Shar
Token Shar
Feature activation+0.000
French
Token French
Feature activation+0.000
military
Token military
Feature activation+0.000
base
Token base
Feature activation+0.000
and
Token and
Feature activation+0.000
after
Token after
Feature activation+0.000
55
Token 55
Feature activation+0.735
days
Token days
Feature activation+0.000
of
Token of
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
,
Token,
Feature activation+0.325
forced
Token forced
Feature activation+0.000
s
Tokens
Feature activation+0.000
players
Token players
Feature activation+0.000
were
Token were
Feature activation+0.000
informed
Token informed
Feature activation+0.000
after
Token after
Feature activation+0.000
school
Token school
Feature activation+0.660
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
email
Token email
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.161
explosion
Token explosion
Feature activation+0.329
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.848
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
labels
Token labels
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
vised
Tokenvised
Feature activation+0.000
release
Token release
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.651
gets
Token gets
Feature activation+0.663
out
Token out
Feature activation+0.550
of
Token of
Feature activation+0.301
prison
Token prison
Feature activation+0.000
under
Token under
Feature activation+0.000

INTERVAL 0.311 - 0.622
CONTAINS 0.045%

few
Token few
Feature activation+0.000
hours
Token hours
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
,
Token,
Feature activation+0.463
not
Token not
Feature activation+0.000
knowing
Token knowing
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
resisted
Token resisted
Feature activation+0.000
after
Token after
Feature activation+0.000
she
Token she
Feature activation+0.441
was
Token was
Feature activation+1.964
cor
Token cor
Feature activation+0.258
nered
Tokennered
Feature activation+0.483
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
room
Token room
Feature activation+0.000
by
Token by
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
boom
Token boom
Feature activation+0.000
after
Token after
Feature activation+0.000
World
Token World
Feature activation+0.406
War
Token War
Feature activation+0.887
II
Token II
Feature activation+0.233
was
Token was
Feature activation+1.926
turning
Token turning
Feature activation+0.389
to
Token to
Feature activation+0.000
minister
Token minister
Feature activation+0.776
Mar
Token Mar
Feature activation+0.000
iano
Tokeniano
Feature activation+0.000
Raj
Token Raj
Feature activation+0.000
oy
Tokenoy
Feature activation+0.000
announced
Token announced
Feature activation+0.476
a
Token a
Feature activation+0.000
major
Token major
Feature activation+0.000
shake
Token shake
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
all
Token all
Feature activation+0.177
,
Token,
Feature activation+0.343
is
Token is
Feature activation+1.706
more
Token more
Feature activation+0.399
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
capsule
Token capsule
Feature activation+0.000
than
Token than
Feature activation+0.000

INTERVAL 0.000 - 0.311
CONTAINS 99.896%

is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
true
Token true
Feature activation+0.000
master
Token master
Feature activation+0.000
of
Token of
Feature activation+0.000
distance
Token distance
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
fights
Token fights
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
Perth
Token Perth
Feature activation+0.000
has
Token has
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
of
Token of
Feature activation+0.000
R
TokenR
Feature activation+0.000
obby
Tokenobby
Feature activation+0.000
F
Token F
Feature activation+0.000
abb
Tokenabb
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Josh
TokenJosh
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
-
Token-
Feature activation+0.000
Smith
TokenSmith
Feature activation+0.000
which
Token which
Feature activation+0.000
prevents
Token prevents
Feature activation+0.000
endless
Token endless
Feature activation+0.000
loops
Token loops
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
contrast
Token contrast
Feature activation+0.000
to
Token to
Feature activation+0.000
chess
Token chess
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Oscar
Token Oscar
Feature activation+0.000
®
Token®
Feature activation+0.000
winning
Token winning
Feature activation+0.000
Dream
Token Dream
Feature activation+0.000
Works
TokenWorks
Feature activation+0.000
film
Token film
Feature activation+0.000
that
Token that
Feature activation+0.000
started
Token started
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H2.3: (feature 10273)

TOP ACTIVATIONS
MAX = 3.560

assistants
Token assistants
Feature activation+0.000
.
Token.
Feature activation+0.000
Where
Token Where
Feature activation+0.000
it
Token it
Feature activation+0.257
goes
Token goes
Feature activation+1.829
from
Token from
Feature activation+3.560
here
Token here
Feature activation+0.000
will
Token will
Feature activation+0.899
help
Token help
Feature activation+1.229
define
Token define
Feature activation+0.000
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
Knowing
TokenKnowing
Feature activation+0.000
where
Token where
Feature activation+0.000
it
Token it
Feature activation+0.556
comes
Token comes
Feature activation+1.940
from
Token from
Feature activation+3.388
,
Token,
Feature activation+0.967
I
Token I
Feature activation+0.323
think
Token think
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
trace
Token trace
Feature activation+0.000
to
Token to
Feature activation+0.000
where
Token where
Feature activation+0.000
it
Token it
Feature activation+0.741
came
Token came
Feature activation+2.178
from
Token from
Feature activation+3.330
.
Token.
Feature activation+0.211
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
explain
Token explain
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.196
money
Token money
Feature activation+0.000
came
Token came
Feature activation+2.397
from
Token from
Feature activation+3.306
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cho
TokenCho
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
are
Token are
Feature activation+2.333
predicted
Token predicted
Feature activation+1.559
to
Token to
Feature activation+2.101
be
Token be
Feature activation+3.147
most
Token most
Feature activation+0.531
severe
Token severe
Feature activation+0.265
,
Token,
Feature activation+0.512
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
where
Token where
Feature activation+0.000
Lara
Token Lara
Feature activation+0.216
's
Token's
Feature activation+0.827
headed
Token headed
Feature activation+3.049
next
Token next
Feature activation+0.457
right
Token right
Feature activation+0.000
here
Token here
Feature activation+0.250
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
can
Token can
Feature activation+0.762
I
Token I
Feature activation+2.142
find
Token find
Feature activation+2.988
it
Token it
Feature activation+1.171
?
Token?
Feature activation+0.077
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
on
Token on
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
Feature activation+0.253
decided
Token decided
Feature activation+0.366
to
Token to
Feature activation+2.094
go
Token go
Feature activation+2.985
with
Token with
Feature activation+0.250
this
Token this
Feature activation+0.000
record
Token record
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
questions
Token questions
Feature activation+0.000
of
Token of
Feature activation+0.000
where
Token where
Feature activation+0.403
our
Token our
Feature activation+0.268
identity
Token identity
Feature activation+0.000
resides
Token resides
Feature activation+2.943
and
Token and
Feature activation+0.848
what
Token what
Feature activation+0.423
are
Token are
Feature activation+0.000
its
Token its
Feature activation+0.000
ir
Token ir
Feature activation+0.000
where
Token where
Feature activation+0.000
all
Token all
Feature activation+0.968
the
Token the
Feature activation+0.666
money
Token money
Feature activation+0.000
is
Token is
Feature activation+1.594
going
Token going
Feature activation+2.929
,
Token,
Feature activation+0.695
creating
Token creating
Feature activation+0.000
the
Token the
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
where
Token where
Feature activation+0.000
to
Token to
Feature activation+1.129
start
Token start
Feature activation+2.873
.
Token.
Feature activation+0.346
And
Token And
Feature activation+0.071
believe
Token believe
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.778
gets
Token gets
Feature activation+0.890
these
Token these
Feature activation+0.206
images
Token images
Feature activation+0.000
from
Token from
Feature activation+2.818
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
creepy
Token creepy
Feature activation+0.000
a
Tokena
Feature activation+0.000
place
Token place
Feature activation+0.000
where
Token where
Feature activation+0.000
one
Token one
Feature activation+0.000
can
Token can
Feature activation+1.517
live
Token live
Feature activation+2.811
safely
Token safely
Feature activation+1.284
,
Token,
Feature activation+0.879
in
Token in
Feature activation+0.354
peace
Token peace
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.261
problem
Token problem
Feature activation+0.000
lies
Token lies
Feature activation+2.800
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
this
Token this
Feature activation+0.000
much
Token much
Feature activation+0.000
bl
Token bl
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.251
the
Token the
Feature activation+0.005
vehicle
Token vehicle
Feature activation+0.000
was
Token was
Feature activation+1.673
placed
Token placed
Feature activation+2.759
in
Token in
Feature activation+0.343
a
Token a
Feature activation+0.000
shipping
Token shipping
Feature activation+0.000
container
Token container
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.735
needs
Token needs
Feature activation+0.563
to
Token to
Feature activation+2.354
be
Token be
Feature activation+2.736
:
Token:
Feature activation+0.703
he
Token he
Feature activation+0.063
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
World
Token World
Feature activation+0.000
Elite
Token Elite
Feature activation+0.000
would
Token would
Feature activation+1.595
find
Token find
Feature activation+2.701
excellent
Token excellent
Feature activation+1.035
kill
Token kill
Feature activation+0.000
opportunities
Token opportunities
Feature activation+0.000
,
Token,
Feature activation+0.443
an
Token an
Feature activation+0.000
venues
Token venues
Feature activation+0.000
where
Token where
Feature activation+0.000
seafood
Token seafood
Feature activation+0.385
fraud
Token fraud
Feature activation+0.000
was
Token was
Feature activation+1.111
found
Token found
Feature activation+2.653
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Rest
TokenRest
Feature activation+0.000
aur
Tokenaur
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
Feature activation+0.198
are
Token are
Feature activation+2.015
heading
Token heading
Feature activation+2.651
.
Token.
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
La
Token La
Feature activation+0.000
o
Tokeno
Feature activation+0.000
T
Token T
Feature activation+0.000
events
Token events
Feature activation+0.000
are
Token are
Feature activation+0.000
where
Token where
Feature activation+0.000
it
Token it
Feature activation+0.762
's
Token's
Feature activation+1.605
at
Token at
Feature activation+2.622
.
Token.
Feature activation+0.000
Further
Token Further
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000

Top DFA by src position
MAX = 4.026

world
Token world
Feature activation-0.018
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
voice
Token voice
Feature activation-0.028
Top resid features:
assistants
Token assistants
Feature activation-0.031
Top resid features:
.
Token.
Feature activation-0.093
Top resid features:
Where
Token Where
Feature activation+4.026
Top resid features:
it
Token it
Feature activation-0.094
Top resid features:
goes
Token goes
Feature activation-0.058
Top resid features:
from
Token from
Feature activation+0.173
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
human
Token human
Feature activation-0.013
Top resid features:
blood
Token blood
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
(
Token (
Feature activation+0.040
Top resid features:
Knowing
TokenKnowing
Feature activation-0.187
Top resid features:
where
Token where
Feature activation+3.988
Top resid features:
it
Token it
Feature activation-0.110
Top resid features:
comes
Token comes
Feature activation-0.153
Top resid features:
from
Token from
Feature activation+0.120
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
You
Token You
Feature activation-0.035
Top resid features:
can
Token can
Feature activation+0.011
Top resid features:
never
Token never
Feature activation+0.109
Top resid features:
trace
Token trace
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.094
Top resid features:
where
Token where
Feature activation+3.672
Top resid features:
it
Token it
Feature activation-0.120
Top resid features:
came
Token came
Feature activation-0.137
Top resid features:
from
Token from
Feature activation+0.111
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
story
Token story
Feature activation-0.027
Top resid features:
and
Token and
Feature activation-0.026
Top resid features:
could
Token could
Feature activation+0.022
Top resid features:
not
Token not
Feature activation+0.068
Top resid features:
explain
Token explain
Feature activation-0.032
Top resid features:
where
Token where
Feature activation+3.903
Top resid features:
the
Token the
Feature activation-0.033
Top resid features:
money
Token money
Feature activation-0.073
Top resid features:
came
Token came
Feature activation-0.160
Top resid features:
from
Token from
Feature activation+0.169
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
weather
Token weather
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
"
Token"
Feature activation-0.015
Top resid features:
Where
TokenWhere
Feature activation+3.129
Top resid features:
conditions
Token conditions
Feature activation+0.038
Top resid features:
are
Token are
Feature activation-0.005
Top resid features:
predicted
Token predicted
Feature activation+0.347
Top resid features:
to
Token to
Feature activation+0.092
Top resid features:
be
Token be
Feature activation-0.005
Top resid features:
took
Token took
Feature activation+0.017
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
closer
Token closer
Feature activation-0.023
Top resid features:
look
Token look
Feature activation-0.053
Top resid features:
at
Token at
Feature activation+0.074
Top resid features:
where
Token where
Feature activation+3.251
Top resid features:
Lara
Token Lara
Feature activation-0.074
Top resid features:
's
Token's
Feature activation+0.108
Top resid features:
headed
Token headed
Feature activation+0.085
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.005
Top resid features:
succeed
Token succeed
Feature activation+0.008
Top resid features:
?
Token?
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Where
TokenWhere
Feature activation+3.568
Top resid features:
can
Token can
Feature activation+0.096
Top resid features:
I
Token I
Feature activation-0.413
Top resid features:
find
Token find
Feature activation-0.084
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
events
Token events
Feature activation-0.025
Top resid features:
have
Token have
Feature activation-0.012
Top resid features:
any
Token any
Feature activation+0.007
Top resid features:
bearing
Token bearing
Feature activation+0.012
Top resid features:
on
Token on
Feature activation+0.081
Top resid features:
where
Token where
Feature activation+3.268
Top resid features:
you
Token you
Feature activation-0.087
Top resid features:
decided
Token decided
Feature activation-0.036
Top resid features:
to
Token to
Feature activation+0.202
Top resid features:
go
Token go
Feature activation-0.001
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
free
Token free
Feature activation+0.024
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
or
Token or
Feature activation+0.041
Top resid features:
questions
Token questions
Feature activation-0.067
Top resid features:
of
Token of
Feature activation+0.056
Top resid features:
where
Token where
Feature activation+3.491
Top resid features:
our
Token our
Feature activation-0.094
Top resid features:
identity
Token identity
Feature activation-0.238
Top resid features:
resides
Token resides
Feature activation-0.017
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
really
Token really
Feature activation-0.012
Top resid features:
easy
Token easy
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.058
Top resid features:
see
Token see
Feature activation-0.010
Top resid features:
where
Token where
Feature activation+3.377
Top resid features:
all
Token all
Feature activation+0.029
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
money
Token money
Feature activation-0.071
Top resid features:
is
Token is
Feature activation-0.152
Top resid features:
going
Token going
Feature activation+0.003
Top resid features:
don
Token don
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ļ
TokenĻ
Feature activation-0.026
Top resid features:
t
Tokent
Feature activation-0.014
Top resid features:
know
Token know
Feature activation-0.152
Top resid features:
where
Token where
Feature activation+3.299
Top resid features:
to
Token to
Feature activation+0.217
Top resid features:
start
Token start
Feature activation-0.170
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
And
Token And
Feature activation+0.000
Top resid features:
believe
Token believe
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
I
Token I
Feature activation-0.002
Top resid features:
don
Token don
Feature activation+0.004
Top resid features:
't
Token't
Feature activation+0.038
Top resid features:
know
Token know
Feature activation-0.050
Top resid features:
where
Token where
Feature activation+3.255
Top resid features:
he
Token he
Feature activation+0.021
Top resid features:
gets
Token gets
Feature activation-0.095
Top resid features:
these
Token these
Feature activation-0.106
Top resid features:
images
Token images
Feature activation-0.130
Top resid features:
from
Token from
Feature activation+0.065
Top resid features:
but
Token but
Feature activation+0.002
Top resid features:
âĢ
Token âĢ
Feature activation+0.023
Top resid features:
ľ
Tokenľ
Feature activation-0.007
Top resid features:
a
Tokena
Feature activation-0.018
Top resid features:
place
Token place
Feature activation-0.015
Top resid features:
where
Token where
Feature activation+2.968
Top resid features:
one
Token one
Feature activation-0.024
Top resid features:
can
Token can
Feature activation+0.196
Top resid features:
live
Token live
Feature activation+0.014
Top resid features:
safely
Token safely
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
And
TokenAnd
Feature activation-0.080
Top resid features:
that
Token that
Feature activation-0.077
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
exactly
Token exactly
Feature activation+0.029
Top resid features:
where
Token where
Feature activation+3.260
Top resid features:
the
Token the
Feature activation-0.060
Top resid features:
problem
Token problem
Feature activation-0.019
Top resid features:
lies
Token lies
Feature activation+0.092
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
With
Token With
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.041
Top resid features:
Detroit
Token Detroit
Feature activation-0.029
Top resid features:
to
Token to
Feature activation+0.057
Top resid features:
Vancouver
Token Vancouver
Feature activation-0.056
Top resid features:
,
Token,
Feature activation-0.038
Top resid features:
where
Token where
Feature activation+3.121
Top resid features:
the
Token the
Feature activation-0.022
Top resid features:
vehicle
Token vehicle
Feature activation-0.015
Top resid features:
was
Token was
Feature activation-0.098
Top resid features:
placed
Token placed
Feature activation-0.012
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
himself
Token himself
Feature activation+0.005
Top resid features:
within
Token within
Feature activation+0.078
Top resid features:
striking
Token striking
Feature activation-0.050
Top resid features:
distance
Token distance
Feature activation+0.025
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
where
Token where
Feature activation+2.966
Top resid features:
he
Token he
Feature activation-0.063
Top resid features:
needs
Token needs
Feature activation-0.051
Top resid features:
to
Token to
Feature activation+0.157
Top resid features:
be
Token be
Feature activation-0.014
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
were
Token were
Feature activation+0.002
Top resid features:
slowly
Token slowly
Feature activation+0.035
Top resid features:
diminishing
Token diminishing
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.035
Top resid features:
Where
TokenWhere
Feature activation+3.141
Top resid features:
World
Token World
Feature activation-0.012
Top resid features:
Elite
Token Elite
Feature activation-0.030
Top resid features:
would
Token would
Feature activation-0.013
Top resid features:
find
Token find
Feature activation+0.045
Top resid features:
excellent
Token excellent
Feature activation+0.000
Top resid features:
locations
Token locations
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.035
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
specific
Token specific
Feature activation+0.001
Top resid features:
venues
Token venues
Feature activation-0.025
Top resid features:
where
Token where
Feature activation+3.018
Top resid features:
seafood
Token seafood
Feature activation-0.028
Top resid features:
fraud
Token fraud
Feature activation-0.019
Top resid features:
was
Token was
Feature activation-0.127
Top resid features:
found
Token found
Feature activation-0.024
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
you
Token you
Feature activation-0.012
Top resid features:
may
Token may
Feature activation-0.015
Top resid features:
end
Token end
Feature activation-0.014
Top resid features:
up
Token up
Feature activation+0.015
Top resid features:
where
Token where
Feature activation+3.137
Top resid features:
you
Token you
Feature activation-0.216
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
heading
Token heading
Feature activation+0.061
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
browser
Token browser
Feature activation-0.020
Top resid features:
environment
Token environment
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
events
Token events
Feature activation-0.019
Top resid features:
are
Token are
Feature activation+0.031
Top resid features:
where
Token where
Feature activation+2.908
Top resid features:
it
Token it
Feature activation-0.075
Top resid features:
's
Token's
Feature activation+0.067
Top resid features:
at
Token at
Feature activation+0.262
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Further
Token Further
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.02

Head 2: 0.04

Head 3: 0.41

Head 4: 0.05

Head 5: 0.08

Head 6: 0.04

Head 7: 0.05

Head 8: 0.05

Head 9: 0.04

Head 10: 0.10

Head 11: 0.05

Positive logits

upon1.43

Interstitial1.34

REDACTED1.26

SPONSORED1.26

ottest1.24

perty1.22

onomous1.18

happiest1.17

yll1.15

surrounded1.13

Maced1.12

imum1.11

intersect1.11

Field1.10

forth1.09

itive1.08

awaited1.06

boarded1.06

arya1.04

Actor1.03

Negative logits

Fas-1.30

Wid-1.13

vier-1.13

Extensions-1.09

uploads-1.05

-1.04

aml-1.02

etheless-1.01

cat-1.00

lish-1.00

extensions-1.00

BP-0.99

Carbon-0.99

atform-0.98

bash-0.98

LI-0.98

guiActiveUn-0.98

selves-0.97

vision-0.97

bear-0.96

INTERVAL 3.204 - 3.560
CONTAINS 0.001%

explain
Token explain
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.196
money
Token money
Feature activation+0.000
came
Token came
Feature activation+2.397
from
Token from
Feature activation+3.306
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cho
TokenCho
Feature activation+0.000
i
Tokeni
Feature activation+0.000
trace
Token trace
Feature activation+0.000
to
Token to
Feature activation+0.000
where
Token where
Feature activation+0.000
it
Token it
Feature activation+0.741
came
Token came
Feature activation+2.178
from
Token from
Feature activation+3.330
.
Token.
Feature activation+0.211
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token (
Feature activation+0.000
Knowing
TokenKnowing
Feature activation+0.000
where
Token where
Feature activation+0.000
it
Token it
Feature activation+0.556
comes
Token comes
Feature activation+1.940
from
Token from
Feature activation+3.388
,
Token,
Feature activation+0.967
I
Token I
Feature activation+0.323
think
Token think
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
assistants
Token assistants
Feature activation+0.000
.
Token.
Feature activation+0.000
Where
Token Where
Feature activation+0.000
it
Token it
Feature activation+0.257
goes
Token goes
Feature activation+1.829
from
Token from
Feature activation+3.560
here
Token here
Feature activation+0.000
will
Token will
Feature activation+0.899
help
Token help
Feature activation+1.229
define
Token define
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.848 - 3.204
CONTAINS 0.001%

look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
where
Token where
Feature activation+0.000
Lara
Token Lara
Feature activation+0.216
's
Token's
Feature activation+0.827
headed
Token headed
Feature activation+3.049
next
Token next
Feature activation+0.457
right
Token right
Feature activation+0.000
here
Token here
Feature activation+0.250
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
are
Token are
Feature activation+2.333
predicted
Token predicted
Feature activation+1.559
to
Token to
Feature activation+2.101
be
Token be
Feature activation+3.147
most
Token most
Feature activation+0.531
severe
Token severe
Feature activation+0.265
,
Token,
Feature activation+0.512
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
on
Token on
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
Feature activation+0.253
decided
Token decided
Feature activation+0.366
to
Token to
Feature activation+2.094
go
Token go
Feature activation+2.985
with
Token with
Feature activation+0.250
this
Token this
Feature activation+0.000
record
Token record
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
where
Token where
Feature activation+0.000
to
Token to
Feature activation+1.129
start
Token start
Feature activation+2.873
.
Token.
Feature activation+0.346
And
Token And
Feature activation+0.071
believe
Token believe
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
can
Token can
Feature activation+0.762
I
Token I
Feature activation+2.142
find
Token find
Feature activation+2.988
it
Token it
Feature activation+1.171
?
Token?
Feature activation+0.077
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 2.492 - 2.848
CONTAINS 0.002%

of
Token of
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.735
needs
Token needs
Feature activation+0.563
to
Token to
Feature activation+2.354
be
Token be
Feature activation+2.736
:
Token:
Feature activation+0.703
he
Token he
Feature activation+0.063
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
4
Token 4
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
Feature activation+0.198
are
Token are
Feature activation+2.015
heading
Token heading
Feature activation+2.651
.
Token.
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
La
Token La
Feature activation+0.000
o
Tokeno
Feature activation+0.000
T
Token T
Feature activation+0.000
is
Token is
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.261
problem
Token problem
Feature activation+0.000
lies
Token lies
Feature activation+2.800
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
this
Token this
Feature activation+0.000
much
Token much
Feature activation+0.000
bl
Token bl
Feature activation+0.000
am
Token am
Feature activation+0.000
wondering
Token wondering
Feature activation+0.000
where
Token where
Feature activation+0.000
I
Token I
Feature activation+0.748
should
Token should
Feature activation+1.842
put
Token put
Feature activation+2.523
my
Token my
Feature activation+0.528
stand
Token stand
Feature activation+1.414
on
Token on
Feature activation+0.000
software
Token software
Feature activation+0.000
diversity
Token diversity
Feature activation+0.000
Up
Token Up
Feature activation+0.000
to
Token to
Feature activation+0.000
where
Token where
Feature activation+0.000
we
Token we
Feature activation+0.720
are
Token are
Feature activation+2.205
now
Token now
Feature activation+2.501
(
Token (
Feature activation+0.641
say
Tokensay
Feature activation+0.000
ep
Token ep
Feature activation+0.000
2
Token 2
Feature activation+0.000
x
Tokenx
Feature activation+0.000

INTERVAL 2.136 - 2.492
CONTAINS 0.003%

?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
can
Token can
Feature activation+0.762
I
Token I
Feature activation+2.142
find
Token find
Feature activation+2.988
it
Token it
Feature activation+1.171
?
Token?
Feature activation+0.077
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
where
Token where
Feature activation+0.000
to
Token to
Feature activation+0.811
put
Token put
Feature activation+2.308
scarce
Token scarce
Feature activation+0.303
research
Token research
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.402
need
Token need
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
building
Token building
Feature activation+0.000
where
Token where
Feature activation+0.000
crews
Token crews
Feature activation+0.000
found
Token found
Feature activation+2.162
the
Token the
Feature activation+0.367
time
Token time
Feature activation+0.573
capsule
Token capsule
Feature activation+0.000
,
Token,
Feature activation+0.017
Montgomery
Token Montgomery
Feature activation+0.000
Tra
TokenTra
Feature activation+0.000
il
Tokenil
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
Feature activation+0.371
can
Token can
Feature activation+1.334
find
Token find
Feature activation+2.170
his
Token his
Feature activation+0.359
latest
Token latest
Feature activation+0.000
research
Token research
Feature activation+0.000
on
Token on
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
not
Token not
Feature activation+0.000
explain
Token explain
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.196
money
Token money
Feature activation+0.000
came
Token came
Feature activation+2.397
from
Token from
Feature activation+3.306
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cho
TokenCho
Feature activation+0.000

INTERVAL 1.780 - 2.136
CONTAINS 0.007%

towns
Token towns
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
jobs
Token jobs
Feature activation+0.122
had
Token had
Feature activation+0.455
moved
Token moved
Feature activation+2.053
overseas
Token overseas
Feature activation+0.229
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
felt
Token felt
Feature activation+0.000
himself
Token himself
Feature activation+0.000
stay
Token stay
Feature activation+0.000
in
Token in
Feature activation+0.000
school
Token school
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.450
belongs
Token belongs
Feature activation+2.127
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
violence
Token violence
Feature activation+0.000
is
Token is
Feature activation+0.000
never
Token never
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
went
Token went
Feature activation+2.066
to
Token to
Feature activation+1.553
Harvard
Token Harvard
Feature activation+0.000
Law
Token Law
Feature activation+0.000
School
Token School
Feature activation+0.000
,
Token,
Feature activation+0.004
'll
Token'll
Feature activation+0.000
see
Token see
Feature activation+0.000
where
Token where
Feature activation+0.000
I
Token I
Feature activation+0.911
end
Token end
Feature activation+1.201
up
Token up
Feature activation+2.046
.
Token.
Feature activation+0.177
Enjoy
TokenEnjoy
Feature activation+0.000
&
Token &
Feature activation+0.000
Until
Token Until
Feature activation+0.000
next
Token next
Feature activation+0.000
where
Token where
Feature activation+0.000
a
Token a
Feature activation+0.000
World
Token World
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
should
Token should
Feature activation+1.658
be
Token be
Feature activation+1.918
held
Token held
Feature activation+0.464
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 1.424 - 1.780
CONTAINS 0.011%

he
Token he
Feature activation+0.239
warped
Token warped
Feature activation+0.000
to
Token to
Feature activation+0.515
the
Token the
Feature activation+0.208
sun
Token sun
Feature activation+0.000
from
Token from
Feature activation+1.554
,
Token,
Feature activation+0.000
warp
Token warp
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
celestial
Token celestial
Feature activation+0.000
where
Token where
Feature activation+0.063
I
Token I
Feature activation+0.853
streamed
Token streamed
Feature activation+1.004
Netflix
Token Netflix
Feature activation+0.381
and
Token and
Feature activation+0.569
live
Token live
Feature activation+1.644
football
Token football
Feature activation+0.000
games
Token games
Feature activation+0.000
over
Token over
Feature activation+0.000
Wi
Token Wi
Feature activation+0.000
-
Token-
Feature activation+0.000
en
Tokenen
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.557
would
Token would
Feature activation+1.205
end
Token end
Feature activation+1.503
up
Token up
Feature activation+1.469
sharing
Token sharing
Feature activation+0.438
the
Token the
Feature activation+0.000
bot
Token bot
Feature activation+0.000
lane
Tokenlane
Feature activation+0.000
in
Token in
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
stalls
Token stalls
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.409
are
Token are
Feature activation+1.529
unable
Token unable
Feature activation+0.735
to
Token to
Feature activation+0.895
turn
Token turn
Feature activation+0.424
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
ways
Token ways
Feature activation+0.000
where
Token where
Feature activation+0.000
we
Token we
Feature activation+0.338
don
Token don
Feature activation+1.573
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.297
t
Tokent
Feature activation+0.442
have
Token have
Feature activation+0.988
to
Token to
Feature activation+1.614

INTERVAL 1.068 - 1.424
CONTAINS 0.014%

Orig
Token Orig
Feature activation+0.000
en
Tokenen
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.557
would
Token would
Feature activation+1.205
end
Token end
Feature activation+1.503
up
Token up
Feature activation+1.469
sharing
Token sharing
Feature activation+0.438
the
Token the
Feature activation+0.000
bot
Token bot
Feature activation+0.000
?
Token?
Feature activation+0.000
No
Token No
Feature activation+0.000
matter
Token matter
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
goes
Token goes
Feature activation+1.227
,
Token,
Feature activation+1.252
the
Token the
Feature activation+0.269
Alliance
Token Alliance
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.111
where
Token where
Feature activation+0.000
each
Token each
Feature activation+0.006
military
Token military
Feature activation+0.000
member
Token member
Feature activation+0.000
had
Token had
Feature activation+0.512
served
Token served
Feature activation+1.147
,
Token,
Feature activation+0.130
and
Token and
Feature activation+0.000
place
Token place
Feature activation+0.000
the
Token the
Feature activation+0.000
flag
Token flag
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
technology
Token technology
Feature activation+0.000
hub
Token hub
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.034
works
Token works
Feature activation+1.250
,
Token,
Feature activation+0.562
casually
Token casually
Feature activation+0.250
making
Token making
Feature activation+0.075
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
different
Tokendifferent
Feature activation+0.000
couples
Token couples
Feature activation+0.000
where
Token where
Feature activation+0.000
one
Token one
Feature activation+0.000
partner
Token partner
Feature activation+0.000
was
Token was
Feature activation+1.393
HIV
Token HIV
Feature activation+0.000
positive
Token positive
Feature activation+0.000
and
Token and
Feature activation+0.317
undet
Token undet
Feature activation+0.000
ect
Tokenect
Feature activation+0.000

INTERVAL 0.712 - 1.068
CONTAINS 0.017%

priorities
Token priorities
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.764
one
Token one
Feature activation+0.329
man
Token man
Feature activation+0.000
in
Token in
Feature activation+0.128
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
where
Token where
Feature activation+0.000
Gand
Token Gand
Feature activation+0.000
olf
Tokenolf
Feature activation+0.339
ini
Tokenini
Feature activation+0.555
was
Token was
Feature activation+2.416
pronounced
Token pronounced
Feature activation+1.041
dead
Token dead
Feature activation+0.901
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
lobby
Token lobby
Feature activation+0.000
area
Token area
Feature activation+0.000
where
Token where
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+1.396
welcomed
Token welcomed
Feature activation+0.734
by
Token by
Feature activation+0.336
the
Token the
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000
reception
Token reception
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
see
Token see
Feature activation+0.000
where
Token where
Feature activation+0.016
criminal
Token criminal
Feature activation+0.359
isation
Tokenisation
Feature activation+0.267
remains
Token remains
Feature activation+2.442
the
Token the
Feature activation+0.943
norm
Token norm
Feature activation+0.136
Get
TokenGet
Feature activation+0.182
the
Token the
Feature activation+0.052
data
Token data
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
TD
Token TD
Feature activation+0.000
Place
Token Place
Feature activation+0.000
stadium
Token stadium
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.821
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.655
ll
Tokenll
Feature activation+0.255
battle
Token battle
Feature activation+0.518
again
Token again
Feature activation+0.544

INTERVAL 0.356 - 0.712
CONTAINS 0.036%

where
Token where
Feature activation+0.000
houses
Token houses
Feature activation+0.000
still
Token still
Feature activation+1.050
are
Token are
Feature activation+2.153
maintained
Token maintained
Feature activation+1.234
and
Token and
Feature activation+0.397
occupied
Token occupied
Feature activation+0.284
by
Token by
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token"
Feature activation+0.000
had
Token had
Feature activation+0.000
stories
Token stories
Feature activation+0.000
where
Token where
Feature activation+0.000
Peter
Token Peter
Feature activation+0.475
had
Token had
Feature activation+0.627
to
Token to
Feature activation+2.164
raise
Token raise
Feature activation+1.554
money
Token money
Feature activation+0.274
to
Token to
Feature activation+0.340
help
Token help
Feature activation+0.468
lives
Token lives
Feature activation+0.000
in
Token in
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
stalls
Token stalls
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.409
are
Token are
Feature activation+1.529
unable
Token unable
Feature activation+0.735
to
Token to
Feature activation+0.895
turn
Token turn
Feature activation+0.424
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
site
Token site
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.000
posted
Token posted
Feature activation+0.640
it
Token it
Feature activation+0.362
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
removal
Token removal
Feature activation+0.000
right
Token right
Feature activation+0.000
no
Token no
Feature activation+0.000
idea
Token idea
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
was
Token was
Feature activation+0.481
spent
Token spent
Feature activation+1.006
once
Token once
Feature activation+0.731
it
Token it
Feature activation+0.000
went
Token went
Feature activation+0.000
into
Token into
Feature activation+0.000

INTERVAL 0.000 - 0.356
CONTAINS 99.909%

safe
Token safe
Feature activation+0.000
bowl
Token bowl
Feature activation+0.000
.
Token.
Feature activation+0.000
Heat
Token Heat
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
microwave
Token microwave
Feature activation+0.000
for
Token for
Feature activation+0.000
45
Token 45
Feature activation+0.000
States
Token States
Feature activation+0.000
and
Token and
Feature activation+0.000
remain
Token remain
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
the
Token the
Feature activation+0.000
reach
Token reach
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
,
Token,
Feature activation+0.000
physically
Token physically
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
looks
Token looks
Feature activation+0.000
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
Cold
Token Cold
Feature activation+0.000
War
Token War
Feature activation+0.000
cases
Token cases
Feature activation+0.000
(
Token (
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
covers
Token covers
Feature activation+0.000
testing
Token testing
Feature activation+0.000
sites
Token sites
Feature activation+0.000
highly
Token highly
Feature activation+0.000
per
Token per
Feature activation+0.000
missive
Tokenmissive
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
allow
Token allow
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
things
Token things
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H2.3: (feature 15605)

TOP ACTIVATIONS
MAX = 3.099

his
Token his
Feature activation+0.000
troops
Token troops
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
operation
Token operation
Feature activation+0.559
began
Token began
Feature activation+3.099
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
died
Token died
Feature activation+0.000
long
Token long
Feature activation+0.000
before
Token before
Feature activation+0.000
you
Token you
Feature activation+0.000
were
Token were
Feature activation+2.123
born
Token born
Feature activation+3.043
.
Token.
Feature activation+0.014
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
before
Token before
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+1.561
born
Token born
Feature activation+3.016
,
Token,
Feature activation+0.439
expanded
Token expanded
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.000
solar
Token solar
Feature activation+0.000
boom
Token boom
Feature activation+0.000
before
Token before
Feature activation+0.000
it
Token it
Feature activation+0.482
gets
Token gets
Feature activation+1.567
started
Token started
Feature activation+2.790
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Today
TokenToday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
began
Token began
Feature activation+2.699
,
Token,
Feature activation+0.621
most
Token most
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
fans
Token fans
Feature activation+0.000
iness
Tokeniness
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.000
it
Token it
Feature activation+0.581
is
Token is
Feature activation+2.632
allowed
Token allowed
Feature activation+0.770
to
Token to
Feature activation+1.193
be
Token be
Feature activation+0.635
posted
Token posted
Feature activation+0.179
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Shortly
TokenShortly
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.772
was
Token was
Feature activation+1.986
hospitalized
Token hospitalized
Feature activation+2.567
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.000
garnered
Token garnered
Feature activation+0.000
,
Token,
Feature activation+0.000
written
Token written
Feature activation+0.000
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.585
officers
Token officers
Feature activation+0.365
were
Token were
Feature activation+2.535
amb
Token amb
Feature activation+0.116
ushed
Tokenushed
Feature activation+0.512
while
Token while
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
in
Token in
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
well
Token well
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
verdict
Token verdict
Feature activation+0.519
was
Token was
Feature activation+2.512
announced
Token announced
Feature activation+1.913
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
adequately
Token adequately
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
before
Token before
Feature activation+0.000
she
Token she
Feature activation+0.951
can
Token can
Feature activation+1.427
leave
Token leave
Feature activation+2.504
her
Token her
Feature activation+0.046
apartment
Token apartment
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
sequ
Token sequ
Feature activation+0.000
ester
Tokenester
Feature activation+0.000
cuts
Token cuts
Feature activation+1.244
went
Token went
Feature activation+2.442
into
Token into
Feature activation+0.736
effect
Token effect
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
Get
Token Get
Feature activation+0.000
yours
Token yours
Feature activation+0.000
before
Token before
Feature activation+0.000
they
Token they
Feature activation+0.827
are
Token are
Feature activation+1.943
gone
Token gone
Feature activation+2.405
,
Token,
Feature activation+0.829
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
part
Token part
Feature activation+0.000
the
Token the
Feature activation+0.000
hall
Token hall
Feature activation+0.000
ways
Tokenways
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.000
started
Token started
Feature activation+2.334
coding
Token coding
Feature activation+0.000
club
Token club
Feature activation+0.000
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
he
Token he
Feature activation+0.000
created
Token created
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.827
nation
Token nation
Feature activation+0.000
became
Token became
Feature activation+2.316
independent
Token independent
Feature activation+0.158
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
firm
Token firm
Feature activation+0.000
.
Token.
Feature activation+0.000
Before
Token Before
Feature activation+0.000
hedge
Token hedge
Feature activation+0.445
funds
Token funds
Feature activation+1.041
began
Token began
Feature activation+2.308
selling
Token selling
Feature activation+0.221
their
Token their
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
Ed
TokenEd
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
she
Token she
Feature activation+0.246
left
Token left
Feature activation+2.301
,
Token,
Feature activation+0.508
I
Token I
Feature activation+0.000
didn
Token didn
Feature activation+0.179
't
Token't
Feature activation+0.000
even
Token even
Feature activation+0.000
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
hours
Token hours
Feature activation+0.000
before
Token before
Feature activation+0.000
police
Token police
Feature activation+0.000
were
Token were
Feature activation+2.298
able
Token able
Feature activation+0.661
to
Token to
Feature activation+1.175
remove
Token remove
Feature activation+0.231
it
Token it
Feature activation+0.000
Tr
Token Tr
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
before
Token before
Feature activation+0.000
it
Token it
Feature activation+0.096
started
Token started
Feature activation+2.276
,
Token,
Feature activation+0.579
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
B
Token B
Feature activation+0.000
amboo
Tokenamboo
Feature activation+0.105
can
Token can
Feature activation+1.008
be
Token be
Feature activation+2.246
used
Token used
Feature activation+1.333
for
Token for
Feature activation+0.193
any
Token any
Feature activation+0.000
lasting
Token lasting
Feature activation+0.000
craft
Token craft
Feature activation+0.000
,
Token,
Feature activation+0.000
five
Token five
Feature activation+0.000
days
Token days
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+1.003
was
Token was
Feature activation+2.246
sworn
Token sworn
Feature activation+1.010
in
Token in
Feature activation+0.644
as
Token as
Feature activation+0.002
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 4.104

Scott
Token Scott
Feature activation-0.017
Top resid features:
Levin
Token Levin
Feature activation-0.014
Top resid features:
told
Token told
Feature activation+0.082
Top resid features:
his
Token his
Feature activation+0.023
Top resid features:
troops
Token troops
Feature activation-0.009
Top resid features:
before
Token before
Feature activation+4.104
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
operation
Token operation
Feature activation-0.079
Top resid features:
began
Token began
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
"
Token"
Feature activation+0.014
Top resid features:
I
TokenI
Feature activation-0.009
Top resid features:
died
Token died
Feature activation+0.063
Top resid features:
long
Token long
Feature activation+0.069
Top resid features:
before
Token before
Feature activation+3.818
Top resid features:
you
Token you
Feature activation+0.334
Top resid features:
were
Token were
Feature activation-0.063
Top resid features:
born
Token born
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
bought
Token bought
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
business
Token business
Feature activation-0.062
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
year
Token year
Feature activation+0.019
Top resid features:
before
Token before
Feature activation+3.978
Top resid features:
I
Token I
Feature activation+0.275
Top resid features:
was
Token was
Feature activation-0.037
Top resid features:
born
Token born
Feature activation-0.048
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
expanded
Token expanded
Feature activation+0.000
Top resid features:
could
Token could
Feature activation-0.006
Top resid features:
stop
Token stop
Feature activation-0.012
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
solar
Token solar
Feature activation-0.038
Top resid features:
boom
Token boom
Feature activation-0.021
Top resid features:
before
Token before
Feature activation+3.668
Top resid features:
it
Token it
Feature activation+0.141
Top resid features:
gets
Token gets
Feature activation+0.205
Top resid features:
started
Token started
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
than
Token than
Feature activation-0.004
Top resid features:
ever
Token ever
Feature activation+0.032
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Before
TokenBefore
Feature activation+3.588
Top resid features:
the
Token the
Feature activation+0.113
Top resid features:
season
Token season
Feature activation+0.023
Top resid features:
began
Token began
Feature activation+0.068
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
truth
Tokentruth
Feature activation-0.005
Top resid features:
iness
Tokeniness
Feature activation-0.044
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ŀ
TokenĿ
Feature activation-0.029
Top resid features:
before
Token before
Feature activation+3.686
Top resid features:
it
Token it
Feature activation+0.099
Top resid features:
is
Token is
Feature activation+0.118
Top resid features:
allowed
Token allowed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.218
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
Shortly
TokenShortly
Feature activation-0.046
Top resid features:
before
Token before
Feature activation+3.434
Top resid features:
he
Token he
Feature activation+0.230
Top resid features:
was
Token was
Feature activation+0.066
Top resid features:
hospitalized
Token hospitalized
Feature activation+0.033
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
article
Token article
Feature activation-0.000
Top resid features:
last
Token last
Feature activation-0.011
Top resid features:
year
Token year
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
written
Token written
Feature activation+0.081
Top resid features:
before
Token before
Feature activation+3.430
Top resid features:
NYPD
Token NYPD
Feature activation-0.044
Top resid features:
officers
Token officers
Feature activation+0.070
Top resid features:
were
Token were
Feature activation+0.112
Top resid features:
amb
Token amb
Feature activation+0.000
Top resid features:
ushed
Tokenushed
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.014
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
found
Token found
Feature activation+0.001
Top resid features:
guilty
Token guilty
Feature activation-0.003
Top resid features:
well
Token well
Feature activation-0.033
Top resid features:
before
Token before
Feature activation+3.375
Top resid features:
the
Token the
Feature activation+0.126
Top resid features:
verdict
Token verdict
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.118
Top resid features:
announced
Token announced
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
heart
Token heart
Feature activation-0.006
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
darkness
Token darkness
Feature activation-0.025
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
But
Token But
Feature activation-0.039
Top resid features:
before
Token before
Feature activation+3.329
Top resid features:
she
Token she
Feature activation+0.177
Top resid features:
can
Token can
Feature activation+0.189
Top resid features:
leave
Token leave
Feature activation+0.020
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
apartment
Token apartment
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
In
TokenIn
Feature activation+0.038
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
memo
Token memo
Feature activation-0.012
Top resid features:
released
Token released
Feature activation+0.048
Top resid features:
before
Token before
Feature activation+3.188
Top resid features:
the
Token the
Feature activation+0.065
Top resid features:
sequ
Token sequ
Feature activation+0.030
Top resid features:
ester
Tokenester
Feature activation-0.004
Top resid features:
cuts
Token cuts
Feature activation-0.003
Top resid features:
went
Token went
Feature activation+0.189
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
success
Token success
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Get
Token Get
Feature activation+0.071
Top resid features:
yours
Token yours
Feature activation+0.073
Top resid features:
before
Token before
Feature activation+3.247
Top resid features:
they
Token they
Feature activation+0.176
Top resid features:
are
Token are
Feature activation-0.079
Top resid features:
gone
Token gone
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
class
Token class
Feature activation-0.047
Top resid features:
or
Token or
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
hall
Token hall
Feature activation-0.024
Top resid features:
ways
Tokenways
Feature activation-0.031
Top resid features:
before
Token before
Feature activation+3.238
Top resid features:
he
Token he
Feature activation+0.200
Top resid features:
started
Token started
Feature activation+0.049
Top resid features:
coding
Token coding
Feature activation+0.000
Top resid features:
club
Token club
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
law
Token law
Feature activation-0.013
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
year
Token year
Feature activation+0.007
Top resid features:
was
Token was
Feature activation+0.033
Top resid features:
created
Token created
Feature activation-0.014
Top resid features:
before
Token before
Feature activation+3.131
Top resid features:
the
Token the
Feature activation+0.122
Top resid features:
new
Token new
Feature activation+0.030
Top resid features:
nation
Token nation
Feature activation-0.007
Top resid features:
became
Token became
Feature activation+0.168
Top resid features:
independent
Token independent
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
financial
Token financial
Feature activation-0.028
Top resid features:
research
Token research
Feature activation-0.023
Top resid features:
firm
Token firm
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Before
Token Before
Feature activation+3.490
Top resid features:
hedge
Token hedge
Feature activation-0.041
Top resid features:
funds
Token funds
Feature activation-0.028
Top resid features:
began
Token began
Feature activation+0.107
Top resid features:
selling
Token selling
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.156
Top resid features:
Ċ
TokenĊ
Feature activation-0.047
Top resid features:
Ċ
TokenĊ
Feature activation-0.045
Top resid features:
"
Token"
Feature activation+0.110
Top resid features:
Before
TokenBefore
Feature activation+3.054
Top resid features:
she
Token she
Feature activation+0.335
Top resid features:
left
Token left
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
enclosure
Token enclosure
Feature activation-0.014
Top resid features:
for
Token for
Feature activation+0.025
Top resid features:
several
Token several
Feature activation-0.037
Top resid features:
hours
Token hours
Feature activation-0.036
Top resid features:
before
Token before
Feature activation+3.208
Top resid features:
police
Token police
Feature activation+0.146
Top resid features:
were
Token were
Feature activation+0.103
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
remove
Token remove
Feature activation+0.000
Top resid features:
We
TokenWe
Feature activation-0.028
Top resid features:
knew
Token knew
Feature activation-0.021
Top resid features:
about
Token about
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
campaign
Token campaign
Feature activation-0.091
Top resid features:
before
Token before
Feature activation+3.344
Top resid features:
it
Token it
Feature activation+0.126
Top resid features:
started
Token started
Feature activation+0.048
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
nature
Token nature
Feature activation-0.001
Top resid features:
live
Token live
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Before
TokenBefore
Feature activation+3.064
Top resid features:
B
Token B
Feature activation-0.031
Top resid features:
amboo
Tokenamboo
Feature activation-0.047
Top resid features:
can
Token can
Feature activation+0.299
Top resid features:
be
Token be
Feature activation+0.074
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
15
Token 15
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
five
Token five
Feature activation+0.038
Top resid features:
days
Token days
Feature activation+0.006
Top resid features:
before
Token before
Feature activation+3.024
Top resid features:
he
Token he
Feature activation+0.233
Top resid features:
was
Token was
Feature activation+0.148
Top resid features:
sworn
Token sworn
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.02

Head 2: 0.05

Head 3: 0.41

Head 4: 0.06

Head 5: 0.09

Head 6: 0.05

Head 7: 0.02

Head 8: 0.07

Head 9: 0.05

Head 10: 0.06

Head 11: 0.03

Positive logits

ordon1.31

ourning1.31

irens1.31

ropolis1.31

uberty1.28

oras1.28

acqu1.27

ushima1.25

strom1.24

itially1.21

agna1.21

Dise1.20

agate1.19

akia1.19

icted1.18

acon1.18

Bloomberg1.17

jen1.14

igon1.14

roma1.11

Negative logits

":"/-1.27

Syd-1.24

Tend-1.17

Stub-1.13

Offline-1.10

underdog-1.10

resilience-1.09

Yad-1.08

exacerbated-1.08

LOT-1.08

Christy-1.07

implication-1.07

Nanto-1.06

Cosponsors-1.05

nevertheless-1.05

Loren-1.05

android-1.05

Osw-1.05

gist-1.04

nonetheless-1.04

INTERVAL 2.790 - 3.099
CONTAINS 0.000%

the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
before
Token before
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+1.561
born
Token born
Feature activation+3.016
,
Token,
Feature activation+0.439
expanded
Token expanded
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
three
Token three
Feature activation+0.000
died
Token died
Feature activation+0.000
long
Token long
Feature activation+0.000
before
Token before
Feature activation+0.000
you
Token you
Feature activation+0.000
were
Token were
Feature activation+2.123
born
Token born
Feature activation+3.043
.
Token.
Feature activation+0.014
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
his
Token his
Feature activation+0.000
troops
Token troops
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
operation
Token operation
Feature activation+0.559
began
Token began
Feature activation+3.099
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
solar
Token solar
Feature activation+0.000
boom
Token boom
Feature activation+0.000
before
Token before
Feature activation+0.000
it
Token it
Feature activation+0.482
gets
Token gets
Feature activation+1.567
started
Token started
Feature activation+2.790
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Today
TokenToday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 2.480 - 2.790
CONTAINS 0.001%

guilty
Token guilty
Feature activation+0.000
well
Token well
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
verdict
Token verdict
Feature activation+0.519
was
Token was
Feature activation+2.512
announced
Token announced
Feature activation+1.913
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
adequately
Token adequately
Feature activation+0.000
,
Token,
Feature activation+0.000
written
Token written
Feature activation+0.000
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.585
officers
Token officers
Feature activation+0.365
were
Token were
Feature activation+2.535
amb
Token amb
Feature activation+0.116
ushed
Tokenushed
Feature activation+0.512
while
Token while
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Shortly
TokenShortly
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.772
was
Token was
Feature activation+1.986
hospitalized
Token hospitalized
Feature activation+2.567
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.000
garnered
Token garnered
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
began
Token began
Feature activation+2.699
,
Token,
Feature activation+0.621
most
Token most
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
fans
Token fans
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
before
Token before
Feature activation+0.000
she
Token she
Feature activation+0.951
can
Token can
Feature activation+1.427
leave
Token leave
Feature activation+2.504
her
Token her
Feature activation+0.046
apartment
Token apartment
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 2.170 - 2.480
CONTAINS 0.002%

really
Token really
Feature activation+0.000
bad
Token bad
Feature activation+0.000
off
Token off
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.499
died
Token died
Feature activation+2.235
...
Token...
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
really
Token really
Feature activation+0.000
bad
Token bad
Feature activation+0.000
site
Token site
Feature activation+0.000
,
Token,
Feature activation+0.000
before
Token before
Feature activation+0.000
plant
Token plant
Feature activation+0.134
remains
Token remains
Feature activation+0.506
were
Token were
Feature activation+2.233
collected
Token collected
Feature activation+1.096
through
Token through
Feature activation+0.000
s
Token s
Feature activation+0.000
ieves
Tokenieves
Feature activation+0.000
with
Token with
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
before
Token before
Feature activation+0.000
it
Token it
Feature activation+0.096
started
Token started
Feature activation+2.276
,
Token,
Feature activation+0.579
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
hours
Token hours
Feature activation+0.000
before
Token before
Feature activation+0.000
police
Token police
Feature activation+0.000
were
Token were
Feature activation+2.298
able
Token able
Feature activation+0.661
to
Token to
Feature activation+1.175
remove
Token remove
Feature activation+0.231
it
Token it
Feature activation+0.000
Tr
Token Tr
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
sequ
Token sequ
Feature activation+0.000
ester
Tokenester
Feature activation+0.000
cuts
Token cuts
Feature activation+1.244
went
Token went
Feature activation+2.442
into
Token into
Feature activation+0.736
effect
Token effect
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000

INTERVAL 1.860 - 2.170
CONTAINS 0.004%

I
TokenI
Feature activation+0.000
died
Token died
Feature activation+0.000
long
Token long
Feature activation+0.000
before
Token before
Feature activation+0.000
you
Token you
Feature activation+0.000
were
Token were
Feature activation+2.123
born
Token born
Feature activation+3.043
.
Token.
Feature activation+0.014
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
paper
Token paper
Feature activation+0.008
started
Token started
Feature activation+1.862
pe
Token pe
Feature activation+0.000
eling
Tokeneling
Feature activation+0.000
off
Token off
Feature activation+0.000
or
Token or
Feature activation+0.000
yellow
Token yellow
Feature activation+0.000
before
Token before
Feature activation+0.000
a
Token a
Feature activation+0.048
Barr
Token Barr
Feature activation+0.000
acks
Tokenacks
Feature activation+0.000
can
Token can
Feature activation+1.293
begin
Token begin
Feature activation+2.056
construction
Token construction
Feature activation+0.126
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Recently
TokenRecently
Feature activation+0.000
,
Token,
Feature activation+0.000
ed
Tokened
Feature activation+0.000
teeth
Token teeth
Feature activation+0.000
,
Token,
Feature activation+0.000
before
Token before
Feature activation+0.000
she
Token she
Feature activation+0.715
died
Token died
Feature activation+1.987
in
Token in
Feature activation+0.723
a
Token a
Feature activation+0.000
Cul
Token Cul
Feature activation+0.000
ross
Tokenross
Feature activation+0.000
jail
Token jail
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
the
Token the
Feature activation+0.000
program
Token program
Feature activation+0.044
comes
Token comes
Feature activation+1.960
up
Token up
Feature activation+0.549
for
Token for
Feature activation+0.420
re
Token re
Feature activation+0.000
author
Tokenauthor
Feature activation+0.000
ization
Tokenization
Feature activation+0.000

INTERVAL 1.550 - 1.860
CONTAINS 0.006%

and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
before
Token before
Feature activation+0.000
garbage
Token garbage
Feature activation+0.398
collection
Token collection
Feature activation+0.030
kicks
Token kicks
Feature activation+1.554
in
Token in
Feature activation+0.078
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
heap
Token heap
Feature activation+0.000
to
Token to
Feature activation+0.000
class
Token class
Feature activation+0.000
before
Token before
Feature activation+0.000
you
Token you
Feature activation+0.018
would
Token would
Feature activation+1.506
get
Token get
Feature activation+1.634
in
Token in
Feature activation+0.937
trouble
Token trouble
Feature activation+0.392
for
Token for
Feature activation+0.000
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
before
Token before
Feature activation+0.000
President
Token President
Feature activation+0.617
Obama
Token Obama
Feature activation+1.422
was
Token was
Feature activation+2.143
elected
Token elected
Feature activation+1.647
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
months
Token months
Feature activation+0.000
of
Token of
Feature activation+0.000
unrest
Token unrest
Feature activation+0.000
before
Token before
Feature activation+0.000
he
Token he
Feature activation+0.441
was
Token was
Feature activation+1.798
captured
Token captured
Feature activation+1.012
in
Token in
Feature activation+0.197
an
Token an
Feature activation+0.000
operation
Token operation
Feature activation+0.000
backed
Token backed
Feature activation+0.000
of
Token of
Feature activation+0.000
experience
Token experience
Feature activation+0.000
.
Token.
Feature activation+0.000
Before
Token Before
Feature activation+0.000
he
Token he
Feature activation+0.376
was
Token was
Feature activation+1.824
Walker
Token Walker
Feature activation+0.000
's
Token's
Feature activation+0.233
legal
Token legal
Feature activation+0.000
mouth
Token mouth
Feature activation+0.000
piece
Tokenpiece
Feature activation+0.000

INTERVAL 1.240 - 1.550
CONTAINS 0.006%

by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
board
Token board
Feature activation+0.000
before
Token before
Feature activation+0.000
becoming
Token becoming
Feature activation+0.233
official
Token official
Feature activation+1.534
,
Token,
Feature activation+0.612
went
Token went
Feature activation+1.220
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
as
Token as
Feature activation+0.000
too
Token too
Feature activation+0.000
long
Token long
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
book
Token book
Feature activation+0.000
makes
Token makes
Feature activation+1.255
it
Token it
Feature activation+0.390
to
Token to
Feature activation+0.154
print
Token print
Feature activation+0.000
unless
Token unless
Feature activation+0.000
I
Token I
Feature activation+0.000
or
Token or
Feature activation+0.000
two
Token two
Feature activation+0.000
[
Token [
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+1.390
out
Token out
Feature activation+0.155
],
Token],
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
'll
Token'll
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
months
Token months
Feature activation+0.000
before
Token before
Feature activation+0.000
they
Token they
Feature activation+0.616
go
Token go
Feature activation+1.519
through
Token through
Feature activation+0.686
the
Token the
Feature activation+0.000
W
Token W
Feature activation+0.000
CA
TokenCA
Feature activation+0.000
process
Token process
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
we
Token we
Feature activation+0.225
jump
Token jump
Feature activation+1.381
into
Token into
Feature activation+1.491
concrete
Token concrete
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
existing
Token existing
Feature activation+0.000
Haskell
Token Haskell
Feature activation+0.000

INTERVAL 0.930 - 1.240
CONTAINS 0.010%

before
Token before
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.116
s
Tokens
Feature activation+0.019
gone
Token gone
Feature activation+1.120
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
and
Token and
Feature activation+0.000
adequate
Token adequate
Feature activation+0.000
warning
Token warning
Feature activation+0.000
before
Token before
Feature activation+0.000
sudden
Token sudden
Feature activation+0.000
releases
Token releases
Feature activation+1.149
of
Token of
Feature activation+0.124
waters
Token waters
Feature activation+0.320
may
Token may
Feature activation+0.386
save
Token save
Feature activation+0.234
lives
Token lives
Feature activation+0.000
release
Token release
Feature activation+0.000
just
Token just
Feature activation+0.000
days
Token days
Feature activation+0.000
before
Token before
Feature activation+0.000
Christmas
Token Christmas
Feature activation+0.620
,
Token,
Feature activation+0.994
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
before
Token before
Feature activation+0.091
to
Token to
Feature activation+1.274
have
Token have
Feature activation+0.778
been
Token been
Feature activation+0.967
part
Token part
Feature activation+0.329
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
crew
Token crew
Feature activation+0.000
,
Token,
Feature activation+0.000
least
Token least
Feature activation+0.000
6
Token 6
Feature activation+0.000
months
Token months
Feature activation+0.000
before
Token before
Feature activation+0.000
I
Token I
Feature activation+0.731
climbed
Token climbed
Feature activation+0.930
back
Token back
Feature activation+0.326
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.052
cliff
Token cliff
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.620 - 0.930
CONTAINS 0.017%

weapon
Token weapon
Feature activation+0.000
before
Token before
Feature activation+0.000
his
Token his
Feature activation+0.000
friend
Token friend
Feature activation+0.089
took
Token took
Feature activation+1.773
it
Token it
Feature activation+0.764
back
Token back
Feature activation+0.000
and
Token and
Feature activation+0.000
st
Token st
Feature activation+0.000
ashed
Tokenashed
Feature activation+0.000
it
Token it
Feature activation+0.000
their
Token their
Feature activation+0.000
papers
Token papers
Feature activation+0.000
before
Token before
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.693
enter
Token enter
Feature activation+0.887
Germany
Token Germany
Feature activation+0.000
since
Token since
Feature activation+0.000
they
Token they
Feature activation+0.000
reveal
Token reveal
Feature activation+0.000
information
Token information
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
before
Token before
Feature activation+0.000
leaving
Token leaving
Feature activation+0.525
it
Token it
Feature activation+0.771
to
Token to
Feature activation+0.369
Bush
Token Bush
Feature activation+0.391
&
Token &
Feature activation+0.000
Co
Token Co
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
before
Token before
Feature activation+0.000
midday
Token midday
Feature activation+0.000
he
Token he
Feature activation+0.894
was
Token was
Feature activation+1.613
taken
Token taken
Feature activation+0.822
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
festival
Token festival
Feature activation+0.000
's
Token's
Feature activation+0.000
was
Token was
Feature activation+0.000
undergoing
Token undergoing
Feature activation+0.000
examinations
Token examinations
Feature activation+0.000
before
Token before
Feature activation+0.000
being
Token being
Feature activation+0.000
operated
Token operated
Feature activation+0.861
on
Token on
Feature activation+0.195
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000

INTERVAL 0.310 - 0.620
CONTAINS 0.030%

in
Token in
Feature activation+0.000
good
Token good
Feature activation+0.000
spirits
Token spirits
Feature activation+0.000
even
Token even
Feature activation+0.000
before
Token before
Feature activation+0.000
she
Token she
Feature activation+0.537
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
stars
Tokenstars
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Please
Token Please
Feature activation+0.000
register
Token register
Feature activation+0.000
before
Token before
Feature activation+0.000
29
Token 29
Feature activation+0.432
August
Token August
Feature activation+0.382
2017
Token 2017
Feature activation+0.907
if
Token if
Feature activation+0.141
you
Token you
Feature activation+0.000
wish
Token wish
Feature activation+0.000
-
Token -
Feature activation+0.000
Before
Token Before
Feature activation+0.000
Ch
Token Ch
Feature activation+0.283
ander
Tokenander
Feature activation+0.769
p
Tokenp
Feature activation+0.581
aul
Tokenaul
Feature activation+0.449
and
Token and
Feature activation+0.186
the
Token the
Feature activation+0.037
Ch
Token Ch
Feature activation+0.000
ander
Tokenander
Feature activation+0.000
p
Tokenp
Feature activation+0.000
But
Token But
Feature activation+0.000
like
Token like
Feature activation+0.000
before
Token before
Feature activation+0.000
my
Token my
Feature activation+0.000
level
Token level
Feature activation+0.000
didn
Token didn
Feature activation+0.554
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
show
Token show
Feature activation+0.000
itself
Token itself
Feature activation+0.000
before
Token before
Feature activation+0.000
sudden
Token sudden
Feature activation+0.000
releases
Token releases
Feature activation+1.149
of
Token of
Feature activation+0.124
waters
Token waters
Feature activation+0.320
may
Token may
Feature activation+0.386
save
Token save
Feature activation+0.234
lives
Token lives
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.000 - 0.310
CONTAINS 99.926%

orn
Tokenorn
Feature activation+0.000
om
Tokenom
Feature activation+0.000
u
Token u
Feature activation+0.000
red
Tokenred
Feature activation+0.000
nik
Tokennik
Feature activation+0.000
u
Tokenu
Feature activation+0.000
inform
Token inform
Feature activation+0.000
at
Tokenat
Feature activation+0.000
iv
Tokeniv
Feature activation+0.000
n
Tokenn
Feature activation+0.000
og
Tokenog
Feature activation+0.000
Effects
Token Effects
Feature activation+0.000
are
Token are
Feature activation+0.000
extremely
Token extremely
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
important
Token important
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
designers
Token designers
Feature activation+0.000
Are
Token Are
Feature activation+0.000
there
Token there
Feature activation+0.000
local
Token local
Feature activation+0.000
variables
Token variables
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
lying
Token lying
Feature activation+0.000
around
Token around
Feature activation+0.000
with
Token with
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
along
Token along
Feature activation+0.000
that
Token that
Feature activation+0.000
helps
Token helps
Feature activation+0.000
us
Token us
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
systematic
Token systematic
Feature activation+0.000
excavation
Token excavation
Feature activation+0.000
and
Token and
Feature activation+0.000
allows
Token allows
Feature activation+0.000
State
Token State
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
.
Token.
Feature activation+0.000
Still
Token Still
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
some
Token some
Feature activation+0.000
information
Token information
Feature activation+0.000
about
Token about
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 7 in H2.3: (feature 10363)

TOP ACTIVATIONS
MAX = 2.572

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.302
expected
Token expected
Feature activation+2.572
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.114
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
control
Token control
Feature activation+0.000
than
Token than
Feature activation+0.000
previously
Token previously
Feature activation+1.538
thought
Token thought
Feature activation+2.436
,
Token,
Feature activation+0.156
say
Token say
Feature activation+0.521
scientists
Token scientists
Feature activation+0.098
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
more
Token more
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.681
could
Token could
Feature activation+2.008
imagine
Token imagine
Feature activation+2.295
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ch
TokenCh
Feature activation+0.000
annels
Tokenannels
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
BBC
Token BBC
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.971
would
Token would
Feature activation+2.276
split
Token split
Feature activation+0.995
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
Kingdom
Token Kingdom
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
more
Token more
Feature activation+0.000
nutrition
Token nutrition
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+1.299
can
Token can
Feature activation+2.271
receive
Token receive
Feature activation+0.406
from
Token from
Feature activation+0.000
breast
Token breast
Feature activation+0.000
milk
Token milk
Feature activation+0.000
alone
Token alone
Feature activation+0.000
providing
Token providing
Feature activation+0.000
more
Token more
Feature activation+0.000
nitrogen
Token nitrogen
Feature activation+0.000
than
Token than
Feature activation+0.000
is
Token is
Feature activation+1.164
needed
Token needed
Feature activation+2.239
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Download
TokenDownload
Feature activation+0.000
my
Token my
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
galaxy
Token galaxy
Feature activation+0.000
than
Token than
Feature activation+0.000
we
Token we
Feature activation+0.767
thought
Token thought
Feature activation+2.223
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
planets
Token planets
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
with
Token with
Feature activation+0.000
Thur
Token Thur
Feature activation+0.000
man
Tokenman
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.283
am
Token am
Feature activation+2.215
with
Token with
Feature activation+1.301
Er
Token Er
Feature activation+0.027
rol
Tokenrol
Feature activation+0.000
,
Token,
Feature activation+0.000
being
Token being
Feature activation+0.000
dangerous
Token dangerous
Feature activation+0.000
for
Token for
Feature activation+0.000
journalists
Token journalists
Feature activation+0.000
than
Token than
Feature activation+0.053
they
Token they
Feature activation+1.596
were
Token were
Feature activation+2.163
before
Token before
Feature activation+1.438
the
Token the
Feature activation+0.000
up
Token up
Feature activation+0.000
ris
Tokenris
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
acquiring
Token acquiring
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000
faster
Token faster
Feature activation+0.000
than
Token than
Feature activation+0.000
we
Token we
Feature activation+1.275
can
Token can
Feature activation+2.114
introduce
Token introduce
Feature activation+0.702
new
Token new
Feature activation+0.000
antibiotics
Token antibiotics
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Lewis
Token Lewis
Feature activation+0.000
to
Token to
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
than
Token than
Feature activation+0.000
We
Token We
Feature activation+0.755
Thought
Token Thought
Feature activation+2.104
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ocene
Tokenocene
Feature activation+0.000
reading
Token reading
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.420
had
Token had
Feature activation+1.686
ever
Token ever
Feature activation+2.083
done
Token done
Feature activation+1.958
before
Token before
Feature activation+1.199
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
just
Token just
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
complicated
Token complicated
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+1.451
looks
Token looks
Feature activation+2.074
.
Token.
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
C
Token C
Feature activation+0.000
aj
Tokenaj
Feature activation+0.000
below
Token below
Feature activation+0.000
more
Token more
Feature activation+0.000
water
Token water
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.741
could
Token could
Feature activation+2.074
ever
Token ever
Feature activation+1.738
imagine
Token imagine
Feature activation+2.002
gravity
Token gravity
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
to
Token to
Feature activation+0.000
into
Token into
Feature activation+0.000
meltdown
Token meltdown
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
than
Token than
Feature activation+0.000
previously
Token previously
Feature activation+1.351
thought
Token thought
Feature activation+2.070
when
Token when
Feature activation+0.209
the
Token the
Feature activation+0.000
earthquake
Token earthquake
Feature activation+0.000
and
Token and
Feature activation+0.000
tsunami
Token tsunami
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
lighter
Token lighter
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.750
expected
Token expected
Feature activation+2.054
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.069
can
Token can
Feature activation+0.501
always
Token always
Feature activation+0.009
re
Token re
Feature activation+0.000
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.201
ever
Token ever
Feature activation+1.448
could
Token could
Feature activation+2.043
have
Token have
Feature activation+1.273
imagined
Token imagined
Feature activation+1.717
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
more
Token more
Feature activation+0.000
often
Token often
Feature activation+0.000
than
Token than
Feature activation+0.000
not
Token not
Feature activation+0.636
must
Token must
Feature activation+1.097
be
Token be
Feature activation+2.031
combined
Token combined
Feature activation+1.040
with
Token with
Feature activation+0.261
another
Token another
Feature activation+0.000
genre
Token genre
Feature activation+0.000
.
Token.
Feature activation+0.000
health
Token health
Feature activation+0.000
than
Token than
Feature activation+0.000
we
Token we
Feature activation+1.237
had
Token had
Feature activation+1.698
previously
Token previously
Feature activation+1.724
imagined
Token imagined
Feature activation+2.030
.
Token.
Feature activation+0.000
Again
Token Again
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
correct
Token correct
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+1.151
were
Token were
Feature activation+2.021
in
Token in
Feature activation+0.777
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
endemic
Token endemic
Feature activation+0.000
pitcher
Token pitcher
Feature activation+0.000

Top DFA by src position
MAX = 2.634

<|endoftext|>
Token<|endoftext|>
Feature activation+0.125
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
more
Token more
Feature activation+0.024
Top resid features:
than
Token than
Feature activation+2.606
Top resid features:
I
Token I
Feature activation+0.322
Top resid features:
expected
Token expected
Feature activation-0.084
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ads
Tokenads
Feature activation-0.001
Top resid features:
may
Token may
Feature activation+0.064
Top resid features:
have
Token have
Feature activation+0.007
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
control
Token control
Feature activation+0.024
Top resid features:
than
Token than
Feature activation+2.540
Top resid features:
previously
Token previously
Feature activation+0.177
Top resid features:
thought
Token thought
Feature activation-0.020
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
scientists
Token scientists
Feature activation+0.000
Top resid features:
filled
Token filled
Feature activation-0.007
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
even
Token even
Feature activation+0.011
Top resid features:
more
Token more
Feature activation-0.013
Top resid features:
wonder
Token wonder
Feature activation-0.045
Top resid features:
than
Token than
Feature activation+2.288
Top resid features:
you
Token you
Feature activation+0.121
Top resid features:
could
Token could
Feature activation+0.253
Top resid features:
imagine
Token imagine
Feature activation+0.056
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.013
Top resid features:
split
Token split
Feature activation+0.045
Top resid features:
up
Token up
Feature activation-0.021
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
BBC
Token BBC
Feature activation+0.021
Top resid features:
than
Token than
Feature activation+2.294
Top resid features:
I
Token I
Feature activation+0.111
Top resid features:
would
Token would
Feature activation+0.111
Top resid features:
split
Token split
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.156
Top resid features:
more
Token more
Feature activation+0.079
Top resid features:
nutrition
Token nutrition
Feature activation-0.041
Top resid features:
than
Token than
Feature activation+2.634
Top resid features:
they
Token they
Feature activation-0.182
Top resid features:
can
Token can
Feature activation+0.061
Top resid features:
receive
Token receive
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
breast
Token breast
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
avoid
Token avoid
Feature activation-0.030
Top resid features:
providing
Token providing
Feature activation+0.015
Top resid features:
more
Token more
Feature activation-0.055
Top resid features:
nitrogen
Token nitrogen
Feature activation+0.033
Top resid features:
than
Token than
Feature activation+2.396
Top resid features:
is
Token is
Feature activation+0.364
Top resid features:
needed
Token needed
Feature activation-0.060
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
habitable
Token habitable
Feature activation+0.041
Top resid features:
worlds
Token worlds
Feature activation-0.020
Top resid features:
in
Token in
Feature activation+0.094
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
galaxy
Token galaxy
Feature activation-0.003
Top resid features:
than
Token than
Feature activation+2.263
Top resid features:
we
Token we
Feature activation+0.230
Top resid features:
thought
Token thought
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
little
Token little
Feature activation-0.026
Top resid features:
more
Token more
Feature activation-0.010
Top resid features:
with
Token with
Feature activation+0.075
Top resid features:
Thur
Token Thur
Feature activation-0.014
Top resid features:
man
Tokenman
Feature activation+0.002
Top resid features:
than
Token than
Feature activation+2.339
Top resid features:
I
Token I
Feature activation+0.105
Top resid features:
am
Token am
Feature activation+0.098
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Er
Token Er
Feature activation+0.000
Top resid features:
rol
Tokenrol
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.023
Top resid features:
more
Token more
Feature activation-0.010
Top resid features:
dangerous
Token dangerous
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.040
Top resid features:
journalists
Token journalists
Feature activation+0.004
Top resid features:
than
Token than
Feature activation+2.374
Top resid features:
they
Token they
Feature activation-0.045
Top resid features:
were
Token were
Feature activation+0.150
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
ogens
Tokenogens
Feature activation-0.023
Top resid features:
are
Token are
Feature activation+0.020
Top resid features:
acquiring
Token acquiring
Feature activation+0.011
Top resid features:
resistance
Token resistance
Feature activation+0.020
Top resid features:
faster
Token faster
Feature activation+0.125
Top resid features:
than
Token than
Feature activation+2.240
Top resid features:
we
Token we
Feature activation-0.010
Top resid features:
can
Token can
Feature activation+0.138
Top resid features:
introduce
Token introduce
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
antibiotics
Token antibiotics
Feature activation+0.000
Top resid features:
V
Token V
Feature activation-0.012
Top resid features:
ulnerable
Tokenulnerable
Feature activation-0.010
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
Mel
Token Mel
Feature activation-0.004
Top resid features:
ting
Tokenting
Feature activation-0.009
Top resid features:
than
Token than
Feature activation+2.347
Top resid features:
We
Token We
Feature activation+0.238
Top resid features:
Thought
Token Thought
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Pl
TokenPl
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.008
Top resid features:
found
Token found
Feature activation+0.025
Top resid features:
myself
Token myself
Feature activation-0.005
Top resid features:
reading
Token reading
Feature activation+0.011
Top resid features:
more
Token more
Feature activation-0.081
Top resid features:
than
Token than
Feature activation+2.113
Top resid features:
I
Token I
Feature activation+0.128
Top resid features:
had
Token had
Feature activation+0.341
Top resid features:
ever
Token ever
Feature activation-0.002
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
skulls
Token skulls
Feature activation+0.018
Top resid features:
is
Token is
Feature activation+0.069
Top resid features:
even
Token even
Feature activation-0.010
Top resid features:
more
Token more
Feature activation-0.035
Top resid features:
complicated
Token complicated
Feature activation+0.025
Top resid features:
than
Token than
Feature activation+2.258
Top resid features:
it
Token it
Feature activation+0.070
Top resid features:
looks
Token looks
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Thanks
Token Thanks
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
below
Token below
Feature activation+0.039
Top resid features:
more
Token more
Feature activation+0.032
Top resid features:
water
Token water
Feature activation+0.006
Top resid features:
than
Token than
Feature activation+2.069
Top resid features:
you
Token you
Feature activation+0.122
Top resid features:
could
Token could
Feature activation+0.159
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
imagine
Token imagine
Feature activation+0.000
Top resid features:
gravity
Token gravity
Feature activation+0.000
Top resid features:
reactors
Token reactors
Feature activation-0.012
Top resid features:
went
Token went
Feature activation+0.029
Top resid features:
into
Token into
Feature activation-0.009
Top resid features:
meltdown
Token meltdown
Feature activation+0.047
Top resid features:
earlier
Token earlier
Feature activation+0.081
Top resid features:
than
Token than
Feature activation+2.131
Top resid features:
previously
Token previously
Feature activation+0.160
Top resid features:
thought
Token thought
Feature activation+0.030
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
earthquake
Token earthquake
Feature activation+0.000
Top resid features:
turns
Token turns
Feature activation+0.000
Top resid features:
out
Token out
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
be
Token be
Feature activation+0.027
Top resid features:
lighter
Token lighter
Feature activation-0.017
Top resid features:
than
Token than
Feature activation+2.179
Top resid features:
you
Token you
Feature activation+0.234
Top resid features:
expected
Token expected
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.039
Top resid features:
more
Token more
Feature activation-0.007
Top resid features:
truth
Token truth
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
it
Token it
Feature activation-0.014
Top resid features:
than
Token than
Feature activation+2.017
Top resid features:
I
Token I
Feature activation+0.097
Top resid features:
ever
Token ever
Feature activation+0.113
Top resid features:
could
Token could
Feature activation+0.158
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
imagined
Token imagined
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.053
Top resid features:
science
Token science
Feature activation-0.018
Top resid features:
fiction
Token fiction
Feature activation-0.004
Top resid features:
more
Token more
Feature activation-0.062
Top resid features:
often
Token often
Feature activation-0.004
Top resid features:
than
Token than
Feature activation+2.061
Top resid features:
not
Token not
Feature activation+0.014
Top resid features:
must
Token must
Feature activation+0.402
Top resid features:
be
Token be
Feature activation+0.025
Top resid features:
combined
Token combined
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
term
Tokenterm
Feature activation-0.012
Top resid features:
threat
Token threat
Feature activation-0.019
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
adult
Token adult
Feature activation-0.022
Top resid features:
health
Token health
Feature activation-0.027
Top resid features:
than
Token than
Feature activation+2.161
Top resid features:
we
Token we
Feature activation+0.092
Top resid features:
had
Token had
Feature activation+0.140
Top resid features:
previously
Token previously
Feature activation+0.141
Top resid features:
imagined
Token imagined
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
he
Token he
Feature activation+0.043
Top resid features:
ms
Tokenms
Feature activation-0.005
Top resid features:
ley
Tokenley
Feature activation-0.007
Top resid features:
ana
Tokenana
Feature activation-0.017
Top resid features:
than
Token than
Feature activation+2.377
Top resid features:
they
Token they
Feature activation-0.140
Top resid features:
were
Token were
Feature activation+0.139
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.02

Head 2: 0.08

Head 3: 0.40

Head 4: 0.07

Head 5: 0.09

Head 6: 0.03

Head 7: 0.02

Head 8: 0.06

Head 9: 0.05

Head 10: 0.06

Head 11: 0.02

Positive logits

SourceFile1.47

DERR1.28

tallest1.27

Integer1.26

utenberg1.24

predec1.21

chop1.18

closest1.18

ecause1.15

iane1.14

ISA1.13

unfold1.12

traditionally1.12

liest1.12

igree1.11

ymph1.11

Root1.11

amaru1.11

yip1.09

verages1.09

Negative logits

teamed-1.13

itan-1.11

Goff-1.07

-1.07

Arcade-1.05

HER-1.05

Chevy-1.05

McA-1.05

Playoff-1.04

VG-1.04

short-1.03

commencement-1.03

assisted-1.03

jection-1.03

-1.02

Sullivan-1.01

XII-1.01

Plymouth-1.00

QC-1.00

Locked-1.00

INTERVAL 2.315 - 2.572
CONTAINS 0.000%

have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
control
Token control
Feature activation+0.000
than
Token than
Feature activation+0.000
previously
Token previously
Feature activation+1.538
thought
Token thought
Feature activation+2.436
,
Token,
Feature activation+0.156
say
Token say
Feature activation+0.521
scientists
Token scientists
Feature activation+0.098
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.302
expected
Token expected
Feature activation+2.572
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.114
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 2.058 - 2.315
CONTAINS 0.001%

dangerous
Token dangerous
Feature activation+0.000
for
Token for
Feature activation+0.000
journalists
Token journalists
Feature activation+0.000
than
Token than
Feature activation+0.053
they
Token they
Feature activation+1.596
were
Token were
Feature activation+2.163
before
Token before
Feature activation+1.438
the
Token the
Feature activation+0.000
up
Token up
Feature activation+0.000
ris
Tokenris
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
reading
Token reading
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.420
had
Token had
Feature activation+1.686
ever
Token ever
Feature activation+2.083
done
Token done
Feature activation+1.958
before
Token before
Feature activation+1.199
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
just
Token just
Feature activation+0.000
into
Token into
Feature activation+0.000
meltdown
Token meltdown
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
than
Token than
Feature activation+0.000
previously
Token previously
Feature activation+1.351
thought
Token thought
Feature activation+2.070
when
Token when
Feature activation+0.209
the
Token the
Feature activation+0.000
earthquake
Token earthquake
Feature activation+0.000
and
Token and
Feature activation+0.000
tsunami
Token tsunami
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
more
Token more
Feature activation+0.000
nutrition
Token nutrition
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+1.299
can
Token can
Feature activation+2.271
receive
Token receive
Feature activation+0.406
from
Token from
Feature activation+0.000
breast
Token breast
Feature activation+0.000
milk
Token milk
Feature activation+0.000
alone
Token alone
Feature activation+0.000
to
Token to
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
than
Token than
Feature activation+0.000
We
Token We
Feature activation+0.755
Thought
Token Thought
Feature activation+2.104
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ocene
Tokenocene
Feature activation+0.000

INTERVAL 1.800 - 2.058
CONTAINS 0.004%

more
Token more
Feature activation+0.000
often
Token often
Feature activation+0.000
than
Token than
Feature activation+0.000
not
Token not
Feature activation+0.636
must
Token must
Feature activation+1.097
be
Token be
Feature activation+2.031
combined
Token combined
Feature activation+1.040
with
Token with
Feature activation+0.261
another
Token another
Feature activation+0.000
genre
Token genre
Feature activation+0.000
.
Token.
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
complicated
Token complicated
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+1.038
appears
Token appears
Feature activation+1.875
,
Token,
Feature activation+0.394
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.094
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
more
Token more
Feature activation+0.000
problems
Token problems
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+1.426
's
Token's
Feature activation+1.061
worth
Token worth
Feature activation+1.967
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
water
Token water
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.741
could
Token could
Feature activation+2.074
ever
Token ever
Feature activation+1.738
imagine
Token imagine
Feature activation+2.002
gravity
Token gravity
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
to
Token to
Feature activation+0.000
rise
Token rise
Feature activation+0.000
above
Token above
Feature activation+0.000
impact
Token impact
Feature activation+0.000
than
Token than
Feature activation+0.000
conventional
Token conventional
Feature activation+0.436
sweet
Token sweet
Feature activation+0.000
crude
Token crude
Feature activation+0.000
are
Token are
Feature activation+1.822
just
Token just
Feature activation+0.142
not
Token not
Feature activation+0.190
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
Atmospheric
Token Atmospheric
Feature activation+0.000

INTERVAL 1.543 - 1.800
CONTAINS 0.004%

times
Token times
Feature activation+0.000
higher
Token higher
Feature activation+0.000
today
Token today
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.608
was
Token was
Feature activation+1.706
in
Token in
Feature activation+0.686
1960
Token 1960
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
legislative
Token legislative
Feature activation+0.000
much
Token much
Feature activation+0.000
faster
Token faster
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.899
could
Token could
Feature activation+1.814
do
Token do
Feature activation+1.686
with
Token with
Feature activation+0.893
D
Token D
Feature activation+0.000
3
Token3
Feature activation+0.000
D
TokenD
Feature activation+0.000
9
Token9
Feature activation+0.000
admitting
Token admitting
Feature activation+0.000
privileges
Token privileges
Feature activation+0.000
requirements
Token requirements
Feature activation+0.000
than
Token than
Feature activation+0.000
were
Token were
Feature activation+1.861
indicated
Token indicated
Feature activation+1.680
during
Token during
Feature activation+0.004
Wednesday
Token Wednesday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
million
Tokenmillion
Feature activation+0.000
more
Token more
Feature activation+0.000
red
Token red
Feature activation+0.000
ink
Token ink
Feature activation+0.000
than
Token than
Feature activation+0.000
was
Token was
Feature activation+1.684
forecast
Token forecast
Feature activation+1.900
in
Token in
Feature activation+0.692
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+0.000
budget
Token budget
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
more
Token more
Feature activation+0.000
convinced
Token convinced
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+1.547
that
Token that
Feature activation+0.223
Texas
Token Texas
Feature activation+0.000
is
Token is
Feature activation+0.949
trending
Token trending
Feature activation+0.000
our
Token our
Feature activation+0.000

INTERVAL 1.286 - 1.543
CONTAINS 0.006%

more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+1.068
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.780
heard
Token heard
Feature activation+1.360
on
Token on
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
energetic
Token energetic
Feature activation+0.000
play
Token play
Feature activation+0.000
behaviors
Token behaviors
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+1.278
normally
Token normally
Feature activation+1.318
do
Token do
Feature activation+1.903
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
more
Token more
Feature activation+0.000
stringent
Token stringent
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+1.354
before
Token before
Feature activation+1.379
in
Token in
Feature activation+0.032
its
Token its
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
)
Token)
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.102
believe
Token believe
Feature activation+1.491
that
Token that
Feature activation+0.102
my
Token my
Feature activation+0.000
son
Token son
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
serious
Token serious
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.922
is
Token is
Feature activation+1.948
now
Token now
Feature activation+1.448
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Scar
TokenScar
Feature activation+0.000
borough
Tokenborough
Feature activation+0.000

INTERVAL 1.029 - 1.286
CONTAINS 0.008%

them
Token them
Feature activation+0.000
less
Token less
Feature activation+0.000
valuable
Token valuable
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.894
used
Token used
Feature activation+1.112
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.803
for
Token for
Feature activation+0.000
players
Token players
Feature activation+0.000
and
Token and
Feature activation+0.000
blacks
Token blacks
Feature activation+0.000
have
Token have
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+1.101
deserve
Token deserve
Feature activation+1.089
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Meanwhile
TokenMeanwhile
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+1.296
are
Token are
Feature activation+1.408
aware
Token aware
Feature activation+1.132
that
Token that
Feature activation+0.185
Planned
Token Planned
Feature activation+0.000
Parenthood
Token Parenthood
Feature activation+0.000
provides
Token provides
Feature activation+0.000
breast
Token breast
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
Jeremy
Token Jeremy
Feature activation+0.000
Lin
Token Lin
Feature activation+0.000
stood
Token stood
Feature activation+1.079
to
Token to
Feature activation+0.089
make
Token make
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
it
Token it
Feature activation+0.000
)
Token)
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+1.102
believe
Token believe
Feature activation+1.491
that
Token that
Feature activation+0.102
my
Token my
Feature activation+0.000
son
Token son
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.772 - 1.029
CONTAINS 0.009%

superflu
Token superflu
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
reason
Token reason
Feature activation+0.000
than
Token than
Feature activation+0.000
to
Token to
Feature activation+0.385
believe
Token believe
Feature activation+1.027
that
Token that
Feature activation+0.000
that
Token that
Feature activation+0.000
man
Token man
Feature activation+0.000
stuck
Token stuck
Feature activation+0.000
his
Token his
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
for
Token for
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.793
costs
Token costs
Feature activation+0.443
to
Token to
Feature activation+0.389
install
Token install
Feature activation+0.000
hot
Token hot
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
less
Token less
Feature activation+0.000
compassionate
Token compassionate
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.961
would
Token would
Feature activation+2.003
have
Token have
Feature activation+1.044
been
Token been
Feature activation+1.762
with
Token with
Feature activation+0.818
you
Token you
Feature activation+0.051
things
Token things
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.580
do
Token do
Feature activation+1.115
and
Token and
Feature activation+0.180
is
Token is
Feature activation+0.929
intent
Token intent
Feature activation+0.193
on
Token on
Feature activation+0.000
setting
Token setting
Feature activation+0.000
you
Token you
Feature activation+0.000
straight
Token straight
Feature activation+0.000
is
Token is
Feature activation+0.000
faster
Token faster
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+1.296
and
Token and
Feature activation+0.405
we
Token we
Feature activation+0.852
are
Token are
Feature activation+1.514
still
Token still
Feature activation+0.535
in
Token in
Feature activation+0.319
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000

INTERVAL 0.514 - 0.772
CONTAINS 0.013%

tested
Token tested
Feature activation+0.000
was
Token was
Feature activation+0.000
something
Token something
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.000
advertised
Token advertised
Feature activation+0.714
.
Token.
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
labeled
Token labeled
Feature activation+0.000
sn
Token sn
Feature activation+0.000
apper
Tokenapper
Feature activation+0.000
that
Token that
Feature activation+0.000
looks
Token looks
Feature activation+0.000
more
Token more
Feature activation+0.000
cohesive
Token cohesive
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.770
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
the
Token the
Feature activation+0.000
they
Token they
Feature activation+0.000
mean
Token mean
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
m
Token m
Feature activation+0.184
umbling
Tokenumbling
Feature activation+0.539
a
Token a
Feature activation+0.000
Hail
Token Hail
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
before
Token before
Feature activation+0.000
voting
Token voting
Feature activation+0.000
ulnerable
Tokenulnerable
Feature activation+0.000
to
Token to
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
than
Token than
Feature activation+0.000
We
Token We
Feature activation+0.755
Thought
Token Thought
Feature activation+2.104
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
i
Tokeni
Feature activation+0.000
than
Token than
Feature activation+0.000
Jim
Token Jim
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ever
Token ever
Feature activation+0.632
did
Token did
Feature activation+1.347
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
will
Token will
Feature activation+0.000
win
Token win
Feature activation+0.000

INTERVAL 0.257 - 0.514
CONTAINS 0.020%

s
Tokens
Feature activation+0.000
notorious
Token notorious
Feature activation+0.000
mess
Token mess
Feature activation+0.000
than
Token than
Feature activation+0.000
still
Token still
Feature activation+0.131
somehow
Token somehow
Feature activation+0.332
flies
Token flies
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
radar
Token radar
Feature activation+0.000
).
Token).
Feature activation+0.000
than
Token than
Feature activation+0.000
175
Token 175
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
signatures
Token signatures
Feature activation+0.000
have
Token have
Feature activation+0.294
been
Token been
Feature activation+0.734
collected
Token collected
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
group
Token group
Feature activation+0.000
be
Token be
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
more
Tokenmore
Feature activation+0.000
than
Token than
Feature activation+0.000
happy
Token happy
Feature activation+0.442
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
testify
Token testify
Feature activation+0.111
to
Token to
Feature activation+0.000
his
Tokenhis
Feature activation+0.000
are
Token are
Feature activation+0.000
doing
Token doing
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
all
Token all
Feature activation+0.461
these
Token these
Feature activation+0.028
put
Token put
Feature activation+0.000
together
Token together
Feature activation+0.000
to
Token to
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000
engagement
Token engagement
Feature activation+0.000
on
Token on
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
than
Token than
Feature activation+0.000
real
Token real
Feature activation+0.321
news
Token news
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
elections
Token elections
Feature activation+0.000
drew
Token drew
Feature activation+0.000

INTERVAL 0.000 - 0.257
CONTAINS 99.934%

seat
Token seat
Feature activation+0.000
so
Token so
Feature activation+0.000
he
Token he
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
't
Token't
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+0.000
baby
Token baby
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
they
Token they
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
software
Token software
Feature activation+0.000
like
Token like
Feature activation+0.000
Kickstarter
Token Kickstarter
Feature activation+0.000
and
Token and
Feature activation+0.000
Ind
Token Ind
Feature activation+0.000
ieg
Tokenieg
Feature activation+0.000
ogo
Tokenogo
Feature activation+0.000
have
Token have
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
head
Token head
Feature activation+0.000
coach
Token coach
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Several
TokenSeveral
Feature activation+0.000
league
Token league
Feature activation+0.000
sources
Token sources
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
Brooks
Token Brooks
Feature activation+0.000
Morning
Token Morning
Feature activation+0.000
Consult
Token Consult
Feature activation+0.000
Co
Token Co
Feature activation+0.000
-
Token-
Feature activation+0.000
Found
TokenFound
Feature activation+0.000
er
Tokener
Feature activation+0.000
and
Token and
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Research
Token Research
Feature activation+0.000
Officer
Token Officer
Feature activation+0.000
Kyle
Token Kyle
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 H2.3: (feature 10071)

TOP ACTIVATIONS
MAX = 3.062

I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+0.267
I
Token I
Feature activation+1.117
want
Token want
Feature activation+3.062
.
Token.
Feature activation+0.440
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
've
Token've
Feature activation+0.000
never
Token never
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.795
want
Token want
Feature activation+2.848
on
Token on
Feature activation+1.012
top
Token top
Feature activation+0.462
of
Token of
Feature activation+0.766
your
Token your
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
can
Token can
Feature activation+0.000
literally
Token literally
Feature activation+0.000
broadcast
Token broadcast
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.720
want
Token want
Feature activation+2.822
to
Token to
Feature activation+1.899
say
Token say
Feature activation+2.721
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.114
whole
Token whole
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
say
Token say
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.624
want
Token want
Feature activation+2.754
to
Token to
Feature activation+1.861
him
Token him
Feature activation+0.673
.
Token.
Feature activation+0.362
The
Token The
Feature activation+0.026
message
Token message
Feature activation+0.000
broadcast
Token broadcast
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.720
want
Token want
Feature activation+2.822
to
Token to
Feature activation+1.899
say
Token say
Feature activation+2.721
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.114
whole
Token whole
Feature activation+0.000
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
doing
Token doing
Feature activation+0.000
whatever
Token whatever
Feature activation+0.132
we
Token we
Feature activation+0.926
need
Token need
Feature activation+2.702
to
Token to
Feature activation+2.245
.
Token.
Feature activation+0.368
Number
Token Number
Feature activation+0.000
two
Token two
Feature activation+0.000
,
Token,
Feature activation+0.000
luck
Token luck
Feature activation+0.000
with
Token with
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.237
're
Token're
Feature activation+1.949
doing
Token doing
Feature activation+2.685
.
Token.
Feature activation+0.347
Thanks
Token Thanks
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
features
Token features
Feature activation+1.035
they
Token they
Feature activation+1.251
like
Token like
Feature activation+2.644
and
Token and
Feature activation+0.080
improve
Token improve
Feature activation+0.510
their
Token their
Feature activation+0.000
looks
Token looks
Feature activation+0.000
.
Token.
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
charge
Token charge
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.551
wanted
Token wanted
Feature activation+2.610
,
Token,
Feature activation+1.062
even
Token even
Feature activation+0.499
for
Token for
Feature activation+0.000
20
Token 20
Feature activation+0.000
months
Token months
Feature activation+0.000
my
Token my
Feature activation+0.000
best
Token best
Feature activation+0.000
at
Token at
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
I
Token I
Feature activation+0.073
do
Token do
Feature activation+2.593
,
Token,
Feature activation+1.007
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
it
Token it
Feature activation+0.000
interrupts
Token interrupts
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
she
Token she
Feature activation+0.750
is
Token is
Feature activation+2.134
doing
Token doing
Feature activation+2.579
,
Token,
Feature activation+0.774
and
Token and
Feature activation+0.000
she
Token she
Feature activation+0.112
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
North
Token North
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
you
Token you
Feature activation+0.372
want
Token want
Feature activation+2.578
a
Token a
Feature activation+1.153
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.146
be
Token be
Feature activation+0.666
European
Token European
Feature activation+0.000
ideal
Token ideal
Feature activation+0.000
,"
Token,"
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.105
say
Token say
Feature activation+2.547
in
Token in
Feature activation+0.596
Brussels
Token Brussels
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
compression
Token compression
Feature activation+0.000
artifacts
Token artifacts
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.243
entertainment
Token entertainment
Feature activation+0.516
to
Token to
Feature activation+1.200
be
Token be
Feature activation+2.508
had
Token had
Feature activation+2.252
from
Token from
Feature activation+0.820
the
Token the
Feature activation+0.424
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.455
him
Token him
Feature activation+0.000
relentlessly
Token relentlessly
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
he
Token he
Feature activation+0.782
does
Token does
Feature activation+2.468
or
Token or
Feature activation+0.899
says
Token says
Feature activation+1.678
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
more
Token more
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
whatever
Tokenwhatever
Feature activation+0.000
you
Token you
Feature activation+0.023
can
Token can
Feature activation+1.548
do
Token do
Feature activation+2.444
.
Token.
Feature activation+0.000
PLEASE
Token PLEASE
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
your
Token your
Feature activation+0.000
your
Token your
Feature activation+0.000
lineup
Token lineup
Feature activation+0.000
is
Token is
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.470
want
Token want
Feature activation+2.385
it
Token it
Feature activation+1.562
to
Token to
Feature activation+1.188
be
Token be
Feature activation+0.966
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.068
People
Token People
Feature activation+0.000
can
Token can
Feature activation+0.000
say
Token say
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.546
want
Token want
Feature activation+2.349
âĢĶ
TokenâĢĶ
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+0.000
story
Token story
Feature activation+0.000
than
Token than
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.502
call
Token call
Feature activation+2.284
THAT
Token THAT
Feature activation+1.308
explanation
Token explanation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
file
Token file
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
information
Token information
Feature activation+0.231
you
Token you
Feature activation+1.354
can
Token can
Feature activation+2.281
to
Token to
Feature activation+1.488
inform
Token inform
Feature activation+1.201
the
Token the
Feature activation+0.000
FCC
Token FCC
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 3.307

list
Token list
Feature activation-0.066
Top resid features:
and
Token and
Feature activation+0.149
Top resid features:
I
Token I
Feature activation+0.039
Top resid features:
can
Token can
Feature activation+0.200
Top resid features:
do
Token do
Feature activation+0.036
Top resid features:
whatever
Token whatever
Feature activation+3.307
Top resid features:
I
Token I
Feature activation+0.626
Top resid features:
want
Token want
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
If
Token If
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
allow
Token allow
Feature activation+0.091
Top resid features:
you
Token you
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.273
Top resid features:
carry
Token carry
Feature activation-0.005
Top resid features:
whatever
Token whatever
Feature activation+3.166
Top resid features:
you
Token you
Feature activation+0.503
Top resid features:
want
Token want
Feature activation-0.024
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Internet
Token Internet
Feature activation-0.014
Top resid features:
connection
Token connection
Feature activation-0.009
Top resid features:
can
Token can
Feature activation+0.132
Top resid features:
literally
Token literally
Feature activation+0.076
Top resid features:
broadcast
Token broadcast
Feature activation-0.012
Top resid features:
whatever
Token whatever
Feature activation+3.052
Top resid features:
they
Token they
Feature activation+0.739
Top resid features:
want
Token want
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.314
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
They
Token They
Feature activation+0.028
Top resid features:
say
Token say
Feature activation-0.021
Top resid features:
whatever
Token whatever
Feature activation+3.113
Top resid features:
they
Token they
Feature activation+0.849
Top resid features:
want
Token want
Feature activation+0.044
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Internet
Token Internet
Feature activation-0.016
Top resid features:
connection
Token connection
Feature activation-0.006
Top resid features:
can
Token can
Feature activation+0.028
Top resid features:
literally
Token literally
Feature activation+0.035
Top resid features:
broadcast
Token broadcast
Feature activation+0.006
Top resid features:
whatever
Token whatever
Feature activation+3.125
Top resid features:
they
Token they
Feature activation+0.202
Top resid features:
want
Token want
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.631
Top resid features:
say
Token say
Feature activation-0.089
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.066
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
we
Token we
Feature activation+0.045
Top resid features:
are
Token are
Feature activation-0.104
Top resid features:
doing
Token doing
Feature activation+0.221
Top resid features:
whatever
Token whatever
Feature activation+2.974
Top resid features:
we
Token we
Feature activation+0.656
Top resid features:
need
Token need
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Number
Token Number
Feature activation+0.000
Top resid features:
forever
Token forever
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.074
Top resid features:
Good
TokenGood
Feature activation-0.005
Top resid features:
luck
Token luck
Feature activation+0.032
Top resid features:
with
Token with
Feature activation+0.149
Top resid features:
whatever
Token whatever
Feature activation+2.859
Top resid features:
you
Token you
Feature activation+0.437
Top resid features:
're
Token're
Feature activation+0.043
Top resid features:
doing
Token doing
Feature activation+0.223
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Thanks
Token Thanks
Feature activation+0.000
Top resid features:
impossible
Token impossible
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.141
Top resid features:
People
Token People
Feature activation-0.008
Top resid features:
can
Token can
Feature activation+0.104
Top resid features:
get
Token get
Feature activation+0.044
Top resid features:
whatever
Token whatever
Feature activation+2.915
Top resid features:
features
Token features
Feature activation-0.031
Top resid features:
they
Token they
Feature activation+0.643
Top resid features:
like
Token like
Feature activation+0.074
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
improve
Token improve
Feature activation+0.000
Top resid features:
weren
Token weren
Feature activation+0.034
Top resid features:
't
Token't
Feature activation+0.055
Top resid features:
allowed
Token allowed
Feature activation+0.088
Top resid features:
to
Token to
Feature activation+0.153
Top resid features:
charge
Token charge
Feature activation-0.007
Top resid features:
whatever
Token whatever
Feature activation+2.673
Top resid features:
they
Token they
Feature activation+0.705
Top resid features:
wanted
Token wanted
Feature activation+0.084
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.108
Top resid features:
be
Token be
Feature activation-0.007
Top resid features:
my
Token my
Feature activation+0.018
Top resid features:
best
Token best
Feature activation+0.009
Top resid features:
at
Token at
Feature activation+0.201
Top resid features:
whatever
Token whatever
Feature activation+2.818
Top resid features:
I
Token I
Feature activation+0.616
Top resid features:
do
Token do
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.352
Top resid features:
a
Tokena
Feature activation-0.003
Top resid features:
)
Token)
Feature activation+0.101
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
interrupts
Token interrupts
Feature activation+0.056
Top resid features:
whatever
Token whatever
Feature activation+3.280
Top resid features:
she
Token she
Feature activation+0.346
Top resid features:
is
Token is
Feature activation-0.160
Top resid features:
doing
Token doing
Feature activation+0.205
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
RB
Token RB
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
North
Token North
Feature activation-0.021
Top resid features:
Carolina
Token Carolina
Feature activation-0.062
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.003
Top resid features:
Whatever
Token Whatever
Feature activation+3.016
Top resid features:
you
Token you
Feature activation+0.721
Top resid features:
want
Token want
Feature activation+0.073
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
running
Token running
Feature activation+0.000
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.059
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
European
Token European
Feature activation-0.101
Top resid features:
ideal
Token ideal
Feature activation+0.018
Top resid features:
,"
Token,"
Feature activation+0.106
Top resid features:
whatever
Token whatever
Feature activation+3.247
Top resid features:
they
Token they
Feature activation+0.518
Top resid features:
say
Token say
Feature activation-0.049
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Brussels
Token Brussels
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.189
Top resid features:
video
Token video
Feature activation+0.064
Top resid features:
compression
Token compression
Feature activation+0.033
Top resid features:
artifacts
Token artifacts
Feature activation+0.046
Top resid features:
Whatever
Token Whatever
Feature activation+3.284
Top resid features:
entertainment
Token entertainment
Feature activation-0.271
Top resid features:
to
Token to
Feature activation+0.710
Top resid features:
be
Token be
Feature activation+0.055
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.237
Top resid features:
him
Token him
Feature activation+0.069
Top resid features:
relentlessly
Token relentlessly
Feature activation+0.047
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Whatever
Token Whatever
Feature activation+2.792
Top resid features:
he
Token he
Feature activation+0.888
Top resid features:
does
Token does
Feature activation+0.027
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
00
Token00
Feature activation-0.010
Top resid features:
or
Token or
Feature activation+0.052
Top resid features:
more
Token more
Feature activation-0.024
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.035
Top resid features:
whatever
Tokenwhatever
Feature activation+3.088
Top resid features:
you
Token you
Feature activation+0.312
Top resid features:
can
Token can
Feature activation+0.270
Top resid features:
do
Token do
Feature activation+0.081
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
PLEASE
Token PLEASE
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.091
Top resid features:
your
Token your
Feature activation+0.023
Top resid features:
lineup
Token lineup
Feature activation-0.028
Top resid features:
is
Token is
Feature activation-0.023
Top resid features:
whatever
Token whatever
Feature activation+2.820
Top resid features:
you
Token you
Feature activation+0.605
Top resid features:
want
Token want
Feature activation+0.032
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
me
Token me
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.116
Top resid features:
People
Token People
Feature activation-0.023
Top resid features:
can
Token can
Feature activation+0.135
Top resid features:
say
Token say
Feature activation-0.030
Top resid features:
whatever
Token whatever
Feature activation+2.919
Top resid features:
they
Token they
Feature activation+0.604
Top resid features:
want
Token want
Feature activation-0.055
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.000
Top resid features:
it
Tokenit
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
slightly
Token slightly
Feature activation+0.019
Top resid features:
different
Token different
Feature activation+0.044
Top resid features:
story
Token story
Feature activation+0.031
Top resid features:
than
Token than
Feature activation+0.002
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.112
Top resid features:
whatever
Token whatever
Feature activation+2.716
Top resid features:
you
Token you
Feature activation+0.737
Top resid features:
call
Token call
Feature activation+0.001
Top resid features:
THAT
Token THAT
Feature activation+0.000
Top resid features:
explanation
Token explanation
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.039
Top resid features:
possible
Token possible
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.097
Top resid features:
file
Token file
Feature activation+0.054
Top resid features:
whatever
Token whatever
Feature activation+2.781
Top resid features:
information
Token information
Feature activation-0.113
Top resid features:
you
Token you
Feature activation+0.450
Top resid features:
can
Token can
Feature activation+0.139
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
inform
Token inform
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.06

Head 3: 0.40

Head 4: 0.05

Head 5: 0.09

Head 6: 0.04

Head 7: 0.03

Head 8: 0.06

Head 9: 0.07

Head 10: 0.07

Head 11: 0.03

Positive logits

whatsoever1.60

lihood1.56

DIT1.48

entails1.45

isine1.43

alogue1.38

deems1.37

utical1.34

occasion1.34

imaginable1.30

fundament1.30

entail1.27

tyr1.26

hereafter1.26

:{1.26

ults1.26

ogical1.25

desired1.23

Ingredients1.23

extract1.23

Negative logits

rontal-1.44

anmar-1.43

gov-1.42

Syracuse-1.34

ortunately-1.34

sted-1.33

shaken-1.32

closed-1.28

abad-1.28

zar-1.25

Roose-1.25

slee-1.23

Troy-1.23

zens-1.20

Leban-1.19

aired-1.19

suicide-1.19

ainment-1.19

ounded-1.19

itted-1.18

INTERVAL 2.756 - 3.062
CONTAINS 0.000%

I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+0.267
I
Token I
Feature activation+1.117
want
Token want
Feature activation+3.062
.
Token.
Feature activation+0.440
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
've
Token've
Feature activation+0.000
never
Token never
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.795
want
Token want
Feature activation+2.848
on
Token on
Feature activation+1.012
top
Token top
Feature activation+0.462
of
Token of
Feature activation+0.766
your
Token your
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
can
Token can
Feature activation+0.000
literally
Token literally
Feature activation+0.000
broadcast
Token broadcast
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.720
want
Token want
Feature activation+2.822
to
Token to
Feature activation+1.899
say
Token say
Feature activation+2.721
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.114
whole
Token whole
Feature activation+0.000

INTERVAL 2.449 - 2.756
CONTAINS 0.001%

luck
Token luck
Feature activation+0.000
with
Token with
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.237
're
Token're
Feature activation+1.949
doing
Token doing
Feature activation+2.685
.
Token.
Feature activation+0.347
Thanks
Token Thanks
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
it
Token it
Feature activation+0.000
interrupts
Token interrupts
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
she
Token she
Feature activation+0.750
is
Token is
Feature activation+2.134
doing
Token doing
Feature activation+2.579
,
Token,
Feature activation+0.774
and
Token and
Feature activation+0.000
she
Token she
Feature activation+0.112
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
doing
Token doing
Feature activation+0.000
whatever
Token whatever
Feature activation+0.132
we
Token we
Feature activation+0.926
need
Token need
Feature activation+2.702
to
Token to
Feature activation+2.245
.
Token.
Feature activation+0.368
Number
Token Number
Feature activation+0.000
two
Token two
Feature activation+0.000
,
Token,
Feature activation+0.000
European
Token European
Feature activation+0.000
ideal
Token ideal
Feature activation+0.000
,"
Token,"
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.105
say
Token say
Feature activation+2.547
in
Token in
Feature activation+0.596
Brussels
Token Brussels
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
compression
Token compression
Feature activation+0.000
artifacts
Token artifacts
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.243
entertainment
Token entertainment
Feature activation+0.516
to
Token to
Feature activation+1.200
be
Token be
Feature activation+2.508
had
Token had
Feature activation+2.252
from
Token from
Feature activation+0.820
the
Token the
Feature activation+0.424
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.455

INTERVAL 2.143 - 2.449
CONTAINS 0.001%

do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
he
Token he
Feature activation+1.289
has
Token has
Feature activation+2.198
to
Token to
Feature activation+1.680
do
Token do
Feature activation+2.253
to
Token to
Feature activation+0.602
protect
Token protect
Feature activation+0.183
himself
Token himself
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
more
Token more
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
whatever
Tokenwhatever
Feature activation+0.000
you
Token you
Feature activation+0.023
can
Token can
Feature activation+1.548
do
Token do
Feature activation+2.444
.
Token.
Feature activation+0.000
PLEASE
Token PLEASE
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
your
Token your
Feature activation+0.000
creatures
Token creatures
Feature activation+0.000
goes
Token goes
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
reason
Token reason
Feature activation+2.278
sex
Token sex
Feature activation+0.000
just
Token just
Feature activation+0.357
doesn
Token doesn
Feature activation+0.379
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
artifacts
Token artifacts
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.243
entertainment
Token entertainment
Feature activation+0.516
to
Token to
Feature activation+1.200
be
Token be
Feature activation+2.508
had
Token had
Feature activation+2.252
from
Token from
Feature activation+0.820
the
Token the
Feature activation+0.424
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.455
demolished
Token demolished
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
disinformation
Token disinformation
Feature activation+0.000
for
Token for
Feature activation+0.000
whatever
Token whatever
Feature activation+0.569
reason
Token reason
Feature activation+2.178
.
Token.
Feature activation+0.179
Here
Token Here
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 1.837 - 2.143
CONTAINS 0.001%

area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
he
Token he
Feature activation+0.686
can
Token can
Feature activation+2.095
give
Token give
Feature activation+1.972
will
Token will
Feature activation+0.137
undoubtedly
Token undoubtedly
Feature activation+0.334
be
Token be
Feature activation+0.597
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
)
Token)
Feature activation+0.000
it
Token it
Feature activation+0.000
interrupts
Token interrupts
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
she
Token she
Feature activation+0.750
is
Token is
Feature activation+2.134
doing
Token doing
Feature activation+2.579
,
Token,
Feature activation+0.774
and
Token and
Feature activation+0.000
she
Token she
Feature activation+0.112
âĢ
TokenâĢ
Feature activation+0.000
literally
Token literally
Feature activation+0.000
broadcast
Token broadcast
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
they
Token they
Feature activation+0.720
want
Token want
Feature activation+2.822
to
Token to
Feature activation+1.899
say
Token say
Feature activation+2.721
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.114
whole
Token whole
Feature activation+0.000
world
Token world
Feature activation+0.000
changed
Token changed
Feature activation+0.000
class
Token class
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
you
Token you
Feature activation+0.532
want
Token want
Feature activation+2.143
to
Token to
Feature activation+1.633
call
Token call
Feature activation+2.038
it
Token it
Feature activation+0.428
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
on
Token on
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
benchmark
Token benchmark
Feature activation+0.295
or
Token or
Feature activation+1.146
requirement
Token requirement
Feature activation+1.854
they
Token they
Feature activation+0.720
need
Token need
Feature activation+0.904
to
Token to
Feature activation+0.559
get
Token get
Feature activation+0.062
funding
Token funding
Feature activation+0.000

INTERVAL 1.531 - 1.837
CONTAINS 0.002%

're
Token're
Feature activation+0.000
set
Token set
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
you
Token you
Feature activation+0.576
're
Token're
Feature activation+1.681
shopping
Token shopping
Feature activation+0.562
for
Token for
Feature activation+0.861
,
Token,
Feature activation+0.387
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
culture
Token culture
Feature activation+0.000
and
Token and
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
else
Token else
Feature activation+0.194
comes
Token comes
Feature activation+1.218
to
Token to
Feature activation+1.668
mind
Token mind
Feature activation+0.415
.
Token.
Feature activation+0.240
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
returning
Token returning
Feature activation+0.000
undefined
Token undefined
Feature activation+0.000
for
Token for
Feature activation+0.000
whatever
Token whatever
Feature activation+0.064
it
Token it
Feature activation+0.165
is
Token is
Feature activation+1.830
given
Token given
Feature activation+0.699
.
Token.
Feature activation+0.230
Note
Token Note
Feature activation+0.000
ably
Tokenably
Feature activation+0.000
void
Token void
Feature activation+0.000
?
Token?
Feature activation+0.000
''
Token ''
Feature activation+0.000
Whatever
TokenWhatever
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+1.543
that
Token that
Feature activation+1.534
was
Token was
Feature activation+0.000
bothering
Token bothering
Feature activation+0.417
her
Token her
Feature activation+0.065
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
different
Token different
Feature activation+0.000
kind
Token kind
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.017
goes
Token goes
Feature activation+0.216
wrong
Token wrong
Feature activation+1.556
for
Token for
Feature activation+1.402
fans
Token fans
Feature activation+0.439
in
Token in
Feature activation+0.645
Brazil
Token Brazil
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.225 - 1.531
CONTAINS 0.002%

smart
Token smart
Feature activation+0.000
character
Token character
Feature activation+0.000
in
Token in
Feature activation+0.000
whatever
Token whatever
Feature activation+0.177
show
Token show
Feature activation+0.462
I
Token I
Feature activation+1.392
watched
Token watched
Feature activation+1.140
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
guess
Token guess
Feature activation+0.000
that
Token that
Feature activation+0.000
possible
Token possible
Feature activation+0.000
to
Token to
Feature activation+0.000
file
Token file
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
information
Token information
Feature activation+0.231
you
Token you
Feature activation+1.354
can
Token can
Feature activation+2.281
to
Token to
Feature activation+1.488
inform
Token inform
Feature activation+1.201
the
Token the
Feature activation+0.000
FCC
Token FCC
Feature activation+0.000
.'
Token.'
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
Tech
Token Tech
Feature activation+0.000
is
Token is
Feature activation+1.481
you
Token you
Feature activation+0.701
don
Token don
Feature activation+0.554
't
Token't
Feature activation+0.962
know
Token know
Feature activation+0.674
the
Token the
Feature activation+0.000
file
Token file
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
information
Token information
Feature activation+0.231
you
Token you
Feature activation+1.354
can
Token can
Feature activation+2.281
to
Token to
Feature activation+1.488
inform
Token inform
Feature activation+1.201
the
Token the
Feature activation+0.000
FCC
Token FCC
Feature activation+0.000
.
Token.
Feature activation+0.000
Public
Token Public
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
says
Token says
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
comes
Token comes
Feature activation+0.182
into
Token into
Feature activation+1.523
his
Token his
Feature activation+1.056
head
Token head
Feature activation+0.000
at
Token at
Feature activation+0.748
the
Token the
Feature activation+0.664
moment
Token moment
Feature activation+0.105

INTERVAL 0.919 - 1.225
CONTAINS 0.004%

Like
TokenLike
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
notes
Token notes
Feature activation+0.384
she
Token she
Feature activation+1.370
had
Token had
Feature activation+1.196
written
Token written
Feature activation+0.952
up
Token up
Feature activation+0.000
about
Token about
Feature activation+0.508
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
shame
Token shame
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
asshole
Token asshole
Feature activation+0.845
is
Token is
Feature activation+1.781
obsessed
Token obsessed
Feature activation+1.405
with
Token with
Feature activation+0.932
my
Token my
Feature activation+0.000
pants
Token pants
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
bul
Token bul
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.795
want
Token want
Feature activation+2.848
on
Token on
Feature activation+1.012
top
Token top
Feature activation+0.462
of
Token of
Feature activation+0.766
your
Token your
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
.
Token.
Feature activation+0.000
Colbert
Token Colbert
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
reason
Token reason
Feature activation+2.268
,
Token,
Feature activation+0.938
it
Token it
Feature activation+0.719
appears
Token appears
Feature activation+0.404
the
Token the
Feature activation+0.161
president
Token president
Feature activation+0.000
was
Token was
Feature activation+0.000
character
Token character
Feature activation+0.000
in
Token in
Feature activation+0.000
whatever
Token whatever
Feature activation+0.177
show
Token show
Feature activation+0.462
I
Token I
Feature activation+1.392
watched
Token watched
Feature activation+1.140
(
Token (
Feature activation+0.000
I
TokenI
Feature activation+0.000
guess
Token guess
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.612 - 0.919
CONTAINS 0.004%

,
Token,
Feature activation+0.000
indeed
Token indeed
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
happens
Token happens
Feature activation+0.000
,
Token,
Feature activation+0.895
they
Token they
Feature activation+0.250
said
Token said
Feature activation+0.220
,
Token,
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
you
Token you
Feature activation+0.576
're
Token're
Feature activation+1.681
shopping
Token shopping
Feature activation+0.562
for
Token for
Feature activation+0.861
,
Token,
Feature activation+0.387
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
for
Token for
Feature activation+0.000
relentlessly
Token relentlessly
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
he
Token he
Feature activation+0.782
does
Token does
Feature activation+2.468
or
Token or
Feature activation+0.899
says
Token says
Feature activation+1.678
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
Â
TokenÂ
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.000
Whatever
TokenWhatever
Feature activation+0.000
negative
Token negative
Feature activation+0.506
perceptions
Token perceptions
Feature activation+0.411
formerly
Token formerly
Feature activation+0.000
were
Token were
Feature activation+0.515
held
Token held
Feature activation+0.701
about
Token about
Feature activation+0.827
the
Token the
Feature activation+0.000
Pac
Token Pac
Feature activation+0.000
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.000
the
Token the
Feature activation+0.000
NRA
Token NRA
Feature activation+0.000
or
Token or
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.917
no
Token no
Feature activation+0.211
other
Token other
Feature activation+0.000
playground
Token playground
Feature activation+0.000
.
Token.
Feature activation+0.000
Indiana
Token Indiana
Feature activation+0.000

INTERVAL 0.306 - 0.612
CONTAINS 0.007%

,
Token,
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
the
Token the
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
of
Token of
Feature activation+0.492
the
Token the
Feature activation+0.310
British
Token British
Feature activation+0.000
vote
Token vote
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
John
Token John
Feature activation+0.000
McCain
Token McCain
Feature activation+0.000
or
Token or
Feature activation+0.000
whoever
Token whoever
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.348
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
aftermath
Token aftermath
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
reason
Token reason
Feature activation+2.278
sex
Token sex
Feature activation+0.000
just
Token just
Feature activation+0.357
doesn
Token doesn
Feature activation+0.379
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
visual
Token visual
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
intersections
Token intersections
Feature activation+0.178
there
Token there
Feature activation+1.154
were
Token were
Feature activation+0.585
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Y
Token Y
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.017
goes
Token goes
Feature activation+0.216
wrong
Token wrong
Feature activation+1.556
for
Token for
Feature activation+1.402
fans
Token fans
Feature activation+0.439
in
Token in
Feature activation+0.645
Brazil
Token Brazil
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000

INTERVAL 0.000 - 0.306
CONTAINS 99.977%

games
Token games
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
shown
Token shown
Feature activation+0.000
on
Token on
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
Sports
Token Sports
Feature activation+0.000
channels
Token channels
Feature activation+0.000
[
Token [
Feature activation+0.000
formerly
Tokenformerly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
STEP
TokenSTEP
Feature activation+0.000
H
TokenH
Feature activation+0.000
EN
TokenEN
Feature activation+0.000
CON
Token CON
Feature activation+0.000
IG
TokenIG
Feature activation+0.000
L
TokenL
Feature activation+0.000
IO
TokenIO
Feature activation+0.000
(
Token (
Feature activation+0.000
Great
TokenGreat
Feature activation+0.000
er
Tokener
Feature activation+0.000
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+0.000
%
Token%
Feature activation+0.000
.[
Token.[
Feature activation+0.000
12
Token12
Feature activation+0.000
]
Token]
Feature activation+0.000
The
Token The
Feature activation+0.000
annual
Token annual
Feature activation+0.000
economic
Token economic
Feature activation+0.000
burden
Token burden
Feature activation+0.000
was
Token was
Feature activation+0.000
line
Tokenline
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
talk
Token talk
Feature activation+0.000
:
Token:
Feature activation+0.000
READ
Token READ
Feature activation+0.000
ING
TokenING
Feature activation+0.000
,
Token,
Feature activation+0.000
STUD
Token STUD
Feature activation+0.000
YING
TokenYING
Feature activation+0.000
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
45
Token 45
Feature activation+0.000
-
Token-
Feature activation+0.000
minute
Tokenminute
Feature activation+0.000
speech
Token speech
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Hillary
TokenHillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
has
Token has
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H2.3: (feature 9251)

TOP ACTIVATIONS
MAX = 3.975

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
either
Token either
Feature activation+0.000
honor
Token honor
Feature activation+0.359
or
Token or
Feature activation+3.975
shame
Token shame
Feature activation+0.000
,
Token,
Feature activation+0.019
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
name
Token name
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
after
Token after
Feature activation+0.000
either
Token either
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
or
Token or
Feature activation+3.727
tasks
Token tasks
Feature activation+0.000
they
Token they
Feature activation+0.671
find
Token find
Feature activation+0.000
pleas
Token pleas
Feature activation+0.000
urable
Tokenurable
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
identify
Token identify
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
gender
Token gender
Feature activation+1.403
or
Token or
Feature activation+3.626
were
Token were
Feature activation+0.739
in
Token in
Feature activation+0.000
transition
Token transition
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
sci
Token sci
Feature activation+0.000
-
Token-
Feature activation+0.000
fi
Tokenfi
Feature activation+0.015
or
Token or
Feature activation+3.610
horror
Token horror
Feature activation+0.428
elements
Token elements
Feature activation+0.392
âĢĶ
TokenâĢĶ
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
base
Token base
Feature activation+0.000
of
Token of
Feature activation+0.000
either
Token either
Feature activation+0.000
cas
Token cas
Feature activation+0.000
hews
Tokenhews
Feature activation+0.000
or
Token or
Feature activation+3.592
t
Token t
Feature activation+0.068
ah
Tokenah
Feature activation+0.000
ini
Tokenini
Feature activation+0.000
.
Token.
Feature activation+0.000
Tah
Token Tah
Feature activation+0.000
contact
Token contact
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+1.595
,
Token,
Feature activation+0.441
or
Token or
Feature activation+3.554
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
any
Token any
Feature activation+0.000
further
Token further
Feature activation+0.000
material
Token material
Feature activation+0.000
of
Token of
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
establishing
Token establishing
Feature activation+0.000
either
Token either
Feature activation+0.000
guilt
Token guilt
Feature activation+0.000
or
Token or
Feature activation+3.516
innocence
Token innocence
Feature activation+0.356
in
Token in
Feature activation+0.124
DUI
Token DUI
Feature activation+0.000
cases
Token cases
Feature activation+0.261
.
Token.
Feature activation+0.000
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
either
Token either
Feature activation+0.000
150
Token 150
Feature activation+0.000
8
Token8
Feature activation+0.000
or
Token or
Feature activation+3.445
150
Token 150
Feature activation+0.000
9
Token9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
sewer
Token sewer
Feature activation+0.000
shows
Token shows
Feature activation+0.000
either
Token either
Feature activation+0.000
laz
Token laz
Feature activation+0.000
iness
Tokeniness
Feature activation+0.000
or
Token or
Feature activation+3.404
corruption
Token corruption
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
police
Token police
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
lived
Token lived
Feature activation+0.000
in
Token in
Feature activation+0.000
either
Token either
Feature activation+0.000
the
Token the
Feature activation+0.039
city
Token city
Feature activation+0.000
or
Token or
Feature activation+3.398
a
Token a
Feature activation+0.000
bland
Token bland
Feature activation+0.000
suburb
Token suburb
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
approval
Token approval
Feature activation+0.000
of
Token of
Feature activation+0.000
either
Token either
Feature activation+0.000
A
Token A
Feature activation+0.000
HS
TokenHS
Feature activation+0.000
or
Token or
Feature activation+3.389
the
Token the
Feature activation+0.147
Government
Token Government
Feature activation+0.000
of
Token of
Feature activation+0.144
Alberta
Token Alberta
Feature activation+0.000
."
Token."
Feature activation+0.000
and
Token and
Feature activation+0.000
adding
Token adding
Feature activation+0.000
either
Token either
Feature activation+0.000
coconut
Token coconut
Feature activation+0.000
milk
Token milk
Feature activation+0.000
or
Token or
Feature activation+3.311
almond
Token almond
Feature activation+0.000
jelly
Token jelly
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
ann
Token ann
Feature activation+0.000
side
Token side
Feature activation+0.000
of
Token of
Feature activation+0.000
either
Token either
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
or
Token or
Feature activation+3.301
public
Token public
Feature activation+0.000
opinion
Token opinion
Feature activation+0.570
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
entries
Token entries
Feature activation+0.000
on
Token on
Feature activation+0.000
either
Token either
Feature activation+0.000
mobile
Token mobile
Feature activation+0.219
or
Token or
Feature activation+3.264
handheld
Token handheld
Feature activation+0.122
platforms
Token platforms
Feature activation+0.108
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
either
Token either
Feature activation+0.000
catch
Token catch
Feature activation+0.819
or
Token or
Feature activation+3.221
dodge
Token dodge
Feature activation+0.000
complex
Token complex
Feature activation+0.000
objects
Token objects
Feature activation+0.000
in
Token in
Feature activation+0.000
full
Token full
Feature activation+0.000
projects
Token projects
Feature activation+0.000
were
Token were
Feature activation+0.000
either
Token either
Feature activation+0.000
disappoint
Token disappoint
Feature activation+0.000
ments
Tokenments
Feature activation+0.000
or
Token or
Feature activation+3.104
were
Token were
Feature activation+0.000
frustrated
Token frustrated
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
financial
Token financial
Feature activation+0.000
affected
Token affected
Feature activation+0.000
by
Token by
Feature activation+0.000
either
Token either
Feature activation+0.000
sc
Token sc
Feature activation+0.000
abies
Tokenabies
Feature activation+0.000
or
Token or
Feature activation+3.087
l
Token l
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
shower
Token shower
Feature activation+0.000
from
Token from
Feature activation+0.000
either
Token either
Feature activation+0.000
burning
Token burning
Feature activation+0.000
sl
Token sl
Feature activation+0.000
udge
Tokenudge
Feature activation+0.000
or
Token or
Feature activation+3.062
methane
Token methane
Feature activation+0.000
derived
Token derived
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
13
Token 13
Feature activation+0.000
major
Token major
Feature activation+0.000
threat
Token threat
Feature activation+0.000
in
Token in
Feature activation+0.000
either
Token either
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
or
Token or
Feature activation+3.011
Afghanistan
Token Afghanistan
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
has
Token has
Feature activation+0.000
till
Token till
Feature activation+0.000
I
Token I
Feature activation+0.000
either
Token either
Feature activation+0.000
fall
Token fall
Feature activation+0.000
off
Token off
Feature activation+0.000
or
Token or
Feature activation+2.996
clean
Token clean
Feature activation+0.000
it
Token it
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 5.259

.
Token.
Feature activation+0.038
Top resid features:
It
Token It
Feature activation-0.021
Top resid features:
âĢ
TokenâĢ
Feature activation-0.045
Top resid features:
Ļ
TokenĻ
Feature activation-0.034
Top resid features:
s
Tokens
Feature activation+0.036
Top resid features:
either
Token either
Feature activation+5.259
Top resid features:
honor
Token honor
Feature activation+0.173
Top resid features:
or
Token or
Feature activation+0.477
Top resid features:
shame
Token shame
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.036
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
name
Token name
Feature activation-0.088
Top resid features:
themselves
Token themselves
Feature activation-0.142
Top resid features:
after
Token after
Feature activation-0.009
Top resid features:
either
Token either
Feature activation+5.205
Top resid features:
jobs
Token jobs
Feature activation+0.140
Top resid features:
or
Token or
Feature activation+0.427
Top resid features:
tasks
Token tasks
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.113
Top resid features:
identify
Token identify
Feature activation-0.238
Top resid features:
with
Token with
Feature activation+0.022
Top resid features:
either
Token either
Feature activation+5.076
Top resid features:
gender
Token gender
Feature activation+0.032
Top resid features:
or
Token or
Feature activation+0.401
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
transition
Token transition
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.012
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
contained
Token contained
Feature activation-0.057
Top resid features:
thriller
Token thriller
Feature activation-0.143
Top resid features:
with
Token with
Feature activation+0.171
Top resid features:
either
Token either
Feature activation+4.610
Top resid features:
sci
Token sci
Feature activation+0.138
Top resid features:
-
Token-
Feature activation+0.108
Top resid features:
fi
Tokenfi
Feature activation+0.258
Top resid features:
or
Token or
Feature activation+0.431
Top resid features:
horror
Token horror
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
have
Token have
Feature activation-0.057
Top resid features:
a
Token a
Feature activation+0.074
Top resid features:
base
Token base
Feature activation-0.104
Top resid features:
of
Token of
Feature activation+0.126
Top resid features:
either
Token either
Feature activation+4.781
Top resid features:
cas
Token cas
Feature activation+0.076
Top resid features:
hews
Tokenhews
Feature activation+0.190
Top resid features:
or
Token or
Feature activation+0.469
Top resid features:
t
Token t
Feature activation+0.000
Top resid features:
ah
Tokenah
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
Times
Token Times
Feature activation-0.090
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
contact
Token contact
Feature activation-0.116
Top resid features:
with
Token with
Feature activation+0.026
Top resid features:
either
Token either
Feature activation+5.209
Top resid features:
source
Token source
Feature activation-0.128
Top resid features:
,
Token,
Feature activation-0.114
Top resid features:
or
Token or
Feature activation+0.571
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
provide
Token provide
Feature activation+0.000
Top resid features:
critical
Token critical
Feature activation-0.041
Top resid features:
piece
Token piece
Feature activation-0.087
Top resid features:
of
Token of
Feature activation+0.051
Top resid features:
evidence
Token evidence
Feature activation-0.087
Top resid features:
establishing
Token establishing
Feature activation+0.004
Top resid features:
either
Token either
Feature activation+4.691
Top resid features:
guilt
Token guilt
Feature activation+0.216
Top resid features:
or
Token or
Feature activation+0.605
Top resid features:
innocence
Token innocence
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
DUI
Token DUI
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.044
Top resid features:
She
Token She
Feature activation+0.001
Top resid features:
was
Token was
Feature activation-0.078
Top resid features:
born
Token born
Feature activation-0.063
Top resid features:
in
Token in
Feature activation+0.084
Top resid features:
either
Token either
Feature activation+4.788
Top resid features:
150
Token 150
Feature activation+0.018
Top resid features:
8
Token8
Feature activation+0.147
Top resid features:
or
Token or
Feature activation+0.316
Top resid features:
150
Token 150
Feature activation+0.000
Top resid features:
9
Token9
Feature activation+0.000
Top resid features:
army
Token army
Feature activation-0.092
Top resid features:
into
Token into
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
sewer
Token sewer
Feature activation-0.129
Top resid features:
shows
Token shows
Feature activation-0.135
Top resid features:
either
Token either
Feature activation+5.196
Top resid features:
laz
Token laz
Feature activation+0.098
Top resid features:
iness
Tokeniness
Feature activation+0.079
Top resid features:
or
Token or
Feature activation+0.528
Top resid features:
corruption
Token corruption
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.077
Top resid features:
ve
Tokenve
Feature activation-0.039
Top resid features:
always
Token always
Feature activation-0.064
Top resid features:
lived
Token lived
Feature activation-0.137
Top resid features:
in
Token in
Feature activation+0.106
Top resid features:
either
Token either
Feature activation+4.720
Top resid features:
the
Token the
Feature activation+0.257
Top resid features:
city
Token city
Feature activation+0.126
Top resid features:
or
Token or
Feature activation+0.412
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
bland
Token bland
Feature activation+0.000
Top resid features:
website
Token website
Feature activation-0.116
Top resid features:
,
Token,
Feature activation-0.035
Top resid features:
without
Token without
Feature activation+0.074
Top resid features:
approval
Token approval
Feature activation-0.165
Top resid features:
of
Token of
Feature activation+0.148
Top resid features:
either
Token either
Feature activation+4.476
Top resid features:
A
Token A
Feature activation+0.088
Top resid features:
HS
TokenHS
Feature activation+0.268
Top resid features:
or
Token or
Feature activation+0.486
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Government
Token Government
Feature activation+0.000
Top resid features:
ika
Tokenika
Feature activation-0.060
Top resid features:
Bag
Token Bag
Feature activation-0.045
Top resid features:
el
Tokenel
Feature activation-0.046
Top resid features:
and
Token and
Feature activation+0.046
Top resid features:
adding
Token adding
Feature activation-0.253
Top resid features:
either
Token either
Feature activation+4.575
Top resid features:
coconut
Token coconut
Feature activation+0.119
Top resid features:
milk
Token milk
Feature activation+0.191
Top resid features:
or
Token or
Feature activation+0.665
Top resid features:
almond
Token almond
Feature activation+0.000
Top resid features:
jelly
Token jelly
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
wrong
Token wrong
Feature activation-0.054
Top resid features:
side
Token side
Feature activation-0.140
Top resid features:
of
Token of
Feature activation+0.114
Top resid features:
either
Token either
Feature activation+4.530
Top resid features:
the
Token the
Feature activation+0.257
Top resid features:
law
Token law
Feature activation+0.171
Top resid features:
or
Token or
Feature activation+0.550
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
opinion
Token opinion
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.076
Top resid features:
-
Token-
Feature activation-0.053
Top resid features:
No
TokenNo
Feature activation-0.000
Top resid features:
entries
Token entries
Feature activation-0.194
Top resid features:
on
Token on
Feature activation+0.095
Top resid features:
either
Token either
Feature activation+4.598
Top resid features:
mobile
Token mobile
Feature activation+0.447
Top resid features:
or
Token or
Feature activation+0.350
Top resid features:
handheld
Token handheld
Feature activation+0.000
Top resid features:
platforms
Token platforms
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.145
Top resid features:
be
Token be
Feature activation-0.105
Top resid features:
able
Token able
Feature activation-0.089
Top resid features:
to
Token to
Feature activation-0.021
Top resid features:
either
Token either
Feature activation+4.381
Top resid features:
catch
Token catch
Feature activation+0.361
Top resid features:
or
Token or
Feature activation+0.392
Top resid features:
dodge
Token dodge
Feature activation+0.000
Top resid features:
complex
Token complex
Feature activation+0.000
Top resid features:
objects
Token objects
Feature activation+0.000
Top resid features:
),
Token),
Feature activation-0.036
Top resid features:
many
Token many
Feature activation-0.024
Top resid features:
other
Token other
Feature activation-0.018
Top resid features:
projects
Token projects
Feature activation-0.188
Top resid features:
were
Token were
Feature activation-0.020
Top resid features:
either
Token either
Feature activation+4.427
Top resid features:
disappoint
Token disappoint
Feature activation+0.242
Top resid features:
ments
Tokenments
Feature activation+0.104
Top resid features:
or
Token or
Feature activation+0.591
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
frustrated
Token frustrated
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.064
Top resid features:
not
Token not
Feature activation-0.013
Top resid features:
been
Token been
Feature activation-0.049
Top resid features:
affected
Token affected
Feature activation-0.077
Top resid features:
by
Token by
Feature activation+0.108
Top resid features:
either
Token either
Feature activation+4.450
Top resid features:
sc
Token sc
Feature activation+0.147
Top resid features:
abies
Tokenabies
Feature activation+0.140
Top resid features:
or
Token or
Feature activation+0.512
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
ice
Tokenice
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
its
Token its
Feature activation-0.024
Top resid features:
power
Token power
Feature activation-0.135
Top resid features:
,
Token,
Feature activation-0.030
Top resid features:
from
Token from
Feature activation+0.123
Top resid features:
either
Token either
Feature activation+4.141
Top resid features:
burning
Token burning
Feature activation+0.053
Top resid features:
sl
Token sl
Feature activation+0.169
Top resid features:
udge
Tokenudge
Feature activation+0.205
Top resid features:
or
Token or
Feature activation+0.557
Top resid features:
methane
Token methane
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.035
Top resid features:
a
Token a
Feature activation+0.022
Top resid features:
major
Token major
Feature activation-0.024
Top resid features:
threat
Token threat
Feature activation-0.115
Top resid features:
in
Token in
Feature activation+0.210
Top resid features:
either
Token either
Feature activation+4.424
Top resid features:
Pakistan
Token Pakistan
Feature activation+0.087
Top resid features:
or
Token or
Feature activation+0.450
Top resid features:
Afghanistan
Token Afghanistan
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
so
Token so
Feature activation-0.070
Top resid features:
on
Token on
Feature activation-0.003
Top resid features:
till
Token till
Feature activation-0.049
Top resid features:
I
Token I
Feature activation-0.031
Top resid features:
either
Token either
Feature activation+4.343
Top resid features:
fall
Token fall
Feature activation+0.006
Top resid features:
off
Token off
Feature activation+0.354
Top resid features:
or
Token or
Feature activation+0.451
Top resid features:
clean
Token clean
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.05

Head 3: 0.39

Head 4: 0.14

Head 5: 0.08

Head 6: 0.05

Head 7: 0.03

Head 8: 0.04

Head 9: 0.04

Head 10: 0.06

Head 11: 0.03

Positive logits

itud1.55

idge1.50

odder1.44

icro1.42

emonic1.34

nor1.32

emon1.31

soever1.27

ource1.27

cific1.26

ition1.19

azard1.17

pite1.17

ologne1.16

ieth1.16

azo1.15

isal1.15

ggie1.14

ellect1.13

iga1.13

Negative logits

secrecy-1.28

arah-1.25

-1.24

Appearances-1.23

successful-1.20

-1.19

-1.18

Collider-1.18

Purg-1.18

Recommend-1.16

%:-1.14

rians-1.13

��-1.12

Names-1.11

Antar-1.10

ank-1.09

-1.08

literally-1.08

��-1.08

anim-1.07

INTERVAL 3.577 - 3.975
CONTAINS 0.001%

base
Token base
Feature activation+0.000
of
Token of
Feature activation+0.000
either
Token either
Feature activation+0.000
cas
Token cas
Feature activation+0.000
hews
Tokenhews
Feature activation+0.000
or
Token or
Feature activation+3.592
t
Token t
Feature activation+0.068
ah
Tokenah
Feature activation+0.000
ini
Tokenini
Feature activation+0.000
.
Token.
Feature activation+0.000
Tah
Token Tah
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
identify
Token identify
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
gender
Token gender
Feature activation+1.403
or
Token or
Feature activation+3.626
were
Token were
Feature activation+0.739
in
Token in
Feature activation+0.000
transition
Token transition
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
name
Token name
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
after
Token after
Feature activation+0.000
either
Token either
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
or
Token or
Feature activation+3.727
tasks
Token tasks
Feature activation+0.000
they
Token they
Feature activation+0.671
find
Token find
Feature activation+0.000
pleas
Token pleas
Feature activation+0.000
urable
Tokenurable
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
sci
Token sci
Feature activation+0.000
-
Token-
Feature activation+0.000
fi
Tokenfi
Feature activation+0.015
or
Token or
Feature activation+3.610
horror
Token horror
Feature activation+0.428
elements
Token elements
Feature activation+0.392
âĢĶ
TokenâĢĶ
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
either
Token either
Feature activation+0.000
honor
Token honor
Feature activation+0.359
or
Token or
Feature activation+3.975
shame
Token shame
Feature activation+0.000
,
Token,
Feature activation+0.019
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 3.180 - 3.577
CONTAINS 0.001%

born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
either
Token either
Feature activation+0.000
150
Token 150
Feature activation+0.000
8
Token8
Feature activation+0.000
or
Token or
Feature activation+3.445
150
Token 150
Feature activation+0.000
9
Token9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
sewer
Token sewer
Feature activation+0.000
shows
Token shows
Feature activation+0.000
either
Token either
Feature activation+0.000
laz
Token laz
Feature activation+0.000
iness
Tokeniness
Feature activation+0.000
or
Token or
Feature activation+3.404
corruption
Token corruption
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
police
Token police
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
approval
Token approval
Feature activation+0.000
of
Token of
Feature activation+0.000
either
Token either
Feature activation+0.000
A
Token A
Feature activation+0.000
HS
TokenHS
Feature activation+0.000
or
Token or
Feature activation+3.389
the
Token the
Feature activation+0.147
Government
Token Government
Feature activation+0.000
of
Token of
Feature activation+0.144
Alberta
Token Alberta
Feature activation+0.000
."
Token."
Feature activation+0.000
and
Token and
Feature activation+0.000
adding
Token adding
Feature activation+0.000
either
Token either
Feature activation+0.000
coconut
Token coconut
Feature activation+0.000
milk
Token milk
Feature activation+0.000
or
Token or
Feature activation+3.311
almond
Token almond
Feature activation+0.000
jelly
Token jelly
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
ann
Token ann
Feature activation+0.000
contact
Token contact
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+1.595
,
Token,
Feature activation+0.441
or
Token or
Feature activation+3.554
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
any
Token any
Feature activation+0.000
further
Token further
Feature activation+0.000
material
Token material
Feature activation+0.000

INTERVAL 2.782 - 3.180
CONTAINS 0.001%

who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
either
Token either
Feature activation+0.000
frown
Token frown
Feature activation+0.000
ing
Tokening
Feature activation+0.000
or
Token or
Feature activation+2.843
smiling
Token smiling
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
mood
Token mood
Feature activation+0.000
at
Token at
Feature activation+0.000
either
Token either
Feature activation+0.000
developing
Token developing
Feature activation+1.349
new
Token new
Feature activation+0.161
skills
Token skills
Feature activation+0.000
or
Token or
Feature activation+2.842
earning
Token earning
Feature activation+0.000
new
Token new
Feature activation+0.000
assets
Token assets
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
notified
Token notified
Feature activation+0.000
by
Token by
Feature activation+0.000
either
Token either
Feature activation+0.000
Brid
Token Brid
Feature activation+0.000
ger
Tokenger
Feature activation+0.000
or
Token or
Feature activation+2.986
local
Token local
Feature activation+0.000
officials
Token officials
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
spill
Token spill
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
either
Token either
Feature activation+0.000
straight
Token straight
Feature activation+0.000
or
Token or
Feature activation+2.822
gay
Token gay
Feature activation+0.045
is
Token is
Feature activation+0.305
pervasive
Token pervasive
Feature activation+0.000
and
Token and
Feature activation+0.000
persistent
Token persistent
Feature activation+0.000
from
Token from
Feature activation+0.000
either
Token either
Feature activation+0.000
burning
Token burning
Feature activation+0.000
sl
Token sl
Feature activation+0.000
udge
Tokenudge
Feature activation+0.000
or
Token or
Feature activation+3.062
methane
Token methane
Feature activation+0.000
derived
Token derived
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
13
Token 13
Feature activation+0.000

INTERVAL 2.385 - 2.782
CONTAINS 0.002%

Association
Token Association
Feature activation+0.000
is
Token is
Feature activation+0.000
either
Token either
Feature activation+0.000
consciously
Token consciously
Feature activation+0.791
lying
Token lying
Feature activation+0.000
or
Token or
Feature activation+2.395
has
Token has
Feature activation+0.629
absolutely
Token absolutely
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
Huawei
Token Huawei
Feature activation+0.000
refuses
Token refuses
Feature activation+0.000
to
Token to
Feature activation+0.000
either
Token either
Feature activation+0.000
confirm
Token confirm
Feature activation+1.402
or
Token or
Feature activation+2.412
deny
Token deny
Feature activation+0.240
any
Token any
Feature activation+0.000
launch
Token launch
Feature activation+0.000
plans
Token plans
Feature activation+0.113
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
cat
Token cat
Feature activation+0.000
has
Token has
Feature activation+0.000
on
Token on
Feature activation+0.000
either
Token either
Feature activation+0.000
side
Token side
Feature activation+2.426
of
Token of
Feature activation+1.228
her
Token her
Feature activation+1.307
nose
Token nose
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.041
(
Token (
Feature activation+0.000
either
Tokeneither
Feature activation+0.000
in
Token in
Feature activation+0.000
source
Token source
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+2.598
create
Token create
Feature activation+0.000
an
Token an
Feature activation+0.000
environment
Token environment
Feature activation+0.000
variable
Token variable
Feature activation+0.000
J
Token J
Feature activation+0.000
would
Token would
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.016
still
Token still
Feature activation+0.000
born
Tokenborn
Feature activation+0.000
or
Token or
Feature activation+2.720
die
Token die
Feature activation+0.000
very
Token very
Feature activation+0.000
shortly
Token shortly
Feature activation+0.000
afterwards
Token afterwards
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.987 - 2.385
CONTAINS 0.002%

ian
Tokenian
Feature activation+0.000
O
TokenO
Feature activation+0.000
,
Token,
Feature activation+0.331
Zer
Token Zer
Feature activation+0.000
O
TokenO
Feature activation+0.000
or
Token or
Feature activation+2.275
free
Token free
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
heard
Token heard
Feature activation+0.000
anything
Token anything
Feature activation+0.000
easy
Token easy
Feature activation+0.000
ride
Token ride
Feature activation+0.000
for
Token for
Feature activation+0.000
either
Token either
Feature activation+0.000
of
Token of
Feature activation+0.931
them
Token them
Feature activation+2.059
;
Token;
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
weight
Token weight
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
counted
Token counted
Feature activation+0.000
for
Token for
Feature activation+0.000
either
Token either
Feature activation+0.000
candidate
Token candidate
Feature activation+2.216
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
recount
Token recount
Feature activation+0.000
official
Token official
Feature activation+0.000
either
Token either
Feature activation+0.000
by
Token by
Feature activation+0.302
custom
Token custom
Feature activation+0.000
applications
Token applications
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+2.116
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
small
Token small
Feature activation+0.000
script
Token script
Feature activation+0.000
launched
Token launched
Feature activation+0.000
US
Token US
Feature activation+0.000
-
Token-
Feature activation+0.000
led
Tokenled
Feature activation+0.000
Coalition
Token Coalition
Feature activation+0.000
personnel
Token personnel
Feature activation+0.000
or
Token or
Feature activation+2.017
Iraqis
Token Iraqis
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 1.590 - 1.987
CONTAINS 0.002%

effects
Token effects
Feature activation+0.000
applied
Token applied
Feature activation+0.000
to
Token to
Feature activation+0.000
either
Token either
Feature activation+0.000
participant
Token participant
Feature activation+1.994
will
Token will
Feature activation+1.600
cancel
Token cancel
Feature activation+0.106
the
Token the
Feature activation+0.000
brawl
Token brawl
Feature activation+0.000
and
Token and
Feature activation+0.000
may
Token may
Feature activation+0.000
either
Token either
Feature activation+0.000
be
Token be
Feature activation+0.000
sold
Token sold
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.747
not
Token not
Feature activation+0.000
..
Token..
Feature activation+0.000
in
Tokenin
Feature activation+0.000
which
Token which
Feature activation+0.000
case
Token case
Feature activation+0.000
law
Token law
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
that
Token that
Feature activation+0.000
either
Token either
Feature activation+0.000
party
Token party
Feature activation+1.879
may
Token may
Feature activation+0.254
cancel
Token cancel
Feature activation+0.000
the
Token the
Feature activation+0.000
contract
Token contract
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
popular
Token popular
Feature activation+0.000
press
Token press
Feature activation+0.000
or
Token or
Feature activation+1.825
in
Token in
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
literature
Token literature
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
answered
Token answered
Feature activation+0.000
either
Token either
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
or
Token or
Feature activation+1.729
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
official
Token official
Feature activation+0.000
left
Token left
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.192 - 1.590
CONTAINS 0.001%

have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
at
Token at
Feature activation+0.000
either
Token either
Feature activation+0.000
developing
Token developing
Feature activation+1.349
new
Token new
Feature activation+0.161
skills
Token skills
Feature activation+0.000
or
Token or
Feature activation+2.842
earning
Token earning
Feature activation+0.000
new
Token new
Feature activation+0.000
.
Token.
Feature activation+0.000
Huawei
Token Huawei
Feature activation+0.000
refuses
Token refuses
Feature activation+0.000
to
Token to
Feature activation+0.000
either
Token either
Feature activation+0.000
confirm
Token confirm
Feature activation+1.402
or
Token or
Feature activation+2.412
deny
Token deny
Feature activation+0.240
any
Token any
Feature activation+0.000
launch
Token launch
Feature activation+0.000
plans
Token plans
Feature activation+0.113
US
Token US
Feature activation+0.000
either
Token either
Feature activation+0.000
still
Token still
Feature activation+0.000
getting
Token getting
Feature activation+0.000
now
Token now
Feature activation+0.000
or
Token or
Feature activation+1.589
digging
Token digging
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.002
the
Token the
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
require
Token require
Feature activation+0.000
either
Token either
Feature activation+0.000
of
Token of
Feature activation+0.559
those
Token those
Feature activation+1.511
things
Token things
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
has
Token has
Feature activation+0.000
on
Token on
Feature activation+0.000
either
Token either
Feature activation+0.000
side
Token side
Feature activation+2.426
of
Token of
Feature activation+1.228
her
Token her
Feature activation+1.307
nose
Token nose
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.041
also
Token also
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.795 - 1.192
CONTAINS 0.002%

this
Token this
Feature activation+0.432
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.780
thermal
Token thermal
Feature activation+0.000
printed
Token printed
Feature activation+0.000
or
Token or
Feature activation+1.181
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
printed
Tokenprinted
Feature activation+0.000
Update
Token Update
Feature activation+0.000
),
Token),
Feature activation+0.000
users
Token users
Feature activation+0.000
may
Token may
Feature activation+0.000
either
Token either
Feature activation+0.000
choose
Token choose
Feature activation+0.953
to
Token to
Feature activation+0.000
override
Token override
Feature activation+0.082
the
Token the
Feature activation+0.000
protection
Token protection
Feature activation+0.000
in
Token in
Feature activation+0.000
scenarios
Token scenarios
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
can
Token can
Feature activation+0.000
either
Token either
Feature activation+0.000
have
Token have
Feature activation+0.921
her
Token her
Feature activation+0.840
life
Token life
Feature activation+0.000
jeopard
Token jeopard
Feature activation+0.022
ized
Tokenized
Feature activation+0.400
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
debates
Token debates
Feature activation+0.000
and
Token and
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
or
Token or
Feature activation+1.162
had
Token had
Feature activation+0.000
its
Token its
Feature activation+0.000
worst
Token worst
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
actively
Token actively
Feature activation+0.000
releases
Token releases
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
either
Token either
Feature activation+0.000
filter
Token filter
Feature activation+0.998
the
Token the
Feature activation+0.130
table
Token table
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000

INTERVAL 0.397 - 0.795
CONTAINS 0.005%

the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
by
Token by
Feature activation+0.000
either
Token either
Feature activation+0.000
monopol
Token monopol
Feature activation+0.000
izing
Tokenizing
Feature activation+0.539
pillar
Token pillar
Feature activation+0.000
industries
Token industries
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
energy
Token energy
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
either
Token either
Feature activation+0.000
left
Token left
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.719
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
debates
Token debates
Feature activation+0.000
and
Token and
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.000
Either
Token Either
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.689
you
Token you
Feature activation+0.000
go
Token go
Feature activation+0.000
log
Token log
Feature activation+0.000
on
Token on
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
live
Token live
Feature activation+0.000
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
"
Token"
Feature activation+0.450
a
Token a
Feature activation+0.078
one
Token one
Feature activation+0.596
-
Token-
Feature activation+0.000
state
Tokenstate
Feature activation+0.000
or
Token or
Feature activation+1.704
a
Token a
Feature activation+0.000
two
Token two
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
strength
Token strength
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.679
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
like
Token like
Feature activation+0.000

INTERVAL 0.000 - 0.397
CONTAINS 99.984%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
from
Token from
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Greenberg
Token Greenberg
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
she
Token she
Feature activation+0.000
met
Token met
Feature activation+0.000
in
Token in
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
economic
Token economic
Feature activation+0.000
disappoint
Token disappoint
Feature activation+0.000
ments
Tokenments
Feature activation+0.000
in
Token in
Feature activation+0.000
emerging
Token emerging
Feature activation+0.000
markets
Token markets
Feature activation+0.000
sent
Token sent
Feature activation+0.000
equity
Token equity
Feature activation+0.000
markets
Token markets
Feature activation+0.000
t
Token t
Feature activation+0.000
umbling
Tokenumbling
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
specify
Token specify
Feature activation+0.000
a
Token a
Feature activation+0.000
round
Token round
Feature activation+0.000
-
Token-
Feature activation+0.000
trip
Tokentrip
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
'
Token '
Feature activation+0.000
touch
Tokentouch
Feature activation+0.000
and
Token and
Feature activation+0.000
go
Token go
Feature activation+0.000
'
Token'
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
clash
Token clash
Feature activation+0.000
with
Token with
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
also
Token also
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
for
Token for
Feature activation+0.000
one
Token one
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