H7.7 top features

Top feature 0 in H7.7: (feature 31956)

TOP ACTIVATIONS
MAX = 3.455

unlock
Token unlock
Feature activation+0.000
and
Token and
Feature activation+0.124
study
Token study
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.813
Ċ
TokenĊ
Feature activation+0.148
16
Token16
Feature activation+3.455
mysterious
Token mysterious
Feature activation+1.220
cards
Token cards
Feature activation+0.885
to
Token to
Feature activation+0.366
collect
Token collect
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.110
revoked
Token revoked
Feature activation+0.000
and
Token and
Feature activation+1.190
banned
Token banned
Feature activation+0.000
;
Token;
Feature activation+1.120
and
Token and
Feature activation+1.291
for
Token for
Feature activation+3.399
a
Token a
Feature activation+1.359
comprehensive
Token comprehensive
Feature activation+0.297
public
Token public
Feature activation+0.000
enqu
Token enqu
Feature activation+0.000
iry
Tokeniry
Feature activation+0.314
moved
Token moved
Feature activation+0.000
from
Token from
Feature activation+0.000
holding
Token holding
Feature activation+0.000
cell
Token cell
Feature activation+0.000
to
Token to
Feature activation+0.000
holding
Token holding
Feature activation+3.142
cell
Token cell
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.000
one
Token one
Feature activation+0.000
filthy
Token filthy
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
and
Token and
Feature activation+2.991
a
Token a
Feature activation+2.553
city
Token city
Feature activation+0.448
that
Token that
Feature activation+0.000
watches
Token watches
Feature activation+0.000
you
Token you
Feature activation+0.000
from
Token from
Feature activation+0.000
community
Token community
Feature activation+0.000
to
Token to
Feature activation+0.227
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.226
from
Token from
Feature activation+2.929
village
Token village
Feature activation+1.978
to
Token to
Feature activation+0.093
village
Token village
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+2.837
from
Token from
Feature activation+2.929
village
Token village
Feature activation+1.978
to
Token to
Feature activation+0.093
village
Token village
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+2.837
town
Token town
Feature activation+0.793
to
Token to
Feature activation+0.040
town
Token town
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000
,
Token,
Feature activation+1.212
the
Token the
Feature activation+0.860
receipt
Token receipt
Feature activation+2.714
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
take
Token take
Feature activation+0.011
out
Tokenout
Feature activation+0.742
bag
Token bag
Feature activation+0.440
take
Token take
Feature activation+0.568
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
to
Token to
Feature activation+0.000
blow
Token blow
Feature activation+0.000
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
and
Token and
Feature activation+2.991
a
Token a
Feature activation+2.553
city
Token city
Feature activation+0.448
that
Token that
Feature activation+0.000
watches
Token watches
Feature activation+0.000
you
Token you
Feature activation+0.000
back
Token back
Feature activation+0.000
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
for
Token for
Feature activation+0.000
taking
Token taking
Feature activation+2.441
a
Token a
Feature activation+1.132
gun
Token gun
Feature activation+0.004
to
Token to
Feature activation+0.000
class
Token class
Feature activation+0.000
."
Token."
Feature activation+0.000
donkey
Token donkey
Feature activation+0.000
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
on
Token on
Feature activation+0.000
or
Token or
Feature activation+0.311
a
Token a
Feature activation+2.423
wagon
Token wagon
Feature activation+1.072
to
Token to
Feature activation+0.573
travel
Token travel
Feature activation+0.000
in
Token in
Feature activation+0.003
,
Token,
Feature activation+0.000
11
Token 11
Feature activation+0.000
seats
Token seats
Feature activation+0.000
to
Token to
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+2.386
to
Token to
Feature activation+0.000
N
Token N
Feature activation+0.000
CP
TokenCP
Feature activation+0.000
and
Token and
Feature activation+0.000
sought
Token sought
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
silly
Token silly
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
US
Token US
Feature activation+0.000
maintains
Token maintains
Feature activation+2.386
nuclear
Token nuclear
Feature activation+0.013
weapons
Token weapons
Feature activation+0.214
to
Token to
Feature activation+0.095
prevent
Token prevent
Feature activation+0.000
such
Token such
Feature activation+0.000
house
Token house
Feature activation+0.000
,
Token,
Feature activation+0.000
room
Token room
Feature activation+0.000
to
Token to
Feature activation+0.000
garden
Token garden
Feature activation+0.000
and
Token and
Feature activation+2.365
have
Token have
Feature activation+0.543
goats
Token goats
Feature activation+0.348
and
Token and
Feature activation+0.000
chickens
Token chickens
Feature activation+0.000
and
Token and
Feature activation+0.031
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
to
Token to
Feature activation+0.000
blow
Token blow
Feature activation+0.000
out
Token out
Feature activation+0.000
piece
Token piece
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.037
take
Token take
Feature activation+0.568
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
pause
Token pause
Feature activation+0.000
,
Token,
Feature activation+0.000
M
Token M
Feature activation+0.356
to
Token to
Feature activation+0.000
mute
Token mute
Feature activation+0.000
,
Token,
Feature activation+2.241
left
Token left
Feature activation+0.781
and
Token and
Feature activation+0.000
right
Token right
Feature activation+0.000
arrows
Token arrows
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
experiment
Token experiment
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.930
're
Token're
Feature activation+1.663
coming
Token coming
Feature activation+2.196
to
Token to
Feature activation+2.039
you
Token you
Feature activation+1.224
for
Token for
Feature activation+0.000
help
Token help
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.000
episode
Token episode
Feature activation+0.782
to
Token to
Feature activation+0.763
episode
Token episode
Feature activation+2.193
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
my
Token my
Feature activation+0.000
and
Token and
Feature activation+0.000
right
Token right
Feature activation+0.000
arrows
Token arrows
Feature activation+0.000
to
Token to
Feature activation+0.000
seek
Token seek
Feature activation+0.000
,
Token,
Feature activation+2.193
up
Token up
Feature activation+0.974
and
Token and
Feature activation+0.030
down
Token down
Feature activation+1.254
arrows
Token arrows
Feature activation+0.764
for
Token for
Feature activation+0.000

Top DFA by src position
MAX = 3.897

Features
Token Features
Feature activation-0.002
Top resid features:
4
Token 4
Feature activation-0.006
Top resid features:
books
Token books
Feature activation-0.038
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
magic
Token magic
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+3.890
Top resid features:
unlock
Token unlock
Feature activation+0.026
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
study
Token study
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.076
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
cell
Token cell
Feature activation-0.000
Top resid features:
lines
Token lines
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
genes
Token genes
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+2.267
Top resid features:
be
Token be
Feature activation+1.583
Top resid features:
revoked
Token revoked
Feature activation+0.086
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
banned
Token banned
Feature activation-0.030
Top resid features:
;
Token;
Feature activation+0.007
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
moved
Token moved
Feature activation-0.011
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
holding
Token holding
Feature activation-0.002
Top resid features:
cell
Token cell
Feature activation-0.027
Top resid features:
to
Token to
Feature activation+3.769
Top resid features:
holding
Token holding
Feature activation-0.008
Top resid features:
cell
Token cell
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.004
Top resid features:
is
Tokenis
Feature activation+0.010
Top resid features:
both
Token both
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.115
Top resid features:
city
Token city
Feature activation+0.072
Top resid features:
to
Token to
Feature activation+2.767
Top resid features:
watch
Token watch
Feature activation+0.661
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
city
Token city
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
It
TokenIt
Feature activation-0.003
Top resid features:
will
Token will
Feature activation-0.004
Top resid features:
go
Token go
Feature activation-0.007
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
community
Token community
Feature activation-0.085
Top resid features:
to
Token to
Feature activation+3.678
Top resid features:
community
Token community
Feature activation-0.070
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
from
Token from
Feature activation-0.016
Top resid features:
village
Token village
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+1.058
Top resid features:
community
Token community
Feature activation-0.042
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
from
Token from
Feature activation-0.009
Top resid features:
village
Token village
Feature activation-0.074
Top resid features:
to
Token to
Feature activation+2.455
Top resid features:
village
Token village
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
from
Token from
Feature activation-0.018
Top resid features:
town
Token town
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
receipt
Token receipt
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
merchant
Token merchant
Feature activation-0.036
Top resid features:
copy
Token copy
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+1.790
Top resid features:
the
Token the
Feature activation+0.149
Top resid features:
bill
Token bill
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
the
Token the
Feature activation-0.055
Top resid features:
receipt
Token receipt
Feature activation-0.020
Top resid features:
or
Token or
Feature activation-0.009
Top resid features:
target
Token target
Feature activation-0.040
Top resid features:
weak
Token weak
Feature activation-0.376
Top resid features:
-
Token-
Feature activation-0.014
Top resid features:
points
Tokenpoints
Feature activation-0.050
Top resid features:
to
Token to
Feature activation+3.897
Top resid features:
blow
Token blow
Feature activation+0.012
Top resid features:
out
Token out
Feature activation+0.003
Top resid features:
entire
Token entire
Feature activation-0.011
Top resid features:
sections
Token sections
Feature activation-0.007
Top resid features:
of
Token of
Feature activation-0.014
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.003
Top resid features:
is
Tokenis
Feature activation+0.006
Top resid features:
both
Token both
Feature activation-0.004
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
city
Token city
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+2.830
Top resid features:
watch
Token watch
Feature activation+0.231
Top resid features:
and
Token and
Feature activation+0.128
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
city
Token city
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.022
Top resid features:
D
Token D
Feature activation-0.028
Top resid features:
IL
TokenIL
Feature activation-0.028
Top resid features:
DO
TokenDO
Feature activation-0.039
Top resid features:
to
Token to
Feature activation+3.010
Top resid features:
class
Token class
Feature activation+0.093
Top resid features:
before
Token before
Feature activation+0.053
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
would
Token would
Feature activation+0.017
Top resid features:
get
Token get
Feature activation+0.003
Top resid features:
money
Token money
Feature activation-0.009
Top resid features:
to
Token to
Feature activation+0.114
Top resid features:
hire
Token hire
Feature activation+0.079
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
donkey
Token donkey
Feature activation-0.040
Top resid features:
to
Token to
Feature activation+2.369
Top resid features:
ride
Token ride
Feature activation+0.228
Top resid features:
on
Token on
Feature activation+0.096
Top resid features:
or
Token or
Feature activation+0.064
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
wagon
Token wagon
Feature activation+0.000
Top resid features:
JD
TokenJD
Feature activation-0.005
Top resid features:
chief
Token chief
Feature activation-0.009
Top resid features:
offered
Token offered
Feature activation-0.003
Top resid features:
11
Token 11
Feature activation+0.005
Top resid features:
seats
Token seats
Feature activation+0.110
Top resid features:
to
Token to
Feature activation+2.700
Top resid features:
Congress
Token Congress
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
1
Token 1
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
N
Token N
Feature activation+0.000
Top resid features:
doesn
Token doesn
Feature activation-0.002
Top resid features:
't
Token't
Feature activation+0.004
Top resid features:
maintain
Token maintain
Feature activation+0.006
Top resid features:
aircraft
Token aircraft
Feature activation-0.061
Top resid features:
carriers
Token carriers
Feature activation-0.104
Top resid features:
to
Token to
Feature activation+2.851
Top resid features:
wage
Token wage
Feature activation+0.015
Top resid features:
war
Token war
Feature activation+0.008
Top resid features:
against
Token against
Feature activation+0.032
Top resid features:
Russia
Token Russia
Feature activation+0.012
Top resid features:
or
Token or
Feature activation+0.019
Top resid features:
my
Token my
Feature activation-0.002
Top resid features:
modest
Token modest
Feature activation-0.010
Top resid features:
house
Token house
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
room
Token room
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+2.500
Top resid features:
garden
Token garden
Feature activation+0.251
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
goats
Token goats
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
or
Token or
Feature activation-0.005
Top resid features:
target
Token target
Feature activation+0.010
Top resid features:
weak
Token weak
Feature activation-0.008
Top resid features:
-
Token-
Feature activation-0.263
Top resid features:
points
Tokenpoints
Feature activation-0.123
Top resid features:
to
Token to
Feature activation+3.217
Top resid features:
blow
Token blow
Feature activation+0.030
Top resid features:
out
Token out
Feature activation+0.004
Top resid features:
entire
Token entire
Feature activation-0.011
Top resid features:
sections
Token sections
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
or
Token or
Feature activation-0.222
Top resid features:
target
Token target
Feature activation-0.009
Top resid features:
weak
Token weak
Feature activation-0.012
Top resid features:
-
Token-
Feature activation-0.008
Top resid features:
points
Tokenpoints
Feature activation-0.010
Top resid features:
to
Token to
Feature activation+3.061
Top resid features:
blow
Token blow
Feature activation+0.055
Top resid features:
out
Token out
Feature activation+0.006
Top resid features:
entire
Token entire
Feature activation-0.011
Top resid features:
sections
Token sections
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
play
Token play
Feature activation+0.006
Top resid features:
or
Token or
Feature activation+0.005
Top resid features:
pause
Token pause
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
M
Token M
Feature activation-0.075
Top resid features:
to
Token to
Feature activation+2.044
Top resid features:
mute
Token mute
Feature activation+0.758
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
left
Token left
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
not
Token not
Feature activation+0.009
Top resid features:
coming
Token coming
Feature activation-0.011
Top resid features:
to
Token to
Feature activation-0.111
Top resid features:
you
Token you
Feature activation+0.056
Top resid features:
to
Token to
Feature activation+2.690
Top resid features:
experiment
Token experiment
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
They
Token They
Feature activation+0.042
Top resid features:
're
Token're
Feature activation+0.008
Top resid features:
coming
Token coming
Feature activation+0.000
Top resid features:
season
Token season
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.203
Top resid features:
season
Token season
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.124
Top resid features:
episode
Token episode
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+2.412
Top resid features:
episode
Token episode
Feature activation+0.063
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
play
Token play
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.011
Top resid features:
pause
Token pause
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
M
Token M
Feature activation-0.058
Top resid features:
to
Token to
Feature activation+2.300
Top resid features:
mute
Token mute
Feature activation+0.185
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
left
Token left
Feature activation-0.084
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
right
Token right
Feature activation-0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.03

Head 3: 0.05

Head 4: 0.03

Head 5: 0.03

Head 6: 0.04

Head 7: 0.55

Head 8: 0.04

Head 9: 0.04

Head 10: 0.05

Head 11: 0.04

Positive logits

to2.50

unto2.26

toc2.17

••2.14

estern2.13

to2.03

rams1.99

Thumbnails1.93

Disclaimer1.87

tein1.84

esi1.84

1.80

sels1.79

=>1.77

vernment1.75

Savior1.73

scissors1.73

To1.70

Js1.68

To1.68

Negative logits

NOR-2.13

ench-2.08

etsk-2.07

Advanced-1.86

IMAGES-1.73

WARD-1.73

competitive-1.66

CU-1.64

Mond-1.63

breaches-1.60

hy-1.60

indu-1.60

natureconservancy-1.60

endiary-1.57

ben-1.56

iform-1.56

RANT-1.55

RF-1.54

rick-1.54

ibe-1.53

INTERVAL 3.109 - 3.455
CONTAINS 0.000%

unlock
Token unlock
Feature activation+0.000
and
Token and
Feature activation+0.124
study
Token study
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.813
Ċ
TokenĊ
Feature activation+0.148
16
Token16
Feature activation+3.455
mysterious
Token mysterious
Feature activation+1.220
cards
Token cards
Feature activation+0.885
to
Token to
Feature activation+0.366
collect
Token collect
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.110
moved
Token moved
Feature activation+0.000
from
Token from
Feature activation+0.000
holding
Token holding
Feature activation+0.000
cell
Token cell
Feature activation+0.000
to
Token to
Feature activation+0.000
holding
Token holding
Feature activation+3.142
cell
Token cell
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.000
one
Token one
Feature activation+0.000
filthy
Token filthy
Feature activation+0.000
revoked
Token revoked
Feature activation+0.000
and
Token and
Feature activation+1.190
banned
Token banned
Feature activation+0.000
;
Token;
Feature activation+1.120
and
Token and
Feature activation+1.291
for
Token for
Feature activation+3.399
a
Token a
Feature activation+1.359
comprehensive
Token comprehensive
Feature activation+0.297
public
Token public
Feature activation+0.000
enqu
Token enqu
Feature activation+0.000
iry
Tokeniry
Feature activation+0.314

INTERVAL 2.764 - 3.109
CONTAINS 0.000%

from
Token from
Feature activation+0.000
community
Token community
Feature activation+0.000
to
Token to
Feature activation+0.227
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.226
from
Token from
Feature activation+2.929
village
Token village
Feature activation+1.978
to
Token to
Feature activation+0.093
village
Token village
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+2.837
from
Token from
Feature activation+2.929
village
Token village
Feature activation+1.978
to
Token to
Feature activation+0.093
village
Token village
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+2.837
town
Token town
Feature activation+0.793
to
Token to
Feature activation+0.040
town
Token town
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
and
Token and
Feature activation+2.991
a
Token a
Feature activation+2.553
city
Token city
Feature activation+0.448
that
Token that
Feature activation+0.000
watches
Token watches
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 2.418 - 2.764
CONTAINS 0.001%

donkey
Token donkey
Feature activation+0.000
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
on
Token on
Feature activation+0.000
or
Token or
Feature activation+0.311
a
Token a
Feature activation+2.423
wagon
Token wagon
Feature activation+1.072
to
Token to
Feature activation+0.573
travel
Token travel
Feature activation+0.000
in
Token in
Feature activation+0.003
,
Token,
Feature activation+0.000
take
Token take
Feature activation+0.568
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
to
Token to
Feature activation+0.000
blow
Token blow
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000
,
Token,
Feature activation+1.212
the
Token the
Feature activation+0.860
receipt
Token receipt
Feature activation+2.714
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
take
Token take
Feature activation+0.011
out
Tokenout
Feature activation+0.742
bag
Token bag
Feature activation+0.440
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.000
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
and
Token and
Feature activation+2.991
a
Token a
Feature activation+2.553
city
Token city
Feature activation+0.448
that
Token that
Feature activation+0.000
watches
Token watches
Feature activation+0.000
you
Token you
Feature activation+0.000
back
Token back
Feature activation+0.000
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
for
Token for
Feature activation+0.000
taking
Token taking
Feature activation+2.441
a
Token a
Feature activation+1.132
gun
Token gun
Feature activation+0.004
to
Token to
Feature activation+0.000
class
Token class
Feature activation+0.000
."
Token."
Feature activation+0.000

INTERVAL 2.073 - 2.418
CONTAINS 0.002%

piece
Token piece
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.037
take
Token take
Feature activation+0.568
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
riff
Token riff
Feature activation+0.000
to
Token to
Feature activation+1.515
a
Token a
Feature activation+2.119
clip
Token clip
Feature activation+1.023
from
Token from
Feature activation+1.699
some
Token some
Feature activation+1.209
television
Token television
Feature activation+0.000
show
Token show
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.219
Ċ
TokenĊ
Feature activation+1.726
C
TokenC
Feature activation+2.108
annon
Tokenannon
Feature activation+0.196
in
Token in
Feature activation+0.082
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
moon
Token moon
Feature activation+0.000
.
Token.
Feature activation+0.000
Religion
Token Religion
Feature activation+0.000
flies
Token flies
Feature activation+2.115
you
Token you
Feature activation+1.485
into
Token into
Feature activation+0.213
buildings
Token buildings
Feature activation+0.254
"
Token"
Feature activation+0.000
-
Token -
Feature activation+0.000
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
to
Token to
Feature activation+0.000
blow
Token blow
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 1.727 - 2.073
CONTAINS 0.002%

-
Token-
Feature activation+0.000
M
TokenM
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
and
Token and
Feature activation+0.000
explains
Token explains
Feature activation+1.852
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
interview
Token interview
Feature activation+0.000
he
Token he
Feature activation+0.000
shared
Token shared
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
and
Token and
Feature activation+0.000
led
Token led
Feature activation+1.871
to
Token to
Feature activation+0.220
fears
Token fears
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
bank
Token bank
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+0.000
receipt
Token receipt
Feature activation+0.000
,
Token,
Feature activation+1.140
the
Token the
Feature activation+0.766
merchant
Token merchant
Feature activation+1.948
copy
Token copy
Feature activation+1.585
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000
,
Token,
Feature activation+1.212
95
Token 95
Feature activation+0.000
%
Token%
Feature activation+0.000
fluor
Token fluor
Feature activation+0.000
ides
Tokenides
Feature activation+0.025
,
Token,
Feature activation+0.124
12
Token 12
Feature activation+2.008
%
Token%
Feature activation+0.957
to
Token to
Feature activation+0.000
35
Token 35
Feature activation+0.000
%
Token%
Feature activation+0.000
T
Token T
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.037
take
Token take
Feature activation+0.568
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
points
Tokenpoints
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.382 - 1.727
CONTAINS 0.004%

)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
guard
Token guard
Feature activation+0.462
(
Token (
Feature activation+1.461
to
Tokento
Feature activation+1.541
his
Token his
Feature activation+1.042
left
Token left
Feature activation+1.146
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
moon
Token moon
Feature activation+0.000
.
Token.
Feature activation+0.000
Religion
Token Religion
Feature activation+0.000
flies
Token flies
Feature activation+2.115
you
Token you
Feature activation+1.485
into
Token into
Feature activation+0.213
buildings
Token buildings
Feature activation+0.254
"
Token"
Feature activation+0.000
-
Token -
Feature activation+0.000
what
Token what
Feature activation+0.000
turn
Token turn
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
qu
Tokenqu
Feature activation+0.000
eat
Tokeneat
Feature activation+0.000
hed
Tokenhed
Feature activation+1.706
the
Token the
Feature activation+0.029
archive
Token archive
Feature activation+0.755
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
V
Token V
Feature activation+0.000
38
Token38
Feature activation+0.000
).
Token).
Feature activation+0.000
Then
Token Then
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
visits
Token visits
Feature activation+1.646
Joseph
Token Joseph
Feature activation+0.519
to
Token to
Feature activation+0.261
ensure
Token ensure
Feature activation+0.000
him
Token him
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
the
Token the
Feature activation+0.000
clueless
Token clueless
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.508
increasingly
Token increasingly
Feature activation+0.000
powerful
Token powerful
Feature activation+0.222
political
Token political
Feature activation+0.000
lobb
Token lobb
Feature activation+0.000
ies
Tokenies
Feature activation+0.000

INTERVAL 1.036 - 1.382
CONTAINS 0.008%

000
Token000
Feature activation+0.000
while
Token while
Feature activation+0.000
work
Token work
Feature activation+0.000
visa
Token visa
Feature activation+0.000
fell
Token fell
Feature activation+1.318
by
Token by
Feature activation+1.285
7
Token 7
Feature activation+0.988
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+2.322
to
Token to
Feature activation+0.896
147
Token 147
Feature activation+0.000
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
on
Token on
Feature activation+0.000
or
Token or
Feature activation+0.311
a
Token a
Feature activation+2.423
wagon
Token wagon
Feature activation+1.072
to
Token to
Feature activation+0.573
travel
Token travel
Feature activation+0.000
in
Token in
Feature activation+0.003
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.385
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token -
Feature activation+0.000
o
Tokeno
Feature activation+0.000
flag
Token flag
Feature activation+0.000
tells
Token tells
Feature activation+1.145
it
Token it
Feature activation+0.462
to
Token to
Feature activation+0.000
name
Token name
Feature activation+0.000
the
Token the
Feature activation+0.000
output
Token output
Feature activation+0.000
Fri
TokenFri
Feature activation+0.000
to
Token to
Feature activation+0.108
07
Token 07
Feature activation+0.109
00
Token00
Feature activation+1.574
-
Token-
Feature activation+0.288
2200
Token2200
Feature activation+1.051
Mon
Token Mon
Feature activation+0.357
-
Token-
Feature activation+0.000
Sat
TokenSat
Feature activation+0.000
:
Token :
Feature activation+0.000
How
Token How
Feature activation+0.000
,
Token,
Feature activation+0.000
down
Token down
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
six
Token six
Feature activation+0.000
points
Token points
Feature activation+1.061
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Pra
Token Pra
Feature activation+0.000
iries
Tokeniries
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.691 - 1.036
CONTAINS 0.016%

give
Token give
Feature activation+0.000
different
Token different
Feature activation+0.000
looks
Token looks
Feature activation+0.000
and
Token and
Feature activation+1.039
two
Token two
Feature activation+1.009
versions
Token versions
Feature activation+0.972
of
Token of
Feature activation+0.712
beauty
Token beauty
Feature activation+0.000
mark
Token mark
Feature activation+0.000
tattoos
Token tattoos
Feature activation+0.000
!
Token!
Feature activation+0.000
directed
Tokendirected
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
to
Token to
Feature activation+0.301
the
Token the
Feature activation+0.977
inf
Token inf
Feature activation+0.000
idel
Tokenidel
Feature activation+0.061
âĢĶ
TokenâĢĶ
Feature activation+0.000
is
Tokenis
Feature activation+0.000
the
Token the
Feature activation+0.000
score
Token score
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
with
Token with
Feature activation+0.000
three
Token three
Feature activation+0.000
assists
Token assists
Feature activation+0.916
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
National
TokenNational
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
since
Token since
Feature activation+0.000
August
Token August
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
while
Token while
Feature activation+0.000
diesel
Token diesel
Feature activation+0.459
prices
Token prices
Feature activation+0.917
reached
Token reached
Feature activation+0.000
their
Token their
Feature activation+0.000
peak
Token peak
Feature activation+0.000
since
Token since
Feature activation+0.000
August
Token August
Feature activation+0.000
Group
Token Group
Feature activation+0.000
announced
Token announced
Feature activation+0.000
a
Token a
Feature activation+0.000
similar
Token similar
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.777
Mid
Token Mid
Feature activation+0.499
land
Tokenland
Feature activation+0.369
across
Token across
Feature activation+0.000
from
Token from
Feature activation+0.000
Dow
Token Dow
Feature activation+0.000

INTERVAL 0.345 - 0.691
CONTAINS 0.050%

simply
Token simply
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
another
Token another
Feature activation+0.000
but
Token but
Feature activation+0.727
to
Token to
Feature activation+0.440
one
Token one
Feature activation+0.000
another
Token another
Feature activation+0.000
through
Token through
Feature activation+0.000
Christ
Token Christ
Feature activation+0.000
.
Token.
Feature activation+0.000
real
Token real
Feature activation+0.000
or
Token or
Feature activation+0.000
perceived
Token perceived
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
more
Token more
Feature activation+0.370
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
stick
Token stick
Feature activation+0.000
by
Token by
Feature activation+0.277
piece
Token piece
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.037
take
Token take
Feature activation+0.568
out
Token out
Feature activation+0.897
their
Token their
Feature activation+0.414
turrets
Token turrets
Feature activation+2.280
or
Token or
Feature activation+1.865
target
Token target
Feature activation+2.604
weak
Token weak
Feature activation+2.360
-
Token-
Feature activation+0.677
D
TokenD
Feature activation+0.000
game
Token game
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
something
Token something
Feature activation+0.496
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
animation
Token animation
Feature activation+0.074
system
Token system
Feature activation+0.144
stomp
Token stomp
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
officer
Token officer
Feature activation+0.000
,
Token,
Feature activation+0.000
recommended
Token recommended
Feature activation+0.000
that
Token that
Feature activation+0.051
two
Token two
Feature activation+0.402
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.000
officers
Token officers
Feature activation+0.000
keep
Token keep
Feature activation+0.000

INTERVAL 0.000 - 0.345
CONTAINS 99.917%

the
Token the
Feature activation+0.000
Moon
Token Moon
Feature activation+0.000
."
Token."
Feature activation+0.000
Although
Token Although
Feature activation+0.000
the
Token the
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
provide
Token provide
Feature activation+0.000
a
Token a
Feature activation+0.000
reminder
Token reminder
Feature activation+0.000
of
Token of
Feature activation+0.000
past
Token past
Feature activation+0.000
second
Token second
Feature activation+0.000
oldest
Token oldest
Feature activation+0.000
continuously
Token continuously
Feature activation+0.000
public
Token public
Feature activation+0.000
high
Token high
Feature activation+0.000
school
Token school
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
.
Token.
Feature activation+0.000
Games
Token Games
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
distance
Token distance
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
log
Token log
Feature activation+0.000
book
Token book
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
Mou
Token Mou
Feature activation+0.000
all
Tokenall
Feature activation+0.000
imi
Tokenimi
Feature activation+0.000
described
Token described
Feature activation+0.000
the
Token the
Feature activation+0.000
annual
Token annual
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
draft
Token draft
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
going
Tokengoing
Feature activation+0.000
his
Token his
Feature activation+0.000
final
Token final
Feature activation+0.000
year
Token year
Feature activation+0.000
of
Token of
Feature activation+0.000
college
Token college
Feature activation+0.000
eligibility
Token eligibility
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 H7.7: (feature 5028)

TOP ACTIVATIONS
MAX = 3.600

justice
Token justice
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
hand
Token hand
Feature activation+0.000
and
Token and
Feature activation+3.600
grat
Token grat
Feature activation+0.533
uit
Tokenuit
Feature activation+0.000
ously
Tokenously
Feature activation+1.735
cruel
Token cruel
Feature activation+0.721
behavior
Token behavior
Feature activation+0.455
spread
Token spread
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+3.473
T
Token T
Feature activation+1.353
-
Token-
Feature activation+0.743
V
TokenV
Feature activation+2.144
irus
Tokenirus
Feature activation+1.726
in
Token in
Feature activation+0.157
Tamil
Token Tamil
Feature activation+0.000
Nadu
Token Nadu
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
south
Token south
Feature activation+0.000
and
Token and
Feature activation+3.337
Him
Token Him
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
al
Tokenal
Feature activation+0.493
Pradesh
Token Pradesh
Feature activation+1.701
and
Token and
Feature activation+1.380
ina
Tokenina
Feature activation+0.000
usk
Tokenusk
Feature activation+0.000
as
Tokenas
Feature activation+0.000
on
Token on
Feature activation+0.000
guitar
Token guitar
Feature activation+0.000
,
Token,
Feature activation+3.262
Al
Token Al
Feature activation+0.333
g
Tokeng
Feature activation+0.000
im
Tokenim
Feature activation+0.283
ant
Tokenant
Feature activation+1.127
as
Tokenas
Feature activation+1.171
,
Token,
Feature activation+0.000
Pl
Token Pl
Feature activation+0.000
utonium
Tokenutonium
Feature activation+0.000
in
Token in
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
,
Token,
Feature activation+3.261
in
Token in
Feature activation+0.185
modern
Token modern
Feature activation+0.000
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
Turkey
Token Turkey
Feature activation+0.000
trust
Token trust
Feature activation+0.000
in
Token in
Feature activation+0.000
cash
Token cash
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+3.178
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
dis
Tokendis
Feature activation+0.000
gu
Token gu
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
,
Token,
Feature activation+0.000
40
Token 40
Feature activation+3.118
m
Token m
Feature activation+0.802
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Ce
Token Ce
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
ro
Token ro
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
kitchen
Token kitchen
Feature activation+0.000
,
Token,
Feature activation+3.113
un
Token un
Feature activation+0.295
ref
Tokenref
Feature activation+0.000
riger
Tokenriger
Feature activation+0.000
ated
Tokenated
Feature activation+0.563
,
Token,
Feature activation+0.000
9
Token9
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
and
Token and
Feature activation+1.979
to
Token to
Feature activation+2.851
increase
Token increase
Feature activation+0.752
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
AW
TokenAW
Feature activation+0.000
S
TokenS
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+1.763
the
Token the
Feature activation+0.998
ability
Token ability
Feature activation+1.772
of
Token of
Feature activation+2.846
Te
Token Te
Feature activation+0.000
emo
Tokenemo
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
Te
Token Te
Feature activation+0.000
making
Token making
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
mornings
Token mornings
Feature activation+0.000
,
Token,
Feature activation+2.833
shuff
Token shuff
Feature activation+0.377
ling
Tokenling
Feature activation+0.271
children
Token children
Feature activation+0.000
off
Token off
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.480
compassion
Token compassion
Feature activation+0.542
in
Token in
Feature activation+0.434
his
Token his
Feature activation+0.000
heart
Token heart
Feature activation+0.000
and
Token and
Feature activation+2.833
steel
Token steel
Feature activation+1.314
in
Token in
Feature activation+0.751
his
Token his
Feature activation+0.000
spine
Token spine
Feature activation+0.000
.
Token.
Feature activation+0.000
Group
Token Group
Feature activation+0.000
announced
Token announced
Feature activation+0.000
a
Token a
Feature activation+0.241
similar
Token similar
Feature activation+0.265
project
Token project
Feature activation+0.594
in
Token in
Feature activation+2.807
Mid
Token Mid
Feature activation+1.546
land
Tokenland
Feature activation+1.936
across
Token across
Feature activation+0.209
from
Token from
Feature activation+0.000
Dow
Token Dow
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+2.760
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
was
Token was
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
from
Token from
Feature activation+0.000
Syri
Token Syri
Feature activation+0.000
za
Tokenza
Feature activation+0.000
in
Token in
Feature activation+0.000
Greece
Token Greece
Feature activation+0.000
and
Token and
Feature activation+2.720
Pod
Token Pod
Feature activation+0.000
em
Tokenem
Feature activation+0.000
os
Tokenos
Feature activation+0.658
in
Token in
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
only
Token only
Feature activation+0.000
boom
Token boom
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bottom
Token bottom
Feature activation+0.000
and
Token and
Feature activation+2.698
w
Token w
Feature activation+0.766
isp
Tokenisp
Feature activation+1.040
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
1916
Token 1916
Feature activation+0.000
,
Token,
Feature activation+0.673
Truman
Token Truman
Feature activation+1.750
in
Token in
Feature activation+0.691
1948
Token 1948
Feature activation+0.051
,
Token,
Feature activation+2.664
Kennedy
Token Kennedy
Feature activation+1.169
in
Token in
Feature activation+0.068
1960
Token 1960
Feature activation+0.000
,
Token,
Feature activation+1.168
and
Token and
Feature activation+0.576
country
Token country
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
owing
Token owing
Feature activation+0.182
something
Token something
Feature activation+0.541
to
Token to
Feature activation+2.539
a
Token a
Feature activation+2.389
club
Token club
Feature activation+1.114
in
Token in
Feature activation+1.031
another
Token another
Feature activation+0.000
country
Token country
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
in
Token in
Feature activation+0.000
2004
Token 2004
Feature activation+0.000
to
Token to
Feature activation+0.079
24
Token 24
Feature activation+1.858
percent
Token percent
Feature activation+2.472
today
Token today
Feature activation+0.000
),
Token),
Feature activation+0.000
college
Token college
Feature activation+0.000
graduates
Token graduates
Feature activation+0.000
(
Token (
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
poll
Token poll
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+2.436
especially
Token especially
Feature activation+0.000
[
Token [
Feature activation+0.000
M
TokenM
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
man
Tokenman
Feature activation+0.000

Top DFA by src position
MAX = 4.257

lies
Token lies
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
or
Token or
Feature activation-0.007
Top resid features:
between
Token between
Feature activation-0.005
Top resid features:
justice
Token justice
Feature activation-0.017
Top resid features:
on
Token on
Feature activation+4.132
Top resid features:
the
Token the
Feature activation+0.093
Top resid features:
one
Token one
Feature activation+0.018
Top resid features:
hand
Token hand
Feature activation-0.076
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
grat
Token grat
Feature activation+0.000
Top resid features:
like
Token like
Feature activation-0.004
Top resid features:
T
Token T
Feature activation+0.178
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
V
TokenV
Feature activation-0.011
Top resid features:
irus
Tokenirus
Feature activation-0.129
Top resid features:
in
Token in
Feature activation+4.257
Top resid features:
R
Token R
Feature activation+0.001
Top resid features:
acco
Tokenacco
Feature activation-0.005
Top resid features:
on
Tokenon
Feature activation-0.001
Top resid features:
City
Token City
Feature activation-0.012
Top resid features:
x
Token x
Feature activation-0.022
Top resid features:
in
Token in
Feature activation+0.052
Top resid features:
Kerala
Token Kerala
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.031
Top resid features:
Tamil
Token Tamil
Feature activation+0.012
Top resid features:
Nadu
Token Nadu
Feature activation+0.047
Top resid features:
in
Token in
Feature activation+3.240
Top resid features:
the
Token the
Feature activation+0.387
Top resid features:
south
Token south
Feature activation+0.057
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
Him
Token Him
Feature activation+0.000
Top resid features:
ach
Tokenach
Feature activation+0.000
Top resid features:
as
Tokenas
Feature activation-0.049
Top resid features:
Lag
Token Lag
Feature activation-0.017
Top resid features:
ina
Tokenina
Feature activation-0.002
Top resid features:
usk
Tokenusk
Feature activation-0.005
Top resid features:
as
Tokenas
Feature activation-0.004
Top resid features:
on
Token on
Feature activation+3.648
Top resid features:
guitar
Token guitar
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
Al
Token Al
Feature activation+0.000
Top resid features:
g
Tokeng
Feature activation+0.000
Top resid features:
im
Tokenim
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.015
Top resid features:
Greek
Token Greek
Feature activation-0.030
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
Pl
Token Pl
Feature activation-0.056
Top resid features:
utonium
Tokenutonium
Feature activation-0.090
Top resid features:
in
Token in
Feature activation+3.927
Top resid features:
Latin
Token Latin
Feature activation+0.067
Top resid features:
,
Token,
Feature activation-0.040
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
modern
Token modern
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.021
Top resid features:
trust
Token trust
Feature activation+0.021
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
cash
Token cash
Feature activation-0.005
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
general
Token general
Feature activation+3.657
Top resid features:
and
Token and
Feature activation+0.062
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.001
Top resid features:
deep
Token deep
Feature activation-0.033
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
100
Token 100
Feature activation+0.010
Top resid features:
m
Token m
Feature activation-0.166
Top resid features:
in
Token in
Feature activation+3.567
Top resid features:
the
Token the
Feature activation+0.260
Top resid features:
case
Token case
Feature activation+0.063
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
U
Token U
Feature activation-0.000
Top resid features:
ria
Tokenria
Feature activation-0.002
Top resid features:
findings
Token findings
Feature activation+0.030
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.023
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
ro
Token ro
Feature activation-0.002
Top resid features:
ach
Tokenach
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+1.852
Top resid features:
the
Token the
Feature activation+1.403
Top resid features:
kitchen
Token kitchen
Feature activation+0.245
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
un
Token un
Feature activation+0.000
Top resid features:
ref
Tokenref
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
7
Token 7
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
9
Token9
Feature activation+0.023
Top resid features:
percent
Token percent
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+3.226
Top resid features:
2017
Token 2017
Feature activation+0.054
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
increase
Token increase
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
ability
Token ability
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Te
Token Te
Feature activation-0.076
Top resid features:
emo
Tokenemo
Feature activation-0.122
Top resid features:
in
Token in
Feature activation+3.774
Top resid features:
which
Token which
Feature activation+0.004
Top resid features:
Te
Token Te
Feature activation-0.066
Top resid features:
emo
Tokenemo
Feature activation-0.017
Top resid features:
blind
Token blind
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
still
Token still
Feature activation-0.003
Top resid features:
together
Token together
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
making
Token making
Feature activation-0.042
Top resid features:
coffee
Token coffee
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+2.352
Top resid features:
the
Token the
Feature activation+0.862
Top resid features:
mornings
Token mornings
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
shuff
Token shuff
Feature activation+0.000
Top resid features:
ling
Tokenling
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
his
Token his
Feature activation+0.012
Top resid features:
soul
Token soul
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
compassion
Token compassion
Feature activation-0.022
Top resid features:
in
Token in
Feature activation+2.908
Top resid features:
his
Token his
Feature activation+0.537
Top resid features:
heart
Token heart
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
steel
Token steel
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
similar
Token similar
Feature activation-0.013
Top resid features:
project
Token project
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
Mid
Token Mid
Feature activation+0.003
Top resid features:
land
Tokenland
Feature activation-0.006
Top resid features:
across
Token across
Feature activation+3.746
Top resid features:
from
Token from
Feature activation+0.048
Top resid features:
Dow
Token Dow
Feature activation+0.001
Top resid features:
Diamond
Token Diamond
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
women
Token women
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
Democrats
Token Democrats
Feature activation+0.023
Top resid features:
in
Token in
Feature activation+0.047
Top resid features:
general
Token general
Feature activation+3.235
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
revealed
Token revealed
Feature activation+0.000
Top resid features:
drawn
Token drawn
Feature activation-0.019
Top resid features:
inspiration
Token inspiration
Feature activation-0.021
Top resid features:
from
Token from
Feature activation-0.039
Top resid features:
Syri
Token Syri
Feature activation-0.020
Top resid features:
za
Tokenza
Feature activation-0.081
Top resid features:
in
Token in
Feature activation+3.537
Top resid features:
Greece
Token Greece
Feature activation-0.017
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
Pod
Token Pod
Feature activation+0.000
Top resid features:
em
Tokenem
Feature activation+0.000
Top resid features:
os
Tokenos
Feature activation+0.000
Top resid features:
out
Token out
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
yielding
Token yielding
Feature activation-0.011
Top resid features:
only
Token only
Feature activation+0.022
Top resid features:
boom
Token boom
Feature activation+0.037
Top resid features:
at
Token at
Feature activation+2.843
Top resid features:
the
Token the
Feature activation+0.315
Top resid features:
bottom
Token bottom
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
w
Token w
Feature activation+0.000
Top resid features:
isp
Tokenisp
Feature activation+0.000
Top resid features:
1912
Token 1912
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.031
Top resid features:
1916
Token 1916
Feature activation+0.025
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
Truman
Token Truman
Feature activation-0.258
Top resid features:
in
Token in
Feature activation+2.467
Top resid features:
1948
Token 1948
Feature activation+0.042
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
Kennedy
Token Kennedy
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
1960
Token 1960
Feature activation+0.000
Top resid features:
owing
Token owing
Feature activation+0.007
Top resid features:
something
Token something
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.081
Top resid features:
club
Token club
Feature activation-0.132
Top resid features:
in
Token in
Feature activation+2.935
Top resid features:
another
Token another
Feature activation+0.068
Top resid features:
country
Token country
Feature activation+0.064
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Col
TokenCol
Feature activation-0.002
Top resid features:
rising
Tokenrising
Feature activation-0.001
Top resid features:
from
Token from
Feature activation-0.007
Top resid features:
18
Token 18
Feature activation+0.014
Top resid features:
percent
Token percent
Feature activation-0.001
Top resid features:
liberal
Token liberal
Feature activation+0.089
Top resid features:
in
Token in
Feature activation+2.566
Top resid features:
2004
Token 2004
Feature activation+0.273
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
24
Token 24
Feature activation+0.012
Top resid features:
percent
Token percent
Feature activation+0.015
Top resid features:
today
Token today
Feature activation+0.000
Top resid features:
doubt
Token doubt
Feature activation+0.001
Top resid features:
Democratic
Token Democratic
Feature activation+0.002
Top resid features:
poll
Token poll
Feature activation+0.005
Top resid features:
sters
Tokensters
Feature activation+0.022
Top resid features:
in
Token in
Feature activation+0.061
Top resid features:
general
Token general
Feature activation+2.786
Top resid features:
and
Token and
Feature activation+0.066
Top resid features:
especially
Token especially
Feature activation+0.000
Top resid features:
[
Token [
Feature activation+0.000
Top resid features:
M
TokenM
Feature activation+0.000
Top resid features:
ell
Tokenell
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.03

Head 6: 0.05

Head 7: 0.54

Head 8: 0.03

Head 9: 0.04

Head 10: 0.04

Head 11: 0.04

Positive logits

Hung2.03

Ukrain1.96

guyen1.89

Sith1.84

redes1.81

Oblivion1.77

Indones1.76

Ethiop1.72

veyard1.68

mosqu1.68

ulty1.66

Merrill1.66

elsewhere1.66

subsequ1.65

among1.63

preval1.63

Myanmar1.62

Ves1.61

Gamb1.61

intrins1.61

Negative logits

});-2.16

Catalog-2.05

nu-2.03

};-1.99

`,-1.97

};-1.97

});-1.90

)?-1.86

)|-1.85

},-1.82

SEE-1.77

\--1.77

');-1.77

.",-1.77

);-1.77

terms-1.76

},-1.75

-----------------1.72

));-1.72

>:-1.71

INTERVAL 3.240 - 3.600
CONTAINS 0.001%

spread
Token spread
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+3.473
T
Token T
Feature activation+1.353
-
Token-
Feature activation+0.743
V
TokenV
Feature activation+2.144
irus
Tokenirus
Feature activation+1.726
in
Token in
Feature activation+0.157
justice
Token justice
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
hand
Token hand
Feature activation+0.000
and
Token and
Feature activation+3.600
grat
Token grat
Feature activation+0.533
uit
Tokenuit
Feature activation+0.000
ously
Tokenously
Feature activation+1.735
cruel
Token cruel
Feature activation+0.721
behavior
Token behavior
Feature activation+0.455
ina
Tokenina
Feature activation+0.000
usk
Tokenusk
Feature activation+0.000
as
Tokenas
Feature activation+0.000
on
Token on
Feature activation+0.000
guitar
Token guitar
Feature activation+0.000
,
Token,
Feature activation+3.262
Al
Token Al
Feature activation+0.333
g
Tokeng
Feature activation+0.000
im
Tokenim
Feature activation+0.283
ant
Tokenant
Feature activation+1.127
as
Tokenas
Feature activation+1.171
,
Token,
Feature activation+0.000
Pl
Token Pl
Feature activation+0.000
utonium
Tokenutonium
Feature activation+0.000
in
Token in
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
,
Token,
Feature activation+3.261
in
Token in
Feature activation+0.185
modern
Token modern
Feature activation+0.000
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
Turkey
Token Turkey
Feature activation+0.000
Tamil
Token Tamil
Feature activation+0.000
Nadu
Token Nadu
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
south
Token south
Feature activation+0.000
and
Token and
Feature activation+3.337
Him
Token Him
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
al
Tokenal
Feature activation+0.493
Pradesh
Token Pradesh
Feature activation+1.701
and
Token and
Feature activation+1.380

INTERVAL 2.880 - 3.240
CONTAINS 0.000%

gu
Token gu
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
,
Token,
Feature activation+0.000
40
Token 40
Feature activation+3.118
m
Token m
Feature activation+0.802
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Ce
Token Ce
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
ro
Token ro
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
kitchen
Token kitchen
Feature activation+0.000
,
Token,
Feature activation+3.113
un
Token un
Feature activation+0.295
ref
Tokenref
Feature activation+0.000
riger
Tokenriger
Feature activation+0.000
ated
Tokenated
Feature activation+0.563
,
Token,
Feature activation+0.000
trust
Token trust
Feature activation+0.000
in
Token in
Feature activation+0.000
cash
Token cash
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+3.178
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
dis
Tokendis
Feature activation+0.000

INTERVAL 2.520 - 2.880
CONTAINS 0.001%

making
Token making
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
mornings
Token mornings
Feature activation+0.000
,
Token,
Feature activation+2.833
shuff
Token shuff
Feature activation+0.377
ling
Tokenling
Feature activation+0.271
children
Token children
Feature activation+0.000
off
Token off
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+1.763
the
Token the
Feature activation+0.998
ability
Token ability
Feature activation+1.772
of
Token of
Feature activation+2.846
Te
Token Te
Feature activation+0.000
emo
Tokenemo
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
Te
Token Te
Feature activation+0.000
from
Token from
Feature activation+0.000
Syri
Token Syri
Feature activation+0.000
za
Tokenza
Feature activation+0.000
in
Token in
Feature activation+0.000
Greece
Token Greece
Feature activation+0.000
and
Token and
Feature activation+2.720
Pod
Token Pod
Feature activation+0.000
em
Tokenem
Feature activation+0.000
os
Tokenos
Feature activation+0.658
in
Token in
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
1916
Token 1916
Feature activation+0.000
,
Token,
Feature activation+0.673
Truman
Token Truman
Feature activation+1.750
in
Token in
Feature activation+0.691
1948
Token 1948
Feature activation+0.051
,
Token,
Feature activation+2.664
Kennedy
Token Kennedy
Feature activation+1.169
in
Token in
Feature activation+0.068
1960
Token 1960
Feature activation+0.000
,
Token,
Feature activation+1.168
and
Token and
Feature activation+0.576
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+2.760
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
was
Token was
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000

INTERVAL 2.160 - 2.520
CONTAINS 0.001%

percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
,
Token,
Feature activation+0.331
and
Token and
Feature activation+0.938
1
Token 1
Feature activation+2.170
percent
Token percent
Feature activation+0.757
each
Token each
Feature activation+0.206
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
and
Token and
Feature activation+0.311
Democratic
Token Democratic
Feature activation+0.000
poll
Token poll
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
and
Token and
Feature activation+2.436
especially
Token especially
Feature activation+0.000
[
Token [
Feature activation+0.000
M
TokenM
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
man
Tokenman
Feature activation+0.000
Samoa
Token Samoa
Feature activation+0.000
will
Token will
Feature activation+0.000
vote
Token vote
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
will
Token will
Feature activation+2.350
a
Token a
Feature activation+0.569
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
of
Token of
Feature activation+0.000
cel
Token cel
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
green
Token green
Feature activation+0.000
,
Token,
Feature activation+0.906
and
Token and
Feature activation+2.211
c
Token c
Feature activation+0.000
uffed
Tokenuffed
Feature activation+0.112
or
Token or
Feature activation+0.000
cropped
Token cropped
Feature activation+0.093
denim
Token denim
Feature activation+0.037
his
Token his
Feature activation+0.000
natural
Token natural
Feature activation+0.000
habitat
Token habitat
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.626
is
Token is
Feature activation+2.403
how
Token how
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Ser
Token Ser
Feature activation+0.000
rel
Tokenrel
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 1.800 - 2.160
CONTAINS 0.003%

ucing
Tokenucing
Feature activation+0.460
the
Token the
Feature activation+0.226
federal
Token federal
Feature activation+0.102
excise
Token excise
Feature activation+0.000
tax
Token tax
Feature activation+0.550
to
Token to
Feature activation+2.024
$
Token $
Feature activation+1.311
16
Token16
Feature activation+1.555
per
Token per
Feature activation+0.809
barrel
Token barrel
Feature activation+0.281
on
Token on
Feature activation+0.232
the
Token the
Feature activation+0.000
Americas
Token Americas
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.000
th
Tokenth
Feature activation+1.804
placed
Token placed
Feature activation+1.238
team
Token team
Feature activation+0.000
in
Token in
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
-
Token-
Feature activation+0.000
ode
Tokenode
Feature activation+0.000
():
Token():
Feature activation+0.000
Argument
Token Argument
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.255
an
Token an
Feature activation+1.862
array
Token array
Feature activation+0.137
in
Token in
Feature activation+0.291
/
Token /
Feature activation+0.480
www
Tokenwww
Feature activation+0.960
/
Token/
Feature activation+0.592
albums
Token albums
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
time
Token time
Feature activation+0.000
list
Token list
Feature activation+0.000
,
Token,
Feature activation+1.914
and
Token and
Feature activation+2.096
was
Token was
Feature activation+1.982
reportedly
Token reportedly
Feature activation+0.000
David
Token David
Feature activation+0.000
Bowie
Token Bowie
Feature activation+0.000
on
Tokenon
Feature activation+0.000
...
Token...
Feature activation+0.431
Dan
TokenDan
Feature activation+0.000
x
Tokenx
Feature activation+0.155
,
Token,
Feature activation+0.584
a
Token a
Feature activation+1.817
Noble
Token Noble
Feature activation+0.609
M
Token M
Feature activation+0.197
unch
Tokenunch
Feature activation+0.000
kin
Tokenkin
Feature activation+0.521
(
Token (
Feature activation+0.000

INTERVAL 1.440 - 1.800
CONTAINS 0.005%

,
Token,
Feature activation+0.000
like
Token like
Feature activation+3.473
T
Token T
Feature activation+1.353
-
Token-
Feature activation+0.743
V
TokenV
Feature activation+2.144
irus
Tokenirus
Feature activation+1.726
in
Token in
Feature activation+0.157
R
Token R
Feature activation+0.000
acco
Tokenacco
Feature activation+0.000
on
Tokenon
Feature activation+0.000
City
Token City
Feature activation+0.000
Shinji
Token Shinji
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
ranks
Token ranks
Feature activation+0.000
,
Token,
Feature activation+0.152
and
Token and
Feature activation+1.522
the
Token the
Feature activation+0.507
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
superior
Token superior
Feature activation+0.000
in
Token in
Feature activation+0.000
some
Token some
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.105
and
Token and
Feature activation+1.652
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.153
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
hand
Token hand
Feature activation+0.000
and
Token and
Feature activation+3.600
grat
Token grat
Feature activation+0.533
uit
Tokenuit
Feature activation+0.000
ously
Tokenously
Feature activation+1.735
cruel
Token cruel
Feature activation+0.721
behavior
Token behavior
Feature activation+0.455
by
Token by
Feature activation+0.000
public
Token public
Feature activation+0.000
officials
Token officials
Feature activation+0.000
in
Token in
Feature activation+1.232
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Os
Token Os
Feature activation+0.000
om
Tokenom
Feature activation+0.000
atsu
Tokenatsu
Feature activation+1.556
,
Token,
Feature activation+0.289
a
Token a
Feature activation+0.615
scene
Token scene
Feature activation+0.239
involving
Token involving
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 1.080 - 1.440
CONTAINS 0.010%

Clay
Token Clay
Feature activation+0.000
counties
Token counties
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.443
also
Token also
Feature activation+0.586
performed
Token performed
Feature activation+1.321
best
Token best
Feature activation+0.273
in
Token in
Feature activation+0.615
McD
Token McD
Feature activation+0.000
owell
Tokenowell
Feature activation+0.000
,
Token,
Feature activation+0.000
reactors
Token reactors
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
stage
Token stage
Feature activation+0.216
and
Token and
Feature activation+1.337
Th
Token Th
Feature activation+0.000
-
Token-
Feature activation+0.000
232
Token232
Feature activation+1.599
/
Token/
Feature activation+0.000
U
TokenU
Feature activation+0.000
Art
Token Art
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.447
Gotham
Token Gotham
Feature activation+1.141
City
Token City
Feature activation+0.833
staff
Token staff
Feature activation+0.000
became
Token became
Feature activation+0.000
Art
Token Art
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
squid
Token squid
Feature activation+0.000
in
Token in
Feature activation+0.000
vegetable
Token vegetable
Feature activation+0.000
oil
Token oil
Feature activation+0.000
,
Token,
Feature activation+1.230
p
Token p
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
sac
Token sac
Feature activation+0.000
20
Token 20
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.000
system
Token system
Feature activation+0.000
and
Token and
Feature activation+1.101
comp
Token comp
Feature activation+0.000
iles
Tokeniles
Feature activation+0.000
base
Token base
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000

INTERVAL 0.720 - 1.080
CONTAINS 0.026%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.768
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
read
Token read
Feature activation+0.000
with
Token with
Feature activation+0.000
dismay
Token dismay
Feature activation+0.000
October
Token October
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
ballot
Token ballot
Feature activation+0.000
or
Token or
Feature activation+0.000
would
Token would
Feature activation+0.000
put
Token put
Feature activation+0.765
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.000
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
others
Token others
Feature activation+0.559
might
Token might
Feature activation+0.283
only
Token only
Feature activation+0.395
experience
Token experience
Feature activation+0.899
attacks
Token attacks
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
mornings
Token mornings
Feature activation+0.000
,
Token,
Feature activation+0.000
gu
Token gu
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
and
Token and
Feature activation+0.000
30
Token 30
Feature activation+1.038
m
Token m
Feature activation+0.170
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
were
Token were
Feature activation+0.000
harassed
Token harassed
Feature activation+0.000
by
Token by
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.724
did
Token did
Feature activation+0.831
nothing
Token nothing
Feature activation+0.252
when
Token when
Feature activation+0.000
an
Token an
Feature activation+0.000
electrical
Token electrical
Feature activation+0.000

INTERVAL 0.360 - 0.720
CONTAINS 0.055%

per
Token per
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
resident
Tokenresident
Feature activation+0.660
,
Token,
Feature activation+0.173
$
Token $
Feature activation+0.000
29
Token29
Feature activation+0.000
,
Token,
Feature activation+0.000
402
Token402
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
"
Token"
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
review
Token review
Feature activation+0.000
of
Token of
Feature activation+0.385
the
Token the
Feature activation+0.244
Al
Token Al
Feature activation+0.000
fa
Tokenfa
Feature activation+0.000
Romeo
Token Romeo
Feature activation+0.000
4
Token 4
Feature activation+0.000
turn
Token turn
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
saw
Token saw
Feature activation+0.593
the
Token the
Feature activation+0.000
big
Token big
Feature activation+0.000
picture
Token picture
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
/
Token/
Feature activation+0.000
block
Tokenblock
Feature activation+0.000
_
Token_
Feature activation+0.000
comm
Tokencomm
Feature activation+0.000
end
Tokenend
Feature activation+0.825
.
Token.
Feature activation+0.435
php
Tokenphp
Feature activation+0.143
on
Token on
Feature activation+0.000
line
Token line
Feature activation+0.000
16
Token 16
Feature activation+0.000
Warning
Token Warning
Feature activation+0.000
and
Token and
Feature activation+0.000
working
Token working
Feature activation+0.000
with
Token with
Feature activation+0.000
others
Token others
Feature activation+0.000
but
Token but
Feature activation+0.320
to
Token to
Feature activation+0.710
lack
Token lack
Feature activation+0.000
the
Token the
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.360
CONTAINS 99.898%

Ļ
TokenĻ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Im
Token Im
Feature activation+0.000
es
Tokenes
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
he
Token he
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Apple
TokenApple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
very
Token very
Feature activation+0.000
own
Token own
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
,
Token,
Feature activation+0.000
your
Token your
Feature activation+0.000
ego
Token ego
Feature activation+0.000
,
Token,
Feature activation+0.000
your
Token your
Feature activation+0.000
emotions
Token emotions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
everything
Token everything
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
use
Token use
Feature activation+0.000
your
Token your
Feature activation+0.000
smartphones
Token smartphones
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
screen
Token screen
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
conscious
Token conscious
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
sentient
Token sentient
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
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 H7.7: (feature 8582)

TOP ACTIVATIONS
MAX = 4.435

âĢĶ-
TokenâĢĶ-
Feature activation+0.000
2
Token2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
Place
Token Place
Feature activation+1.347
,
Token,
Feature activation+2.805
Player
Token Player
Feature activation+4.435
C
Token C
Feature activation+1.760
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.534
Added
TokenAdded
Feature activation+0.514
:
Token:
Feature activation+3.883
Xperia
Token Xperia
Feature activation+4.205
V
Token V
Feature activation+0.848
:
Token:
Feature activation+0.000
Initial
Token Initial
Feature activation+0.000
builds
Token builds
Feature activation+0.000
for
Token for
Feature activation+0.000
kicking
Token kicking
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.534
Added
TokenAdded
Feature activation+0.514
:
Token:
Feature activation+3.883
Xperia
Token Xperia
Feature activation+4.205
V
Token V
Feature activation+0.848
:
Token:
Feature activation+0.000
Initial
Token Initial
Feature activation+0.000
builds
Token builds
Feature activation+0.000
light
Token light
Feature activation+0.000
stre
Token stre
Feature activation+0.000
aked
Tokenaked
Feature activation+0.000
inst
Token inst
Feature activation+0.000
ants
Tokenants
Feature activation+0.000
!
Token!
Feature activation+3.837
Color
Token Color
Feature activation+0.535
G
Token G
Feature activation+0.000
els
Tokenels
Feature activation+0.539
:
Token:
Feature activation+0.000
Transform
Token Transform
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.405
,
Token,
Feature activation+1.108
Player
Token Player
Feature activation+3.625
B
Token B
Feature activation+0.283
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000
no
Token no
Feature activation+0.000
'/
Token '/
Feature activation+0.000
'.
Token'.
Feature activation+0.000
Mir
Token Mir
Feature activation+0.000
aj
Tokenaj
Feature activation+0.647
understands
Token understands
Feature activation+3.531
void
Token void
Feature activation+1.240
elements
Token elements
Feature activation+2.641
:
Token:
Feature activation+1.231
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.133
,
Token,
Feature activation+0.990
Player
Token Player
Feature activation+3.265
A
Token A
Feature activation+0.682
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Wind
Token Wind
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
:
Token:
Feature activation+0.000
6
Token 6
Feature activation+0.130
3
Token 3
Feature activation+1.445
.
Token.
Feature activation+3.231
Massachusetts
Token Massachusetts
Feature activation+0.344
:
Token:
Feature activation+0.000
6
Token 6
Feature activation+0.000
.
Token.
Feature activation+0.777
4
Token4
Feature activation+0.330
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.381
,
Token,
Feature activation+1.163
Player
Token Player
Feature activation+3.184
C
Token C
Feature activation+1.489
:
Token:
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.000
St
Token St
Feature activation+0.000
aves
Tokenaves
Feature activation+0.000
,
Token,
Feature activation+0.000
Axe
Token Axe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.424
Ċ
TokenĊ
Feature activation+3.087
H
TokenH
Feature activation+2.222
RC
TokenRC
Feature activation+0.810
:
Token:
Feature activation+0.000
Chest
Token Chest
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
tan
Token tan
Feature activation+0.000
shoes
Token shoes
Feature activation+0.000
.
Token.
Feature activation+2.884
Mid
Token Mid
Feature activation+0.000
Grey
Token Grey
Feature activation+0.000
:
Token:
Feature activation+0.274
Black
Token Black
Feature activation+0.028
works
Token works
Feature activation+0.000
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
2
Token2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
Place
Token Place
Feature activation+1.347
,
Token,
Feature activation+2.805
Player
Token Player
Feature activation+4.435
C
Token C
Feature activation+1.760
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.262
,
Token,
Feature activation+0.572
Player
Token Player
Feature activation+2.775
B
Token B
Feature activation+0.763
:
Token:
Feature activation+0.000
Inv
Token Inv
Feature activation+0.000
oked
Tokenoked
Feature activation+0.000
True
Token True
Feature activation+0.000
55
Token 55
Feature activation+0.000
-
Token-
Feature activation+0.000
60
Token60
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.996
Ċ
TokenĊ
Feature activation+2.773
Saturday
TokenSaturday
Feature activation+1.393
:
Token:
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
and
Token and
Feature activation+0.000
clouds
Token clouds
Feature activation+0.000
->
Token->
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.005
/
Token /
Feature activation+1.534
T
Token T
Feature activation+2.762
2
Token2
Feature activation+1.539
:
Token:
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.621
Ċ
TokenĊ
Feature activation+1.725
Em
TokenEm
Feature activation+0.463
otional
Tokenotional
Feature activation+2.526
insight
Token insight
Feature activation+2.758
:
Token:
Feature activation+0.000
You
Token You
Feature activation+0.000
understand
Token understand
Feature activation+0.000
your
Token your
Feature activation+0.000
feelings
Token feelings
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.312
,
Token,
Feature activation+0.701
Player
Token Player
Feature activation+2.720
A
Token A
Feature activation+1.389
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Wind
Token Wind
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.096
,
Token,
Feature activation+0.990
Player
Token Player
Feature activation+2.717
B
Token B
Feature activation+0.814
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Metal
Token Metal
Feature activation+0.000
=
Token =
Feature activation+0.000
Geo
Token Geo
Feature activation+0.000
Trust
TokenTrust
Feature activation+0.000
Global
Token Global
Feature activation+0.000
CA
Token CA
Feature activation+0.000
verify
Token verify
Feature activation+2.666
return
Token return
Feature activation+0.208
:
Token:
Feature activation+0.000
1
Token1
Feature activation+0.071
depth
Token depth
Feature activation+0.000
=
Token=
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.266
,
Token,
Feature activation+0.807
Player
Token Player
Feature activation+2.660
C
Token C
Feature activation+1.348
:
Token:
Feature activation+0.102
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000

Top DFA by src position
MAX = 4.993

nd
Tokennd
Feature activation-0.016
Top resid features:
Place
Token Place
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Player
Token Player
Feature activation+0.005
Top resid features:
B
Token B
Feature activation+0.058
Top resid features:
:
Token:
Feature activation+4.993
Top resid features:
True
Token True
Feature activation+0.008
Top resid features:
Draco
Token Draco
Feature activation-0.006
Top resid features:
Dinosaur
Token Dinosaur
Feature activation+0.015
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.020
Top resid features:
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.347
Top resid features:
Added
TokenAdded
Feature activation-0.001
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
Xperia
Token Xperia
Feature activation-0.002
Top resid features:
M
Token M
Feature activation+0.106
Top resid features:
:
Token:
Feature activation+4.447
Top resid features:
The
Token The
Feature activation+0.103
Top resid features:
Alpha
Token Alpha
Feature activation+0.012
Top resid features:
2
Token 2
Feature activation+0.020
Top resid features:
build
Token build
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.318
Top resid features:
Added
TokenAdded
Feature activation-0.002
Top resid features:
:
Token:
Feature activation-0.013
Top resid features:
Xperia
Token Xperia
Feature activation-0.000
Top resid features:
M
Token M
Feature activation+0.040
Top resid features:
:
Token:
Feature activation+4.311
Top resid features:
The
Token The
Feature activation+0.047
Top resid features:
Alpha
Token Alpha
Feature activation+0.008
Top resid features:
2
Token 2
Feature activation+0.018
Top resid features:
build
Token build
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.006
Top resid features:
Infinite
Token Infinite
Feature activation-0.009
Top resid features:
Long
Token Long
Feature activation+0.003
Top resid features:
Ex
Token Ex
Feature activation+0.003
Top resid features:
pos
Tokenpos
Feature activation+0.003
Top resid features:
ures
Tokenures
Feature activation+0.003
Top resid features:
:
Token:
Feature activation+4.422
Top resid features:
Perfect
Token Perfect
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
low
Token low
Feature activation+0.003
Top resid features:
light
Token light
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
th
Tokenth
Feature activation-0.008
Top resid features:
Place
Token Place
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
Player
Token Player
Feature activation+0.004
Top resid features:
A
Token A
Feature activation-0.077
Top resid features:
:
Token:
Feature activation+4.331
Top resid features:
Mask
Token Mask
Feature activation+0.009
Top resid features:
ed
Tokened
Feature activation+0.003
Top resid features:
HERO
Token HERO
Feature activation-0.004
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.006
Top resid features:
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation-0.003
Top resid features:
Mir
Token Mir
Feature activation-0.001
Top resid features:
aj
Tokenaj
Feature activation-0.000
Top resid features:
understands
Token understands
Feature activation-0.001
Top resid features:
empty
Token empty
Feature activation-0.108
Top resid features:
elements
Token elements
Feature activation+0.018
Top resid features:
:
Token:
Feature activation+3.963
Top resid features:
Ċ
TokenĊ
Feature activation+0.233
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
HTML
TokenHTML
Feature activation-0.003
Top resid features:
5
Token5
Feature activation-0.002
Top resid features:
void
Token void
Feature activation-0.010
Top resid features:
nd
Tokennd
Feature activation-0.004
Top resid features:
Place
Token Place
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Player
Token Player
Feature activation+0.004
Top resid features:
B
Token B
Feature activation+0.012
Top resid features:
:
Token:
Feature activation+2.168
Top resid features:
True
Token True
Feature activation+0.004
Top resid features:
Draco
Token Draco
Feature activation-0.002
Top resid features:
Dinosaur
Token Dinosaur
Feature activation+0.009
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.005
Top resid features:
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
Top resid features:
3
Token3
Feature activation+0.004
Top resid features:
2
Token 2
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
New
Token New
Feature activation+0.112
Top resid features:
York
Token York
Feature activation+0.035
Top resid features:
:
Token:
Feature activation+3.301
Top resid features:
6
Token 6
Feature activation+0.183
Top resid features:
3
Token 3
Feature activation+0.221
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Massachusetts
Token Massachusetts
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation+0.002
Top resid features:
Place
Token Place
Feature activation+0.004
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Player
Token Player
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+0.140
Top resid features:
:
Token:
Feature activation+3.488
Top resid features:
True
Token True
Feature activation+0.004
Top resid features:
Draco
Token Draco
Feature activation-0.004
Top resid features:
Dinosaur
Token Dinosaur
Feature activation-0.005
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.015
Top resid features:
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation-0.002
Top resid features:
parts
Token parts
Feature activation-0.008
Top resid features:
:
Token:
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
AA
TokenAA
Feature activation-0.015
Top resid features:
:
Token:
Feature activation+3.783
Top resid features:
Helmet
Token Helmet
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
Should
Token Should
Feature activation+0.004
Top resid features:
er
Tokener
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
tan
Token tan
Feature activation+0.001
Top resid features:
shoes
Token shoes
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.035
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
:
Token:
Feature activation+3.557
Top resid features:
We
Token We
Feature activation+0.055
Top resid features:
suggest
Token suggest
Feature activation+0.002
Top resid features:
black
Token black
Feature activation+0.011
Top resid features:
over
Token over
Feature activation+0.001
Top resid features:
any
Token any
Feature activation-0.002
Top resid features:
nd
Tokennd
Feature activation-0.001
Top resid features:
Place
Token Place
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
Player
Token Player
Feature activation-0.094
Top resid features:
B
Token B
Feature activation+0.103
Top resid features:
:
Token:
Feature activation+3.399
Top resid features:
True
Token True
Feature activation+0.006
Top resid features:
Draco
Token Draco
Feature activation-0.004
Top resid features:
Dinosaur
Token Dinosaur
Feature activation+0.008
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.034
Top resid features:
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation-0.001
Top resid features:
rd
Tokenrd
Feature activation+0.005
Top resid features:
Place
Token Place
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
Player
Token Player
Feature activation-0.001
Top resid features:
A
Token A
Feature activation-0.097
Top resid features:
:
Token:
Feature activation+2.619
Top resid features:
True
Token True
Feature activation+0.005
Top resid features:
Draco
Token Draco
Feature activation-0.004
Top resid features:
Wind
Token Wind
Feature activation+0.000
Top resid features:
witch
Tokenwitch
Feature activation+0.001
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Friday
TokenFriday
Feature activation-0.027
Top resid features:
Night
Token Night
Feature activation-0.011
Top resid features:
:
Token:
Feature activation+3.189
Top resid features:
Clear
Token Clear
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
partly
Token partly
Feature activation+0.011
Top resid features:
cloudy
Token cloudy
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
2
Token2
Feature activation-0.004
Top resid features:
/
Token /
Feature activation-0.000
Top resid features:
T
Token T
Feature activation+0.005
Top resid features:
2
Token2
Feature activation-0.050
Top resid features:
:
Token:
Feature activation+3.047
Top resid features:
1
Token 1
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
8
Token8
Feature activation-0.008
Top resid features:
->
Token->
Feature activation+0.005
Top resid features:
1
Token1
Feature activation-0.000
Top resid features:
Real
TokenReal
Feature activation+0.004
Top resid features:
istic
Tokenistic
Feature activation-0.003
Top resid features:
self
Token self
Feature activation+0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
confidence
Tokenconfidence
Feature activation+0.004
Top resid features:
:
Token:
Feature activation+3.083
Top resid features:
You
Token You
Feature activation+0.037
Top resid features:
understand
Token understand
Feature activation+0.003
Top resid features:
your
Token your
Feature activation+0.005
Top resid features:
own
Token own
Feature activation+0.004
Top resid features:
strengths
Token strengths
Feature activation+0.003
Top resid features:
rd
Tokenrd
Feature activation+0.002
Top resid features:
Place
Token Place
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Player
Token Player
Feature activation+0.001
Top resid features:
A
Token A
Feature activation-0.125
Top resid features:
:
Token:
Feature activation+1.433
Top resid features:
True
Token True
Feature activation+0.002
Top resid features:
Draco
Token Draco
Feature activation-0.001
Top resid features:
Wind
Token Wind
Feature activation+0.000
Top resid features:
witch
Tokenwitch
Feature activation+0.001
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.002
Top resid features:
rd
Tokenrd
Feature activation+0.000
Top resid features:
Place
Token Place
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Player
Token Player
Feature activation+0.001
Top resid features:
B
Token B
Feature activation-0.046
Top resid features:
:
Token:
Feature activation+1.641
Top resid features:
Inv
Token Inv
Feature activation+0.028
Top resid features:
oked
Tokenoked
Feature activation+0.002
Top resid features:
True
Token True
Feature activation+0.001
Top resid features:
Draco
Token Draco
Feature activation-0.000
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.002
Top resid features:
Secure
Token Secure
Feature activation+0.002
Top resid features:
Certificate
Token Certificate
Feature activation+0.001
Top resid features:
Authority
Token Authority
Feature activation+0.004
Top resid features:
verify
Token verify
Feature activation+0.009
Top resid features:
return
Token return
Feature activation+0.081
Top resid features:
:
Token:
Feature activation+2.811
Top resid features:
1
Token1
Feature activation+0.259
Top resid features:
depth
Token depth
Feature activation+0.008
Top resid features:
=
Token=
Feature activation+0.015
Top resid features:
2
Token2
Feature activation+0.007
Top resid features:
C
Token C
Feature activation-0.000
Top resid features:
rd
Tokenrd
Feature activation+0.000
Top resid features:
Place
Token Place
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Player
Token Player
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+0.211
Top resid features:
:
Token:
Feature activation+2.103
Top resid features:
Inv
Token Inv
Feature activation+0.025
Top resid features:
oked
Tokenoked
Feature activation-0.000
Top resid features:
True
Token True
Feature activation-0.002
Top resid features:
Draco
Token Draco
Feature activation-0.003
Top resid features:
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.04

Head 3: 0.05

Head 4: 0.03

Head 5: 0.04

Head 6: 0.06

Head 7: 0.54

Head 8: 0.03

Head 9: 0.03

Head 10: 0.04

Head 11: 0.05

Positive logits

%:4.92

.):4.53

):4.47

*:4.45

]:4.35

!:4.31

':4.06

:4.06

:[3.94

?:3.92

.:3.83

:3.80

):3.58

":3.51

:]3.35

:"3.23

():3.23

:-3.17

:(3.05

™:3.04

Negative logits

hower-2.13

itionally-2.05

ancial-2.00

theless-1.92

ADRA-1.84

ikarp-1.79

DragonMagazine-1.74

Vik-1.71

oubted-1.71

levard-1.69

RTX-1.67

eteenth-1.65

ratulations-1.63

idable-1.62

estern-1.62

icro-1.61

��-1.60

oubtedly-1.60

emort-1.57

',"-1.56

INTERVAL 3.991 - 4.435
CONTAINS 0.000%

!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.534
Added
TokenAdded
Feature activation+0.514
:
Token:
Feature activation+3.883
Xperia
Token Xperia
Feature activation+4.205
V
Token V
Feature activation+0.848
:
Token:
Feature activation+0.000
Initial
Token Initial
Feature activation+0.000
builds
Token builds
Feature activation+0.000
for
Token for
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
2
Token2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
Place
Token Place
Feature activation+1.347
,
Token,
Feature activation+2.805
Player
Token Player
Feature activation+4.435
C
Token C
Feature activation+1.760
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000

INTERVAL 3.548 - 3.991
CONTAINS 0.000%

kicking
Token kicking
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.534
Added
TokenAdded
Feature activation+0.514
:
Token:
Feature activation+3.883
Xperia
Token Xperia
Feature activation+4.205
V
Token V
Feature activation+0.848
:
Token:
Feature activation+0.000
Initial
Token Initial
Feature activation+0.000
builds
Token builds
Feature activation+0.000
light
Token light
Feature activation+0.000
stre
Token stre
Feature activation+0.000
aked
Tokenaked
Feature activation+0.000
inst
Token inst
Feature activation+0.000
ants
Tokenants
Feature activation+0.000
!
Token!
Feature activation+3.837
Color
Token Color
Feature activation+0.535
G
Token G
Feature activation+0.000
els
Tokenels
Feature activation+0.539
:
Token:
Feature activation+0.000
Transform
Token Transform
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.405
,
Token,
Feature activation+1.108
Player
Token Player
Feature activation+3.625
B
Token B
Feature activation+0.283
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000

INTERVAL 3.104 - 3.548
CONTAINS 0.001%

no
Token no
Feature activation+0.000
'/
Token '/
Feature activation+0.000
'.
Token'.
Feature activation+0.000
Mir
Token Mir
Feature activation+0.000
aj
Tokenaj
Feature activation+0.647
understands
Token understands
Feature activation+3.531
void
Token void
Feature activation+1.240
elements
Token elements
Feature activation+2.641
:
Token:
Feature activation+1.231
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
:
Token:
Feature activation+0.000
6
Token 6
Feature activation+0.130
3
Token 3
Feature activation+1.445
.
Token.
Feature activation+3.231
Massachusetts
Token Massachusetts
Feature activation+0.344
:
Token:
Feature activation+0.000
6
Token 6
Feature activation+0.000
.
Token.
Feature activation+0.777
4
Token4
Feature activation+0.330
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.381
,
Token,
Feature activation+1.163
Player
Token Player
Feature activation+3.184
C
Token C
Feature activation+1.489
:
Token:
Feature activation+0.000
Dem
Token Dem
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
3
Token3
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
Place
Token Place
Feature activation+0.133
,
Token,
Feature activation+0.990
Player
Token Player
Feature activation+3.265
A
Token A
Feature activation+0.682
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Wind
Token Wind
Feature activation+0.000

INTERVAL 2.661 - 3.104
CONTAINS 0.001%

âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
2
Token2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
Place
Token Place
Feature activation+1.347
,
Token,
Feature activation+2.805
Player
Token Player
Feature activation+4.435
C
Token C
Feature activation+1.760
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
->
Token->
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.005
/
Token /
Feature activation+1.534
T
Token T
Feature activation+2.762
2
Token2
Feature activation+1.539
:
Token:
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
55
Token 55
Feature activation+0.000
-
Token-
Feature activation+0.000
60
Token60
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.996
Ċ
TokenĊ
Feature activation+2.773
Saturday
TokenSaturday
Feature activation+1.393
:
Token:
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
and
Token and
Feature activation+0.000
clouds
Token clouds
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
tan
Token tan
Feature activation+0.000
shoes
Token shoes
Feature activation+0.000
.
Token.
Feature activation+2.884
Mid
Token Mid
Feature activation+0.000
Grey
Token Grey
Feature activation+0.000
:
Token:
Feature activation+0.274
Black
Token Black
Feature activation+0.028
works
Token works
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.096
,
Token,
Feature activation+0.990
Player
Token Player
Feature activation+2.717
B
Token B
Feature activation+0.814
:
Token:
Feature activation+0.000
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Metal
Token Metal
Feature activation+0.000

INTERVAL 2.217 - 2.661
CONTAINS 0.003%

ph
Token ph
Feature activation+0.010
alan
Tokenalan
Feature activation+0.000
x
Tokenx
Feature activation+0.049
heavy
Token heavy
Feature activation+0.920
right
Token right
Feature activation+2.363
T
Token T
Feature activation+2.241
1
Token1
Feature activation+0.144
:
Token:
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
for
Token for
Feature activation+0.000
ph
Token ph
Feature activation+0.010
alan
Tokenalan
Feature activation+0.000
x
Tokenx
Feature activation+0.049
heavy
Token heavy
Feature activation+0.920
right
Token right
Feature activation+2.363
T
Token T
Feature activation+2.241
1
Token1
Feature activation+0.144
:
Token:
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
Hawaii
Token Hawaii
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
#
Token#
Feature activation+0.000
2
Token2
Feature activation+0.711
)
Token)
Feature activation+2.316
Arizona
Token Arizona
Feature activation+1.372
:
Token:
Feature activation+0.000
Jack
Token Jack
Feature activation+0.000
Del
Token Del
Feature activation+0.000
Rio
Token Rio
Feature activation+0.000
football
Token football
Feature activation+0.000
a
Token a
Feature activation+0.000
try
Token try
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.054
Ċ
TokenĊ
Feature activation+2.473
A
TokenA
Feature activation+0.710
UM
Token UM
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
->
Token->
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.042
/
Token /
Feature activation+0.950
T
Token T
Feature activation+2.298
3
Token3
Feature activation+1.727
:
Token:
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000

INTERVAL 1.774 - 2.217
CONTAINS 0.005%

y
Tokeny
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.232
A
Token A
Feature activation+0.388
third
Token third
Feature activation+2.138
added
Token added
Feature activation+1.259
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.292
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.796
th
Tokenth
Feature activation+2.087
month
Token month
Feature activation+0.000
(
Token (
Feature activation+0.000
11
Token11
Feature activation+1.000
45
Token45
Feature activation+1.073
):
Token):
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.000
256
Token 256
Feature activation+0.000
MB
Token MB
Feature activation+0.236
Hard
Token Hard
Feature activation+1.889
Drive
Token Drive
Feature activation+1.031
:
Token:
Feature activation+0.000
123
Token 123
Feature activation+0.000
MB
Token MB
Feature activation+0.000
Important
Token Important
Feature activation+0.000
Videos
Token Videos
Feature activation+0.000
...
Token ...
Feature activation+0.000
MUST
Token MUST
Feature activation+0.000
WATCH
Token WATCH
Feature activation+0.000
Booker
Token Booker
Feature activation+1.230
on
Token on
Feature activation+1.872
GOP
Token GOP
Feature activation+1.473
health
Token health
Feature activation+0.863
strategy
Token strategy
Feature activation+1.313
:
Token:
Feature activation+0.037
'
Token '
Feature activation+0.000
dad
Token dad
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
#
Token#
Feature activation+0.000
3
Token3
Feature activation+0.216
)
Token)
Feature activation+1.997
Baylor
Token Baylor
Feature activation+1.299
:
Token:
Feature activation+0.000
O
Token O
Feature activation+0.000
rel
Tokenrel
Feature activation+0.000
Hers
Token Hers
Feature activation+0.000

INTERVAL 1.330 - 1.774
CONTAINS 0.012%

Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.000
800
Token 800
Feature activation+0.000
M
Token M
Feature activation+0.000
hz
Tokenhz
Feature activation+1.041
RAM
Token RAM
Feature activation+1.638
:
Token :
Feature activation+0.000
256
Token 256
Feature activation+0.000
MB
Token MB
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
But
TokenBut
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
also
Token also
Feature activation+1.355
some
Token some
Feature activation+0.225
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
with
Token with
Feature activation+0.000
2
Token 2
Feature activation+0.000
assists
Token assists
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.452
Ċ
TokenĊ
Feature activation+1.019
Best
TokenBest
Feature activation+1.451
Goal
Token Goal
Feature activation+0.000
keeper
Tokenkeeper
Feature activation+0.469
:
Token:
Feature activation+0.000
Sylv
Token Sylv
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
15
Token 15
Feature activation+0.000
th
Tokenth
Feature activation+0.000
century
Token century
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.088
Ċ
TokenĊ
Feature activation+1.546
Div
TokenDiv
Feature activation+0.000
isions
Tokenisions
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.166
-
Token-
Feature activation+0.000
60
Token60
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.996
Ċ
TokenĊ
Feature activation+2.773
Saturday
TokenSaturday
Feature activation+1.393
:
Token:
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
and
Token and
Feature activation+0.000
clouds
Token clouds
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.887 - 1.330
CONTAINS 0.018%

context
Token context
Feature activation+0.000
Barney
Token Barney
Feature activation+0.000
declares
Token declares
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.902
Brown
TokenBrown
Feature activation+0.000
shoes
Token shoes
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
dark
Token dark
Feature activation+0.000
Lind
Token Lind
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.089
Ċ
TokenĊ
Feature activation+1.126
O
TokenO
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
K
Token K
Feature activation+0.047
ri
Tokenri
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
Any
Token Any
Feature activation+0.000
,
Token,
Feature activation+0.000
Source
Token Source
Feature activation+0.000
:
Token:
Feature activation+0.000
Any
Token Any
Feature activation+0.000
,
Token,
Feature activation+0.889
Destination
Token Destination
Feature activation+0.000
:
Token:
Feature activation+0.000
Any
Token Any
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.682
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.183
The
TokenThe
Feature activation+0.563
shop
Token shop
Feature activation+0.460
also
Token also
Feature activation+1.010
does
Token does
Feature activation+0.474
print
Token print
Feature activation+0.000
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
Google
Token Google
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Authority
Token Authority
Feature activation+0.000
G
Token G
Feature activation+0.000
2
Token2
Feature activation+0.000
verify
Token verify
Feature activation+1.229
return
Token return
Feature activation+0.000
:
Token:
Feature activation+0.000
1
Token1
Feature activation+0.000
depth
Token depth
Feature activation+0.000
=
Token=
Feature activation+0.000

INTERVAL 0.443 - 0.887
CONTAINS 0.040%

who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
contract
Token contract
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.876
Ċ
TokenĊ
Feature activation+0.372
Film
TokenFilm
Feature activation+0.000
criticism
Token criticism
Feature activation+0.000
also
Token also
Feature activation+0.000
shifted
Token shifted
Feature activation+0.000
:
Token:
Feature activation+0.000
On
Token On
Feature activation+0.000
om
Tokenom
Feature activation+0.000
ichi
Tokenichi
Feature activation+0.000
Dock
Token Dock
Feature activation+0.194
yard
Tokenyard
Feature activation+0.535
Yard
Token Yard
Feature activation+0.497
number
Token number
Feature activation+0.000
:
Token:
Feature activation+0.000
118
Token 118
Feature activation+0.000
Laun
Token Laun
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.535
Russia
TokenRussia
Feature activation+0.000
Comic
Token Comic
Feature activation+0.000
Con
Token Con
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.109
Ċ
TokenĊ
Feature activation+0.528
In
TokenIn
Feature activation+0.000
aug
Tokenaug
Feature activation+0.000
urated
Tokenurated
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
BRA
Token BRA
Feature activation+0.000
VO
TokenVO
Feature activation+0.000
8
Token 8
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
PM
Token PM
Feature activation+0.773
9
Token 9
Feature activation+0.000
:
Token:
Feature activation+0.000
15
Token15
Feature activation+0.000
PM
Token PM
Feature activation+0.000
2
Token 2
Feature activation+0.000
mystery
Token mystery
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.309
Ċ
TokenĊ
Feature activation+1.110
Big
TokenBig
Feature activation+0.021
gest
Tokengest
Feature activation+0.601
losses
Token losses
Feature activation+0.000
:
Token:
Feature activation+0.000
On
Token On
Feature activation+0.000
the
Token the
Feature activation+0.000
plus
Token plus
Feature activation+0.000

INTERVAL 0.000 - 0.443
CONTAINS 99.921%

Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
poll
Token poll
Feature activation+0.000
Still
Token Still
Feature activation+0.000
others
Token others
Feature activation+0.000
are
Token are
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
the
Token the
Feature activation+0.000
practice
Token practice
Feature activation+0.000
of
Token of
Feature activation+0.000
medicine
Token medicine
Feature activation+0.000
altogether
Token altogether
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Google
Token Google
Feature activation+0.000
Maps
Token Maps
Feature activation+0.000
features
Token features
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
TokenNew
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
utch
Tokenutch
Feature activation+0.000
Ped
Token Ped
Feature activation+0.000
al
Tokenal
Feature activation+0.000
and
Token and
Feature activation+0.000
U
Token U
Feature activation+0.000
UC
TokenUC
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
m
Tokenm
Feature activation+0.000
payment
Token payment
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
Fifa
Token Fifa
Feature activation+0.000
in
Token in
Feature activation+0.000
relation
Token relation
Feature activation+0.000
to
Token to
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 H7.7: (feature 45112)

TOP ACTIVATIONS
MAX = 4.360

way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
those
Token those
Feature activation+1.402
who
Token who
Feature activation+1.286
can
Token can
Feature activation+4.360
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.519
,
Token,
Feature activation+2.400
it
Token it
Feature activation+0.000
improve
Token improve
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.153
;
Token;
Feature activation+0.185
to
Token to
Feature activation+3.428
be
Token be
Feature activation+3.075
perfect
Token perfect
Feature activation+1.060
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
padded
Token padded
Feature activation+0.000
envelop
Token envelop
Feature activation+0.000
-
Token -
Feature activation+3.226
inside
Token inside
Feature activation+1.696
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
sea
Token sea
Feature activation+0.000
breeze
Token breeze
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.000
or
Token or
Feature activation+1.556
âĢ
Token âĢ
Feature activation+2.196
ľ
Tokenľ
Feature activation+3.212
not
Tokennot
Feature activation+0.524
observing
Token observing
Feature activation+0.562
E
Token E
Feature activation+0.000
lowers
Token lowers
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.253
Total
Token Total
Feature activation+1.149
losses
Token losses
Feature activation+2.885
of
Token of
Feature activation+3.154
the
Token the
Feature activation+1.220
National
Token National
Feature activation+0.289
ist
Tokenist
Feature activation+0.771
Air
Token Air
Feature activation+1.361
Force
Token Force
Feature activation+2.087
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.153
;
Token;
Feature activation+0.185
to
Token to
Feature activation+3.428
be
Token be
Feature activation+3.075
perfect
Token perfect
Feature activation+1.060
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
often
Token often
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.253
Total
Token Total
Feature activation+1.149
losses
Token losses
Feature activation+2.885
of
Token of
Feature activation+3.154
the
Token the
Feature activation+1.220
National
Token National
Feature activation+0.289
ist
Tokenist
Feature activation+0.771
Air
Token Air
Feature activation+1.361
fires
Token fires
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.003
ľ
Tokenľ
Feature activation+2.712
Almost
TokenAlmost
Feature activation+0.663
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Lower
Token Lower
Feature activation+0.000
A
Token A
Feature activation+0.000
towel
Token towel
Feature activation+0.000
is
Token is
Feature activation+0.000
deform
Token deform
Feature activation+0.000
able
Tokenable
Feature activation+0.000
;
Token;
Feature activation+2.664
a
Token a
Feature activation+1.932
mug
Token mug
Feature activation+0.209
or
Token or
Feature activation+0.139
a
Token a
Feature activation+0.166
computer
Token computer
Feature activation+0.543
,
Token,
Feature activation+0.095
this
Token this
Feature activation+0.843
is
Token is
Feature activation+0.264
really
Token really
Feature activation+0.000
awesome
Token awesome
Feature activation+0.416
that
Token that
Feature activation+2.636
Cle
Token Cle
Feature activation+0.822
my
Tokenmy
Feature activation+0.743
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
spread
Token spread
Feature activation+0.000
The
Token The
Feature activation+0.000
official
Token official
Feature activation+0.000
theory
Token theory
Feature activation+0.606
of
Token of
Feature activation+1.506
the
Token the
Feature activation+1.172
destruction
Token destruction
Feature activation+2.423
of
Token of
Feature activation+0.577
WTC
Token WTC
Feature activation+0.000
7
Token 7
Feature activation+0.175
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.710
Ċ
TokenĊ
Feature activation+1.311
Wikipedia
TokenWikipedia
Feature activation+2.401
®
Token®
Feature activation+1.216
is
Token is
Feature activation+0.378
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
who
Token who
Feature activation+1.286
can
Token can
Feature activation+4.360
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.519
,
Token,
Feature activation+2.400
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000
compensate
Token compensate
Feature activation+0.000
of
Token of
Feature activation+0.000
The
Token The
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Group
Token Group
Feature activation+0.000
.
Token.
Feature activation+0.292
Ċ
TokenĊ
Feature activation+2.346
Ċ
TokenĊ
Feature activation+1.666
Virtual
TokenVirtual
Feature activation+1.825
Box
TokenBox
Feature activation+2.103
®
Token®
Feature activation+2.246
is
Token is
Feature activation+0.477
profit
Tokenprofit
Feature activation+0.000
organization
Token organization
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.350
Ċ
TokenĊ
Feature activation+1.295
Windows
TokenWindows
Feature activation+2.283
®
Token®
Feature activation+2.074
is
Token is
Feature activation+0.669
a
Token a
Feature activation+0.129
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
.
Token.
Feature activation+0.292
Ċ
TokenĊ
Feature activation+2.346
Ċ
TokenĊ
Feature activation+1.666
Virtual
TokenVirtual
Feature activation+1.825
Box
TokenBox
Feature activation+2.103
®
Token®
Feature activation+2.246
is
Token is
Feature activation+0.477
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
of
Token of
Feature activation+0.000
Warriors
Token Warriors
Feature activation+0.000
Chapter
Token Chapter
Feature activation+0.000
,
Token,
Feature activation+0.761
the
Token the
Feature activation+0.805
spirit
Token spirit
Feature activation+1.205
of
Token of
Feature activation+2.243
the
Token the
Feature activation+2.064
player
Token player
Feature activation+0.570
is
Token is
Feature activation+0.132
linked
Token linked
Feature activation+0.000
with
Token with
Feature activation+0.000
Oracle
Token Oracle
Feature activation+0.000
.
Token.
Feature activation+0.080
Ċ
TokenĊ
Feature activation+2.179
Ċ
TokenĊ
Feature activation+1.819
VM
TokenVM
Feature activation+1.482
ware
Tokenware
Feature activation+2.212
®
Token®
Feature activation+1.773
is
Token is
Feature activation+0.430
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Tom
TokenTom
Feature activation+0.000
H
Token H
Feature activation+0.000
anks
Tokenanks
Feature activation+1.228
'
Token'
Feature activation+2.209
hero
Token hero
Feature activation+0.129
in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
Terminal
Token Terminal
Feature activation+0.000
is
Token is
Feature activation+0.451
P
TokenP
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.000
or
Token or
Feature activation+1.556
âĢ
Token âĢ
Feature activation+2.196
ľ
Tokenľ
Feature activation+3.212
not
Tokennot
Feature activation+0.524
observing
Token observing
Feature activation+0.562
E
Token E
Feature activation+0.000
lowers
Token lowers
Feature activation+0.000

Top DFA by src position
MAX = 4.953

who
Token who
Feature activation+0.001
Top resid features:
can
Token can
Feature activation+0.001
Top resid features:
draw
Token draw
Feature activation-0.148
Top resid features:
tracing
Token tracing
Feature activation+0.022
Top resid features:
paper
Token paper
Feature activation-0.013
Top resid features:
is
Token is
Feature activation+4.953
Top resid features:
just
Token just
Feature activation+0.086
Top resid features:
another
Token another
Feature activation+0.002
Top resid features:
tool
Token tool
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
9
Token9
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
To
Token To
Feature activation-0.001
Top resid features:
improve
Token improve
Feature activation-0.036
Top resid features:
is
Token is
Feature activation+3.941
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
change
Token change
Feature activation-0.050
Top resid features:
;
Token;
Feature activation+0.035
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
padded
Token padded
Feature activation+0.010
Top resid features:
envelop
Token envelop
Feature activation+0.003
Top resid features:
-
Token -
Feature activation-0.020
Top resid features:
inside
Token inside
Feature activation-0.203
Top resid features:
is
Token is
Feature activation+3.911
Top resid features:
a
Token a
Feature activation+0.023
Top resid features:
sea
Token sea
Feature activation+0.002
Top resid features:
breeze
Token breeze
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Air
Token Air
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
E
TokenE
Feature activation-0.049
Top resid features:
is
Token is
Feature activation+3.719
Top resid features:
evidence
Token evidence
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
favor
Token favor
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
H
Token H
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
National
Token National
Feature activation+0.017
Top resid features:
ist
Tokenist
Feature activation+0.001
Top resid features:
Air
Token Air
Feature activation-0.000
Top resid features:
Force
Token Force
Feature activation-0.036
Top resid features:
were
Token were
Feature activation+3.877
Top resid features:
2
Token 2
Feature activation-0.072
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
468
Token468
Feature activation+0.007
Top resid features:
aircraft
Token aircraft
Feature activation+0.002
Top resid features:
(
Token (
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
9
Token9
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
To
Token To
Feature activation+0.003
Top resid features:
improve
Token improve
Feature activation-0.034
Top resid features:
is
Token is
Feature activation+3.470
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
change
Token change
Feature activation-0.031
Top resid features:
;
Token;
Feature activation+0.114
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
be
Token be
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
National
Token National
Feature activation+0.018
Top resid features:
ist
Tokenist
Feature activation+0.000
Top resid features:
Air
Token Air
Feature activation-0.000
Top resid features:
Force
Token Force
Feature activation-0.004
Top resid features:
were
Token were
Feature activation+3.486
Top resid features:
2
Token 2
Feature activation+0.008
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
468
Token468
Feature activation+0.003
Top resid features:
aircraft
Token aircraft
Feature activation-0.001
Top resid features:
(
Token (
Feature activation-0.003
Top resid features:
this
Token this
Feature activation+0.009
Top resid features:
severe
Token severe
Feature activation+0.000
Top resid features:
situation
Token situation
Feature activation+0.005
Top resid features:
so
Token so
Feature activation+0.001
Top resid features:
early
Token early
Feature activation+0.009
Top resid features:
has
Token has
Feature activation+2.874
Top resid features:
been
Token been
Feature activation+0.247
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
weather
Token weather
Feature activation-0.002
Top resid features:
conditions
Token conditions
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
't
Token't
Feature activation+0.003
Top resid features:
predictable
Token predictable
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
A
Token A
Feature activation+0.011
Top resid features:
towel
Token towel
Feature activation+0.037
Top resid features:
is
Token is
Feature activation+2.974
Top resid features:
deform
Token deform
Feature activation+0.008
Top resid features:
able
Tokenable
Feature activation+0.042
Top resid features:
;
Token;
Feature activation-0.027
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
mug
Token mug
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.002
Top resid features:
awesome
Token awesome
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
Cle
Token Cle
Feature activation-0.009
Top resid features:
my
Tokenmy
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+2.572
Top resid features:
now
Token now
Feature activation+0.454
Top resid features:
spread
Token spread
Feature activation+0.006
Top resid features:
across
Token across
Feature activation+0.013
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
games
Token games
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.074
Top resid features:
WTC
Token WTC
Feature activation-0.001
Top resid features:
1
Token 1
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
2
Token 2
Feature activation+0.031
Top resid features:
is
Token is
Feature activation+2.694
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
aircraft
Token aircraft
Feature activation+0.001
Top resid features:
impact
Token impact
Feature activation-0.001
Top resid features:
damage
Token damage
Feature activation+0.002
Top resid features:
combined
Token combined
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
UN
TokenUN
Feature activation+0.004
Top resid features:
IX
TokenIX
Feature activation+0.005
Top resid features:
®
Token®
Feature activation-0.017
Top resid features:
is
Token is
Feature activation+0.671
Top resid features:
a
Token a
Feature activation+0.287
Top resid features:
registered
Token registered
Feature activation+0.034
Top resid features:
trademark
Token trademark
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
who
Token who
Feature activation-0.002
Top resid features:
can
Token can
Feature activation+0.004
Top resid features:
draw
Token draw
Feature activation-0.012
Top resid features:
tracing
Token tracing
Feature activation+0.006
Top resid features:
paper
Token paper
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+2.553
Top resid features:
just
Token just
Feature activation+0.390
Top resid features:
another
Token another
Feature activation+0.013
Top resid features:
tool
Token tool
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.075
Top resid features:
UN
TokenUN
Feature activation+0.040
Top resid features:
IX
TokenIX
Feature activation+0.048
Top resid features:
®
Token®
Feature activation+0.029
Top resid features:
is
Token is
Feature activation+1.763
Top resid features:
a
Token a
Feature activation+0.238
Top resid features:
registered
Token registered
Feature activation+0.034
Top resid features:
trademark
Token trademark
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
UN
TokenUN
Feature activation+0.005
Top resid features:
IX
TokenIX
Feature activation+0.008
Top resid features:
®
Token®
Feature activation-0.009
Top resid features:
is
Token is
Feature activation+0.738
Top resid features:
a
Token a
Feature activation+0.152
Top resid features:
registered
Token registered
Feature activation+0.013
Top resid features:
trademark
Token trademark
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
UN
TokenUN
Feature activation+0.003
Top resid features:
IX
TokenIX
Feature activation+0.005
Top resid features:
®
Token®
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.847
Top resid features:
a
Token a
Feature activation+1.103
Top resid features:
registered
Token registered
Feature activation+0.247
Top resid features:
trademark
Token trademark
Feature activation+0.082
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
Open
Token Open
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
spirit
Token spirit
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.021
Top resid features:
player
Token player
Feature activation-0.051
Top resid features:
is
Token is
Feature activation+2.617
Top resid features:
linked
Token linked
Feature activation+0.082
Top resid features:
with
Token with
Feature activation+0.042
Top resid features:
Android
Token Android
Feature activation-0.005
Top resid features:
18
Token 18
Feature activation-0.019
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
UN
TokenUN
Feature activation+0.003
Top resid features:
IX
TokenIX
Feature activation+0.004
Top resid features:
®
Token®
Feature activation-0.021
Top resid features:
is
Token is
Feature activation+0.677
Top resid features:
a
Token a
Feature activation+0.364
Top resid features:
registered
Token registered
Feature activation+0.124
Top resid features:
trademark
Token trademark
Feature activation+0.046
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
Citizen
Token Citizen
Feature activation-0.011
Top resid features:
Charles
Token Charles
Feature activation-0.050
Top resid features:
Foster
Token Foster
Feature activation-0.004
Top resid features:
Kane
Token Kane
Feature activation-0.018
Top resid features:
is
Token is
Feature activation+2.393
Top resid features:
based
Token based
Feature activation+0.217
Top resid features:
on
Token on
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
controversial
Token controversial
Feature activation+0.006
Top resid features:
publisher
Token publisher
Feature activation+0.002
Top resid features:
),
Token),
Feature activation+0.001
Top resid features:
or
Token or
Feature activation-0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.003
Top resid features:
ľ
Tokenľ
Feature activation-0.250
Top resid features:
E
TokenE
Feature activation-0.141
Top resid features:
is
Token is
Feature activation+2.926
Top resid features:
evidence
Token evidence
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
favor
Token favor
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
H
Token H
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.03

Head 6: 0.06

Head 7: 0.52

Head 8: 0.03

Head 9: 0.04

Head 10: 0.04

Head 11: 0.04

Positive logits

is2.55

isn2.27

denotes2.20

consists2.17

There2.15

belongs2.12

entails2.09

Jenner2.05

was2.04

There2.04

comprises2.03

Isn2.01

there2.00

involves1.99

Gram1.99

SQL1.97

THERE1.96

includes1.94

refers1.93

Congratulations1.91

Negative logits

irlf-2.34

aretz-2.07

yna-2.03

urat-1.93

hens-1.93

aho-1.92

democrat-1.87

abol-1.84

fid-1.84

inspector-1.84

uty-1.82

umbn-1.79

kered-1.76

usa-1.73

icro-1.73

ront-1.72

idav-1.71

-1.71

yden-1.69

oblig-1.68

INTERVAL 3.924 - 4.360
CONTAINS 0.000%

way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
those
Token those
Feature activation+1.402
who
Token who
Feature activation+1.286
can
Token can
Feature activation+4.360
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.519
,
Token,
Feature activation+2.400
it
Token it
Feature activation+0.000

INTERVAL 3.488 - 3.924
CONTAINS 0.000%

INTERVAL 3.052 - 3.488
CONTAINS 0.001%

improve
Token improve
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.153
;
Token;
Feature activation+0.185
to
Token to
Feature activation+3.428
be
Token be
Feature activation+3.075
perfect
Token perfect
Feature activation+1.060
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.153
;
Token;
Feature activation+0.185
to
Token to
Feature activation+3.428
be
Token be
Feature activation+3.075
perfect
Token perfect
Feature activation+1.060
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
change
Token change
Feature activation+0.000
often
Token often
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.000
or
Token or
Feature activation+1.556
âĢ
Token âĢ
Feature activation+2.196
ľ
Tokenľ
Feature activation+3.212
not
Tokennot
Feature activation+0.524
observing
Token observing
Feature activation+0.562
E
Token E
Feature activation+0.000
lowers
Token lowers
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.253
Total
Token Total
Feature activation+1.149
losses
Token losses
Feature activation+2.885
of
Token of
Feature activation+3.154
the
Token the
Feature activation+1.220
National
Token National
Feature activation+0.289
ist
Tokenist
Feature activation+0.771
Air
Token Air
Feature activation+1.361
Force
Token Force
Feature activation+2.087
delivered
Token delivered
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
padded
Token padded
Feature activation+0.000
envelop
Token envelop
Feature activation+0.000
-
Token -
Feature activation+3.226
inside
Token inside
Feature activation+1.696
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
sea
Token sea
Feature activation+0.000
breeze
Token breeze
Feature activation+0.000

INTERVAL 2.616 - 3.052
CONTAINS 0.000%

,
Token,
Feature activation+0.095
this
Token this
Feature activation+0.843
is
Token is
Feature activation+0.264
really
Token really
Feature activation+0.000
awesome
Token awesome
Feature activation+0.416
that
Token that
Feature activation+2.636
Cle
Token Cle
Feature activation+0.822
my
Tokenmy
Feature activation+0.743
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
spread
Token spread
Feature activation+0.000
fires
Token fires
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.003
ľ
Tokenľ
Feature activation+2.712
Almost
TokenAlmost
Feature activation+0.663
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Lower
Token Lower
Feature activation+0.000
A
Token A
Feature activation+0.000
towel
Token towel
Feature activation+0.000
is
Token is
Feature activation+0.000
deform
Token deform
Feature activation+0.000
able
Tokenable
Feature activation+0.000
;
Token;
Feature activation+2.664
a
Token a
Feature activation+1.932
mug
Token mug
Feature activation+0.209
or
Token or
Feature activation+0.139
a
Token a
Feature activation+0.166
computer
Token computer
Feature activation+0.543
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.253
Total
Token Total
Feature activation+1.149
losses
Token losses
Feature activation+2.885
of
Token of
Feature activation+3.154
the
Token the
Feature activation+1.220
National
Token National
Feature activation+0.289
ist
Tokenist
Feature activation+0.771
Air
Token Air
Feature activation+1.361

INTERVAL 2.180 - 2.616
CONTAINS 0.001%

profit
Tokenprofit
Feature activation+0.000
organization
Token organization
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.350
Ċ
TokenĊ
Feature activation+1.295
Windows
TokenWindows
Feature activation+2.283
®
Token®
Feature activation+2.074
is
Token is
Feature activation+0.669
a
Token a
Feature activation+0.129
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
of
Token of
Feature activation+0.000
The
Token The
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Group
Token Group
Feature activation+0.000
.
Token.
Feature activation+0.292
Ċ
TokenĊ
Feature activation+2.346
Ċ
TokenĊ
Feature activation+1.666
Virtual
TokenVirtual
Feature activation+1.825
Box
TokenBox
Feature activation+2.103
®
Token®
Feature activation+2.246
is
Token is
Feature activation+0.477
.
Token.
Feature activation+0.292
Ċ
TokenĊ
Feature activation+2.346
Ċ
TokenĊ
Feature activation+1.666
Virtual
TokenVirtual
Feature activation+1.825
Box
TokenBox
Feature activation+2.103
®
Token®
Feature activation+2.246
is
Token is
Feature activation+0.477
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
of
Token of
Feature activation+0.000
P
TokenP
Feature activation+0.000
(
Token(
Feature activation+0.000
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.000
or
Token or
Feature activation+1.556
âĢ
Token âĢ
Feature activation+2.196
ľ
Tokenľ
Feature activation+3.212
not
Tokennot
Feature activation+0.524
observing
Token observing
Feature activation+0.562
E
Token E
Feature activation+0.000
lowers
Token lowers
Feature activation+0.000
,
Token,
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.710
Ċ
TokenĊ
Feature activation+1.311
Wikipedia
TokenWikipedia
Feature activation+2.401
®
Token®
Feature activation+1.216
is
Token is
Feature activation+0.378
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000

INTERVAL 1.744 - 2.180
CONTAINS 0.003%

countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.542
Ċ
TokenĊ
Feature activation+1.692
Ċ
TokenĊ
Feature activation+0.529
UN
TokenUN
Feature activation+0.583
IX
TokenIX
Feature activation+2.124
®
Token®
Feature activation+0.594
is
Token is
Feature activation+0.257
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
and
Token and
Feature activation+0.000
above
Token above
Feature activation+0.000
:
Token:
Feature activation+0.180
the
Token the
Feature activation+1.901
up
Token up
Feature activation+0.338
values
Tokenvalues
Feature activation+0.373
are
Token are
Feature activation+0.576
mut
Token mut
Feature activation+0.000
able
Tokenable
Feature activation+0.000
while
Token while
Feature activation+0.947
ten
Token ten
Feature activation+0.297
ement
Tokenement
Feature activation+0.564
-
Token-
Feature activation+0.000
houses
Tokenhouses
Feature activation+0.000
[
Token [
Feature activation+1.785
were
Tokenwere
Feature activation+0.018
]
Token]
Feature activation+0.000
owned
Token owned
Feature activation+0.000
jointly
Token jointly
Feature activation+0.000
by
Token by
Feature activation+0.000
Group
Token Group
Feature activation+0.000
.
Token.
Feature activation+0.292
Ċ
TokenĊ
Feature activation+2.346
Ċ
TokenĊ
Feature activation+1.666
Virtual
TokenVirtual
Feature activation+1.825
Box
TokenBox
Feature activation+2.103
®
Token®
Feature activation+2.246
is
Token is
Feature activation+0.477
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
trademark
Token trademark
Feature activation+0.000
towel
Token towel
Feature activation+0.000
is
Token is
Feature activation+0.000
deform
Token deform
Feature activation+0.000
able
Tokenable
Feature activation+0.000
;
Token;
Feature activation+2.664
a
Token a
Feature activation+1.932
mug
Token mug
Feature activation+0.209
or
Token or
Feature activation+0.139
a
Token a
Feature activation+0.166
computer
Token computer
Feature activation+0.543
isn
Token isn
Feature activation+0.000

INTERVAL 1.308 - 1.744
CONTAINS 0.008%

Florida
Token Florida
Feature activation+0.000
State
Token State
Feature activation+0.000
Fair
Token Fair
Feature activation+0.000
grounds
Tokengrounds
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+1.432
on
Token on
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
,
Token,
Feature activation+0.314
about
Token about
Feature activation+0.000
7
Token 7
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
ever
Token ever
Feature activation+0.000
need
Token need
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
that
Token that
Feature activation+1.336
their
Token their
Feature activation+0.089
software
Token software
Feature activation+0.000
detects
Token detects
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
ages
Token ages
Feature activation+0.000
:
Token:
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
is
Token is
Feature activation+0.000
justified
Token justified
Feature activation+0.000
,
Token,
Feature activation+1.355
true
Token true
Feature activation+0.000
belief
Token belief
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
Oracle
Token Oracle
Feature activation+0.000
.
Token.
Feature activation+0.080
Ċ
TokenĊ
Feature activation+2.179
Ċ
TokenĊ
Feature activation+1.819
VM
TokenVM
Feature activation+1.482
ware
Tokenware
Feature activation+2.212
®
Token®
Feature activation+1.773
is
Token is
Feature activation+0.430
a
Token a
Feature activation+0.000
registered
Token registered
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
is
Token is
Feature activation+0.000
located
Token located
Feature activation+0.000
at
Token at
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.501
Eastern
Token Eastern
Feature activation+0.700
Is
Token Is
Feature activation+0.000
let
Tokenlet
Feature activation+0.775
is
Token is
Feature activation+0.000
located
Token located
Feature activation+0.000

INTERVAL 0.872 - 1.308
CONTAINS 0.018%

A
TokenA
Feature activation+0.000
IL
TokenIL
Feature activation+0.000
AV
Token AV
Feature activation+0.000
EN
TokenEN
Feature activation+0.000
UE
TokenUE
Feature activation+0.000
:
Token:
Feature activation+1.078
A
Token A
Feature activation+0.755
drunken
Token drunken
Feature activation+0.000
woman
Token woman
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.348
a
Token a
Feature activation+0.746
fifth
Token fifth
Feature activation+0.722
of
Token of
Feature activation+1.149
our
Token our
Feature activation+0.956
laws
Token laws
Feature activation+0.328
would
Token would
Feature activation+0.171
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
no
Token no
Feature activation+0.000
values
Token values
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
JavaScript
Token JavaScript
Feature activation+0.000
,
Token,
Feature activation+1.169
void
Token void
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
operator
Token operator
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
ninth
Token ninth
Feature activation+0.000
grade
Token grade
Feature activation+0.000
,
Token,
Feature activation+1.282
six
Token six
Feature activation+0.000
feet
Token feet
Feature activation+0.000
tall
Token tall
Feature activation+0.000
and
Token and
Feature activation+0.131
on
Token on
Feature activation+0.000
s
Tokens
Feature activation+0.000
huge
Token huge
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
And
Token And
Feature activation+1.279
Picard
Token Picard
Feature activation+0.379
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 0.436 - 0.872
CONTAINS 0.060%

with
Token with
Feature activation+0.000
yogurt
Token yogurt
Feature activation+0.000
sauce
Token sauce
Feature activation+0.000
;
Token;
Feature activation+0.132
Bro
Token Bro
Feature activation+0.000
dy
Tokendy
Feature activation+0.450
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.082
s
Tokens
Feature activation+0.106
Br
Token Br
Feature activation+0.000
ats
Tokenats
Feature activation+0.000
for
Token for
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
body
Token body
Feature activation+0.000
weight
Tokenweight
Feature activation+0.000
.
Token.
Feature activation+0.203
Ċ
TokenĊ
Feature activation+0.661
Ċ
TokenĊ
Feature activation+0.452
Oh
TokenOh
Feature activation+0.042
N
Token N
Feature activation+0.000
uts
Tokenuts
Feature activation+0.000
!
Token!
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
,
Token,
Feature activation+0.000
writing
Token writing
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.847
we
Tokenwe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
never
Token never
Feature activation+0.000
Shel
Token Shel
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
in
Token in
Feature activation+0.005
Pac
Token Pac
Feature activation+0.000
o
Tokeno
Feature activation+0.000
ima
Tokenima
Feature activation+0.724
,
Token,
Feature activation+0.000
Long
Token Long
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
and
Token and
Feature activation+0.000
Pom
Token Pom
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
an
Token an
Feature activation+0.000
offense
Token offense
Feature activation+0.000
while
Token while
Feature activation+0.097
less
Token less
Feature activation+0.503
scoring
Token scoring
Feature activation+1.062
,
Token,
Feature activation+0.492
or
Token or
Feature activation+0.000
,
Token,
Feature activation+0.000
better
Token better
Feature activation+0.000

INTERVAL 0.000 - 0.436
CONTAINS 99.909%

to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
whether
Token whether
Feature activation+0.000
a
Token a
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
federal
Token federal
Feature activation+0.000
grant
Token grant
Feature activation+0.000
to
Token to
Feature activation+0.000
Cad
Token Cad
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
would
Token would
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
absolute
Token absolute
Feature activation+0.000
considering
Token considering
Feature activation+0.000
our
Token our
Feature activation+0.000
new
Token new
Feature activation+0.000
-
Token-
Feature activation+0.000
found
Tokenfound
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
h
Tokenh
Feature activation+0.000
onest
Tokenonest
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
apologise
Token apologise
Feature activation+0.000
)
Token)
Feature activation+0.000
but
Token but
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
ository
Tokenository
Feature activation+0.000
stance
Token stance
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000
matter
Token matter
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
says
Token says
Feature activation+0.000
photographer
Token photographer
Feature activation+0.000
back
Token back
Feature activation+0.000
as
Token as
Feature activation+0.000
December
Token December
Feature activation+0.000
are
Token are
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
being
Token being
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
claim
Token claim
Feature activation+0.000
the
Token the
Feature activation+0.000
voucher
Token voucher
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 H7.7: (feature 1531)

TOP ACTIVATIONS
MAX = 3.416

gu
Token gu
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
and
Token and
Feature activation+0.455
30
Token 30
Feature activation+3.416
m
Token m
Feature activation+1.531
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
least
Token least
Feature activation+0.000
squares
Token squares
Feature activation+0.000
for
Token for
Feature activation+0.000
continuous
Token continuous
Feature activation+0.000
variables
Token variables
Feature activation+0.000
and
Token and
Feature activation+2.945
maximum
Token maximum
Feature activation+0.387
likelihood
Token likelihood
Feature activation+0.000
for
Token for
Feature activation+0.000
categ
Token categ
Feature activation+0.000
orical
Tokenorical
Feature activation+0.000
for
Token for
Feature activation+0.000
auto
Token auto
Feature activation+0.000
and
Token and
Feature activation+0.000
truck
Token truck
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
or
Token or
Feature activation+2.705
to
Token to
Feature activation+0.661
produce
Token produce
Feature activation+0.003
electricity
Token electricity
Feature activation+0.000
.
Token.
Feature activation+0.000
Cedar
Token Cedar
Feature activation+0.000
Hank
Token Hank
Feature activation+0.000
er
Tokener
Feature activation+0.000
for
Token for
Feature activation+0.000
simpler
Token simpler
Feature activation+0.000
times
Token times
Feature activation+0.000
,
Token,
Feature activation+2.655
when
Token when
Feature activation+0.000
mastery
Token mastery
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+0.000
for
Token for
Feature activation+0.000
low
Token low
Feature activation+0.000
income
Token income
Feature activation+0.000
earners
Token earners
Feature activation+0.000
to
Token to
Feature activation+1.560
$
Token $
Feature activation+2.415
1000
Token1000
Feature activation+0.595
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
These
TokenThese
Feature activation+0.000
two
Token two
Feature activation+0.000
and
Token and
Feature activation+1.156
up
Token up
Feature activation+0.514
to
Token to
Feature activation+0.795
$
Token $
Feature activation+0.180
1
Token1
Feature activation+0.000
million
Token million
Feature activation+2.261
for
Token for
Feature activation+0.010
a
Token a
Feature activation+0.000
corporation
Token corporation
Feature activation+0.000
selling
Token selling
Feature activation+0.000
across
Token across
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
for
Token for
Feature activation+0.000
parts
Token parts
Feature activation+0.000
and
Token and
Feature activation+0.317
45
Token 45
Feature activation+2.198
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.294
for
Token for
Feature activation+0.000
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+0.000
id
Tokenid
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
whole
Token whole
Feature activation+0.000
month
Token month
Feature activation+0.000
and
Token and
Feature activation+2.122
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
annual
Token annual
Feature activation+0.000
contract
Token contract
Feature activation+0.000
two
Token two
Feature activation+0.000
Glock
Token Glock
Feature activation+0.000
pistols
Token pistols
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.282
300
Token 300
Feature activation+2.122
cartridges
Token cartridges
Feature activation+0.441
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
pump
Token pump
Feature activation+0.000
-
Token-
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Tata
Token Tata
Feature activation+0.000
group
Token group
Feature activation+0.000
,
Token,
Feature activation+0.000
92
Token 92
Feature activation+2.111
.
Token.
Feature activation+0.000
16
Token16
Feature activation+0.626
%
Token%
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
automatic
Tokenautomatic
Feature activation+0.000
AR
Token AR
Feature activation+0.000
-
Token-
Feature activation+0.000
15
Token15
Feature activation+0.000
rifle
Token rifle
Feature activation+0.000
,
Token,
Feature activation+2.101
another
Token another
Feature activation+0.344
3
Token 3
Feature activation+1.578
,
Token,
Feature activation+0.541
000
Token000
Feature activation+0.591
for
Token for
Feature activation+0.000
there
Token there
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
stories
Token stories
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+2.098
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.322
here
Token here
Feature activation+0.690
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
awesome
Token awesome
Feature activation+0.000
cover
Token cover
Feature activation+0.000
and
Token and
Feature activation+1.629
thanks
Token thanks
Feature activation+1.234
to
Token to
Feature activation+2.047
everyone
Token everyone
Feature activation+0.708
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
nice
Token nice
Feature activation+0.000
things
Token things
Feature activation+0.000
pop
Token pop
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
small
Token small
Feature activation+0.000
ones
Token ones
Feature activation+0.000
and
Token and
Feature activation+1.976
about
Token about
Feature activation+0.876
$
Token $
Feature activation+0.287
12
Token12
Feature activation+0.861
for
Token for
Feature activation+0.067
the
Token the
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+1.973
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.424
here
Token here
Feature activation+0.490
because
Token because
Feature activation+0.000
walking
Token walking
Feature activation+0.000
groups
Token groups
Feature activation+0.000
for
Token for
Feature activation+0.000
seniors
Token seniors
Feature activation+0.000
and
Token and
Feature activation+1.229
a
Token a
Feature activation+1.891
program
Token program
Feature activation+1.546
that
Token that
Feature activation+0.000
brings
Token brings
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
produce
Token produce
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.858
raising
Token raising
Feature activation+1.793
capital
Token capital
Feature activation+0.000
gains
Token gains
Feature activation+0.000
tax
Token tax
Feature activation+0.415
and
Token and
Feature activation+0.000
mis
Tokenmis
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
for
Token for
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+0.000
and
Token and
Feature activation+1.823
destruction
Token destruction
Feature activation+1.677
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
fragile
Token fragile
Feature activation+0.000
life
Token life
Feature activation+0.000
election
Token election
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.867
am
Token am
Feature activation+0.827
going
Token going
Feature activation+1.504
to
Token to
Feature activation+1.822
teach
Token teach
Feature activation+0.000
a
Token a
Feature activation+0.000
lesson
Token lesson
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
for
Token for
Feature activation+0.000
track
Token track
Feature activation+0.004
and
Token and
Feature activation+0.000
process
Token process
Feature activation+0.417
to
Token to
Feature activation+0.415
company
Token company
Feature activation+1.821
content
Token content
Feature activation+1.120
of
Token of
Feature activation+0.000
cases
Token cases
Feature activation+0.000
for
Token for
Feature activation+0.821
design
Token design
Feature activation+0.797

Top DFA by src position
MAX = 4.269

m
Tokenm
Feature activation-0.000
Top resid features:
ots
Tokenots
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
40
Token 40
Feature activation-0.017
Top resid features:
m
Token m
Feature activation-0.329
Top resid features:
for
Token for
Feature activation+4.269
Top resid features:
the
Token the
Feature activation+0.285
Top resid features:
Ce
Token Ce
Feature activation+0.002
Top resid features:
pp
Tokenpp
Feature activation-0.005
Top resid features:
hus
Tokenhus
Feature activation-0.005
Top resid features:
gu
Token gu
Feature activation-0.001
Top resid features:
were
Token were
Feature activation-0.011
Top resid features:
assessed
Token assessed
Feature activation+0.015
Top resid features:
using
Token using
Feature activation+0.016
Top resid features:
least
Token least
Feature activation-0.018
Top resid features:
squares
Token squares
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+3.554
Top resid features:
continuous
Token continuous
Feature activation+0.026
Top resid features:
variables
Token variables
Feature activation+0.040
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
maximum
Token maximum
Feature activation+0.000
Top resid features:
likelihood
Token likelihood
Feature activation+0.000
Top resid features:
used
Token used
Feature activation-0.028
Top resid features:
as
Token as
Feature activation-0.003
Top resid features:
either
Token either
Feature activation+0.157
Top resid features:
natural
Token natural
Feature activation+0.051
Top resid features:
gas
Token gas
Feature activation-0.029
Top resid features:
for
Token for
Feature activation+3.453
Top resid features:
auto
Token auto
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
truck
Token truck
Feature activation-0.019
Top resid features:
fuel
Token fuel
Feature activation+0.040
Top resid features:
or
Token or
Feature activation-0.024
Top resid features:
too
Token too
Feature activation-0.024
Top resid features:
much
Token much
Feature activation-0.009
Top resid features:
?
Token?
Feature activation-0.052
Top resid features:
Hank
Token Hank
Feature activation+0.030
Top resid features:
er
Tokener
Feature activation-0.010
Top resid features:
for
Token for
Feature activation+3.308
Top resid features:
simpler
Token simpler
Feature activation+0.066
Top resid features:
times
Token times
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
mastery
Token mastery
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
current
Token current
Feature activation+0.030
Top resid features:
$
Token $
Feature activation+0.015
Top resid features:
500
Token500
Feature activation+0.027
Top resid features:
for
Token for
Feature activation+2.929
Top resid features:
low
Token low
Feature activation+0.010
Top resid features:
income
Token income
Feature activation+0.015
Top resid features:
earners
Token earners
Feature activation+0.018
Top resid features:
to
Token to
Feature activation-0.035
Top resid features:
$
Token $
Feature activation-0.036
Top resid features:
$
Token $
Feature activation+0.010
Top resid features:
250
Token250
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
000
Token000
Feature activation-0.002
Top resid features:
fine
Token fine
Feature activation-0.009
Top resid features:
for
Token for
Feature activation+1.965
Top resid features:
an
Token an
Feature activation+0.719
Top resid features:
individual
Token individual
Feature activation+0.288
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
up
Token up
Feature activation-0.059
Top resid features:
to
Token to
Feature activation+0.034
Top resid features:
Ŀ
TokenĿ
Feature activation-0.002
Top resid features:
at
Token at
Feature activation+0.037
Top resid features:
35
Token 35
Feature activation-0.005
Top resid features:
per
Token per
Feature activation-0.174
Top resid features:
cent
Token cent
Feature activation-0.083
Top resid features:
for
Token for
Feature activation+2.956
Top resid features:
parts
Token parts
Feature activation+0.152
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
45
Token 45
Feature activation-0.014
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
cent
Token cent
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.007
Top resid features:
than
Token than
Feature activation+0.016
Top resid features:
twenty
Token twenty
Feature activation-0.006
Top resid features:
qu
Token qu
Feature activation+0.011
Top resid features:
id
Tokenid
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+2.334
Top resid features:
a
Token a
Feature activation+0.249
Top resid features:
whole
Token whole
Feature activation+0.038
Top resid features:
month
Token month
Feature activation+0.087
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
another
Token another
Feature activation+0.009
Top resid features:
3
Token 3
Feature activation-0.016
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
000
Token000
Feature activation-0.043
Top resid features:
for
Token for
Feature activation+1.688
Top resid features:
his
Token his
Feature activation+0.290
Top resid features:
two
Token two
Feature activation+0.016
Top resid features:
Glock
Token Glock
Feature activation+0.009
Top resid features:
pistols
Token pistols
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
within
Token within
Feature activation+0.003
Top resid features:
India
Token India
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
83
Token 83
Feature activation-0.010
Top resid features:
%
Token%
Feature activation-0.134
Top resid features:
for
Token for
Feature activation+2.886
Top resid features:
the
Token the
Feature activation+0.123
Top resid features:
Tata
Token Tata
Feature activation+0.023
Top resid features:
group
Token group
Feature activation+0.017
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
92
Token 92
Feature activation-0.035
Top resid features:
ammunition
Token ammunition
Feature activation+0.003
Top resid features:
:
Token:
Feature activation+0.019
Top resid features:
3
Token 3
Feature activation-0.019
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
000
Token000
Feature activation-0.005
Top resid features:
for
Token for
Feature activation+2.750
Top resid features:
his
Token his
Feature activation+0.101
Top resid features:
.
Token .
Feature activation+0.015
Top resid features:
233
Token233
Feature activation+0.004
Top resid features:
semi
Token semi
Feature activation-0.006
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation-0.035
Top resid features:
re
Tokenre
Feature activation-0.037
Top resid features:
not
Token not
Feature activation-0.026
Top resid features:
there
Token there
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+2.950
Top resid features:
their
Token their
Feature activation+0.075
Top resid features:
stories
Token stories
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
we
Token we
Feature activation-0.038
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
Simon
Token Simon
Feature activation-0.062
Top resid features:
Hol
Token Hol
Feature activation-0.017
Top resid features:
ub
Tokenub
Feature activation-0.012
Top resid features:
for
Token for
Feature activation+2.088
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
awesome
Token awesome
Feature activation-0.005
Top resid features:
cover
Token cover
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
thanks
Token thanks
Feature activation+0.052
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.053
Top resid features:
4
Token4
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.022
Top resid features:
pop
Token pop
Feature activation+0.026
Top resid features:
for
Token for
Feature activation+2.212
Top resid features:
the
Token the
Feature activation+0.242
Top resid features:
small
Token small
Feature activation+0.076
Top resid features:
ones
Token ones
Feature activation+0.119
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.027
Top resid features:
Ļ
TokenĻ
Feature activation-0.029
Top resid features:
re
Tokenre
Feature activation-0.120
Top resid features:
not
Token not
Feature activation-0.010
Top resid features:
here
Token here
Feature activation-0.030
Top resid features:
for
Token for
Feature activation+2.418
Top resid features:
the
Token the
Feature activation+0.388
Top resid features:
money
Token money
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
we
Token we
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ville
Tokenville
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
including
Token including
Feature activation+0.041
Top resid features:
walking
Token walking
Feature activation-0.024
Top resid features:
groups
Token groups
Feature activation+0.093
Top resid features:
for
Token for
Feature activation+2.342
Top resid features:
seniors
Token seniors
Feature activation+0.059
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
a
Token a
Feature activation+0.048
Top resid features:
program
Token program
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.078
Top resid features:
tax
Token tax
Feature activation+0.082
Top resid features:
(
Token (
Feature activation+0.134
Top resid features:
48
Token48
Feature activation-0.005
Top resid features:
%)
Token%)
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+2.114
Top resid features:
people
Token people
Feature activation+0.094
Top resid features:
who
Token who
Feature activation+0.039
Top resid features:
earn
Token earn
Feature activation+0.019
Top resid features:
over
Token over
Feature activation-0.002
Top resid features:
âĤ¬
Token âĤ¬
Feature activation+0.004
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
sickness
Token sickness
Feature activation-0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.004
Top resid features:
mis
Tokenmis
Feature activation-0.027
Top resid features:
ery
Tokenery
Feature activation-0.077
Top resid features:
for
Token for
Feature activation+2.521
Top resid features:
human
Token human
Feature activation-0.003
Top resid features:
beings
Token beings
Feature activation+0.152
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
destruction
Token destruction
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
not
Token not
Feature activation-0.004
Top resid features:
going
Token going
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
AAP
Token AAP
Feature activation-0.037
Top resid features:
for
Token for
Feature activation+2.433
Top resid features:
a
Token a
Feature activation+0.035
Top resid features:
ticket
Token ticket
Feature activation+0.045
Top resid features:
or
Token or
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
contest
Token contest
Feature activation-0.007
Top resid features:
components
Token components
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.045
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
company
Token company
Feature activation-0.006
Top resid features:
test
Token test
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.878
Top resid features:
company
Token company
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.869
Top resid features:
track
Token track
Feature activation+0.038
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
process
Token process
Feature activation+0.019
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.02

Head 3: 0.05

Head 4: 0.05

Head 5: 0.05

Head 6: 0.05

Head 7: 0.52

Head 8: 0.04

Head 9: 0.03

Head 10: 0.05

Head 11: 0.04

Positive logits

allows2.31

limit2.17

Allows2.11

cutoff2.02

spoilers1.94

Allows1.93

crates1.92

••1.91

for1.83

elsen1.81

guarantees1.81

Skydragon1.80

helps1.77

Palest1.75

boxes1.72

Measures1.72

Franch1.69

spoiler1.69

Lim1.69

significance1.68

Negative logits

ophys-2.11

indu-1.93

grow-1.90

rored-1.89

mobile-1.88

ablished-1.84

escent-1.84

phys-1.83

aria-1.80

minent-1.79

rina-1.78

acia-1.78

stroke-1.75

irit-1.75

accidents-1.73

initialized-1.72

racted-1.71

igenous-1.69

ablish-1.69

bite-1.69

INTERVAL 3.074 - 3.416
CONTAINS 0.000%

gu
Token gu
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ots
Tokenots
Feature activation+0.000
and
Token and
Feature activation+0.455
30
Token 30
Feature activation+3.416
m
Token m
Feature activation+1.531
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000

INTERVAL 2.732 - 3.074
CONTAINS 0.000%

least
Token least
Feature activation+0.000
squares
Token squares
Feature activation+0.000
for
Token for
Feature activation+0.000
continuous
Token continuous
Feature activation+0.000
variables
Token variables
Feature activation+0.000
and
Token and
Feature activation+2.945
maximum
Token maximum
Feature activation+0.387
likelihood
Token likelihood
Feature activation+0.000
for
Token for
Feature activation+0.000
categ
Token categ
Feature activation+0.000
orical
Tokenorical
Feature activation+0.000

INTERVAL 2.391 - 2.732
CONTAINS 0.000%

Hank
Token Hank
Feature activation+0.000
er
Tokener
Feature activation+0.000
for
Token for
Feature activation+0.000
simpler
Token simpler
Feature activation+0.000
times
Token times
Feature activation+0.000
,
Token,
Feature activation+2.655
when
Token when
Feature activation+0.000
mastery
Token mastery
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+0.000
for
Token for
Feature activation+0.000
low
Token low
Feature activation+0.000
income
Token income
Feature activation+0.000
earners
Token earners
Feature activation+0.000
to
Token to
Feature activation+1.560
$
Token $
Feature activation+2.415
1000
Token1000
Feature activation+0.595
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
These
TokenThese
Feature activation+0.000
two
Token two
Feature activation+0.000
for
Token for
Feature activation+0.000
auto
Token auto
Feature activation+0.000
and
Token and
Feature activation+0.000
truck
Token truck
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
or
Token or
Feature activation+2.705
to
Token to
Feature activation+0.661
produce
Token produce
Feature activation+0.003
electricity
Token electricity
Feature activation+0.000
.
Token.
Feature activation+0.000
Cedar
Token Cedar
Feature activation+0.000

INTERVAL 2.049 - 2.391
CONTAINS 0.001%

for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Tata
Token Tata
Feature activation+0.000
group
Token group
Feature activation+0.000
,
Token,
Feature activation+0.000
92
Token 92
Feature activation+2.111
.
Token.
Feature activation+0.000
16
Token16
Feature activation+0.626
%
Token%
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
id
Tokenid
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
whole
Token whole
Feature activation+0.000
month
Token month
Feature activation+0.000
and
Token and
Feature activation+2.122
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
annual
Token annual
Feature activation+0.000
contract
Token contract
Feature activation+0.000
two
Token two
Feature activation+0.000
Glock
Token Glock
Feature activation+0.000
pistols
Token pistols
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.282
300
Token 300
Feature activation+2.122
cartridges
Token cartridges
Feature activation+0.441
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
pump
Token pump
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+1.156
up
Token up
Feature activation+0.514
to
Token to
Feature activation+0.795
$
Token $
Feature activation+0.180
1
Token1
Feature activation+0.000
million
Token million
Feature activation+2.261
for
Token for
Feature activation+0.010
a
Token a
Feature activation+0.000
corporation
Token corporation
Feature activation+0.000
selling
Token selling
Feature activation+0.000
across
Token across
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
for
Token for
Feature activation+0.000
parts
Token parts
Feature activation+0.000
and
Token and
Feature activation+0.317
45
Token 45
Feature activation+2.198
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.294
for
Token for
Feature activation+0.000
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.708 - 2.049
CONTAINS 0.002%

000
Token000
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.858
raising
Token raising
Feature activation+1.793
capital
Token capital
Feature activation+0.000
gains
Token gains
Feature activation+0.000
tax
Token tax
Feature activation+0.415
and
Token and
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
for
Token for
Feature activation+0.000
chickens
Token chickens
Feature activation+0.000
and
Token and
Feature activation+0.000
bees
Token bees
Feature activation+0.000
,
Token,
Feature activation+1.772
vegetable
Token vegetable
Feature activation+0.000
beds
Token beds
Feature activation+0.000
for
Token for
Feature activation+0.000
sunny
Token sunny
Feature activation+0.000
spots
Token spots
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.469
up
Token up
Feature activation+1.407
to
Token to
Feature activation+1.778
five
Token five
Feature activation+0.350
years
Token years
Feature activation+1.111
behind
Token behind
Feature activation+0.145
bars
Token bars
Feature activation+0.000
,
Token,
Feature activation+0.000
walking
Token walking
Feature activation+0.000
groups
Token groups
Feature activation+0.000
for
Token for
Feature activation+0.000
seniors
Token seniors
Feature activation+0.000
and
Token and
Feature activation+1.229
a
Token a
Feature activation+1.891
program
Token program
Feature activation+1.546
that
Token that
Feature activation+0.000
brings
Token brings
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
produce
Token produce
Feature activation+0.000
mis
Tokenmis
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
for
Token for
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+0.000
and
Token and
Feature activation+1.823
destruction
Token destruction
Feature activation+1.677
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
fragile
Token fragile
Feature activation+0.000
life
Token life
Feature activation+0.000

INTERVAL 1.366 - 1.708
CONTAINS 0.003%

guests
Token guests
Feature activation+0.000
on
Token on
Feature activation+0.000
arrival
Token arrival
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+1.403
as
Token as
Feature activation+1.269
a
Token a
Feature activation+0.449
full
Token full
Feature activation+0.254
wedding
Token wedding
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
,
Token,
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
for
Token for
Feature activation+0.000
governor
Token governor
Feature activation+0.000
and
Token and
Feature activation+1.613
Jean
Token Jean
Feature activation+0.203
Sch
Token Sch
Feature activation+0.000
od
Tokenod
Feature activation+0.000
orf
Tokenorf
Feature activation+1.427
for
Token for
Feature activation+0.000
-
Token-
Feature activation+0.000
15
Token15
Feature activation+0.000
rifle
Token rifle
Feature activation+0.000
,
Token,
Feature activation+2.101
another
Token another
Feature activation+0.344
3
Token 3
Feature activation+1.578
,
Token,
Feature activation+0.541
000
Token000
Feature activation+0.591
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
two
Token two
Feature activation+0.000
drill
Token drill
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
34
Token 34
Feature activation+0.744
inches
Token inches
Feature activation+1.574
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
surface
Token surface
Feature activation+0.000
which
Token which
Feature activation+0.000
500
Token500
Feature activation+0.000
for
Token for
Feature activation+0.000
low
Token low
Feature activation+0.000
income
Token income
Feature activation+0.000
earners
Token earners
Feature activation+0.000
to
Token to
Feature activation+1.560
$
Token $
Feature activation+2.415
1000
Token1000
Feature activation+0.595
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
These
TokenThese
Feature activation+0.000

INTERVAL 1.025 - 1.366
CONTAINS 0.004%

The
TokenThe
Feature activation+0.000
state
Token state
Feature activation+0.000
also
Token also
Feature activation+0.061
objected
Token objected
Feature activation+0.272
to
Token to
Feature activation+1.732
a
Token a
Feature activation+1.307
bail
Token bail
Feature activation+0.448
application
Token application
Feature activation+0.071
on
Token on
Feature activation+0.000
behalf
Token behalf
Feature activation+0.000
of
Token of
Feature activation+0.000
for
Token for
Feature activation+0.000
our
Token our
Feature activation+0.000
elderly
Token elderly
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
our
Token our
Feature activation+1.277
young
Token young
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
our
Token our
Feature activation+0.000
workers
Token workers
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
awesome
Token awesome
Feature activation+0.000
cover
Token cover
Feature activation+0.000
and
Token and
Feature activation+1.629
thanks
Token thanks
Feature activation+1.234
to
Token to
Feature activation+2.047
everyone
Token everyone
Feature activation+0.708
who
Token who
Feature activation+0.000
said
Token said
Feature activation+0.000
nice
Token nice
Feature activation+0.000
the
Token the
Feature activation+0.000
16
Token 16
Feature activation+0.000
GB
TokenGB
Feature activation+0.000
model
Token model
Feature activation+0.000
and
Token and
Feature activation+1.751
$
Token $
Feature activation+1.264
300
Token300
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
32
Token 32
Feature activation+0.000
GB
TokenGB
Feature activation+0.000
Mult
TokenMult
Feature activation+0.000
ipl
Tokenipl
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
Spec
Token Spec
Feature activation+0.000
ifies
Tokenifies
Feature activation+0.604
the
Token the
Feature activation+1.250
scaling
Token scaling
Feature activation+0.690
factor
Token factor
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
damage
Token damage
Feature activation+0.000

INTERVAL 0.683 - 1.025
CONTAINS 0.010%

16
Token16
Feature activation+1.041
per
Token per
Feature activation+0.946
barrel
Token barrel
Feature activation+0.804
on
Token on
Feature activation+0.537
the
Token the
Feature activation+0.604
first
Token first
Feature activation+0.684
6
Token 6
Feature activation+0.000
million
Token million
Feature activation+1.253
barrels
Token barrels
Feature activation+0.071
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
:
Token:
Feature activation+0.000
automatic
Token automatic
Feature activation+0.000
triggers
Token triggers
Feature activation+0.000
for
Token for
Feature activation+0.000
sanctions
Token sanctions
Feature activation+0.000
;
Token;
Feature activation+0.744
no
Token no
Feature activation+0.195
commitment
Token commitment
Feature activation+0.000
to
Token to
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
rebel
Token rebel
Feature activation+0.000
of
Token of
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
for
Token for
Feature activation+0.000
Medicare
Token Medicare
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.821
Social
Token Social
Feature activation+0.000
Security
Token Security
Feature activation+0.321
physically
Token physically
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
warp
Token warp
Feature activation+0.000
-
Token-
Feature activation+0.000
around
Tokenaround
Feature activation+0.000
shower
Token shower
Feature activation+0.000
curtains
Token curtains
Feature activation+0.000
and
Token and
Feature activation+0.812
sturdy
Token sturdy
Feature activation+1.408
longer
Token longer
Feature activation+0.000
platforms
Token platforms
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
amnesty
Token amnesty
Feature activation+0.000
for
Token for
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.000
,
Token,
Feature activation+0.702
said
Token said
Feature activation+0.000
Br
Token Br
Feature activation+0.000
at
Tokenat
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 0.342 - 0.683
CONTAINS 0.022%

movements
Token movements
Feature activation+0.000
of
Token of
Feature activation+0.000
classical
Token classical
Feature activation+0.000
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.636
it
Token it
Feature activation+0.690
fails
Token fails
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
try
Token try
Feature activation+0.000
t
Tokent
Feature activation+0.000
for
Token for
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
this
Tokenthis
Feature activation+0.023
is
Token is
Feature activation+0.528
a
Token a
Feature activation+0.219
simulation
Token simulation
Feature activation+0.000
that
Token that
Feature activation+0.000
demands
Token demands
Feature activation+0.000
dedication
Token dedication
Feature activation+0.000
information
Token information
Feature activation+0.000
,
Token,
Feature activation+0.277
for
Token for
Feature activation+0.000
writing
Token writing
Feature activation+0.000
reports
Token reports
Feature activation+0.000
,
Token,
Feature activation+0.460
for
Token for
Feature activation+0.000
research
Token research
Feature activation+0.002
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.317
for
Token for
Feature activation+0.000
young
Token young
Feature activation+0.000
adult
Token adult
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.000
nor
Token nor
Feature activation+0.708
the
Token the
Feature activation+0.639
path
Token path
Feature activation+0.000
to
Token to
Feature activation+0.000
citizenship
Token citizenship
Feature activation+0.000
contained
Token contained
Feature activation+0.000
in
Token in
Feature activation+0.000
byte
Token byte
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
enum
Token enum
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.552
padding
Token padding
Feature activation+0.042
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
pointers
Token pointers
Feature activation+0.000

INTERVAL 0.000 - 0.342
CONTAINS 99.958%

doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
belong
Token belong
Feature activation+0.000
to
Token to
Feature activation+0.000
AZ
Token AZ
Feature activation+0.000
A
TokenA
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
rules
Token rules
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
bowl
Token bowl
Feature activation+0.000
,
Token,
Feature activation+0.000
mix
Token mix
Feature activation+0.000
your
Token your
Feature activation+0.000
oats
Token oats
Feature activation+0.000
,
Token,
Feature activation+0.000
sugar
Token sugar
Feature activation+0.000
John
Token John
Feature activation+0.000
sson
Tokensson
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
John
TokenJohn
Feature activation+0.000
sson
Tokensson
Feature activation+0.000
stated
Token stated
Feature activation+0.000
that
Token that
Feature activation+0.000
although
Token although
Feature activation+0.000
to
Token to
Feature activation+0.000
grab
Token grab
Feature activation+0.000
its
Token its
Feature activation+0.000
target
Token target
Feature activation+0.000
audience
Token audience
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
shoulders
Token shoulders
Feature activation+0.000
and
Token and
Feature activation+0.000
insist
Token insist
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
name
Token name
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
assigned
Token assigned
Feature activation+0.000
the
Token the
Feature activation+0.000
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.000
photographer
Token photographer
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H7.7: (feature 41454)

TOP ACTIVATIONS
MAX = 5.107

interfering
Token interfering
Feature activation+0.000
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.173
in
Token in
Feature activation+3.976
any
Token any
Feature activation+1.424
way
Token way
Feature activation+5.107
disturbing
Token disturbing
Feature activation+0.014
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
or
Token or
Feature activation+0.000
access
Token access
Feature activation+0.212
letter
Token letter
Feature activation+0.000
also
Token also
Feature activation+0.000
responded
Token responded
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+5.057
seemed
Token seemed
Feature activation+3.439
to
Token to
Feature activation+1.708
debunk
Token debunk
Feature activation+0.289
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.077
engagement
Token engagement
Feature activation+4.874
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
communities
Token communities
Feature activation+0.000
must
Token must
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+4.795
after
Token after
Feature activation+0.000
,
Token,
Feature activation+0.000
approving
Token approving
Feature activation+0.000
the
Token the
Feature activation+0.000
2005
Token 2005
Feature activation+0.000
that
Token that
Feature activation+0.000
results
Token results
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+3.221
is
Token is
Feature activation+4.735
likely
Token likely
Feature activation+4.063
to
Token to
Feature activation+2.539
result
Token result
Feature activation+2.998
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
template
Token template
Feature activation+0.000
?
Token?
Feature activation+0.000
XML
Token XML
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
XML
Token XML
Feature activation+4.243
out
Token out
Feature activation+0.549
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+0.000
score
Token score
Feature activation+0.000
is
Token is
Feature activation+0.000
equal
Token equal
Feature activation+0.000
to
Token to
Feature activation+0.000
or
Token or
Feature activation+0.764
greater
Token greater
Feature activation+4.220
than
Token than
Feature activation+0.000
80
Token 80
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
action
Token action
Feature activation+0.000
Iraqis
Token Iraqis
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.149
or
Token or
Feature activation+3.923
in
Token in
Feature activation+4.174
collaboration
Token collaboration
Feature activation+3.950
with
Token with
Feature activation+0.035
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Coalition
Token Coalition
Feature activation+0.000
increase
Token increase
Feature activation+0.000
in
Token in
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.694
promotion
Token promotion
Feature activation+4.068
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
language
Token language
Feature activation+0.000
.
Token.
Feature activation+0.000
Public
Token Public
Feature activation+0.000
results
Token results
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+3.221
is
Token is
Feature activation+4.735
likely
Token likely
Feature activation+4.063
to
Token to
Feature activation+2.539
result
Token result
Feature activation+2.998
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
physical
Token physical
Feature activation+0.000
restrained
Token restrained
Feature activation+0.000
from
Token from
Feature activation+0.000
interfering
Token interfering
Feature activation+0.000
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.173
in
Token in
Feature activation+3.976
any
Token any
Feature activation+1.424
way
Token way
Feature activation+5.107
disturbing
Token disturbing
Feature activation+0.014
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.149
or
Token or
Feature activation+3.923
in
Token in
Feature activation+4.174
collaboration
Token collaboration
Feature activation+3.950
with
Token with
Feature activation+0.035
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Coalition
Token Coalition
Feature activation+0.000
forces
Token forces
Feature activation+0.000
or
Token or
Feature activation+0.000
Iraqis
Token Iraqis
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.149
or
Token or
Feature activation+3.923
in
Token in
Feature activation+4.174
collaboration
Token collaboration
Feature activation+3.950
with
Token with
Feature activation+0.035
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
construed
Token construed
Feature activation+0.000
to
Token to
Feature activation+0.000
invalid
Token invalid
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
,
Token,
Feature activation+0.000
impair
Token impair
Feature activation+3.913
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
supers
Token supers
Feature activation+0.000
ede
Tokenede
Feature activation+0.000
any
Token any
Feature activation+0.000
the
Token the
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Is
Token Is
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
is
Token is
Feature activation+2.373
located
Token located
Feature activation+3.687
at
Token at
Feature activation+1.202
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
routinely
Token routinely
Feature activation+0.000
ask
Token ask
Feature activation+0.000
for
Token for
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+1.417
receive
Token receive
Feature activation+3.672
âĢĶ
Token âĢĶ
Feature activation+0.000
user
Token user
Feature activation+0.000
data
Token data
Feature activation+0.000
from
Token from
Feature activation+0.000
telecom
Token telecom
Feature activation+0.000
also
Token also
Feature activation+0.000
responded
Token responded
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+5.057
seemed
Token seemed
Feature activation+3.439
to
Token to
Feature activation+1.708
debunk
Token debunk
Feature activation+0.289
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
claim
Token claim
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.124
not
Token not
Feature activation+3.222
doing
Token doing
Feature activation+0.000
something
Token something
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
,
Token,
Feature activation+0.129
at
Token at
Feature activation+0.000
violence
Token violence
Feature activation+0.000
that
Token that
Feature activation+0.000
results
Token results
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+3.221
is
Token is
Feature activation+4.735
likely
Token likely
Feature activation+4.063
to
Token to
Feature activation+2.539
result
Token result
Feature activation+2.998
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.012
or
Token or
Feature activation+0.039
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.071
very
Token very
Feature activation+0.188
least
Token least
Feature activation+3.056
raise
Token raise
Feature activation+0.028
a
Token a
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
eyebrow
Token eyebrow
Feature activation+0.000
at
Token at
Feature activation+0.000

Top DFA by src position
MAX = 5.490

is
Token is
Feature activation+0.028
Top resid features:
restrained
Token restrained
Feature activation-0.000
Top resid features:
from
Token from
Feature activation+0.023
Top resid features:
interfering
Token interfering
Feature activation+0.014
Top resid features:
with
Token with
Feature activation+0.034
Top resid features:
or
Token or
Feature activation+5.490
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
any
Token any
Feature activation+0.029
Top resid features:
way
Token way
Feature activation+0.017
Top resid features:
disturbing
Token disturbing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
12
Token12
Feature activation-0.013
Top resid features:
letter
Token letter
Feature activation-0.069
Top resid features:
also
Token also
Feature activation-0.048
Top resid features:
responded
Token responded
Feature activation-0.020
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+4.785
Top resid features:
and
Token and
Feature activation+1.088
Top resid features:
seemed
Token seemed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
debunk
Token debunk
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
nature
Token nature
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
citizen
Token citizen
Feature activation+0.012
Top resid features:
interest
Token interest
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.070
Top resid features:
and
Token and
Feature activation+5.351
Top resid features:
engagement
Token engagement
Feature activation+0.024
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
affected
Token affected
Feature activation-0.009
Top resid features:
communities
Token communities
Feature activation-0.002
Top resid features:
must
Token must
Feature activation+0.029
Top resid features:
heard
Token heard
Feature activation+0.002
Top resid features:
before
Token before
Feature activation-0.050
Top resid features:
,
Token,
Feature activation+5.477
Top resid features:
not
Token not
Feature activation-0.009
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
approving
Token approving
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
violence
Token violence
Feature activation-0.027
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
results
Token results
Feature activation+0.046
Top resid features:
in
Token in
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+1.974
Top resid features:
or
Token or
Feature activation+3.287
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
template
Token template
Feature activation-0.003
Top resid features:
?
Token?
Feature activation+0.022
Top resid features:
XML
Token XML
Feature activation-0.003
Top resid features:
in
Token in
Feature activation-0.347
Top resid features:
,
Token,
Feature activation+5.241
Top resid features:
XML
Token XML
Feature activation-0.009
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
guessed
Token guessed
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
score
Token score
Feature activation-0.032
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
equal
Token equal
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
or
Token or
Feature activation+4.888
Top resid features:
greater
Token greater
Feature activation+0.001
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
80
Token 80
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Another
Token Another
Feature activation+0.000
Top resid features:
personnel
Token personnel
Feature activation-0.008
Top resid features:
or
Token or
Feature activation-0.011
Top resid features:
Iraqis
Token Iraqis
Feature activation-0.011
Top resid features:
working
Token working
Feature activation+0.063
Top resid features:
for
Token for
Feature activation+0.031
Top resid features:
,
Token,
Feature activation+2.393
Top resid features:
or
Token or
Feature activation+2.266
Top resid features:
in
Token in
Feature activation+0.016
Top resid features:
collaboration
Token collaboration
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
gradual
Token gradual
Feature activation+0.033
Top resid features:
increase
Token increase
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.015
Top resid features:
attention
Token attention
Feature activation-0.033
Top resid features:
to
Token to
Feature activation-0.045
Top resid features:
and
Token and
Feature activation+4.703
Top resid features:
promotion
Token promotion
Feature activation+0.038
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
language
Token language
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
violence
Token violence
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
results
Token results
Feature activation+0.031
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+1.466
Top resid features:
or
Token or
Feature activation+3.178
Top resid features:
is
Token is
Feature activation-0.013
Top resid features:
likely
Token likely
Feature activation-0.018
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
restrained
Token restrained
Feature activation-0.003
Top resid features:
from
Token from
Feature activation-0.000
Top resid features:
interfering
Token interfering
Feature activation-0.006
Top resid features:
with
Token with
Feature activation+0.026
Top resid features:
or
Token or
Feature activation+4.478
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
disturbing
Token disturbing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
personnel
Token personnel
Feature activation-0.039
Top resid features:
or
Token or
Feature activation-0.034
Top resid features:
Iraqis
Token Iraqis
Feature activation-0.035
Top resid features:
working
Token working
Feature activation+0.017
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+3.520
Top resid features:
or
Token or
Feature activation+0.990
Top resid features:
in
Token in
Feature activation+0.108
Top resid features:
collaboration
Token collaboration
Feature activation+0.032
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
personnel
Token personnel
Feature activation-0.012
Top resid features:
or
Token or
Feature activation-0.016
Top resid features:
Iraqis
Token Iraqis
Feature activation-0.031
Top resid features:
working
Token working
Feature activation+0.143
Top resid features:
for
Token for
Feature activation+0.180
Top resid features:
,
Token,
Feature activation+3.803
Top resid features:
or
Token or
Feature activation+0.448
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
collaboration
Token collaboration
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
construed
Token construed
Feature activation-0.014
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
invalid
Token invalid
Feature activation-0.005
Top resid features:
ate
Tokenate
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+4.546
Top resid features:
impair
Token impair
Feature activation-0.059
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
supers
Token supers
Feature activation+0.000
Top resid features:
ede
Tokenede
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
let
Tokenlet
Feature activation-0.022
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
located
Token located
Feature activation+0.003
Top resid features:
at
Token at
Feature activation-0.231
Top resid features:
and
Token and
Feature activation+4.591
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
Eastern
Token Eastern
Feature activation-0.065
Top resid features:
Is
Token Is
Feature activation-0.000
Top resid features:
let
Tokenlet
Feature activation-0.020
Top resid features:
is
Token is
Feature activation-0.008
Top resid features:
already
Token already
Feature activation+0.006
Top resid features:
routinely
Token routinely
Feature activation+0.049
Top resid features:
ask
Token ask
Feature activation+0.053
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.836
Top resid features:
and
Token and
Feature activation+2.345
Top resid features:
receive
Token receive
Feature activation+0.059
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
user
Token user
Feature activation+0.000
Top resid features:
data
Token data
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
letter
Token letter
Feature activation-0.037
Top resid features:
also
Token also
Feature activation-0.035
Top resid features:
responded
Token responded
Feature activation-0.077
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+1.576
Top resid features:
and
Token and
Feature activation+2.708
Top resid features:
seemed
Token seemed
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
debunk
Token debunk
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:
osphere
Tokenosphere
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
way
Token way
Feature activation+0.032
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+3.312
Top resid features:
if
Token if
Feature activation+0.356
Top resid features:
not
Token not
Feature activation+0.011
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.000
Top resid features:
exactly
Token exactly
Feature activation+0.000
Top resid features:
based
Tokenbased
Feature activation-0.005
Top resid features:
violence
Token violence
Feature activation-0.007
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
results
Token results
Feature activation+0.078
Top resid features:
in
Token in
Feature activation+0.066
Top resid features:
,
Token,
Feature activation+2.815
Top resid features:
or
Token or
Feature activation+0.775
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.000
Top resid features:
should
Token should
Feature activation-0.019
Top resid features:
you
Token you
Feature activation-0.003
Top resid features:
avoid
Token avoid
Feature activation+0.102
Top resid features:
,
Token,
Feature activation+0.714
Top resid features:
dismiss
Token dismiss
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+2.393
Top resid features:
or
Token or
Feature activation+0.362
Top resid features:
at
Token at
Feature activation+0.115
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
very
Token very
Feature activation+0.005
Top resid features:
least
Token least
Feature activation-0.108
Top resid features:

Decoder Weights Distribution

Head 0: 0.11

Head 1: 0.02

Head 2: 0.01

Head 3: 0.04

Head 4: 0.08

Head 5: 0.03

Head 6: 0.03

Head 7: 0.49

Head 8: 0.06

Head 9: 0.07

Head 10: 0.02

Head 11: 0.03

Positive logits

Joined3.22

against2.89

Catalog2.81

Against2.81

externalActionCode2.72

SOURCE2.52

Favorite2.40

ARGET2.37

Reply2.34

behind2.23

Opp2.23

TO2.18

VALUE2.17

Source2.13

lead2.10

Destroy2.09

oided2.08

Represent2.06

against2.05

Following2.04

Negative logits

Kung-2.67

Tuc-2.33

Yao-2.20

Koreans-2.17

Yok-2.16

Kul-2.16

Beans-2.12

Typhoon-2.11

Gaw-2.09

Beef-2.06

Gong-2.06

Shib-2.06

Mankind-2.06

Bah-2.04

Salam-2.02

Esp-2.00

Cheese-1.99

Zeit-1.99

Malays-1.99

Wan-1.99

INTERVAL 4.596 - 5.107
CONTAINS 0.001%

of
Token of
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.077
engagement
Token engagement
Feature activation+4.874
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
letter
Token letter
Feature activation+0.000
also
Token also
Feature activation+0.000
responded
Token responded
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+5.057
seemed
Token seemed
Feature activation+3.439
to
Token to
Feature activation+1.708
debunk
Token debunk
Feature activation+0.289
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
results
Token results
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+3.221
is
Token is
Feature activation+4.735
likely
Token likely
Feature activation+4.063
to
Token to
Feature activation+2.539
result
Token result
Feature activation+2.998
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
interfering
Token interfering
Feature activation+0.000
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.173
in
Token in
Feature activation+3.976
any
Token any
Feature activation+1.424
way
Token way
Feature activation+5.107
disturbing
Token disturbing
Feature activation+0.014
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
or
Token or
Feature activation+0.000
access
Token access
Feature activation+0.212
communities
Token communities
Feature activation+0.000
must
Token must
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+4.795
after
Token after
Feature activation+0.000
,
Token,
Feature activation+0.000
approving
Token approving
Feature activation+0.000
the
Token the
Feature activation+0.000
2005
Token 2005
Feature activation+0.000

INTERVAL 4.085 - 4.596
CONTAINS 0.000%

template
Token template
Feature activation+0.000
?
Token?
Feature activation+0.000
XML
Token XML
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
XML
Token XML
Feature activation+4.243
out
Token out
Feature activation+0.549
-
Token -
Feature activation+0.000
you
Token you
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+0.000
score
Token score
Feature activation+0.000
is
Token is
Feature activation+0.000
equal
Token equal
Feature activation+0.000
to
Token to
Feature activation+0.000
or
Token or
Feature activation+0.764
greater
Token greater
Feature activation+4.220
than
Token than
Feature activation+0.000
80
Token 80
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
action
Token action
Feature activation+0.000
Iraqis
Token Iraqis
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.149
or
Token or
Feature activation+3.923
in
Token in
Feature activation+4.174
collaboration
Token collaboration
Feature activation+3.950
with
Token with
Feature activation+0.035
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Coalition
Token Coalition
Feature activation+0.000

INTERVAL 3.575 - 4.085
CONTAINS 0.001%

the
Token the
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Is
Token Is
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
is
Token is
Feature activation+2.373
located
Token located
Feature activation+3.687
at
Token at
Feature activation+1.202
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
routinely
Token routinely
Feature activation+0.000
ask
Token ask
Feature activation+0.000
for
Token for
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+1.417
receive
Token receive
Feature activation+3.672
âĢĶ
Token âĢĶ
Feature activation+0.000
user
Token user
Feature activation+0.000
data
Token data
Feature activation+0.000
from
Token from
Feature activation+0.000
telecom
Token telecom
Feature activation+0.000
restrained
Token restrained
Feature activation+0.000
from
Token from
Feature activation+0.000
interfering
Token interfering
Feature activation+0.000
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.173
in
Token in
Feature activation+3.976
any
Token any
Feature activation+1.424
way
Token way
Feature activation+5.107
disturbing
Token disturbing
Feature activation+0.014
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
construed
Token construed
Feature activation+0.000
to
Token to
Feature activation+0.000
invalid
Token invalid
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
,
Token,
Feature activation+0.000
impair
Token impair
Feature activation+3.913
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
supers
Token supers
Feature activation+0.000
ede
Tokenede
Feature activation+0.000
any
Token any
Feature activation+0.000
or
Token or
Feature activation+0.000
Iraqis
Token Iraqis
Feature activation+0.000
working
Token working
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.149
or
Token or
Feature activation+3.923
in
Token in
Feature activation+4.174
collaboration
Token collaboration
Feature activation+3.950
with
Token with
Feature activation+0.035
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.064 - 3.575
CONTAINS 0.000%

also
Token also
Feature activation+0.000
responded
Token responded
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+5.057
seemed
Token seemed
Feature activation+3.439
to
Token to
Feature activation+1.708
debunk
Token debunk
Feature activation+0.289
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
claim
Token claim
Feature activation+0.000
violence
Token violence
Feature activation+0.000
that
Token that
Feature activation+0.000
results
Token results
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+3.221
is
Token is
Feature activation+4.735
likely
Token likely
Feature activation+4.063
to
Token to
Feature activation+2.539
result
Token result
Feature activation+2.998
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.124
not
Token not
Feature activation+3.222
doing
Token doing
Feature activation+0.000
something
Token something
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
,
Token,
Feature activation+0.129
at
Token at
Feature activation+0.000

INTERVAL 2.553 - 3.064
CONTAINS 0.001%

working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.000
it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+2.915
six
Token six
Feature activation+0.000
years
Token years
Feature activation+0.111
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+3.221
is
Token is
Feature activation+4.735
likely
Token likely
Feature activation+4.063
to
Token to
Feature activation+2.539
result
Token result
Feature activation+2.998
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
physical
Token physical
Feature activation+0.000
,
Token,
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
,
Token,
Feature activation+0.012
or
Token or
Feature activation+0.039
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.071
very
Token very
Feature activation+0.188
least
Token least
Feature activation+3.056
raise
Token raise
Feature activation+0.028
a
Token a
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
eyebrow
Token eyebrow
Feature activation+0.000
at
Token at
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
disliked
Token disliked
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+2.671
despised
Token despised
Feature activation+0.000
modern
Token modern
Feature activation+0.000
art
Token art
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
President
Token President
Feature activation+0.000
and
Token and
Feature activation+0.000
local
Token local
Feature activation+0.000
police
Token police
Feature activation+0.000
tolerated
Token tolerated
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+2.784
encouraged
Token encouraged
Feature activation+1.080
,
Token,
Feature activation+0.000
mob
Token mob
Feature activation+0.000
violence
Token violence
Feature activation+0.000
against
Token against
Feature activation+0.000

INTERVAL 2.043 - 2.553
CONTAINS 0.001%

range
Token range
Feature activation+0.000
of
Token of
Feature activation+0.000
functions
Token functions
Feature activation+0.000
both
Token both
Feature activation+0.000
within
Token within
Feature activation+0.000
and
Token and
Feature activation+2.292
outside
Token outside
Feature activation+0.000
the
Token the
Feature activation+0.000
immune
Token immune
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
Rogers
Token Rogers
Feature activation+0.000
had
Token had
Feature activation+0.000
formed
Token formed
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.923
then
Token then
Feature activation+2.546
breached
Token breached
Feature activation+0.635
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
contract
Token contract
Feature activation+0.000
with
Token with
Feature activation+0.000
improvements
Token improvements
Feature activation+0.000
in
Token in
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
technology
Token technology
Feature activation+0.000
during
Token during
Feature activation+0.000
and
Token and
Feature activation+2.075
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+0.000
convinced
Token convinced
Feature activation+0.000
many
Token many
Feature activation+0.000
wise
Token wise
Feature activation+0.000
to
Token to
Feature activation+0.000
acknowledge
Token acknowledge
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.005
even
Token even
Feature activation+2.305
consider
Token consider
Feature activation+0.742
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
importance
Token importance
Feature activation+0.000
of
Token of
Feature activation+0.000
became
Token became
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+0.000
as
Token as
Feature activation+0.000
or
Token or
Feature activation+0.080
better
Token better
Feature activation+2.050
than
Token than
Feature activation+0.000
humans
Token humans
Feature activation+0.000
at
Token at
Feature activation+0.000
many
Token many
Feature activation+0.000
types
Token types
Feature activation+0.000

INTERVAL 1.532 - 2.043
CONTAINS 0.002%

world
Token world
Feature activation+0.000
began
Token began
Feature activation+0.000
to
Token to
Feature activation+0.000
classify
Token classify
Feature activation+0.000
,
Token,
Feature activation+0.000
study
Token study
Feature activation+1.750
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
collect
Token collect
Feature activation+0.000
all
Token all
Feature activation+0.000
such
Token such
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
in
Token in
Feature activation+0.000
between
Token between
Feature activation+0.000
and
Token and
Feature activation+0.140
on
Token on
Feature activation+1.896
the
Token the
Feature activation+0.243
run
Token run
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
most
Token most
Feature activation+0.039
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.298
certainly
Token certainly
Feature activation+1.647
wouldn
Token wouldn
Feature activation+0.699
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
everything
Token everything
Feature activation+0.000
that
Token that
Feature activation+0.000
goes
Token goes
Feature activation+0.000
on
Token on
Feature activation+0.000
within
Token within
Feature activation+0.000
and
Token and
Feature activation+1.989
without
Token without
Feature activation+0.032
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
essentially
Token essentially
Feature activation+0.000
follow
Token follow
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.700
drive
Token drive
Feature activation+1.858
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.140
the
Token the
Feature activation+0.000
direction
Token direction
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.021 - 1.532
CONTAINS 0.003%

Trump
Token Trump
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
was
Token was
Feature activation+0.000
willing
Token willing
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+1.222
even
Token even
Feature activation+1.767
eager
Token eager
Feature activation+0.036
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
depress
Token depress
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
often
Token often
Feature activation+0.000
,
Token,
Feature activation+1.357
abuse
Token abuse
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
result
Token result
Feature activation+0.000
to
Token to
Feature activation+0.000
intimidate
Token intimidate
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.964
actually
Token actually
Feature activation+0.282
to
Token to
Feature activation+1.052
compliment
Token compliment
Feature activation+0.000
.*
Token.*
Feature activation+0.000
This
Token This
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+1.300
,
Token,
Feature activation+0.000
other
Token other
Feature activation+0.000
credible
Token credible
Feature activation+0.000
,
Token,
Feature activation+0.000
serious
Token serious
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
manage
Token manage
Feature activation+0.000
,
Token,
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+1.407
be
Token be
Feature activation+0.895
victimized
Token victimized
Feature activation+0.000
by
Token by
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 0.511 - 1.021
CONTAINS 0.009%

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+0.000
or
Token or
Feature activation+0.763
dodge
Token dodge
Feature activation+0.009
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
igs
Tokenigs
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
gown
Token gown
Feature activation+0.074
s
Tokens
Feature activation+0.827
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.000
very
Token very
Feature activation+0.000
worked
Token worked
Feature activation+0.600
for
Token for
Feature activation+0.244
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.856
)
Token)
Feature activation+0.000
fought
Token fought
Feature activation+0.573
for
Token for
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Republicans
TokenRepublicans
Feature activation+0.000
getting
Token getting
Feature activation+0.000
his
Token his
Feature activation+0.000
cue
Token cue
Feature activation+0.000
from
Token from
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.766
voice
Token voice
Feature activation+1.528
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
chorus
Token chorus
Feature activation+0.000
of
Token of
Feature activation+0.000
believers
Token believers
Feature activation+0.000
bl
Token bl
Feature activation+0.000
ithe
Tokenithe
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
ignore
Token ignore
Feature activation+0.000
or
Token or
Feature activation+0.556
gloss
Token gloss
Feature activation+0.019
over
Token over
Feature activation+0.000
these
Token these
Feature activation+0.000
differences
Token differences
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.511
CONTAINS 99.982%

(
Token (
Feature activation+0.000
B
TokenB
Feature activation+0.000
).
Token).
Feature activation+0.000
AI
Token AI
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
filler
Token filler
Feature activation+0.000
concept
Token concept
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
based
Token based
Feature activation+0.000
Mueller
Token Mueller
Feature activation+0.000
is
Token is
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
witch
Token witch
Feature activation+0.000
hunt
Token hunt
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
leads
Token leads
Feature activation+0.000
the
Token the
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.000
points
Token points
Feature activation+0.000
touched
Token touched
Feature activation+0.000
upon
Token upon
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
election
Token election
Feature activation+0.000
and
Token and
Feature activation+0.000
She
Token She
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
enthusiastic
Token enthusiastic
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
Rid
Token Rid
Feature activation+0.000
gew
Tokengew
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
iding
Tokeniding
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 H7.7: (feature 13538)

TOP ACTIVATIONS
MAX = 3.426

where
Token where
Feature activation+0.000
intact
Token intact
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.343
you
Token you
Feature activation+1.366
had
Token had
Feature activation+3.426
communities
Token communities
Feature activation+0.846
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
standing
Token standing
Feature activation+0.000
up
Token up
Feature activation+0.000
standing
Token standing
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.001
when
Token when
Feature activation+0.285
you
Token you
Feature activation+1.005
had
Token had
Feature activation+3.032
better
Token better
Feature activation+1.128
education
Token education
Feature activation+0.241
opportunities
Token opportunities
Feature activation+0.019
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.605
When
Token When
Feature activation+1.252
something
Token something
Feature activation+1.113
is
Token is
Feature activation+1.719
said
Token said
Feature activation+2.301
on
Token on
Feature activation+2.990
channel
Token channel
Feature activation+2.300
1
Token 1
Feature activation+2.429
that
Token that
Feature activation+1.346
needs
Token needs
Feature activation+0.441
to
Token to
Feature activation+0.370
in
Token in
Feature activation+0.000
500
Token 500
Feature activation+0.000
.
Token.
Feature activation+0.088
(
Token (
Feature activation+0.105
With
TokenWith
Feature activation+2.371
the
Token the
Feature activation+2.938
Pill
Token Pill
Feature activation+0.701
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.440
,
Token,
Feature activation+2.705
with
Token with
Feature activation+2.208
larger
Token larger
Feature activation+1.093
proposals
Token proposals
Feature activation+0.258
that
Token that
Feature activation+0.303
would
Token would
Feature activation+0.000
and
Token and
Feature activation+0.000
another
Token another
Feature activation+0.000
third
Token third
Feature activation+0.000
are
Token are
Feature activation+1.067
working
Token working
Feature activation+2.172
in
Token in
Feature activation+2.673
jobs
Token jobs
Feature activation+2.019
that
Token that
Feature activation+1.955
require
Token require
Feature activation+0.302
degrees
Token degrees
Feature activation+0.719
purely
Token purely
Feature activation+0.000
that
Token that
Feature activation+0.000
issue
Token issue
Feature activation+0.000
debt
Token debt
Feature activation+0.000
and
Token and
Feature activation+0.000
equity
Token equity
Feature activation+0.000
to
Token to
Feature activation+2.640
the
Token the
Feature activation+1.898
largest
Token largest
Feature activation+0.026
credit
Token credit
Feature activation+0.000
rating
Token rating
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
strong
Token strong
Feature activation+0.382
evidence
Token evidence
Feature activation+0.705
to
Token to
Feature activation+0.536
back
Token back
Feature activation+2.592
a
Token a
Feature activation+1.891
licensed
Token licensed
Feature activation+0.539
cannabis
Token cannabis
Feature activation+0.633
-
Token-
Feature activation+0.000
ext
Tokenext
Feature activation+0.000
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
6
Token 6
Feature activation+0.000
;
Token;
Feature activation+0.000
with
Token with
Feature activation+0.195
the
Token the
Feature activation+2.526
rhythm
Token rhythm
Feature activation+0.106
method
Token method
Feature activation+0.000
its
Token its
Feature activation+0.000
closer
Token closer
Feature activation+0.000
to
Token to
Feature activation+0.000
touch
Token touch
Feature activation+0.000
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
;
Token;
Feature activation+0.168
and
Token and
Feature activation+1.207
about
Token about
Feature activation+2.480
a
Token a
Feature activation+2.346
young
Token young
Feature activation+0.788
girl
Token girl
Feature activation+1.348
who
Token who
Feature activation+0.154
wrote
Token wrote
Feature activation+0.000
something
Token something
Feature activation+1.113
is
Token is
Feature activation+1.719
said
Token said
Feature activation+2.301
on
Token on
Feature activation+2.990
channel
Token channel
Feature activation+2.300
1
Token 1
Feature activation+2.429
that
Token that
Feature activation+1.346
needs
Token needs
Feature activation+0.441
to
Token to
Feature activation+0.370
be
Token be
Feature activation+0.000
passed
Token passed
Feature activation+0.000
"
Token "
Feature activation+0.000
love
Tokenlove
Feature activation+0.000
our
Token our
Feature activation+0.000
people
Token people
Feature activation+0.000
"
Token"
Feature activation+0.000
from
Token from
Feature activation+2.419
those
Token those
Feature activation+1.005
who
Token who
Feature activation+0.386
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
500
Token 500
Feature activation+0.000
.
Token.
Feature activation+0.088
(
Token (
Feature activation+0.105
With
TokenWith
Feature activation+2.371
the
Token the
Feature activation+2.938
Pill
Token Pill
Feature activation+0.701
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
;
Token;
Feature activation+0.168
and
Token and
Feature activation+1.207
about
Token about
Feature activation+2.480
a
Token a
Feature activation+2.346
young
Token young
Feature activation+0.788
girl
Token girl
Feature activation+1.348
who
Token who
Feature activation+0.154
wrote
Token wrote
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.605
When
Token When
Feature activation+1.252
something
Token something
Feature activation+1.113
is
Token is
Feature activation+1.719
said
Token said
Feature activation+2.301
on
Token on
Feature activation+2.990
channel
Token channel
Feature activation+2.300
1
Token 1
Feature activation+2.429
that
Token that
Feature activation+1.346
needs
Token needs
Feature activation+0.441
When
Token When
Feature activation+1.252
something
Token something
Feature activation+1.113
is
Token is
Feature activation+1.719
said
Token said
Feature activation+2.301
on
Token on
Feature activation+2.990
channel
Token channel
Feature activation+2.300
1
Token 1
Feature activation+2.429
that
Token that
Feature activation+1.346
needs
Token needs
Feature activation+0.441
to
Token to
Feature activation+0.370
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
.)
Token.)
Feature activation+0.183
Clinton
Token Clinton
Feature activation+0.000
,
Token,
Feature activation+1.065
the
Token the
Feature activation+2.229
Democrat
Token Democrat
Feature activation+0.696
who
Token who
Feature activation+0.626
claims
Token claims
Feature activation+0.000
a
Token a
Feature activation+0.175
âĢ
Token âĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.440
,
Token,
Feature activation+2.705
with
Token with
Feature activation+2.208
larger
Token larger
Feature activation+1.093
proposals
Token proposals
Feature activation+0.258
that
Token that
Feature activation+0.303
would
Token would
Feature activation+0.000
likely
Token likely
Feature activation+0.000
s
Tokens
Feature activation+0.000
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
11
Token 11
Feature activation+0.000
;
Token;
Feature activation+0.154
with
Token with
Feature activation+2.195
condoms
Token condoms
Feature activation+0.126
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
6
Token 6
Feature activation+0.000
;
Token;
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+1.363
the
Token the
Feature activation+2.179
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.756
No
TokenNo
Feature activation+0.291
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

Top DFA by src position
MAX = 3.657

<|endoftext|>
Token<|endoftext|>
Feature activation-0.002
Top resid features:
when
Token when
Feature activation-0.001
Top resid features:
you
Token you
Feature activation-0.004
Top resid features:
had
Token had
Feature activation+0.002
Top resid features:
families
Token families
Feature activation+0.070
Top resid features:
that
Token that
Feature activation+3.657
Top resid features:
where
Token where
Feature activation+0.104
Top resid features:
intact
Token intact
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
when
Token when
Feature activation+0.004
Top resid features:
you
Token you
Feature activation+0.039
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
Top resid features:
when
Token when
Feature activation-0.002
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
had
Token had
Feature activation+0.001
Top resid features:
families
Token families
Feature activation+0.018
Top resid features:
that
Token that
Feature activation+1.527
Top resid features:
where
Token where
Feature activation+0.029
Top resid features:
intact
Token intact
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
when
Token when
Feature activation+0.007
Top resid features:
you
Token you
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
channel
Token channel
Feature activation-0.114
Top resid features:
1
Token 1
Feature activation+0.212
Top resid features:
that
Token that
Feature activation+3.302
Top resid features:
needs
Token needs
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
passed
Token passed
Feature activation+0.000
Top resid features:
along
Token along
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
With
TokenWith
Feature activation-0.013
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Pill
Token Pill
Feature activation+0.083
Top resid features:
that
Token that
Feature activation+3.307
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
1
Token 1
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.350
Top resid features:
âĢ
Token âĢ
Feature activation-0.008
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
real
Tokenreal
Feature activation+0.016
Top resid features:
plans
Token plans
Feature activation+0.038
Top resid features:
that
Token that
Feature activation+2.277
Top resid features:
work
Token work
Feature activation+0.082
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+0.020
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.010
Top resid features:
working
Token working
Feature activation+0.002
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
jobs
Token jobs
Feature activation+0.235
Top resid features:
that
Token that
Feature activation+2.243
Top resid features:
don
Token don
Feature activation+0.498
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation+0.031
Top resid features:
require
Token require
Feature activation+0.117
Top resid features:
investment
Token investment
Feature activation-0.030
Top resid features:
chain
Token chain
Feature activation-0.038
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
from
Token from
Feature activation-0.031
Top resid features:
companies
Token companies
Feature activation+0.211
Top resid features:
that
Token that
Feature activation+2.899
Top resid features:
issue
Token issue
Feature activation+0.108
Top resid features:
debt
Token debt
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
equity
Token equity
Feature activation-0.014
Top resid features:
to
Token to
Feature activation-0.021
Top resid features:
cannabis
Token cannabis
Feature activation-0.004
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
ext
Tokenext
Feature activation-0.000
Top resid features:
ract
Tokenract
Feature activation+0.001
Top resid features:
medicine
Token medicine
Feature activation+0.026
Top resid features:
which
Token which
Feature activation+2.612
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
Department
Token Department
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Health
Token Health
Feature activation+0.000
Top resid features:
plans
Token plans
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
(
Token (
Feature activation-0.002
Top resid features:
With
TokenWith
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
Pill
Token Pill
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+2.860
Top resid features:
âĢ
TokenâĢ
Feature activation+0.053
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
1
Token 1
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
about
Token about
Feature activation+0.018
Top resid features:
a
Token a
Feature activation-0.016
Top resid features:
supporter
Token supporter
Feature activation+0.100
Top resid features:
in
Token in
Feature activation+0.122
Top resid features:
Iowa
Token Iowa
Feature activation-0.004
Top resid features:
who
Token who
Feature activation+2.408
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
despite
Token despite
Feature activation+0.016
Top resid features:
being
Token being
Feature activation+0.004
Top resid features:
weakened
Token weakened
Feature activation+0.012
Top resid features:
by
Token by
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
channel
Token channel
Feature activation+0.003
Top resid features:
1
Token 1
Feature activation+0.003
Top resid features:
that
Token that
Feature activation+2.099
Top resid features:
needs
Token needs
Feature activation+0.268
Top resid features:
to
Token to
Feature activation+0.290
Top resid features:
be
Token be
Feature activation+0.092
Top resid features:
passed
Token passed
Feature activation+0.002
Top resid features:
along
Token along
Feature activation+0.020
Top resid features:
how
Token how
Feature activation-0.010
Top resid features:
he
Token he
Feature activation-0.010
Top resid features:
would
Token would
Feature activation-0.013
Top resid features:
distinguish
Token distinguish
Feature activation-0.033
Top resid features:
immigrants
Token immigrants
Feature activation-0.041
Top resid features:
who
Token who
Feature activation+2.703
Top resid features:
"
Token "
Feature activation+0.029
Top resid features:
share
Tokenshare
Feature activation+0.036
Top resid features:
our
Token our
Feature activation+0.004
Top resid features:
values
Token values
Feature activation+0.014
Top resid features:
"
Token"
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
With
TokenWith
Feature activation-0.013
Top resid features:
the
Token the
Feature activation-0.137
Top resid features:
Pill
Token Pill
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+2.856
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
1
Token 1
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.011
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
supporter
Token supporter
Feature activation+0.084
Top resid features:
in
Token in
Feature activation+0.153
Top resid features:
Iowa
Token Iowa
Feature activation-0.003
Top resid features:
who
Token who
Feature activation+2.273
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
despite
Token despite
Feature activation+0.023
Top resid features:
being
Token being
Feature activation+0.008
Top resid features:
weakened
Token weakened
Feature activation+0.014
Top resid features:
by
Token by
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.003
Top resid features:
on
Token on
Feature activation-0.452
Top resid features:
channel
Token channel
Feature activation+0.021
Top resid features:
1
Token 1
Feature activation+0.050
Top resid features:
that
Token that
Feature activation+3.084
Top resid features:
needs
Token needs
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
be
Token be
Feature activation+0.023
Top resid features:
passed
Token passed
Feature activation+0.001
Top resid features:
along
Token along
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
channel
Token channel
Feature activation+0.004
Top resid features:
1
Token 1
Feature activation-0.081
Top resid features:
that
Token that
Feature activation+2.724
Top resid features:
needs
Token needs
Feature activation+0.037
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
be
Token be
Feature activation+0.005
Top resid features:
passed
Token passed
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.507
Top resid features:
âĢ
Token âĢ
Feature activation-0.004
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
real
Tokenreal
Feature activation+0.017
Top resid features:
plans
Token plans
Feature activation+0.012
Top resid features:
that
Token that
Feature activation+1.650
Top resid features:
work
Token work
Feature activation+0.040
Top resid features:
.
Token.
Feature activation+0.095
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ŀ
TokenĿ
Feature activation-0.000
Top resid features:
(
Token (
Feature activation+0.014
Top resid features:
with
Token with
Feature activation+0.016
Top resid features:
âĢ
Token âĢ
Feature activation-0.089
Top resid features:
ľ
Tokenľ
Feature activation+0.011
Top resid features:
real
Tokenreal
Feature activation+0.012
Top resid features:
plans
Token plans
Feature activation+0.158
Top resid features:
that
Token that
Feature activation+2.347
Top resid features:
work
Token work
Feature activation+0.161
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
(
Token (
Feature activation-0.007
Top resid features:
With
TokenWith
Feature activation-0.018
Top resid features:
the
Token the
Feature activation-0.183
Top resid features:
Pill
Token Pill
Feature activation-0.036
Top resid features:
that
Token that
Feature activation+2.791
Top resid features:
âĢ
TokenâĢ
Feature activation+0.066
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
âĢ
Token âĢ
Feature activation-0.052
Top resid features:
ĺ
Tokenĺ
Feature activation+0.003
Top resid features:
No
TokenNo
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.007
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+2.660
Top resid features:
God
Token God
Feature activation+0.047
Top resid features:
scrolls
Token scrolls
Feature activation+0.025
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
wall
Token wall
Feature activation-0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.08

Head 2: 0.03

Head 3: 0.04

Head 4: 0.03

Head 5: 0.04

Head 6: 0.07

Head 7: 0.49

Head 8: 0.03

Head 9: 0.04

Head 10: 0.04

Head 11: 0.05

Positive logits

204392.49

artifacts2.47

"{2.33

pmwiki2.25

whose2.24

whose2.21

{*2.08

theless2.08

ones2.06

wherein2.04

those2.00

ighters1.98

00000001.96

Reviewer1.95

modules1.93

uds1.93

products1.92

inconsistent1.91

ousy1.89

condos1.88

Negative logits

Rahul-2.18

Strauss-2.17

seiz-2.14

Chop-2.09

Quinn-2.04

otto-2.03

ophe-1.98

Gaga-1.94

Brooke-1.83

Shiva-1.81

hene-1.80

ierce-1.80

aye-1.79

Diana-1.78

Enjoy-1.77

Kali-1.75

Philipp-1.75

ovember-1.74

ince-1.74

Wagner-1.71

INTERVAL 3.083 - 3.426
CONTAINS 0.000%

where
Token where
Feature activation+0.000
intact
Token intact
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.343
you
Token you
Feature activation+1.366
had
Token had
Feature activation+3.426
communities
Token communities
Feature activation+0.846
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
standing
Token standing
Feature activation+0.000
up
Token up
Feature activation+0.000

INTERVAL 2.741 - 3.083
CONTAINS 0.000%

in
Token in
Feature activation+0.000
500
Token 500
Feature activation+0.000
.
Token.
Feature activation+0.088
(
Token (
Feature activation+0.105
With
TokenWith
Feature activation+2.371
the
Token the
Feature activation+2.938
Pill
Token Pill
Feature activation+0.701
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.605
When
Token When
Feature activation+1.252
something
Token something
Feature activation+1.113
is
Token is
Feature activation+1.719
said
Token said
Feature activation+2.301
on
Token on
Feature activation+2.990
channel
Token channel
Feature activation+2.300
1
Token 1
Feature activation+2.429
that
Token that
Feature activation+1.346
needs
Token needs
Feature activation+0.441
to
Token to
Feature activation+0.370
standing
Token standing
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.001
when
Token when
Feature activation+0.285
you
Token you
Feature activation+1.005
had
Token had
Feature activation+3.032
better
Token better
Feature activation+1.128
education
Token education
Feature activation+0.241
opportunities
Token opportunities
Feature activation+0.019
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 2.398 - 2.741
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.440
,
Token,
Feature activation+2.705
with
Token with
Feature activation+2.208
larger
Token larger
Feature activation+1.093
proposals
Token proposals
Feature activation+0.258
that
Token that
Feature activation+0.303
would
Token would
Feature activation+0.000
touch
Token touch
Feature activation+0.000
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
;
Token;
Feature activation+0.168
and
Token and
Feature activation+1.207
about
Token about
Feature activation+2.480
a
Token a
Feature activation+2.346
young
Token young
Feature activation+0.788
girl
Token girl
Feature activation+1.348
who
Token who
Feature activation+0.154
wrote
Token wrote
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
strong
Token strong
Feature activation+0.382
evidence
Token evidence
Feature activation+0.705
to
Token to
Feature activation+0.536
back
Token back
Feature activation+2.592
a
Token a
Feature activation+1.891
licensed
Token licensed
Feature activation+0.539
cannabis
Token cannabis
Feature activation+0.633
-
Token-
Feature activation+0.000
ext
Tokenext
Feature activation+0.000
something
Token something
Feature activation+1.113
is
Token is
Feature activation+1.719
said
Token said
Feature activation+2.301
on
Token on
Feature activation+2.990
channel
Token channel
Feature activation+2.300
1
Token 1
Feature activation+2.429
that
Token that
Feature activation+1.346
needs
Token needs
Feature activation+0.441
to
Token to
Feature activation+0.370
be
Token be
Feature activation+0.000
passed
Token passed
Feature activation+0.000
that
Token that
Feature activation+0.000
issue
Token issue
Feature activation+0.000
debt
Token debt
Feature activation+0.000
and
Token and
Feature activation+0.000
equity
Token equity
Feature activation+0.000
to
Token to
Feature activation+2.640
the
Token the
Feature activation+1.898
largest
Token largest
Feature activation+0.026
credit
Token credit
Feature activation+0.000
rating
Token rating
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000

INTERVAL 2.056 - 2.398
CONTAINS 0.001%

with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
;
Token;
Feature activation+0.168
and
Token and
Feature activation+1.207
about
Token about
Feature activation+2.480
a
Token a
Feature activation+2.346
young
Token young
Feature activation+0.788
girl
Token girl
Feature activation+1.348
who
Token who
Feature activation+0.154
wrote
Token wrote
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
s
Tokens
Feature activation+0.000
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
11
Token 11
Feature activation+0.000
;
Token;
Feature activation+0.154
with
Token with
Feature activation+2.195
condoms
Token condoms
Feature activation+0.126
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
6
Token 6
Feature activation+0.000
;
Token;
Feature activation+0.000
emerge
Token emerge
Feature activation+0.000
;
Token;
Feature activation+0.384
and
Token and
Feature activation+0.519
a
Token a
Feature activation+0.330
destructive
Token destructive
Feature activation+1.002
one
Token one
Feature activation+2.085
in
Token in
Feature activation+1.366
which
Token which
Feature activation+0.000
old
Token old
Feature activation+0.000
ways
Token ways
Feature activation+0.000
of
Token of
Feature activation+0.000
1
Token 1
Feature activation+0.000
in
Token in
Feature activation+0.000
500
Token 500
Feature activation+0.000
.
Token.
Feature activation+0.088
(
Token (
Feature activation+0.105
With
TokenWith
Feature activation+2.371
the
Token the
Feature activation+2.938
Pill
Token Pill
Feature activation+0.701
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+1.363
the
Token the
Feature activation+2.179
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.756
No
TokenNo
Feature activation+0.291
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.713 - 2.056
CONTAINS 0.002%

no
Token no
Feature activation+0.000
strong
Token strong
Feature activation+0.382
evidence
Token evidence
Feature activation+0.705
to
Token to
Feature activation+0.536
back
Token back
Feature activation+2.592
a
Token a
Feature activation+1.891
licensed
Token licensed
Feature activation+0.539
cannabis
Token cannabis
Feature activation+0.633
-
Token-
Feature activation+0.000
ext
Tokenext
Feature activation+0.000
ract
Tokenract
Feature activation+0.504
clipse
Tokenclipse
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
,"
Token,"
Feature activation+0.000
the
Token the
Feature activation+0.186
threat
Token threat
Feature activation+1.727
of
Token of
Feature activation+0.826
Islamic
Token Islamic
Feature activation+0.000
extremism
Token extremism
Feature activation+0.162
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
own
Token own
Feature activation+0.000
assaults
Token assaults
Feature activation+0.000
.
Token.
Feature activation+0.572
The
Token The
Feature activation+1.245
same
Token same
Feature activation+1.917
rape
Token rape
Feature activation+1.992
culture
Token culture
Feature activation+1.095
that
Token that
Feature activation+0.670
leaves
Token leaves
Feature activation+0.000
the
Token the
Feature activation+0.000
majority
Token majority
Feature activation+0.000
strange
Token strange
Feature activation+0.000
or
Token or
Feature activation+0.431
bizarre
Token bizarre
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+1.497
they
Token they
Feature activation+1.719
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.393
regarded
Token regarded
Feature activation+0.094
by
Token by
Feature activation+0.000
together
Token together
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.056
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.870
see
Token see
Feature activation+1.844
that
Token that
Feature activation+0.000
order
Token order
Feature activation+0.000
increasingly
Token increasingly
Feature activation+0.000
strained
Token strained
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 1.370 - 1.713
CONTAINS 0.002%

000
Token000
Feature activation+0.000
people
Token people
Feature activation+0.000
against
Token against
Feature activation+0.203
the
Token the
Feature activation+0.000
rights
Token rights
Feature activation+0.599
of
Token of
Feature activation+1.635
its
Token its
Feature activation+0.960
female
Token female
Feature activation+0.000
workers
Token workers
Feature activation+0.000
to
Token to
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
not
Token not
Feature activation+0.000
talking
Token talking
Feature activation+0.355
about
Token about
Feature activation+1.609
some
Token some
Feature activation+0.629
Bir
Token Bir
Feature activation+0.000
ken
Tokenken
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ocked
Tokenocked
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
want
Token want
Feature activation+0.468
a
Token a
Feature activation+1.364
president
Token president
Feature activation+1.410
who
Token who
Feature activation+0.754
promises
Token promises
Feature activation+0.000
to
Token to
Feature activation+0.000
drain
Token drain
Feature activation+0.000
the
Token the
Feature activation+0.000
database
Token database
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.469
a
Token a
Feature activation+1.812
thing
Token thing
Feature activation+0.710
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
update
Token update
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
assault
Token assault
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
need
Token need
Feature activation+1.543
a
Token a
Feature activation+1.665
law
Token law
Feature activation+1.336
against
Token against
Feature activation+0.000
F
Token F
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
/
Token/
Feature activation+0.000

INTERVAL 1.028 - 1.370
CONTAINS 0.008%

of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
assaults
Token assaults
Feature activation+0.000
.
Token.
Feature activation+0.572
The
Token The
Feature activation+1.245
same
Token same
Feature activation+1.917
rape
Token rape
Feature activation+1.992
culture
Token culture
Feature activation+1.095
that
Token that
Feature activation+0.670
leaves
Token leaves
Feature activation+0.000
football
Token football
Feature activation+0.000
through
Token through
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.295
the
Token the
Feature activation+1.137
tallest
Token tallest
Feature activation+1.155
tree
Token tree
Feature activation+0.131
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
seen
Token seen
Feature activation+0.000
since
Token since
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
want
Token want
Feature activation+0.468
a
Token a
Feature activation+1.364
president
Token president
Feature activation+1.410
who
Token who
Feature activation+0.754
promises
Token promises
Feature activation+0.000
to
Token to
Feature activation+0.000
drain
Token drain
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
also
Token also
Feature activation+0.271
about
Token about
Feature activation+1.363
Big
Token Big
Feature activation+0.000
Money
Token Money
Feature activation+0.196
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
igated
Tokenigated
Feature activation+0.000
.
Token.
Feature activation+0.927
The
Token The
Feature activation+1.510
same
Token same
Feature activation+1.362
rape
Token rape
Feature activation+2.038
culture
Token culture
Feature activation+1.080
that
Token that
Feature activation+0.616
refers
Token refers
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
victims
Token victims
Feature activation+0.000

INTERVAL 0.685 - 1.028
CONTAINS 0.015%

not
Token not
Feature activation+0.000
reflect
Token reflect
Feature activation+0.000
our
Token our
Feature activation+0.000
values
Token values
Feature activation+0.000
"
Token"
Feature activation+0.000
and
Token and
Feature activation+0.735
may
Token may
Feature activation+0.000
endanger
Token endanger
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
peace
Token peace
Feature activation+0.000
talks
Token talks
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
everybody
Token everybody
Feature activation+0.000
has
Token has
Feature activation+0.647
a
Token a
Feature activation+0.903
mother
Token mother
Feature activation+0.290
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
pet
Token pet
Feature activation+0.000
pee
Token pee
Feature activation+0.000
player
Token player
Feature activation+0.230
already
Token already
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.714
Ċ
TokenĊ
Feature activation+0.685
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
;
Token;
Feature activation+0.168
and
Token and
Feature activation+1.207
about
Token about
Feature activation+2.480
a
Token a
Feature activation+2.346
young
Token young
Feature activation+0.788
girl
Token girl
Feature activation+1.348
who
Token who
Feature activation+0.154
wrote
Token wrote
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
letters
Token letters
Feature activation+0.000
wish
Token wish
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
dead
Token dead
Feature activation+0.000
.
Token.
Feature activation+0.728
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
recent
Token recent
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000

INTERVAL 0.343 - 0.685
CONTAINS 0.035%

certainly
Token certainly
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.424
play
Token play
Feature activation+0.000
along
Token along
Feature activation+0.000
recordings
Token recordings
Feature activation+0.000
or
Token or
Feature activation+0.000
any
Token any
Feature activation+0.000
,
Token,
Feature activation+0.021
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.197
as
Token as
Feature activation+0.845
controversial
Token controversial
Feature activation+0.319
releases
Token releases
Feature activation+0.362
like
Token like
Feature activation+0.000
Aliens
Token Aliens
Feature activation+0.000
:
Token:
Feature activation+0.000
Colonial
Token Colonial
Feature activation+0.000
Marines
Token Marines
Feature activation+0.000
Origin
Token Origin
Feature activation+0.000
Server
Token Server
Feature activation+0.000
?
Token?
Feature activation+0.000
Can
Token Can
Feature activation+0.000
a
Token a
Feature activation+0.093
response
Token response
Feature activation+0.385
be
Token be
Feature activation+0.275
served
Token served
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
cache
Token cache
Feature activation+0.000
,
Token,
Feature activation+0.221
and
Token and
Feature activation+0.049
they
Token they
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
want
Token want
Feature activation+0.494
a
Token a
Feature activation+1.315
president
Token president
Feature activation+1.338
who
Token who
Feature activation+0.536
has
Token has
Feature activation+0.375
too
Token too
Feature activation+0.000
Bowman
Token Bowman
Feature activation+0.000
.
Token.
Feature activation+0.285
The
Token The
Feature activation+0.408
elusive
Token elusive
Feature activation+0.342
and
Token and
Feature activation+0.000
explosive
Token explosive
Feature activation+0.614
D
Token D
Feature activation+0.000
ere
Tokenere
Feature activation+0.000
l
Tokenl
Feature activation+0.000
Walker
Token Walker
Feature activation+0.244
who
Token who
Feature activation+0.124

INTERVAL 0.000 - 0.343
CONTAINS 99.935%

no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
rule
Token rule
Feature activation+0.000
.
Token.
Feature activation+0.000
Maxwell
Token Maxwell
Feature activation+0.000
points
Token points
Feature activation+0.000
out
Token out
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
innate
Token innate
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Bulls
Token Bulls
Feature activation+0.000
coach
Token coach
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
Thib
Token Thib
Feature activation+0.000
ode
Tokenode
Feature activation+0.000
au
Tokenau
Feature activation+0.000
said
Token said
Feature activation+0.000
of
Token of
Feature activation+0.000
Noah
Token Noah
Feature activation+0.000
it
Token it
Feature activation+0.000
fails
Token fails
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
apply
Token apply
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
static
Token static
Feature activation+0.000
was
Token was
Feature activation+0.000
born
Token born
Feature activation+0.000
a
Token a
Feature activation+0.000
share
Token share
Feature activation+0.000
cro
Tokencro
Feature activation+0.000
pper
Tokenpper
Feature activation+0.000
in
Token in
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Mississippi
Token Mississippi
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
anto
Tokenanto
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
wished
Token wished
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
his
Token his
Feature activation+0.000
face
Token face
Feature activation+0.000
or
Token or
Feature activation+0.000
use
Token use
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 H7.7: (feature 8140)

TOP ACTIVATIONS
MAX = 3.364

uring
Tokenuring
Feature activation+0.000
Kyl
Token Kyl
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
ogue
Tokenogue
Feature activation+0.000
),
Token),
Feature activation+3.015
"
Token "
Feature activation+0.143
Mer
TokenMer
Feature activation+0.000
cy
Tokency
Feature activation+0.000
Seat
Token Seat
Feature activation+0.000
"
Token"
Feature activation+0.000
lot
Token lot
Feature activation+0.000
(
Token (
Feature activation+0.000
55
Token55
Feature activation+0.000
%)
Token%)
Feature activation+0.000
or
Token or
Feature activation+2.747
a
Token a
Feature activation+2.876
little
Token little
Feature activation+1.731
(
Token (
Feature activation+0.018
30
Token30
Feature activation+0.000
%)
Token%)
Feature activation+0.000
about
Token about
Feature activation+0.000
Railway
Token Railway
Feature activation+0.000
Children
Token Children
Feature activation+0.000
(
Token (
Feature activation+0.000
1970
Token1970
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+2.786
The
Token The
Feature activation+0.567
Go
Token Go
Feature activation+0.000
-
Token-
Feature activation+0.000
Between
TokenBetween
Feature activation+0.517
(
Token (
Feature activation+0.248
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
(
Token (
Feature activation+0.000
55
Token55
Feature activation+0.000
%)
Token%)
Feature activation+0.000
or
Token or
Feature activation+2.747
a
Token a
Feature activation+2.876
little
Token little
Feature activation+1.731
(
Token (
Feature activation+0.018
30
Token30
Feature activation+0.000
%)
Token%)
Feature activation+0.000
comment
Token comment
Feature activation+0.000
stored
Token stored
Feature activation+0.000
(
Token (
Feature activation+0.000
true
Tokentrue
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+2.523
not
Token not
Feature activation+0.705
(
Token (
Feature activation+0.694
false
Tokenfalse
Feature activation+0.000
).
Token).
Feature activation+0.000
We
Token We
Feature activation+0.000
==
Token ==
Feature activation+0.076
pure
Token pure
Feature activation+0.015
a
Token a
Feature activation+0.000
c
Token c
Feature activation+0.477
fold
Tokenfold
Feature activation+1.585
l
Tokenl
Feature activation+2.362
'
Token'
Feature activation+0.961
(
Token (
Feature activation+0.000
f
Tokenf
Feature activation+0.000
map
Tokenmap
Feature activation+0.000
h
Token h
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.029
7
Token 7
Feature activation+0.761
th
Tokenth
Feature activation+2.362
month
Token month
Feature activation+0.076
(
Token (
Feature activation+0.415
11
Token11
Feature activation+0.463
45
Token45
Feature activation+0.945
):
Token):
Feature activation+0.000
,
Token,
Feature activation+0.000
Gu
Token Gu
Feature activation+0.000
zar
Tokenzar
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
),
Token),
Feature activation+0.822
or
Token or
Feature activation+2.351
un
Token un
Feature activation+0.000
requ
Tokenrequ
Feature activation+0.000
ited
Tokenited
Feature activation+1.088
love
Token love
Feature activation+0.412
(
Token (
Feature activation+0.000
DM
Token DM
Feature activation+0.000
X
TokenX
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
brands
Token brands
Feature activation+0.000
),
Token),
Feature activation+2.299
Image
Token Image
Feature activation+0.286
Sound
Token Sound
Feature activation+0.000
and
Token and
Feature activation+0.000
Play
Token Play
Feature activation+0.000
Networks
Token Networks
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Government
Token Government
Feature activation+0.000
(
Token (
Feature activation+0.000
50
Token50
Feature activation+0.000
%),
Token%),
Feature activation+0.943
the
Token the
Feature activation+2.182
state
Token state
Feature activation+1.028
Government
Token Government
Feature activation+0.840
(
Token (
Feature activation+0.497
25
Token25
Feature activation+0.000
%)
Token%)
Feature activation+0.000
for
Token for
Feature activation+0.000
Prosper
Token Prosper
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
(
Token (
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
),
Token),
Feature activation+2.150
the
Token the
Feature activation+0.809
Freedom
Token Freedom
Feature activation+0.000
Partners
Token Partners
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
inj
Token inj
Feature activation+0.000
era
Tokenera
Feature activation+0.000
(
Token (
Feature activation+0.000
bread
Tokenbread
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+2.068
na
Token na
Feature activation+0.000
an
Tokenan
Feature activation+0.000
cris
Token cris
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
(
Token (
Feature activation+0.000
18
Token18
Feature activation+0.000
%),
Token%),
Feature activation+1.016
Asian
Token Asian
Feature activation+1.978
and
Token and
Feature activation+0.464
Native
Token Native
Feature activation+0.862
Hawaiian
Token Hawaiian
Feature activation+0.513
/
Token/
Feature activation+0.000
Pacific
TokenPacific
Feature activation+0.000
news
Tokennews
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
(
Token (
Feature activation+0.000
2
Token2
Feature activation+0.000
),
Token),
Feature activation+1.974
cog
Token cog
Feature activation+0.324
ent
Tokenent
Feature activation+0.250
comment
Tokencomment
Feature activation+0.498
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.475
gun
Token gun
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+1.966
Chief
Token Chief
Feature activation+0.000
N
Token N
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Tokena
Feature activation+0.000
stream
Token stream
Feature activation+0.000
(
Token (
Feature activation+0.000
VB
TokenVB
Feature activation+0.000
1
Token1
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.927
mid
Token mid
Feature activation+0.739
stream
Tokenstream
Feature activation+0.557
(
Token (
Feature activation+0.276
VB
TokenVB
Feature activation+0.000
2
Token2
Feature activation+0.000
gen
Tokengen
Feature activation+0.000
heim
Tokenheim
Feature activation+0.000
(
Token (
Feature activation+0.000
2000
Token2000
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.922
the
Token the
Feature activation+1.126
Smithsonian
Token Smithsonian
Feature activation+0.000
(
Token (
Feature activation+0.000
2013
Token2013
Feature activation+0.000
),
Token),
Feature activation+0.000
been
Token been
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
featured
Token featured
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.020
newer
Token newer
Feature activation+1.794
names
Token names
Feature activation+0.110
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
something
Token something
Feature activation+0.000
unique
Token unique
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
list
Token list
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.787
non
Token non
Feature activation+0.874
-
Token-
Feature activation+0.000
commercial
Tokencommercial
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
trees
Token trees
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+1.785
snow
Token snow
Feature activation+0.522
monsters
Token monsters
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 3.441

the
Token the
Feature activation-0.004
Top resid features:
Wild
Token Wild
Feature activation-0.001
Top resid features:
Roses
Token Roses
Feature activation-0.004
Top resid features:
Grow
Token Grow
Feature activation+0.001
Top resid features:
"
Token"
Feature activation+0.114
Top resid features:
(
Token (
Feature activation+3.360
Top resid features:
feat
Tokenfeat
Feature activation+0.028
Top resid features:
uring
Tokenuring
Feature activation+0.014
Top resid features:
Kyl
Token Kyl
Feature activation+0.031
Top resid features:
ie
Tokenie
Feature activation+0.018
Top resid features:
Mon
Token Mon
Feature activation+0.008
Top resid features:
they
Token they
Feature activation+0.011
Top resid features:
have
Token have
Feature activation+0.010
Top resid features:
heard
Token heard
Feature activation-0.023
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
lot
Token lot
Feature activation-0.115
Top resid features:
(
Token (
Feature activation+3.309
Top resid features:
55
Token55
Feature activation+0.008
Top resid features:
%)
Token%)
Feature activation+0.244
Top resid features:
or
Token or
Feature activation+0.380
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
little
Token little
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
including
Token including
Feature activation+0.019
Top resid features:
The
Token The
Feature activation-0.146
Top resid features:
Railway
Token Railway
Feature activation-0.039
Top resid features:
Children
Token Children
Feature activation+0.027
Top resid features:
(
Token (
Feature activation+3.441
Top resid features:
1970
Token1970
Feature activation+0.042
Top resid features:
)
Token)
Feature activation+0.099
Top resid features:
and
Token and
Feature activation+0.067
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Go
Token Go
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.030
Top resid features:
have
Token have
Feature activation+0.022
Top resid features:
heard
Token heard
Feature activation-0.040
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
lot
Token lot
Feature activation-0.078
Top resid features:
(
Token (
Feature activation+3.413
Top resid features:
55
Token55
Feature activation+0.010
Top resid features:
%)
Token%)
Feature activation+0.158
Top resid features:
or
Token or
Feature activation+0.166
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
little
Token little
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.016
Top resid features:
have
Token have
Feature activation+0.022
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
comment
Token comment
Feature activation+0.059
Top resid features:
stored
Token stored
Feature activation-0.015
Top resid features:
(
Token (
Feature activation+3.051
Top resid features:
true
Tokentrue
Feature activation+0.104
Top resid features:
)
Token)
Feature activation+0.130
Top resid features:
or
Token or
Feature activation+0.072
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
c
Tokenc
Feature activation-0.008
Top resid features:
fold
Tokenfold
Feature activation+0.002
Top resid features:
l
Tokenl
Feature activation-0.040
Top resid features:
'
Token'
Feature activation+0.082
Top resid features:
(
Token (
Feature activation+2.550
Top resid features:
pure
Tokenpure
Feature activation+0.111
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
)
Token )
Feature activation+0.070
Top resid features:
==
Token ==
Feature activation+0.069
Top resid features:
pure
Token pure
Feature activation+0.030
Top resid features:
th
Tokenth
Feature activation+0.014
Top resid features:
month
Token month
Feature activation+0.056
Top resid features:
(
Token (
Feature activation+0.897
Top resid features:
11
Token11
Feature activation+0.031
Top resid features:
43
Token43
Feature activation+0.058
Top resid features:
):
Token):
Feature activation+1.407
Top resid features:
Kon
Token Kon
Feature activation+0.007
Top resid features:
oe
Tokenoe
Feature activation-0.000
Top resid features:
passed
Token passed
Feature activation-0.001
Top resid features:
his
Token his
Feature activation-0.008
Top resid features:
days
Token days
Feature activation+0.013
Top resid features:
red
Tokenred
Feature activation-0.006
Top resid features:
around
Token around
Feature activation+0.026
Top resid features:
a
Token a
Feature activation+0.059
Top resid features:
handic
Token handic
Feature activation+0.003
Top resid features:
ap
Tokenap
Feature activation+0.068
Top resid features:
(
Token (
Feature activation+2.860
Top resid features:
K
TokenK
Feature activation+0.024
Top resid features:
ham
Tokenham
Feature activation-0.003
Top resid features:
oshi
Tokenoshi
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Black
Token Black
Feature activation-0.002
Top resid features:
Other
Token Other
Feature activation-0.007
Top resid features:
companies
Token companies
Feature activation+0.055
Top resid features:
include
Token include
Feature activation+0.225
Top resid features:
Mood
Token Mood
Feature activation-0.031
Top resid features:
Media
Token Media
Feature activation+0.098
Top resid features:
(
Token (
Feature activation+2.548
Top resid features:
owner
Tokenowner
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
m
Tokenm
Feature activation-0.001
Top resid features:
borne
Token borne
Feature activation+0.006
Top resid features:
by
Token by
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Federal
Token Federal
Feature activation+0.009
Top resid features:
Government
Token Government
Feature activation-0.023
Top resid features:
(
Token (
Feature activation+3.048
Top resid features:
50
Token50
Feature activation+0.002
Top resid features:
%),
Token%),
Feature activation+0.190
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
Government
Token Government
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.099
Top resid features:
Americans
Token Americans
Feature activation-0.015
Top resid features:
for
Token for
Feature activation+0.022
Top resid features:
Prosper
Token Prosper
Feature activation+0.044
Top resid features:
ity
Tokenity
Feature activation+0.080
Top resid features:
(
Token (
Feature activation+2.585
Top resid features:
AFP
TokenAFP
Feature activation+0.036
Top resid features:
),
Token),
Feature activation+0.134
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Freedom
Token Freedom
Feature activation+0.000
Top resid features:
Partners
Token Partners
Feature activation+0.000
Top resid features:
dips
Token dips
Feature activation-0.035
Top resid features:
served
Token served
Feature activation+0.024
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
inj
Token inj
Feature activation-0.024
Top resid features:
era
Tokenera
Feature activation+0.091
Top resid features:
(
Token (
Feature activation+2.741
Top resid features:
bread
Tokenbread
Feature activation+0.008
Top resid features:
)
Token)
Feature activation+0.127
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
na
Token na
Feature activation+0.000
Top resid features:
an
Tokenan
Feature activation+0.000
Top resid features:
Hawaii
Token Hawaii
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
white
Token white
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.035
Top resid features:
Asian
Token Asian
Feature activation-0.024
Top resid features:
(
Token (
Feature activation+2.256
Top resid features:
18
Token18
Feature activation+0.170
Top resid features:
%),
Token%),
Feature activation+0.496
Top resid features:
Asian
Token Asian
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Native
Token Native
Feature activation+0.000
Top resid features:
yd
Tokenyd
Feature activation-0.011
Top resid features:
aily
Tokenaily
Feature activation-0.038
Top resid features:
news
Tokennews
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
com
Tokencom
Feature activation-0.020
Top resid features:
(
Token (
Feature activation+2.943
Top resid features:
2
Token2
Feature activation-0.028
Top resid features:
),
Token),
Feature activation+0.067
Top resid features:
cog
Token cog
Feature activation+0.000
Top resid features:
ent
Tokenent
Feature activation+0.000
Top resid features:
comment
Tokencomment
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
1
Token1
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Crazy
Token Crazy
Feature activation-0.149
Top resid features:
Crab
Token Crab
Feature activation+0.051
Top resid features:
(
Token (
Feature activation+2.854
Top resid features:
G
TokenG
Feature activation-0.009
Top resid features:
iants
Tokeniants
Feature activation-0.041
Top resid features:
)
Token)
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.101
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Initial
TokenInitial
Feature activation-0.004
Top resid features:
stream
Token stream
Feature activation+0.064
Top resid features:
(
Token (
Feature activation+2.375
Top resid features:
VB
TokenVB
Feature activation+0.036
Top resid features:
1
Token1
Feature activation+0.051
Top resid features:
)
Token)
Feature activation+0.209
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
mid
Token mid
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.146
Top resid features:
G
Token G
Feature activation-0.035
Top resid features:
ug
Tokenug
Feature activation+0.001
Top resid features:
gen
Tokengen
Feature activation-0.006
Top resid features:
heim
Tokenheim
Feature activation-0.010
Top resid features:
(
Token (
Feature activation+2.143
Top resid features:
2000
Token2000
Feature activation+0.020
Top resid features:
)
Token)
Feature activation+0.252
Top resid features:
and
Token and
Feature activation+0.140
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Smithsonian
Token Smithsonian
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
world
Token world
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
famous
Tokenfamous
Feature activation-0.014
Top resid features:
contributors
Token contributors
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+2.395
Top resid features:
Alexander
TokenAlexander
Feature activation+0.006
Top resid features:
Mc
Token Mc
Feature activation-0.001
Top resid features:
Queen
TokenQueen
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
D
Token D
Feature activation-0.005
Top resid features:
mods
Token mods
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
both
Token both
Feature activation-0.016
Top resid features:
commer
Token commer
Feature activation+0.049
Top resid features:
ical
Tokenical
Feature activation+0.070
Top resid features:
(
Token (
Feature activation+2.438
Top resid features:
the
Tokenthe
Feature activation+0.003
Top resid features:
list
Token list
Feature activation+0.013
Top resid features:
)
Token)
Feature activation+0.129
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
non
Token non
Feature activation+0.000
Top resid features:
here
Token here
Feature activation-0.009
Top resid features:
call
Token call
Feature activation-0.029
Top resid features:
j
Token j
Feature activation-0.048
Top resid features:
uh
Tokenuh
Feature activation-0.012
Top resid features:
yo
Tokenyo
Feature activation+0.020
Top resid features:
(
Token (
Feature activation+2.553
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
ice
Tokenice
Feature activation+0.001
Top resid features:
trees
Token trees
Feature activation+0.017
Top resid features:
âĢ
TokenâĢ
Feature activation+0.027
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.03

Head 3: 0.08

Head 4: 0.05

Head 5: 0.04

Head 6: 0.05

Head 7: 0.49

Head 8: 0.05

Head 9: 0.03

Head 10: 0.03

Head 11: 0.05

Positive logits

(#2.74

(_2.63

(2.60

(%2.58

(-2.57

(.2.55

([2.47

(−2.41

(~2.41

()2.41

($2.33

(+2.33

(?,2.30

('2.20

();2.12

("2.06

(!2.02

({1.98

((1.92

subt1.88

Negative logits

VIDE-2.21

.''.-2.18

laughs-2.01

ODUCT-2.01

.).-1.97

esides-1.94

>.-1.94

,)-1.88

...)-1.85

AMY-1.81

chair-1.80

TAG-1.80

agine-1.80

hao-1.76

OULD-1.75

oubtedly-1.74

Isn-1.73

idges-1.73

AKING-1.72

$$$$-1.71

INTERVAL 3.028 - 3.364
CONTAINS 0.000%

INTERVAL 2.691 - 3.028
CONTAINS 0.000%

a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
(
Token (
Feature activation+0.000
55
Token55
Feature activation+0.000
%)
Token%)
Feature activation+0.000
or
Token or
Feature activation+2.747
a
Token a
Feature activation+2.876
little
Token little
Feature activation+1.731
(
Token (
Feature activation+0.018
30
Token30
Feature activation+0.000
%)
Token%)
Feature activation+0.000
lot
Token lot
Feature activation+0.000
(
Token (
Feature activation+0.000
55
Token55
Feature activation+0.000
%)
Token%)
Feature activation+0.000
or
Token or
Feature activation+2.747
a
Token a
Feature activation+2.876
little
Token little
Feature activation+1.731
(
Token (
Feature activation+0.018
30
Token30
Feature activation+0.000
%)
Token%)
Feature activation+0.000
about
Token about
Feature activation+0.000
uring
Tokenuring
Feature activation+0.000
Kyl
Token Kyl
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
ogue
Tokenogue
Feature activation+0.000
),
Token),
Feature activation+3.015
"
Token "
Feature activation+0.143
Mer
TokenMer
Feature activation+0.000
cy
Tokency
Feature activation+0.000
Seat
Token Seat
Feature activation+0.000
"
Token"
Feature activation+0.000
Railway
Token Railway
Feature activation+0.000
Children
Token Children
Feature activation+0.000
(
Token (
Feature activation+0.000
1970
Token1970
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+2.786
The
Token The
Feature activation+0.567
Go
Token Go
Feature activation+0.000
-
Token-
Feature activation+0.000
Between
TokenBetween
Feature activation+0.517
(
Token (
Feature activation+0.248

INTERVAL 2.355 - 2.691
CONTAINS 0.000%

==
Token ==
Feature activation+0.076
pure
Token pure
Feature activation+0.015
a
Token a
Feature activation+0.000
c
Token c
Feature activation+0.477
fold
Tokenfold
Feature activation+1.585
l
Tokenl
Feature activation+2.362
'
Token'
Feature activation+0.961
(
Token (
Feature activation+0.000
f
Tokenf
Feature activation+0.000
map
Tokenmap
Feature activation+0.000
h
Token h
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.029
7
Token 7
Feature activation+0.761
th
Tokenth
Feature activation+2.362
month
Token month
Feature activation+0.076
(
Token (
Feature activation+0.415
11
Token11
Feature activation+0.463
45
Token45
Feature activation+0.945
):
Token):
Feature activation+0.000
comment
Token comment
Feature activation+0.000
stored
Token stored
Feature activation+0.000
(
Token (
Feature activation+0.000
true
Tokentrue
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+2.523
not
Token not
Feature activation+0.705
(
Token (
Feature activation+0.694
false
Tokenfalse
Feature activation+0.000
).
Token).
Feature activation+0.000
We
Token We
Feature activation+0.000

INTERVAL 2.019 - 2.355
CONTAINS 0.001%

for
Token for
Feature activation+0.000
Prosper
Token Prosper
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
(
Token (
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
),
Token),
Feature activation+2.150
the
Token the
Feature activation+0.809
Freedom
Token Freedom
Feature activation+0.000
Partners
Token Partners
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Government
Token Government
Feature activation+0.000
(
Token (
Feature activation+0.000
50
Token50
Feature activation+0.000
%),
Token%),
Feature activation+0.943
the
Token the
Feature activation+2.182
state
Token state
Feature activation+1.028
Government
Token Government
Feature activation+0.840
(
Token (
Feature activation+0.497
25
Token25
Feature activation+0.000
%)
Token%)
Feature activation+0.000
DM
Token DM
Feature activation+0.000
X
TokenX
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
brands
Token brands
Feature activation+0.000
),
Token),
Feature activation+2.299
Image
Token Image
Feature activation+0.286
Sound
Token Sound
Feature activation+0.000
and
Token and
Feature activation+0.000
Play
Token Play
Feature activation+0.000
Networks
Token Networks
Feature activation+0.000
,
Token,
Feature activation+0.000
Gu
Token Gu
Feature activation+0.000
zar
Tokenzar
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
),
Token),
Feature activation+0.822
or
Token or
Feature activation+2.351
un
Token un
Feature activation+0.000
requ
Tokenrequ
Feature activation+0.000
ited
Tokenited
Feature activation+1.088
love
Token love
Feature activation+0.412
(
Token (
Feature activation+0.000
inj
Token inj
Feature activation+0.000
era
Tokenera
Feature activation+0.000
(
Token (
Feature activation+0.000
bread
Tokenbread
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+2.068
na
Token na
Feature activation+0.000
an
Tokenan
Feature activation+0.000
cris
Token cris
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
;
Token;
Feature activation+0.000

INTERVAL 1.682 - 2.019
CONTAINS 0.002%

gun
Token gun
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+1.966
Chief
Token Chief
Feature activation+0.000
N
Token N
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Tokena
Feature activation+0.000
(
Token (
Feature activation+0.000
55
Token55
Feature activation+0.000
%)
Token%)
Feature activation+0.000
or
Token or
Feature activation+2.747
a
Token a
Feature activation+2.876
little
Token little
Feature activation+1.731
(
Token (
Feature activation+0.018
30
Token30
Feature activation+0.000
%)
Token%)
Feature activation+0.000
about
Token about
Feature activation+0.000
claims
Token claims
Feature activation+0.000
been
Token been
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
featured
Token featured
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.020
newer
Token newer
Feature activation+1.794
names
Token names
Feature activation+0.110
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
something
Token something
Feature activation+0.000
unique
Token unique
Feature activation+0.000
flights
Token flights
Feature activation+0.000
(
Token (
Feature activation+0.000
to
Tokento
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.765
Anton
Token Anton
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
Airlines
Token Airlines
Feature activation+0.000
offers
Token offers
Feature activation+0.000
cargo
Token cargo
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
list
Token list
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.787
non
Token non
Feature activation+0.874
-
Token-
Feature activation+0.000
commercial
Tokencommercial
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000

INTERVAL 1.346 - 1.682
CONTAINS 0.002%

and
Token and
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.294
won
Token won
Feature activation+1.048
it
Token it
Feature activation+1.214
in
Token in
Feature activation+1.375
2009
Token 2009
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Then
TokenThen
Feature activation+0.000
and
Token and
Feature activation+0.000
/
Token/
Feature activation+0.000
or
Tokenor
Feature activation+0.000
HC
Token HC
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+1.431
in
Token in
Feature activation+0.000
house
Token house
Feature activation+0.000
laboratory
Token laboratory
Feature activation+0.000
tests
Token tests
Feature activation+0.000
captured
Token captured
Feature activation+0.000
)
Token )
Feature activation+0.000
==
Token ==
Feature activation+0.076
pure
Token pure
Feature activation+0.015
a
Token a
Feature activation+0.000
c
Token c
Feature activation+0.477
fold
Tokenfold
Feature activation+1.585
l
Tokenl
Feature activation+2.362
'
Token'
Feature activation+0.961
(
Token (
Feature activation+0.000
f
Tokenf
Feature activation+0.000
map
Tokenmap
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Transform
TokenTransform
Feature activation+0.000
your
Token your
Feature activation+0.000
photos
Token photos
Feature activation+0.000
with
Token with
Feature activation+1.414
color
Token color
Feature activation+0.000
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+0.000
a
Token a
Feature activation+0.134
flash
Token flash
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
p
Token p
Feature activation+0.000
her
Tokenher
Feature activation+0.000
om
Tokenom
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
?),
Token?),
Feature activation+1.535
vision
Token vision
Feature activation+0.000
(
Token (
Feature activation+0.000
does
Tokendoes
Feature activation+0.000
the
Token the
Feature activation+0.000
female
Token female
Feature activation+0.000

INTERVAL 1.009 - 1.346
CONTAINS 0.005%

in
Token in
Feature activation+0.000
policy
Token policy
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
(
Token (
Feature activation+0.000
85
Token85
Feature activation+0.000
%),
Token%),
Feature activation+1.200
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
being
Token being
Feature activation+0.000
serious
Token serious
Feature activation+0.000
),
Token),
Feature activation+1.019
something
Token something
Feature activation+0.000
disturbing
Token disturbing
Feature activation+0.165
-
Token-
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
(
Token (
Feature activation+0.000
red
Tokenred
Feature activation+0.000
),
Token),
Feature activation+0.000
He
Token He
Feature activation+0.000
zb
Tokenzb
Feature activation+0.000
-
Token-
Feature activation+0.000
i
Tokeni
Feature activation+1.200
Islam
Token Islam
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Gul
Token Gul
Feature activation+0.000
b
Tokenb
Feature activation+0.000
uddin
Tokenuddin
Feature activation+0.000
($
Token ($
Feature activation+0.000
21
Token21
Feature activation+0.000
.
Token.
Feature activation+0.000
99
Token99
Feature activation+0.000
)
Token)
Feature activation+0.206
and
Token and
Feature activation+1.043
spaghetti
Token spaghetti
Feature activation+0.478
(
Token (
Feature activation+0.065
from
Tokenfrom
Feature activation+0.339
$
Token $
Feature activation+0.000
16
Token16
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Wars
Token Wars
Feature activation+0.000
Rebels
Token Rebels
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.416
Ċ
TokenĊ
Feature activation+1.068
Y
TokenY
Feature activation+0.103
oda
Tokenoda
Feature activation+0.321
(
Token (
Feature activation+0.000
Star
TokenStar
Feature activation+0.000
Wars
Token Wars
Feature activation+0.000

INTERVAL 0.673 - 1.009
CONTAINS 0.012%

(
Token (
Feature activation+0.000
CB
TokenCB
Feature activation+0.000
,
Token,
Feature activation+0.000
LSU
Token LSU
Feature activation+0.120
)
Token)
Feature activation+0.000
or
Token or
Feature activation+0.745
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
case
Token case
Feature activation+0.000
scenario
Token scenario
Feature activation+0.000
),
Token),
Feature activation+0.000
Don
Token Don
Feature activation+0.000
atell
Tokenatell
Feature activation+0.000
i
Tokeni
Feature activation+0.000
6
Token 6
Feature activation+0.000
(
Token (
Feature activation+0.707
Pat
TokenPat
Feature activation+0.121
erson
Tokenerson
Feature activation+0.000
68
Token 68
Feature activation+0.000
âĢ²
TokenâĢ²
Feature activation+0.000
),
Token),
Feature activation+0.000
24
Token 24
Feature activation+0.000
percent
Token percent
Feature activation+0.000
today
Token today
Feature activation+0.000
),
Token),
Feature activation+0.904
college
Token college
Feature activation+0.664
graduates
Token graduates
Feature activation+0.813
(
Token (
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
48
Token 48
Feature activation+0.000
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+0.000
Prosper
Token Prosper
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
(
Token (
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
),
Token),
Feature activation+2.150
the
Token the
Feature activation+0.809
Freedom
Token Freedom
Feature activation+0.000
Partners
Token Partners
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
N
TokenN
Feature activation+0.000
BI
TokenBI
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.732
International
Token International
Feature activation+0.334
Living
Token Living
Feature activation+0.000
Future
Token Future
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 0.336 - 0.673
CONTAINS 0.024%

meaning
Tokenmeaning
Feature activation+0.000
"
Token "
Feature activation+0.000
woman
Tokenwoman
Feature activation+0.000
")
Token")
Feature activation+0.000
and
Token and
Feature activation+1.755
mat
Token mat
Feature activation+0.604
lat
Tokenlat
Feature activation+0.424
l
Tokenl
Feature activation+0.251
(
Token (
Feature activation+0.000
meaning
Tokenmeaning
Feature activation+0.000
"
Token "
Feature activation+0.000
),
Token),
Feature activation+0.822
or
Token or
Feature activation+2.351
un
Token un
Feature activation+0.000
requ
Tokenrequ
Feature activation+0.000
ited
Tokenited
Feature activation+1.088
love
Token love
Feature activation+0.412
(
Token (
Feature activation+0.000
Hum
TokenHum
Feature activation+0.000
Dil
Token Dil
Feature activation+0.000
De
Token De
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
light
Token light
Feature activation+0.000
sab
Token sab
Feature activation+0.000
er
Tokener
Feature activation+0.000
),
Token),
Feature activation+0.508
assault
Token assault
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
disorderly
Token disorderly
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
use
Token use
Feature activation+0.000
face
Token face
Feature activation+0.000
transpl
Token transpl
Feature activation+0.000
ants
Tokenants
Feature activation+0.000
)
Token)
Feature activation+0.207
and
Token and
Feature activation+0.348
a
Token a
Feature activation+0.631
strong
Token strong
Feature activation+0.675
female
Token female
Feature activation+0.310
protagonist
Token protagonist
Feature activation+0.256
.
Token.
Feature activation+0.000
set
Token set
Feature activation+0.588
weight
Tokenweight
Feature activation+0.000
(
Token (
Feature activation+0.084
to
Token to
Feature activation+0.503
_
Token_
Feature activation+0.087
ts
Tokents
Feature activation+0.367
vector
Tokenvector
Feature activation+0.000
(
Token (
Feature activation+0.000
coales
Token coales
Feature activation+0.000
ce
Tokence
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 0.000 - 0.336
CONTAINS 99.954%

Real
Token Real
Feature activation+0.000
Estate
Token Estate
Feature activation+0.000
Investments
Token Investments
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
loan
Token loan
Feature activation+0.000
had
Token had
Feature activation+0.000
an
Token an
Feature activation+0.000
interest
Token interest
Feature activation+0.000
rate
Token rate
Feature activation+0.000
of
Token of
Feature activation+0.000
response
Token response
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Res
TokenRes
Feature activation+0.000
idential
Tokenidential
Feature activation+0.000
and
Token and
Feature activation+0.000
business
Token business
Feature activation+0.000
alarm
Token alarm
Feature activation+0.000
systems
Token systems
Feature activation+0.000
inexpl
Token inexpl
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
smart
Token smart
Feature activation+0.000
ing
Tokening
Feature activation+0.000
from
Token from
Feature activation+0.000
legislative
Token legislative
Feature activation+0.000
changes
Token changes
Feature activation+0.000
that
Token that
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
restricted
Token restricted
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
weighing
Token weighing
Feature activation+0.000
their
Token their
Feature activation+0.000
options
Token options
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Represent
TokenRepresent
Feature activation+0.000
sharp
Token sharp
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
tariff
Token tariff
Feature activation+0.000
will
Token will
Feature activation+0.000
go
Token go
Feature activation+0.000
up
Token up
Feature activation+0.000
very
Token very
Feature activation+0.000
sharply
Token sharply
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ¦
TokenâĢ¦
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 H7.7: (feature 7050)

TOP ACTIVATIONS
MAX = 2.627

the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
uh
Tokenuh
Feature activation+0.000
iri
Tokeniri
Feature activation+0.000
,
Token,
Feature activation+1.361
to
Token to
Feature activation+2.627
the
Token the
Feature activation+2.122
M
Token M
Feature activation+0.000
Äģ
TokenÄģ
Feature activation+0.000
ori
Tokenori
Feature activation+1.028
ward
Token ward
Feature activation+0.452
the
Token the
Feature activation+0.000
k
Token k
Feature activation+0.000
aim
Tokenaim
Feature activation+0.000
ahi
Tokenahi
Feature activation+0.000
working
Token working
Feature activation+0.000
to
Token to
Feature activation+2.552
cater
Token cater
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
uh
Tokenuh
Feature activation+0.000
;
Token;
Feature activation+1.098
it
Token it
Feature activation+0.663
will
Token will
Feature activation+0.643
be
Token be
Feature activation+1.669
one
Token one
Feature activation+2.436
of
Token of
Feature activation+2.442
officers
Token officers
Feature activation+0.819
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
target
Token target
Feature activation+0.000
of
Token of
Feature activation+0.000
person
Token person
Feature activation+0.000
;
Token;
Feature activation+1.098
it
Token it
Feature activation+0.663
will
Token will
Feature activation+0.643
be
Token be
Feature activation+1.669
one
Token one
Feature activation+2.436
of
Token of
Feature activation+2.442
officers
Token officers
Feature activation+0.819
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
target
Token target
Feature activation+0.000
get
Token get
Feature activation+0.000
married
Token married
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
or
Token or
Feature activation+2.395
Vegeta
Token Vegeta
Feature activation+1.646
saying
Token saying
Feature activation+0.465
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.383
a
Token a
Feature activation+0.471
case
Token case
Feature activation+0.741
of
Token of
Feature activation+1.972
one
Token one
Feature activation+2.274
of
Token of
Feature activation+1.786
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.533
of
Token of
Feature activation+1.791
one
Token one
Feature activation+2.156
of
Token of
Feature activation+0.592
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.385
.
Token.
Feature activation+0.000
man
Token man
Feature activation+0.000
uh
Tokenuh
Feature activation+0.000
iri
Tokeniri
Feature activation+0.000
,
Token,
Feature activation+1.361
to
Token to
Feature activation+2.627
the
Token the
Feature activation+2.122
M
Token M
Feature activation+0.000
Äģ
TokenÄģ
Feature activation+0.000
ori
Tokenori
Feature activation+1.028
ward
Token ward
Feature activation+0.452
ens
Tokenens
Feature activation+0.000
a
Token a
Feature activation+0.000
com
Token com
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+1.478
to
Token to
Feature activation+2.054
pet
Token pet
Feature activation+0.152
owners
Token owners
Feature activation+1.560
snapping
Token snapping
Feature activation+0.000
photos
Token photos
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.740
at
Token at
Feature activation+1.999
the
Token the
Feature activation+2.047
woman
Token woman
Feature activation+1.433
being
Token being
Feature activation+1.102
heck
Token heck
Feature activation+0.000
led
Tokenled
Feature activation+0.000
by
Token by
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.740
at
Token at
Feature activation+1.999
the
Token the
Feature activation+2.047
woman
Token woman
Feature activation+1.433
being
Token being
Feature activation+1.102
heck
Token heck
Feature activation+0.000
led
Tokenled
Feature activation+0.000
someone
Token someone
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.383
a
Token a
Feature activation+0.471
case
Token case
Feature activation+0.741
of
Token of
Feature activation+1.972
one
Token one
Feature activation+2.274
of
Token of
Feature activation+1.786
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
getting
Token getting
Feature activation+0.000
cold
Token cold
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.893
g
Token g
Feature activation+0.079
az
Tokenaz
Feature activation+0.000
p
Tokenp
Feature activation+0.000
acho
Tokenacho
Feature activation+1.707
âĢ
TokenâĢ
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
worried
Token worried
Feature activation+1.373
about
Token about
Feature activation+1.878
drought
Token drought
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
these
Token these
Feature activation+0.000
things
Token things
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
to
Tokento
Feature activation+0.000
promote
Token promote
Feature activation+0.396
medicines
Token medicines
Feature activation+0.579
to
Token to
Feature activation+1.792
children
Token children
Feature activation+1.080
suggesting
Token suggesting
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
someone
Token someone
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.533
of
Token of
Feature activation+1.791
one
Token one
Feature activation+2.156
of
Token of
Feature activation+0.592
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.385
is
Token is
Feature activation+0.383
a
Token a
Feature activation+0.471
case
Token case
Feature activation+0.741
of
Token of
Feature activation+1.972
one
Token one
Feature activation+2.274
of
Token of
Feature activation+1.786
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
,
Token,
Feature activation+1.369
hip
Token hip
Feature activation+0.781
sters
Tokensters
Feature activation+0.918
sitting
Token sitting
Feature activation+0.000
around
Token around
Feature activation+0.198
,
Token,
Feature activation+1.745
actors
Token actors
Feature activation+0.567
working
Token working
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
,
Token,
Feature activation+1.532
Pokémon
Token Pokémon
Feature activation+0.201
the
Token the
Feature activation+0.000
bitter
Token bitter
Feature activation+0.000
cold
Token cold
Feature activation+0.000
,
Token,
Feature activation+0.549
to
Token to
Feature activation+1.547
the
Token the
Feature activation+1.723
many
Token many
Feature activation+0.583
and
Token and
Feature activation+0.000
varied
Token varied
Feature activation+0.000
workshops
Token workshops
Feature activation+0.195
for
Token for
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.893
g
Token g
Feature activation+0.079
az
Tokenaz
Feature activation+0.000
p
Tokenp
Feature activation+0.000
acho
Tokenacho
Feature activation+1.707
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.557
s
Tokens
Feature activation+0.936
getting
Token getting
Feature activation+0.203
warm
Token warm
Feature activation+0.000

Top DFA by src position
MAX = 2.989

from
Token from
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
k
Token k
Feature activation-0.009
Top resid features:
aim
Tokenaim
Feature activation-0.009
Top resid features:
ahi
Tokenahi
Feature activation-0.031
Top resid features:
working
Token working
Feature activation+2.989
Top resid features:
to
Token to
Feature activation+0.071
Top resid features:
cater
Token cater
Feature activation+0.004
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
man
Token man
Feature activation-0.003
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
k
Token k
Feature activation-0.009
Top resid features:
aim
Tokenaim
Feature activation-0.026
Top resid features:
ahi
Tokenahi
Feature activation-0.049
Top resid features:
working
Token working
Feature activation+2.974
Top resid features:
to
Token to
Feature activation+0.152
Top resid features:
cater
Token cater
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
man
Token man
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.014
Top resid features:
not
Token not
Feature activation-0.013
Top resid features:
one
Token one
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
officers
Token officers
Feature activation+0.196
Top resid features:
walking
Token walking
Feature activation+2.702
Top resid features:
free
Token free
Feature activation+0.137
Top resid features:
after
Token after
Feature activation+0.005
Top resid features:
killing
Token killing
Feature activation+0.033
Top resid features:
an
Token an
Feature activation+0.002
Top resid features:
unarmed
Token unarmed
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.044
Top resid features:
not
Token not
Feature activation-0.015
Top resid features:
one
Token one
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.190
Top resid features:
officers
Token officers
Feature activation+0.101
Top resid features:
walking
Token walking
Feature activation+2.745
Top resid features:
free
Token free
Feature activation+0.065
Top resid features:
after
Token after
Feature activation+0.003
Top resid features:
killing
Token killing
Feature activation+0.013
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
unarmed
Token unarmed
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
such
Token such
Feature activation+0.004
Top resid features:
as
Token as
Feature activation+0.019
Top resid features:
Yam
Token Yam
Feature activation-0.114
Top resid features:
cha
Tokencha
Feature activation-0.017
Top resid features:
saying
Token saying
Feature activation+2.864
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
âĢ
Token âĢ
Feature activation-0.007
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
I
TokenI
Feature activation+0.002
Top resid features:
want
Token want
Feature activation+0.004
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
case
Token case
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
stranger
Token stranger
Feature activation+0.233
Top resid features:
hitting
Token hitting
Feature activation+2.455
Top resid features:
someone
Token someone
Feature activation+0.014
Top resid features:
this
Token this
Feature activation+0.028
Top resid features:
is
Token is
Feature activation+0.073
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
case
Token case
Feature activation+0.010
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
case
Token case
Feature activation-0.015
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
stranger
Token stranger
Feature activation+0.288
Top resid features:
hitting
Token hitting
Feature activation+2.198
Top resid features:
someone
Token someone
Feature activation+0.022
Top resid features:
this
Token this
Feature activation+0.031
Top resid features:
is
Token is
Feature activation+0.036
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
case
Token case
Feature activation-0.016
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
k
Token k
Feature activation-0.121
Top resid features:
aim
Tokenaim
Feature activation-0.019
Top resid features:
ahi
Tokenahi
Feature activation-0.060
Top resid features:
working
Token working
Feature activation+2.695
Top resid features:
to
Token to
Feature activation+0.082
Top resid features:
cater
Token cater
Feature activation+0.008
Top resid features:
for
Token for
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
man
Token man
Feature activation-0.004
Top resid features:
or
Token or
Feature activation+0.007
Top resid features:
humorous
Token humorous
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
From
Token From
Feature activation-0.013
Top resid features:
parents
Token parents
Feature activation+0.134
Top resid features:
shaming
Token shaming
Feature activation+2.470
Top resid features:
their
Token their
Feature activation+0.010
Top resid features:
kids
Token kids
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
com
Token com
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
or
Token or
Feature activation+0.009
Top resid features:
at
Token at
Feature activation-0.015
Top resid features:
the
Token the
Feature activation-0.025
Top resid features:
girl
Token girl
Feature activation+0.160
Top resid features:
being
Token being
Feature activation+2.078
Top resid features:
carried
Token carried
Feature activation+0.199
Top resid features:
around
Token around
Feature activation+0.002
Top resid features:
unconscious
Token unconscious
Feature activation+0.016
Top resid features:
around
Token around
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
or
Token or
Feature activation+0.009
Top resid features:
at
Token at
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
girl
Token girl
Feature activation+0.134
Top resid features:
being
Token being
Feature activation+2.197
Top resid features:
carried
Token carried
Feature activation+0.126
Top resid features:
around
Token around
Feature activation-0.002
Top resid features:
unconscious
Token unconscious
Feature activation+0.016
Top resid features:
around
Token around
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
case
Token case
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
a
Token a
Feature activation+0.079
Top resid features:
stranger
Token stranger
Feature activation+0.415
Top resid features:
hitting
Token hitting
Feature activation+1.935
Top resid features:
someone
Token someone
Feature activation-0.001
Top resid features:
this
Token this
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.060
Top resid features:
a
Token a
Feature activation+0.040
Top resid features:
case
Token case
Feature activation+0.026
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
salmon
Token salmon
Feature activation-0.039
Top resid features:
âĢ
TokenâĢ
Feature activation-0.049
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.050
Top resid features:
getting
Token getting
Feature activation+2.286
Top resid features:
cold
Token cold
Feature activation+0.104
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
g
Token g
Feature activation+0.000
Top resid features:
az
Tokenaz
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation-0.000
Top resid features:
worried
Token worried
Feature activation+0.037
Top resid features:
about
Token about
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
grid
Token grid
Feature activation-0.079
Top resid features:
being
Token being
Feature activation+2.308
Top resid features:
on
Token on
Feature activation+0.017
Top resid features:
edge
Token edge
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
We
Token We
Feature activation+0.033
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
to
Tokento
Feature activation-0.001
Top resid features:
promote
Token promote
Feature activation-0.002
Top resid features:
medicines
Token medicines
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
children
Token children
Feature activation+0.083
Top resid features:
suggesting
Token suggesting
Feature activation+2.083
Top resid features:
that
Token that
Feature activation+0.037
Top resid features:
they
Token they
Feature activation+0.033
Top resid features:
are
Token are
Feature activation-0.000
Top resid features:
100
Token 100
Feature activation+0.020
Top resid features:
%
Token%
Feature activation+0.015
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
case
Token case
Feature activation-0.024
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.035
Top resid features:
stranger
Token stranger
Feature activation+0.549
Top resid features:
hitting
Token hitting
Feature activation+1.714
Top resid features:
someone
Token someone
Feature activation+0.005
Top resid features:
this
Token this
Feature activation+0.020
Top resid features:
is
Token is
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
case
Token case
Feature activation-0.014
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
case
Token case
Feature activation-0.008
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.034
Top resid features:
stranger
Token stranger
Feature activation+0.247
Top resid features:
hitting
Token hitting
Feature activation+1.894
Top resid features:
someone
Token someone
Feature activation+0.013
Top resid features:
this
Token this
Feature activation+0.016
Top resid features:
is
Token is
Feature activation+0.066
Top resid features:
a
Token a
Feature activation+0.029
Top resid features:
case
Token case
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
sun
Token sun
Feature activation+0.026
Top resid features:
b
Tokenb
Feature activation-0.002
Top resid features:
ather
Tokenather
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
laying
Token laying
Feature activation+0.974
Top resid features:
about
Token about
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
hip
Token hip
Feature activation+0.025
Top resid features:
sters
Tokensters
Feature activation+0.088
Top resid features:
sitting
Token sitting
Feature activation+0.749
Top resid features:
from
Token from
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
k
Token k
Feature activation-0.072
Top resid features:
aim
Tokenaim
Feature activation-0.009
Top resid features:
ahi
Tokenahi
Feature activation-0.019
Top resid features:
working
Token working
Feature activation+1.653
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
cater
Token cater
Feature activation+0.004
Top resid features:
for
Token for
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
man
Token man
Feature activation+0.006
Top resid features:
The
Token The
Feature activation+0.008
Top resid features:
salmon
Token salmon
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.102
Top resid features:
Ļ
TokenĻ
Feature activation+0.020
Top resid features:
s
Tokens
Feature activation+0.030
Top resid features:
getting
Token getting
Feature activation+2.102
Top resid features:
cold
Token cold
Feature activation+0.129
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.150
Top resid features:
g
Token g
Feature activation+0.014
Top resid features:
az
Tokenaz
Feature activation-0.014
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.03

Head 3: 0.05

Head 4: 0.07

Head 5: 0.06

Head 6: 0.05

Head 7: 0.48

Head 8: 0.04

Head 9: 0.04

Head 10: 0.04

Head 11: 0.05

Positive logits

crashing3.05

shifting2.87

scrambling2.83

leaking2.83

whispering2.80

tearing2.77

disappearing2.77

popping2.76

swapping2.75

buzzing2.74

stripping2.72

disgruntled2.68

clicking2.66

falling2.64

sneaking2.64

moaning2.64

grinding2.62

shutting2.61

whining2.61

yelling2.60

Negative logits

dule-2.51

Grade-2.50

shall-2.45

Favor-2.43

Ep-2.41

Recommended-2.38

');-2.32

Benz-2.30

Appearance-2.29

Champ-2.26

requires-2.23

canon-2.22

represents-2.22

corresponds-2.21

expires-2.21

constitutes-2.20

lore-2.17

Beg-2.17

Aven-2.16

must-2.16

INTERVAL 2.364 - 2.627
CONTAINS 0.001%

get
Token get
Feature activation+0.000
married
Token married
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
or
Token or
Feature activation+2.395
Vegeta
Token Vegeta
Feature activation+1.646
saying
Token saying
Feature activation+0.465
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Token the
Feature activation+0.000
k
Token k
Feature activation+0.000
aim
Tokenaim
Feature activation+0.000
ahi
Tokenahi
Feature activation+0.000
working
Token working
Feature activation+0.000
to
Token to
Feature activation+2.552
cater
Token cater
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
uh
Tokenuh
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
uh
Tokenuh
Feature activation+0.000
iri
Tokeniri
Feature activation+0.000
,
Token,
Feature activation+1.361
to
Token to
Feature activation+2.627
the
Token the
Feature activation+2.122
M
Token M
Feature activation+0.000
Äģ
TokenÄģ
Feature activation+0.000
ori
Tokenori
Feature activation+1.028
ward
Token ward
Feature activation+0.452
person
Token person
Feature activation+0.000
;
Token;
Feature activation+1.098
it
Token it
Feature activation+0.663
will
Token will
Feature activation+0.643
be
Token be
Feature activation+1.669
one
Token one
Feature activation+2.436
of
Token of
Feature activation+2.442
officers
Token officers
Feature activation+0.819
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
target
Token target
Feature activation+0.000
;
Token;
Feature activation+1.098
it
Token it
Feature activation+0.663
will
Token will
Feature activation+0.643
be
Token be
Feature activation+1.669
one
Token one
Feature activation+2.436
of
Token of
Feature activation+2.442
officers
Token officers
Feature activation+0.819
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
target
Token target
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 2.101 - 2.364
CONTAINS 0.000%

man
Token man
Feature activation+0.000
uh
Tokenuh
Feature activation+0.000
iri
Tokeniri
Feature activation+0.000
,
Token,
Feature activation+1.361
to
Token to
Feature activation+2.627
the
Token the
Feature activation+2.122
M
Token M
Feature activation+0.000
Äģ
TokenÄģ
Feature activation+0.000
ori
Tokenori
Feature activation+1.028
ward
Token ward
Feature activation+0.452
ens
Tokenens
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.383
a
Token a
Feature activation+0.471
case
Token case
Feature activation+0.741
of
Token of
Feature activation+1.972
one
Token one
Feature activation+2.274
of
Token of
Feature activation+1.786
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.533
of
Token of
Feature activation+1.791
one
Token one
Feature activation+2.156
of
Token of
Feature activation+0.592
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.385
.
Token.
Feature activation+0.000

INTERVAL 1.839 - 2.101
CONTAINS 0.001%

a
Token a
Feature activation+0.000
com
Token com
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+1.478
to
Token to
Feature activation+2.054
pet
Token pet
Feature activation+0.152
owners
Token owners
Feature activation+1.560
snapping
Token snapping
Feature activation+0.000
photos
Token photos
Feature activation+0.000
of
Token of
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
getting
Token getting
Feature activation+0.000
cold
Token cold
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.893
g
Token g
Feature activation+0.079
az
Tokenaz
Feature activation+0.000
p
Tokenp
Feature activation+0.000
acho
Tokenacho
Feature activation+1.707
âĢ
TokenâĢ
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.740
at
Token at
Feature activation+1.999
the
Token the
Feature activation+2.047
woman
Token woman
Feature activation+1.433
being
Token being
Feature activation+1.102
heck
Token heck
Feature activation+0.000
led
Tokenled
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.740
at
Token at
Feature activation+1.999
the
Token the
Feature activation+2.047
woman
Token woman
Feature activation+1.433
being
Token being
Feature activation+1.102
heck
Token heck
Feature activation+0.000
led
Tokenled
Feature activation+0.000
by
Token by
Feature activation+0.000
someone
Token someone
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.383
a
Token a
Feature activation+0.471
case
Token case
Feature activation+0.741
of
Token of
Feature activation+1.972
one
Token one
Feature activation+2.274
of
Token of
Feature activation+1.786
her
Token her
Feature activation+0.000
best
Token best
Feature activation+0.000
friends
Token friends
Feature activation+0.000

INTERVAL 1.576 - 1.839
CONTAINS 0.002%

the
Token the
Feature activation+0.000
bitter
Token bitter
Feature activation+0.000
cold
Token cold
Feature activation+0.000
,
Token,
Feature activation+0.549
to
Token to
Feature activation+1.547
the
Token the
Feature activation+1.723
many
Token many
Feature activation+0.583
and
Token and
Feature activation+0.000
varied
Token varied
Feature activation+0.000
workshops
Token workshops
Feature activation+0.195
for
Token for
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
to
Tokento
Feature activation+0.000
promote
Token promote
Feature activation+0.396
medicines
Token medicines
Feature activation+0.579
to
Token to
Feature activation+1.792
children
Token children
Feature activation+1.080
suggesting
Token suggesting
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
from
Token from
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
Wayne
Token Wayne
Feature activation+0.000
being
Token being
Feature activation+0.000
Batman
Token Batman
Feature activation+0.000
to
Token to
Feature activation+1.671
Atlantis
Token Atlantis
Feature activation+0.000
and
Token and
Feature activation+0.211
Them
Token Them
Feature activation+0.000
ysc
Tokenysc
Feature activation+0.000
ira
Tokenira
Feature activation+0.155
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
stomach
Token stomach
Feature activation+0.481
s
Tokens
Feature activation+0.493
of
Token of
Feature activation+1.606
fish
Token fish
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
eaten
Token eaten
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+1.893
g
Token g
Feature activation+0.079
az
Tokenaz
Feature activation+0.000
p
Tokenp
Feature activation+0.000
acho
Tokenacho
Feature activation+1.707
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.557
s
Tokens
Feature activation+0.936
getting
Token getting
Feature activation+0.203
warm
Token warm
Feature activation+0.000

INTERVAL 1.313 - 1.576
CONTAINS 0.002%

no
Token no
Feature activation+0.000
team
Token team
Feature activation+0.000
winning
Token winning
Feature activation+0.000
every
Token every
Feature activation+0.000
game
Token game
Feature activation+0.000
and
Token and
Feature activation+1.441
10
Token 10
Feature activation+1.193
of
Token of
Feature activation+0.412
the
Token the
Feature activation+0.000
27
Token 27
Feature activation+0.000
games
Token games
Feature activation+0.000
devoted
Token devoted
Feature activation+0.000
to
Token to
Feature activation+0.000
our
Token our
Feature activation+0.000
cause
Token cause
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.406
sufficient
Token sufficient
Feature activation+1.343
police
Token police
Feature activation+0.389
and
Token and
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.633
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
bitter
Token bitter
Feature activation+0.000
cold
Token cold
Feature activation+0.000
,
Token,
Feature activation+0.549
to
Token to
Feature activation+1.547
the
Token the
Feature activation+1.723
many
Token many
Feature activation+0.583
and
Token and
Feature activation+0.000
varied
Token varied
Feature activation+0.000
workshops
Token workshops
Feature activation+0.195
,
Token,
Feature activation+0.482
and
Token and
Feature activation+0.772
z
Token z
Feature activation+0.000
en
Tokenen
Feature activation+1.286
or
Token or
Feature activation+1.499
goodness
Token goodness
Feature activation+1.329
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
compassionate
Token compassionate
Feature activation+0.000
service
Token service
Feature activation+0.000
piece
Token piece
Feature activation+0.000
piece
Token piece
Feature activation+0.000
,
Token,
Feature activation+0.482
and
Token and
Feature activation+0.772
z
Token z
Feature activation+0.000
en
Tokenen
Feature activation+1.286
or
Token or
Feature activation+1.499
goodness
Token goodness
Feature activation+1.329
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
compassionate
Token compassionate
Feature activation+0.000
service
Token service
Feature activation+0.000

INTERVAL 1.051 - 1.313
CONTAINS 0.004%

Leader
Token Leader
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Sel
Token Sel
Feature activation+0.000
inger
Tokeninger
Feature activation+0.000
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+1.149
per
Token per
Feature activation+0.127
cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
Liberal
Token Liberal
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.976
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.313
sitting
Token sitting
Feature activation+1.105
opposite
Token opposite
Feature activation+0.000
both
Token both
Feature activation+0.000
parties
Token parties
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
reating
Tokenreating
Feature activation+0.000
the
Token the
Feature activation+0.000
machines
Token machines
Feature activation+0.000
,
Token,
Feature activation+0.156
or
Token or
Feature activation+1.667
each
Token each
Feature activation+1.274
other
Token other
Feature activation+0.544
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ah
TokenAh
Feature activation+0.000
with
Token with
Feature activation+0.000
her
Token her
Feature activation+0.000
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.711
about
Token about
Feature activation+1.395
a
Token a
Feature activation+1.189
young
Token young
Feature activation+0.328
girl
Token girl
Feature activation+0.635
who
Token who
Feature activation+0.144
wrote
Token wrote
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
activity
Token activity
Feature activation+0.000
or
Token or
Feature activation+0.459
that
Token that
Feature activation+0.000
,
Token,
Feature activation+1.084
taking
Token taking
Feature activation+0.483
trips
Token trips
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
plays
Token plays
Feature activation+0.000

INTERVAL 0.788 - 1.051
CONTAINS 0.004%

it
Token it
Feature activation+0.663
will
Token will
Feature activation+0.643
be
Token be
Feature activation+1.669
one
Token one
Feature activation+2.436
of
Token of
Feature activation+2.442
officers
Token officers
Feature activation+0.819
becoming
Token becoming
Feature activation+0.000
the
Token the
Feature activation+0.000
target
Token target
Feature activation+0.000
of
Token of
Feature activation+0.000
sporadic
Token sporadic
Feature activation+0.000
examples
Token examples
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
four
Token four
Feature activation+0.000
years
Token years
Feature activation+0.998
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cont
TokenCont
Feature activation+0.000
roversial
Tokenroversial
Feature activation+0.000
with
Token with
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.999
some
Token some
Feature activation+0.416
suggesting
Token suggesting
Feature activation+0.000
it
Token it
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
aker
Tokenaker
Feature activation+0.000
for
Token for
Feature activation+0.000
India
Token India
Feature activation+0.000
,
Token,
Feature activation+0.000
followed
Token followed
Feature activation+0.000
by
Token by
Feature activation+0.882
R
Token R
Feature activation+0.000
Ash
Token Ash
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
and
Token and
Feature activation+0.000
R
Token R
Feature activation+0.000
players
Token players
Feature activation+0.366
GO
Token GO
Feature activation+0.093
-
Token-
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+1.097
classical
Token classical
Feature activation+0.904
musicians
Token musicians
Feature activation+0.522
performing
Token performing
Feature activation+0.167
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.016
you
Token you
Feature activation+0.000

INTERVAL 0.525 - 0.788
CONTAINS 0.013%

and
Token and
Feature activation+0.703
Mind
Token Mind
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Posts
Token Posts
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.680
sometimes
Token sometimes
Feature activation+0.889
I
Token I
Feature activation+0.000
narr
Token narr
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
the
Token the
Feature activation+0.000
this
Token this
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
one
Token one
Feature activation+0.000
about
Token about
Feature activation+0.696
a
Token a
Feature activation+0.729
connection
Token connection
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
Bronx
Token Bronx
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
and
Token and
Feature activation+0.000
about
Token about
Feature activation+0.000
90
Token 90
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.624
the
Token the
Feature activation+0.333
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
received
Token received
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.406
sufficient
Token sufficient
Feature activation+1.343
police
Token police
Feature activation+0.389
and
Token and
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.633
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
our
Token our
Feature activation+0.000
interest
Token interest
Feature activation+0.000
.
Token.
Feature activation+0.000
10
Token10
Feature activation+0.000
.
Token.
Feature activation+0.000
10
Token10
Feature activation+0.000
,
Token,
Feature activation+0.907
and
Token and
Feature activation+1.227
some
Token some
Feature activation+0.637
paid
Token paid
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
.
Token.
Feature activation+0.000
10
Token10
Feature activation+0.000

INTERVAL 0.263 - 0.525
CONTAINS 0.030%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
;
Token ;
Feature activation+0.000
be
Token be
Feature activation+0.000
it
Token it
Feature activation+0.313
the
Token the
Feature activation+0.000
Cal
Token Cal
Feature activation+0.000
iban
Tokeniban
Feature activation+0.000
nature
Token nature
Feature activation+0.000
of
Token of
Feature activation+0.000
Samoa
Token Samoa
Feature activation+0.000
will
Token will
Feature activation+0.000
vote
Token vote
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
will
Token will
Feature activation+0.437
a
Token a
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
harassment
Token harassment
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.055
on
Token on
Feature activation+0.346
clear
Token clear
Feature activation+0.000
legal
Token legal
Feature activation+0.000
and
Token and
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
honorable
Token honorable
Feature activation+0.000
journey
Token journey
Feature activation+0.000
,
Token,
Feature activation+0.018
and
Token and
Feature activation+0.334
Gand
Token Gand
Feature activation+0.000
alf
Tokenalf
Feature activation+0.078
's
Token's
Feature activation+0.466
frequent
Token frequent
Feature activation+0.000
abs
Token abs
Feature activation+0.000
there
Token there
Feature activation+0.000
;
Token ;
Feature activation+0.000
-)
Token-)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.298
comment
Token comment
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Irish
Token Irish
Feature activation+0.000
Left
Token Left
Feature activation+0.000

INTERVAL 0.000 - 0.263
CONTAINS 99.944%

the
Token the
Feature activation+0.000
ocean
Token ocean
Feature activation+0.000
's
Token's
Feature activation+0.000
surface
Token surface
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hur
TokenHur
Feature activation+0.000
ricane
Tokenricane
Feature activation+0.000
Sandy
Token Sandy
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
general
Token general
Feature activation+0.000
sense
Token sense
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
specific
Token specific
Feature activation+0.000
sense
Token sense
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
innovation
Token innovation
Feature activation+0.000
and
Token and
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
education
Token education
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
unavailable
Token unavailable
Feature activation+0.000
for
Token for
Feature activation+0.000
comment
Token comment
Feature activation+0.000
.
Token.
Feature activation+0.000
primary
Token primary
Feature activation+0.000
reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
endorsement
Token endorsement
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-
Token-
Feature activation+0.000
round
Tokenround
Feature activation+0.000
pick
Token pick
Feature activation+0.000
was
Token was
Feature activation+0.000
thrown
Token thrown
Feature activation+0.000
right
Token right
Feature activation+0.000
back
Token back
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
mix
Token mix
Feature activation+0.000
and
Token and
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 H7.7: (feature 27716)

TOP ACTIVATIONS
MAX = 3.273

some
Token some
Feature activation+0.000
attendees
Token attendees
Feature activation+0.000
chat
Token chat
Feature activation+0.000
tered
Tokentered
Feature activation+0.000
,
Token,
Feature activation+0.293
others
Token others
Feature activation+3.273
came
Token came
Feature activation+1.339
and
Token and
Feature activation+0.065
went
Token went
Feature activation+0.000
,
Token,
Feature activation+0.155
and
Token and
Feature activation+0.079
must
Token must
Feature activation+0.000
rule
Token rule
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
others
Token others
Feature activation+3.089
obey
Token obey
Feature activation+0.574
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.000
no
Token no
Feature activation+0.000
great
Token great
Feature activation+0.000
interest
Token interest
Feature activation+0.000
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
less
Token less
Feature activation+3.085
zeal
Token zeal
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
getting
Token getting
Feature activation+0.000
to
Token to
Feature activation+0.000
jokes
Token jokes
Feature activation+0.000
land
Token land
Feature activation+0.000
,
Token,
Feature activation+0.047
and
Token and
Feature activation+0.265
the
Token the
Feature activation+0.431
pacing
Token pacing
Feature activation+2.774
is
Token is
Feature activation+0.670
crisp
Token crisp
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000
His
Token His
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
run
Token run
Feature activation+0.000
,
Token,
Feature activation+0.883
staffed
Token staffed
Feature activation+2.732
,
Token,
Feature activation+0.592
advised
Token advised
Feature activation+0.707
,
Token,
Feature activation+0.620
and
Token and
Feature activation+0.898
funded
Token funded
Feature activation+0.010
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
goal
Token goal
Feature activation+0.000
,
Token,
Feature activation+0.534
not
Token not
Feature activation+2.155
a
Token a
Feature activation+2.667
mandate
Token mandate
Feature activation+0.073
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
was
Token was
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+0.261
not
Token not
Feature activation+2.472
a
Token a
Feature activation+1.846
privilege
Token privilege
Feature activation+0.167
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
en
Tokenen
Feature activation+0.000
There
Token There
Feature activation+0.000
,
Token,
Feature activation+0.000
Done
Token Done
Feature activation+2.175
That
Token That
Feature activation+0.720
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
________
Token________
Feature activation+0.000
__
Token__
Feature activation+0.000
give
Token give
Feature activation+0.000
th
Tokenth
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.255
Lord
Token Lord
Feature activation+0.890
t
Token t
Feature activation+2.161
ak
Tokenak
Feature activation+0.303
eth
Tokeneth
Feature activation+1.330
away
Token away
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.180
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
goal
Token goal
Feature activation+0.000
,
Token,
Feature activation+0.534
not
Token not
Feature activation+2.155
a
Token a
Feature activation+2.667
mandate
Token mandate
Feature activation+0.073
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
is
Token is
Feature activation+0.000
justified
Token justified
Feature activation+0.000
,
Token,
Feature activation+0.018
true
Token true
Feature activation+0.015
belief
Token belief
Feature activation+2.082
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
other
Token other
Feature activation+0.000
Rogers
Token Rogers
Feature activation+0.000
had
Token had
Feature activation+0.000
formed
Token formed
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.229
then
Token then
Feature activation+2.070
breached
Token breached
Feature activation+0.171
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
contract
Token contract
Feature activation+0.000
with
Token with
Feature activation+0.000
they
Token they
Feature activation+0.000
clean
Token clean
Feature activation+0.000
;
Token;
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+1.235
they
Token they
Feature activation+2.037
kill
Token kill
Feature activation+1.223
.
Token.
Feature activation+0.000
America
Token America
Feature activation+0.000
also
Token also
Feature activation+0.139
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
care
Token care
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
cats
Token cats
Feature activation+2.036
don
Token don
Feature activation+0.508
't
Token't
Feature activation+0.616
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
argument
Token argument
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
won
Token won
Feature activation+0.002
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.915
drink
Token drink
Feature activation+0.482
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
won
Token won
Feature activation+0.000
do
Token do
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
assist
Token assist
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.908
only
Token only
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
ig
Tokenig
Feature activation+0.000
ua
Tokenua
Feature activation+0.000
and
Token and
Feature activation+0.000
patient
Token patient
Feature activation+0.174
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.549
listened
Token listened
Feature activation+0.875
,
Token,
Feature activation+0.023
he
Token he
Feature activation+1.853
absorbed
Token absorbed
Feature activation+0.789
and
Token and
Feature activation+0.000
assimil
Token assimil
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+0.261
not
Token not
Feature activation+2.472
a
Token a
Feature activation+1.846
privilege
Token privilege
Feature activation+0.167
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Given
TokenGiven
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.046
am
Token am
Feature activation+1.804
unhappy
Token unhappy
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
was
Token was
Feature activation+0.000
willing
Token willing
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+1.278
even
Token even
Feature activation+1.797
eager
Token eager
Feature activation+0.147
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
with
Token with
Feature activation+0.000

Top DFA by src position
MAX = 3.630

,
Token,
Feature activation+0.002
Top resid features:
some
Token some
Feature activation-0.005
Top resid features:
attendees
Token attendees
Feature activation+0.005
Top resid features:
chat
Token chat
Feature activation+0.014
Top resid features:
tered
Tokentered
Feature activation+0.053
Top resid features:
,
Token,
Feature activation+3.630
Top resid features:
others
Token others
Feature activation+0.010
Top resid features:
came
Token came
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
went
Token went
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.014
Top resid features:
some
Token some
Feature activation-0.016
Top resid features:
few
Token few
Feature activation-0.052
Top resid features:
must
Token must
Feature activation+0.023
Top resid features:
rule
Token rule
Feature activation+0.071
Top resid features:
,
Token,
Feature activation+3.105
Top resid features:
and
Token and
Feature activation+0.317
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
others
Token others
Feature activation+0.056
Top resid features:
obey
Token obey
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
shown
Token shown
Feature activation+0.009
Top resid features:
no
Token no
Feature activation-0.000
Top resid features:
great
Token great
Feature activation-0.021
Top resid features:
interest
Token interest
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+3.549
Top resid features:
much
Token much
Feature activation-0.020
Top resid features:
less
Token less
Feature activation+0.003
Top resid features:
zeal
Token zeal
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
funny
Token funny
Feature activation-0.002
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.059
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
jokes
Token jokes
Feature activation-0.001
Top resid features:
land
Token land
Feature activation+0.118
Top resid features:
,
Token,
Feature activation+2.777
Top resid features:
and
Token and
Feature activation+0.273
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
pacing
Token pacing
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
crisp
Token crisp
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
His
Token His
Feature activation-0.001
Top resid features:
campaign
Token campaign
Feature activation+0.010
Top resid features:
is
Token is
Feature activation+0.019
Top resid features:
run
Token run
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+3.170
Top resid features:
staffed
Token staffed
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
advised
Token advised
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
goal
Token goal
Feature activation+0.275
Top resid features:
,
Token,
Feature activation+2.648
Top resid features:
not
Token not
Feature activation+0.216
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
mandate
Token mandate
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.005
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
"
Token "
Feature activation-0.001
Top resid features:
a
Tokena
Feature activation-0.017
Top resid features:
right
Token right
Feature activation+0.125
Top resid features:
,
Token,
Feature activation+2.767
Top resid features:
not
Token not
Feature activation+0.055
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
privilege
Token privilege
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-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Be
TokenBe
Feature activation-0.001
Top resid features:
en
Tokenen
Feature activation+0.004
Top resid features:
There
Token There
Feature activation-0.211
Top resid features:
,
Token,
Feature activation+2.926
Top resid features:
Done
Token Done
Feature activation-0.027
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
________
Token________
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.016
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
Lord
Token Lord
Feature activation+0.001
Top resid features:
give
Token give
Feature activation+0.006
Top resid features:
th
Tokenth
Feature activation+0.075
Top resid features:
and
Token and
Feature activation+2.418
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
Lord
Token Lord
Feature activation+0.029
Top resid features:
t
Token t
Feature activation+0.006
Top resid features:
ak
Tokenak
Feature activation+0.000
Top resid features:
eth
Tokeneth
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
goal
Token goal
Feature activation+0.527
Top resid features:
,
Token,
Feature activation+1.987
Top resid features:
not
Token not
Feature activation+0.080
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
mandate
Token mandate
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ages
Token ages
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.000
Top resid features:
knowledge
Token knowledge
Feature activation-0.005
Top resid features:
is
Token is
Feature activation+0.028
Top resid features:
justified
Token justified
Feature activation+0.123
Top resid features:
,
Token,
Feature activation+2.261
Top resid features:
true
Token true
Feature activation+0.069
Top resid features:
belief
Token belief
Feature activation+0.020
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:
claiming
Token claiming
Feature activation+0.020
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
Rogers
Token Rogers
Feature activation-0.012
Top resid features:
had
Token had
Feature activation+0.007
Top resid features:
formed
Token formed
Feature activation-0.030
Top resid features:
,
Token,
Feature activation+1.989
Top resid features:
and
Token and
Feature activation+0.488
Top resid features:
then
Token then
Feature activation+0.091
Top resid features:
breached
Token breached
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
In
Token In
Feature activation-0.005
Top resid features:
India
Token India
Feature activation-0.001
Top resid features:
they
Token they
Feature activation+0.004
Top resid features:
clean
Token clean
Feature activation+0.030
Top resid features:
;
Token;
Feature activation+2.503
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
America
Token America
Feature activation+0.007
Top resid features:
they
Token they
Feature activation+0.019
Top resid features:
kill
Token kill
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
dogs
Token dogs
Feature activation+0.000
Top resid features:
care
Token care
Feature activation+0.085
Top resid features:
and
Token and
Feature activation+2.346
Top resid features:
the
Token the
Feature activation-0.046
Top resid features:
cats
Token cats
Feature activation+0.079
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
t
Tokent
Feature activation-0.003
Top resid features:
stand
Token stand
Feature activation+0.038
Top resid features:
up
Token up
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+2.372
Top resid features:
I
Token I
Feature activation+0.044
Top resid features:
won
Token won
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.051
Top resid features:
Ļ
TokenĻ
Feature activation-0.011
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
can
Token can
Feature activation+0.001
Top resid features:
do
Token do
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
is
Token is
Feature activation-0.005
Top resid features:
assist
Token assist
Feature activation+0.127
Top resid features:
,
Token,
Feature activation+2.210
Top resid features:
not
Token not
Feature activation+0.058
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
Ant
Token Ant
Feature activation+0.000
Top resid features:
ig
Tokenig
Feature activation+0.000
Top resid features:
ua
Tokenua
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.008
Top resid features:
patient
Token patient
Feature activation+0.079
Top resid features:
,
Token,
Feature activation+0.135
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
listened
Token listened
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+1.853
Top resid features:
he
Token he
Feature activation+0.010
Top resid features:
absorbed
Token absorbed
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
assimil
Token assimil
Feature activation+0.000
Top resid features:
ated
Tokenated
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.008
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
a
Tokena
Feature activation-0.005
Top resid features:
right
Token right
Feature activation+0.068
Top resid features:
,
Token,
Feature activation+2.039
Top resid features:
not
Token not
Feature activation+0.215
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
privilege
Token privilege
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Given
TokenGiven
Feature activation-0.002
Top resid features:
that
Token that
Feature activation-0.008
Top resid features:
I
Token I
Feature activation-0.007
Top resid features:
am
Token am
Feature activation-0.013
Top resid features:
unhappy
Token unhappy
Feature activation+0.211
Top resid features:
,
Token,
Feature activation+2.229
Top resid features:
I
Token I
Feature activation+0.009
Top resid features:
have
Token have
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
right
Token right
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Trump
Token Trump
Feature activation-0.011
Top resid features:
campaign
Token campaign
Feature activation-0.003
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
willing
Token willing
Feature activation+0.070
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.025
Top resid features:
and
Token and
Feature activation+0.220
Top resid features:
even
Token even
Feature activation-0.023
Top resid features:
eager
Token eager
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.02

Head 3: 0.07

Head 4: 0.04

Head 5: 0.04

Head 6: 0.03

Head 7: 0.48

Head 8: 0.05

Head 9: 0.09

Head 10: 0.03

Head 11: 0.05

Positive logits

ancel2.30

redo2.12

whats2.07

ossom2.04

actionDate1.98

isable1.98

forcement1.97

present1.92

etc1.91

exit1.90

jriwal1.89

pickups1.89

flourish1.86

progress1.85

seek1.85

Done1.84

itect1.83

success1.82

respons1.82

done1.81

Negative logits

Pacific-2.34

nian-2.18

Racial-2.16

Boxing-2.14

urinary-2.11

Hawaiian-2.09

Bos-2.05

Hodg-1.98

Klu-1.97

Belgian-1.93

GI-1.93

Commando-1.92

Hungarian-1.91

Croatian-1.90

龍�-1.89

Samoa-1.86

Kol-1.81

longitudinal-1.80

Serbian-1.79

Hawai-1.78

INTERVAL 2.946 - 3.273
CONTAINS 0.000%

must
Token must
Feature activation+0.000
rule
Token rule
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
others
Token others
Feature activation+3.089
obey
Token obey
Feature activation+0.574
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.000
no
Token no
Feature activation+0.000
great
Token great
Feature activation+0.000
interest
Token interest
Feature activation+0.000
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
less
Token less
Feature activation+3.085
zeal
Token zeal
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
getting
Token getting
Feature activation+0.000
to
Token to
Feature activation+0.000
some
Token some
Feature activation+0.000
attendees
Token attendees
Feature activation+0.000
chat
Token chat
Feature activation+0.000
tered
Tokentered
Feature activation+0.000
,
Token,
Feature activation+0.293
others
Token others
Feature activation+3.273
came
Token came
Feature activation+1.339
and
Token and
Feature activation+0.065
went
Token went
Feature activation+0.000
,
Token,
Feature activation+0.155
and
Token and
Feature activation+0.079

INTERVAL 2.619 - 2.946
CONTAINS 0.000%

s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
goal
Token goal
Feature activation+0.000
,
Token,
Feature activation+0.534
not
Token not
Feature activation+2.155
a
Token a
Feature activation+2.667
mandate
Token mandate
Feature activation+0.073
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
Token His
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
is
Token is
Feature activation+0.000
run
Token run
Feature activation+0.000
,
Token,
Feature activation+0.883
staffed
Token staffed
Feature activation+2.732
,
Token,
Feature activation+0.592
advised
Token advised
Feature activation+0.707
,
Token,
Feature activation+0.620
and
Token and
Feature activation+0.898
funded
Token funded
Feature activation+0.010
jokes
Token jokes
Feature activation+0.000
land
Token land
Feature activation+0.000
,
Token,
Feature activation+0.047
and
Token and
Feature activation+0.265
the
Token the
Feature activation+0.431
pacing
Token pacing
Feature activation+2.774
is
Token is
Feature activation+0.670
crisp
Token crisp
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000

INTERVAL 2.291 - 2.619
CONTAINS 0.000%

was
Token was
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Tokena
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+0.261
not
Token not
Feature activation+2.472
a
Token a
Feature activation+1.846
privilege
Token privilege
Feature activation+0.167
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.964 - 2.291
CONTAINS 0.001%

knowledge
Token knowledge
Feature activation+0.000
is
Token is
Feature activation+0.000
justified
Token justified
Feature activation+0.000
,
Token,
Feature activation+0.018
true
Token true
Feature activation+0.015
belief
Token belief
Feature activation+2.082
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
other
Token other
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
goal
Token goal
Feature activation+0.000
,
Token,
Feature activation+0.534
not
Token not
Feature activation+2.155
a
Token a
Feature activation+2.667
mandate
Token mandate
Feature activation+0.073
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
they
Token they
Feature activation+0.000
clean
Token clean
Feature activation+0.000
;
Token;
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+1.235
they
Token they
Feature activation+2.037
kill
Token kill
Feature activation+1.223
.
Token.
Feature activation+0.000
America
Token America
Feature activation+0.000
also
Token also
Feature activation+0.139
has
Token has
Feature activation+0.000
give
Token give
Feature activation+0.000
th
Tokenth
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.255
Lord
Token Lord
Feature activation+0.890
t
Token t
Feature activation+2.161
ak
Tokenak
Feature activation+0.303
eth
Tokeneth
Feature activation+1.330
away
Token away
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.180
Ċ
TokenĊ
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
en
Tokenen
Feature activation+0.000
There
Token There
Feature activation+0.000
,
Token,
Feature activation+0.000
Done
Token Done
Feature activation+2.175
That
Token That
Feature activation+0.720
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
________
Token________
Feature activation+0.000
__
Token__
Feature activation+0.000

INTERVAL 1.637 - 1.964
CONTAINS 0.002%

what
Token what
Feature activation+0.000
gets
Token gets
Feature activation+0.000
prosecuted
Token prosecuted
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.640
gets
Token gets
Feature activation+1.659
ignored
Token ignored
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
've
Token've
Feature activation+0.000
worked
Token worked
Feature activation+0.000
hard
Token hard
Feature activation+0.000
,
Token,
Feature activation+0.346
we
Token we
Feature activation+1.747
're
Token're
Feature activation+1.684
doing
Token doing
Feature activation+1.349
this
Token this
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
won
Token won
Feature activation+0.002
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.915
drink
Token drink
Feature activation+0.482
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
won
Token won
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
declare
Token declare
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
others
Token others
Feature activation+1.683
,
Token,
Feature activation+0.400
like
Token like
Feature activation+0.000
holy
Token holy
Feature activation+0.000
alignment
Token alignment
Feature activation+0.000
,
Token,
Feature activation+0.000
require
Token require
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.280
do
Token do
Feature activation+1.705
not
Token not
Feature activation+1.129
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
that
Token that
Feature activation+0.141
don
Token don
Feature activation+0.228

INTERVAL 1.309 - 1.637
CONTAINS 0.005%

are
Token are
Feature activation+0.000
struck
Token struck
Feature activation+0.000
,
Token,
Feature activation+0.161
all
Token all
Feature activation+0.000
ethics
Token ethics
Feature activation+0.065
are
Token are
Feature activation+1.545
thrown
Token thrown
Feature activation+0.206
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
winds
Token winds
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.630
but
Token but
Feature activation+0.334
perhaps
Token perhaps
Feature activation+0.020
more
Token more
Feature activation+0.000
importantly
Token importantly
Feature activation+0.815
he
Token he
Feature activation+1.446
seems
Token seems
Feature activation+0.482
to
Token to
Feature activation+0.112
have
Token have
Feature activation+0.683
the
Token the
Feature activation+1.694
drive
Token drive
Feature activation+0.353
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
;
Token;
Feature activation+0.000
this
Token this
Feature activation+0.000
has
Token has
Feature activation+0.366
to
Token to
Feature activation+1.415
look
Token look
Feature activation+0.762
like
Token like
Feature activation+0.044
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
walk
Token walk
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.681
has
Token has
Feature activation+1.373
told
Token told
Feature activation+0.164
metropolitan
Token metropolitan
Feature activation+0.000
areas
Token areas
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
been
Token been
Feature activation+0.860
preparing
Token preparing
Feature activation+0.157
for
Token for
Feature activation+1.604
it
Token it
Feature activation+0.143
my
Token my
Feature activation+0.055
whole
Token whole
Feature activation+0.000
life
Token life
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.982 - 1.309
CONTAINS 0.011%

to
Token to
Feature activation+0.000
cook
Token cook
Feature activation+0.000
,
Token,
Feature activation+0.092
cook
Token cook
Feature activation+0.068
,
Token,
Feature activation+0.000
take
Token take
Feature activation+1.243
care
Token care
Feature activation+0.607
of
Token of
Feature activation+0.281
babies
Token babies
Feature activation+0.000
,
Token,
Feature activation+0.000
clean
Token clean
Feature activation+0.000
on
Token on
Feature activation+0.000
group
Token group
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Tokenone
Feature activation+0.009
is
Token is
Feature activation+1.091
based
Token based
Feature activation+1.107
on
Token on
Feature activation+1.230
crime
Token crime
Feature activation+0.001
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
continue
Token continue
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
may
Token may
Feature activation+0.748
it
Token it
Feature activation+1.216
help
Token help
Feature activation+0.549
to
Token to
Feature activation+0.168
bring
Token bring
Feature activation+0.000
better
Token better
Feature activation+0.000
times
Token times
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.280
do
Token do
Feature activation+1.705
not
Token not
Feature activation+1.129
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
that
Token that
Feature activation+0.141
don
Token don
Feature activation+0.228
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
held
Token held
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
images
Token images
Feature activation+1.081
I
Token I
Feature activation+0.615
have
Token have
Feature activation+0.228
created
Token created
Feature activation+0.078
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.655 - 0.982
CONTAINS 0.026%

You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
rules
Token rules
Feature activation+0.000
,
Token,
Feature activation+0.336
You
Token You
Feature activation+0.962
've
Token've
Feature activation+1.487
played
Token played
Feature activation+0.214
the
Token the
Feature activation+0.383
classic
Token classic
Feature activation+0.139
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.883
staffed
Token staffed
Feature activation+2.732
,
Token,
Feature activation+0.592
advised
Token advised
Feature activation+0.707
,
Token,
Feature activation+0.620
and
Token and
Feature activation+0.898
funded
Token funded
Feature activation+0.010
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
help
Token help
Feature activation+0.000
of
Token of
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
hands
Token hands
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.511
feet
Token feet
Feature activation+0.793
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
Ap
Token Ap
Feature activation+0.000
od
Tokenod
Feature activation+0.000
aca
Tokenaca
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
think
Token think
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.794
solve
Token solve
Feature activation+0.164
problems
Token problems
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.159
Aid
TokenAid
Feature activation+0.000
and
Token and
Feature activation+0.000
reveal
Token reveal
Feature activation+0.000
what
Token what
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+0.761
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.327 - 0.655
CONTAINS 0.075%

difficult
Token difficult
Feature activation+0.000
will
Token will
Feature activation+0.000
it
Token it
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.504
how
Token how
Feature activation+0.015
long
Token long
Feature activation+0.612
would
Token would
Feature activation+0.023
it
Token it
Feature activation+0.158
take
Token take
Feature activation+0.000
,
Token,
Feature activation+0.036
Ireland
Token Ireland
Feature activation+0.000
also
Token also
Feature activation+0.210
began
Token began
Feature activation+0.000
by
Token by
Feature activation+0.000
conced
Token conced
Feature activation+0.362
ing
Tokening
Feature activation+0.854
four
Token four
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
algorithms
Token algorithms
Feature activation+0.000
with
Token with
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.354
tens
Token tens
Feature activation+0.000
of
Token of
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
UKIP
Token UKIP
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
I
Token I
Feature activation+0.000
questioned
Token questioned
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.370
later
Token later
Feature activation+0.300
attacked
Token attacked
Feature activation+0.000
,
Token,
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
going
Token going
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.104
keep
Token keep
Feature activation+0.472
working
Token working
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
way
Token way
Feature activation+0.000

INTERVAL 0.000 - 0.327
CONTAINS 99.879%

support
Token support
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
actions
Token actions
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
day
Token day
Feature activation+0.000
are
Token are
Feature activation+0.000
disgusting
Token disgusting
Feature activation+0.000
,
Token,
Feature activation+0.000
group
Token group
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
heroes
Token heroes
Feature activation+0.000
locked
Token locked
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
rural
Token rural
Feature activation+0.000
farming
Token farming
Feature activation+0.000
town
Token town
Feature activation+0.000
,
Token,
Feature activation+0.000
disgusting
Token disgusting
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Weiss
TokenWeiss
Feature activation+0.000
let
Token let
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
deep
Token deep
Feature activation+0.000
sigh
Token sigh
Feature activation+0.000
as
Token as
Feature activation+0.000
she
Token she
Feature activation+0.000
finally
Token finally
Feature activation+0.000
reached
Token reached
Feature activation+0.000
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.000
attention
Token attention
Feature activation+0.000
-
Token-
Feature activation+0.000
seeking
Tokenseeking
Feature activation+0.000
rabbit
Token rabbit
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
say
Token say
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