H3.6 top features

Top feature 0 in H3.6: (feature 6799)

TOP ACTIVATIONS
MAX = 4.037

lé
Tokenlé
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.530
biggest
Token biggest
Feature activation+4.037
bott
Token bott
Feature activation+1.724
ler
Tokenler
Feature activation+1.844
of
Token of
Feature activation+0.997
water
Token water
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
court
Token court
Feature activation+0.000
upheld
Token upheld
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.406
toughest
Token toughest
Feature activation+3.977
tobacco
Token tobacco
Feature activation+0.000
law
Token law
Feature activation+0.359
on
Token on
Feature activation+0.983
Wednesday
Token Wednesday
Feature activation+0.858
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.261
Ļ
TokenĻ
Feature activation+1.227
s
Tokens
Feature activation+0.659
biggest
Token biggest
Feature activation+3.650
charitable
Token charitable
Feature activation+1.181
group
Token group
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
Harvey
Token Harvey
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.158
first
Token first
Feature activation+3.573
child
Token child
Feature activation+0.573
to
Token to
Feature activation+0.363
receive
Token receive
Feature activation+0.104
a
Token a
Feature activation+0.000
bilateral
Token bilateral
Feature activation+0.000
ME
TokenME
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.128
largest
Token largest
Feature activation+3.505
futures
Token futures
Feature activation+0.656
exchange
Token exchange
Feature activation+0.535
,
Token,
Feature activation+0.055
and
Token and
Feature activation+0.153
its
Token its
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.767
most
Token most
Feature activation+3.449
str
Token str
Feature activation+0.000
ident
Tokenident
Feature activation+2.707
atheists
Token atheists
Feature activation+0.309
commun
Token commun
Feature activation+0.000
ed
Tokened
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.392
s
Tokens
Feature activation+1.050
second
Token second
Feature activation+1.018
-
Token-
Feature activation+0.000
big
Tokenbig
Feature activation+0.569
gest
Tokengest
Feature activation+3.360
economy
Token economy
Feature activation+1.111
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.858
most
Token most
Feature activation+3.341
advanced
Token advanced
Feature activation+2.110
economies
Token economies
Feature activation+0.336
,
Token,
Feature activation+0.176
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.496
`
Token`
Feature activation+1.252
s
Tokens
Feature activation+1.900
two
Token two
Feature activation+1.566
largest
Token largest
Feature activation+3.324
economies
Token economies
Feature activation+1.003
as
Token as
Feature activation+0.000
President
Token President
Feature activation+0.000
Xi
Token Xi
Feature activation+0.000
Jinping
Token Jinping
Feature activation+0.000
UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Unless
Token Unless
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.047
sees
Token sees
Feature activation+3.322
a
Token a
Feature activation+1.183
second
Token second
Feature activation+0.223
green
Token green
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
,
Token,
Feature activation+0.205
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.093
âĢ
TokenâĢ
Feature activation+0.567
Ļ
TokenĻ
Feature activation+1.282
s
Tokens
Feature activation+0.529
largest
Token largest
Feature activation+3.321
brewer
Token brewer
Feature activation+1.793
,
Token,
Feature activation+0.000
An
Token An
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
user
Tokenuser
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.066
confronts
Token confronts
Feature activation+3.293
global
Token global
Feature activation+0.688
warming
Token warming
Feature activation+0.124
,
Token,
Feature activation+0.056
fossil
Token fossil
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
onis
Tokenonis
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.572
greatest
Token greatest
Feature activation+3.288
all
Token all
Feature activation+0.776
rounder
Tokenrounder
Feature activation+0.236
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.697
Ļ
TokenĻ
Feature activation+1.435
s
Tokens
Feature activation+0.633
largest
Token largest
Feature activation+3.284
crowdfunding
Token crowdfunding
Feature activation+0.000
to
Token to
Feature activation+0.000
date
Token date
Feature activation+0.208
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.000
accused
Token accused
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.379
body
Token body
Feature activation+3.282
of
Token of
Feature activation+1.871
not
Token not
Feature activation+0.144
consulting
Token consulting
Feature activation+1.563
with
Token with
Feature activation+0.599
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.151
forg
Token forg
Feature activation+2.614
ets
Tokenets
Feature activation+3.227
the
Token the
Feature activation+0.613
images
Token images
Feature activation+0.086
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
children
Token children
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.986
Ļ
TokenĻ
Feature activation+2.349
s
Tokens
Feature activation+1.674
oldest
Token oldest
Feature activation+3.213
Islamist
Token Islamist
Feature activation+0.451
organisation
Token organisation
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
interference
Token interference
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.064
Ļ
TokenĻ
Feature activation+0.061
s
Tokens
Feature activation+0.192
biggest
Token biggest
Feature activation+3.211
seed
Token seed
Feature activation+0.000
makers
Token makers
Feature activation+0.000
,
Token,
Feature activation+0.000
Sy
Token Sy
Feature activation+0.000
ng
Tokenng
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.550
largest
Token largest
Feature activation+3.203
weapons
Token weapons
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Trident
Token Trident
Feature activation+0.000
.
Token.
Feature activation+0.000
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
saw
Token saw
Feature activation+3.197
Ferguson
Token Ferguson
Feature activation+0.000
Police
Token Police
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000

Top DFA by src position
MAX = 4.632

N
TokenN
Feature activation+0.001
Top resid features:
est
Tokenest
Feature activation+0.012
Top resid features:
lé
Tokenlé
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.210
Top resid features:
world
Token world
Feature activation+4.632
Top resid features:
's
Token's
Feature activation+0.322
Top resid features:
biggest
Token biggest
Feature activation+0.042
Top resid features:
bott
Token bott
Feature activation+0.000
Top resid features:
ler
Tokenler
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.026
Top resid features:
highest
Token highest
Feature activation-0.013
Top resid features:
court
Token court
Feature activation-0.041
Top resid features:
upheld
Token upheld
Feature activation+0.184
Top resid features:
the
Token the
Feature activation+0.249
Top resid features:
world
Token world
Feature activation+4.444
Top resid features:
's
Token's
Feature activation+0.283
Top resid features:
toughest
Token toughest
Feature activation+0.095
Top resid features:
tobacco
Token tobacco
Feature activation+0.000
Top resid features:
law
Token law
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
B
Token B
Feature activation-0.003
Top resid features:
MG
TokenMG
Feature activation+0.009
Top resid features:
F
TokenF
Feature activation-0.006
Top resid features:
is
Token is
Feature activation+0.072
Top resid features:
the
Token the
Feature activation+0.258
Top resid features:
world
Token world
Feature activation+4.100
Top resid features:
âĢ
TokenâĢ
Feature activation+0.136
Top resid features:
Ļ
TokenĻ
Feature activation+0.124
Top resid features:
s
Tokens
Feature activation+0.175
Top resid features:
biggest
Token biggest
Feature activation-0.002
Top resid features:
charitable
Token charitable
Feature activation+0.000
Top resid features:
old
Tokenold
Feature activation-0.005
Top resid features:
Zion
Token Zion
Feature activation-0.017
Top resid features:
Harvey
Token Harvey
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.100
Top resid features:
the
Token the
Feature activation+0.123
Top resid features:
world
Token world
Feature activation+4.084
Top resid features:
's
Token's
Feature activation+0.448
Top resid features:
first
Token first
Feature activation+0.049
Top resid features:
child
Token child
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
receive
Token receive
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
C
Token C
Feature activation-0.019
Top resid features:
ME
TokenME
Feature activation-0.022
Top resid features:
,
Token,
Feature activation+0.096
Top resid features:
the
Token the
Feature activation+0.268
Top resid features:
world
Token world
Feature activation+4.159
Top resid features:
's
Token's
Feature activation+0.309
Top resid features:
largest
Token largest
Feature activation+0.004
Top resid features:
futures
Token futures
Feature activation+0.000
Top resid features:
exchange
Token exchange
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Yes
Token Yes
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.088
Top resid features:
one
Token one
Feature activation+0.034
Top resid features:
of
Token of
Feature activation-0.055
Top resid features:
the
Token the
Feature activation+0.146
Top resid features:
world
Token world
Feature activation+4.142
Top resid features:
's
Token's
Feature activation+0.263
Top resid features:
most
Token most
Feature activation+0.063
Top resid features:
str
Token str
Feature activation+0.000
Top resid features:
ident
Tokenident
Feature activation+0.000
Top resid features:
atheists
Token atheists
Feature activation+0.000
Top resid features:
put
Token put
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
brakes
Token brakes
Feature activation-0.004
Top resid features:
on
Token on
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.060
Top resid features:
world
Token world
Feature activation+4.101
Top resid features:
âĢ
TokenâĢ
Feature activation+0.128
Top resid features:
Ļ
TokenĻ
Feature activation+0.237
Top resid features:
s
Tokens
Feature activation+0.038
Top resid features:
second
Token second
Feature activation+0.109
Top resid features:
-
Token-
Feature activation+0.035
Top resid features:
"
Token"
Feature activation+0.001
Top resid features:
As
TokenAs
Feature activation+0.080
Top resid features:
one
Token one
Feature activation+0.024
Top resid features:
of
Token of
Feature activation-0.027
Top resid features:
the
Token the
Feature activation+0.134
Top resid features:
world
Token world
Feature activation+4.002
Top resid features:
's
Token's
Feature activation+0.281
Top resid features:
most
Token most
Feature activation+0.072
Top resid features:
advanced
Token advanced
Feature activation+0.000
Top resid features:
economies
Token economies
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ant
Tokenant
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.039
Top resid features:
relations
Token relations
Feature activation-0.029
Top resid features:
between
Token between
Feature activation+0.140
Top resid features:
the
Token the
Feature activation+0.126
Top resid features:
world
Token world
Feature activation+3.855
Top resid features:
`
Token`
Feature activation+0.062
Top resid features:
s
Tokens
Feature activation+0.156
Top resid features:
two
Token two
Feature activation+0.198
Top resid features:
largest
Token largest
Feature activation-0.056
Top resid features:
economies
Token economies
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
UK
Token UK
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
Unless
Token Unless
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.285
Top resid features:
world
Token world
Feature activation+4.061
Top resid features:
sees
Token sees
Feature activation+0.100
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
green
Token green
Feature activation+0.000
Top resid features:
revolution
Token revolution
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
heels
Token heels
Feature activation+0.033
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
world
Token world
Feature activation+4.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.157
Top resid features:
Ļ
TokenĻ
Feature activation+0.108
Top resid features:
s
Tokens
Feature activation+0.155
Top resid features:
largest
Token largest
Feature activation-0.002
Top resid features:
brewer
Token brewer
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
which
Token which
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.132
Top resid features:
as
Token as
Feature activation+0.138
Top resid features:
the
Token the
Feature activation+0.221
Top resid features:
world
Token world
Feature activation+3.966
Top resid features:
confronts
Token confronts
Feature activation+0.070
Top resid features:
global
Token global
Feature activation+0.000
Top resid features:
warming
Token warming
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
fossil
Token fossil
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.016
Top resid features:
Ad
Token Ad
Feature activation-0.009
Top resid features:
onis
Tokenonis
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.124
Top resid features:
the
Token the
Feature activation+0.147
Top resid features:
world
Token world
Feature activation+3.822
Top resid features:
's
Token's
Feature activation+0.402
Top resid features:
greatest
Token greatest
Feature activation+0.087
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
rounder
Tokenrounder
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
contracts
Token contracts
Feature activation-0.019
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
rapidly
Token rapidly
Feature activation+0.015
Top resid features:
became
Token became
Feature activation+0.084
Top resid features:
the
Token the
Feature activation+0.156
Top resid features:
world
Token world
Feature activation+3.862
Top resid features:
âĢ
TokenâĢ
Feature activation+0.152
Top resid features:
Ļ
TokenĻ
Feature activation+0.180
Top resid features:
s
Tokens
Feature activation+0.153
Top resid features:
largest
Token largest
Feature activation-0.011
Top resid features:
crowdfunding
Token crowdfunding
Feature activation+0.000
Top resid features:
Yemeni
Token Yemeni
Feature activation-0.022
Top resid features:
government
Token government
Feature activation-0.063
Top resid features:
and
Token and
Feature activation+0.065
Top resid features:
accused
Token accused
Feature activation+0.095
Top resid features:
the
Token the
Feature activation+0.183
Top resid features:
world
Token world
Feature activation+4.348
Top resid features:
body
Token body
Feature activation-0.049
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
consulting
Token consulting
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.016
Top resid features:
this
Token this
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.093
Top resid features:
eventually
Token eventually
Feature activation-0.041
Top resid features:
the
Token the
Feature activation+0.265
Top resid features:
world
Token world
Feature activation+3.912
Top resid features:
forg
Token forg
Feature activation+0.088
Top resid features:
ets
Tokenets
Feature activation+0.062
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
images
Token images
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
Muslim
Token Muslim
Feature activation-0.023
Top resid features:
Brotherhood
Token Brotherhood
Feature activation-0.043
Top resid features:
-
Token -
Feature activation+0.106
Top resid features:
the
Token the
Feature activation+0.177
Top resid features:
world
Token world
Feature activation+3.819
Top resid features:
âĢ
TokenâĢ
Feature activation+0.138
Top resid features:
Ļ
TokenĻ
Feature activation+0.094
Top resid features:
s
Tokens
Feature activation+0.148
Top resid features:
oldest
Token oldest
Feature activation+0.039
Top resid features:
Islamist
Token Islamist
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
Two
TokenTwo
Feature activation+0.140
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
world
Token world
Feature activation+3.806
Top resid features:
âĢ
TokenâĢ
Feature activation+0.086
Top resid features:
Ļ
TokenĻ
Feature activation+0.201
Top resid features:
s
Tokens
Feature activation+0.151
Top resid features:
biggest
Token biggest
Feature activation-0.012
Top resid features:
seed
Token seed
Feature activation+0.000
Top resid features:
Martin
Token Martin
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.138
Top resid features:
one
Token one
Feature activation+0.032
Top resid features:
of
Token of
Feature activation-0.037
Top resid features:
the
Token the
Feature activation+0.125
Top resid features:
world
Token world
Feature activation+4.013
Top resid features:
's
Token's
Feature activation+0.138
Top resid features:
largest
Token largest
Feature activation+0.010
Top resid features:
weapons
Token weapons
Feature activation+0.000
Top resid features:
manufacturers
Token manufacturers
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Aug
Token Aug
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.070
Top resid features:
the
Token the
Feature activation+0.111
Top resid features:
world
Token world
Feature activation+4.033
Top resid features:
saw
Token saw
Feature activation+0.135
Top resid features:
Ferguson
Token Ferguson
Feature activation+0.000
Top resid features:
Police
Token Police
Feature activation+0.000
Top resid features:
Chief
Token Chief
Feature activation+0.000
Top resid features:
Thomas
Token Thomas
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.07

Head 3: 0.04

Head 4: 0.02

Head 5: 0.05

Head 6: 0.47

Head 7: 0.11

Head 8: 0.03

Head 9: 0.04

Head 10: 0.06

Head 11: 0.05

Positive logits

Consortium1.50

Summit1.28

heid1.24

Colomb1.24

istani1.22

Glob1.22

Arab1.21

Babel1.20

Columb1.20

Tire1.20

industrialized1.19

joice1.18

franc1.18

paved1.17

Hug1.17

istan1.16

Cup1.16

Expo1.15

watchdog1.13

reckoning1.13

Negative logits

tesy-1.42

tein-1.41

utsu-1.34

xtap-1.33

caut-1.32

ooters-1.23

:[-1.21

opsis-1.20

��-1.20

boa-1.19

utterstock-1.19

-1.19

{"-1.19

chan-1.19

oldemort-1.13

-1.13

ranch-1.11

deletion-1.08

incent-1.08

combe-1.08

INTERVAL 3.634 - 4.037
CONTAINS 0.000%

the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.261
Ļ
TokenĻ
Feature activation+1.227
s
Tokens
Feature activation+0.659
biggest
Token biggest
Feature activation+3.650
charitable
Token charitable
Feature activation+1.181
group
Token group
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
court
Token court
Feature activation+0.000
upheld
Token upheld
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.406
toughest
Token toughest
Feature activation+3.977
tobacco
Token tobacco
Feature activation+0.000
law
Token law
Feature activation+0.359
on
Token on
Feature activation+0.983
Wednesday
Token Wednesday
Feature activation+0.858
.
Token.
Feature activation+0.000
lé
Tokenlé
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.530
biggest
Token biggest
Feature activation+4.037
bott
Token bott
Feature activation+1.724
ler
Tokenler
Feature activation+1.844
of
Token of
Feature activation+0.997
water
Token water
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000

INTERVAL 3.230 - 3.634
CONTAINS 0.001%

UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Unless
Token Unless
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.047
sees
Token sees
Feature activation+3.322
a
Token a
Feature activation+1.183
second
Token second
Feature activation+0.223
green
Token green
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
,
Token,
Feature activation+0.205
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.767
most
Token most
Feature activation+3.449
str
Token str
Feature activation+0.000
ident
Tokenident
Feature activation+2.707
atheists
Token atheists
Feature activation+0.309
commun
Token commun
Feature activation+0.000
ed
Tokened
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.066
confronts
Token confronts
Feature activation+3.293
global
Token global
Feature activation+0.688
warming
Token warming
Feature activation+0.124
,
Token,
Feature activation+0.056
fossil
Token fossil
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
onis
Tokenonis
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.572
greatest
Token greatest
Feature activation+3.288
all
Token all
Feature activation+0.776
rounder
Tokenrounder
Feature activation+0.236
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.697
Ļ
TokenĻ
Feature activation+1.435
s
Tokens
Feature activation+0.633
largest
Token largest
Feature activation+3.284
crowdfunding
Token crowdfunding
Feature activation+0.000
to
Token to
Feature activation+0.000
date
Token date
Feature activation+0.208
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.826 - 3.230
CONTAINS 0.001%

fury
Token fury
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+1.041
has
Token has
Feature activation+2.669
never
Token never
Feature activation+2.953
seen
Token seen
Feature activation+2.969
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Analysis
TokenAnalysis
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.449
Ļ
TokenĻ
Feature activation+1.778
s
Tokens
Feature activation+0.230
largest
Token largest
Feature activation+3.174
dat
Token dat
Feature activation+0.000
acent
Tokenacent
Feature activation+0.000
ers
Tokeners
Feature activation+0.189
,
Token,
Feature activation+0.017
aka
Token aka
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.258
âĢ
TokenâĢ
Feature activation+0.702
Ļ
TokenĻ
Feature activation+1.530
s
Tokens
Feature activation+0.813
leading
Token leading
Feature activation+3.143
producer
Token producer
Feature activation+1.931
of
Token of
Feature activation+0.000
counterfeit
Token counterfeit
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.986
Ļ
TokenĻ
Feature activation+2.349
s
Tokens
Feature activation+1.674
oldest
Token oldest
Feature activation+3.213
Islamist
Token Islamist
Feature activation+0.451
organisation
Token organisation
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
interference
Token interference
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.550
largest
Token largest
Feature activation+3.203
weapons
Token weapons
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Trident
Token Trident
Feature activation+0.000

INTERVAL 2.422 - 2.826
CONTAINS 0.002%

as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
gets
Token gets
Feature activation+1.478
ready
Token ready
Feature activation+2.712
to
Token to
Feature activation+2.472
(
Token (
Feature activation+0.000
maybe
Tokenmaybe
Feature activation+0.000
)
Token)
Feature activation+0.000
R
Token R
Feature activation+0.000
umblr
Tokenumblr
Feature activation+0.000
industry
Token industry
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+2.177
truly
Token truly
Feature activation+2.646
changed
Token changed
Feature activation+2.524
.
Token.
Feature activation+0.409
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+2.177
truly
Token truly
Feature activation+2.646
changed
Token changed
Feature activation+2.524
.
Token.
Feature activation+0.409
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
and
Token and
Feature activation+0.000
fury
Token fury
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+1.041
has
Token has
Feature activation+2.669
never
Token never
Feature activation+2.953
seen
Token seen
Feature activation+2.969
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
est
Tokenest
Feature activation+0.000
lé
Tokenlé
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.530
biggest
Token biggest
Feature activation+4.037
bott
Token bott
Feature activation+1.724
ler
Tokenler
Feature activation+1.844
of
Token of
Feature activation+0.997
water
Token water
Feature activation+0.000

INTERVAL 2.019 - 2.422
CONTAINS 0.004%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
World
TokenWorld
Feature activation+0.070
leaders
Token leaders
Feature activation+1.915
condemned
Token condemned
Feature activation+2.197
the
Token the
Feature activation+0.126
proposal
Token proposal
Feature activation+0.000
,
Token,
Feature activation+0.000
prompting
Token prompting
Feature activation+0.000
some
Token some
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.872
oldest
Token oldest
Feature activation+2.126
maps
Token maps
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
after
Token after
Feature activation+0.000
world
Token world
Feature activation+0.896
powers
Token powers
Feature activation+2.376
agreed
Token agreed
Feature activation+2.383
on
Token on
Feature activation+1.140
the
Token the
Feature activation+0.603
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
cess
Tokencess
Feature activation+0.000
that
Token that
Feature activation+0.000
America
Token America
Feature activation+0.000
remains
Token remains
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.454
standard
Token standard
Feature activation+2.371
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
drivers
Token drivers
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
prepares
Token prepares
Feature activation+2.360
for
Token for
Feature activation+1.713
the
Token the
Feature activation+0.501
coming
Token coming
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.615 - 2.019
CONTAINS 0.006%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
World
TokenWorld
Feature activation+0.069
âĢ
TokenâĢ
Feature activation+1.256
Ļ
TokenĻ
Feature activation+1.716
s
Tokens
Feature activation+0.777
most
Token most
Feature activation+1.017
dreaded
Token dreaded
Feature activation+1.156
terrorist
Token terrorist
Feature activation+0.244
organisation
Token organisation
Feature activation+0.265
ranked
Token ranked
Feature activation+0.000
seventh
Token seventh
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.229
in
Token in
Feature activation+1.938
competition
Token competition
Feature activation+0.825
lead
Token lead
Feature activation+0.000
climbing
Token climbing
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
prepares
Token prepares
Feature activation+2.360
for
Token for
Feature activation+1.713
the
Token the
Feature activation+0.501
coming
Token coming
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
driver
Token driver
Feature activation+0.000
lion
Token lion
Feature activation+0.000
captured
Token captured
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.383
imagination
Token imagination
Feature activation+1.861
in
Token in
Feature activation+1.621
this
Token this
Feature activation+0.325
way
Token way
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
for
Token for
Feature activation+0.000
geries
Tokengeries
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.594
over
Token over
Feature activation+1.882
.
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

INTERVAL 1.211 - 1.615
CONTAINS 0.008%

told
Token told
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
that
Token that
Feature activation+1.244
Iran
Token Iran
Feature activation+0.000
had
Token had
Feature activation+0.000
met
Token met
Feature activation+0.000
its
Token its
Feature activation+0.000
commitments
Token commitments
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.103
âĢ
TokenâĢ
Feature activation+0.385
Ļ
TokenĻ
Feature activation+0.611
s
Tokens
Feature activation+0.730
banking
Token banking
Feature activation+1.356
sector
Token sector
Feature activation+0.333
eventually
Token eventually
Feature activation+0.000
hit
Token hit
Feature activation+0.000
Cyprus
Token Cyprus
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.385
Ļ
TokenĻ
Feature activation+0.636
s
Tokens
Feature activation+0.416
best
Token best
Feature activation+1.351
fighters
Token fighters
Feature activation+0.279
and
Token and
Feature activation+0.000
bombers
Token bombers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
prank
Token prank
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
over
Token over
Feature activation+1.392
,
Token,
Feature activation+0.000
meet
Token meet
Feature activation+0.143
your
Token your
Feature activation+0.000
new
Token new
Feature activation+0.000
god
Token god
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.360
Ļ
TokenĻ
Feature activation+1.704
s
Tokens
Feature activation+1.199
gone
Token gone
Feature activation+1.824
crazy
Token crazy
Feature activation+0.504
!
Token!
Feature activation+0.000

INTERVAL 0.807 - 1.211
CONTAINS 0.013%

data
Token data
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
World
Token World
Feature activation+0.648
Health
Token Health
Feature activation+1.282
Organization
Token Organization
Feature activation+0.977
(
Token (
Feature activation+0.000
WHO
TokenWHO
Feature activation+0.000
),
Token),
Feature activation+0.000
6
Token 6
Feature activation+0.000
32
Token32
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
after
Token after
Feature activation+0.000
world
Token world
Feature activation+0.896
powers
Token powers
Feature activation+2.376
agreed
Token agreed
Feature activation+2.383
on
Token on
Feature activation+1.140
the
Token the
Feature activation+0.603
âĢ
Token âĢ
Feature activation+0.000
i
Tokeni
Feature activation+0.000
means
Token means
Feature activation+0.000
"
Token "
Feature activation+0.000
world
Tokenworld
Feature activation+0.000
map
Token map
Feature activation+0.626
"
Token"
Feature activation+0.875
in
Token in
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Here
TokenHere
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
super
Tokensuper
Feature activation+0.000
world
Token world
Feature activation+0.000
church
Token church
Feature activation+1.071
âĢ
TokenâĢ
Feature activation+0.125
Ŀ
TokenĿ
Feature activation+0.881
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
rugby
Token rugby
Feature activation+0.000
world
Token world
Feature activation+0.007
are
Token are
Feature activation+0.886
sure
Token sure
Feature activation+1.109
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
treated
Token treated
Feature activation+0.000
to
Token to
Feature activation+0.000
another
Token another
Feature activation+0.000

INTERVAL 0.404 - 0.807
CONTAINS 0.026%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+1.572
greatest
Token greatest
Feature activation+3.288
all
Token all
Feature activation+0.776
rounder
Tokenrounder
Feature activation+0.236
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
kindness
Token kindness
Feature activation+0.000
is
Token is
Feature activation+0.000
gone
Token gone
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.419
!"
Token!"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
No
TokenNo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.093
âĢ
TokenâĢ
Feature activation+0.567
Ļ
TokenĻ
Feature activation+1.282
s
Tokens
Feature activation+0.529
largest
Token largest
Feature activation+3.321
brewer
Token brewer
Feature activation+1.793
,
Token,
Feature activation+0.000
An
Token An
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
y
Tokeny
Feature activation+0.000
comments
Token comments
Feature activation+0.000
about
Token about
Feature activation+0.000
weak
Token weak
Feature activation+0.000
global
Token global
Feature activation+0.000
growth
Token growth
Feature activation+0.569
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
International
Token International
Feature activation+0.000
Monetary
Token Monetary
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.445
Ļ
TokenĻ
Feature activation+1.073
s
Tokens
Feature activation+0.599
economic
Token economic
Feature activation+1.201
superpower
Token superpower
Feature activation+0.466
was
Token was
Feature activation+0.000
established
Token established
Feature activation+0.209
in
Token in
Feature activation+0.021
the
Token the
Feature activation+0.000
period
Token period
Feature activation+0.000

INTERVAL 0.000 - 0.404
CONTAINS 99.940%

assist
Token assist
Feature activation+0.000
in
Token in
Feature activation+0.000
disease
Token disease
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
played
Token played
Feature activation+0.000
Last
Token Last
Feature activation+0.000
25
Token 25
Feature activation+0.000
25
Token 25
Feature activation+0.000
Next
Token Next
Feature activation+0.000
>>>
Token >>>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
Name
Token Name
Feature activation+0.000
Style
Token Style
Feature activation+0.000
Stock
Token Stock
Feature activation+0.000
wired
Tokenwired
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
similar
Token similar
Feature activation+0.000
ways
Token ways
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
some
Token some
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
have
Token have
Feature activation+0.000
The
Token The
Feature activation+0.000
SM
Token SM
Feature activation+0.000
ART
TokenART
Feature activation+0.000
reactor
Token reactor
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
design
Token design
Feature activation+0.000
that
Token that
Feature activation+0.000
uses
Token uses
Feature activation+0.000
integral
Token integral
Feature activation+0.000
steam
Token steam
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
Dozens
Token Dozens
Feature activation+0.000
of
Token of
Feature activation+0.000
fame
Token fame
Feature activation+0.000
-
Token-
Feature activation+0.000
obs
Tokenobs
Feature activation+0.000
essed
Tokenessed
Feature activation+0.000
teens
Token teens
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H3.6: (feature 5383)

TOP ACTIVATIONS
MAX = 3.060

it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.000
day
Token day
Feature activation+0.283
at
Token at
Feature activation+0.000
a
Token a
Feature activation+1.278
time
Token time
Feature activation+3.060
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+1.418
have
Token have
Feature activation+1.067
to
Token to
Feature activation+2.115
wonder
Token wonder
Feature activation+2.770
if
Token if
Feature activation+1.719
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
had
Token had
Feature activation+0.000
truly
Token truly
Feature activation+0.000
libraries
Token libraries
Feature activation+0.000
has
Token has
Feature activation+0.000
one
Token one
Feature activation+0.000
library
Token library
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+2.652
19
Token 19
Feature activation+0.665
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.000
taking
Token taking
Feature activation+0.000
things
Token things
Feature activation+0.000
one
Token one
Feature activation+0.000
step
Token step
Feature activation+0.000
at
Token at
Feature activation+1.015
time
Token time
Feature activation+2.633
-
Token -
Feature activation+0.000
first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
full
Token full
Feature activation+0.000
everything
Token everything
Feature activation+0.000
else
Token else
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
can
Token can
Feature activation+1.311
blame
Token blame
Feature activation+2.548
the
Token the
Feature activation+0.000
conspir
Token conspir
Feature activation+0.000
atorial
Tokenatorial
Feature activation+0.000
blogs
Token blogs
Feature activation+0.125
...
Token...
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
can
Token can
Feature activation+0.986
only
Token only
Feature activation+2.467
imagine
Token imagine
Feature activation+2.012
the
Token the
Feature activation+0.172
stories
Token stories
Feature activation+0.570
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.029
âĢ
TokenâĢ
Feature activation+0.120
Ļ
TokenĻ
Feature activation+0.427
s
Tokens
Feature activation+1.666
per
Token per
Feature activation+2.387
verted
Tokenverted
Feature activation+0.000
,
Token,
Feature activation+0.000
pr
Token pr
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ient
Tokenient
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.027
man
Token man
Feature activation+0.104
in
Token in
Feature activation+0.000
a
Token a
Feature activation+1.299
thousand
Token thousand
Feature activation+2.372
who
Token who
Feature activation+0.000
cares
Token cares
Feature activation+0.000
a
Token a
Feature activation+0.000
rap
Token rap
Feature activation+0.000
about
Token about
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
must
Token must
Feature activation+1.676
also
Token also
Feature activation+1.468
wonder
Token wonder
Feature activation+2.328
when
Token when
Feature activation+0.494
there
Token there
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
ad
Token ad
Feature activation+0.000
key
Token key
Feature activation+0.000
times
Token times
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.062
's
Token's
Feature activation+0.965
life
Token life
Feature activation+2.327
,
Token,
Feature activation+0.077
using
Token using
Feature activation+0.000
materials
Token materials
Feature activation+0.245
of
Token of
Feature activation+0.000
personal
Token personal
Feature activation+0.000
absence
Token absence
Feature activation+0.000
where
Token where
Feature activation+0.000
one
Token one
Feature activation+0.132
would
Token would
Feature activation+1.070
otherwise
Token otherwise
Feature activation+1.180
expect
Token expect
Feature activation+2.308
to
Token to
Feature activation+1.818
find
Token find
Feature activation+2.092
a
Token a
Feature activation+0.445
something
Token something
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
one
Token one
Feature activation+0.000
cannot
Token cannot
Feature activation+1.003
see
Token see
Feature activation+2.304
the
Token the
Feature activation+0.540
rich
Token rich
Feature activation+0.000
diversity
Token diversity
Feature activation+0.000
in
Token in
Feature activation+0.000
these
Token these
Feature activation+0.000
from
Token from
Feature activation+0.000
farmers
Token farmers
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
could
Token could
Feature activation+1.197
imagine
Token imagine
Feature activation+2.261
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
one
Token one
Feature activation+0.000
things
Token things
Feature activation+0.591
for
Token for
Feature activation+1.148
sure
Token sure
Feature activation+2.251
âĢĵ
TokenâĢĵ
Feature activation+0.000
while
Tokenwhile
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
pain
Token pain
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+1.468
expect
Token expect
Feature activation+2.248
were
Token were
Feature activation+0.290
strong
Token strong
Feature activation+0.000
acid
Token acid
Feature activation+0.000
dumped
Token dumped
Feature activation+0.000
into
Token into
Feature activation+0.039
purchase
Token purchase
Feature activation+0.000
about
Token about
Feature activation+0.000
one
Token one
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.928
every
Token every
Feature activation+2.246
20
Token 20
Feature activation+0.758
items
Token items
Feature activation+0.000
it
Token it
Feature activation+0.000
recommends
Token recommends
Feature activation+0.000
.
Token.
Feature activation+0.000
church
Token church
Feature activation+0.000
serves
Token serves
Feature activation+0.000
one
Token one
Feature activation+0.000
meal
Token meal
Feature activation+0.282
a
Token a
Feature activation+1.546
day
Token day
Feature activation+2.242
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
sust
Token sust
Feature activation+0.000
ains
Tokenains
Feature activation+0.000
many
Token many
Feature activation+0.000
average
Token average
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.710
every
Token every
Feature activation+2.219
four
Token four
Feature activation+1.203
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.526
one
Token one
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
one
Token one
Feature activation+0.000
could
Token could
Feature activation+0.990
almost
Token almost
Feature activation+1.508
hear
Token hear
Feature activation+2.146
the
Token the
Feature activation+0.055
sound
Token sound
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.113
billion
Token billion
Feature activation+0.000
library
Token library
Feature activation+0.000
,
Token,
Feature activation+0.000
providing
Token providing
Feature activation+0.000
one
Token one
Feature activation+0.000
function
Token function
Feature activation+0.794
per
Token per
Feature activation+2.137
HTML
Token HTML
Feature activation+0.000
5
Token5
Feature activation+0.000
element
Token element
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000

Top DFA by src position
MAX = 3.020

just
Token just
Feature activation+0.016
Top resid features:
going
Token going
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
take
Token take
Feature activation+0.013
Top resid features:
it
Token it
Feature activation-0.015
Top resid features:
one
Token one
Feature activation+3.020
Top resid features:
day
Token day
Feature activation+0.067
Top resid features:
at
Token at
Feature activation+0.357
Top resid features:
a
Token a
Feature activation+0.099
Top resid features:
time
Token time
Feature activation+0.043
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.127
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
one
Token one
Feature activation+3.005
Top resid features:
would
Token would
Feature activation+0.013
Top resid features:
have
Token have
Feature activation+0.093
Top resid features:
to
Token to
Feature activation+0.091
Top resid features:
wonder
Token wonder
Feature activation+0.010
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
500
Token500
Feature activation-0.033
Top resid features:
public
Token public
Feature activation-0.001
Top resid features:
libraries
Token libraries
Feature activation+0.003
Top resid features:
has
Token has
Feature activation+0.043
Top resid features:
one
Token one
Feature activation+2.801
Top resid features:
library
Token library
Feature activation+0.084
Top resid features:
for
Token for
Feature activation+0.208
Top resid features:
every
Token every
Feature activation+0.057
Top resid features:
19
Token 19
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
case
Token case
Feature activation+0.022
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
taking
Token taking
Feature activation+0.011
Top resid features:
things
Token things
Feature activation+0.014
Top resid features:
one
Token one
Feature activation+2.536
Top resid features:
step
Token step
Feature activation+0.094
Top resid features:
at
Token at
Feature activation+0.510
Top resid features:
time
Token time
Feature activation+0.044
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
for
Token for
Feature activation+0.036
Top resid features:
everything
Token everything
Feature activation+0.007
Top resid features:
else
Token else
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
one
Token one
Feature activation+2.919
Top resid features:
can
Token can
Feature activation+0.025
Top resid features:
blame
Token blame
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
conspir
Token conspir
Feature activation+0.000
Top resid features:
atorial
Tokenatorial
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
One
TokenOne
Feature activation+2.834
Top resid features:
can
Token can
Feature activation+0.061
Top resid features:
only
Token only
Feature activation+0.028
Top resid features:
imagine
Token imagine
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
order
Token order
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.013
Top resid features:
engage
Token engage
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
one
Token one
Feature activation+2.555
Top resid features:
âĢ
TokenâĢ
Feature activation+0.064
Top resid features:
Ļ
TokenĻ
Feature activation+0.054
Top resid features:
s
Tokens
Feature activation+0.070
Top resid features:
per
Token per
Feature activation+0.069
Top resid features:
verted
Tokenverted
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Where
TokenWhere
Feature activation+0.009
Top resid features:
there
Token there
Feature activation-0.015
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
one
Token one
Feature activation+2.468
Top resid features:
man
Token man
Feature activation+0.064
Top resid features:
in
Token in
Feature activation+0.268
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
thousand
Token thousand
Feature activation+0.079
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
banner
Token banner
Feature activation-0.001
Top resid features:
ad
Token ad
Feature activation+0.003
Top resid features:
industry
Token industry
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.053
Top resid features:
one
Token one
Feature activation+2.655
Top resid features:
must
Token must
Feature activation-0.019
Top resid features:
also
Token also
Feature activation+0.101
Top resid features:
wonder
Token wonder
Feature activation+0.038
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.031
Top resid features:
pinpoint
Token pinpoint
Feature activation+0.031
Top resid features:
key
Token key
Feature activation-0.024
Top resid features:
times
Token times
Feature activation+0.021
Top resid features:
in
Token in
Feature activation+0.030
Top resid features:
one
Token one
Feature activation+2.485
Top resid features:
's
Token's
Feature activation+0.276
Top resid features:
life
Token life
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
using
Token using
Feature activation+0.000
Top resid features:
materials
Token materials
Feature activation+0.000
Top resid features:
time
Token time
Feature activation-0.002
Top resid features:
establishing
Token establishing
Feature activation-0.012
Top resid features:
an
Token an
Feature activation+0.033
Top resid features:
absence
Token absence
Feature activation+0.016
Top resid features:
where
Token where
Feature activation+0.077
Top resid features:
one
Token one
Feature activation+2.566
Top resid features:
would
Token would
Feature activation-0.004
Top resid features:
otherwise
Token otherwise
Feature activation+0.040
Top resid features:
expect
Token expect
Feature activation+0.071
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
deep
Tokendeep
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
If
TokenIf
Feature activation-0.016
Top resid features:
one
Token one
Feature activation+2.861
Top resid features:
cannot
Token cannot
Feature activation+0.039
Top resid features:
see
Token see
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
rich
Token rich
Feature activation+0.000
Top resid features:
diversity
Token diversity
Feature activation+0.000
Top resid features:
far
Token far
Feature activation-0.258
Top resid features:
away
Token away
Feature activation-0.015
Top resid features:
from
Token from
Feature activation-0.000
Top resid features:
farmers
Token farmers
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.138
Top resid features:
one
Token one
Feature activation+2.970
Top resid features:
could
Token could
Feature activation-0.012
Top resid features:
imagine
Token imagine
Feature activation-0.023
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
skills
Token skills
Feature activation+0.002
Top resid features:
gap
Token gap
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
But
Token But
Feature activation-0.019
Top resid features:
one
Token one
Feature activation+2.512
Top resid features:
things
Token things
Feature activation+0.139
Top resid features:
for
Token for
Feature activation+0.118
Top resid features:
sure
Token sure
Feature activation-0.023
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation+0.000
Top resid features:
while
Tokenwhile
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
kind
Token kind
Feature activation-0.074
Top resid features:
of
Token of
Feature activation-0.017
Top resid features:
pain
Token pain
Feature activation+0.041
Top resid features:
one
Token one
Feature activation+2.724
Top resid features:
would
Token would
Feature activation-0.006
Top resid features:
expect
Token expect
Feature activation+0.061
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
strong
Token strong
Feature activation+0.000
Top resid features:
acid
Token acid
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
we
Token we
Feature activation-0.016
Top resid features:
actually
Token actually
Feature activation-0.026
Top resid features:
purchase
Token purchase
Feature activation-0.005
Top resid features:
about
Token about
Feature activation+0.064
Top resid features:
one
Token one
Feature activation+2.710
Top resid features:
out
Token out
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.063
Top resid features:
every
Token every
Feature activation+0.114
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
items
Token items
Feature activation+0.000
Top resid features:
cafeteria
Token cafeteria
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
The
Token The
Feature activation-0.005
Top resid features:
church
Token church
Feature activation-0.006
Top resid features:
serves
Token serves
Feature activation+0.009
Top resid features:
one
Token one
Feature activation+2.397
Top resid features:
meal
Token meal
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.252
Top resid features:
day
Token day
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
moment
Token moment
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
On
Token On
Feature activation+0.026
Top resid features:
average
Token average
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
one
Token one
Feature activation+2.501
Top resid features:
out
Token out
Feature activation+0.095
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
every
Token every
Feature activation+0.090
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
oot
Tokenoot
Feature activation-0.003
Top resid features:
opia
Tokenopia
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+2.611
Top resid features:
could
Token could
Feature activation-0.007
Top resid features:
almost
Token almost
Feature activation+0.008
Top resid features:
hear
Token hear
Feature activation-0.035
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
sound
Token sound
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.006
Top resid features:
dom
Tokendom
Feature activation-0.003
Top resid features:
library
Token library
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
providing
Token providing
Feature activation-0.041
Top resid features:
one
Token one
Feature activation+2.532
Top resid features:
function
Token function
Feature activation+0.043
Top resid features:
per
Token per
Feature activation+0.083
Top resid features:
HTML
Token HTML
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
element
Token element
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.05

Head 2: 0.06

Head 3: 0.04

Head 4: 0.02

Head 5: 0.04

Head 6: 0.47

Head 7: 0.06

Head 8: 0.05

Head 9: 0.04

Head 10: 0.07

Head 11: 0.07

Positive logits

racuse1.27

subtract1.26

agall1.24

uala1.24

merce1.22

aukee1.14

anten1.11

eph1.11

symp1.09

mobi1.08

ItemLevel1.08

FontSize1.07

ipeg1.06

predicts1.05

dich1.04

mant1.04

DRAG1.04

parity1.03

ufact1.03

cember1.03

Negative logits

Ly-1.38

Jer-1.21

Lock-1.18

leigh-1.15

retch-1.09

approved-1.08

Junk-1.06

Gerr-1.05

Vance-1.04

Cruise-1.04

approved-1.03

ancer-1.02

Scar-1.02

around-1.02

lie-1.01

lie-1.01

Article-1.01

Woods-1.01

Barn-1.01

Dru-1.00

INTERVAL 2.754 - 3.060
CONTAINS 0.000%

,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+1.418
have
Token have
Feature activation+1.067
to
Token to
Feature activation+2.115
wonder
Token wonder
Feature activation+2.770
if
Token if
Feature activation+1.719
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
had
Token had
Feature activation+0.000
truly
Token truly
Feature activation+0.000
it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.000
day
Token day
Feature activation+0.283
at
Token at
Feature activation+0.000
a
Token a
Feature activation+1.278
time
Token time
Feature activation+3.060
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000

INTERVAL 2.448 - 2.754
CONTAINS 0.000%

libraries
Token libraries
Feature activation+0.000
has
Token has
Feature activation+0.000
one
Token one
Feature activation+0.000
library
Token library
Feature activation+0.000
for
Token for
Feature activation+0.000
every
Token every
Feature activation+2.652
19
Token 19
Feature activation+0.665
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
people
Token people
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
One
TokenOne
Feature activation+0.000
can
Token can
Feature activation+0.986
only
Token only
Feature activation+2.467
imagine
Token imagine
Feature activation+2.012
the
Token the
Feature activation+0.172
stories
Token stories
Feature activation+0.570
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+0.000
everything
Token everything
Feature activation+0.000
else
Token else
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
can
Token can
Feature activation+1.311
blame
Token blame
Feature activation+2.548
the
Token the
Feature activation+0.000
conspir
Token conspir
Feature activation+0.000
atorial
Tokenatorial
Feature activation+0.000
blogs
Token blogs
Feature activation+0.125
...
Token...
Feature activation+0.000
taking
Token taking
Feature activation+0.000
things
Token things
Feature activation+0.000
one
Token one
Feature activation+0.000
step
Token step
Feature activation+0.000
at
Token at
Feature activation+1.015
time
Token time
Feature activation+2.633
-
Token -
Feature activation+0.000
first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
full
Token full
Feature activation+0.000

INTERVAL 2.142 - 2.448
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
one
Token one
Feature activation+0.000
cannot
Token cannot
Feature activation+1.003
see
Token see
Feature activation+2.304
the
Token the
Feature activation+0.540
rich
Token rich
Feature activation+0.000
diversity
Token diversity
Feature activation+0.000
in
Token in
Feature activation+0.000
these
Token these
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
one
Token one
Feature activation+0.000
could
Token could
Feature activation+0.990
almost
Token almost
Feature activation+1.508
hear
Token hear
Feature activation+2.146
the
Token the
Feature activation+0.055
sound
Token sound
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.113
billion
Token billion
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
one
Token one
Feature activation+0.000
things
Token things
Feature activation+0.591
for
Token for
Feature activation+1.148
sure
Token sure
Feature activation+2.251
âĢĵ
TokenâĢĵ
Feature activation+0.000
while
Tokenwhile
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
average
Token average
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.710
every
Token every
Feature activation+2.219
four
Token four
Feature activation+1.203
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.526
one
Token one
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
must
Token must
Feature activation+1.676
also
Token also
Feature activation+1.468
wonder
Token wonder
Feature activation+2.328
when
Token when
Feature activation+0.494
there
Token there
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
ad
Token ad
Feature activation+0.000

INTERVAL 1.836 - 2.142
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+1.418
have
Token have
Feature activation+1.067
to
Token to
Feature activation+2.115
wonder
Token wonder
Feature activation+2.770
if
Token if
Feature activation+1.719
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
had
Token had
Feature activation+0.000
library
Token library
Feature activation+0.000
,
Token,
Feature activation+0.000
providing
Token providing
Feature activation+0.000
one
Token one
Feature activation+0.000
function
Token function
Feature activation+0.794
per
Token per
Feature activation+2.137
HTML
Token HTML
Feature activation+0.000
5
Token5
Feature activation+0.000
element
Token element
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
would
Token would
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
might
Token might
Feature activation+1.319
think
Token think
Feature activation+1.930
,
Token,
Feature activation+2.091
be
Token be
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
unstable
Token unstable
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
thing
Token thing
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.221
Ļ
TokenĻ
Feature activation+0.229
s
Tokens
Feature activation+1.215
for
Token for
Feature activation+0.731
sure
Token sure
Feature activation+1.889
,
Token,
Feature activation+0.118
though
Token though
Feature activation+0.434
;
Token;
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
China
Token China
Feature activation+0.000
recently
Token recently
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.116
cannot
Token cannot
Feature activation+1.032
blame
Token blame
Feature activation+1.856
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000

INTERVAL 1.530 - 1.836
CONTAINS 0.005%

was
Token was
Feature activation+0.000
confident
Token confident
Feature activation+0.000
"
Token "
Feature activation+0.000
one
Tokenone
Feature activation+0.000
,
Token,
Feature activation+0.000
maybe
Token maybe
Feature activation+1.833
two
Token two
Feature activation+0.817
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.000
class
Tokenclass
Feature activation+0.000
games
Token games
Feature activation+0.185
great
Token great
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
one
Token one
Feature activation+0.000
could
Token could
Feature activation+0.719
call
Token call
Feature activation+1.619
into
Token into
Feature activation+0.502
question
Token question
Feature activation+0.629
either
Token either
Feature activation+0.411
Father
Token Father
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
felt
Token felt
Feature activation+0.000
like
Token like
Feature activation+0.000
one
Token one
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
appropriation
Token appropriation
Feature activation+0.560
too
Token too
Feature activation+1.563
far
Token far
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
second
Token second
Feature activation+0.000
,
Token,
Feature activation+0.000
el
Tokenel
Feature activation+0.000
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
and
Token and
Feature activation+1.590
one
Token one
Feature activation+0.245
just
Token just
Feature activation+0.228
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
hill
Token hill
Feature activation+0.000
engage
Token engage
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.029
âĢ
TokenâĢ
Feature activation+0.120
Ļ
TokenĻ
Feature activation+0.427
s
Tokens
Feature activation+1.666
per
Token per
Feature activation+2.387
verted
Tokenverted
Feature activation+0.000
,
Token,
Feature activation+0.000
pr
Token pr
Feature activation+0.000
ur
Tokenur
Feature activation+0.000

INTERVAL 1.224 - 1.530
CONTAINS 0.008%

take
Token take
Feature activation+0.000
it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.000
day
Token day
Feature activation+0.283
at
Token at
Feature activation+0.000
a
Token a
Feature activation+1.278
time
Token time
Feature activation+3.060
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
places
Token places
Feature activation+0.000
within
Token within
Feature activation+0.000
one
Token one
Feature activation+0.000
time
Token time
Feature activation+1.327
zone
Token zone
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.089
would
Token would
Feature activation+1.416
be
Token be
Feature activation+0.888
expected
Token expected
Feature activation+1.643
to
Token to
Feature activation+1.418
,
Token,
Feature activation+0.074
the
Token the
Feature activation+0.000
protagonists
Token protagonists
Feature activation+0.000
bluntly
Token bluntly
Feature activation+0.000
speak
Token speak
Feature activation+0.000
nefarious
Token nefarious
Feature activation+0.000
access
Token access
Feature activation+0.000
into
Token into
Feature activation+0.000
one
Token one
Feature activation+0.000
's
Token's
Feature activation+0.831
internal
Token internal
Feature activation+1.486
network
Token network
Feature activation+0.443
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Many
TokenMany
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
registers
Token registers
Feature activation+1.291
it
Token it
Feature activation+0.578
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000

INTERVAL 0.918 - 1.224
CONTAINS 0.013%

position
Token position
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
One
TokenOne
Feature activation+0.029
begins
Token begins
Feature activation+1.044
to
Token to
Feature activation+1.600
get
Token get
Feature activation+1.292
the
Token the
Feature activation+0.873
impression
Token impression
Feature activation+1.517
,
Token,
Feature activation+0.740
one
Token one
Feature activation+0.000
million
Token million
Feature activation+1.336
women
Token women
Feature activation+0.000
experience
Token experience
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.992
one
Token one
Feature activation+0.128
incident
Token incident
Feature activation+0.000
of
Token of
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
effect
Token effect
Feature activation+0.000
of
Token of
Feature activation+0.000
yielding
Token yielding
Feature activation+0.000
one
Token one
Feature activation+0.000
's
Token's
Feature activation+1.024
back
Token back
Feature activation+1.066
and
Token and
Feature activation+0.370
net
Token net
Feature activation+0.000
her
Tokenher
Feature activation+0.000
region
Token region
Feature activation+0.000
to
Token to
Feature activation+0.262
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+0.984
to
Token to
Feature activation+0.853
design
Token design
Feature activation+0.000
a
Token a
Feature activation+0.237
car
Token car
Feature activation+0.841
but
Token but
Feature activation+0.304
caps
Token caps
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
logo
Token logo
Feature activation+0.203
must
Token must
Feature activation+1.081
be
Token be
Feature activation+0.482
chosen
Token chosen
Feature activation+0.000
.
Token.
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
Football
Token Football
Feature activation+0.000

INTERVAL 0.612 - 0.918
CONTAINS 0.028%

one
Token one
Feature activation+0.000
important
Token important
Feature activation+0.000
thing
Token thing
Feature activation+1.045
to
Token to
Feature activation+0.546
remember
Token remember
Feature activation+0.529
:
Token:
Feature activation+0.755
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
are
Token are
Feature activation+0.000
Nazi
Token Nazi
Feature activation+0.000
regime
Token regime
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
one
Token one
Feature activation+0.000
piece
Token piece
Feature activation+0.777
has
Token has
Feature activation+0.000
resur
Token resur
Feature activation+0.000
faced
Tokenfaced
Feature activation+0.000
and
Token and
Feature activation+0.000
found
Token found
Feature activation+0.114
December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.630
southeast
Token southeast
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Di
Token Di
Feature activation+0.000
y
Tokeny
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.342
one
Tokenone
Feature activation+0.000
matchups
Token matchups
Feature activation+0.852
;
Token;
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
other
Token other
Feature activation+0.000
great
Token great
Feature activation+0.000
reports
Token reports
Feature activation+0.000
put
Token put
Feature activation+0.000
one
Token one
Feature activation+0.000
woman
Token woman
Feature activation+0.767
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.728
bike
Token bike
Feature activation+0.322
for
Token for
Feature activation+0.132
every
Token every
Feature activation+2.094
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000

INTERVAL 0.306 - 0.612
CONTAINS 0.056%

.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
is
Token is
Feature activation+0.220
to
Token to
Feature activation+0.757
go
Token go
Feature activation+0.193
to
Token to
Feature activation+0.607
court
Token court
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Cole
Token Cole
Feature activation+0.000
has
Token has
Feature activation+0.000
3
Token3
Feature activation+0.000
)
Token)
Feature activation+0.000
got
Token got
Feature activation+0.000
within
Token within
Feature activation+0.000
one
Token one
Feature activation+0.000
goal
Token goal
Feature activation+0.465
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.352
penalty
Token penalty
Feature activation+0.000
kick
Token kick
Feature activation+0.000
goal
Token goal
Feature activation+0.000
completing
Token completing
Feature activation+0.000
a
Token a
Feature activation+0.000
unit
Token unit
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
in
Token in
Feature activation+0.450
20
Token 20
Feature activation+2.126
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
means
Token means
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
One
TokenOne
Feature activation+0.108
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
questions
Token questions
Feature activation+0.449
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
been
Token been
Feature activation+0.000
central
Token central
Feature activation+0.000
master
Token master
Feature activation+0.000
negotiator
Token negotiator
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.127
contender
Token contender
Feature activation+0.373
who
Token who
Feature activation+0.000
can
Token can
Feature activation+0.000
take
Token take
Feature activation+0.000
charge
Token charge
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.306
CONTAINS 99.886%

his
Token his
Feature activation+0.000
$
Token $
Feature activation+0.000
35
Token35
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
purchase
Token purchase
Feature activation+0.000
with
Token with
Feature activation+0.000
another
Token another
Feature activation+0.000
staffer
Token staffer
Feature activation+0.000
,
Token,
Feature activation+0.000
essentially
Token essentially
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
eliminate
Token eliminate
Feature activation+0.000
Darwin
Token Darwin
Feature activation+0.000
from
Token from
Feature activation+0.000
textbooks
Token textbooks
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
,
Token,
Feature activation+0.000
Y
Token Y
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
deserted
Token deserted
Feature activation+0.000
their
Token their
Feature activation+0.000
units
Token units
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
wars
Token wars
Feature activation+0.000
in
Token in
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
TokenK
Feature activation+0.000
urt
Tokenurt
Feature activation+0.000
Coleman
Token Coleman
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
Safety
Token Safety
Feature activation+0.000
on
Token on
Feature activation+0.000
disagrees
Token disagrees
Feature activation+0.000
and
Token and
Feature activation+0.000
thinks
Token thinks
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
none
Tokennone
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
above
Token above
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H3.6: (feature 1779)

TOP ACTIVATIONS
MAX = 4.000

It
TokenIt
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+4.000
.
Token.
Feature activation+1.017
Try
Token Try
Feature activation+0.000
repeating
Token repeating
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+0.000
k
Tokenk
Feature activation+0.000
gets
Token gets
Feature activation+0.000
even
Token even
Feature activation+0.000
mur
Token mur
Feature activation+0.000
k
Tokenk
Feature activation+0.000
ier
Tokenier
Feature activation+3.976
as
Token as
Feature activation+0.912
we
Token we
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
K
Token K
Feature activation+0.000
iko
Tokeniko
Feature activation+0.000
Alonso
Token Alonso
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
faster
Token faster
Feature activation+3.933
.
Token.
Feature activation+0.088
Really
Token Really
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
fraction
Token fraction
Feature activation+0.000
been
Token been
Feature activation+0.000
lifting
Token lifting
Feature activation+0.000
wages
Token wages
Feature activation+0.000
even
Token even
Feature activation+0.000
faster
Token faster
Feature activation+3.586
than
Token than
Feature activation+3.907
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.215
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
of
Token of
Feature activation+0.000
even
Token even
Feature activation+0.000
gra
Token gra
Feature activation+1.292
ver
Tokenver
Feature activation+3.843
concern
Token concern
Feature activation+0.000
.
Token.
Feature activation+0.005
Its
Token Its
Feature activation+0.000
on
Token on
Feature activation+0.000
eness
Tokeneness
Feature activation+0.000
For
Token For
Feature activation+0.000
her
Token her
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+3.626
because
Token because
Feature activation+0.000
she
Token she
Feature activation+0.000
felt
Token felt
Feature activation+0.000
betrayed
Token betrayed
Feature activation+0.000
by
Token by
Feature activation+0.000
these
Token these
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
to
Token to
Feature activation+0.000
grow
Token grow
Feature activation+0.000
even
Token even
Feature activation+0.472
faster
Token faster
Feature activation+3.601
.
Token.
Feature activation+0.274
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ep
TokenEp
Feature activation+0.000
idem
Tokenidem
Feature activation+0.000
i
Tokeni
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
lifting
Token lifting
Feature activation+0.000
wages
Token wages
Feature activation+0.000
even
Token even
Feature activation+0.000
faster
Token faster
Feature activation+3.586
than
Token than
Feature activation+3.907
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.215
âĢ
TokenâĢ
Feature activation+0.000
gains
Token gains
Feature activation+0.000
,
Token,
Feature activation+0.000
indicating
Token indicating
Feature activation+0.000
that
Token that
Feature activation+0.000
even
Token even
Feature activation+0.000
older
Token older
Feature activation+3.562
Android
Token Android
Feature activation+0.000
hands
Token hands
Feature activation+0.000
ets
Tokenets
Feature activation+0.000
could
Token could
Feature activation+0.056
gain
Token gain
Feature activation+0.000
Spawn
Token Spawn
Feature activation+0.000
ing
Tokening
Feature activation+0.000
salmon
Token salmon
Feature activation+0.000
need
Token need
Feature activation+0.000
even
Token even
Feature activation+0.000
cooler
Token cooler
Feature activation+3.430
water
Token water
Feature activation+0.069
.
Token.
Feature activation+0.675
Recent
Token Recent
Feature activation+0.000
daily
Token daily
Feature activation+0.000
maximum
Token maximum
Feature activation+0.000
skulls
Token skulls
Feature activation+0.000
is
Token is
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.395
complicated
Token complicated
Feature activation+1.275
than
Token than
Feature activation+3.411
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
.
Token.
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
made
Token made
Feature activation+0.000
even
Token even
Feature activation+0.000
ju
Token ju
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ier
Tokenier
Feature activation+3.410
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.014
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
each
Token each
Feature activation+0.000
and
Token and
Feature activation+0.000
2022
Token 2022
Feature activation+0.000
-
Token -
Feature activation+0.000
even
Token even
Feature activation+0.154
worse
Token worse
Feature activation+2.589
than
Token than
Feature activation+3.389
Japan
Token Japan
Feature activation+0.000
from
Token from
Feature activation+0.000
1990
Token 1990
Feature activation+0.000
to
Token to
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
who
Token who
Feature activation+0.000
inspires
Token inspires
Feature activation+0.000
even
Token even
Feature activation+0.000
greater
Token greater
Feature activation+2.688
terror
Token terror
Feature activation+0.047
than
Token than
Feature activation+3.341
Mug
Token Mug
Feature activation+0.000
abe
Tokenabe
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
hourly
Token hourly
Feature activation+0.000
breakdown
Token breakdown
Feature activation+0.000
is
Token is
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+3.300
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hour
TokenHour
Feature activation+0.000
one
Token one
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
could
Token could
Feature activation+0.000
get
Token get
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+3.285
:
Token:
Feature activation+0.138
imagine
Token imagine
Feature activation+0.000
your
Token your
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
completely
Token completely
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
even
Token even
Feature activation+0.000
easier
Token easier
Feature activation+3.252
for
Token for
Feature activation+1.125
customers
Token customers
Feature activation+0.216
to
Token to
Feature activation+0.000
book
Token book
Feature activation+0.000
one
Token one
Feature activation+0.000
to
Token to
Feature activation+0.000
pray
Token pray
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
even
Token even
Feature activation+0.040
greater
Token greater
Feature activation+3.138
number
Token number
Feature activation+1.597
of
Token of
Feature activation+0.000
LGBT
Token LGBT
Feature activation+0.000
teens
Token teens
Feature activation+0.000
battling
Token battling
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
hom
Token hom
Feature activation+0.000
estead
Tokenestead
Feature activation+0.000
even
Token even
Feature activation+0.000
simpler
Token simpler
Feature activation+3.127
.
Token.
Feature activation+0.392
Use
Token Use
Feature activation+0.000
the
Token the
Feature activation+0.000
built
Token built
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
word
Token word
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
even
Token even
Feature activation+0.000
bigger
Token bigger
Feature activation+3.122
Galaxy
Token Galaxy
Feature activation+0.000
Note
Token Note
Feature activation+0.000
II
Token II
Feature activation+0.000
is
Token is
Feature activation+0.173
spreading
Token spreading
Feature activation+0.000

Top DFA by src position
MAX = 5.130

Ċ
TokenĊ
Feature activation+0.023
Top resid features:
It
TokenIt
Feature activation+0.048
Top resid features:
used
Token used
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.064
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
even
Token even
Feature activation+4.927
Top resid features:
worse
Token worse
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Try
Token Try
Feature activation+0.000
Top resid features:
repeating
Token repeating
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
The
TokenThe
Feature activation-0.017
Top resid features:
mur
Token mur
Feature activation-0.010
Top resid features:
k
Tokenk
Feature activation+0.013
Top resid features:
gets
Token gets
Feature activation+0.045
Top resid features:
even
Token even
Feature activation+5.130
Top resid features:
mur
Token mur
Feature activation-0.019
Top resid features:
k
Tokenk
Feature activation-0.021
Top resid features:
ier
Tokenier
Feature activation+0.133
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.015
Top resid features:
K
Token K
Feature activation+0.000
Top resid features:
iko
Tokeniko
Feature activation+0.013
Top resid features:
Alonso
Token Alonso
Feature activation+0.021
Top resid features:
was
Token was
Feature activation-0.042
Top resid features:
even
Token even
Feature activation+5.025
Top resid features:
faster
Token faster
Feature activation+0.142
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Really
Token Really
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:
could
Token could
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.024
Top resid features:
been
Token been
Feature activation+0.029
Top resid features:
lifting
Token lifting
Feature activation+0.016
Top resid features:
wages
Token wages
Feature activation+0.030
Top resid features:
even
Token even
Feature activation+4.858
Top resid features:
faster
Token faster
Feature activation+0.055
Top resid features:
than
Token than
Feature activation+0.106
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.015
Top resid features:
mindfulness
Token mindfulness
Feature activation-0.022
Top resid features:
should
Token should
Feature activation-0.001
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
even
Token even
Feature activation+4.805
Top resid features:
gra
Token gra
Feature activation+0.356
Top resid features:
ver
Tokenver
Feature activation+0.001
Top resid features:
concern
Token concern
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Its
Token Its
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
For
Token For
Feature activation-0.059
Top resid features:
her
Token her
Feature activation-0.026
Top resid features:
it
Token it
Feature activation+0.042
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
even
Token even
Feature activation+5.047
Top resid features:
worse
Token worse
Feature activation+0.009
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
felt
Token felt
Feature activation+0.000
Top resid features:
betrayed
Token betrayed
Feature activation+0.000
Top resid features:
expect
Token expect
Feature activation-0.007
Top resid features:
these
Token these
Feature activation+0.012
Top resid features:
numbers
Token numbers
Feature activation+0.053
Top resid features:
to
Token to
Feature activation+0.084
Top resid features:
grow
Token grow
Feature activation+0.021
Top resid features:
even
Token even
Feature activation+4.523
Top resid features:
faster
Token faster
Feature activation+0.178
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
Ep
TokenEp
Feature activation+0.000
Top resid features:
idem
Tokenidem
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.017
Top resid features:
have
Token have
Feature activation+0.015
Top resid features:
been
Token been
Feature activation+0.032
Top resid features:
lifting
Token lifting
Feature activation+0.053
Top resid features:
wages
Token wages
Feature activation+0.064
Top resid features:
even
Token even
Feature activation+4.403
Top resid features:
faster
Token faster
Feature activation+0.175
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
performance
Token performance
Feature activation+0.010
Top resid features:
gains
Token gains
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
indicating
Token indicating
Feature activation+0.009
Top resid features:
that
Token that
Feature activation-0.031
Top resid features:
even
Token even
Feature activation+4.596
Top resid features:
older
Token older
Feature activation+0.267
Top resid features:
Android
Token Android
Feature activation+0.000
Top resid features:
hands
Token hands
Feature activation+0.000
Top resid features:
ets
Tokenets
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Spawn
Token Spawn
Feature activation+0.003
Top resid features:
ing
Tokening
Feature activation-0.008
Top resid features:
salmon
Token salmon
Feature activation+0.004
Top resid features:
need
Token need
Feature activation-0.217
Top resid features:
even
Token even
Feature activation+4.621
Top resid features:
cooler
Token cooler
Feature activation+0.198
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Recent
Token Recent
Feature activation+0.000
Top resid features:
daily
Token daily
Feature activation+0.000
Top resid features:
thing
Token thing
Feature activation+0.016
Top resid features:
inside
Token inside
Feature activation+0.006
Top resid features:
our
Token our
Feature activation+0.004
Top resid features:
skulls
Token skulls
Feature activation+0.029
Top resid features:
is
Token is
Feature activation+0.041
Top resid features:
even
Token even
Feature activation+4.495
Top resid features:
more
Token more
Feature activation-0.031
Top resid features:
complicated
Token complicated
Feature activation+0.031
Top resid features:
than
Token than
Feature activation+0.107
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
looks
Token looks
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.063
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.009
Top resid features:
made
Token made
Feature activation-0.145
Top resid features:
even
Token even
Feature activation+4.617
Top resid features:
ju
Token ju
Feature activation+0.057
Top resid features:
ic
Tokenic
Feature activation+0.009
Top resid features:
ier
Tokenier
Feature activation+0.079
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
between
Token between
Feature activation-0.015
Top resid features:
now
Token now
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
2022
Token 2022
Feature activation+0.013
Top resid features:
-
Token -
Feature activation+0.064
Top resid features:
even
Token even
Feature activation+4.381
Top resid features:
worse
Token worse
Feature activation+0.031
Top resid features:
than
Token than
Feature activation+0.126
Top resid features:
Japan
Token Japan
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
1990
Token 1990
Feature activation+0.000
Top resid features:
person
Token person
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
Zimbabwe
Token Zimbabwe
Feature activation+0.028
Top resid features:
who
Token who
Feature activation-0.002
Top resid features:
inspires
Token inspires
Feature activation+0.048
Top resid features:
even
Token even
Feature activation+4.447
Top resid features:
greater
Token greater
Feature activation-0.040
Top resid features:
terror
Token terror
Feature activation-0.015
Top resid features:
than
Token than
Feature activation+0.068
Top resid features:
Mug
Token Mug
Feature activation+0.000
Top resid features:
abe
Tokenabe
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
The
TokenThe
Feature activation-0.016
Top resid features:
hourly
Token hourly
Feature activation+0.008
Top resid features:
breakdown
Token breakdown
Feature activation+0.007
Top resid features:
is
Token is
Feature activation-0.047
Top resid features:
even
Token even
Feature activation+4.581
Top resid features:
worse
Token worse
Feature activation+0.019
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:
Hour
TokenHour
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
It
TokenIt
Feature activation+0.025
Top resid features:
could
Token could
Feature activation-0.002
Top resid features:
get
Token get
Feature activation+0.119
Top resid features:
even
Token even
Feature activation+4.303
Top resid features:
worse
Token worse
Feature activation+0.084
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
imagine
Token imagine
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
exchange
Token exchange
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.008
Top resid features:
effort
Token effort
Feature activation-0.017
Top resid features:
to
Token to
Feature activation+0.031
Top resid features:
make
Token make
Feature activation-0.095
Top resid features:
it
Token it
Feature activation-0.009
Top resid features:
even
Token even
Feature activation+4.521
Top resid features:
easier
Token easier
Feature activation+0.079
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
customers
Token customers
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
book
Token book
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
pray
Token pray
Feature activation-0.006
Top resid features:
for
Token for
Feature activation-0.068
Top resid features:
the
Token the
Feature activation-0.168
Top resid features:
even
Token even
Feature activation+4.651
Top resid features:
greater
Token greater
Feature activation+0.025
Top resid features:
number
Token number
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
LGBT
Token LGBT
Feature activation+0.000
Top resid features:
teens
Token teens
Feature activation+0.000
Top resid features:
life
Token life
Feature activation-0.021
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.027
Top resid features:
hom
Token hom
Feature activation-0.007
Top resid features:
estead
Tokenestead
Feature activation+0.053
Top resid features:
even
Token even
Feature activation+4.434
Top resid features:
simpler
Token simpler
Feature activation+0.125
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Use
Token Use
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
built
Token built
Feature activation+0.000
Top resid features:
Remember
Token Remember
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
word
Token word
Feature activation+0.018
Top resid features:
of
Token of
Feature activation-0.145
Top resid features:
an
Token an
Feature activation-0.053
Top resid features:
even
Token even
Feature activation+4.478
Top resid features:
bigger
Token bigger
Feature activation+0.041
Top resid features:
Galaxy
Token Galaxy
Feature activation+0.000
Top resid features:
Note
Token Note
Feature activation+0.000
Top resid features:
II
Token II
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.05

Head 3: 0.05

Head 4: 0.02

Head 5: 0.04

Head 6: 0.47

Head 7: 0.04

Head 8: 0.03

Head 9: 0.04

Head 10: 0.09

Head 11: 0.10

Positive logits

��1.19

��1.17

thinkable1.16

Seym1.05

1.04

gettable1.01

antioxidants0.99

oho0.98

SAP0.98

Trend0.97

referen0.97

methodological0.96

GOODMAN0.96

=>0.95

!--0.94

裏�0.94

Formula0.94

genic0.92

antioxidant0.92

horm0.92

Negative logits

wright-1.23

orian-1.09

liv-1.07

leys-1.02

quar-1.01

ki-1.01

mire-1.01

keep-1.00

iewicz-1.00

missions-0.99

nan-0.99

nard-0.99

anamo-0.98

pei-0.97

nell-0.97

logs-0.96

tell-0.96

Lump-0.96

nels-0.95

ley-0.95

INTERVAL 3.600 - 4.000
CONTAINS 0.001%

For
Token For
Feature activation+0.000
her
Token her
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+3.626
because
Token because
Feature activation+0.000
she
Token she
Feature activation+0.000
felt
Token felt
Feature activation+0.000
betrayed
Token betrayed
Feature activation+0.000
by
Token by
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
of
Token of
Feature activation+0.000
even
Token even
Feature activation+0.000
gra
Token gra
Feature activation+1.292
ver
Tokenver
Feature activation+3.843
concern
Token concern
Feature activation+0.000
.
Token.
Feature activation+0.005
Its
Token Its
Feature activation+0.000
on
Token on
Feature activation+0.000
eness
Tokeneness
Feature activation+0.000
these
Token these
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
to
Token to
Feature activation+0.000
grow
Token grow
Feature activation+0.000
even
Token even
Feature activation+0.472
faster
Token faster
Feature activation+3.601
.
Token.
Feature activation+0.274
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ep
TokenEp
Feature activation+0.000
idem
Tokenidem
Feature activation+0.000
i
Tokeni
Feature activation+0.000
been
Token been
Feature activation+0.000
lifting
Token lifting
Feature activation+0.000
wages
Token wages
Feature activation+0.000
even
Token even
Feature activation+0.000
faster
Token faster
Feature activation+3.586
than
Token than
Feature activation+3.907
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.215
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
K
Token K
Feature activation+0.000
iko
Tokeniko
Feature activation+0.000
Alonso
Token Alonso
Feature activation+0.000
was
Token was
Feature activation+0.000
even
Token even
Feature activation+0.000
faster
Token faster
Feature activation+3.933
.
Token.
Feature activation+0.088
Really
Token Really
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
fraction
Token fraction
Feature activation+0.000

INTERVAL 3.200 - 3.600
CONTAINS 0.001%

and
Token and
Feature activation+0.000
2022
Token 2022
Feature activation+0.000
-
Token -
Feature activation+0.000
even
Token even
Feature activation+0.154
worse
Token worse
Feature activation+2.589
than
Token than
Feature activation+3.389
Japan
Token Japan
Feature activation+0.000
from
Token from
Feature activation+0.000
1990
Token 1990
Feature activation+0.000
to
Token to
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
The
TokenThe
Feature activation+0.000
hourly
Token hourly
Feature activation+0.000
breakdown
Token breakdown
Feature activation+0.000
is
Token is
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+3.300
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hour
TokenHour
Feature activation+0.000
one
Token one
Feature activation+0.000
skulls
Token skulls
Feature activation+0.000
is
Token is
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.395
complicated
Token complicated
Feature activation+1.275
than
Token than
Feature activation+3.411
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
.
Token.
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
made
Token made
Feature activation+0.000
even
Token even
Feature activation+0.000
ju
Token ju
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ier
Tokenier
Feature activation+3.410
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.014
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
each
Token each
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
could
Token could
Feature activation+0.000
get
Token get
Feature activation+0.000
even
Token even
Feature activation+0.000
worse
Token worse
Feature activation+3.285
:
Token:
Feature activation+0.138
imagine
Token imagine
Feature activation+0.000
your
Token your
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
completely
Token completely
Feature activation+0.000

INTERVAL 2.800 - 3.200
CONTAINS 0.001%

But
TokenBut
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
probably
Token probably
Feature activation+0.000
even
Token even
Feature activation+0.000
harder
Token harder
Feature activation+3.068
for
Token for
Feature activation+0.239
a
Token a
Feature activation+0.000
parent
Token parent
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
,
Token,
Feature activation+0.000
word
Token word
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
even
Token even
Feature activation+0.000
bigger
Token bigger
Feature activation+3.122
Galaxy
Token Galaxy
Feature activation+0.000
Note
Token Note
Feature activation+0.000
II
Token II
Feature activation+0.000
is
Token is
Feature activation+0.173
spreading
Token spreading
Feature activation+0.000
new
Token new
Feature activation+0.000
regime
Token regime
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
even
Token even
Feature activation+0.000
harsher
Token harsher
Feature activation+2.879
,
Token,
Feature activation+0.053
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
many
Token many
Feature activation+0.000
employment
Token employment
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
hom
Token hom
Feature activation+0.000
estead
Tokenestead
Feature activation+0.000
even
Token even
Feature activation+0.000
simpler
Token simpler
Feature activation+3.127
.
Token.
Feature activation+0.392
Use
Token Use
Feature activation+0.000
the
Token the
Feature activation+0.000
built
Token built
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
an
Token an
Feature activation+0.000
even
Token even
Feature activation+0.054
better
Token better
Feature activation+3.011
year
Token year
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
if
Token if
Feature activation+0.000

INTERVAL 2.400 - 2.800
CONTAINS 0.003%

one
Token one
Feature activation+0.000
bug
Token bug
Feature activation+0.000
could
Token could
Feature activation+0.000
cause
Token cause
Feature activation+0.000
even
Token even
Feature activation+0.224
more
Token more
Feature activation+2.761
bugs
Token bugs
Feature activation+0.151
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
L
TokenL
Feature activation+0.000
ank
Tokenank
Feature activation+0.000
ford
Tokenford
Feature activation+0.000
in
Token in
Feature activation+0.000
Zimbabwe
Token Zimbabwe
Feature activation+0.000
who
Token who
Feature activation+0.000
inspires
Token inspires
Feature activation+0.000
even
Token even
Feature activation+0.000
greater
Token greater
Feature activation+2.688
terror
Token terror
Feature activation+0.047
than
Token than
Feature activation+3.341
Mug
Token Mug
Feature activation+0.000
abe
Tokenabe
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.650
surreal
Token surreal
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Asked
TokenAsked
Feature activation+0.000
holding
Token holding
Feature activation+0.000
the
Token the
Feature activation+0.000
fire
Token fire
Feature activation+0.000
button
Token button
Feature activation+0.000
even
Token even
Feature activation+0.000
longer
Token longer
Feature activation+2.633
the
Token the
Feature activation+0.202
gun
Token gun
Feature activation+0.000
creates
Token creates
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
blasts
Token blasts
Feature activation+0.000
clear
Token clear
Feature activation+0.000
and
Token and
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.586
stark
Token stark
Feature activation+0.284
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 2.000 - 2.400
CONTAINS 0.002%

atheists
Token atheists
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.350
upset
Token upset
Feature activation+0.000
by
Token by
Feature activation+0.000
this
Token this
Feature activation+0.000
than
Token than
Feature activation+2.019
they
Token they
Feature activation+0.000
England
Token England
Feature activation+0.000
which
Token which
Feature activation+0.000
made
Token made
Feature activation+0.000
this
Token this
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.135
cool
Token cool
Feature activation+1.822
,
Token,
Feature activation+0.395
since
Token since
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
year
Token year
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
something
Token something
Feature activation+0.000
even
Token even
Feature activation+0.000
better
Token better
Feature activation+2.057
.
Token.
Feature activation+0.185
So
Token So
Feature activation+0.000
come
Token come
Feature activation+0.000
on
Token on
Feature activation+0.000
out
Token out
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.350
upset
Token upset
Feature activation+0.000
by
Token by
Feature activation+0.000
this
Token this
Feature activation+0.000
than
Token than
Feature activation+2.019
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
by
Token by
Feature activation+0.000
what
Token what
Feature activation+0.000
she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
make
Token make
Feature activation+0.000
your
Token your
Feature activation+0.000
kitchen
Token kitchen
Feature activation+0.000
even
Token even
Feature activation+0.000
smarter
Token smarter
Feature activation+2.118
.
Token.
Feature activation+0.111
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.600 - 2.000
CONTAINS 0.003%

secure
Token secure
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
worse
Token worse
Feature activation+1.829
,
Token,
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
devices
Token devices
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
easy
Token easy
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
for
Token for
Feature activation+1.640
someone
Token someone
Feature activation+0.000
who
Token who
Feature activation+0.000
's
Token's
Feature activation+0.000
been
Token been
Feature activation+0.000
blind
Token blind
Feature activation+0.000
the
Token the
Feature activation+0.000
supply
Token supply
Feature activation+0.000
of
Token of
Feature activation+0.000
nurses
Token nurses
Feature activation+0.000
even
Token even
Feature activation+0.000
further
Token further
Feature activation+1.822
.
Token.
Feature activation+0.311
Making
Token Making
Feature activation+0.000
nurses
Token nurses
Feature activation+0.000
from
Token from
Feature activation+0.000
outside
Token outside
Feature activation+0.000
Control
Token Control
Feature activation+0.000
Deck
Token Deck
Feature activation+0.000
and
Token and
Feature activation+0.000
gain
Token gain
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+1.784
control
Token control
Feature activation+0.712
by
Token by
Feature activation+0.000
using
Token using
Feature activation+0.000
two
Token two
Feature activation+0.000
sticks
Token sticks
Feature activation+0.000
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.000
he
Token he
Feature activation+0.000
took
Token took
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+1.973
issue
Token issue
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
timing
Token timing
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.200 - 1.600
CONTAINS 0.004%

our
Token our
Feature activation+0.000
skulls
Token skulls
Feature activation+0.000
is
Token is
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+2.395
complicated
Token complicated
Feature activation+1.275
than
Token than
Feature activation+3.411
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
.
Token.
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
committee
Token committee
Feature activation+0.000
pushed
Token pushed
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+1.326
do
Token do
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
approach
Token approach
Feature activation+0.000
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+1.467
unlikely
Token unlikely
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
team
Token team
Feature activation+0.000
of
Token of
Feature activation+0.000
cur
Token cur
Feature activation+0.000
ators
Tokenators
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+1.434
traditional
Token traditional
Feature activation+0.699
TV
Token TV
Feature activation+0.000
shows
Token shows
Feature activation+0.000
,
Token,
Feature activation+0.000
movies
Token movies
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.037
more
Token more
Feature activation+0.854
disturbing
Token disturbing
Feature activation+1.599
is
Token is
Feature activation+0.752
why
Token why
Feature activation+0.377
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
violence
Token violence
Feature activation+0.000

INTERVAL 0.800 - 1.200
CONTAINS 0.006%

arch
Tokenarch
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.211
within
Token within
Feature activation+0.856
the
Token the
Feature activation+0.000
anarchist
Token anarchist
Feature activation+0.000
mil
Token mil
Feature activation+0.000
ieu
Tokenieu
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
best
Token best
Feature activation+0.000
,
Token,
Feature activation+0.000
irresponsible
Token irresponsible
Feature activation+0.000
even
Token even
Feature activation+0.000
.
Token.
Feature activation+1.170
If
Token If
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
no
Token no
Feature activation+0.000
money
Token money
Feature activation+0.000
my
Token my
Feature activation+0.000
7
Token 7
Feature activation+0.000
yr
Token yr
Feature activation+0.000
old
Token old
Feature activation+0.000
even
Token even
Feature activation+0.000
got
Token got
Feature activation+0.816
something
Token something
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token ,
Feature activation+0.000
when
Token when
Feature activation+0.120
he
Token he
Feature activation+0.000
"
Token "
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
ing
Tokening
Feature activation+0.000
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+0.785
is
Token is
Feature activation+0.888
midday
Token midday
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
here
Tokenhere
Feature activation+0.000
is
Token is
Feature activation+0.000
safe
Token safe
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.062
here
Token here
Feature activation+0.917
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.131
Guardian
Token Guardian
Feature activation+0.000
Science
Token Science
Feature activation+0.000

INTERVAL 0.400 - 0.800
CONTAINS 0.021%

rules
Token rules
Feature activation+0.000
have
Token have
Feature activation+0.000
put
Token put
Feature activation+0.000
even
Token even
Feature activation+0.000
tougher
Token tougher
Feature activation+2.135
limits
Token limits
Feature activation+0.739
on
Token on
Feature activation+0.091
down
Token down
Feature activation+0.000
payments
Token payments
Feature activation+0.000
,
Token,
Feature activation+0.000
loan
Token loan
Feature activation+0.000
?
Token?
Feature activation+0.000
31
Token 31
Feature activation+0.000
?
Token?
Feature activation+0.000
32
Token 32
Feature activation+0.000
?
Token?
Feature activation+0.000
Even
Token Even
Feature activation+0.427
Mo
Token Mo
Feature activation+0.000
Vaughn
Token Vaughn
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
question
Token question
Feature activation+0.000
:
Token:
Feature activation+0.000
Does
Token Does
Feature activation+0.000
it
Token it
Feature activation+0.000
even
Token even
Feature activation+0.000
matter
Token matter
Feature activation+0.480
that
Token that
Feature activation+0.019
his
Token his
Feature activation+0.000
new
Token new
Feature activation+0.000
album
Token album
Feature activation+0.000
is
Token is
Feature activation+0.000
s
Tokens
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
job
Token job
Feature activation+0.000
.
Token.
Feature activation+0.568
Even
Token Even
Feature activation+0.173
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
roaming
Token roaming
Feature activation+0.000
the
Token the
Feature activation+0.000
field
Token field
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.476
the
Token the
Feature activation+0.000
oddly
Token oddly
Feature activation+0.000
named
Token named
Feature activation+0.000
yet
Token yet
Feature activation+0.000
rebuilt
Token rebuilt
Feature activation+0.000

INTERVAL 0.000 - 0.400
CONTAINS 99.959%

and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.000
parties
Token parties
Feature activation+0.000
have
Token have
Feature activation+0.000
their
Token their
Feature activation+0.000
candidates
Token candidates
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
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
features
Token features
Feature activation+0.000
five
Token five
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+0.000
wing
Tokenwing
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
the
Token the
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
could
Token could
Feature activation+0.000
tell
Token tell
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
fluid
Token fluid
Feature activation+0.000
moved
Token moved
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
they
Token they
Feature activation+0.000
was
Token was
Feature activation+0.000
15
Token 15
Feature activation+0.000
and
Token and
Feature activation+0.000
recently
Token recently
Feature activation+0.000
completed
Token completed
Feature activation+0.000
her
Token her
Feature activation+0.000
Bronze
Token Bronze
Feature activation+0.000
Stage
Token Stage
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Features
TokenFeatures
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Nissan
Token Nissan
Feature activation+0.000
Heisman
Token Heisman
Feature activation+0.000
House
Token House
Feature activation+0.000
allow
Token allow
Feature activation+0.000
fans
Token fans
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 H3.6: (feature 20679)

TOP ACTIVATIONS
MAX = 2.762

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.467
top
Token top
Feature activation+1.936
spy
Token spy
Feature activation+1.911
agencies
Token agencies
Feature activation+2.762
,
Token,
Feature activation+0.153
the
Token the
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
actions
Token actions
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.534
Supreme
Token Supreme
Feature activation+2.248
Court
Token Court
Feature activation+2.421
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
Carter
Token Carter
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.978
president
Token president
Feature activation+2.383
said
Token said
Feature activation+0.599
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
future
Token future
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
oyle
Tokenoyle
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
US
TokenUS
Feature activation+0.718
President
Token President
Feature activation+2.257
Donald
Token Donald
Feature activation+0.468
Trump
Token Trump
Feature activation+0.000
stunned
Token stunned
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
democratic
Tokendemocratic
Feature activation+0.000
actions
Token actions
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.534
Supreme
Token Supreme
Feature activation+2.248
Court
Token Court
Feature activation+2.421
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
process
Token process
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.415
government
Token government
Feature activation+2.224
is
Token is
Feature activation+0.792
making
Token making
Feature activation+0.824
it
Token it
Feature activation+0.073
easy
Token easy
Feature activation+0.000
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.436
Court
Token Court
Feature activation+1.793
of
Token of
Feature activation+2.222
Appeals
Token Appeals
Feature activation+1.735
for
Token for
Feature activation+0.824
the
Token the
Feature activation+0.117
Second
Token Second
Feature activation+0.000
Circuit
Token Circuit
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
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.511
government
Token government
Feature activation+2.184
for
Token for
Feature activation+0.476
a
Token a
Feature activation+0.206
security
Token security
Feature activation+0.003
system
Token system
Feature activation+0.293
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.611
government
Token government
Feature activation+2.178
âĢ
TokenâĢ
Feature activation+0.093
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.242
responsibility
Token responsibility
Feature activation+1.043
to
Token to
Feature activation+0.701
"
Token"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.949
Attorney
Token Attorney
Feature activation+1.364
General
Token General
Feature activation+2.177
Eric
Token Eric
Feature activation+0.000
Holder
Token Holder
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
held
Token held
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.000
hacks
Token hacks
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.432
government
Token government
Feature activation+2.147
,
Token,
Feature activation+0.121
the
Token the
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Reserve
Token Reserve
Feature activation+0.000
and
Token and
Feature activation+0.000
iv
Tokeniv
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.621
Navy
Token Navy
Feature activation+2.147
has
Token has
Feature activation+0.485
restricted
Token restricted
Feature activation+0.324
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
some
Token some
Feature activation+0.000
Group
Token Group
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
investment
Token investment
Feature activation+0.502
arm
Token arm
Feature activation+2.146
of
Token of
Feature activation+1.573
convicted
Token convicted
Feature activation+0.507
felon
Token felon
Feature activation+0.000
R
Token R
Feature activation+0.000
.
Token.
Feature activation+0.000
released
Token released
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
US
Token US
Feature activation+0.000
Supreme
Token Supreme
Feature activation+1.656
Court
Token Court
Feature activation+2.112
is
Token is
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
rule
Token rule
Feature activation+0.000
on
Token on
Feature activation+0.000
[
Token [
Feature activation+0.000
and
Tokenand
Feature activation+0.000
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.714
media
Token media
Feature activation+2.111
falsely
Token falsely
Feature activation+0.000
accused
Token accused
Feature activation+1.048
China
Token China
Feature activation+0.000
of
Token of
Feature activation+0.000
using
Token using
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
President
Token President
Feature activation+2.098
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
move
Token move
Feature activation+0.000
in
Token in
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
,
Token,
Feature activation+0.000
US
Token US
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.520
Command
Token Command
Feature activation+2.097
(
Token (
Feature activation+0.833
C
TokenC
Feature activation+0.411
IN
TokenIN
Feature activation+0.000
CP
TokenCP
Feature activation+0.000
AC
TokenAC
Feature activation+0.000
or
Token or
Feature activation+0.000
locked
Token locked
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
government
Token government
Feature activation+2.090
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.020
association
Token association
Feature activation+0.147
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
outlook
Token outlook
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
economy
Token economy
Feature activation+2.084
.
Token.
Feature activation+0.013
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Gl
TokenGl
Feature activation+0.000
oom
Tokenoom
Feature activation+0.000
contributor
Token contributor
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.071
energy
Token energy
Feature activation+1.706
economy
Token economy
Feature activation+2.069
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 3.635

the
Token the
Feature activation+0.086
Top resid features:
former
Token former
Feature activation+0.043
Top resid features:
head
Token head
Feature activation+0.089
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.131
Top resid features:
US
Token US
Feature activation+3.039
Top resid features:
top
Token top
Feature activation+0.072
Top resid features:
spy
Token spy
Feature activation+0.130
Top resid features:
agencies
Token agencies
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.012
Top resid features:
democratic
Tokendemocratic
Feature activation+0.002
Top resid features:
actions
Token actions
Feature activation-0.035
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.113
Top resid features:
US
Token US
Feature activation+3.547
Top resid features:
Supreme
Token Supreme
Feature activation-0.101
Top resid features:
Court
Token Court
Feature activation-0.066
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
By
TokenBy
Feature activation+0.000
Top resid features:
territory
Token territory
Feature activation-0.019
Top resid features:
'
Token'
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
US
Token US
Feature activation+3.075
Top resid features:
president
Token president
Feature activation+0.338
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
RC
TokenRC
Feature activation-0.001
Top resid features:
oyle
Tokenoyle
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.039
Top resid features:
com
Tokencom
Feature activation+0.025
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.271
Top resid features:
US
TokenUS
Feature activation+3.289
Top resid features:
President
Token President
Feature activation+0.278
Top resid features:
Donald
Token Donald
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
stunned
Token stunned
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.016
Top resid features:
democratic
Tokendemocratic
Feature activation+0.006
Top resid features:
actions
Token actions
Feature activation-0.032
Top resid features:
by
Token by
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.145
Top resid features:
US
Token US
Feature activation+3.116
Top resid features:
Supreme
Token Supreme
Feature activation-0.010
Top resid features:
Court
Token Court
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
By
TokenBy
Feature activation+0.000
Top resid features:
IT
TokenIT
Feature activation+0.005
Top resid features:
process
Token process
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.045
Top resid features:
but
Token but
Feature activation-0.085
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
US
Token US
Feature activation+2.955
Top resid features:
government
Token government
Feature activation+0.174
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
easy
Token easy
Feature activation+0.000
Top resid features:
November
Token November
Feature activation+0.007
Top resid features:
2017
Token 2017
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
The
TokenThe
Feature activation+0.032
Top resid features:
US
Token US
Feature activation+3.419
Top resid features:
Court
Token Court
Feature activation-0.189
Top resid features:
of
Token of
Feature activation-0.077
Top resid features:
Appeals
Token Appeals
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:
under
Token under
Feature activation+0.025
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
contract
Token contract
Feature activation-0.034
Top resid features:
with
Token with
Feature activation+0.124
Top resid features:
the
Token the
Feature activation+0.141
Top resid features:
US
Token US
Feature activation+2.695
Top resid features:
government
Token government
Feature activation+0.165
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
security
Token security
Feature activation+0.000
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.054
Top resid features:
Ļ
TokenĻ
Feature activation+0.097
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
US
Token US
Feature activation+2.684
Top resid features:
government
Token government
Feature activation+0.211
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:
responsibility
Token responsibility
Feature activation+0.000
Top resid features:
ens
Token ens
Feature activation-0.004
Top resid features:
ue
Tokenue
Feature activation+0.001
Top resid features:
"
Token"
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.040
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
US
TokenUS
Feature activation+3.635
Top resid features:
Attorney
Token Attorney
Feature activation-0.372
Top resid features:
General
Token General
Feature activation+0.011
Top resid features:
Eric
Token Eric
Feature activation+0.000
Top resid features:
Holder
Token Holder
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
profile
Tokenprofile
Feature activation-0.006
Top resid features:
hacks
Token hacks
Feature activation+0.018
Top resid features:
against
Token against
Feature activation-0.021
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
US
Token US
Feature activation+2.785
Top resid features:
government
Token government
Feature activation+0.138
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Federal
Token Federal
Feature activation+0.000
Top resid features:
Reserve
Token Reserve
Feature activation+0.000
Top resid features:
ull
Tokenull
Feature activation+0.015
Top resid features:
iv
Tokeniv
Feature activation-0.005
Top resid features:
ans
Tokenans
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.111
Top resid features:
US
Token US
Feature activation+2.943
Top resid features:
Navy
Token Navy
Feature activation+0.045
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
restricted
Token restricted
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Stanford
Token Stanford
Feature activation+0.013
Top resid features:
Financial
Token Financial
Feature activation+0.021
Top resid features:
Group
Token Group
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.267
Top resid features:
US
Token US
Feature activation+2.535
Top resid features:
investment
Token investment
Feature activation+0.025
Top resid features:
arm
Token arm
Feature activation+0.108
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
convicted
Token convicted
Feature activation+0.000
Top resid features:
felon
Token felon
Feature activation+0.000
Top resid features:
opinion
Token opinion
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
released
Token released
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.116
Top resid features:
The
Token The
Feature activation+0.057
Top resid features:
US
Token US
Feature activation+3.402
Top resid features:
Supreme
Token Supreme
Feature activation-0.089
Top resid features:
Court
Token Court
Feature activation-0.067
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
expected
Token expected
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
endeavors
Token endeavors
Feature activation-0.025
Top resid features:
[
Token [
Feature activation-0.029
Top resid features:
and
Tokenand
Feature activation-0.010
Top resid features:
]
Token]
Feature activation+0.060
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
US
Token US
Feature activation+2.886
Top resid features:
media
Token media
Feature activation+0.215
Top resid features:
falsely
Token falsely
Feature activation+0.000
Top resid features:
accused
Token accused
Feature activation+0.000
Top resid features:
China
Token China
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Beijing
Token Beijing
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.052
Top resid features:
Ċ
TokenĊ
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
US
TokenUS
Feature activation+3.120
Top resid features:
President
Token President
Feature activation+0.125
Top resid features:
Barack
Token Barack
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.061
Top resid features:
Commander
Token Commander
Feature activation+0.021
Top resid features:
in
Token in
Feature activation+0.053
Top resid features:
Chief
Token Chief
Feature activation-0.040
Top resid features:
,
Token,
Feature activation-0.077
Top resid features:
US
Token US
Feature activation+2.902
Top resid features:
Pacific
Token Pacific
Feature activation-0.238
Top resid features:
Command
Token Command
Feature activation+0.062
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
IN
TokenIN
Feature activation+0.000
Top resid features:
censored
Token censored
Feature activation+0.009
Top resid features:
or
Token or
Feature activation+0.021
Top resid features:
locked
Token locked
Feature activation-0.020
Top resid features:
by
Token by
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.135
Top resid features:
US
Token US
Feature activation+2.660
Top resid features:
government
Token government
Feature activation+0.150
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
association
Token association
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
outlook
Token outlook
Feature activation-0.000
Top resid features:
for
Token for
Feature activation-0.077
Top resid features:
the
Token the
Feature activation+0.256
Top resid features:
US
Token US
Feature activation+2.531
Top resid features:
economy
Token economy
Feature activation+0.101
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:
Gl
TokenGl
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
significant
Token significant
Feature activation-0.034
Top resid features:
contributor
Token contributor
Feature activation-0.021
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.231
Top resid features:
US
Token US
Feature activation+2.497
Top resid features:
energy
Token energy
Feature activation+0.235
Top resid features:
economy
Token economy
Feature activation+0.048
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.06

Head 3: 0.05

Head 4: 0.03

Head 5: 0.05

Head 6: 0.46

Head 7: 0.07

Head 8: 0.04

Head 9: 0.03

Head 10: 0.09

Head 11: 0.05

Positive logits

consulate1.46

embassy1.39

ambassador1.36

assies1.34

Ambassador1.34

Embassy1.28

Slave1.24

diplomat1.20

apego1.16

ruary1.14

gage1.11

aspberry1.11

ember1.10

extradition1.09

��1.09

elsen1.09

southwest1.08

actory1.08

embargo1.08

eland1.07

Negative logits

-1.19

ksh-1.09

cryptoc-1.09

Nem-1.07

ictions-1.05

govtrack-1.04

Ic-1.04

ANC-1.03

ijn-1.02

Kad-1.01

Ol-0.99

Keys-0.98

Por-0.98

amaz-0.97

sqor-0.97

hypert-0.97

lov-0.96

Chop-0.96

Mou-0.96

sar-0.95

INTERVAL 2.486 - 2.762
CONTAINS 0.000%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.467
top
Token top
Feature activation+1.936
spy
Token spy
Feature activation+1.911
agencies
Token agencies
Feature activation+2.762
,
Token,
Feature activation+0.153
the
Token the
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.210 - 2.486
CONTAINS 0.001%

oyle
Tokenoyle
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
US
TokenUS
Feature activation+0.718
President
Token President
Feature activation+2.257
Donald
Token Donald
Feature activation+0.468
Trump
Token Trump
Feature activation+0.000
stunned
Token stunned
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
process
Token process
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.415
government
Token government
Feature activation+2.224
is
Token is
Feature activation+0.792
making
Token making
Feature activation+0.824
it
Token it
Feature activation+0.073
easy
Token easy
Feature activation+0.000
for
Token for
Feature activation+0.000
actions
Token actions
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.534
Supreme
Token Supreme
Feature activation+2.248
Court
Token Court
Feature activation+2.421
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
Carter
Token Carter
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.978
president
Token president
Feature activation+2.383
said
Token said
Feature activation+0.599
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
future
Token future
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
US
Token US
Feature activation+0.436
Court
Token Court
Feature activation+1.793
of
Token of
Feature activation+2.222
Appeals
Token Appeals
Feature activation+1.735
for
Token for
Feature activation+0.824
the
Token the
Feature activation+0.117
Second
Token Second
Feature activation+0.000
Circuit
Token Circuit
Feature activation+0.000

INTERVAL 1.934 - 2.210
CONTAINS 0.003%

in
Token in
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
,
Token,
Feature activation+0.000
US
Token US
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.520
Command
Token Command
Feature activation+2.097
(
Token (
Feature activation+0.833
C
TokenC
Feature activation+0.411
IN
TokenIN
Feature activation+0.000
CP
TokenCP
Feature activation+0.000
AC
TokenAC
Feature activation+0.000
the
Token the
Feature activation+0.000
administrator
Token administrator
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
Agency
Token Agency
Feature activation+1.938
for
Token for
Feature activation+0.964
International
Token International
Feature activation+0.633
Development
Token Development
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
as
Token as
Feature activation+0.000
US
Token US
Feature activation+0.409
President
Token President
Feature activation+2.048
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
Macron
Token Macron
Feature activation+0.000
[
Token [
Feature activation+0.000
and
Tokenand
Feature activation+0.000
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.714
media
Token media
Feature activation+2.111
falsely
Token falsely
Feature activation+0.000
accused
Token accused
Feature activation+1.048
China
Token China
Feature activation+0.000
of
Token of
Feature activation+0.000
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
economy
Token economy
Feature activation+2.030
has
Token has
Feature activation+1.138
already
Token already
Feature activation+0.559
been
Token been
Feature activation+0.376
damaged
Token damaged
Feature activation+0.275
by
Token by
Feature activation+0.000

INTERVAL 1.657 - 1.934
CONTAINS 0.004%

and
Token and
Feature activation+0.713
head
Token head
Feature activation+0.398
of
Token of
Feature activation+0.770
the
Token the
Feature activation+0.548
US
Token US
Feature activation+0.000
delegation
Token delegation
Feature activation+1.815
dealing
Token dealing
Feature activation+0.325
with
Token with
Feature activation+0.000
WC
Token WC
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
:
Token:
Feature activation+0.000
significant
Token significant
Feature activation+0.000
contributor
Token contributor
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.071
energy
Token energy
Feature activation+1.706
economy
Token economy
Feature activation+2.069
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
plan
Token plan
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
US
TokenUS
Feature activation+0.622
Geological
Token Geological
Feature activation+1.182
Survey
Token Survey
Feature activation+1.859
says
Token says
Feature activation+0.000
quake
Token quake
Feature activation+0.000
struck
Token struck
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
head
Token head
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.467
top
Token top
Feature activation+1.936
spy
Token spy
Feature activation+1.911
agencies
Token agencies
Feature activation+2.762
,
Token,
Feature activation+0.153
the
Token the
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
,
Token,
Feature activation+0.000
Nicolas
Token Nicolas
Feature activation+0.000
Maduro
Token Maduro
Feature activation+0.000
accused
Token accused
Feature activation+0.000
US
Token US
Feature activation+0.545
intelligence
Token intelligence
Feature activation+1.802
services
Token services
Feature activation+1.820
of
Token of
Feature activation+0.596
giving
Token giving
Feature activation+0.662
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
green
Tokengreen
Feature activation+0.000

INTERVAL 1.381 - 1.657
CONTAINS 0.005%

of
Token of
Feature activation+0.000
somewhat
Token somewhat
Feature activation+0.000
murky
Token murky
Feature activation+0.000
US
Token US
Feature activation+0.000
policies
Token policies
Feature activation+1.314
in
Token in
Feature activation+1.517
regards
Token regards
Feature activation+0.000
to
Token to
Feature activation+0.073
cryptocurrencies
Token cryptocurrencies
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
investment
Token investment
Feature activation+0.502
arm
Token arm
Feature activation+2.146
of
Token of
Feature activation+1.573
convicted
Token convicted
Feature activation+0.507
felon
Token felon
Feature activation+0.000
R
Token R
Feature activation+0.000
.
Token.
Feature activation+0.000
Allen
Token Allen
Feature activation+0.000
Mass
Token Mass
Feature activation+0.000
Destruction
Token Destruction
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
US
Token US
Feature activation+0.000
Strategy
Token Strategy
Feature activation+1.453
at
Token at
Feature activation+0.854
the
Token the
Feature activation+0.094
University
Token University
Feature activation+0.000
of
Token of
Feature activation+0.000
Georgia
Token Georgia
Feature activation+0.000
ALD
TokenALD
Feature activation+0.000
TRUMP
Token TRUMP
Feature activation+0.000
Is
Token Is
Feature activation+0.000
First
Token First
Feature activation+0.000
US
Token US
Feature activation+0.000
President
Token President
Feature activation+1.619
Inv
Token Inv
Feature activation+1.145
ited
Tokenited
Feature activation+1.243
to
Token to
Feature activation+1.038
D
Token D
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
in
Token in
Feature activation+0.000
courts
Token courts
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.716
law
Token law
Feature activation+1.394
firm
Token firm
Feature activation+0.938
that
Token that
Feature activation+0.405
represent
Token represent
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
SO
Token SO
Feature activation+0.000

INTERVAL 1.105 - 1.381
CONTAINS 0.009%

2016
Token 2016
Feature activation+0.000
.)
Token.)
Feature activation+0.000
That
Token That
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
presence
Token presence
Feature activation+1.369
in
Token in
Feature activation+1.869
Benghazi
Token Benghazi
Feature activation+0.000
was
Token was
Feature activation+0.000
essentially
Token essentially
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
driven
Token driven
Feature activation+0.000
by
Token by
Feature activation+0.000
oppressive
Token oppressive
Feature activation+0.000
US
Token US
Feature activation+0.252
foreign
Token foreign
Feature activation+1.286
policies
Token policies
Feature activation+1.191
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
highly
Token highly
Feature activation+0.000
to
Token to
Feature activation+0.000
suspect
Token suspect
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
wants
Token wants
Feature activation+1.155
to
Token to
Feature activation+0.673
divert
Token divert
Feature activation+1.203
attention
Token attention
Feature activation+0.000
and
Token and
Feature activation+0.000
regain
Token regain
Feature activation+0.058
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.888
official
Token official
Feature activation+1.321
.
Token.
Feature activation+0.000
Critics
Token Critics
Feature activation+0.000
say
Token say
Feature activation+0.000
such
Token such
Feature activation+0.000
trips
Token trips
Feature activation+0.000
Manning
Token Manning
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
soldier
Token soldier
Feature activation+1.349
formerly
Token formerly
Feature activation+1.114
called
Token called
Feature activation+0.091
Bradley
Token Bradley
Feature activation+0.000
serving
Token serving
Feature activation+0.000
a
Token a
Feature activation+0.000
35
Token 35
Feature activation+0.000

INTERVAL 0.829 - 1.105
CONTAINS 0.015%

103
Token103
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+0.249
the
Token the
Feature activation+0.089
US
Token US
Feature activation+0.000
in
Token in
Feature activation+0.995
2016
Token 2016
Feature activation+0.000
.[
Token.[
Feature activation+0.000
11
Token11
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
Soy
Token Soy
Feature activation+0.583
Board
Token Board
Feature activation+0.976
,
Token,
Feature activation+0.000
soy
Token soy
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
for
Token for
Feature activation+0.000
61
Token 61
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
patent
Token patent
Feature activation+0.205
system
Token system
Feature activation+1.012
in
Token in
Feature activation+0.728
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
then
Token then
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.946
David
Token David
Feature activation+0.000
Cameron
Token Cameron
Feature activation+0.000
who
Token who
Feature activation+0.000
a
Token a
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
that
Token that
Feature activation+0.000
could
Token could
Feature activation+0.000
harm
Token harm
Feature activation+0.000
US
Token US
Feature activation+0.387
intelligence
Token intelligence
Feature activation+1.400
operations
Token operations
Feature activation+1.037
or
Token or
Feature activation+0.022
personnel
Token personnel
Feature activation+1.023
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000

INTERVAL 0.552 - 0.829
CONTAINS 0.028%

the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.-
Token.-
Feature activation+0.021
trained
Tokentrained
Feature activation+0.596
force
Token force
Feature activation+0.731
that
Token that
Feature activation+0.000
initially
Token initially
Feature activation+0.000
fled
Token fled
Feature activation+0.000
in
Token in
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
ola
Tokenola
Feature activation+0.000
-
Token -
Feature activation+0.000
US
Token US
Feature activation+0.213
(
Token (
Feature activation+0.758
1972
Token1972
Feature activation+0.583
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
that
Token that
Feature activation+0.000
sight
Token sight
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.296
minister
Token minister
Feature activation+0.796
of
Token of
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
origin
Token origin
Feature activation+0.000
,
Token,
Feature activation+0.000
Jo
Token Jo
Feature activation+0.000
The
TokenThe
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.739
Court
Token Court
Feature activation+0.845
announced
Token announced
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
Guam
Token Guam
Feature activation+0.000
or
Token or
Feature activation+0.000
US
Token US
Feature activation+0.000
bases
Token bases
Feature activation+0.269
in
Token in
Feature activation+0.680
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 0.276 - 0.552
CONTAINS 0.049%

U
TokenU
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token 1
Feature activation+0.000
st
Tokenst
Feature activation+0.420
Lt
Token Lt
Feature activation+0.000
.
Token.
Feature activation+0.000
Nath
Token Nath
Feature activation+0.000
Perry
Token Perry
Feature activation+0.000
of
Token of
Feature activation+0.000
banks
Token banks
Feature activation+0.000
'
Token'
Feature activation+0.000
assets
Token assets
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.488
are
Token are
Feature activation+0.000
turned
Token turned
Feature activation+0.000
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
refining
Token refining
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.405
.
Token.
Feature activation+0.000
Pet
TokenPet
Feature activation+0.034
rol
Tokenrol
Feature activation+0.000
price
Token price
Feature activation+0.000
in
Token in
Feature activation+0.000
scheduled
Token scheduled
Feature activation+0.000
appearance
Token appearance
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
US
Token US
Feature activation+0.000
fundraiser
Token fundraiser
Feature activation+0.424
for
Token for
Feature activation+0.499
"
Token "
Feature activation+0.000
friends
Tokenfriends
Feature activation+0.000
"
Token"
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
report
Token report
Feature activation+0.000
by
Token by
Feature activation+0.000
US
Token US
Feature activation+0.813
-
Token-
Feature activation+0.397
based
Tokenbased
Feature activation+1.615
Enough
Token Enough
Feature activation+0.000
Project
Token Project
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.276
CONTAINS 99.887%

Tenn
Token Tenn
Feature activation+0.000
es
Tokenes
Feature activation+0.000
ee
Tokenee
Feature activation+0.000
Williams
Token Williams
Feature activation+0.000
before
Token before
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Glass
Token Glass
Feature activation+0.000
Men
Token Men
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
legendary
Token legendary
Feature activation+0.000
spy
Token spy
Feature activation+0.000
,
Token,
Feature activation+0.000
outstanding
Token outstanding
Feature activation+0.000
professional
Token professional
Feature activation+0.000
[
Token [
Feature activation+0.000
but
Token but
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
compel
Token compel
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
join
Token join
Feature activation+0.000
a
Token a
Feature activation+0.000
mandatory
Token mandatory
Feature activation+0.000
international
Token international
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
like
Token like
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000
followed
Token followed
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
a
Token a
Feature activation+0.000
dramatic
Token dramatic
Feature activation+0.000
employees
Token employees
Feature activation+0.000
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
adult
Token adult
Feature activation+0.000
children
Token children
Feature activation+0.000
save
Token save
Feature activation+0.000
money
Token money
Feature activation+0.000
on
Token on
Feature activation+0.000
rent
Token rent
Feature activation+0.000
and
Token and
Feature activation+0.000
household
Token household
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H3.6: (feature 21031)

TOP ACTIVATIONS
MAX = 3.069

UP
TokenUP
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
)
Token)
Feature activation+0.000
invited
Token invited
Feature activation+0.000
American
Token American
Feature activation+0.828
cities
Token cities
Feature activation+3.069
with
Token with
Feature activation+0.466
Sister
Token Sister
Feature activation+0.276
City
Token City
Feature activation+0.000
partnerships
Token partnerships
Feature activation+0.000
in
Token in
Feature activation+0.000
Cent
Token Cent
Feature activation+0.000
rists
Tokenrists
Feature activation+0.000
Can
Token Can
Feature activation+0.000
Change
Token Change
Feature activation+0.000
American
Token American
Feature activation+0.397
Politics
Token Politics
Feature activation+2.988
."
Token."
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
warning
Token warning
Feature activation+0.000
American
Token American
Feature activation+0.499
travelers
Token travelers
Feature activation+2.846
about
Token about
Feature activation+0.732
the
Token the
Feature activation+0.052
widespread
Token widespread
Feature activation+0.000
threats
Token threats
Feature activation+0.000
posed
Token posed
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+0.000
American
Token American
Feature activation+0.000
energy
Token energy
Feature activation+2.651
sources
Token sources
Feature activation+2.485
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
beneficial
Token beneficial
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
struggling
Token struggling
Feature activation+0.000
American
Token American
Feature activation+0.000
worker
Token worker
Feature activation+2.623
,
Token,
Feature activation+0.582
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
bike
Token bike
Feature activation+0.000
paths
Token paths
Feature activation+0.000
us
Token us
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
American
Token American
Feature activation+0.000
corporation
Token corporation
Feature activation+2.615
is
Token is
Feature activation+0.230
responding
Token responding
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
growing
Token growing
Feature activation+0.000
volume
Token volume
Feature activation+0.000
of
Token of
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
that
Token that
Feature activation+0.000
American
Token American
Feature activation+0.000
agencies
Token agencies
Feature activation+2.604
had
Token had
Feature activation+1.184
regarding
Token regarding
Feature activation+0.004
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.000
expect
Token expect
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
when
Token when
Feature activation+0.000
American
Token American
Feature activation+1.000
values
Token values
Feature activation+2.548
are
Token are
Feature activation+1.119
at
Token at
Feature activation+0.000
stake
Token stake
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
representatives
Token representatives
Feature activation+0.000
claim
Token claim
Feature activation+0.000
.
Token.
Feature activation+0.000
Since
Token Since
Feature activation+0.000
American
Token American
Feature activation+1.329
cities
Token cities
Feature activation+2.543
are
Token are
Feature activation+1.016
much
Token much
Feature activation+0.000
less
Token less
Feature activation+0.000
dense
Token dense
Feature activation+0.000
than
Token than
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
promote
Token promote
Feature activation+0.000
American
Token American
Feature activation+0.000
energy
Token energy
Feature activation+2.651
sources
Token sources
Feature activation+2.485
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
are
Token are
Feature activation+0.000
great
Token great
Feature activation+0.000
fans
Token fans
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.106
energy
Token energy
Feature activation+2.483
independence
Token independence
Feature activation+1.222
,
Token,
Feature activation+0.078
innovation
Token innovation
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
posted
Token posted
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.680
Family
Token Family
Feature activation+0.284
Association
Token Association
Feature activation+2.468
website
Token website
Feature activation+0.000
,
Token,
Feature activation+0.000
asking
Token asking
Feature activation+0.000
people
Token people
Feature activation+0.000
to
Token to
Feature activation+0.000
eliminating
Token eliminating
Feature activation+0.000
bureaucracy
Token bureaucracy
Feature activation+0.000
,
Token,
Feature activation+0.000
boost
Token boost
Feature activation+0.000
American
Token American
Feature activation+0.075
business
Token business
Feature activation+2.453
by
Token by
Feature activation+0.524
eliminating
Token eliminating
Feature activation+0.000
health
Token health
Feature activation+0.278
costs
Token costs
Feature activation+0.000
and
Token and
Feature activation+0.000
association
Token association
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.423
brewing
Token brewing
Feature activation+2.056
industry
Token industry
Feature activation+2.440
,
Token,
Feature activation+0.542
representing
Token representing
Feature activation+0.000
both
Token both
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.054
political
Token political
Feature activation+2.438
discourse
Token discourse
Feature activation+1.456
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
legislative
Token legislative
Feature activation+0.000
typo
Token typo
Feature activation+0.000
in
Token in
Feature activation+0.000
American
Token American
Feature activation+0.497
history
Token history
Feature activation+2.434
,
Token,
Feature activation+0.258
we
Token we
Feature activation+0.000
dug
Token dug
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
execution
Token execution
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.246
citizens
Token citizens
Feature activation+2.431
on
Token on
Feature activation+1.257
presidential
Token presidential
Feature activation+0.012
orders
Token orders
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
poll
Token poll
Feature activation+0.000
uting
Tokenuting
Feature activation+0.000
American
Token American
Feature activation+1.099
political
Token political
Feature activation+2.556
disc
Token disc
Feature activation+1.074
ourses
Tokenourses
Feature activation+2.425
was
Token was
Feature activation+0.144
that
Token that
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
forefront
Token forefront
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
political
Token political
Feature activation+1.804
consciousness
Token consciousness
Feature activation+2.419
,
Token,
Feature activation+0.117
swat
Token swat
Feature activation+0.000
hes
Tokenhes
Feature activation+0.000
of
Token of
Feature activation+0.105
pressure
Token pressure
Feature activation+0.000
every
Token every
Feature activation+0.000
corner
Token corner
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.370
continent
Token continent
Feature activation+2.408
,
Token,
Feature activation+0.657
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
DOI
Token DOI
Feature activation+0.000

Top DFA by src position
MAX = 3.886

A
TokenA
Feature activation-0.007
Top resid features:
UP
TokenUP
Feature activation-0.084
Top resid features:
AP
TokenAP
Feature activation-0.015
Top resid features:
)
Token)
Feature activation-0.039
Top resid features:
invited
Token invited
Feature activation-0.120
Top resid features:
American
Token American
Feature activation+3.886
Top resid features:
cities
Token cities
Feature activation+0.103
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Sister
Token Sister
Feature activation+0.000
Top resid features:
City
Token City
Feature activation+0.000
Top resid features:
partnerships
Token partnerships
Feature activation+0.000
Top resid features:
How
Token How
Feature activation-0.010
Top resid features:
Cent
Token Cent
Feature activation+0.010
Top resid features:
rists
Tokenrists
Feature activation-0.061
Top resid features:
Can
Token Can
Feature activation-0.027
Top resid features:
Change
Token Change
Feature activation-0.072
Top resid features:
American
Token American
Feature activation+3.355
Top resid features:
Politics
Token Politics
Feature activation+0.412
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
It
TokenIt
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
alert
Token alert
Feature activation-0.013
Top resid features:
on
Token on
Feature activation-0.017
Top resid features:
Monday
Token Monday
Feature activation-0.033
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
warning
Token warning
Feature activation+0.093
Top resid features:
American
Token American
Feature activation+3.040
Top resid features:
travelers
Token travelers
Feature activation+0.270
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
widespread
Token widespread
Feature activation+0.000
Top resid features:
threats
Token threats
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
âĢ
Token âĢ
Feature activation+0.010
Top resid features:
ľ
Tokenľ
Feature activation+0.011
Top resid features:
To
TokenTo
Feature activation-0.009
Top resid features:
promote
Token promote
Feature activation-0.111
Top resid features:
American
Token American
Feature activation+3.299
Top resid features:
energy
Token energy
Feature activation+0.172
Top resid features:
sources
Token sources
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
projects
Token projects
Feature activation-0.048
Top resid features:
beneficial
Token beneficial
Feature activation-0.032
Top resid features:
for
Token for
Feature activation+0.019
Top resid features:
the
Token the
Feature activation-0.280
Top resid features:
struggling
Token struggling
Feature activation+0.044
Top resid features:
American
Token American
Feature activation+3.360
Top resid features:
worker
Token worker
Feature activation+0.180
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
bike
Token bike
Feature activation+0.000
Top resid features:
shows
Token shows
Feature activation-0.016
Top resid features:
us
Token us
Feature activation-0.008
Top resid features:
that
Token that
Feature activation-0.050
Top resid features:
the
Token the
Feature activation-0.194
Top resid features:
powerful
Token powerful
Feature activation-0.029
Top resid features:
American
Token American
Feature activation+3.268
Top resid features:
corporation
Token corporation
Feature activation+0.213
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
responding
Token responding
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
precise
Token precise
Feature activation-0.000
Top resid features:
volume
Token volume
Feature activation-0.010
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
intelligence
Token intelligence
Feature activation-0.056
Top resid features:
that
Token that
Feature activation-0.068
Top resid features:
American
Token American
Feature activation+3.506
Top resid features:
agencies
Token agencies
Feature activation-0.038
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
regarding
Token regarding
Feature activation+0.000
Top resid features:
al
Token al
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.024
Top resid features:
expect
Token expect
Feature activation-0.037
Top resid features:
to
Token to
Feature activation-0.030
Top resid features:
see
Token see
Feature activation-0.014
Top resid features:
when
Token when
Feature activation+0.022
Top resid features:
American
Token American
Feature activation+2.997
Top resid features:
values
Token values
Feature activation+0.240
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
stake
Token stake
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
industry
Token industry
Feature activation+0.014
Top resid features:
representatives
Token representatives
Feature activation-0.006
Top resid features:
claim
Token claim
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Since
Token Since
Feature activation-0.167
Top resid features:
American
Token American
Feature activation+3.022
Top resid features:
cities
Token cities
Feature activation+0.243
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
dense
Token dense
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
âĢ
Token âĢ
Feature activation+0.023
Top resid features:
ľ
Tokenľ
Feature activation+0.013
Top resid features:
To
TokenTo
Feature activation-0.001
Top resid features:
promote
Token promote
Feature activation-0.108
Top resid features:
American
Token American
Feature activation+3.339
Top resid features:
energy
Token energy
Feature activation+0.005
Top resid features:
sources
Token sources
Feature activation-0.128
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
Republicans
TokenRepublicans
Feature activation-0.094
Top resid features:
are
Token are
Feature activation-0.015
Top resid features:
great
Token great
Feature activation-0.025
Top resid features:
fans
Token fans
Feature activation-0.071
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
American
Token American
Feature activation+3.146
Top resid features:
energy
Token energy
Feature activation+0.127
Top resid features:
independence
Token independence
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
innovation
Token innovation
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.082
Top resid features:
posted
Token posted
Feature activation-0.057
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.043
Top resid features:
American
Token American
Feature activation+3.208
Top resid features:
Family
Token Family
Feature activation+0.049
Top resid features:
Association
Token Association
Feature activation-0.107
Top resid features:
website
Token website
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
asking
Token asking
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.003
Top resid features:
eliminating
Token eliminating
Feature activation-0.002
Top resid features:
bureaucracy
Token bureaucracy
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
boost
Token boost
Feature activation-0.034
Top resid features:
American
Token American
Feature activation+3.092
Top resid features:
business
Token business
Feature activation+0.154
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
eliminating
Token eliminating
Feature activation+0.000
Top resid features:
health
Token health
Feature activation+0.000
Top resid features:
costs
Token costs
Feature activation+0.000
Top resid features:
national
Token national
Feature activation+0.000
Top resid features:
trade
Token trade
Feature activation-0.008
Top resid features:
association
Token association
Feature activation-0.069
Top resid features:
for
Token for
Feature activation+0.070
Top resid features:
the
Token the
Feature activation-0.245
Top resid features:
American
Token American
Feature activation+3.169
Top resid features:
brewing
Token brewing
Feature activation+0.225
Top resid features:
industry
Token industry
Feature activation-0.074
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
representing
Token representing
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
contemplate
Token contemplate
Feature activation-0.055
Top resid features:
the
Token the
Feature activation-0.034
Top resid features:
current
Token current
Feature activation-0.062
Top resid features:
state
Token state
Feature activation+0.020
Top resid features:
of
Token of
Feature activation-0.096
Top resid features:
American
Token American
Feature activation+3.106
Top resid features:
political
Token political
Feature activation+0.256
Top resid features:
discourse
Token discourse
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
most
Token most
Feature activation-0.023
Top resid features:
expensive
Token expensive
Feature activation+0.106
Top resid features:
legislative
Token legislative
Feature activation-0.033
Top resid features:
typo
Token typo
Feature activation+0.054
Top resid features:
in
Token in
Feature activation-0.043
Top resid features:
American
Token American
Feature activation+3.006
Top resid features:
history
Token history
Feature activation+0.073
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
dug
Token dug
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
applied
Token applied
Feature activation-0.019
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.031
Top resid features:
execution
Token execution
Feature activation-0.049
Top resid features:
of
Token of
Feature activation-0.125
Top resid features:
American
Token American
Feature activation+3.029
Top resid features:
citizens
Token citizens
Feature activation+0.267
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
presidential
Token presidential
Feature activation+0.000
Top resid features:
orders
Token orders
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.156
Top resid features:
poll
Token poll
Feature activation+0.010
Top resid features:
uting
Tokenuting
Feature activation-0.015
Top resid features:
American
Token American
Feature activation+3.030
Top resid features:
political
Token political
Feature activation+0.044
Top resid features:
disc
Token disc
Feature activation+0.042
Top resid features:
ourses
Tokenourses
Feature activation-0.025
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
into
Token into
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
forefront
Token forefront
Feature activation-0.046
Top resid features:
of
Token of
Feature activation-0.084
Top resid features:
the
Token the
Feature activation-0.176
Top resid features:
American
Token American
Feature activation+3.299
Top resid features:
political
Token political
Feature activation+0.069
Top resid features:
consciousness
Token consciousness
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
swat
Token swat
Feature activation+0.000
Top resid features:
hes
Tokenhes
Feature activation+0.000
Top resid features:
affects
Token affects
Feature activation-0.012
Top resid features:
every
Token every
Feature activation-0.003
Top resid features:
corner
Token corner
Feature activation+0.047
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
the
Token the
Feature activation-0.069
Top resid features:
American
Token American
Feature activation+2.942
Top resid features:
continent
Token continent
Feature activation+0.156
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.10

Head 3: 0.04

Head 4: 0.03

Head 5: 0.03

Head 6: 0.44

Head 7: 0.09

Head 8: 0.04

Head 9: 0.04

Head 10: 0.09

Head 11: 0.05

Positive logits

iquette1.38

Ambassador1.21

Slave1.19

ambassador1.18

ember1.14

Standards1.13

vre1.08

��1.08

civilization1.07

consulate1.06

Tire1.06

Diplom1.05

voy1.05

Embassy1.04

Alias1.04

Society1.03

isine1.03

Advocate1.03

greg1.03

ICAN1.03

Negative logits

tein-1.16

arious-1.16

delet-1.14

hypert-1.10

redund-1.10

zes-1.08

byn-1.06

deleting-1.04

onomous-1.02

Iw-1.02

Croatian-0.99

deletion-0.98

eru-0.98

epile-0.97

subdivision-0.97

burse-0.97

Uk-0.97

plet-0.96

ş-0.96

layoffs-0.96

INTERVAL 2.762 - 3.069
CONTAINS 0.000%

on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
warning
Token warning
Feature activation+0.000
American
Token American
Feature activation+0.499
travelers
Token travelers
Feature activation+2.846
about
Token about
Feature activation+0.732
the
Token the
Feature activation+0.052
widespread
Token widespread
Feature activation+0.000
threats
Token threats
Feature activation+0.000
posed
Token posed
Feature activation+0.000
Cent
Token Cent
Feature activation+0.000
rists
Tokenrists
Feature activation+0.000
Can
Token Can
Feature activation+0.000
Change
Token Change
Feature activation+0.000
American
Token American
Feature activation+0.397
Politics
Token Politics
Feature activation+2.988
."
Token."
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
UP
TokenUP
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
)
Token)
Feature activation+0.000
invited
Token invited
Feature activation+0.000
American
Token American
Feature activation+0.828
cities
Token cities
Feature activation+3.069
with
Token with
Feature activation+0.466
Sister
Token Sister
Feature activation+0.276
City
Token City
Feature activation+0.000
partnerships
Token partnerships
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.455 - 2.762
CONTAINS 0.001%

volume
Token volume
Feature activation+0.000
of
Token of
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
that
Token that
Feature activation+0.000
American
Token American
Feature activation+0.000
agencies
Token agencies
Feature activation+2.604
had
Token had
Feature activation+1.184
regarding
Token regarding
Feature activation+0.004
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
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+0.000
American
Token American
Feature activation+0.000
energy
Token energy
Feature activation+2.651
sources
Token sources
Feature activation+2.485
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
beneficial
Token beneficial
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
struggling
Token struggling
Feature activation+0.000
American
Token American
Feature activation+0.000
worker
Token worker
Feature activation+2.623
,
Token,
Feature activation+0.582
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
bike
Token bike
Feature activation+0.000
paths
Token paths
Feature activation+0.000
posted
Token posted
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.680
Family
Token Family
Feature activation+0.284
Association
Token Association
Feature activation+2.468
website
Token website
Feature activation+0.000
,
Token,
Feature activation+0.000
asking
Token asking
Feature activation+0.000
people
Token people
Feature activation+0.000
to
Token to
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
promote
Token promote
Feature activation+0.000
American
Token American
Feature activation+0.000
energy
Token energy
Feature activation+2.651
sources
Token sources
Feature activation+2.485
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000

INTERVAL 2.148 - 2.455
CONTAINS 0.003%

announced
Token announced
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
for
Token for
Feature activation+0.000
American
Token American
Feature activation+0.000
independence
Token independence
Feature activation+2.222
on
Token on
Feature activation+1.328
July
Token July
Feature activation+0.000
4
Token 4
Feature activation+0.000
,
Token,
Feature activation+0.000
17
Token 17
Feature activation+0.000
P
TokenP
Feature activation+0.000
_
Token_
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
An
TokenAn
Feature activation+0.000
American
Token American
Feature activation+0.092
building
Token building
Feature activation+2.211
materials
Token materials
Feature activation+1.945
company
Token company
Feature activation+2.052
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+1.136
Bever
Token Bever
Feature activation+0.414
age
Tokenage
Feature activation+2.394
Association
Token Association
Feature activation+2.300
dismissed
Token dismissed
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
870
Token870
Feature activation+0.000
troops
Token troops
Feature activation+0.000
include
Token include
Feature activation+0.000
American
Token American
Feature activation+0.000
trainers
Token trainers
Feature activation+2.360
and
Token and
Feature activation+0.593
advisers
Token advisers
Feature activation+1.879
array
Token array
Feature activation+0.000
ed
Tokened
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.054
political
Token political
Feature activation+2.438
discourse
Token discourse
Feature activation+1.456
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.841 - 2.148
CONTAINS 0.005%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+0.686
Family
Token Family
Feature activation+0.634
Association
Token Association
Feature activation+2.108
(
Token (
Feature activation+0.608
A
TokenA
Feature activation+0.000
FA
TokenFA
Feature activation+0.000
),
Token),
Feature activation+0.000
based
Token based
Feature activation+0.000
proliferation
Token proliferation
Feature activation+0.000
of
Token of
Feature activation+0.000
gambling
Token gambling
Feature activation+0.000
in
Token in
Feature activation+0.000
American
Token American
Feature activation+0.547
society
Token society
Feature activation+1.963
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
accepted
Token accepted
Feature activation+0.000
variations
Token variations
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.705
classic
Token classic
Feature activation+1.865
of
Token of
Feature activation+1.845
mac
Token mac
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
n
Tokenn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+0.000
how
Token how
Feature activation+0.000
many
Token many
Feature activation+0.000
American
Token American
Feature activation+0.000
communications
Token communications
Feature activation+1.932
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
mistakenly
Token mistakenly
Feature activation+0.000
collected
Token collected
Feature activation+0.000
by
Token by
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+0.000
Forest
Token Forest
Feature activation+0.000
and
Token and
Feature activation+0.522
Paper
Token Paper
Feature activation+1.891
Association
Token Association
Feature activation+1.794
estimates
Token estimates
Feature activation+0.000
that
Token that
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
logging
Token logging
Feature activation+0.000

INTERVAL 1.535 - 1.841
CONTAINS 0.006%

marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
victory
Token victory
Feature activation+0.000
for
Token for
Feature activation+0.000
American
Token American
Feature activation+0.000
freedom
Token freedom
Feature activation+1.599
over
Token over
Feature activation+0.484
Presidential
Token Presidential
Feature activation+0.000
tyranny
Token tyranny
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
-
Token -
Feature activation+0.000
American
TokenAmerican
Feature activation+0.149
Institutes
Token Institutes
Feature activation+0.163
for
Token for
Feature activation+1.642
Research
Token Research
Feature activation+0.622
,
Token,
Feature activation+0.466
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
29
Token 29
Feature activation+0.000
of
Token of
Feature activation+0.000
elderly
Token elderly
Feature activation+0.000
tourists
Token tourists
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
American
TokenAmerican
Feature activation+0.860
,
Token,
Feature activation+1.682
Japanese
Token Japanese
Feature activation+0.017
,
Token,
Feature activation+0.000
British
Token British
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
w
Tokenw
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
War
Token War
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
American
Token American
Feature activation+0.000
culture
Token culture
Feature activation+1.795
at
Token at
Feature activation+0.579
least
Token least
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
ocating
Tokenocating
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
American
Token American
Feature activation+0.000
military
Token military
Feature activation+1.073
installation
Token installation
Feature activation+1.586
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
truth
Token truth
Feature activation+0.000

INTERVAL 1.228 - 1.535
CONTAINS 0.007%

forever
Token forever
Feature activation+0.000
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
people
Token people
Feature activation+1.399
to
Token to
Feature activation+0.248
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
input
Token input
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
prominent
Token prominent
Feature activation+0.000
critic
Token critic
Feature activation+0.000
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.271
foreign
Token foreign
Feature activation+1.468
policy
Token policy
Feature activation+1.774
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
has
Token has
Feature activation+0.000
frequently
Token frequently
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
American
Token American
Feature activation+0.439
attacking
Token attacking
Feature activation+1.445
midfielder
Token midfielder
Feature activation+0.328
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
staple
Token staple
Feature activation+0.000
of
Token of
Feature activation+0.000
perspectives
Token perspectives
Feature activation+0.000
:
Token:
Feature activation+0.000
American
Token American
Feature activation+0.233
military
Token military
Feature activation+1.902
members
Token members
Feature activation+1.357
,
Token,
Feature activation+1.257
people
Token people
Feature activation+0.771
in
Token in
Feature activation+0.049
the
Token the
Feature activation+0.000
anti
Token anti
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
American
TokenAmerican
Feature activation+1.094
security
Token security
Feature activation+2.031
expert
Token expert
Feature activation+1.505
Bruce
Token Bruce
Feature activation+0.000
Blair
Token Blair
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000

INTERVAL 0.921 - 1.228
CONTAINS 0.007%

Officials
TokenOfficials
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
nonprofit
Token nonprofit
Feature activation+0.000
American
Token American
Feature activation+0.267
Astron
Token Astron
Feature activation+1.100
omical
Tokenomical
Feature activation+1.384
Society
Token Society
Feature activation+1.585
are
Token are
Feature activation+0.000
warning
Token warning
Feature activation+0.000
people
Token people
Feature activation+0.000
militants
Token militants
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
American
Token American
Feature activation+0.000
drone
Token drone
Feature activation+0.727
strike
Token strike
Feature activation+1.030
in
Token in
Feature activation+0.621
N
Token N
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
har
Tokenhar
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
American
TokenAmerican
Feature activation+1.249
actor
Token actor
Feature activation+2.029
and
Token and
Feature activation+1.334
professional
Token professional
Feature activation+0.948
wrestler
Token wrestler
Feature activation+1.992
Ċ
TokenĊ
Feature activation+1.568
Ċ
TokenĊ
Feature activation+1.210
"
Token"
Feature activation+0.000
David
TokenDavid
Feature activation+0.000
(
Token (
Feature activation+0.000
Pierre
TokenPierre
Feature activation+0.000
Trudeau
Token Trudeau
Feature activation+0.000
,
Token,
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Prime
Token Prime
Feature activation+1.104
Minister
Token Minister
Feature activation+1.254
for
Token for
Feature activation+0.738
over
Token over
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
American
Token American
Feature activation+0.000
billionaire
Token billionaire
Feature activation+0.942
who
Token who
Feature activation+0.207
had
Token had
Feature activation+0.000
spent
Token spent
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.614 - 0.921
CONTAINS 0.013%

soft
Token soft
Feature activation+0.000
landing
Token landing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
housing
Token housing
Feature activation+0.629
market
Token market
Feature activation+0.904
in
Token in
Feature activation+0.420
2014
Token 2014
Feature activation+0.000
and
Token and
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
A
TokenA
Feature activation+0.000
UP
TokenUP
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
)
Token)
Feature activation+0.000
invited
Token invited
Feature activation+0.000
American
Token American
Feature activation+0.828
cities
Token cities
Feature activation+3.069
with
Token with
Feature activation+0.466
Sister
Token Sister
Feature activation+0.276
City
Token City
Feature activation+0.000
partnerships
Token partnerships
Feature activation+0.000
overwhelming
Token overwhelming
Feature activation+0.000
8
Token 8
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
American
Token American
Feature activation+0.000
troops
Token troops
Feature activation+0.681
fighting
Token fighting
Feature activation+0.608
as
Token as
Feature activation+0.000
United
Token United
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
forces
Token forces
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
yet
Token yet
Feature activation+0.000
American
Token American
Feature activation+0.000
modern
Token modern
Feature activation+1.526
life
Token life
Feature activation+0.887
,
Token,
Feature activation+0.584
with
Token with
Feature activation+0.000
its
Token its
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
daddy
Token daddy
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
an
Token an
Feature activation+0.000
American
Token American
Feature activation+0.000
citizen
Token citizen
Feature activation+0.632
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
R
TokenR
Feature activation+0.000
USH
TokenUSH
Feature activation+0.000

INTERVAL 0.307 - 0.614
CONTAINS 0.024%

viewpoints
Token viewpoints
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
broadcasting
Token broadcasting
Feature activation+0.258
system
Token system
Feature activation+0.397
,
Token,
Feature activation+0.047
the
Token the
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
notes
Token notes
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
allows
Token allows
Feature activation+0.000
American
Token American
Feature activation+0.000
troops
Token troops
Feature activation+1.669
to
Token to
Feature activation+0.439
build
Token build
Feature activation+0.762
storage
Token storage
Feature activation+0.350
facilities
Token facilities
Feature activation+0.000
for
Token for
Feature activation+0.000
maritime
Token maritime
Feature activation+0.000
doing
Token doing
Feature activation+0.000
better
Token better
Feature activation+0.000
lately
Token lately
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
American
Token American
Feature activation+0.502
-
Token-
Feature activation+0.682
led
Tokenled
Feature activation+1.359
air
Token air
Feature activation+1.299
assault
Token assault
Feature activation+0.928
against
Token against
Feature activation+0.035
received
Token received
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000
calls
Token calls
Feature activation+0.000
from
Token from
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Prime
Token Prime
Feature activation+0.438
Minister
Token Minister
Feature activation+0.519
Justin
Token Justin
Feature activation+0.000
Trudeau
Token Trudeau
Feature activation+0.000
and
Token and
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
housing
Token housing
Feature activation+0.629
market
Token market
Feature activation+0.904
in
Token in
Feature activation+0.420
2014
Token 2014
Feature activation+0.000
and
Token and
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.307
CONTAINS 99.934%

key
Token key
Feature activation+0.000
theme
Token theme
Feature activation+0.000
of
Token of
Feature activation+0.000
female
Token female
Feature activation+0.000
agency
Token agency
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
90
Token 90
Feature activation+0.000
s
Tokens
Feature activation+0.000
house
Token house
Feature activation+0.000
rhythm
Token rhythm
Feature activation+0.000
N
Token N
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
Soviet
Token Soviet
Feature activation+0.000
Union
Token Union
Feature activation+0.000
and
Token and
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
Kennedy
Token Kennedy
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
publishers
Token publishers
Feature activation+0.000
passed
Token passed
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
Another
TokenAnother
Feature activation+0.000
student
Token student
Feature activation+0.000
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
--
Token --
Feature activation+0.000
a
Token a
Feature activation+0.000
21
Token 21
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
Brick
Token Brick
Feature activation+0.000
man
Tokenman
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
analyst
Token analyst
Feature activation+0.000
at
Token at
Feature activation+0.000
ET
Token ET
Feature activation+0.000
M
TokenM
Feature activation+0.000
analytics
Token analytics
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H3.6: (feature 12269)

TOP ACTIVATIONS
MAX = 3.724

campaign
Token campaign
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.125
seemed
Token seemed
Feature activation+3.724
as
Token as
Feature activation+0.810
if
Token if
Feature activation+0.497
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.538
a
Token a
Feature activation+0.000
and
Token and
Feature activation+0.000
contributors
Token contributors
Feature activation+0.000
from
Token from
Feature activation+0.000
just
Token just
Feature activation+0.102
about
Token about
Feature activation+2.103
every
Token every
Feature activation+3.346
major
Token major
Feature activation+0.000
media
Token media
Feature activation+0.000
outlet
Token outlet
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
favorite
Token favorite
Feature activation+0.000
tweets
Token tweets
Feature activation+0.000
from
Token from
Feature activation+0.000
just
Token just
Feature activation+0.692
about
Token about
Feature activation+2.443
anybody
Token anybody
Feature activation+3.299
in
Token in
Feature activation+0.049
our
Token our
Feature activation+0.566
orbit
Token orbit
Feature activation+0.000
:
Token:
Feature activation+0.000
gadget
Token gadget
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.202
about
Token about
Feature activation+1.706
any
Token any
Feature activation+3.225
situation
Token situation
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
are
Token are
Feature activation+0.000
actively
Token actively
Feature activation+0.000
trying
Token trying
Feature activation+0.000
just
Token just
Feature activation+0.192
about
Token about
Feature activation+2.388
everything
Token everything
Feature activation+3.189
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
to
Token to
Feature activation+0.000
improve
Token improve
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+0.000
normal
Token normal
Feature activation+0.000
in
Token in
Feature activation+0.000
just
Token just
Feature activation+0.572
about
Token about
Feature activation+1.929
any
Token any
Feature activation+3.185
fresh
Token fresh
Feature activation+0.000
C
Token C
Feature activation+0.000
NC
TokenNC
Feature activation+0.000
part
Token part
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.212
don
Token don
Feature activation+1.907
âĢ
TokenâĢ
Feature activation+2.033
Ļ
TokenĻ
Feature activation+0.760
t
Tokent
Feature activation+3.100
repeat
Token repeat
Feature activation+0.366
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
mistake
Token mistake
Feature activation+0.000
.
Token.
Feature activation+0.000
exceptions
Token exceptions
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.203
nothing
Token nothing
Feature activation+3.066
that
Token that
Feature activation+0.000
comes
Token comes
Feature activation+0.000
even
Token even
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
medical
Token medical
Feature activation+0.000
card
Token card
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+1.828
any
Token any
Feature activation+3.057
reason
Token reason
Feature activation+0.070
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
man
Tokenman
Feature activation+0.000
is
Token is
Feature activation+0.000
facing
Token facing
Feature activation+0.000
just
Token just
Feature activation+0.014
as
Token as
Feature activation+0.924
much
Token much
Feature activation+3.053
uncertainty
Token uncertainty
Feature activation+0.039
as
Token as
Feature activation+0.283
those
Token those
Feature activation+0.000
being
Token being
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
have
Token have
Feature activation+0.000
likely
Token likely
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
what
Token what
Feature activation+0.000
just
Token just
Feature activation+0.000
happened
Token happened
Feature activation+3.007
to
Token to
Feature activation+1.792
JPMorgan
Token JPMorgan
Feature activation+0.000
.
Token.
Feature activation+0.000
Levin
Token Levin
Feature activation+0.000
told
Token told
Feature activation+0.000
of
Token of
Feature activation+0.000
mouse
Token mouse
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+1.098
any
Token any
Feature activation+2.982
piece
Token piece
Feature activation+0.000
information
Token information
Feature activation+0.000
can
Token can
Feature activation+0.373
be
Token be
Feature activation+0.000
unearthed
Token unearthed
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
began
Token began
Feature activation+0.000
as
Token as
Feature activation+0.000
just
Token just
Feature activation+0.000
fun
Token fun
Feature activation+2.914
Q
Token Q
Feature activation+0.000
&
Token&
Feature activation+0.000
As
TokenAs
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
see
Token see
Feature activation+0.000
sk
Token sk
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+1.521
everywhere
Token everywhere
Feature activation+2.885
sw
Token sw
Feature activation+0.000
iping
Tokeniping
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.053
seems
Token seems
Feature activation+2.855
that
Token that
Feature activation+0.038
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
does
Token does
Feature activation+0.000
better
Token better
Feature activation+0.000
and
Token and
Feature activation+0.000
carried
Token carried
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.254
like
Token like
Feature activation+0.623
any
Token any
Feature activation+2.822
other
Token other
Feature activation+0.000
cargo
Token cargo
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
505
Token 505
Feature activation+0.000
can
Token can
Feature activation+0.000
always
Token always
Feature activation+0.000
just
Token just
Feature activation+0.000
search
Token search
Feature activation+0.000
for
Token for
Feature activation+0.048
any
Token any
Feature activation+2.755
term
Token term
Feature activation+0.000
by
Token by
Feature activation+0.000
typing
Token typing
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
miracles
Token miracles
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
just
Token just
Feature activation+0.806
figure
Token figure
Feature activation+2.685
out
Token out
Feature activation+0.455
what
Token what
Feature activation+0.252
language
Token language
Feature activation+0.000
people
Token people
Feature activation+0.000
like
Token like
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+2.678
important
Token important
Feature activation+1.006
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
live
Tokenlive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
get
Token get
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+2.678
different
Token different
Feature activation+0.000
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
might
Token might
Feature activation+0.155
be
Token be
Feature activation+0.000

Top DFA by src position
MAX = 4.471

independence
Token independence
Feature activation-0.000
Top resid features:
campaign
Token campaign
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
how
Token how
Feature activation-0.172
Top resid features:
it
Token it
Feature activation-0.036
Top resid features:
just
Token just
Feature activation+4.471
Top resid features:
seemed
Token seemed
Feature activation+0.079
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Journalists
Token Journalists
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.024
Top resid features:
contributors
Token contributors
Feature activation-0.011
Top resid features:
from
Token from
Feature activation-0.170
Top resid features:
just
Token just
Feature activation+4.440
Top resid features:
about
Token about
Feature activation-0.249
Top resid features:
every
Token every
Feature activation-0.025
Top resid features:
major
Token major
Feature activation+0.000
Top resid features:
media
Token media
Feature activation+0.000
Top resid features:
outlet
Token outlet
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.287
Top resid features:
our
Token our
Feature activation-0.016
Top resid features:
favorite
Token favorite
Feature activation-0.009
Top resid features:
tweets
Token tweets
Feature activation-0.008
Top resid features:
from
Token from
Feature activation-0.031
Top resid features:
just
Token just
Feature activation+4.215
Top resid features:
about
Token about
Feature activation-0.167
Top resid features:
anybody
Token anybody
Feature activation-0.063
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
orbit
Token orbit
Feature activation+0.000
Top resid features:
which
Token which
Feature activation-0.007
Top resid features:
can
Token can
Feature activation-0.066
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
used
Token used
Feature activation-0.011
Top resid features:
for
Token for
Feature activation-0.058
Top resid features:
just
Token just
Feature activation+4.251
Top resid features:
about
Token about
Feature activation-0.204
Top resid features:
any
Token any
Feature activation-0.036
Top resid features:
situation
Token situation
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
days
Token days
Feature activation+0.003
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.012
Top resid features:
are
Token are
Feature activation-0.012
Top resid features:
actively
Token actively
Feature activation+0.005
Top resid features:
trying
Token trying
Feature activation+0.023
Top resid features:
just
Token just
Feature activation+4.054
Top resid features:
about
Token about
Feature activation-0.260
Top resid features:
everything
Token everything
Feature activation-0.052
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.280
Top resid features:
rs
Tokenrs
Feature activation-0.007
Top resid features:
are
Token are
Feature activation-0.013
Top resid features:
normal
Token normal
Feature activation-0.017
Top resid features:
in
Token in
Feature activation-0.069
Top resid features:
just
Token just
Feature activation+4.235
Top resid features:
about
Token about
Feature activation-0.304
Top resid features:
any
Token any
Feature activation-0.024
Top resid features:
fresh
Token fresh
Feature activation+0.000
Top resid features:
C
Token C
Feature activation+0.000
Top resid features:
NC
TokenNC
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
ll
Tokenll
Feature activation+0.002
Top resid features:
eventually
Token eventually
Feature activation-0.010
Top resid features:
realize
Token realize
Feature activation-0.020
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Just
Token Just
Feature activation+3.623
Top resid features:
don
Token don
Feature activation-0.104
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.037
Top resid features:
t
Tokent
Feature activation+0.044
Top resid features:
repeat
Token repeat
Feature activation+0.000
Top resid features:
few
Token few
Feature activation+0.004
Top resid features:
exceptions
Token exceptions
Feature activation+0.017
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
there
Token there
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.104
Top resid features:
just
Token just
Feature activation+3.719
Top resid features:
nothing
Token nothing
Feature activation+0.038
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
comes
Token comes
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
medical
Token medical
Feature activation+0.004
Top resid features:
card
Token card
Feature activation-0.001
Top resid features:
for
Token for
Feature activation-0.087
Top resid features:
just
Token just
Feature activation+4.129
Top resid features:
about
Token about
Feature activation-0.296
Top resid features:
any
Token any
Feature activation-0.032
Top resid features:
reason
Token reason
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Why
Token Why
Feature activation+0.000
Top resid features:
old
Tokenold
Feature activation-0.001
Top resid features:
defence
Token defence
Feature activation-0.006
Top resid features:
man
Tokenman
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.013
Top resid features:
facing
Token facing
Feature activation+0.006
Top resid features:
just
Token just
Feature activation+4.369
Top resid features:
as
Token as
Feature activation-0.643
Top resid features:
much
Token much
Feature activation-0.086
Top resid features:
uncertainty
Token uncertainty
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
likely
Token likely
Feature activation-0.013
Top resid features:
prevented
Token prevented
Feature activation+0.010
Top resid features:
what
Token what
Feature activation-0.270
Top resid features:
just
Token just
Feature activation+3.776
Top resid features:
happened
Token happened
Feature activation+0.123
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
JPMorgan
Token JPMorgan
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Levin
Token Levin
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
click
Token click
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
mouse
Token mouse
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.035
Top resid features:
just
Token just
Feature activation+3.934
Top resid features:
about
Token about
Feature activation-0.260
Top resid features:
any
Token any
Feature activation-0.026
Top resid features:
piece
Token piece
Feature activation+0.000
Top resid features:
information
Token information
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
questions
Token questions
Feature activation-0.010
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
It
Token It
Feature activation+0.007
Top resid features:
began
Token began
Feature activation+0.037
Top resid features:
as
Token as
Feature activation-0.212
Top resid features:
just
Token just
Feature activation+3.713
Top resid features:
fun
Token fun
Feature activation+0.006
Top resid features:
Q
Token Q
Feature activation+0.000
Top resid features:
&
Token&
Feature activation+0.000
Top resid features:
As
TokenAs
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
continue
Token continue
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
see
Token see
Feature activation+0.002
Top resid features:
sk
Token sk
Feature activation-0.016
Top resid features:
immers
Tokenimmers
Feature activation-0.016
Top resid features:
just
Token just
Feature activation+3.741
Top resid features:
about
Token about
Feature activation-0.115
Top resid features:
everywhere
Token everywhere
Feature activation-0.091
Top resid features:
sw
Token sw
Feature activation+0.000
Top resid features:
iping
Tokeniping
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
long
Token long
Feature activation+0.001
Top resid features:
time
Token time
Feature activation-0.008
Top resid features:
and
Token and
Feature activation-0.044
Top resid features:
it
Token it
Feature activation-0.086
Top resid features:
just
Token just
Feature activation+3.586
Top resid features:
seems
Token seems
Feature activation+0.037
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
economy
Token economy
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:
water
Token water
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.045
Top resid features:
carried
Token carried
Feature activation-0.007
Top resid features:
it
Token it
Feature activation+0.025
Top resid features:
just
Token just
Feature activation+3.782
Top resid features:
like
Token like
Feature activation-0.267
Top resid features:
any
Token any
Feature activation-0.001
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
cargo
Token cargo
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Also
Token Also
Feature activation-0.035
Top resid features:
you
Token you
Feature activation-0.004
Top resid features:
can
Token can
Feature activation-0.004
Top resid features:
always
Token always
Feature activation-0.000
Top resid features:
just
Token just
Feature activation+3.475
Top resid features:
search
Token search
Feature activation+0.043
Top resid features:
for
Token for
Feature activation-0.048
Top resid features:
any
Token any
Feature activation-0.044
Top resid features:
term
Token term
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
miracles
Token miracles
Feature activation-0.003
Top resid features:
every
Token every
Feature activation+0.006
Top resid features:
day
Token day
Feature activation+0.005
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.020
Top resid features:
just
Token just
Feature activation+3.175
Top resid features:
figure
Token figure
Feature activation+0.068
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
language
Token language
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
)
Token)
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation-0.034
Top resid features:
I
TokenI
Feature activation-0.021
Top resid features:
know
Token know
Feature activation+0.056
Top resid features:
just
Token just
Feature activation+3.296
Top resid features:
how
Token how
Feature activation+0.049
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ĺ
Tokenĺ
Feature activation+0.000
Top resid features:
live
Tokenlive
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.029
Top resid features:
get
Token get
Feature activation+0.003
Top resid features:
us
Token us
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
imagine
Token imagine
Feature activation+0.150
Top resid features:
just
Token just
Feature activation+3.165
Top resid features:
how
Token how
Feature activation+0.015
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
economy
Token economy
Feature activation+0.000
Top resid features:
might
Token might
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.07

Head 2: 0.07

Head 3: 0.04

Head 4: 0.02

Head 5: 0.03

Head 6: 0.43

Head 7: 0.05

Head 8: 0.05

Head 9: 0.05

Head 10: 0.05

Head 11: 0.12

Positive logits

darn1.08

Switch1.06

aspirin1.04

Sold1.03

Emails1.01

rpm0.98

Merit0.96

EVA0.95

Horror0.94

Airl0.93

Solitaire0.93

AIR0.93

Protective0.93

antioxid0.93

unbeliev0.92

behavi0.92

Defin0.92

horm0.91

0.91

ROS0.91

Negative logits

meet-1.33

ourses-1.26

uli-1.19

elist-1.18

advertisement-1.15

orship-1.12

heast-1.11

zik-1.11

posts-1.09

zzi-1.06

bryce-1.05

upp-1.05

upt-1.05

arters-1.04

achable-1.04

ile-1.04

pora-1.04

tu-1.03

only-1.03

orate-1.02

INTERVAL 3.352 - 3.724
CONTAINS 0.000%

campaign
Token campaign
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.125
seemed
Token seemed
Feature activation+3.724
as
Token as
Feature activation+0.810
if
Token if
Feature activation+0.497
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.538
a
Token a
Feature activation+0.000

INTERVAL 2.979 - 3.352
CONTAINS 0.001%

and
Token and
Feature activation+0.000
contributors
Token contributors
Feature activation+0.000
from
Token from
Feature activation+0.000
just
Token just
Feature activation+0.102
about
Token about
Feature activation+2.103
every
Token every
Feature activation+3.346
major
Token major
Feature activation+0.000
media
Token media
Feature activation+0.000
outlet
Token outlet
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
of
Token of
Feature activation+0.000
mouse
Token mouse
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+1.098
any
Token any
Feature activation+2.982
piece
Token piece
Feature activation+0.000
information
Token information
Feature activation+0.000
can
Token can
Feature activation+0.373
be
Token be
Feature activation+0.000
unearthed
Token unearthed
Feature activation+0.000
medical
Token medical
Feature activation+0.000
card
Token card
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+1.828
any
Token any
Feature activation+3.057
reason
Token reason
Feature activation+0.070
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
exceptions
Token exceptions
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.203
nothing
Token nothing
Feature activation+3.066
that
Token that
Feature activation+0.000
comes
Token comes
Feature activation+0.000
even
Token even
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.212
don
Token don
Feature activation+1.907
âĢ
TokenâĢ
Feature activation+2.033
Ļ
TokenĻ
Feature activation+0.760
t
Tokent
Feature activation+3.100
repeat
Token repeat
Feature activation+0.366
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
mistake
Token mistake
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.607 - 2.979
CONTAINS 0.002%

Sanders
Token Sanders
Feature activation+0.000
faced
Token faced
Feature activation+0.000
off
Token off
Feature activation+0.000
with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
each
Token each
Feature activation+2.642
other
Token other
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.091
Democratic
Token Democratic
Feature activation+0.000
debate
Token debate
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+2.678
important
Token important
Feature activation+1.006
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
live
Tokenlive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
has
Token has
Feature activation+0.000
extra
Token extra
Feature activation+0.000
references
Token references
Feature activation+0.000
that
Token that
Feature activation+0.000
just
Token just
Feature activation+0.045
aren
Token aren
Feature activation+2.663
âĢ
TokenâĢ
Feature activation+0.764
Ļ
TokenĻ
Feature activation+0.066
t
Tokent
Feature activation+2.146
needed
Token needed
Feature activation+0.580
anymore
Token anymore
Feature activation+0.479
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.053
seems
Token seems
Feature activation+2.855
that
Token that
Feature activation+0.038
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
does
Token does
Feature activation+0.000
better
Token better
Feature activation+0.000
headaches
Token headaches
Feature activation+0.000
,
Token,
Feature activation+0.000
most
Token most
Feature activation+0.000
appreciate
Token appreciate
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+2.634
painful
Token painful
Feature activation+0.555
and
Token and
Feature activation+0.000
frustrating
Token frustrating
Feature activation+0.000
these
Token these
Feature activation+0.000
m
Token m
Feature activation+0.000

INTERVAL 2.235 - 2.607
CONTAINS 0.003%

this
Token this
Feature activation+0.000
case
Token case
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.000
wasn
Token wasn
Feature activation+2.256
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.515
the
Token the
Feature activation+0.000
teenager
Token teenager
Feature activation+0.000
never
Token never
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
just
Token just
Feature activation+0.363
how
Token how
Feature activation+2.362
big
Token big
Feature activation+0.000
a
Token a
Feature activation+0.000
b
Token b
Feature activation+0.000
osh
Tokenosh
Feature activation+0.000
't
Token't
Feature activation+0.000
open
Token open
Feature activation+0.000
,
Token,
Feature activation+0.000
drink
Token drink
Feature activation+0.000
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
perfect
Token perfect
Feature activation+2.236
amount
Token amount
Feature activation+0.606
of
Token of
Feature activation+0.079
wine
Token wine
Feature activation+0.000
and
Token and
Feature activation+0.000
stay
Token stay
Feature activation+0.000
neck
Token neck
Feature activation+0.000
muscles
Token muscles
Feature activation+0.000
at
Token at
Feature activation+0.000
just
Token just
Feature activation+1.416
the
Token the
Feature activation+0.690
right
Token right
Feature activation+2.308
time
Token time
Feature activation+0.402
for
Token for
Feature activation+0.074
the
Token the
Feature activation+0.087
ball
Token ball
Feature activation+0.000
to
Token to
Feature activation+0.000
my
Token my
Feature activation+0.000
face
Token face
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.148
feels
Token feels
Feature activation+2.558
unbelievable
Token unbelievable
Feature activation+0.904
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000

INTERVAL 1.862 - 2.235
CONTAINS 0.004%

our
Token our
Feature activation+0.000
tongues
Token tongues
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
out
Token out
Feature activation+1.290
of
Token of
Feature activation+2.214
reach
Token reach
Feature activation+0.628
,
Token,
Feature activation+0.749
and
Token and
Feature activation+0.839
the
Token the
Feature activation+0.000
memory
Token memory
Feature activation+0.000
sex
Token sex
Feature activation+0.000
just
Token just
Feature activation+0.000
doesn
Token doesn
Feature activation+0.613
âĢ
TokenâĢ
Feature activation+0.331
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.095
appeal
Token appeal
Feature activation+0.641
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
anymore
Token anymore
Feature activation+0.000
.
Token.
Feature activation+0.000
videos
Token videos
Feature activation+0.000
from
Token from
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Just
TokenJust
Feature activation+0.121
âĢ
TokenâĢ
Feature activation+2.045
Ļ
TokenĻ
Feature activation+1.141
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.219
ĺ
Tokenĺ
Feature activation+0.061
House
TokenHouse
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
just
Token just
Feature activation+0.181
where
Token where
Feature activation+2.214
the
Token the
Feature activation+0.021
concepts
Token concepts
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ne
Token Ne
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.134
showed
Token showed
Feature activation+2.013
up
Token up
Feature activation+1.964
on
Token on
Feature activation+0.138
the
Token the
Feature activation+0.252
Dig
Token Dig
Feature activation+0.000
il
Tokenil
Feature activation+0.000

INTERVAL 1.490 - 1.862
CONTAINS 0.007%

likely
Token likely
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
what
Token what
Feature activation+0.000
just
Token just
Feature activation+0.000
happened
Token happened
Feature activation+3.007
to
Token to
Feature activation+1.792
JPMorgan
Token JPMorgan
Feature activation+0.000
.
Token.
Feature activation+0.000
Levin
Token Levin
Feature activation+0.000
told
Token told
Feature activation+0.000
CNBC
Token CNBC
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
I
Token I
Feature activation+0.000
realized
Token realized
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.000
didn
Token didn
Feature activation+1.790
âĢ
TokenâĢ
Feature activation+0.292
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.569
work
Token work
Feature activation+1.338
for
Token for
Feature activation+0.126
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
just
Token just
Feature activation+0.026
how
Token how
Feature activation+1.967
many
Token many
Feature activation+1.674
merchants
Token merchants
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Whedon
Token Whedon
Feature activation+0.000
would
Token would
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.129
so
Token so
Feature activation+1.768
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
.
Token.
Feature activation+0.000
2017
Token2017
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
found
Token found
Feature activation+0.964
out
Token out
Feature activation+1.584
recently
Token recently
Feature activation+0.031
about
Token about
Feature activation+0.647
the
Token the
Feature activation+0.000
F
Token F
Feature activation+0.000
23
Token23
Feature activation+0.000

INTERVAL 1.117 - 1.490
CONTAINS 0.014%

's
Token's
Feature activation+0.000
capabilities
Token capabilities
Feature activation+0.000
in
Token in
Feature activation+0.000
just
Token just
Feature activation+1.101
a
Token a
Feature activation+0.853
small
Token small
Feature activation+1.381
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.000
didn
Token didn
Feature activation+2.183
âĢ
TokenâĢ
Feature activation+0.086
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+1.440
work
Token work
Feature activation+0.846
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
whole
Token whole
Feature activation+0.000
system
Token system
Feature activation+0.000
enthusiasts
Token enthusiasts
Feature activation+0.000
,
Token,
Feature activation+0.000
pros
Token pros
Feature activation+0.000
and
Token and
Feature activation+0.000
just
Token just
Feature activation+0.168
plain
Token plain
Feature activation+1.191
tone
Token tone
Feature activation+0.000
junk
Token junk
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
!
Token!
Feature activation+0.000
Low
Token Low
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
just
Token just
Feature activation+0.000
nobody
Token nobody
Feature activation+1.353
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.594
Ŀ
TokenĿ
Feature activation+0.244
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000
just
Token just
Feature activation+0.332
waiting
Token waiting
Feature activation+1.208
to
Token to
Feature activation+0.898
be
Token be
Feature activation+0.474
revealed
Token revealed
Feature activation+1.433
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
idea
Token idea
Feature activation+0.000

INTERVAL 0.745 - 1.117
CONTAINS 0.020%

simply
Token simply
Feature activation+0.000
not
Token not
Feature activation+0.337
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
any
Token any
Feature activation+0.797
legitimate
Token legitimate
Feature activation+0.000
insight
Token insight
Feature activation+0.000
into
Token into
Feature activation+0.000
inter
Token inter
Feature activation+0.000
gender
Tokengender
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
strained
Token strained
Feature activation+0.000
relations
Token relations
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.911
the
Token the
Feature activation+0.208
two
Token two
Feature activation+0.000
sides
Token sides
Feature activation+0.000
were
Token were
Feature activation+0.000
wrestling
Token wrestling
Feature activation+0.000
choice
Token choice
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.566
bad
Token bad
Feature activation+0.950
as
Token as
Feature activation+0.520
not
Token not
Feature activation+0.000
enough
Token enough
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
just
Token just
Feature activation+0.000
sets
Token sets
Feature activation+0.899
up
Token up
Feature activation+0.902
the
Token the
Feature activation+0.007
body
Token body
Feature activation+0.000
--
Token --
Feature activation+0.000
it
Token it
Feature activation+0.000
special
Token special
Feature activation+0.000
teams
Token teams
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
just
Token just
Feature activation+0.309
plain
Token plain
Feature activation+0.757
bad
Token bad
Feature activation+0.000
luck
Token luck
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.372 - 0.745
CONTAINS 0.047%

that
Token that
Feature activation+0.000
others
Token others
Feature activation+0.000
found
Token found
Feature activation+0.000
before
Token before
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
just
Token just
Feature activation+0.693
because
Token because
Feature activation+1.121
the
Token the
Feature activation+0.412
relevant
Token relevant
Feature activation+0.329
information
Token information
Feature activation+0.000
is
Token is
Feature activation+0.000
99
Token99
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.407
click
Token click
Feature activation+0.687
on
Token on
Feature activation+0.226
the
Token the
Feature activation+0.455
link
Token link
Feature activation+0.623
âĢĵ
Token âĢĵ
Feature activation+0.468
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.089
www
Tokenwww
Feature activation+0.000
leading
Token leading
Feature activation+0.000
to
Token to
Feature activation+0.000
more
Token more
Feature activation+0.000
just
Token just
Feature activation+0.000
and
Token and
Feature activation+0.000
equitable
Token equitable
Feature activation+0.661
science
Token science
Feature activation+0.000
and
Token and
Feature activation+0.000
human
Token human
Feature activation+0.035
-
Token-
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
found
Token found
Feature activation+0.000
before
Token before
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
just
Token just
Feature activation+0.693
because
Token because
Feature activation+1.121
the
Token the
Feature activation+0.412
relevant
Token relevant
Feature activation+0.329
information
Token information
Feature activation+0.000
is
Token is
Feature activation+0.000
buried
Token buried
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
remain
Token remain
Feature activation+0.000
are
Token are
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.442
capable
Token capable
Feature activation+0.938
of
Token of
Feature activation+0.318
making
Token making
Feature activation+0.000
a
Token a
Feature activation+0.000
mess
Token mess
Feature activation+0.000

INTERVAL 0.000 - 0.372
CONTAINS 99.902%

essors
Tokenessors
Feature activation+0.000
(
Token (
Feature activation+0.000
AA
TokenAA
Feature activation+0.000
UP
TokenUP
Feature activation+0.000
),
Token),
Feature activation+0.000
76
Token 76
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
college
Token college
Feature activation+0.000
instructors
Token instructors
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
W
TokenW
Feature activation+0.000
ä
Tokenä
Feature activation+0.000
h
Tokenh
Feature activation+0.000
rend
Tokenrend
Feature activation+0.000
also
Token also
Feature activation+0.000
Schw
Token Schw
Feature activation+0.000
ule
Tokenule
Feature activation+0.000
m
Token m
Feature activation+0.000
enez
Tokenenez
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
longtime
Token longtime
Feature activation+0.000
president
Token president
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Friends
Token Friends
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
hepatitis
Token hepatitis
Feature activation+0.000
C
Token C
Feature activation+0.000
patients
Token patients
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
are
Token are
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
ill
Token ill
Feature activation+0.000
<
Token<
Feature activation+0.000
string
Tokenstring
Feature activation+0.000
name
Token name
Feature activation+0.000
=
Token=
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
access
Tokenaccess
Feature activation+0.000
ibility
Tokenibility
Feature activation+0.000
_
Token_
Feature activation+0.000
rew
Tokenrew
Feature activation+0.000
ind
Tokenind
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H3.6: (feature 14043)

TOP ACTIVATIONS
MAX = 2.174

government
Token government
Feature activation+0.612
budget
Token budget
Feature activation+1.597
because
Token because
Feature activation+0.257
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.499
pays
Token pays
Feature activation+2.174
for
Token for
Feature activation+1.091
a
Token a
Feature activation+0.267
big
Token big
Feature activation+0.000
fraction
Token fraction
Feature activation+0.000
of
Token of
Feature activation+0.000
The
Token The
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.395
on
Token on
Feature activation+0.836
Thursday
Token Thursday
Feature activation+0.248
decided
Token decided
Feature activation+2.003
to
Token to
Feature activation+0.116
sue
Token sue
Feature activation+0.444
Pakistan
Token Pakistan
Feature activation+0.000
Te
Token Te
Feature activation+0.000
h
Tokenh
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.753
's
Token's
Feature activation+1.998
new
Token new
Feature activation+1.285
guide
Token guide
Feature activation+1.078
includes
Token includes
Feature activation+0.591
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
Harper
Token Harper
Feature activation+0.000
government
Token government
Feature activation+0.000
issued
Token issued
Feature activation+1.940
a
Token a
Feature activation+0.898
legal
Token legal
Feature activation+0.732
threat
Token threat
Feature activation+0.388
over
Token over
Feature activation+0.726
the
Token the
Feature activation+0.000
In
TokenIn
Feature activation+0.000
December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.079
gave
Token gave
Feature activation+1.904
the
Token the
Feature activation+0.314
green
Token green
Feature activation+0.152
light
Tokenlight
Feature activation+0.000
for
Token for
Feature activation+0.291
10
Token 10
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
's
Token's
Feature activation+1.471
spy
Token spy
Feature activation+1.870
systems
Token systems
Feature activation+0.808
may
Token may
Feature activation+0.490
be
Token be
Feature activation+0.000
directed
Token directed
Feature activation+0.509
to
Token to
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.599
's
Token's
Feature activation+1.703
interest
Token interest
Feature activation+1.869
to
Token to
Feature activation+0.764
get
Token get
Feature activation+0.197
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
in
Token in
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+1.007
has
Token has
Feature activation+1.197
made
Token made
Feature activation+1.866
eas
Token eas
Feature activation+0.000
ement
Tokenement
Feature activation+0.000
deals
Token deals
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Government
TokenGovernment
Feature activation+0.000
has
Token has
Feature activation+0.164
also
Token also
Feature activation+0.725
given
Token given
Feature activation+1.846
a
Token a
Feature activation+0.591
final
Token final
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.120
to
Token to
Feature activation+0.766
another
Token another
Feature activation+0.000
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Government
Token Government
Feature activation+0.951
's
Token's
Feature activation+1.768
austerity
Token austerity
Feature activation+1.091
drive
Token drive
Feature activation+0.768
.
Token.
Feature activation+0.116
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
out
Token out
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.194
has
Token has
Feature activation+0.990
made
Token made
Feature activation+1.767
no
Token no
Feature activation+0.216
case
Token case
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.918
's
Token's
Feature activation+1.760
wildly
Token wildly
Feature activation+0.562
expensive
Token expensive
Feature activation+1.168
F
Token F
Feature activation+0.000
-
Token-
Feature activation+0.000
35
Token35
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.736
estimates
Token estimates
Feature activation+1.746
up
Token up
Feature activation+1.041
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
million
Token million
Feature activation+0.000
women
Token women
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Government
Token Government
Feature activation+0.957
of
Token of
Feature activation+0.380
India
Token India
Feature activation+0.000
has
Token has
Feature activation+0.943
allocated
Token allocated
Feature activation+1.723
Rs
Token Rs
Feature activation+0.000
400
Token 400
Feature activation+0.000
crore
Token crore
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
privacy
Token privacy
Feature activation+0.000
.
Token.
Feature activation+0.000
Given
Token Given
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.620
's
Token's
Feature activation+1.704
failure
Token failure
Feature activation+1.677
to
Token to
Feature activation+1.219
respond
Token respond
Feature activation+1.266
to
Token to
Feature activation+0.110
European
Token European
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.599
's
Token's
Feature activation+1.703
interest
Token interest
Feature activation+1.869
to
Token to
Feature activation+0.764
get
Token get
Feature activation+0.197
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.527
's
Token's
Feature activation+1.698
erratic
Token erratic
Feature activation+1.036
and
Token and
Feature activation+0.000
chaotic
Token chaotic
Feature activation+1.249
attempts
Token attempts
Feature activation+0.761
to
Token to
Feature activation+0.544
While
TokenWhile
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.612
has
Token has
Feature activation+1.222
been
Token been
Feature activation+0.894
pushing
Token pushing
Feature activation+1.689
the
Token the
Feature activation+0.657
country
Token country
Feature activation+0.000
as
Token as
Feature activation+0.289
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+0.000
.
Token.
Feature activation+0.000
Given
Token Given
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.620
's
Token's
Feature activation+1.704
failure
Token failure
Feature activation+1.677
to
Token to
Feature activation+1.219
respond
Token respond
Feature activation+1.266
to
Token to
Feature activation+0.110
European
Token European
Feature activation+0.000
judgments
Token judgments
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.139
had
Token had
Feature activation+0.964
created
Token created
Feature activation+1.647
a
Token a
Feature activation+0.505
"
Token "
Feature activation+0.000
financial
Tokenfinancial
Feature activation+0.282
climate
Token climate
Feature activation+0.000
that
Token that
Feature activation+0.000

Top DFA by src position
MAX = 3.331

the
Token the
Feature activation+0.023
Top resid features:
government
Token government
Feature activation+0.196
Top resid features:
budget
Token budget
Feature activation+0.063
Top resid features:
because
Token because
Feature activation+0.091
Top resid features:
the
Token the
Feature activation+0.161
Top resid features:
government
Token government
Feature activation+3.156
Top resid features:
pays
Token pays
Feature activation+0.136
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
big
Token big
Feature activation+0.000
Top resid features:
fraction
Token fraction
Feature activation+0.000
Top resid features:
AB
TokenAB
Feature activation+0.002
Top resid features:
AD
TokenAD
Feature activation+0.004
Top resid features:
:
Token:
Feature activation+0.013
Top resid features:
The
Token The
Feature activation+0.115
Top resid features:
federal
Token federal
Feature activation+0.391
Top resid features:
government
Token government
Feature activation+2.907
Top resid features:
on
Token on
Feature activation+0.133
Top resid features:
Thursday
Token Thursday
Feature activation+0.088
Top resid features:
decided
Token decided
Feature activation+0.069
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sue
Token sue
Feature activation+0.000
Top resid features:
graduating
Token graduating
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
Ċ
TokenĊ
Feature activation+0.109
Top resid features:
The
TokenThe
Feature activation+0.101
Top resid features:
government
Token government
Feature activation+3.231
Top resid features:
's
Token's
Feature activation+0.147
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
guide
Token guide
Feature activation+0.000
Top resid features:
includes
Token includes
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
bud
Token bud
Feature activation+0.004
Top resid features:
ge
Tokenge
Feature activation-0.000
Top resid features:
after
Token after
Feature activation+0.199
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
Harper
Token Harper
Feature activation+0.427
Top resid features:
government
Token government
Feature activation+2.971
Top resid features:
issued
Token issued
Feature activation+0.012
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
threat
Token threat
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.048
Top resid features:
In
TokenIn
Feature activation-0.001
Top resid features:
December
Token December
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
government
Token government
Feature activation+3.331
Top resid features:
gave
Token gave
Feature activation+0.081
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
green
Token green
Feature activation+0.000
Top resid features:
light
Tokenlight
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
Muslim
Token Muslim
Feature activation-0.011
Top resid features:
Americans
Token Americans
Feature activation+0.010
Top resid features:
--
Token --
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
government
Token government
Feature activation+3.221
Top resid features:
's
Token's
Feature activation+0.194
Top resid features:
spy
Token spy
Feature activation+0.051
Top resid features:
systems
Token systems
Feature activation+0.000
Top resid features:
may
Token may
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.057
Top resid features:
it
Token it
Feature activation+0.395
Top resid features:
's
Token's
Feature activation+0.062
Top resid features:
in
Token in
Feature activation+0.123
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
government
Token government
Feature activation+2.616
Top resid features:
's
Token's
Feature activation+0.187
Top resid features:
interest
Token interest
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.005
Top resid features:
most
Token most
Feature activation+0.019
Top resid features:
cases
Token cases
Feature activation-0.041
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
government
Token government
Feature activation+3.120
Top resid features:
has
Token has
Feature activation+0.161
Top resid features:
made
Token made
Feature activation+0.146
Top resid features:
eas
Token eas
Feature activation+0.000
Top resid features:
ement
Tokenement
Feature activation+0.000
Top resid features:
deals
Token deals
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
rejected
Token rejected
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.095
Top resid features:
Ċ
TokenĊ
Feature activation+0.069
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
Government
TokenGovernment
Feature activation+2.900
Top resid features:
has
Token has
Feature activation+0.187
Top resid features:
also
Token also
Feature activation+0.190
Top resid features:
given
Token given
Feature activation+0.101
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
final
Token final
Feature activation+0.000
Top resid features:
restrictions
Token restrictions
Feature activation+0.011
Top resid features:
as
Token as
Feature activation+0.115
Top resid features:
part
Token part
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.127
Top resid features:
Government
Token Government
Feature activation+3.165
Top resid features:
's
Token's
Feature activation+0.087
Top resid features:
austerity
Token austerity
Feature activation+0.000
Top resid features:
drive
Token drive
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Critics
Token Critics
Feature activation+0.009
Top resid features:
point
Token point
Feature activation+0.068
Top resid features:
out
Token out
Feature activation+0.034
Top resid features:
that
Token that
Feature activation+0.058
Top resid features:
the
Token the
Feature activation+0.111
Top resid features:
government
Token government
Feature activation+2.867
Top resid features:
has
Token has
Feature activation+0.170
Top resid features:
made
Token made
Feature activation+0.107
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
noted
Token noted
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
cost
Token cost
Feature activation+0.104
Top resid features:
of
Token of
Feature activation-0.017
Top resid features:
the
Token the
Feature activation+0.100
Top resid features:
government
Token government
Feature activation+3.103
Top resid features:
's
Token's
Feature activation+0.062
Top resid features:
wildly
Token wildly
Feature activation+0.000
Top resid features:
expensive
Token expensive
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Survey
Token Survey
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
However
Token However
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.136
Top resid features:
government
Token government
Feature activation+2.900
Top resid features:
estimates
Token estimates
Feature activation+0.339
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.009
Top resid features:
Ŀ
TokenĿ
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
The
TokenThe
Feature activation+0.096
Top resid features:
Government
Token Government
Feature activation+2.796
Top resid features:
of
Token of
Feature activation+0.089
Top resid features:
India
Token India
Feature activation+0.092
Top resid features:
has
Token has
Feature activation+0.196
Top resid features:
allocated
Token allocated
Feature activation+0.075
Top resid features:
Rs
Token Rs
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
privacy
Token privacy
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.097
Top resid features:
Given
Token Given
Feature activation+0.060
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
government
Token government
Feature activation+3.008
Top resid features:
's
Token's
Feature activation+0.130
Top resid features:
failure
Token failure
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
respond
Token respond
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.047
Top resid features:
it
Token it
Feature activation+0.104
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.087
Top resid features:
the
Token the
Feature activation+0.114
Top resid features:
government
Token government
Feature activation+2.908
Top resid features:
's
Token's
Feature activation+0.151
Top resid features:
interest
Token interest
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
ruling
Token ruling
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
"
Token "
Feature activation+0.067
Top resid features:
The
TokenThe
Feature activation+0.049
Top resid features:
government
Token government
Feature activation+3.085
Top resid features:
's
Token's
Feature activation+0.172
Top resid features:
erratic
Token erratic
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
chaotic
Token chaotic
Feature activation+0.000
Top resid features:
attempts
Token attempts
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
While
TokenWhile
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.124
Top resid features:
government
Token government
Feature activation+2.632
Top resid features:
has
Token has
Feature activation+0.172
Top resid features:
been
Token been
Feature activation+0.244
Top resid features:
pushing
Token pushing
Feature activation+0.131
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
privacy
Token privacy
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.153
Top resid features:
Given
Token Given
Feature activation+0.089
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
government
Token government
Feature activation+2.397
Top resid features:
's
Token's
Feature activation+0.215
Top resid features:
failure
Token failure
Feature activation+0.196
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
respond
Token respond
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
Burn
Token Burn
Feature activation-0.005
Top resid features:
ham
Tokenham
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.173
Top resid features:
the
Token the
Feature activation+0.164
Top resid features:
government
Token government
Feature activation+2.841
Top resid features:
had
Token had
Feature activation+0.123
Top resid features:
created
Token created
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
financial
Tokenfinancial
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.06

Head 3: 0.03

Head 4: 0.03

Head 5: 0.07

Head 6: 0.43

Head 7: 0.12

Head 8: 0.05

Head 9: 0.04

Head 10: 0.07

Head 11: 0.05

Positive logits

funding1.60

appoint1.50

commissions1.45

subsid1.36

regulatory1.36

grant1.34

decree1.31

oversight1.29

prosecutions1.29

appointing1.28

prosecuting1.28

indemn1.28

antitrust1.26

approvals1.26

authorization1.25

governors1.25

legisl1.23

patent1.22

appropriations1.21

regulations1.21

Negative logits

uv-1.36

Pirates-1.27

initely-1.27

Penguins-1.22

onge-1.20

eva-1.16

Sharks-1.11

byn-1.10

iov-1.09

Warriors-1.08

Pirate-1.06

Stranger-1.06

IFF-1.06

chan-1.06

itars-1.06

Mong-1.05

pel-1.05

sing-1.04

Tigers-1.04

spin-1.03

INTERVAL 1.956 - 2.174
CONTAINS 0.000%

The
Token The
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.395
on
Token on
Feature activation+0.836
Thursday
Token Thursday
Feature activation+0.248
decided
Token decided
Feature activation+2.003
to
Token to
Feature activation+0.116
sue
Token sue
Feature activation+0.444
Pakistan
Token Pakistan
Feature activation+0.000
Te
Token Te
Feature activation+0.000
h
Tokenh
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.753
's
Token's
Feature activation+1.998
new
Token new
Feature activation+1.285
guide
Token guide
Feature activation+1.078
includes
Token includes
Feature activation+0.591
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
government
Token government
Feature activation+0.612
budget
Token budget
Feature activation+1.597
because
Token because
Feature activation+0.257
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.499
pays
Token pays
Feature activation+2.174
for
Token for
Feature activation+1.091
a
Token a
Feature activation+0.267
big
Token big
Feature activation+0.000
fraction
Token fraction
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.739 - 1.956
CONTAINS 0.001%

In
TokenIn
Feature activation+0.000
December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.079
gave
Token gave
Feature activation+1.904
the
Token the
Feature activation+0.314
green
Token green
Feature activation+0.152
light
Tokenlight
Feature activation+0.000
for
Token for
Feature activation+0.291
10
Token 10
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.736
estimates
Token estimates
Feature activation+1.746
up
Token up
Feature activation+1.041
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
million
Token million
Feature activation+0.000
women
Token women
Feature activation+0.000
out
Token out
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.194
has
Token has
Feature activation+0.990
made
Token made
Feature activation+1.767
no
Token no
Feature activation+0.216
case
Token case
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
why
Token why
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
's
Token's
Feature activation+1.471
spy
Token spy
Feature activation+1.870
systems
Token systems
Feature activation+0.808
may
Token may
Feature activation+0.490
be
Token be
Feature activation+0.000
directed
Token directed
Feature activation+0.509
to
Token to
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+1.007
has
Token has
Feature activation+1.197
made
Token made
Feature activation+1.866
eas
Token eas
Feature activation+0.000
ement
Tokenement
Feature activation+0.000
deals
Token deals
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.522 - 1.739
CONTAINS 0.002%

ham
Tokenham
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.139
had
Token had
Feature activation+0.964
created
Token created
Feature activation+1.647
a
Token a
Feature activation+0.505
"
Token "
Feature activation+0.000
financial
Tokenfinancial
Feature activation+0.282
climate
Token climate
Feature activation+0.000
that
Token that
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.612
has
Token has
Feature activation+1.222
been
Token been
Feature activation+0.894
pushing
Token pushing
Feature activation+1.689
the
Token the
Feature activation+0.657
country
Token country
Feature activation+0.000
as
Token as
Feature activation+0.289
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+0.000
government
Token government
Feature activation+0.294
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.711
rationale
Token rationale
Feature activation+1.635
for
Token for
Feature activation+1.550
setting
Token setting
Feature activation+0.000
it
Token it
Feature activation+0.000
up
Token up
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
industry
Token industry
Feature activation+0.000
contended
Token contended
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.690
regulation
Token regulation
Feature activation+1.546
was
Token was
Feature activation+0.432
unwanted
Token unwanted
Feature activation+1.051
by
Token by
Feature activation+0.544
parents
Token parents
Feature activation+0.000
.
Token.
Feature activation+0.000
gal
Tokengal
Feature activation+0.000
infection
Token infection
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
government
Token government
Feature activation+1.048
recommends
Token recommends
Feature activation+1.574
doctors
Token doctors
Feature activation+0.000
stop
Token stop
Feature activation+0.000
using
Token using
Feature activation+0.000
any
Token any
Feature activation+0.000
sterile
Token sterile
Feature activation+0.000

INTERVAL 1.304 - 1.522
CONTAINS 0.003%

Muslim
Token Muslim
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
's
Token's
Feature activation+1.471
spy
Token spy
Feature activation+1.870
systems
Token systems
Feature activation+0.808
may
Token may
Feature activation+0.490
be
Token be
Feature activation+0.000
directed
Token directed
Feature activation+0.509
government
Token government
Feature activation+0.416
,
Token,
Feature activation+0.208
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.924
issued
Token issued
Feature activation+1.468
a
Token a
Feature activation+0.000
'
Token '
Feature activation+0.000
def
Tokendef
Feature activation+0.000
iciency
Tokeniciency
Feature activation+0.000
memo
Token memo
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Government
Token Government
Feature activation+0.620
tries
Token tries
Feature activation+1.593
to
Token to
Feature activation+1.599
cut
Token cut
Feature activation+1.343
the
Token the
Feature activation+0.039
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
demand
Token demand
Feature activation+0.000
compensation
Token compensation
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+1.222
for
Token for
Feature activation+1.461
depri
Token depri
Feature activation+0.582
ving
Tokenving
Feature activation+0.717
her
Token her
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
the
Token the
Feature activation+0.000
absence
Token absence
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.389
aid
Token aid
Feature activation+1.488
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.087 - 1.304
CONTAINS 0.007%

,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
a
Token a
Feature activation+0.000
government
Token government
Feature activation+0.000
report
Token report
Feature activation+1.120
which
Token which
Feature activation+0.000
showed
Token showed
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.561
will
Token will
Feature activation+0.762
not
Token not
Feature activation+0.801
fulfill
Token fulfill
Feature activation+1.189
its
Token its
Feature activation+0.535
promise
Token promise
Feature activation+0.159
.
Token.
Feature activation+0.215
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
referring
Token referring
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.205
reward
Token reward
Feature activation+1.186
for
Token for
Feature activation+1.186
information
Token information
Feature activation+0.031
leading
Token leading
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
capture
Token capture
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.527
's
Token's
Feature activation+1.698
erratic
Token erratic
Feature activation+1.036
and
Token and
Feature activation+0.000
chaotic
Token chaotic
Feature activation+1.249
attempts
Token attempts
Feature activation+0.761
to
Token to
Feature activation+0.544
enforce
Token enforce
Feature activation+0.000
this
Token this
Feature activation+0.000
unconstitutional
Token unconstitutional
Feature activation+0.000
N
TokenN
Feature activation+0.000
is
Token is
Feature activation+0.000
saying
Token saying
Feature activation+0.000
the
Token the
Feature activation+0.000
Government
Token Government
Feature activation+0.138
is
Token is
Feature activation+1.237
shooting
Token shooting
Feature activation+1.121
itself
Token itself
Feature activation+0.900
in
Token in
Feature activation+0.093
the
Token the
Feature activation+0.000
foot
Token foot
Feature activation+0.000

INTERVAL 0.870 - 1.087
CONTAINS 0.010%

,
Token,
Feature activation+0.000
government
Token government
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+0.026
-
Token-
Feature activation+0.644
politics
Tokenpolitics
Feature activation+0.882
,
Token,
Feature activation+0.446
aust
Token aust
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.753
's
Token's
Feature activation+1.998
new
Token new
Feature activation+1.285
guide
Token guide
Feature activation+1.078
includes
Token includes
Feature activation+0.591
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
dos
Token dos
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
government
Token government
Feature activation+0.000
investment
Token investment
Feature activation+1.039
in
Token in
Feature activation+0.660
infrastructure
Token infrastructure
Feature activation+0.245
has
Token has
Feature activation+0.000
hurt
Token hurt
Feature activation+0.000
production
Token production
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
government
Token government
Feature activation+0.000
is
Token is
Feature activation+0.194
making
Token making
Feature activation+0.942
it
Token it
Feature activation+0.249
easy
Token easy
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
,
Token,
Feature activation+0.000
government
Token government
Feature activation+0.000
will
Token will
Feature activation+0.139
have
Token have
Feature activation+0.263
to
Token to
Feature activation+0.215
raise
Token raise
Feature activation+0.933
taxes
Token taxes
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
will
Token will
Feature activation+0.000
further
Token further
Feature activation+0.000

INTERVAL 0.652 - 0.870
CONTAINS 0.016%

submitted
Token submitted
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
website
Token website
Feature activation+0.746
had
Token had
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
signatures
Token signatures
Feature activation+0.000
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.124
government
Token government
Feature activation+0.439
is
Token is
Feature activation+0.691
now
Token now
Feature activation+1.008
making
Token making
Feature activation+1.556
a
Token a
Feature activation+0.632
significant
Token significant
Feature activation+0.000
investment
Token investment
Feature activation+0.674
assistance
Token assistance
Feature activation+0.000
illegally
Token illegally
Feature activation+0.000
from
Token from
Feature activation+0.000
several
Token several
Feature activation+0.000
government
Token government
Feature activation+0.000
programs
Token programs
Feature activation+0.863
designed
Token designed
Feature activation+0.039
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
the
Token the
Feature activation+0.000
poor
Token poor
Feature activation+0.000
handed
Tokenhanded
Feature activation+0.000
comment
Token comment
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
's
Token's
Feature activation+0.740
course
Token course
Feature activation+0.220
?
Token?
Feature activation+0.000
NBC
Token NBC
Feature activation+0.000
's
Token's
Feature activation+0.000
Andrea
Token Andrea
Feature activation+0.000
complained
Token complained
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
's
Token's
Feature activation+0.629
priorities
Token priorities
Feature activation+0.835
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.435 - 0.652
CONTAINS 0.022%

that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.215
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.512
interpretation
Token interpretation
Feature activation+1.346
of
Token of
Feature activation+0.856
these
Token these
Feature activation+0.000
laws
Token laws
Feature activation+0.000
is
Token is
Feature activation+0.007
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
German
Token German
Feature activation+0.000
government
Token government
Feature activation+0.000
now
Token now
Feature activation+0.000
believes
Token believes
Feature activation+0.476
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
eurozone
Token eurozone
Feature activation+0.000
is
Token is
Feature activation+0.000
able
Token able
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
have
Token have
Feature activation+0.117
acted
Token acted
Feature activation+0.533
to
Token to
Feature activation+0.065
cover
Token cover
Feature activation+0.167
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
existence
Token existence
Feature activation+0.000
former
Token former
Feature activation+0.000
Labor
Token Labor
Feature activation+0.000
government
Token government
Feature activation+0.000
's
Token's
Feature activation+0.534
discussions
Token discussions
Feature activation+1.010
with
Token with
Feature activation+0.470
Sri
Token Sri
Feature activation+0.000
Lanka
Token Lanka
Feature activation+0.000
.
Token.
Feature activation+0.000
Respond
Token Respond
Feature activation+0.000
ing
Tokening
Feature activation+0.000
government
Token government
Feature activation+0.000
-
Token-
Feature activation+0.116
and
Tokenand
Feature activation+0.455
-
Token-
Feature activation+0.965
politics
Tokenpolitics
Feature activation+0.751
,
Token,
Feature activation+0.468
elections
Token elections
Feature activation+0.000
,
Token,
Feature activation+0.000
federal
Token federal
Feature activation+0.000
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000

INTERVAL 0.217 - 0.435
CONTAINS 0.037%

direct
Token direct
Feature activation+0.000
help
Token help
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.593
.
Token .
Feature activation+0.277
It
Token It
Feature activation+0.000
appears
Token appears
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Mitt
Token Mitt
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
of
Token of
Feature activation+0.000
government
Token government
Feature activation+0.000
cuts
Token cuts
Feature activation+0.431
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
COMMUN
Token COMMUN
Feature activation+0.000
ITY
TokenITY
Feature activation+0.000
has
Token has
Feature activation+0.000
especially
Token especially
Feature activation+0.000
those
Token those
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000
government
Token government
Feature activation+0.000
grants
Token grants
Feature activation+0.702
for
Token for
Feature activation+0.407
their
Token their
Feature activation+0.000
confirmation
Token confirmation
Feature activation+0.000
bias
Token bias
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
state
Token state
Feature activation+0.000
also
Token also
Feature activation+0.000
objected
Token objected
Feature activation+0.399
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
bail
Token bail
Feature activation+0.000
application
Token application
Feature activation+0.000
on
Token on
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
brought
Token brought
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
government
Token government
Feature activation+0.000
default
Token default
Feature activation+0.258
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000

INTERVAL 0.000 - 0.217
CONTAINS 99.902%

ll
Tokenll
Feature activation+0.000
feel
Token feel
Feature activation+0.000
like
Token like
Feature activation+0.000
you
Token you
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
moon
Token moon
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Tokens
Feature activation+0.000
usually
Token usually
Feature activation+0.000
mal
Token mal
Feature activation+0.000
eness
Tokeneness
Feature activation+0.000
that
Token that
Feature activation+0.000
gets
Token gets
Feature activation+0.000
things
Token things
Feature activation+0.000
done
Token done
Feature activation+0.000
;
Token;
Feature activation+0.000
people
Token people
Feature activation+0.000
listen
Token listen
Feature activation+0.000
pass
Token pass
Feature activation+0.000
it
Token it
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
parameter
Token parameter
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
importing
Token importing
Feature activation+0.000
the
Token the
Feature activation+0.000
script
Token script
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
some
Token some
Feature activation+0.000
hitch
Token hitch
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
surface
Token surface
Feature activation+0.000
,
Token,
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
denied
Token denied
Feature activation+0.000
the
Token the
Feature activation+0.000
charges
Token charges
Feature activation+0.000
of
Token of
Feature activation+0.000
raping
Token raping
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
women
Token women
Feature activation+0.000
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
ash
Token ash
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+0.089
Development
Token Development
Feature activation+0.227
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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+0.089
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 7 in H3.6: (feature 16531)

TOP ACTIVATIONS
MAX = 3.718

body
Token body
Feature activation+0.000
count
Token count
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000
ately
Tokenately
Feature activation+0.000
far
Token far
Feature activation+0.000
greater
Token greater
Feature activation+3.718
than
Token than
Feature activation+2.942
the
Token the
Feature activation+0.808
number
Token number
Feature activation+0.032
of
Token of
Feature activation+0.000
fatalities
Token fatalities
Feature activation+0.000
But
Token But
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
far
Token far
Feature activation+0.793
more
Token more
Feature activation+3.716
sinister
Token sinister
Feature activation+1.824
occurring
Token occurring
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
streets
Token streets
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
That
TokenThat
Feature activation+0.000
shift
Token shift
Feature activation+0.000
meant
Token meant
Feature activation+0.000
far
Token far
Feature activation+0.797
more
Token more
Feature activation+3.630
settlements
Token settlements
Feature activation+0.176
ended
Token ended
Feature activation+0.000
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
eat
Token eat
Feature activation+0.000
far
Token far
Feature activation+0.395
less
Token less
Feature activation+3.525
dairy
Token dairy
Feature activation+0.528
in
Token in
Feature activation+0.774
these
Token these
Feature activation+0.151
three
Token three
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
far
Token far
Feature activation+0.321
greater
Token greater
Feature activation+3.403
levels
Token levels
Feature activation+1.843
of
Token of
Feature activation+0.474
trace
Token trace
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
and
Token and
Feature activation+0.000
owners
Token owners
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
far
Token far
Feature activation+0.418
more
Token more
Feature activation+3.372
gun
Token gun
Feature activation+0.166
deaths
Token deaths
Feature activation+0.036
.
Token.
Feature activation+0.000
Studies
Token Studies
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
ignore
Token ignore
Feature activation+0.000
science
Token science
Feature activation+0.000
that
Token that
Feature activation+0.000
far
Token far
Feature activation+0.432
exceeds
Token exceeds
Feature activation+3.329
even
Token even
Feature activation+0.970
the
Token the
Feature activation+0.173
positions
Token positions
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
free
Token free
Feature activation+0.000
agent
Token agent
Feature activation+0.000
pitches
Token pitches
Feature activation+0.000
;
Token;
Feature activation+0.000
far
Token far
Feature activation+0.918
more
Token more
Feature activation+3.272
than
Token than
Feature activation+3.203
Jim
Token Jim
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
buy
Token buy
Feature activation+0.000
less
Token less
Feature activation+0.000
furniture
Token furniture
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+1.056
less
Token less
Feature activation+3.254
lawn
Token lawn
Feature activation+0.030
and
Token and
Feature activation+0.252
gardening
Token gardening
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
and
Token and
Feature activation+0.000
meaning
Token meaning
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
introduce
Token introduce
Feature activation+0.000
far
Token far
Feature activation+0.557
more
Token more
Feature activation+3.243
without
Token without
Feature activation+1.720
feeling
Token feeling
Feature activation+0.000
less
Token less
Feature activation+1.661
than
Token than
Feature activation+0.837
much
Token much
Feature activation+0.000
ball
Token ball
Feature activation+0.000
retention
Token retention
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
far
Token far
Feature activation+0.017
better
Token better
Feature activation+3.243
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
with
Token with
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.175
more
Token more
Feature activation+3.241
chaotic
Token chaotic
Feature activation+1.928
than
Token than
Feature activation+2.258
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+0.000
needed
Token needed
Feature activation+0.000
agent
Token agent
Feature activation+0.000
pitches
Token pitches
Feature activation+0.000
;
Token;
Feature activation+0.000
far
Token far
Feature activation+0.918
more
Token more
Feature activation+3.272
than
Token than
Feature activation+3.203
Jim
Token Jim
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ever
Token ever
Feature activation+0.000
settlements
Token settlements
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
less
Token less
Feature activation+3.200
costly
Token costly
Feature activation+2.910
than
Token than
Feature activation+2.492
taking
Token taking
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
far
Token far
Feature activation+0.833
more
Token more
Feature activation+3.192
to
Token to
Feature activation+0.487
offer
Token offer
Feature activation+0.000
the
Token the
Feature activation+0.182
Peter
Token Peter
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
between
Token between
Feature activation+0.000
two
Token two
Feature activation+0.000
measurements
Token measurements
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.442
larger
Token larger
Feature activation+3.166
than
Token than
Feature activation+2.804
what
Token what
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+0.000
normally
Token normally
Feature activation+0.000
world
Token world
Feature activation+0.000
over
Token over
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
far
Token far
Feature activation+0.598
more
Token more
Feature activation+3.105
universal
Token universal
Feature activation+0.835
:
Token:
Feature activation+0.000
fun
Token fun
Feature activation+0.000
.
Token.
Feature activation+0.000
Look
Token Look
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
spending
Token spending
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.962
less
Token less
Feature activation+2.682
than
Token than
Feature activation+3.071
the
Token the
Feature activation+1.161
$
Token $
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+1.323
too
Token too
Feature activation+3.065
short
Token short
Feature activation+1.309
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
go
Token go
Feature activation+0.000
energy
Token energy
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
taking
Token taking
Feature activation+0.000
far
Token far
Feature activation+0.534
more
Token more
Feature activation+3.052
politically
Token politically
Feature activation+0.409
challenging
Token challenging
Feature activation+0.000
steps
Token steps
Feature activation+0.000
to
Token to
Feature activation+0.000
tackle
Token tackle
Feature activation+0.000

Top DFA by src position
MAX = 4.516

the
Token the
Feature activation-0.023
Top resid features:
body
Token body
Feature activation-0.008
Top resid features:
count
Token count
Feature activation+0.047
Top resid features:
proportion
Token proportion
Feature activation-0.223
Top resid features:
ately
Tokenately
Feature activation-0.071
Top resid features:
far
Token far
Feature activation+4.219
Top resid features:
greater
Token greater
Feature activation+0.349
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
number
Token number
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
But
Token But
Feature activation-0.212
Top resid features:
there
Token there
Feature activation-0.080
Top resid features:
is
Token is
Feature activation-0.053
Top resid features:
something
Token something
Feature activation+0.157
Top resid features:
far
Token far
Feature activation+4.500
Top resid features:
more
Token more
Feature activation+0.073
Top resid features:
sinister
Token sinister
Feature activation+0.000
Top resid features:
occurring
Token occurring
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.241
Top resid features:
That
TokenThat
Feature activation-0.039
Top resid features:
shift
Token shift
Feature activation-0.014
Top resid features:
meant
Token meant
Feature activation-0.404
Top resid features:
far
Token far
Feature activation+4.516
Top resid features:
more
Token more
Feature activation+0.138
Top resid features:
settlements
Token settlements
Feature activation+0.000
Top resid features:
ended
Token ended
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
cipline
Tokencipline
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
I
Token I
Feature activation-0.021
Top resid features:
did
Token did
Feature activation-0.026
Top resid features:
eat
Token eat
Feature activation-0.150
Top resid features:
far
Token far
Feature activation+4.134
Top resid features:
less
Token less
Feature activation+0.167
Top resid features:
dairy
Token dairy
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
three
Token three
Feature activation+0.000
Top resid features:
suppliers
Token suppliers
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.036
Top resid features:
that
Token that
Feature activation-0.007
Top resid features:
they
Token they
Feature activation+0.011
Top resid features:
have
Token have
Feature activation+0.025
Top resid features:
far
Token far
Feature activation+3.920
Top resid features:
greater
Token greater
Feature activation+0.220
Top resid features:
levels
Token levels
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
trace
Token trace
Feature activation+0.000
Top resid features:
ability
Tokenability
Feature activation+0.000
Top resid features:
gun
Token gun
Feature activation+0.008
Top resid features:
owners
Token owners
Feature activation-0.015
Top resid features:
,
Token,
Feature activation-0.070
Top resid features:
there
Token there
Feature activation-0.072
Top resid features:
are
Token are
Feature activation-0.062
Top resid features:
far
Token far
Feature activation+4.079
Top resid features:
more
Token more
Feature activation+0.274
Top resid features:
gun
Token gun
Feature activation+0.000
Top resid features:
deaths
Token deaths
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Studies
Token Studies
Feature activation+0.000
Top resid features:
determination
Token determination
Feature activation-0.018
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
ignore
Token ignore
Feature activation-0.031
Top resid features:
science
Token science
Feature activation+0.005
Top resid features:
that
Token that
Feature activation-0.075
Top resid features:
far
Token far
Feature activation+3.980
Top resid features:
exceeds
Token exceeds
Feature activation+0.189
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
positions
Token positions
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
free
Token free
Feature activation+0.006
Top resid features:
agent
Token agent
Feature activation+0.000
Top resid features:
pitches
Token pitches
Feature activation-0.012
Top resid features:
;
Token;
Feature activation-0.249
Top resid features:
far
Token far
Feature activation+4.108
Top resid features:
more
Token more
Feature activation+0.132
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
Jim
Token Jim
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:
they
Token they
Feature activation-0.001
Top resid features:
buy
Token buy
Feature activation-0.028
Top resid features:
less
Token less
Feature activation-0.006
Top resid features:
furniture
Token furniture
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.228
Top resid features:
far
Token far
Feature activation+4.069
Top resid features:
less
Token less
Feature activation+0.200
Top resid features:
lawn
Token lawn
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
gardening
Token gardening
Feature activation+0.000
Top resid features:
equipment
Token equipment
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.044
Top resid features:
meaning
Token meaning
Feature activation-0.158
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
can
Token can
Feature activation-0.092
Top resid features:
introduce
Token introduce
Feature activation-0.137
Top resid features:
far
Token far
Feature activation+4.226
Top resid features:
more
Token more
Feature activation+0.123
Top resid features:
without
Token without
Feature activation+0.000
Top resid features:
feeling
Token feeling
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
their
Token their
Feature activation-0.025
Top resid features:
ball
Token ball
Feature activation+0.017
Top resid features:
retention
Token retention
Feature activation-0.048
Top resid features:
must
Token must
Feature activation-0.300
Top resid features:
be
Token be
Feature activation-0.084
Top resid features:
far
Token far
Feature activation+4.065
Top resid features:
better
Token better
Feature activation+0.220
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:
As
TokenAs
Feature activation+0.000
Top resid features:
criticism
Token criticism
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
This
Token This
Feature activation+0.023
Top resid features:
situation
Token situation
Feature activation-0.084
Top resid features:
,
Token,
Feature activation-0.207
Top resid features:
far
Token far
Feature activation+3.975
Top resid features:
more
Token more
Feature activation+0.113
Top resid features:
chaotic
Token chaotic
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
free
Token free
Feature activation+0.002
Top resid features:
agent
Token agent
Feature activation+0.006
Top resid features:
pitches
Token pitches
Feature activation-0.015
Top resid features:
;
Token;
Feature activation-0.086
Top resid features:
far
Token far
Feature activation+3.806
Top resid features:
more
Token more
Feature activation+0.075
Top resid features:
than
Token than
Feature activation+0.049
Top resid features:
Jim
Token Jim
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:
of
Token of
Feature activation+0.011
Top resid features:
settlements
Token settlements
Feature activation+0.004
Top resid features:
because
Token because
Feature activation-0.022
Top resid features:
it
Token it
Feature activation-0.070
Top resid features:
is
Token is
Feature activation-0.078
Top resid features:
far
Token far
Feature activation+3.822
Top resid features:
less
Token less
Feature activation+0.195
Top resid features:
costly
Token costly
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
deep
Token deep
Feature activation+0.000
Top resid features:
Earth
TokenEarth
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
though
Token though
Feature activation-0.037
Top resid features:
,
Token,
Feature activation-0.179
Top resid features:
with
Token with
Feature activation-0.043
Top resid features:
far
Token far
Feature activation+3.922
Top resid features:
more
Token more
Feature activation+0.112
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
offer
Token offer
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Peter
Token Peter
Feature activation+0.000
Top resid features:
improvement
Token improvement
Feature activation+0.008
Top resid features:
between
Token between
Feature activation+0.005
Top resid features:
two
Token two
Feature activation+0.004
Top resid features:
measurements
Token measurements
Feature activation-0.031
Top resid features:
is
Token is
Feature activation-0.373
Top resid features:
far
Token far
Feature activation+3.832
Top resid features:
larger
Token larger
Feature activation+0.337
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
world
Token world
Feature activation+0.006
Top resid features:
over
Token over
Feature activation-0.024
Top resid features:
is
Token is
Feature activation-0.115
Top resid features:
something
Token something
Feature activation-0.014
Top resid features:
far
Token far
Feature activation+3.823
Top resid features:
more
Token more
Feature activation+0.103
Top resid features:
universal
Token universal
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
fun
Token fun
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.020
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
emergency
Token emergency
Feature activation-0.006
Top resid features:
spending
Token spending
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.050
Top resid features:
far
Token far
Feature activation+3.573
Top resid features:
less
Token less
Feature activation+0.034
Top resid features:
than
Token than
Feature activation+0.152
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
3
Token3
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
his
Token his
Feature activation-0.007
Top resid features:
life
Token life
Feature activation-0.023
Top resid features:
was
Token was
Feature activation-0.033
Top resid features:
cut
Token cut
Feature activation-0.005
Top resid features:
far
Token far
Feature activation+3.559
Top resid features:
too
Token too
Feature activation+0.217
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
My
Token My
Feature activation+0.000
Top resid features:
condolences
Token condolences
Feature activation+0.000
Top resid features:
offshore
Token offshore
Feature activation-0.011
Top resid features:
energy
Token energy
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
avoid
Token avoid
Feature activation+0.108
Top resid features:
taking
Token taking
Feature activation+0.050
Top resid features:
far
Token far
Feature activation+3.315
Top resid features:
more
Token more
Feature activation+0.151
Top resid features:
politically
Token politically
Feature activation+0.000
Top resid features:
challenging
Token challenging
Feature activation+0.000
Top resid features:
steps
Token steps
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.08

Head 3: 0.05

Head 4: 0.02

Head 5: 0.03

Head 6: 0.43

Head 7: 0.06

Head 8: 0.08

Head 9: 0.06

Head 10: 0.08

Head 11: 0.08

Positive logits

"]=>1.04

Wein0.97

Spiel0.97

Hew0.92

erman0.91

enthal0.91

WTO0.91

gal0.91

Weber0.90

rontal0.90

Fed0.89

ATCH0.89

lier0.88

Cer0.87

EMS0.86

Wins0.86

Sensor0.86

USD0.86

Hoff0.85

Crimes0.84

Negative logits

/,-1.17

blance-1.13

pai-1.13

ictionary-1.10

plementation-1.09

iage-1.09

>-1.04

ea-1.02

pet-1.02

etc-1.01

advertisement-1.01

ppo-1.00

yip-1.00

ocument-0.99

anasia-0.99

pei-0.98

utsu-0.97

oğan-0.97

ei-0.96

iframe-0.96

INTERVAL 3.346 - 3.718
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
That
TokenThat
Feature activation+0.000
shift
Token shift
Feature activation+0.000
meant
Token meant
Feature activation+0.000
far
Token far
Feature activation+0.797
more
Token more
Feature activation+3.630
settlements
Token settlements
Feature activation+0.176
ended
Token ended
Feature activation+0.000
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
owners
Token owners
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
far
Token far
Feature activation+0.418
more
Token more
Feature activation+3.372
gun
Token gun
Feature activation+0.166
deaths
Token deaths
Feature activation+0.036
.
Token.
Feature activation+0.000
Studies
Token Studies
Feature activation+0.000
have
Token have
Feature activation+0.000
body
Token body
Feature activation+0.000
count
Token count
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000
ately
Tokenately
Feature activation+0.000
far
Token far
Feature activation+0.000
greater
Token greater
Feature activation+3.718
than
Token than
Feature activation+2.942
the
Token the
Feature activation+0.808
number
Token number
Feature activation+0.032
of
Token of
Feature activation+0.000
fatalities
Token fatalities
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
eat
Token eat
Feature activation+0.000
far
Token far
Feature activation+0.395
less
Token less
Feature activation+3.525
dairy
Token dairy
Feature activation+0.528
in
Token in
Feature activation+0.774
these
Token these
Feature activation+0.151
three
Token three
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
far
Token far
Feature activation+0.321
greater
Token greater
Feature activation+3.403
levels
Token levels
Feature activation+1.843
of
Token of
Feature activation+0.474
trace
Token trace
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.974 - 3.346
CONTAINS 0.002%

between
Token between
Feature activation+0.000
two
Token two
Feature activation+0.000
measurements
Token measurements
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.442
larger
Token larger
Feature activation+3.166
than
Token than
Feature activation+2.804
what
Token what
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+0.000
normally
Token normally
Feature activation+0.000
ball
Token ball
Feature activation+0.000
retention
Token retention
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
far
Token far
Feature activation+0.017
better
Token better
Feature activation+3.243
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
with
Token with
Feature activation+0.000
exhaustion
Token exhaustion
Feature activation+0.000
to
Token to
Feature activation+0.000
establish
Token establish
Feature activation+0.000
in
Token in
Feature activation+0.000
far
Token far
Feature activation+0.735
more
Token more
Feature activation+2.976
swiftly
Token swiftly
Feature activation+1.767
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
buy
Token buy
Feature activation+0.000
less
Token less
Feature activation+0.000
furniture
Token furniture
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+1.056
less
Token less
Feature activation+3.254
lawn
Token lawn
Feature activation+0.030
and
Token and
Feature activation+0.252
gardening
Token gardening
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
situation
Token situation
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.175
more
Token more
Feature activation+3.241
chaotic
Token chaotic
Feature activation+1.928
than
Token than
Feature activation+2.258
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+0.000
needed
Token needed
Feature activation+0.000

INTERVAL 2.603 - 2.974
CONTAINS 0.002%

intervals
Token intervals
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+2.843
precise
Token precise
Feature activation+2.012
than
Token than
Feature activation+2.087
even
Token even
Feature activation+0.221
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
less
Token less
Feature activation+3.200
costly
Token costly
Feature activation+2.910
than
Token than
Feature activation+2.492
taking
Token taking
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
other
Token other
Feature activation+0.000
hand
Token hand
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
bigger
Token bigger
Feature activation+2.929
than
Token than
Feature activation+2.620
the
Token the
Feature activation+0.770
New
Token New
Feature activation+0.000
Republic
Token Republic
Feature activation+0.000
hopes
Token hopes
Feature activation+0.000
economies
Token economies
Feature activation+0.000
could
Token could
Feature activation+0.000
perform
Token perform
Feature activation+0.000
far
Token far
Feature activation+1.662
better
Token better
Feature activation+2.830
than
Token than
Feature activation+2.837
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
IMF
Token IMF
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
spending
Token spending
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.962
less
Token less
Feature activation+2.682
than
Token than
Feature activation+3.071
the
Token the
Feature activation+1.161
$
Token $
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.231 - 2.603
CONTAINS 0.001%

have
Token have
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
low
Token low
Feature activation+0.000
far
Token far
Feature activation+1.389
longer
Token longer
Feature activation+2.918
than
Token than
Feature activation+2.492
most
Token most
Feature activation+0.000
expected
Token expected
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Port
Token Port
Feature activation+0.000
e
Tokene
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+0.683
more
Token more
Feature activation+2.435
devastating
Token devastating
Feature activation+1.049
effect
Token effect
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
British
Token British
Feature activation+0.000
12
Token 12
Feature activation+0.000
basic
Token basic
Feature activation+0.000
zones
Token zones
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.286
fewer
Token fewer
Feature activation+2.515
than
Token than
Feature activation+2.697
is
Token is
Feature activation+0.574
typical
Token typical
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
,
Token,
Feature activation+0.000
people
Token people
Feature activation+0.000
would
Token would
Feature activation+0.000
do
Token do
Feature activation+0.000
far
Token far
Feature activation+0.629
better
Token better
Feature activation+2.380
under
Token under
Feature activation+1.053
the
Token the
Feature activation+0.899
existing
Token existing
Feature activation+0.000
tipping
Token tipping
Feature activation+0.000
model
Token model
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
less
Token less
Feature activation+3.200
costly
Token costly
Feature activation+2.910
than
Token than
Feature activation+2.492
taking
Token taking
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+0.079

INTERVAL 1.859 - 2.231
CONTAINS 0.001%

conducted
Token conducted
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
far
Token far
Feature activation+0.309
c
Tokenc
Feature activation+0.611
ical
Tokenical
Feature activation+1.902
entrance
Token entrance
Feature activation+0.526
tests
Token tests
Feature activation+0.000
by
Token by
Feature activation+0.000
supplying
Token supplying
Feature activation+0.000
both
Token both
Feature activation+0.000
But
Token But
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+0.734
better
Token better
Feature activation+1.996
option
Token option
Feature activation+0.014
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.000
ticket
Token ticket
Feature activation+0.000
.
Token.
Feature activation+0.000
odds
Token odds
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.000
far
Token far
Feature activation+1.184
o
Tokeno
Feature activation+0.746
or
Token or
Feature activation+1.909
other
Token other
Feature activation+2.324
card
Token card
Feature activation+0.292
games
Token games
Feature activation+0.000
.[
Token.[
Feature activation+0.000
1
Token1
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+2.843
precise
Token precise
Feature activation+2.012
than
Token than
Feature activation+2.087
even
Token even
Feature activation+0.221
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
skilled
Token skilled
Feature activation+0.000
tw
Token tw
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
Far
TokenFar
Feature activation+0.000
too
Token too
Feature activation+2.038
often
Token often
Feature activation+1.344
when
Token when
Feature activation+0.792
Black
Token Black
Feature activation+0.000
gay
Token gay
Feature activation+0.000
men
Token men
Feature activation+0.000

INTERVAL 1.487 - 1.859
CONTAINS 0.001%

further
Token further
Feature activation+0.000
underground
Token underground
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+1.095
from
Token from
Feature activation+0.886
the
Token the
Feature activation+1.672
reach
Token reach
Feature activation+0.360
of
Token of
Feature activation+0.000
potential
Token potential
Feature activation+0.000
sav
Token sav
Feature activation+0.000
iors
Tokeniors
Feature activation+0.000
Link
TokenLink
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
above
Token above
Feature activation+1.469
and
Token and
Feature activation+0.367
beyond
Token beyond
Feature activation+1.573
anything
Token anything
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+1.385
away
Tokenaway
Feature activation+0.828
kingdom
Token kingdom
Feature activation+1.581
turned
Token turned
Feature activation+0.000
upside
Token upside
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
far
Token far
Feature activation+0.321
greater
Token greater
Feature activation+3.403
levels
Token levels
Feature activation+1.843
of
Token of
Feature activation+0.474
trace
Token trace
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.000
far
Token far
Feature activation+0.567
-
Token-
Feature activation+1.366
away
Tokenaway
Feature activation+1.177
locations
Token locations
Feature activation+1.843
that
Token that
Feature activation+0.197
cost
Token cost
Feature activation+0.000
a
Token a
Feature activation+0.000
fortune
Token fortune
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.115 - 1.487
CONTAINS 0.004%

:
Token:
Feature activation+0.000
Century
Token Century
Feature activation+0.000
Link
TokenLink
Feature activation+0.000
is
Token is
Feature activation+0.000
far
Token far
Feature activation+0.000
above
Token above
Feature activation+1.469
and
Token and
Feature activation+0.367
beyond
Token beyond
Feature activation+1.573
anything
Token anything
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
stage
Token stage
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+1.385
away
Tokenaway
Feature activation+0.828
kingdom
Token kingdom
Feature activation+1.581
turned
Token turned
Feature activation+0.000
upside
Token upside
Feature activation+0.000
down
Token down
Feature activation+0.000
bad
Token bad
Feature activation+0.000
game
Token game
Feature activation+0.000
-
Token -
Feature activation+0.000
far
Token far
Feature activation+1.122
from
Token from
Feature activation+0.104
it
Token it
Feature activation+1.449
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dave
TokenDave
Feature activation+0.000
made
Token made
Feature activation+0.000
and
Token and
Feature activation+0.000
who
Token who
Feature activation+0.000
sits
Token sits
Feature activation+0.000
far
Token far
Feature activation+0.752
to
Token to
Feature activation+1.176
the
Token the
Feature activation+1.307
left
Token left
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
Party
Token Party
Feature activation+0.000
a
Token a
Feature activation+0.000
wearable
Token wearable
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+1.216
aday
Tokenaday
Feature activation+1.106
cage
Token cage
Feature activation+1.350
.
Token.
Feature activation+0.000
E
Token E
Feature activation+0.000
SD
TokenSD
Feature activation+0.000

INTERVAL 0.744 - 1.115
CONTAINS 0.008%

a
Token a
Feature activation+0.000
Democrat
Token Democrat
Feature activation+0.000
and
Token and
Feature activation+0.000
who
Token who
Feature activation+0.000
sits
Token sits
Feature activation+0.000
far
Token far
Feature activation+0.752
to
Token to
Feature activation+1.176
the
Token the
Feature activation+1.307
left
Token left
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
drive
Token drive
Feature activation+0.000
them
Token them
Feature activation+0.000
further
Token further
Feature activation+0.000
underground
Token underground
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+1.095
from
Token from
Feature activation+0.886
the
Token the
Feature activation+1.672
reach
Token reach
Feature activation+0.360
of
Token of
Feature activation+0.000
potential
Token potential
Feature activation+0.000
them
Token them
Feature activation+0.000
further
Token further
Feature activation+0.000
underground
Token underground
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+1.095
from
Token from
Feature activation+0.886
the
Token the
Feature activation+1.672
reach
Token reach
Feature activation+0.360
of
Token of
Feature activation+0.000
potential
Token potential
Feature activation+0.000
sav
Token sav
Feature activation+0.000
idiot
Token idiot
Feature activation+0.000
."
Token."
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+0.885
cry
Token cry
Feature activation+0.810
from
Token from
Feature activation+0.182
the
Token the
Feature activation+0.118
classic
Token classic
Feature activation+0.000
TV
Token TV
Feature activation+0.000
aced
Tokenaced
Feature activation+0.000
and
Token and
Feature activation+0.000
dis
Token dis
Feature activation+0.000
re
Tokenre
Feature activation+0.000
putable
Tokenputable
Feature activation+0.000
far
Token far
Feature activation+0.775
-
Token-
Feature activation+1.675
left
Tokenleft
Feature activation+0.016
and
Token and
Feature activation+1.941
so
Token so
Feature activation+0.950
-
Token-
Feature activation+0.000

INTERVAL 0.372 - 0.744
CONTAINS 0.011%

rather
Token rather
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
far
Token far
Feature activation+0.000
the
Token the
Feature activation+0.376
contents
Token contents
Feature activation+0.000
of
Token of
Feature activation+0.000
four
Token four
Feature activation+0.000
basic
Token basic
Feature activation+0.000
boxes
Token boxes
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
financing
Token financing
Feature activation+0.000
levels
Token levels
Feature activation+0.000
are
Token are
Feature activation+0.000
far
Token far
Feature activation+0.669
below
Token below
Feature activation+2.585
those
Token those
Feature activation+0.126
even
Token even
Feature activation+0.062
in
Token in
Feature activation+0.000
other
Token other
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
far
Tokenfar
Feature activation+0.000
removed
Token removed
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.374
lived
Token lived
Feature activation+0.000
realities
Token realities
Feature activation+0.000
of
Token of
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
over
Token over
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
far
Token far
Feature activation+0.598
more
Token more
Feature activation+3.105
universal
Token universal
Feature activation+0.835
:
Token:
Feature activation+0.000
fun
Token fun
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
local
Token local
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
far
Token far
Feature activation+0.542
(
Token (
Feature activation+0.666
Mel
TokenMel
Feature activation+0.000
bourne
Tokenbourne
Feature activation+0.000
in
Token in
Feature activation+0.000
particular
Token particular
Feature activation+0.000

INTERVAL 0.000 - 0.372
CONTAINS 99.969%

manufacturer
Token manufacturer
Feature activation+0.000
Z
Token Z
Feature activation+0.000
d
Tokend
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ien
Tokenien
Feature activation+0.000
ci
Tokenci
Feature activation+0.000
k
Tokenk
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.000
is
Token is
Feature activation+0.000
already
Token already
Feature activation+0.000
historically
Token historically
Feature activation+0.000
unpopular
Token unpopular
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
president
Token president
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
,
Token,
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
'
Token '
Feature activation+0.000
cause
Tokencause
Feature activation+0.000
I
Token I
Feature activation+0.000
thought
Token thought
Feature activation+0.000
like
Tokenlike
Feature activation+0.000
composition
Token composition
Feature activation+0.000
from
Token from
Feature activation+0.000
Live
Token Live
Feature activation+0.000
More
TokenMore
Feature activation+0.000
including
Token including
Feature activation+0.000
Eventually
TokenEventually
Feature activation+0.000
,
Token,
Feature activation+0.000
World
Token World
Feature activation+0.000
Elite
Token Elite
Feature activation+0.000
would
Token would
Feature activation+0.000
the
Token the
Feature activation+0.000
November
Token November
Feature activation+0.000
figures
Token figures
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
40
Token 40
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H3.6: (feature 3604)

TOP ACTIVATIONS
MAX = 2.583

because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
president
Token president
Feature activation+0.792
's
Token's
Feature activation+2.583
continued
Token continued
Feature activation+1.135
attacks
Token attacks
Feature activation+1.391
on
Token on
Feature activation+0.877
freedom
Token freedom
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
president
Token president
Feature activation+1.607
âĢ
TokenâĢ
Feature activation+1.358
Ļ
TokenĻ
Feature activation+0.618
s
Tokens
Feature activation+2.550
millions
Token millions
Feature activation+1.327
of
Token of
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.040
concerns
Token concerns
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.643
's
Token's
Feature activation+2.301
comments
Token comments
Feature activation+2.488
are
Token are
Feature activation+0.222
affecting
Token affecting
Feature activation+1.038
public
Token public
Feature activation+0.134
perceptions
Token perceptions
Feature activation+0.000
.
Token.
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.486
âĢ
TokenâĢ
Feature activation+0.773
Ļ
TokenĻ
Feature activation+0.269
s
Tokens
Feature activation+2.473
handling
Token handling
Feature activation+1.116
of
Token of
Feature activation+0.725
foreign
Token foreign
Feature activation+0.019
policy
Token policy
Feature activation+0.000
.
Token.
Feature activation+0.000
have
Token have
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.643
's
Token's
Feature activation+2.301
comments
Token comments
Feature activation+2.488
are
Token are
Feature activation+0.222
affecting
Token affecting
Feature activation+1.038
public
Token public
Feature activation+0.134
perceptions
Token perceptions
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.624
is
Token is
Feature activation+1.550
emph
Token emph
Feature activation+0.970
atic
Tokenatic
Feature activation+0.911
about
Token about
Feature activation+2.237
it
Token it
Feature activation+0.322
.
Token.
Feature activation+0.275
We
Token We
Feature activation+0.000
're
Token're
Feature activation+0.000
going
Token going
Feature activation+0.000
dramatic
Token dramatic
Feature activation+0.000
reversal
Token reversal
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+1.486
himself
Token himself
Feature activation+2.225
shared
Token shared
Feature activation+1.386
some
Token some
Feature activation+0.426
concerning
Token concerning
Feature activation+0.048
details
Token details
Feature activation+0.000
about
Token about
Feature activation+0.732
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+1.781
added
Token added
Feature activation+2.171
that
Token that
Feature activation+0.915
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
during
Tokenduring
Feature activation+0.000
this
Token this
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.548
âĢ
TokenâĢ
Feature activation+1.098
Ļ
TokenĻ
Feature activation+0.455
s
Tokens
Feature activation+2.099
premise
Token premise
Feature activation+1.744
,
Token,
Feature activation+0.260
all
Token all
Feature activation+0.000
150
Token 150
Feature activation+0.000
global
Token global
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.501
or
Token or
Feature activation+1.831
the
Token the
Feature activation+1.564
foreign
Token foreign
Feature activation+2.087
minister
Token minister
Feature activation+0.811
of
Token of
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.022
ing
Tokening
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.533
âĢ
TokenâĢ
Feature activation+1.528
Ļ
TokenĻ
Feature activation+0.642
s
Tokens
Feature activation+2.033
address
Token address
Feature activation+1.056
,
Token,
Feature activation+0.344
McInt
Token McInt
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.543
âĢ
TokenâĢ
Feature activation+0.950
Ļ
TokenĻ
Feature activation+0.229
s
Tokens
Feature activation+1.990
supposed
Token supposed
Feature activation+1.207
secret
Token secret
Feature activation+1.064
Islamic
Token Islamic
Feature activation+0.036
faith
Token faith
Feature activation+0.000
have
Token have
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.000
likened
Token likened
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.847
's
Token's
Feature activation+1.946
health
Token health
Feature activation+1.940
-
Token-
Feature activation+0.000
care
Tokencare
Feature activation+0.000
fight
Token fight
Feature activation+0.375
to
Token to
Feature activation+0.000
he
Token he
Feature activation+0.000
likened
Token likened
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.847
's
Token's
Feature activation+1.946
health
Token health
Feature activation+1.940
-
Token-
Feature activation+0.000
care
Tokencare
Feature activation+0.000
fight
Token fight
Feature activation+0.375
to
Token to
Feature activation+0.000
Napoleon
Token Napoleon
Feature activation+0.000
then
Token then
Feature activation+0.000
granted
Token granted
Feature activation+0.000
the
Token the
Feature activation+0.000
authority
Token authority
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+1.929
requested
Token requested
Feature activation+1.868
in
Token in
Feature activation+1.216
October
Token October
Feature activation+0.000
.
Token.
Feature activation+0.055
In
Token In
Feature activation+0.000
strategies
Token strategies
Feature activation+0.000
aside
Token aside
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.805
believes
Token believes
Feature activation+1.927
that
Token that
Feature activation+1.036
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.000
shows
Token shows
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.450
âĢ
TokenâĢ
Feature activation+1.083
Ļ
TokenĻ
Feature activation+0.451
s
Tokens
Feature activation+1.894
lead
Token lead
Feature activation+1.374
is
Token is
Feature activation+0.600
just
Token just
Feature activation+0.000
outside
Token outside
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
President
Token President
Feature activation+1.708
's
Token's
Feature activation+1.660
campaign
Token campaign
Feature activation+1.885
-
Token-
Feature activation+0.000
like
Tokenlike
Feature activation+0.091
appearance
Token appearance
Feature activation+0.757
came
Token came
Feature activation+0.418
at
Token at
Feature activation+0.000
granted
Token granted
Feature activation+0.000
the
Token the
Feature activation+0.000
authority
Token authority
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+1.929
requested
Token requested
Feature activation+1.868
in
Token in
Feature activation+1.216
October
Token October
Feature activation+0.000
.
Token.
Feature activation+0.055
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
it
Token it
Feature activation+0.000
gives
Token gives
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+1.157
options
Token options
Feature activation+1.258
in
Token in
Feature activation+1.863
the
Token the
Feature activation+1.132
region
Token region
Feature activation+0.267
.
Token.
Feature activation+0.446
But
Token But
Feature activation+0.000
I
Token I
Feature activation+0.000

Top DFA by src position
MAX = 2.931

attend
Token attend
Feature activation-0.003
Top resid features:
because
Token because
Feature activation+0.126
Top resid features:
of
Token of
Feature activation+0.150
Top resid features:
"
Token "
Feature activation+0.020
Top resid features:
the
Tokenthe
Feature activation+0.149
Top resid features:
president
Token president
Feature activation+2.750
Top resid features:
's
Token's
Feature activation+0.017
Top resid features:
continued
Token continued
Feature activation+0.000
Top resid features:
attacks
Token attacks
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
freedom
Token freedom
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
The
TokenThe
Feature activation+0.229
Top resid features:
president
Token president
Feature activation+2.816
Top resid features:
âĢ
TokenâĢ
Feature activation+0.059
Top resid features:
Ļ
TokenĻ
Feature activation+0.055
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
millions
Token millions
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
does
Token does
Feature activation-0.006
Top resid features:
have
Token have
Feature activation+0.014
Top resid features:
concerns
Token concerns
Feature activation-0.008
Top resid features:
that
Token that
Feature activation+0.107
Top resid features:
the
Token the
Feature activation+0.161
Top resid features:
president
Token president
Feature activation+2.931
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
comments
Token comments
Feature activation-0.100
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
affecting
Token affecting
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
approval
Token approval
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.120
Top resid features:
president
Token president
Feature activation+2.762
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.099
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
handling
Token handling
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
does
Token does
Feature activation-0.002
Top resid features:
have
Token have
Feature activation+0.015
Top resid features:
concerns
Token concerns
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.197
Top resid features:
president
Token president
Feature activation+2.632
Top resid features:
's
Token's
Feature activation+0.022
Top resid features:
comments
Token comments
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
affecting
Token affecting
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
legitimate
Token legitimate
Feature activation-0.012
Top resid features:
question
Token question
Feature activation-0.034
Top resid features:
,
Token,
Feature activation+0.099
Top resid features:
the
Token the
Feature activation+0.102
Top resid features:
president
Token president
Feature activation+2.508
Top resid features:
is
Token is
Feature activation+0.109
Top resid features:
emph
Token emph
Feature activation+0.045
Top resid features:
atic
Tokenatic
Feature activation-0.022
Top resid features:
about
Token about
Feature activation+0.027
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
dramatic
Token dramatic
Feature activation+0.004
Top resid features:
reversal
Token reversal
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
The
Token The
Feature activation+0.123
Top resid features:
president
Token president
Feature activation+2.581
Top resid features:
himself
Token himself
Feature activation+0.051
Top resid features:
shared
Token shared
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
concerning
Token concerning
Feature activation+0.000
Top resid features:
details
Token details
Feature activation+0.000
Top resid features:
28
Token 28
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ŀ
TokenĿ
Feature activation+0.034
Top resid features:
The
Token The
Feature activation+0.181
Top resid features:
president
Token president
Feature activation+2.526
Top resid features:
added
Token added
Feature activation-0.016
Top resid features:
that
Token that
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:
during
Tokenduring
Feature activation+0.000
Top resid features:
asc
Token asc
Feature activation+0.004
Top resid features:
ribe
Tokenribe
Feature activation+0.010
Top resid features:
validity
Token validity
Feature activation-0.019
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.113
Top resid features:
president
Token president
Feature activation+2.395
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.113
Top resid features:
s
Tokens
Feature activation+0.029
Top resid features:
premise
Token premise
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
't
Token't
Feature activation-0.000
Top resid features:
hear
Token hear
Feature activation-0.002
Top resid features:
much
Token much
Feature activation+0.001
Top resid features:
about
Token about
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
president
Token president
Feature activation+2.152
Top resid features:
or
Token or
Feature activation+0.217
Top resid features:
the
Token the
Feature activation+0.229
Top resid features:
foreign
Token foreign
Feature activation+0.129
Top resid features:
minister
Token minister
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Preview
TokenPreview
Feature activation+0.019
Top resid features:
ing
Tokening
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.106
Top resid features:
president
Token president
Feature activation+2.306
Top resid features:
âĢ
TokenâĢ
Feature activation+0.049
Top resid features:
Ļ
TokenĻ
Feature activation+0.038
Top resid features:
s
Tokens
Feature activation+0.022
Top resid features:
address
Token address
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Cons
TokenCons
Feature activation+0.017
Top resid features:
piracy
Tokenpiracy
Feature activation+0.003
Top resid features:
theories
Token theories
Feature activation-0.027
Top resid features:
about
Token about
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.093
Top resid features:
president
Token president
Feature activation+2.387
Top resid features:
âĢ
TokenâĢ
Feature activation+0.059
Top resid features:
Ļ
TokenĻ
Feature activation+0.069
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
supposed
Token supposed
Feature activation+0.000
Top resid features:
secret
Token secret
Feature activation+0.000
Top resid features:
allies
Token allies
Feature activation-0.013
Top resid features:
after
Token after
Feature activation+0.017
Top resid features:
he
Token he
Feature activation+0.005
Top resid features:
likened
Token likened
Feature activation+0.154
Top resid features:
the
Token the
Feature activation+0.211
Top resid features:
president
Token president
Feature activation+2.146
Top resid features:
's
Token's
Feature activation+0.028
Top resid features:
health
Token health
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
care
Tokencare
Feature activation+0.000
Top resid features:
fight
Token fight
Feature activation+0.000
Top resid features:
allies
Token allies
Feature activation-0.003
Top resid features:
after
Token after
Feature activation-0.010
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
likened
Token likened
Feature activation+0.068
Top resid features:
the
Token the
Feature activation+0.151
Top resid features:
president
Token president
Feature activation+2.328
Top resid features:
's
Token's
Feature activation+0.028
Top resid features:
health
Token health
Feature activation-0.034
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
care
Tokencare
Feature activation+0.000
Top resid features:
fight
Token fight
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.005
Top resid features:
granted
Token granted
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.084
Top resid features:
authority
Token authority
Feature activation-0.162
Top resid features:
the
Token the
Feature activation+0.339
Top resid features:
President
Token President
Feature activation+2.269
Top resid features:
requested
Token requested
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
October
Token October
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:
tax
Token tax
Feature activation-0.003
Top resid features:
strategies
Token strategies
Feature activation-0.018
Top resid features:
aside
Token aside
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.104
Top resid features:
the
Token the
Feature activation+0.106
Top resid features:
president
Token president
Feature activation+2.407
Top resid features:
believes
Token believes
Feature activation-0.053
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
released
Token released
Feature activation+0.010
Top resid features:
Wednesday
Token Wednesday
Feature activation-0.032
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
shows
Token shows
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.142
Top resid features:
president
Token president
Feature activation+2.143
Top resid features:
âĢ
TokenâĢ
Feature activation+0.043
Top resid features:
Ļ
TokenĻ
Feature activation+0.104
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
lead
Token lead
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
ammunition
Token ammunition
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
The
TokenThe
Feature activation+0.155
Top resid features:
President
Token President
Feature activation+2.311
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
campaign
Token campaign
Feature activation+0.026
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
like
Tokenlike
Feature activation+0.000
Top resid features:
appearance
Token appearance
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.041
Top resid features:
granted
Token granted
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.069
Top resid features:
authority
Token authority
Feature activation-0.050
Top resid features:
the
Token the
Feature activation+0.229
Top resid features:
President
Token President
Feature activation+2.093
Top resid features:
requested
Token requested
Feature activation+0.062
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
October
Token October
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:
,
Token,
Feature activation+0.033
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
gives
Token gives
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
President
Token President
Feature activation+2.085
Top resid features:
options
Token options
Feature activation+0.125
Top resid features:
in
Token in
Feature activation+0.104
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
region
Token region
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.06

Head 3: 0.04

Head 4: 0.04

Head 5: 0.06

Head 6: 0.42

Head 7: 0.07

Head 8: 0.05

Head 9: 0.04

Head 10: 0.08

Head 11: 0.06

Positive logits

�士1.57

EStream1.31

veto1.31

panic1.28

umatic1.28

覚醒1.28

uct1.26

hyde1.26

reath1.25

1.20

Exhibit1.20

Cabin1.19

alsh1.16

chal1.16

reditary1.16

uphem1.14

cuff1.14

Mosque1.14

oggles1.14

1.13

Negative logits

collectively-1.18

ρ-1.07

LEVEL-1.07

specialization-1.06

ikhail-1.05

Tes-1.04

humankind-1.03

respectively-1.02

ancers-1.01

themselves-0.99

caster-0.99

ERE-0.98

blight-0.97

ancer-0.97

ANC-0.97

offline-0.97

Artemis-0.96

shards-0.95

OUR-0.95

juveniles-0.95

INTERVAL 2.325 - 2.583
CONTAINS 0.000%

because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
president
Token president
Feature activation+0.792
's
Token's
Feature activation+2.583
continued
Token continued
Feature activation+1.135
attacks
Token attacks
Feature activation+1.391
on
Token on
Feature activation+0.877
freedom
Token freedom
Feature activation+0.000
of
Token of
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.643
's
Token's
Feature activation+2.301
comments
Token comments
Feature activation+2.488
are
Token are
Feature activation+0.222
affecting
Token affecting
Feature activation+1.038
public
Token public
Feature activation+0.134
perceptions
Token perceptions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
president
Token president
Feature activation+1.607
âĢ
TokenâĢ
Feature activation+1.358
Ļ
TokenĻ
Feature activation+0.618
s
Tokens
Feature activation+2.550
millions
Token millions
Feature activation+1.327
of
Token of
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.040
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.486
âĢ
TokenâĢ
Feature activation+0.773
Ļ
TokenĻ
Feature activation+0.269
s
Tokens
Feature activation+2.473
handling
Token handling
Feature activation+1.116
of
Token of
Feature activation+0.725
foreign
Token foreign
Feature activation+0.019
policy
Token policy
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.066 - 2.325
CONTAINS 0.001%

about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.501
or
Token or
Feature activation+1.831
the
Token the
Feature activation+1.564
foreign
Token foreign
Feature activation+2.087
minister
Token minister
Feature activation+0.811
of
Token of
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.022
dramatic
Token dramatic
Feature activation+0.000
reversal
Token reversal
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+1.486
himself
Token himself
Feature activation+2.225
shared
Token shared
Feature activation+1.386
some
Token some
Feature activation+0.426
concerning
Token concerning
Feature activation+0.048
details
Token details
Feature activation+0.000
about
Token about
Feature activation+0.732
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.624
is
Token is
Feature activation+1.550
emph
Token emph
Feature activation+0.970
atic
Tokenatic
Feature activation+0.911
about
Token about
Feature activation+2.237
it
Token it
Feature activation+0.322
.
Token.
Feature activation+0.275
We
Token We
Feature activation+0.000
're
Token're
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.548
âĢ
TokenâĢ
Feature activation+1.098
Ļ
TokenĻ
Feature activation+0.455
s
Tokens
Feature activation+2.099
premise
Token premise
Feature activation+1.744
,
Token,
Feature activation+0.260
all
Token all
Feature activation+0.000
150
Token 150
Feature activation+0.000
global
Token global
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+1.781
added
Token added
Feature activation+2.171
that
Token that
Feature activation+0.915
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
during
Tokenduring
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 1.808 - 2.066
CONTAINS 0.002%

hear
Token hear
Feature activation+0.000
much
Token much
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.501
or
Token or
Feature activation+1.831
the
Token the
Feature activation+1.564
foreign
Token foreign
Feature activation+2.087
minister
Token minister
Feature activation+0.811
of
Token of
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
talks
Token talks
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.513
weighed
Token weighed
Feature activation+1.841
in
Token in
Feature activation+0.434
with
Token with
Feature activation+0.169
Schumer
Token Schumer
Feature activation+0.000
from
Token from
Feature activation+0.000
Air
Token Air
Feature activation+0.000
after
Token after
Feature activation+0.000
he
Token he
Feature activation+0.000
likened
Token likened
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.847
's
Token's
Feature activation+1.946
health
Token health
Feature activation+1.940
-
Token-
Feature activation+0.000
care
Tokencare
Feature activation+0.000
fight
Token fight
Feature activation+0.375
to
Token to
Feature activation+0.000
granted
Token granted
Feature activation+0.000
the
Token the
Feature activation+0.000
authority
Token authority
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+1.929
requested
Token requested
Feature activation+1.868
in
Token in
Feature activation+1.216
October
Token October
Feature activation+0.000
.
Token.
Feature activation+0.055
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
then
Token then
Feature activation+0.000
granted
Token granted
Feature activation+0.000
the
Token the
Feature activation+0.000
authority
Token authority
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+1.929
requested
Token requested
Feature activation+1.868
in
Token in
Feature activation+1.216
October
Token October
Feature activation+0.000
.
Token.
Feature activation+0.055
In
Token In
Feature activation+0.000

INTERVAL 1.550 - 1.808
CONTAINS 0.004%

not
Token not
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.281
or
Token or
Feature activation+1.676
prime
Token prime
Feature activation+1.591
minister
Token minister
Feature activation+1.242
of
Token of
Feature activation+0.200
a
Token a
Feature activation+0.069
country
Token country
Feature activation+0.000
is
Token is
Feature activation+0.609
does
Token does
Feature activation+0.000
have
Token have
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.643
's
Token's
Feature activation+2.301
comments
Token comments
Feature activation+2.488
are
Token are
Feature activation+0.222
affecting
Token affecting
Feature activation+1.038
public
Token public
Feature activation+0.134
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.726
âĢ
TokenâĢ
Feature activation+0.893
Ļ
TokenĻ
Feature activation+0.292
s
Tokens
Feature activation+1.678
first
Token first
Feature activation+1.056
ludicrous
Token ludicrous
Feature activation+0.781
experience
Token experience
Feature activation+0.777
with
Token with
Feature activation+0.215
chicken
Token chicken
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.172
will
Token will
Feature activation+1.007
do
Token do
Feature activation+1.614
in
Token in
Feature activation+1.619
support
Token support
Feature activation+0.323
of
Token of
Feature activation+0.000
Strange
Token Strange
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
President
Token President
Feature activation+1.708
's
Token's
Feature activation+1.660
campaign
Token campaign
Feature activation+1.885
-
Token-
Feature activation+0.000
like
Tokenlike
Feature activation+0.091
appearance
Token appearance
Feature activation+0.757
came
Token came
Feature activation+0.418

INTERVAL 1.291 - 1.550
CONTAINS 0.007%

the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.526
âĢ
TokenâĢ
Feature activation+0.569
Ļ
TokenĻ
Feature activation+0.078
s
Tokens
Feature activation+1.794
current
Token current
Feature activation+1.351
strategy
Token strategy
Feature activation+1.001
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
president
Token president
Feature activation+1.607
âĢ
TokenâĢ
Feature activation+1.358
Ļ
TokenĻ
Feature activation+0.618
s
Tokens
Feature activation+2.550
millions
Token millions
Feature activation+1.327
of
Token of
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.211
âĢ
TokenâĢ
Feature activation+0.244
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.166
actions
Token actions
Feature activation+1.458
were
Token were
Feature activation+0.357
lawful
Token lawful
Feature activation+0.628
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.918
from
Token from
Feature activation+1.313
being
Token being
Feature activation+0.700
re
Token re
Feature activation+0.111
-
Token-
Feature activation+0.000
elected
Tokenelected
Feature activation+0.259
.
Token.
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
who
Token who
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.671
to
Token to
Feature activation+1.363
do
Token do
Feature activation+1.377
more
Token more
Feature activation+0.011
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.033 - 1.291
CONTAINS 0.009%

called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.927
"
Token "
Feature activation+0.986
completely
Tokencompletely
Feature activation+0.565
detached
Token detached
Feature activation+1.095
from
Token from
Feature activation+0.723
reality
Token reality
Feature activation+0.000
"
Token"
Feature activation+0.000
and
Token and
Feature activation+0.000
later
Token later
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
anything
Token anything
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.172
will
Token will
Feature activation+1.007
do
Token do
Feature activation+1.614
in
Token in
Feature activation+1.619
support
Token support
Feature activation+0.323
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.643
's
Token's
Feature activation+2.301
comments
Token comments
Feature activation+2.488
are
Token are
Feature activation+0.222
affecting
Token affecting
Feature activation+1.038
public
Token public
Feature activation+0.134
perceptions
Token perceptions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.122
of
Token of
Feature activation+0.448
the
Token the
Feature activation+0.433
J
Token J
Feature activation+0.118
ax
Tokenax
Feature activation+0.000
USA
TokenUSA
Feature activation+0.000
party
Token party
Feature activation+0.000
from
Token from
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+1.273
has
Token has
Feature activation+1.559
tweeted
Token tweeted
Feature activation+1.247
his
Token his
Feature activation+0.295
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.775 - 1.033
CONTAINS 0.012%

Houston
Token Houston
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Mayor
Token Mayor
Feature activation+0.000
is
Token is
Feature activation+0.081
particularly
Token particularly
Feature activation+0.808
concerned
Token concerned
Feature activation+0.722
that
Token that
Feature activation+0.052
mass
Token mass
Feature activation+0.000
layoffs
Token layoffs
Feature activation+0.000
could
Token could
Feature activation+0.000
this
Token this
Feature activation+0.000
costs
Token costs
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+0.813
's
Token's
Feature activation+1.832
terrible
Token terrible
Feature activation+1.714
energy
Token energy
Feature activation+0.736
policies
Token policies
Feature activation+1.236
are
Token are
Feature activation+0.023
These
TokenThese
Feature activation+0.000
banners
Token banners
Feature activation+0.000
,
Token,
Feature activation+0.000
welcoming
Token welcoming
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.953
in
Token in
Feature activation+1.484
carefully
Token carefully
Feature activation+0.495
arranged
Token arranged
Feature activation+0.236
sequences
Token sequences
Feature activation+0.301
of
Token of
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.617
did
Token did
Feature activation+1.353
not
Token not
Feature activation+0.936
ignore
Token ignore
Feature activation+1.424
her
Token her
Feature activation+0.205
son
Token son
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
NYT
Token NYT
Feature activation+0.000
Editor
Token Editor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.328
note
Token note
Feature activation+0.871
.
Token.
Feature activation+0.046
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.517 - 0.775
CONTAINS 0.017%

for
Token for
Feature activation+0.000
something
Token something
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+1.342
âĢ
TokenâĢ
Feature activation+0.716
Ļ
TokenĻ
Feature activation+0.111
s
Tokens
Feature activation+1.646
name
Token name
Feature activation+1.522
on
Token on
Feature activation+0.530
it
Token it
Feature activation+0.428
any
Token any
Feature activation+0.000
obligations
Token obligations
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
chancellor
Token chancellor
Feature activation+0.527
.
Token.
Feature activation+0.158
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
BER
TokenBER
Feature activation+0.000
LIN
TokenLIN
Feature activation+0.000
prime
Token prime
Feature activation+1.591
minister
Token minister
Feature activation+1.242
of
Token of
Feature activation+0.200
a
Token a
Feature activation+0.069
country
Token country
Feature activation+0.000
is
Token is
Feature activation+0.609
selected
Token selected
Feature activation+0.570
:
Token:
Feature activation+0.457
He
Token He
Feature activation+0.000
gets
Token gets
Feature activation+0.000
the
Token the
Feature activation+0.000
's
Token's
Feature activation+1.832
terrible
Token terrible
Feature activation+1.714
energy
Token energy
Feature activation+0.736
policies
Token policies
Feature activation+1.236
are
Token are
Feature activation+0.023
costing
Token costing
Feature activation+0.764
us
Token us
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.463
of
Token of
Feature activation+0.045
Higher
Token Higher
Feature activation+0.000
Education
Token Education
Feature activation+0.000
went
Token went
Feature activation+0.562
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
Budget
Token Budget
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000

INTERVAL 0.258 - 0.517
CONTAINS 0.037%

Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.124
economic
Token economic
Feature activation+0.354
advisory
Token advisory
Feature activation+0.233
group
Token group
Feature activation+0.152
inspired
Token inspired
Feature activation+0.000
a
Token a
Feature activation+0.000
viral
Token viral
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
attempts
Token attempts
Feature activation+0.347
to
Token to
Feature activation+0.392
reject
Token reject
Feature activation+0.079
or
Token or
Feature activation+0.000
undermine
Token undermine
Feature activation+0.219
or
Token or
Feature activation+0.000
Harvard
Token Harvard
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.470
went
Token went
Feature activation+1.113
to
Token to
Feature activation+0.911
Harvard
Token Harvard
Feature activation+0.000
Law
Token Law
Feature activation+0.000
School
Token School
Feature activation+0.000
"
Token"
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
mogul
Token mogul
Feature activation+0.000
running
Token running
Feature activation+0.406
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
nomination
Token nomination
Feature activation+0.000
issue
Token issue
Feature activation+0.000
like
Token like
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
Dana
Token Dana
Feature activation+0.284
White
Token White
Feature activation+0.136
interview
Token interview
Feature activation+0.073
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 0.000 - 0.258
CONTAINS 99.913%

but
Token but
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
unp
Token unp
Feature activation+0.000
added
Tokenadded
Feature activation+0.000
bra
Token bra
Feature activation+0.000
am
Token am
Feature activation+0.000
azes
Tokenazes
Feature activation+0.000
me
Token me
Feature activation+0.000
with
Token with
Feature activation+0.000
up
Token up
Feature activation+0.000
worsh
Token worsh
Feature activation+0.000
ipping
Tokenipping
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Jonathan
Token Jonathan
Feature activation+0.000
I
Token I
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
put
Token put
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Un
TokenUn
Feature activation+0.000
surprisingly
Tokensurprisingly
Feature activation+0.000
,
Token,
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
Bennett
Token Bennett
Feature activation+0.000
was
Token was
Feature activation+0.000
awarded
Token awarded
Feature activation+0.000
the
Token the
Feature activation+0.000
George
Token George
Feature activation+0.083
Medal
Token Medal
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
reports
Token reports
Feature activation+0.000
state
Token state
Feature activation+0.000
Ahmed
Token Ahmed
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
studying
Token studying
Feature activation+0.000
journalism
Token journalism
Feature activation+0.000
how
Token how
Feature activation+0.000
termination
Token termination
Feature activation+0.000
would
Token would
Feature activation+0.000
affect
Token affect
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
voters
Token voters
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
received
Token received
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H3.6: (feature 17128)

TOP ACTIVATIONS
MAX = 3.822

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.626
first
Token first
Feature activation+3.822
drive
Token drive
Feature activation+0.062
Sunday
Token Sunday
Feature activation+0.000
,
Token,
Feature activation+0.000
Belichick
Token Belichick
Feature activation+0.000
and
Token and
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
very
Token very
Feature activation+0.664
first
Token first
Feature activation+3.500
scene
Token scene
Feature activation+0.380
,
Token,
Feature activation+0.282
with
Token with
Feature activation+0.000
H
Token H
Feature activation+0.000
ux
Tokenux
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.912
first
Token first
Feature activation+3.357
image
Token image
Feature activation+0.258
of
Token of
Feature activation+0.419
the
Token the
Feature activation+0.000
release
Token release
Feature activation+0.000
we
Token we
Feature activation+0.000
new
Token new
Feature activation+0.000
songs
Token songs
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.154
first
Token first
Feature activation+3.354
time
Token time
Feature activation+2.615
live
Token live
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.580
next
Token next
Feature activation+3.257
day
Token day
Feature activation+1.011
,
Token,
Feature activation+0.264
the
Token the
Feature activation+0.000
bureau
Token bureau
Feature activation+0.000
named
Token named
Feature activation+0.000
this
Token this
Feature activation+0.000
project
Token project
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.634
beginning
Token beginning
Feature activation+3.247
was
Token was
Feature activation+0.242
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
an
Token an
Feature activation+0.000
exp
Token exp
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Travis
Token Travis
Feature activation+0.000
purchased
Token purchased
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
first
Token first
Feature activation+3.186
certificate
Token certificate
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Spart
Token Spart
Feature activation+0.000
a
Tokena
Feature activation+0.000
the
Token the
Feature activation+0.000
cross
Token cross
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.939
entrance
Token entrance
Feature activation+3.089
to
Token to
Feature activation+0.140
an
Token an
Feature activation+0.000
African
Token African
Feature activation+0.000
-
Token-
Feature activation+0.000
American
TokenAmerican
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
owned
Token owned
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.043
wealthy
Token wealthy
Feature activation+3.082
get
Token get
Feature activation+0.000
government
Token government
Feature activation+0.000
subsidies
Token subsidies
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
that
Token that
Feature activation+0.000
reputation
Token reputation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.643
court
Token court
Feature activation+3.053
filings
Token filings
Feature activation+0.603
,
Token,
Feature activation+0.461
that
Token that
Feature activation+0.000
says
Token says
Feature activation+0.000
something
Token something
Feature activation+0.000
/
Token/
Feature activation+0.000
11
Token11
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.637
end
Token end
Feature activation+3.021
of
Token of
Feature activation+0.760
Remember
Token Remember
Feature activation+0.000
Me
Token Me
Feature activation+0.000
and
Token and
Feature activation+0.000
all
Token all
Feature activation+0.000
deep
Token deep
Feature activation+0.000
crack
Token crack
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.034
foundation
Token foundation
Feature activation+3.007
of
Token of
Feature activation+2.775
the
Token the
Feature activation+1.444
faith
Token faith
Feature activation+1.300
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
es
Tokenes
Feature activation+0.000
you
Token you
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.658
first
Token first
Feature activation+2.938
bargain
Token bargain
Feature activation+0.000
you
Token you
Feature activation+0.277
see
Token see
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
that
Token that
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.598
last
Token last
Feature activation+2.914
moment
Token moment
Feature activation+1.520
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.000
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
that
Token that
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.018
moment
Token moment
Feature activation+2.878
the
Token the
Feature activation+0.201
coin
Token coin
Feature activation+0.000
rang
Token rang
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
zig
Tokenzig
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.097
first
Token first
Feature activation+2.801
time
Token time
Feature activation+1.979
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
crack
Token crack
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.034
foundation
Token foundation
Feature activation+3.007
of
Token of
Feature activation+2.775
the
Token the
Feature activation+1.444
faith
Token faith
Feature activation+1.300
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
central
Token central
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.400
foundation
Token foundation
Feature activation+2.732
of
Token of
Feature activation+2.442
the
Token the
Feature activation+1.371
beliefs
Token beliefs
Feature activation+0.690
.
Token.
Feature activation+0.000
Especially
Token Especially
Feature activation+0.000
to
Token to
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
very
Token very
Feature activation+0.910
same
Token same
Feature activation+2.670
Lockheed
Token Lockheed
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
given
Token given
Feature activation+0.000
charge
Token charge
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.713
best
Token best
Feature activation+2.668
I
Token I
Feature activation+0.993
UD
TokenUD
Feature activation+0.000
s
Tokens
Feature activation+0.396
and
Token and
Feature activation+0.000
implants
Token implants
Feature activation+0.000

Top DFA by src position
MAX = 4.703

***
Token***
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
From
TokenFrom
Feature activation-0.169
Top resid features:
the
Token the
Feature activation-0.056
Top resid features:
very
Token very
Feature activation+4.703
Top resid features:
first
Token first
Feature activation-0.062
Top resid features:
drive
Token drive
Feature activation+0.000
Top resid features:
Sunday
Token Sunday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Belichick
Token Belichick
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation-0.003
Top resid features:
ahead
Token ahead
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation-0.046
Top resid features:
The
TokenThe
Feature activation-0.078
Top resid features:
very
Token very
Feature activation+4.322
Top resid features:
first
Token first
Feature activation-0.092
Top resid features:
scene
Token scene
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
H
Token H
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
In
TokenIn
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.121
Top resid features:
very
Token very
Feature activation+4.119
Top resid features:
first
Token first
Feature activation-0.073
Top resid features:
image
Token image
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
release
Token release
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.019
Top resid features:
new
Token new
Feature activation-0.031
Top resid features:
songs
Token songs
Feature activation-0.061
Top resid features:
for
Token for
Feature activation-0.178
Top resid features:
the
Token the
Feature activation-0.086
Top resid features:
very
Token very
Feature activation+4.173
Top resid features:
first
Token first
Feature activation-0.019
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
live
Token live
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
defense
Token defense
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
"
Token "
Feature activation-0.018
Top resid features:
And
TokenAnd
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.136
Top resid features:
very
Token very
Feature activation+4.146
Top resid features:
next
Token next
Feature activation-0.107
Top resid features:
day
Token day
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:
bureau
Token bureau
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.006
Top resid features:
this
Token this
Feature activation-0.006
Top resid features:
project
Token project
Feature activation-0.064
Top resid features:
from
Token from
Feature activation-0.039
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
very
Token very
Feature activation+3.853
Top resid features:
beginning
Token beginning
Feature activation+0.015
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.006
Top resid features:
Mark
Token Mark
Feature activation+0.002
Top resid features:
Travis
Token Travis
Feature activation-0.003
Top resid features:
purchased
Token purchased
Feature activation-0.117
Top resid features:
the
Token the
Feature activation-0.116
Top resid features:
very
Token very
Feature activation+4.201
Top resid features:
first
Token first
Feature activation-0.111
Top resid features:
certificate
Token certificate
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Spart
Token Spart
Feature activation+0.000
Top resid features:
burn
Token burn
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
cross
Token cross
Feature activation-0.225
Top resid features:
at
Token at
Feature activation+0.207
Top resid features:
the
Token the
Feature activation-0.125
Top resid features:
very
Token very
Feature activation+3.837
Top resid features:
entrance
Token entrance
Feature activation-0.067
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
African
Token African
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Corpor
Token Corpor
Feature activation-0.012
Top resid features:
ations
Tokenations
Feature activation-0.024
Top resid features:
owned
Token owned
Feature activation-0.011
Top resid features:
by
Token by
Feature activation-0.089
Top resid features:
the
Token the
Feature activation-0.039
Top resid features:
very
Token very
Feature activation+3.863
Top resid features:
wealthy
Token wealthy
Feature activation-0.143
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
subsidies
Token subsidies
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ates
Tokenates
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.039
Top resid features:
reputation
Token reputation
Feature activation-0.026
Top resid features:
in
Token in
Feature activation-0.055
Top resid features:
the
Token the
Feature activation-0.098
Top resid features:
very
Token very
Feature activation+3.865
Top resid features:
court
Token court
Feature activation-0.143
Top resid features:
filings
Token filings
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
9
Token 9
Feature activation+0.003
Top resid features:
/
Token/
Feature activation-0.017
Top resid features:
11
Token11
Feature activation-0.027
Top resid features:
at
Token at
Feature activation+0.070
Top resid features:
the
Token the
Feature activation-0.139
Top resid features:
very
Token very
Feature activation+3.666
Top resid features:
end
Token end
Feature activation-0.045
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Remember
Token Remember
Feature activation+0.000
Top resid features:
Me
Token Me
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.063
Top resid features:
deep
Token deep
Feature activation-0.074
Top resid features:
crack
Token crack
Feature activation-0.154
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
very
Token very
Feature activation+3.889
Top resid features:
foundation
Token foundation
Feature activation-0.066
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
faith
Token faith
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
impress
Token impress
Feature activation+0.000
Top resid features:
es
Tokenes
Feature activation-0.007
Top resid features:
you
Token you
Feature activation-0.009
Top resid features:
with
Token with
Feature activation-0.102
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
very
Token very
Feature activation+3.726
Top resid features:
first
Token first
Feature activation-0.087
Top resid features:
bargain
Token bargain
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.014
Top resid features:
reporting
Token reporting
Feature activation-0.014
Top resid features:
that
Token that
Feature activation+0.023
Top resid features:
at
Token at
Feature activation-0.024
Top resid features:
the
Token the
Feature activation-0.166
Top resid features:
very
Token very
Feature activation+3.632
Top resid features:
last
Token last
Feature activation+0.007
Top resid features:
moment
Token moment
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
seems
Token seems
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.001
Top resid features:
claimed
Token claimed
Feature activation-0.060
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
in
Token in
Feature activation-0.080
Top resid features:
the
Token the
Feature activation-0.093
Top resid features:
very
Token very
Feature activation+3.695
Top resid features:
moment
Token moment
Feature activation-0.051
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
coin
Token coin
Feature activation+0.000
Top resid features:
rang
Token rang
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Le
Token Le
Feature activation-0.039
Top resid features:
ip
Tokenip
Feature activation+0.009
Top resid features:
zig
Tokenzig
Feature activation-0.017
Top resid features:
for
Token for
Feature activation-0.319
Top resid features:
the
Token the
Feature activation-0.094
Top resid features:
very
Token very
Feature activation+3.900
Top resid features:
first
Token first
Feature activation-0.089
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.020
Top resid features:
deep
Token deep
Feature activation-0.026
Top resid features:
crack
Token crack
Feature activation-0.034
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
very
Token very
Feature activation+3.631
Top resid features:
foundation
Token foundation
Feature activation-0.257
Top resid features:
of
Token of
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
faith
Token faith
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
cases
Token cases
Feature activation-0.019
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
central
Token central
Feature activation-0.042
Top resid features:
to
Token to
Feature activation-0.171
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
very
Token very
Feature activation+3.459
Top resid features:
foundation
Token foundation
Feature activation-0.020
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
beliefs
Token beliefs
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Martin
Token Martin
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
Israel
Token Israel
Feature activation-0.021
Top resid features:
.
Token.
Feature activation-0.134
Top resid features:
The
Token The
Feature activation-0.108
Top resid features:
very
Token very
Feature activation+3.257
Top resid features:
same
Token same
Feature activation+0.062
Top resid features:
Lockheed
Token Lockheed
Feature activation+0.000
Top resid features:
Martin
Token Martin
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
charge
Token charge
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
including
Token including
Feature activation-0.072
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
very
Token very
Feature activation+3.313
Top resid features:
best
Token best
Feature activation-0.033
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
UD
TokenUD
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.05

Head 3: 0.10

Head 4: 0.02

Head 5: 0.03

Head 6: 0.42

Head 7: 0.08

Head 8: 0.07

Head 9: 0.03

Head 10: 0.05

Head 11: 0.10

Positive logits

sheets1.14

ones1.14

mega1.10

Hack1.08

Thing1.07

Wid1.04

}}}1.01

majorities1.01

fractions1.00

thing1.00

docs0.98

0.97

installer0.97

IRC0.96

parted0.96

Odin0.96

Forbidden0.95

Liberation0.95

Beast0.94

forums0.93

Negative logits

poke-1.36

etta-1.32

artney-1.26

ctica-1.25

isively-1.24

orously-1.24

roximately-1.24

axter-1.17

eat-1.14

enture-1.14

entimes-1.13

cens-1.12

oche-1.11

ationally-1.10

aina-1.10

elope-1.10

angelo-1.10

lie-1.09

TPPStreamerBot-1.08

ando-1.08

INTERVAL 3.440 - 3.822
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.626
first
Token first
Feature activation+3.822
drive
Token drive
Feature activation+0.062
Sunday
Token Sunday
Feature activation+0.000
,
Token,
Feature activation+0.000
Belichick
Token Belichick
Feature activation+0.000
and
Token and
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
very
Token very
Feature activation+0.664
first
Token first
Feature activation+3.500
scene
Token scene
Feature activation+0.380
,
Token,
Feature activation+0.282
with
Token with
Feature activation+0.000
H
Token H
Feature activation+0.000
ux
Tokenux
Feature activation+0.000

INTERVAL 3.058 - 3.440
CONTAINS 0.001%

new
Token new
Feature activation+0.000
songs
Token songs
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.154
first
Token first
Feature activation+3.354
time
Token time
Feature activation+2.615
live
Token live
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
owned
Token owned
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.043
wealthy
Token wealthy
Feature activation+3.082
get
Token get
Feature activation+0.000
government
Token government
Feature activation+0.000
subsidies
Token subsidies
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.580
next
Token next
Feature activation+3.257
day
Token day
Feature activation+1.011
,
Token,
Feature activation+0.264
the
Token the
Feature activation+0.000
bureau
Token bureau
Feature activation+0.000
named
Token named
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Travis
Token Travis
Feature activation+0.000
purchased
Token purchased
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
first
Token first
Feature activation+3.186
certificate
Token certificate
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Spart
Token Spart
Feature activation+0.000
a
Tokena
Feature activation+0.000
the
Token the
Feature activation+0.000
cross
Token cross
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.939
entrance
Token entrance
Feature activation+3.089
to
Token to
Feature activation+0.140
an
Token an
Feature activation+0.000
African
Token African
Feature activation+0.000
-
Token-
Feature activation+0.000
American
TokenAmerican
Feature activation+0.000

INTERVAL 2.675 - 3.058
CONTAINS 0.001%

crack
Token crack
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.034
foundation
Token foundation
Feature activation+3.007
of
Token of
Feature activation+2.775
the
Token the
Feature activation+1.444
faith
Token faith
Feature activation+1.300
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
reputation
Token reputation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.643
court
Token court
Feature activation+3.053
filings
Token filings
Feature activation+0.603
,
Token,
Feature activation+0.461
that
Token that
Feature activation+0.000
says
Token says
Feature activation+0.000
something
Token something
Feature activation+0.000
deep
Token deep
Feature activation+0.000
crack
Token crack
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.034
foundation
Token foundation
Feature activation+3.007
of
Token of
Feature activation+2.775
the
Token the
Feature activation+1.444
faith
Token faith
Feature activation+1.300
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
zig
Tokenzig
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.097
first
Token first
Feature activation+2.801
time
Token time
Feature activation+1.979
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
that
Token that
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.598
last
Token last
Feature activation+2.914
moment
Token moment
Feature activation+1.520
it
Token it
Feature activation+0.000
seems
Token seems
Feature activation+0.000
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+0.000

INTERVAL 2.293 - 2.675
CONTAINS 0.002%

late
Token late
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.923
existence
Token existence
Feature activation+2.167
of
Token of
Feature activation+2.313
our
Token our
Feature activation+1.107
Republic
Token Republic
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
stake
Token stake
Feature activation+0.000
"
Token "
Feature activation+0.000
Because
TokenBecause
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.195
high
Token high
Feature activation+2.316
price
Token price
Feature activation+0.060
of
Token of
Feature activation+0.501
child
Token child
Feature activation+0.000
-
Token-
Feature activation+0.000
re
Tokenre
Feature activation+0.000
take
Token take
Feature activation+0.000
her
Token her
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.701
heart
Token heart
Feature activation+2.481
of
Token of
Feature activation+1.728
darkness
Token darkness
Feature activation+0.515
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
before
Token before
Feature activation+0.000
psychiatric
Token psychiatric
Feature activation+0.000
help
Token help
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.229
nature
Token nature
Feature activation+2.587
of
Token of
Feature activation+1.974
their
Token their
Feature activation+0.128
disorder
Token disorder
Feature activation+0.779
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Industries
Token Industries
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.095
first
Token first
Feature activation+2.657
private
Token private
Feature activation+0.000
sector
Token sector
Feature activation+0.000
small
Token small
Feature activation+0.000
arms
Token arms
Feature activation+0.000
factory
Token factory
Feature activation+0.000

INTERVAL 1.911 - 2.293
CONTAINS 0.002%

help
Token help
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.229
nature
Token nature
Feature activation+2.587
of
Token of
Feature activation+1.974
their
Token their
Feature activation+0.128
disorder
Token disorder
Feature activation+0.779
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
more
Token more
Feature activation+0.000
trend
Token trend
Feature activation+0.000
share
Token share
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.107
popular
Token popular
Feature activation+2.261
Ubuntu
Token Ubuntu
Feature activation+0.553
Unity
Token Unity
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Expand
Token Expand
Feature activation+0.000
by
Token by
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
very
Token very
Feature activation+0.385
moral
Token moral
Feature activation+2.247
fabric
Token fabric
Feature activation+0.969
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
electoral
Token electoral
Feature activation+0.000
process
Token process
Feature activation+0.000
;
Token;
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.718
process
Token process
Feature activation+2.009
that
Token that
Feature activation+1.478
actually
Token actually
Feature activation+0.000
made
Token made
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
the
Token the
Feature activation+0.000
opposing
Token opposing
Feature activation+0.000
taxation
Token taxation
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
very
Token very
Feature activation+0.380
wealthy
Token wealthy
Feature activation+2.276
control
Token control
Feature activation+0.000
enough
Token enough
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000

INTERVAL 1.529 - 1.911
CONTAINS 0.002%

and
Token and
Feature activation+0.000
le
Token le
Feature activation+0.000
appear
Token appear
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.546
top
Token top
Feature activation+2.655
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
words
Token words
Feature activation+0.000
like
Token like
Feature activation+0.000
problems
Token problems
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
very
Token very
Feature activation+0.385
day
Token day
Feature activation+1.534
,
Token,
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000
liked
Token liked
Feature activation+0.000
Mole
Token Mole
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.951
people
Token people
Feature activation+2.532
whose
Token whose
Feature activation+1.771
cooperation
Token cooperation
Feature activation+0.000
is
Token is
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
my
Token my
Feature activation+0.000
opic
Tokenopic
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.775
least
Token least
Feature activation+2.338
,
Token,
Feature activation+0.061
it
Token it
Feature activation+0.000
felt
Token felt
Feature activation+0.000
as
Token as
Feature activation+0.000
her
Token her
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.701
heart
Token heart
Feature activation+2.481
of
Token of
Feature activation+1.728
darkness
Token darkness
Feature activation+0.515
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
before
Token before
Feature activation+0.000
she
Token she
Feature activation+0.000

INTERVAL 1.147 - 1.529
CONTAINS 0.003%

âĢĵ
Token âĢĵ
Feature activation+0.000
is
Token is
Feature activation+0.000
why
Token why
Feature activation+0.000
these
Token these
Feature activation+0.000
very
Token very
Feature activation+0.000
likely
Token likely
Feature activation+1.494
conting
Token conting
Feature activation+0.000
encies
Tokenencies
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
fact
Token fact
Feature activation+0.000
ime
Tokenime
Feature activation+0.000
Change
Token Change
Feature activation+0.000
outlined
Token outlined
Feature activation+0.000
this
Token this
Feature activation+0.000
very
Token very
Feature activation+0.094
scenario
Token scenario
Feature activation+1.277
âĢĵ
Token âĢĵ
Feature activation+0.309
where
Token where
Feature activation+0.121
a
Token a
Feature activation+0.000
manufactured
Token manufactured
Feature activation+0.000
humanitarian
Token humanitarian
Feature activation+0.000
seek
Token seek
Feature activation+0.000
psychiatric
Token psychiatric
Feature activation+0.000
help
Token help
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.229
nature
Token nature
Feature activation+2.587
of
Token of
Feature activation+1.974
their
Token their
Feature activation+0.128
disorder
Token disorder
Feature activation+0.779
.
Token.
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
with
Token with
Feature activation+0.000
achieving
Token achieving
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.848
protections
Token protections
Feature activation+1.440
for
Token for
Feature activation+0.625
those
Token those
Feature activation+0.200
with
Token with
Feature activation+0.000
pree
Token pree
Feature activation+0.000
x
Tokenx
Feature activation+0.000
it
Token it
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
extremely
Token extremely
Feature activation+0.475
courageous
Token courageous
Feature activation+1.498
actions
Token actions
Feature activation+0.320
of
Token of
Feature activation+0.589
ex
Token ex
Feature activation+0.000
-
Token-
Feature activation+0.000
serv
Tokenserv
Feature activation+0.000

INTERVAL 0.764 - 1.147
CONTAINS 0.004%

He
Token He
Feature activation+0.000
claimed
Token claimed
Feature activation+0.000
that
Token that
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.018
moment
Token moment
Feature activation+2.878
the
Token the
Feature activation+0.201
coin
Token coin
Feature activation+0.000
rang
Token rang
Feature activation+0.000
in
Token in
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
with
Token with
Feature activation+0.000
achieving
Token achieving
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.848
protections
Token protections
Feature activation+1.440
for
Token for
Feature activation+0.625
those
Token those
Feature activation+0.200
with
Token with
Feature activation+0.000
pree
Token pree
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
very
Token very
Feature activation+0.675
experiences
Token experiences
Feature activation+2.393
we
Token we
Feature activation+1.014
fear
Token fear
Feature activation+0.000
keep
Token keep
Feature activation+0.000
repeating
Token repeating
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
if
Token if
Feature activation+0.000
is
Token is
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.058
âĢ
Token âĢ
Feature activation+0.902
ľ
Tokenľ
Feature activation+1.168
pattern
Tokenpattern
Feature activation+0.400
of
Token of
Feature activation+1.156
life
Token life
Feature activation+0.080
"
Token "
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.580
next
Token next
Feature activation+3.257
day
Token day
Feature activation+1.011
,
Token,
Feature activation+0.264
the
Token the
Feature activation+0.000
bureau
Token bureau
Feature activation+0.000
named
Token named
Feature activation+0.000
Bruce
Token Bruce
Feature activation+0.000

INTERVAL 0.382 - 0.764
CONTAINS 0.010%

with
Token with
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
very
Token very
Feature activation+0.000
difficult
Token difficult
Feature activation+0.609
time
Token time
Feature activation+0.835
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Topics
TokenTopics
Feature activation+0.000
of
Token of
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
it
Token it
Feature activation+0.000
felt
Token felt
Feature activation+0.000
very
Token very
Feature activation+0.000
much
Token much
Feature activation+0.499
like
Token like
Feature activation+0.000
a
Token a
Feature activation+0.000
coming
Token coming
Feature activation+0.000
together
Token together
Feature activation+0.000
of
Token of
Feature activation+0.000
of
Token of
Feature activation+0.000
land
Token land
Feature activation+0.000
in
Token in
Feature activation+0.000
very
Token very
Feature activation+0.160
remote
Token remote
Feature activation+1.332
spaces
Token spaces
Feature activation+0.625
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
monitor
Token monitor
Feature activation+0.000
the
Token the
Feature activation+0.000
very
Token very
Feature activation+1.058
âĢ
Token âĢ
Feature activation+0.902
ľ
Tokenľ
Feature activation+1.168
pattern
Tokenpattern
Feature activation+0.400
of
Token of
Feature activation+1.156
life
Token life
Feature activation+0.080
,
Token,
Feature activation+0.024
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
hold
Token hold
Feature activation+0.000
rates
Token rates
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
low
Token low
Feature activation+0.622
levels
Token levels
Feature activation+0.692
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.382
CONTAINS 99.975%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
availability
Token availability
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
security
Token security
Feature activation+0.000
section
Token section
Feature activation+0.000
will
Token will
Feature activation+0.000
show
Token show
Feature activation+0.000
assigned
Token assigned
Feature activation+0.000
CVE
Token CVE
Feature activation+0.000
simultaneously
Token simultaneously
Feature activation+0.000
sync
Token sync
Feature activation+0.000
up
Token up
Feature activation+0.000
your
Token your
Feature activation+0.000
work
Token work
Feature activation+0.000
with
Token with
Feature activation+0.000
others
Token others
Feature activation+0.000
to
Token to
Feature activation+0.000
flesh
Token flesh
Feature activation+0.000
out
Token out
Feature activation+0.000
ideas
Token ideas
Feature activation+0.000
Mul
Token Mul
Feature activation+0.000
v
Tokenv
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
intermediary
Token intermediary
Feature activation+0.000
to
Token to
Feature activation+0.000
threaten
Token threaten
Feature activation+0.000
to
Token to
Feature activation+0.000
oust
Token oust
Feature activation+0.000
Sanford
Token Sanford
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
,
Token,
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
and
Token and
Feature activation+0.000
articles
Token articles
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
as
Token as
Feature activation+0.000
colour
Token colour
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
for
Token for
Feature activation+0.000
reports
Token reports
Feature activation+0.000
that
Token that
Feature activation+0.000
arose
Token arose
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
adoption
Token adoption
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
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