H11.4 top features

Top feature 0 in H11.4: (feature 23859)

TOP ACTIVATIONS
MAX = 14.359

,
Token,
Feature activation+5.220
The
Token The
Feature activation+2.217
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
on
Token on
Feature activation+2.241
Thursday
Token Thursday
Feature activation+8.023
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
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
watchdog
Token watchdog
Feature activation+3.131
said
Token said
Feature activation+14.081
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.304
total
Token total
Feature activation+0.486
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
sanctions
Token sanctions
Feature activation+2.436
monitors
Token monitors
Feature activation+3.120
said
Token said
Feature activation+14.003
in
Token in
Feature activation+0.575
a
Token a
Feature activation+0.971
new
Token new
Feature activation+1.031
report
Token report
Feature activation+4.322
.
Token.
Feature activation+0.000
consultancy
Token consultancy
Feature activation+0.000
firm
Token firm
Feature activation+0.000
Wood
Token Wood
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
enzie
Tokenenzie
Feature activation+5.287
said
Token said
Feature activation+12.998
on
Token on
Feature activation+0.939
Monday
Token Monday
Feature activation+3.994
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
systems
Token systems
Feature activation+0.752
hit
Token hit
Feature activation+1.506
$
Token $
Feature activation+0.000
840
Token840
Feature activation+4.609
million
Token million
Feature activation+12.519
in
Token in
Feature activation+0.823
March
Token March
Feature activation+0.904
,
Token,
Feature activation+1.364
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
Road
Token Road
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
she
Token she
Feature activation+2.518
attacked
Token attacked
Feature activation+6.005
the
Token the
Feature activation+2.145
presidential
Token presidential
Feature activation+0.000
palace
Token palace
Feature activation+5.040
in
Token in
Feature activation+0.272
Aden
Token Aden
Feature activation+11.517
on
Token on
Feature activation+1.720
Thursday
Token Thursday
Feature activation+5.389
after
Token after
Feature activation+0.923
rival
Token rival
Feature activation+0.645
forces
Token forces
Feature activation+1.192
in
Token in
Feature activation+0.300
California
Token California
Feature activation+3.206
under
Token under
Feature activation+0.557
a
Token a
Feature activation+0.719
bill
Token bill
Feature activation+3.907
passed
Token passed
Feature activation+10.514
on
Token on
Feature activation+0.737
Wednesday
Token Wednesday
Feature activation+3.367
by
Token by
Feature activation+0.638
a
Token a
Feature activation+0.000
committee
Token committee
Feature activation+2.984
,
Token,
Feature activation+3.838
an
Token an
Feature activation+1.559
official
Token official
Feature activation+3.924
and
Token and
Feature activation+2.525
residents
Token residents
Feature activation+3.911
said
Token said
Feature activation+10.167
,
Token,
Feature activation+3.909
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.405
sharp
Token sharp
Feature activation+0.206
escalation
Token escalation
Feature activation+0.906
N
TokenN
Feature activation+0.000
225
Token225
Feature activation+0.309
dropped
Token dropped
Feature activation+0.582
1
Token 1
Feature activation+4.598
.
Token.
Feature activation+0.000
9
Token9
Feature activation+9.628
percent
Token percent
Feature activation+0.617
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
s
Tokens
Feature activation+0.000
defense
Token defense
Feature activation+0.000
secretary
Token secretary
Feature activation+0.183
warned
Token warned
Feature activation+5.616
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+9.564
on
Token on
Feature activation+0.119
Friday
Token Friday
Feature activation+1.749
of
Token of
Feature activation+0.624
an
Token an
Feature activation+0.579
âĢ
Token âĢ
Feature activation+0.000
-
Token-
Feature activation+1.794
week
Tokenweek
Feature activation+0.000
high
Token high
Feature activation+8.640
against
Token against
Feature activation+0.000
the
Token the
Feature activation+6.810
dollar
Token dollar
Feature activation+9.540
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.613
Asian
Token Asian
Feature activation+0.000
trading
Token trading
Feature activation+2.511
on
Token on
Feature activation+0.132
it
Token it
Feature activation+3.635
chose
Token chose
Feature activation+1.945
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
weapons
Token weapons
Feature activation+8.904
,
Token,
Feature activation+5.853
as
Token as
Feature activation+1.851
he
Token he
Feature activation+0.598
reassured
Token reassured
Feature activation+1.145
South
Token South
Feature activation+0.000
to
Token to
Feature activation+0.834
a
Token a
Feature activation+0.516
seven
Token seven
Feature activation+5.331
-
Token-
Feature activation+1.794
week
Tokenweek
Feature activation+0.000
high
Token high
Feature activation+8.640
against
Token against
Feature activation+0.000
the
Token the
Feature activation+6.810
dollar
Token dollar
Feature activation+9.540
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.613
Silk
Token Silk
Feature activation+0.000
Road
Token Road
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
on
Token on
Feature activation+2.241
Thursday
Token Thursday
Feature activation+8.023
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
iting
Tokeniting
Feature activation+1.620
charge
Token charge
Feature activation+1.082
,
Token,
Feature activation+5.220
The
Token The
Feature activation+2.217
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
on
Token on
Feature activation+2.241
Thursday
Token Thursday
Feature activation+8.023
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
she
Token she
Feature activation+2.518
would
Token would
Feature activation+0.000
seven
Token seven
Feature activation+5.331
-
Token-
Feature activation+1.794
week
Tokenweek
Feature activation+0.000
high
Token high
Feature activation+8.640
against
Token against
Feature activation+0.000
the
Token the
Feature activation+6.810
dollar
Token dollar
Feature activation+9.540
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.613
Asian
Token Asian
Feature activation+0.000
trading
Token trading
Feature activation+2.511
Coal
Token Coal
Feature activation+0.000
will
Token will
Feature activation+0.000
surpass
Token surpass
Feature activation+0.000
oil
Token oil
Feature activation+2.298
as
Token as
Feature activation+2.566
the
Token the
Feature activation+6.705
key
Token key
Feature activation+0.651
fuel
Token fuel
Feature activation+1.001
for
Token for
Feature activation+1.549
the
Token the
Feature activation+2.379
global
Token global
Feature activation+0.000

Top DFA by src position
MAX = 15.245

.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.015
Top resid features:
WASHINGTON
TokenWASHINGTON
Feature activation-0.002
Top resid features:
(
Token (
Feature activation+0.018
Top resid features:
Reuters
TokenReuters
Feature activation-0.089
Top resid features:
)
Token)
Feature activation+15.245
Top resid features:
-
Token -
Feature activation+0.173
Top resid features:
The
Token The
Feature activation-0.003
Top resid features:
United
Token United
Feature activation-0.001
Top resid features:
States
Token States
Feature activation+0.009
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
war
Tokenwar
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.011
Top resid features:
WASHINGTON
TokenWASHINGTON
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+0.024
Top resid features:
Reuters
TokenReuters
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+14.689
Top resid features:
-
Token -
Feature activation+0.244
Top resid features:
Ten
Token Ten
Feature activation+0.008
Top resid features:
months
Token months
Feature activation+0.001
Top resid features:
after
Token after
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
ITED
TokenITED
Feature activation-0.002
Top resid features:
N
Token N
Feature activation-0.000
Top resid features:
ATIONS
TokenATIONS
Feature activation-0.003
Top resid features:
(
Token (
Feature activation+0.013
Top resid features:
Reuters
TokenReuters
Feature activation-0.007
Top resid features:
)
Token)
Feature activation+14.960
Top resid features:
-
Token -
Feature activation+0.196
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
Taliban
Token Taliban
Feature activation+0.025
Top resid features:
âĢ
TokenâĢ
Feature activation-0.049
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Oct
Token Oct
Feature activation-0.051
Top resid features:
14
Token 14
Feature activation+0.030
Top resid features:
(
Token (
Feature activation-0.001
Top resid features:
Reuters
TokenReuters
Feature activation-0.021
Top resid features:
)
Token)
Feature activation+14.304
Top resid features:
-
Token -
Feature activation+0.091
Top resid features:
Coal
Token Coal
Feature activation-0.003
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
surpass
Token surpass
Feature activation-0.003
Top resid features:
oil
Token oil
Feature activation+0.008
Top resid features:
war
Tokenwar
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
WASHINGTON
TokenWASHINGTON
Feature activation+0.012
Top resid features:
(
Token (
Feature activation+0.009
Top resid features:
Reuters
TokenReuters
Feature activation+0.017
Top resid features:
)
Token)
Feature activation+13.963
Top resid features:
-
Token -
Feature activation+0.130
Top resid features:
Ten
Token Ten
Feature activation+0.010
Top resid features:
months
Token months
Feature activation+0.008
Top resid features:
after
Token after
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
L
TokenL
Feature activation+0.003
Top resid features:
ONDON
TokenONDON
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+0.021
Top resid features:
Reuters
TokenReuters
Feature activation+0.025
Top resid features:
)
Token)
Feature activation+12.895
Top resid features:
-
Token -
Feature activation+0.161
Top resid features:
China
Token China
Feature activation+0.003
Top resid features:
has
Token has
Feature activation+0.006
Top resid features:
invited
Token invited
Feature activation+0.018
Top resid features:
British
Token British
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.004
Top resid features:
AD
TokenAD
Feature activation+0.006
Top resid features:
EN
TokenEN
Feature activation+0.011
Top resid features:
(
Token (
Feature activation+0.031
Top resid features:
Reuters
TokenReuters
Feature activation+0.009
Top resid features:
)
Token)
Feature activation+11.677
Top resid features:
-
Token -
Feature activation+0.505
Top resid features:
An
Token An
Feature activation+0.002
Top resid features:
unidentified
Token unidentified
Feature activation+0.009
Top resid features:
war
Token war
Feature activation+0.002
Top resid features:
plane
Tokenplane
Feature activation+0.149
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
Calif
Token Calif
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
(
Token (
Feature activation+0.025
Top resid features:
Reuters
TokenReuters
Feature activation+0.068
Top resid features:
)
Token)
Feature activation+11.096
Top resid features:
-
Token -
Feature activation+0.323
Top resid features:
Phys
Token Phys
Feature activation-0.006
Top resid features:
ician
Tokenician
Feature activation-0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
assisted
Tokenassisted
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.045
Top resid features:
AD
TokenAD
Feature activation+0.003
Top resid features:
EN
TokenEN
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.007
Top resid features:
Reuters
TokenReuters
Feature activation-0.012
Top resid features:
)
Token)
Feature activation+10.541
Top resid features:
-
Token -
Feature activation+0.315
Top resid features:
An
Token An
Feature activation-0.008
Top resid features:
unidentified
Token unidentified
Feature activation-0.002
Top resid features:
war
Token war
Feature activation+0.000
Top resid features:
plane
Tokenplane
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.600
Top resid features:
O
TokenO
Feature activation+0.001
Top resid features:
(
Token (
Feature activation-0.012
Top resid features:
Reuters
TokenReuters
Feature activation-0.011
Top resid features:
)
Token)
Feature activation+11.139
Top resid features:
-
Token -
Feature activation+0.063
Top resid features:
The
Token The
Feature activation-0.000
Top resid features:
yen
Token yen
Feature activation-0.030
Top resid features:
rocket
Token rocket
Feature activation-0.001
Top resid features:
ed
Tokened
Feature activation+0.008
Top resid features:
SE
TokenSE
Feature activation-0.008
Top resid features:
OU
TokenOU
Feature activation+0.001
Top resid features:
L
TokenL
Feature activation+0.019
Top resid features:
(
Token (
Feature activation+0.016
Top resid features:
Reuters
TokenReuters
Feature activation-0.005
Top resid features:
)
Token)
Feature activation+10.060
Top resid features:
-
Token -
Feature activation+0.422
Top resid features:
U
Token U
Feature activation-0.017
Top resid features:
.
Token.
Feature activation-0.049
Top resid features:
S
TokenS
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.574
Top resid features:
O
TokenO
Feature activation+0.006
Top resid features:
(
Token (
Feature activation-0.026
Top resid features:
Reuters
TokenReuters
Feature activation-0.050
Top resid features:
)
Token)
Feature activation+10.725
Top resid features:
-
Token -
Feature activation+0.465
Top resid features:
The
Token The
Feature activation-0.013
Top resid features:
yen
Token yen
Feature activation+0.010
Top resid features:
rocket
Token rocket
Feature activation-0.009
Top resid features:
ed
Tokened
Feature activation+0.154
Top resid features:
SE
TokenSE
Feature activation-0.005
Top resid features:
OU
TokenOU
Feature activation-0.001
Top resid features:
L
TokenL
Feature activation+0.011
Top resid features:
(
Token (
Feature activation+0.015
Top resid features:
Reuters
TokenReuters
Feature activation-0.018
Top resid features:
)
Token)
Feature activation+9.372
Top resid features:
-
Token -
Feature activation+0.369
Top resid features:
U
Token U
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
S
TokenS
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.568
Top resid features:
O
TokenO
Feature activation+0.008
Top resid features:
(
Token (
Feature activation-0.042
Top resid features:
Reuters
TokenReuters
Feature activation-0.082
Top resid features:
)
Token)
Feature activation+9.922
Top resid features:
-
Token -
Feature activation+0.340
Top resid features:
The
Token The
Feature activation+0.004
Top resid features:
yen
Token yen
Feature activation+0.032
Top resid features:
rocket
Token rocket
Feature activation+0.069
Top resid features:
ed
Tokened
Feature activation+0.148
Top resid features:
/
Token/
Feature activation-0.017
Top resid features:
L
TokenL
Feature activation+0.041
Top resid features:
ONDON
TokenONDON
Feature activation+0.030
Top resid features:
(
Token (
Feature activation+0.093
Top resid features:
Reuters
TokenReuters
Feature activation+0.257
Top resid features:
)
Token)
Feature activation+8.565
Top resid features:
-
Token -
Feature activation+0.237
Top resid features:
China
Token China
Feature activation-0.019
Top resid features:
has
Token has
Feature activation+0.020
Top resid features:
invited
Token invited
Feature activation+0.017
Top resid features:
British
Token British
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.031
Top resid features:
WASHINGTON
TokenWASHINGTON
Feature activation+0.018
Top resid features:
(
Token (
Feature activation+0.007
Top resid features:
Reuters
TokenReuters
Feature activation-0.132
Top resid features:
)
Token)
Feature activation+8.797
Top resid features:
-
Token -
Feature activation+0.251
Top resid features:
The
Token The
Feature activation-0.003
Top resid features:
United
Token United
Feature activation-0.001
Top resid features:
States
Token States
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.006
Top resid features:
WASHINGTON
TokenWASHINGTON
Feature activation+0.012
Top resid features:
(
Token (
Feature activation+0.046
Top resid features:
Reuters
TokenReuters
Feature activation-0.198
Top resid features:
)
Token)
Feature activation+8.417
Top resid features:
-
Token -
Feature activation+0.275
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
United
Token United
Feature activation+0.000
Top resid features:
States
Token States
Feature activation+0.005
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
/
Token/
Feature activation+0.014
Top resid features:
L
TokenL
Feature activation+0.002
Top resid features:
ONDON
TokenONDON
Feature activation+0.075
Top resid features:
(
Token (
Feature activation+0.029
Top resid features:
Reuters
TokenReuters
Feature activation-0.027
Top resid features:
)
Token)
Feature activation+7.884
Top resid features:
-
Token -
Feature activation+0.257
Top resid features:
China
Token China
Feature activation+0.017
Top resid features:
has
Token has
Feature activation+0.031
Top resid features:
invited
Token invited
Feature activation+0.004
Top resid features:
British
Token British
Feature activation+0.034
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.586
Top resid features:
O
TokenO
Feature activation+0.017
Top resid features:
(
Token (
Feature activation-0.009
Top resid features:
Reuters
TokenReuters
Feature activation-0.083
Top resid features:
)
Token)
Feature activation+8.203
Top resid features:
-
Token -
Feature activation+0.244
Top resid features:
The
Token The
Feature activation+0.054
Top resid features:
yen
Token yen
Feature activation-0.045
Top resid features:
rocket
Token rocket
Feature activation+0.025
Top resid features:
ed
Tokened
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
Oct
Token Oct
Feature activation-0.000
Top resid features:
14
Token 14
Feature activation+0.004
Top resid features:
(
Token (
Feature activation+0.028
Top resid features:
Reuters
TokenReuters
Feature activation-0.022
Top resid features:
)
Token)
Feature activation+7.771
Top resid features:
-
Token -
Feature activation+0.291
Top resid features:
Coal
Token Coal
Feature activation-0.004
Top resid features:
will
Token will
Feature activation+0.094
Top resid features:
surpass
Token surpass
Feature activation+0.058
Top resid features:
oil
Token oil
Feature activation+0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.03

Head 2: 0.03

Head 3: 0.03

Head 4: 0.43

Head 5: 0.02

Head 6: 0.01

Head 7: 0.05

Head 8: 0.20

Head 9: 0.02

Head 10: 0.03

Head 11: 0.05

Positive logits

apeake2.22

rawdownloadcloneembedreportprint2.15

ocl2.08

sylv2.03

asin2.00

ulia1.98

iterranean1.93

venth1.91

Shi1.91

urrection1.89

Centauri1.88

nineteen1.81

deen1.78

batt1.78

pperc1.75

lobe1.74

aurus1.73

outher1.72

fif1.71

ultan1.71

Negative logits

JJ-2.45

JPM-2.43

Interested-2.39

[…]-2.39

…)-2.33

JM-2.32

Dems-2.29

JJ-2.27

('-2.26

…]-2.24

DK-2.24

MSM-2.20

SJ-2.18

ETH-2.18

EW-2.16

🙂-2.13

MS-2.12

EFF-2.12

RH-2.10

AUD-2.08

INTERVAL 12.924 - 14.359
CONTAINS 0.000%

consultancy
Token consultancy
Feature activation+0.000
firm
Token firm
Feature activation+0.000
Wood
Token Wood
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
enzie
Tokenenzie
Feature activation+5.287
said
Token said
Feature activation+12.998
on
Token on
Feature activation+0.939
Monday
Token Monday
Feature activation+3.994
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
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
watchdog
Token watchdog
Feature activation+3.131
said
Token said
Feature activation+14.081
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.304
total
Token total
Feature activation+0.486
,
Token,
Feature activation+5.220
The
Token The
Feature activation+2.217
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
on
Token on
Feature activation+2.241
Thursday
Token Thursday
Feature activation+8.023
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
sanctions
Token sanctions
Feature activation+2.436
monitors
Token monitors
Feature activation+3.120
said
Token said
Feature activation+14.003
in
Token in
Feature activation+0.575
a
Token a
Feature activation+0.971
new
Token new
Feature activation+1.031
report
Token report
Feature activation+4.322
.
Token.
Feature activation+0.000

INTERVAL 11.488 - 12.924
CONTAINS 0.000%

Road
Token Road
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
she
Token she
Feature activation+2.518
supporting
Token supporting
Feature activation+0.000
systems
Token systems
Feature activation+0.752
hit
Token hit
Feature activation+1.506
$
Token $
Feature activation+0.000
840
Token840
Feature activation+4.609
million
Token million
Feature activation+12.519
in
Token in
Feature activation+0.823
March
Token March
Feature activation+0.904
,
Token,
Feature activation+1.364
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
attacked
Token attacked
Feature activation+6.005
the
Token the
Feature activation+2.145
presidential
Token presidential
Feature activation+0.000
palace
Token palace
Feature activation+5.040
in
Token in
Feature activation+0.272
Aden
Token Aden
Feature activation+11.517
on
Token on
Feature activation+1.720
Thursday
Token Thursday
Feature activation+5.389
after
Token after
Feature activation+0.923
rival
Token rival
Feature activation+0.645
forces
Token forces
Feature activation+1.192

INTERVAL 10.052 - 11.488
CONTAINS 0.000%

,
Token,
Feature activation+3.838
an
Token an
Feature activation+1.559
official
Token official
Feature activation+3.924
and
Token and
Feature activation+2.525
residents
Token residents
Feature activation+3.911
said
Token said
Feature activation+10.167
,
Token,
Feature activation+3.909
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.405
sharp
Token sharp
Feature activation+0.206
escalation
Token escalation
Feature activation+0.906
in
Token in
Feature activation+0.300
California
Token California
Feature activation+3.206
under
Token under
Feature activation+0.557
a
Token a
Feature activation+0.719
bill
Token bill
Feature activation+3.907
passed
Token passed
Feature activation+10.514
on
Token on
Feature activation+0.737
Wednesday
Token Wednesday
Feature activation+3.367
by
Token by
Feature activation+0.638
a
Token a
Feature activation+0.000
committee
Token committee
Feature activation+2.984

INTERVAL 8.616 - 10.052
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
defense
Token defense
Feature activation+0.000
secretary
Token secretary
Feature activation+0.183
warned
Token warned
Feature activation+5.616
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+9.564
on
Token on
Feature activation+0.119
Friday
Token Friday
Feature activation+1.749
of
Token of
Feature activation+0.624
an
Token an
Feature activation+0.579
âĢ
Token âĢ
Feature activation+0.000
it
Token it
Feature activation+3.635
chose
Token chose
Feature activation+1.945
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
weapons
Token weapons
Feature activation+8.904
,
Token,
Feature activation+5.853
as
Token as
Feature activation+1.851
he
Token he
Feature activation+0.598
reassured
Token reassured
Feature activation+1.145
South
Token South
Feature activation+0.000
to
Token to
Feature activation+0.834
a
Token a
Feature activation+0.516
seven
Token seven
Feature activation+5.331
-
Token-
Feature activation+1.794
week
Tokenweek
Feature activation+0.000
high
Token high
Feature activation+8.640
against
Token against
Feature activation+0.000
the
Token the
Feature activation+6.810
dollar
Token dollar
Feature activation+9.540
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.613
-
Token-
Feature activation+1.794
week
Tokenweek
Feature activation+0.000
high
Token high
Feature activation+8.640
against
Token against
Feature activation+0.000
the
Token the
Feature activation+6.810
dollar
Token dollar
Feature activation+9.540
in
Token in
Feature activation+0.000
early
Token early
Feature activation+0.613
Asian
Token Asian
Feature activation+0.000
trading
Token trading
Feature activation+2.511
on
Token on
Feature activation+0.132
N
TokenN
Feature activation+0.000
225
Token225
Feature activation+0.309
dropped
Token dropped
Feature activation+0.582
1
Token 1
Feature activation+4.598
.
Token.
Feature activation+0.000
9
Token9
Feature activation+9.628
percent
Token percent
Feature activation+0.617
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 7.180 - 8.616
CONTAINS 0.000%

Silk
Token Silk
Feature activation+0.000
Road
Token Road
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
she
Token she
Feature activation+2.518
would
Token would
Feature activation+0.000
charge
Token charge
Feature activation+1.082
,
Token,
Feature activation+5.220
The
Token The
Feature activation+2.217
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
on
Token on
Feature activation+2.241
Thursday
Token Thursday
Feature activation+8.023
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
on
Token on
Feature activation+2.241
Thursday
Token Thursday
Feature activation+8.023
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
iting
Tokeniting
Feature activation+1.620

INTERVAL 5.744 - 7.180
CONTAINS 0.001%

Coal
Token Coal
Feature activation+0.000
will
Token will
Feature activation+0.000
surpass
Token surpass
Feature activation+0.000
oil
Token oil
Feature activation+2.298
as
Token as
Feature activation+2.566
the
Token the
Feature activation+6.705
key
Token key
Feature activation+0.651
fuel
Token fuel
Feature activation+1.001
for
Token for
Feature activation+1.549
the
Token the
Feature activation+2.379
global
Token global
Feature activation+0.000
for
Token for
Feature activation+1.549
the
Token the
Feature activation+2.379
global
Token global
Feature activation+0.000
economy
Token economy
Feature activation+4.315
by
Token by
Feature activation+0.000
2020
Token 2020
Feature activation+6.109
despite
Token despite
Feature activation+0.655
government
Token government
Feature activation+0.000
efforts
Token efforts
Feature activation+3.118
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.104
s
Tokens
Feature activation+0.000
federal
Token federal
Feature activation+0.000
health
Token health
Feature activation+0.000
insurance
Token insurance
Feature activation+0.279
exchange
Token exchange
Feature activation+6.581
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
dogged
Token dogged
Feature activation+2.121
by
Token by
Feature activation+0.000
cost
Token cost
Feature activation+0.106
Urs
Token Urs
Feature activation+0.000
ula
Tokenula
Feature activation+0.000
von
Token von
Feature activation+0.000
der
Token der
Feature activation+0.000
Ley
Token Ley
Feature activation+0.000
en
Tokenen
Feature activation+6.456
on
Token on
Feature activation+0.266
Sunday
Token Sunday
Feature activation+0.981
rejected
Token rejected
Feature activation+1.363
U
Token U
Feature activation+0.328
.
Token.
Feature activation+0.000
chose
Token chose
Feature activation+1.945
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
weapons
Token weapons
Feature activation+8.904
,
Token,
Feature activation+5.853
as
Token as
Feature activation+1.851
he
Token he
Feature activation+0.598
reassured
Token reassured
Feature activation+1.145
South
Token South
Feature activation+0.000
Korea
Token Korea
Feature activation+2.868

INTERVAL 4.308 - 5.744
CONTAINS 0.003%

of
Token of
Feature activation+0.050
political
Token political
Feature activation+0.000
separatists
Token separatists
Feature activation+1.233
without
Token without
Feature activation+0.000
charge
Token charge
Feature activation+1.082
,
Token,
Feature activation+5.220
The
Token The
Feature activation+2.217
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+7.525
reported
Token reported
Feature activation+14.359
ATIONS
TokenATIONS
Feature activation+0.000
(
Token (
Feature activation+0.000
Reuters
TokenReuters
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
The
Token The
Feature activation+5.413
Taliban
Token Taliban
Feature activation+1.523
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
reliance
Token reliance
Feature activation+0.000
new
Token new
Feature activation+0.671
Silk
Token Silk
Feature activation+0.000
Road
Token Road
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
America
Token America
Feature activation+3.850
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
nation
Token nation
Feature activation+4.466
,
Token,
Feature activation+0.169
thrust
Token thrust
Feature activation+0.000
ing
Tokening
Feature activation+0.000
his
Token his
Feature activation+0.000
center
Token center
Feature activation+0.000
a
Token a
Feature activation+2.225
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.064
report
Token report
Feature activation+3.901
to
Token to
Feature activation+0.643
Congress
Token Congress
Feature activation+4.509
last
Token last
Feature activation+0.934
month
Token month
Feature activation+1.333
,
Token,
Feature activation+1.910
the
Token the
Feature activation+4.826
Times
Token Times
Feature activation+6.197

INTERVAL 2.872 - 4.308
CONTAINS 0.004%

build
Token build
Feature activation+1.110
a
Token a
Feature activation+0.505
new
Token new
Feature activation+0.671
Silk
Token Silk
Feature activation+0.000
Road
Token Road
Feature activation+0.000
,
Token,
Feature activation+3.933
diplomatic
Token diplomatic
Feature activation+1.793
sources
Token sources
Feature activation+5.620
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
house
Token house
Feature activation+3.852
for
Token for
Feature activation+0.000
Latin
Token Latin
Feature activation+0.332
America
Token America
Feature activation+3.850
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
nation
Token nation
Feature activation+4.466
college
Token college
Feature activation+0.000
drop
Token drop
Feature activation+0.000
out
Tokenout
Feature activation+2.748
born
Token born
Feature activation+0.000
in
Token in
Feature activation+0.000
exile
Token exile
Feature activation+3.159
during
Token during
Feature activation+0.225
Brazil
Token Brazil
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Washington
Token Washington
Feature activation+1.855
,
Token,
Feature activation+1.317
D
Token D
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.,
Token.,
Feature activation+2.999
follows
Token follows
Feature activation+0.060
last
Token last
Feature activation+0.734
week
Token week
Feature activation+0.035
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
government
Token government
Feature activation+0.000
efforts
Token efforts
Feature activation+3.118
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
carbon
Token carbon
Feature activation+0.000
emissions
Token emissions
Feature activation+3.598
,
Token,
Feature activation+0.000
energy
Token energy
Feature activation+0.000
consultancy
Token consultancy
Feature activation+0.000
firm
Token firm
Feature activation+0.000
Wood
Token Wood
Feature activation+0.000

INTERVAL 1.436 - 2.872
CONTAINS 0.008%

Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
she
Token she
Feature activation+2.518
would
Token would
Feature activation+0.000
visit
Token visit
Feature activation+0.000
China
Token China
Feature activation+3.296
this
Token this
Feature activation+0.366
year
Token year
Feature activation+0.553
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
months
Token months
Feature activation+0.000
-
Token-
Feature activation+0.000
long
Tokenlong
Feature activation+0.000
conflict
Token conflict
Feature activation+1.892
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ilit
Tokenilit
Feature activation+0.000
told
Token told
Feature activation+8.043
Reuters
Token Reuters
Feature activation+12.042
,
Token,
Feature activation+7.481
as
Token as
Feature activation+0.791
London
Token London
Feature activation+0.953
said
Token said
Feature activation+2.339
she
Token she
Feature activation+2.518
would
Token would
Feature activation+0.000
visit
Token visit
Feature activation+0.000
China
Token China
Feature activation+3.296
this
Token this
Feature activation+0.366
the
Token the
Feature activation+2.145
presidential
Token presidential
Feature activation+0.000
palace
Token palace
Feature activation+5.040
in
Token in
Feature activation+0.272
Aden
Token Aden
Feature activation+11.517
on
Token on
Feature activation+1.720
Thursday
Token Thursday
Feature activation+5.389
after
Token after
Feature activation+0.923
rival
Token rival
Feature activation+0.645
forces
Token forces
Feature activation+1.192
fought
Token fought
Feature activation+1.617
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
An
Token An
Feature activation+1.094
unidentified
Token unidentified
Feature activation+2.313
war
Token war
Feature activation+0.000
plane
Tokenplane
Feature activation+1.919
attacked
Token attacked
Feature activation+6.005
the
Token the
Feature activation+2.145
presidential
Token presidential
Feature activation+0.000
palace
Token palace
Feature activation+5.040
in
Token in
Feature activation+0.272

INTERVAL 0.000 - 1.436
CONTAINS 99.983%

the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
Party
Token Party
Feature activation+0.000
at
Token at
Feature activation+0.000
every
Token every
Feature activation+0.000
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
rock
Tokenrock
Feature activation+0.000
at
Token at
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
Qaeda
Token Qaeda
Feature activation+0.000
fighters
Token fighters
Feature activation+0.000
and
Token and
Feature activation+0.000
Taliban
Token Taliban
Feature activation+0.000
gu
Token gu
Feature activation+0.000
err
Tokenerr
Feature activation+0.000
illas
Tokenillas
Feature activation+0.000
from
Token from
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
close
Token close
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
commitment
Token commitment
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
modern
Token modern
Feature activation+0.000
professional
Token professional
Feature activation+0.000
athlete
Token athlete
Feature activation+0.000
is
Token is
Feature activation+0.000
clear
Token clear
Feature activation+0.000
generate
Token generate
Feature activation+0.000
back
Token back
Feature activation+0.000
.[
Token.[
Feature activation+0.000
c
Tokenc
Feature activation+0.000
itation
Tokenitation
Feature activation+0.000
needed
Token needed
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Exper
TokenExper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.000
the
Token the
Feature activation+0.000
kind
Token kind
Feature activation+0.000
Ukrainians
Token Ukrainians
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
under
Token under
Feature activation+0.000
amid
Token amid
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
and
Token and
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H11.4: (feature 14919)

TOP ACTIVATIONS
MAX = 8.981

have
Token have
Feature activation+0.000
on
Token on
Feature activation+1.857
the
Token the
Feature activation+0.000
charity
Token charity
Feature activation+0.000
and
Token and
Feature activation+1.346
specifically
Token specifically
Feature activation+8.981
Tony
Token Tony
Feature activation+0.000
and
Token and
Feature activation+3.529
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
."
Token."
Feature activation+0.000
are
Token are
Feature activation+0.000
willing
Token willing
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
,
Token,
Feature activation+2.022
but
Token but
Feature activation+7.442
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
prepared
Token prepared
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
off
Token off
Feature activation+4.913
the
Token the
Feature activation+0.000
priests
Token priests
Feature activation+0.000
,
Token,
Feature activation+0.558
and
Token and
Feature activation+3.397
carries
Token carries
Feature activation+7.401
A
Token A
Feature activation+0.000
oud
Tokenoud
Feature activation+0.000
a
Tokena
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+1.732
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
recover
Token recover
Feature activation+0.000
the
Token the
Feature activation+0.000
body
Token body
Feature activation+0.000
,
Token,
Feature activation+7.126
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.062
officials
Token officials
Feature activation+0.000
,
Token,
Feature activation+1.908
Par
Token Par
Feature activation+0.000
se
Tokense
Feature activation+0.000
yan
Tokenyan
Feature activation+0.000
said
Token said
Feature activation+7.082
the
Token the
Feature activation+1.129
process
Token process
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.311
a
Token a
Feature activation+0.000
."
Token."
Feature activation+0.436
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.735
In
TokenIn
Feature activation+1.026
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+6.973
,
Token,
Feature activation+2.626
Anthony
Token Anthony
Feature activation+0.000
's
Token's
Feature activation+1.322
publisher
Token publisher
Feature activation+0.000
,
Token,
Feature activation+0.423
cut
Token cut
Feature activation+4.977
the
Token the
Feature activation+3.412
funding
Token funding
Feature activation+1.015
of
Token of
Feature activation+5.810
another
Token another
Feature activation+3.314
,
Token,
Feature activation+6.849
the
Token the
Feature activation+1.567
Patient
Token Patient
Feature activation+0.000
-
Token-
Feature activation+0.000
Cent
TokenCent
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
,
Token,
Feature activation+0.423
Authent
Token Authent
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
Media
Token Media
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+6.797
that
Token that
Feature activation+4.776
it
Token it
Feature activation+0.000
was
Token was
Feature activation+2.444
withdrawing
Token withdrawing
Feature activation+5.760
T
Token T
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
the
Token the
Feature activation+0.126
way
Token way
Feature activation+3.004
,
Token,
Feature activation+6.751
the
Token the
Feature activation+3.303
ROM
Token ROM
Feature activation+0.000
itself
Token itself
Feature activation+0.000
is
Token is
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
OM
TokenOM
Feature activation+0.000
and
Token and
Feature activation+4.518
Gh
Token Gh
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
,
Token,
Feature activation+6.739
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
focus
Token focus
Feature activation+0.612
on
Token on
Feature activation+2.201
completing
Token completing
Feature activation+6.421
hours
Token hours
Feature activation+0.000
gained
Token gained
Feature activation+3.763
earlier
Token earlier
Feature activation+1.963
are
Token are
Feature activation+0.000
lost
Token lost
Feature activation+0.000
,
Token,
Feature activation+6.546
but
Token but
Feature activation+4.744
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
shows
Token shows
Feature activation+4.176
no
Token no
Feature activation+0.000
.
Token.
Feature activation+1.341
This
Token This
Feature activation+0.000
progress
Token progress
Feature activation+0.000
has
Token has
Feature activation+1.172
quietly
Token quietly
Feature activation+0.000
turned
Token turned
Feature activation+6.469
him
Token him
Feature activation+0.000
into
Token into
Feature activation+1.524
a
Token a
Feature activation+0.000
lockdown
Token lockdown
Feature activation+0.000
corner
Token corner
Feature activation+0.000
,
Token,
Feature activation+6.739
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
focus
Token focus
Feature activation+0.612
on
Token on
Feature activation+2.201
completing
Token completing
Feature activation+6.421
the
Token the
Feature activation+0.923
Gr
Token Gr
Feature activation+0.000
at
Tokenat
Feature activation+0.000
iot
Tokeniot
Feature activation+0.000
jail
Token jail
Feature activation+0.000
legs
Token legs
Feature activation+0.000
are
Token are
Feature activation+0.000
their
Token their
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
strength
Token strength
Feature activation+0.000
,
Token,
Feature activation+6.371
they
Token they
Feature activation+0.000
modify
Token modify
Feature activation+1.545
their
Token their
Feature activation+1.239
entry
Token entry
Feature activation+0.000
into
Token into
Feature activation+4.446
Cosmos
Token Cosmos
Feature activation+0.000
used
Token used
Feature activation+5.696
to
Token to
Feature activation+0.000
be
Token be
Feature activation+3.320
,
Token,
Feature activation+1.090
but
Token but
Feature activation+6.279
sources
Token sources
Feature activation+0.000
tell
Token tell
Feature activation+0.000
Goal
Token Goal
Feature activation+0.000
USA
Token USA
Feature activation+4.263
they
Token they
Feature activation+0.000
,
Token,
Feature activation+0.490
and
Token and
Feature activation+4.909
QB
Token QB
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
Fitzgerald
Token Fitzgerald
Feature activation+0.000
knows
Token knows
Feature activation+6.081
it
Token it
Feature activation+0.000
.
Token.
Feature activation+2.324
He
Token He
Feature activation+0.000
f
Token f
Feature activation+0.000
akes
Tokenakes
Feature activation+0.401
in
Token in
Feature activation+0.010
NASL
Token NASL
Feature activation+0.000
.
Token.
Feature activation+0.813
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.687
And
TokenAnd
Feature activation+5.939
what
Token what
Feature activation+1.177
of
Token of
Feature activation+1.809
MLS
Token MLS
Feature activation+0.000
?
Token?
Feature activation+0.000
Sources
Token Sources
Feature activation+0.000
say
Token say
Feature activation+5.659
the
Token the
Feature activation+0.438
five
Token five
Feature activation+0.000
men
Token men
Feature activation+0.000
charged
Token charged
Feature activation+1.155
in
Token in
Feature activation+5.896
the
Token the
Feature activation+2.050
fatal
Token fatal
Feature activation+0.301
shooting
Token shooting
Feature activation+0.000
are
Token are
Feature activation+1.050
members
Token members
Feature activation+0.000
proud
Token proud
Feature activation+0.152
to
Token to
Feature activation+0.000
present
Token present
Feature activation+3.979
the
Token the
Feature activation+3.276
latest
Token latest
Feature activation+3.507
in
Token in
Feature activation+5.868
our
Token our
Feature activation+2.352
series
Token series
Feature activation+1.135
of
Token of
Feature activation+2.246
guest
Token guest
Feature activation+0.000
posts
Token posts
Feature activation+0.000
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.452
cut
Token cut
Feature activation+4.977
the
Token the
Feature activation+3.412
funding
Token funding
Feature activation+1.015
of
Token of
Feature activation+5.810
another
Token another
Feature activation+3.314
,
Token,
Feature activation+6.849
the
Token the
Feature activation+1.567
Patient
Token Patient
Feature activation+0.000
-
Token-
Feature activation+0.000

Top DFA by src position
MAX = 10.048

recognise
Token recognise
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
good
Token good
Feature activation+0.005
Top resid features:
work
Token work
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.008
Top resid features:
A
Token A
Feature activation+10.048
Top resid features:
vant
Tokenvant
Feature activation+0.033
Top resid features:
i
Tokeni
Feature activation+0.039
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
Tony
Token Tony
Feature activation+0.036
Top resid features:
Anthony
Token Anthony
Feature activation+0.009
Top resid features:
whom
Token whom
Feature activation+0.007
Top resid features:
Jean
Token Jean
Feature activation-0.061
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
Mic
TokenMic
Feature activation-0.007
Top resid features:
hel
Tokenhel
Feature activation+0.001
Top resid features:
A
Token A
Feature activation+6.991
Top resid features:
ulas
Tokenulas
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
Lyon
Token Lyon
Feature activation-0.013
Top resid features:
president
Token president
Feature activation-0.002
Top resid features:
out
Tokenout
Feature activation+0.022
Top resid features:
takes
Token takes
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
place
Token place
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
A
Token A
Feature activation+8.545
Top resid features:
oud
Tokenoud
Feature activation+0.052
Top resid features:
a
Tokena
Feature activation+0.075
Top resid features:
's
Token's
Feature activation+0.022
Top resid features:
deceased
Token deceased
Feature activation+0.018
Top resid features:
husband
Token husband
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Math
TokenMath
Feature activation+0.054
Top resid features:
ilde
Tokenilde
Feature activation-0.053
Top resid features:
A
Token A
Feature activation+8.185
Top resid features:
uv
Tokenuv
Feature activation+0.107
Top resid features:
ill
Tokenill
Feature activation-0.004
Top resid features:
ain
Tokenain
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.082
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
without
Token without
Feature activation+0.009
Top resid features:
approval
Token approval
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
either
Token either
Feature activation+0.012
Top resid features:
A
Token A
Feature activation+7.102
Top resid features:
HS
TokenHS
Feature activation+0.045
Top resid features:
or
Token or
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Government
Token Government
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
Attempts
TokenAttempts
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
reach
Token reach
Feature activation+0.007
Top resid features:
Anthony
Token Anthony
Feature activation-0.021
Top resid features:
through
Token through
Feature activation+0.029
Top resid features:
A
Token A
Feature activation+3.018
Top resid features:
vant
Tokenvant
Feature activation+0.006
Top resid features:
i
Tokeni
Feature activation+0.021
Top resid features:
's
Token's
Feature activation+0.027
Top resid features:
email
Token email
Feature activation+0.010
Top resid features:
address
Token address
Feature activation+0.002
Top resid features:
Healthcare
Token Healthcare
Feature activation+0.002
Top resid features:
Research
Token Research
Feature activation-0.009
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
Quality
Token Quality
Feature activation-0.003
Top resid features:
(
Token (
Feature activation-0.009
Top resid features:
A
TokenA
Feature activation+7.976
Top resid features:
HR
TokenHR
Feature activation+0.062
Top resid features:
Q
TokenQ
Feature activation+0.007
Top resid features:
),
Token),
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
cut
Token cut
Feature activation+0.009
Top resid features:
recognise
Token recognise
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.002
Top resid features:
work
Token work
Feature activation-0.004
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
A
Token A
Feature activation+3.441
Top resid features:
vant
Tokenvant
Feature activation+0.027
Top resid features:
i
Tokeni
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
Tony
Token Tony
Feature activation+0.006
Top resid features:
Anthony
Token Anthony
Feature activation-0.001
Top resid features:
it
Token it
Feature activation-0.018
Top resid features:
being
Token being
Feature activation+0.004
Top resid features:
very
Token very
Feature activation+0.001
Top resid features:
similar
Token similar
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
A
Token A
Feature activation+8.038
Top resid features:
OSP
TokenOSP
Feature activation+0.029
Top resid features:
but
Token but
Feature activation+0.010
Top resid features:
with
Token with
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.058
Top resid features:
we
Token we
Feature activation-0.028
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
settled
Token settled
Feature activation+0.022
Top resid features:
with
Token with
Feature activation+0.054
Top resid features:
A
Token A
Feature activation+7.714
Top resid features:
EC
TokenEC
Feature activation+0.079
Top resid features:
OM
TokenOM
Feature activation+0.057
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
Gh
Token Gh
Feature activation+0.076
Top resid features:
af
Tokenaf
Feature activation+0.027
Top resid features:
out
Tokenout
Feature activation+0.003
Top resid features:
takes
Token takes
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
place
Token place
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
A
Token A
Feature activation+3.921
Top resid features:
oud
Tokenoud
Feature activation+0.012
Top resid features:
a
Tokena
Feature activation+0.018
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
deceased
Token deceased
Feature activation+0.010
Top resid features:
husband
Token husband
Feature activation+0.005
Top resid features:
2016
Token 2016
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
though
Token though
Feature activation+0.004
Top resid features:
;
Token;
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
A
Token A
Feature activation+3.748
Top resid features:
verett
Tokenverett
Feature activation+0.029
Top resid features:
emerged
Token emerged
Feature activation+0.003
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.045
Top resid features:
we
Token we
Feature activation-0.009
Top resid features:
have
Token have
Feature activation+0.013
Top resid features:
settled
Token settled
Feature activation+0.026
Top resid features:
with
Token with
Feature activation+0.047
Top resid features:
A
Token A
Feature activation+7.573
Top resid features:
EC
TokenEC
Feature activation+0.057
Top resid features:
OM
TokenOM
Feature activation+0.040
Top resid features:
and
Token and
Feature activation+0.054
Top resid features:
Gh
Token Gh
Feature activation+0.029
Top resid features:
af
Tokenaf
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
amput
Token amput
Feature activation+0.015
Top resid features:
ation
Tokenation
Feature activation+0.004
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
an
Token an
Feature activation-0.063
Top resid features:
A
Token A
Feature activation+5.552
Top resid features:
5
Token5
Feature activation+0.053
Top resid features:
classified
Token classified
Feature activation+0.012
Top resid features:
sports
Token sports
Feature activation-0.017
Top resid features:
person
Tokenperson
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
teams
Token teams
Feature activation+0.015
Top resid features:
might
Token might
Feature activation+0.017
Top resid features:
be
Token be
Feature activation+0.006
Top resid features:
interested
Token interested
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.020
Top resid features:
A
Token A
Feature activation+4.855
Top resid features:
du
Tokendu
Feature activation+0.039
Top resid features:
at
Token at
Feature activation+0.013
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
point
Token point
Feature activation+0.011
Top resid features:
?
Token?
Feature activation+0.141
Top resid features:
slot
Token slot
Feature activation+0.003
Top resid features:
receiver
Token receiver
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.055
Top resid features:
This
Token This
Feature activation+0.026
Top resid features:
leaves
Token leaves
Feature activation+0.005
Top resid features:
A
Token A
Feature activation+7.154
Top resid features:
verett
Tokenverett
Feature activation+0.039
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
an
Token an
Feature activation-0.017
Top resid features:
island
Token island
Feature activation+0.005
Top resid features:
against
Token against
Feature activation+0.012
Top resid features:
but
Token but
Feature activation+0.011
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
remains
Token remains
Feature activation-0.000
Top resid features:
unclear
Token unclear
Feature activation-0.003
Top resid features:
whether
Token whether
Feature activation+0.003
Top resid features:
A
Token A
Feature activation+6.980
Top resid features:
du
Tokendu
Feature activation+0.052
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
ready
Token ready
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
listen
Token listen
Feature activation+0.007
Top resid features:
ell
Tokenell
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
shook
Token shook
Feature activation+0.006
Top resid features:
hands
Token hands
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.032
Top resid features:
A
Token A
Feature activation+7.144
Top resid features:
yn
Tokenyn
Feature activation+0.035
Top resid features:
is
Tokenis
Feature activation+0.052
Top resid features:
'
Token'
Feature activation+0.007
Top resid features:
mother
Token mother
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
ate
Tokenate
Feature activation+0.032
Top resid features:
ge
Tokenge
Feature activation+0.005
Top resid features:
ez
Tokenez
Feature activation+0.011
Top resid features:
er
Tokener
Feature activation+0.024
Top resid features:
vs
Token vs
Feature activation+0.004
Top resid features:
A
Token A
Feature activation+6.403
Top resid features:
Bowl
Token Bowl
Feature activation+0.057
Top resid features:
Full
Token Full
Feature activation+0.017
Top resid features:
Of
Token Of
Feature activation+0.007
Top resid features:
Dirt
Token Dirt
Feature activation+0.074
Top resid features:
(
Token (
Feature activation+0.008
Top resid features:
Healthcare
Token Healthcare
Feature activation+0.008
Top resid features:
Research
Token Research
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Quality
Token Quality
Feature activation-0.000
Top resid features:
(
Token (
Feature activation-0.002
Top resid features:
A
TokenA
Feature activation+6.635
Top resid features:
HR
TokenHR
Feature activation+0.058
Top resid features:
Q
TokenQ
Feature activation+0.012
Top resid features:
),
Token),
Feature activation+0.020
Top resid features:
and
Token and
Feature activation+0.078
Top resid features:
cut
Token cut
Feature activation+0.015
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.05

Head 3: 0.05

Head 4: 0.42

Head 5: 0.04

Head 6: 0.08

Head 7: 0.05

Head 8: 0.07

Head 9: 0.05

Head 10: 0.04

Head 11: 0.04

Positive logits

A7.74

A4.88

An4.03

AA2.81

One2.59

Ae2.37

Another2.24

As2.11

At2.11

AQ2.11

AFC2.10

AN2.08

ahime2.07

AAP2.06

AAC2.03

affiliates2.02

AJ2.02

Nine2.02

Two2.02

An2.01

Negative logits

ItemImage-2.68

ministic-2.57

idge-2.28

ItemThumbnailImage-2.28

ropy-2.21

enegger-2.20

Percent-2.19

rences-2.16

resy-2.08

quickShipAvailable-2.00

icans-1.99

rics-1.98

ptions-1.92

ermanent-1.90

Center-1.87

iences-1.81

ience-1.81

esc-1.78

omer-1.76

adows-1.74

INTERVAL 8.083 - 8.981
CONTAINS 0.000%

have
Token have
Feature activation+0.000
on
Token on
Feature activation+1.857
the
Token the
Feature activation+0.000
charity
Token charity
Feature activation+0.000
and
Token and
Feature activation+1.346
specifically
Token specifically
Feature activation+8.981
Tony
Token Tony
Feature activation+0.000
and
Token and
Feature activation+3.529
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
."
Token."
Feature activation+0.000

INTERVAL 7.185 - 8.083
CONTAINS 0.000%

off
Token off
Feature activation+4.913
the
Token the
Feature activation+0.000
priests
Token priests
Feature activation+0.000
,
Token,
Feature activation+0.558
and
Token and
Feature activation+3.397
carries
Token carries
Feature activation+7.401
A
Token A
Feature activation+0.000
oud
Tokenoud
Feature activation+0.000
a
Tokena
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+1.732
are
Token are
Feature activation+0.000
willing
Token willing
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
,
Token,
Feature activation+2.022
but
Token but
Feature activation+7.442
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
prepared
Token prepared
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000

INTERVAL 6.287 - 7.185
CONTAINS 0.001%

officials
Token officials
Feature activation+0.000
,
Token,
Feature activation+1.908
Par
Token Par
Feature activation+0.000
se
Tokense
Feature activation+0.000
yan
Tokenyan
Feature activation+0.000
said
Token said
Feature activation+7.082
the
Token the
Feature activation+1.129
process
Token process
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.311
a
Token a
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
recover
Token recover
Feature activation+0.000
the
Token the
Feature activation+0.000
body
Token body
Feature activation+0.000
,
Token,
Feature activation+7.126
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.062
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
the
Token the
Feature activation+0.126
way
Token way
Feature activation+3.004
,
Token,
Feature activation+6.751
the
Token the
Feature activation+3.303
ROM
Token ROM
Feature activation+0.000
itself
Token itself
Feature activation+0.000
is
Token is
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
OM
TokenOM
Feature activation+0.000
and
Token and
Feature activation+4.518
Gh
Token Gh
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
,
Token,
Feature activation+6.739
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
focus
Token focus
Feature activation+0.612
on
Token on
Feature activation+2.201
completing
Token completing
Feature activation+6.421
,
Token,
Feature activation+0.423
Authent
Token Authent
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
Media
Token Media
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+6.797
that
Token that
Feature activation+4.776
it
Token it
Feature activation+0.000
was
Token was
Feature activation+2.444
withdrawing
Token withdrawing
Feature activation+5.760
T
Token T
Feature activation+0.000

INTERVAL 5.389 - 6.287
CONTAINS 0.002%

the
Token the
Feature activation+1.132
time
Token time
Feature activation+0.000
has
Token has
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
Feature activation+5.807
its
Token its
Feature activation+0.589
ministries
Token ministries
Feature activation+0.000
."
Token."
Feature activation+0.436
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.735
the
Token the
Feature activation+2.050
fatal
Token fatal
Feature activation+0.301
shooting
Token shooting
Feature activation+0.000
are
Token are
Feature activation+1.050
members
Token members
Feature activation+0.000
of
Token of
Feature activation+5.485
the
Token the
Feature activation+1.802
Harriet
Token Harriet
Feature activation+0.081
Street
Token Street
Feature activation+0.000
gang
Token gang
Feature activation+0.000
,
Token,
Feature activation+0.056
,
Token,
Feature activation+0.490
and
Token and
Feature activation+4.909
QB
Token QB
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
Fitzgerald
Token Fitzgerald
Feature activation+0.000
knows
Token knows
Feature activation+6.081
it
Token it
Feature activation+0.000
.
Token.
Feature activation+2.324
He
Token He
Feature activation+0.000
f
Token f
Feature activation+0.000
akes
Tokenakes
Feature activation+0.401
,
Token,
Feature activation+0.000
said
Token said
Feature activation+6.797
that
Token that
Feature activation+4.776
it
Token it
Feature activation+0.000
was
Token was
Feature activation+2.444
withdrawing
Token withdrawing
Feature activation+5.760
T
Token T
Feature activation+0.000
aming
Tokenaming
Feature activation+0.000
the
Token the
Feature activation+0.000
Tiger
Token Tiger
Feature activation+0.000
,
Token,
Feature activation+3.233
ub
Tokenub
Feature activation+0.000
eni
Tokeneni
Feature activation+0.000
Corp
Token Corp
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
oversee
Token oversee
Feature activation+5.542
the
Token the
Feature activation+1.583
launch
Token launch
Feature activation+0.000
.
Token.
Feature activation+0.000
G
Token G
Feature activation+0.000
av
Tokenav
Feature activation+0.000

INTERVAL 4.491 - 5.389
CONTAINS 0.003%

Authent
Token Authent
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
Media
Token Media
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+6.797
that
Token that
Feature activation+4.776
it
Token it
Feature activation+0.000
was
Token was
Feature activation+2.444
withdrawing
Token withdrawing
Feature activation+5.760
T
Token T
Feature activation+0.000
aming
Tokenaming
Feature activation+0.000
gained
Token gained
Feature activation+3.763
earlier
Token earlier
Feature activation+1.963
are
Token are
Feature activation+0.000
lost
Token lost
Feature activation+0.000
,
Token,
Feature activation+6.546
but
Token but
Feature activation+4.744
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
shows
Token shows
Feature activation+4.176
no
Token no
Feature activation+0.000
regret
Token regret
Feature activation+0.000
become
Token become
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
's
Token's
Feature activation+0.000
soundtrack
Token soundtrack
Feature activation+0.000
,
Token,
Feature activation+5.197
Gu
Token Gu
Feature activation+0.000
zman
Tokenzman
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.000
asked
Token asked
Feature activation+5.497
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.682
have
Token have
Feature activation+0.000
prompted
Token prompted
Feature activation+1.623
threats
Token threats
Feature activation+0.000
from
Token from
Feature activation+4.696
the
Token the
Feature activation+1.725
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
and
Token and
Feature activation+2.344
lawmakers
Token lawmakers
Feature activation+0.000
able
Token able
Feature activation+0.064
bod
Token bod
Feature activation+0.000
ied
Tokenied
Feature activation+2.993
sw
Token sw
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.664
,
Token,
Feature activation+4.950
sw
Token sw
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.000
in
Token in
Feature activation+2.765
this
Token this
Feature activation+1.493
class
Token class
Feature activation+0.000

INTERVAL 3.592 - 4.491
CONTAINS 0.006%

Ċ
TokenĊ
Feature activation+0.000
âĢ¢
TokenâĢ¢
Feature activation+0.000
consider
Token consider
Feature activation+2.802
fandom
Token fandom
Feature activation+0.000
,
Token,
Feature activation+1.118
including
Token including
Feature activation+4.049
an
Token an
Feature activation+2.026
un
Token un
Feature activation+0.000
break
Tokenbreak
Feature activation+0.000
able
Tokenable
Feature activation+0.000
connection
Token connection
Feature activation+0.000
more
Token more
Feature activation+2.904
energy
Token energy
Feature activation+0.000
was
Token was
Feature activation+0.000
required
Token required
Feature activation+0.000
to
Token to
Feature activation+0.000
break
Token break
Feature activation+4.401
Mus
Token Mus
Feature activation+0.970
skin
Token skin
Feature activation+0.747
relative
Token relative
Feature activation+0.000
to
Token to
Feature activation+1.929
A
Token A
Feature activation+0.000
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
A
Token A
Feature activation+0.000
verett
Tokenverett
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
as
Token as
Feature activation+3.931
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
option
Token option
Feature activation+0.000
when
Token when
Feature activation+3.392
Alabama
Token Alabama
Feature activation+0.000
ials
Tokenials
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
one
Token one
Feature activation+0.000
from
Token from
Feature activation+1.980
a
Token a
Feature activation+0.000
former
Token former
Feature activation+3.613
military
Token military
Feature activation+0.000
medic
Token medic
Feature activation+0.000
and
Token and
Feature activation+0.000
another
Token another
Feature activation+0.000
penned
Token penned
Feature activation+0.000
the
Token the
Feature activation+0.923
Gr
Token Gr
Feature activation+0.000
at
Tokenat
Feature activation+0.000
iot
Tokeniot
Feature activation+0.000
jail
Token jail
Feature activation+0.000
;
Token;
Feature activation+4.371
the
Token the
Feature activation+1.705
next
Token next
Feature activation+0.562
step
Token step
Feature activation+0.000
is
Token is
Feature activation+1.665
preparing
Token preparing
Feature activation+3.377

INTERVAL 2.694 - 3.592
CONTAINS 0.011%

ve
Tokenve
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+3.877
the
Token the
Feature activation+3.493
veterinary
Token veterinary
Feature activation+0.000
school
Token school
Feature activation+0.000
on
Token on
Feature activation+0.000
campus
Token campus
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.685
yesterday
Token yesterday
Feature activation+0.000
only
Token only
Feature activation+0.000
that
Token that
Feature activation+3.194
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
gone
Token gone
Feature activation+0.000
to
Token to
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
;
Token;
Feature activation+4.371
the
Token the
Feature activation+1.705
next
Token next
Feature activation+0.562
step
Token step
Feature activation+0.000
is
Token is
Feature activation+1.665
preparing
Token preparing
Feature activation+3.377
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
issuing
Token issuing
Feature activation+0.205
a
Token a
Feature activation+0.000
design
Token design
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
.
Token.
Feature activation+3.913
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.732
Arsenal
TokenArsenal
Feature activation+0.000
value
Token value
Feature activation+3.319
Lac
Token Lac
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
ette
Tokenette
Feature activation+0.000
at
Token at
Feature activation+0.000
âĤ¬
Token âĤ¬
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Please
TokenPlease
Feature activation+0.000
note
Token note
Feature activation+0.000
that
Token that
Feature activation+3.496
there
Token there
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
slight
Token slight
Feature activation+0.000
errors
Token errors
Feature activation+0.000

INTERVAL 1.796 - 2.694
CONTAINS 0.022%

to
Token to
Feature activation+0.000
break
Token break
Feature activation+4.401
Mus
Token Mus
Feature activation+0.970
skin
Token skin
Feature activation+0.747
relative
Token relative
Feature activation+0.000
to
Token to
Feature activation+1.929
A
Token A
Feature activation+0.000
com
Tokencom
Feature activation+0.000
ys
Tokenys
Feature activation+1.207
skin
Token skin
Feature activation+0.000
(
Token (
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
died
Token died
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+2.202
the
Token the
Feature activation+2.961
university
Token university
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
little
Token little
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+2.259
back
Token back
Feature activation+0.000
surgery
Token surgery
Feature activation+0.000
over
Token over
Feature activation+0.000
nons
Token nons
Feature activation+0.000
urgical
Tokenurgical
Feature activation+0.000
âĢ¢
TokenâĢ¢
Feature activation+0.000
consider
Token consider
Feature activation+2.802
fandom
Token fandom
Feature activation+0.000
,
Token,
Feature activation+1.118
including
Token including
Feature activation+4.049
an
Token an
Feature activation+2.026
un
Token un
Feature activation+0.000
break
Tokenbreak
Feature activation+0.000
able
Tokenable
Feature activation+0.000
connection
Token connection
Feature activation+0.000
with
Token with
Feature activation+2.090
anxiety
Token anxiety
Feature activation+0.000
.
Token.
Feature activation+0.000
Recent
Token Recent
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
indicates
Token indicates
Feature activation+1.889
that
Token that
Feature activation+1.960
the
Token the
Feature activation+0.387
disease
Token disease
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
trans
Token trans
Feature activation+0.000

INTERVAL 0.898 - 1.796
CONTAINS 0.042%

's
Token's
Feature activation+0.000
most
Token most
Feature activation+0.000
populous
Token populous
Feature activation+0.000
nation
Token nation
Feature activation+0.000
and
Token and
Feature activation+0.000
why
Token why
Feature activation+1.688
Hollywood
Token Hollywood
Feature activation+0.000
should
Token should
Feature activation+0.000
regard
Token regard
Feature activation+1.858
Wolf
Token Wolf
Feature activation+0.000
Warrior
Token Warrior
Feature activation+0.235
mascot
Token mascot
Feature activation+0.000
of
Token of
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
A
Token A
Feature activation+0.000
&
Token&
Feature activation+0.000
M
TokenM
Feature activation+1.354
,
Token,
Feature activation+1.130
Reve
Token Reve
Feature activation+0.000
ille
Tokenille
Feature activation+0.246
VII
Token VII
Feature activation+0.000
,
Token,
Feature activation+0.000
court
Token court
Feature activation+0.000
documents
Token documents
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.989
first
Token first
Feature activation+1.150
indictment
Token indictment
Feature activation+0.000
count
Token count
Feature activation+0.000
alleges
Token alleges
Feature activation+0.000
You
Token You
Feature activation+0.000
rep
Token rep
Feature activation+0.000
lying
Tokenlying
Feature activation+0.000
to
Token to
Feature activation+0.731
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
whether
Token whether
Feature activation+0.902
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
policy
Token policy
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
-
Token-
Feature activation+0.000
series
Tokenseries
Feature activation+0.793
chips
Token chips
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.596
encrypted
Token encrypted
Feature activation+0.998
SE
Token SE
Feature activation+0.000
P
TokenP
Feature activation+0.000
is
Token is
Feature activation+0.000
completely
Token completely
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000

INTERVAL 0.000 - 0.898
CONTAINS 99.912%

Mic
TokenMic
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
son
Tokenson
Feature activation+0.000
took
Token took
Feature activation+0.000
nine
Token nine
Feature activation+0.000
shots
Token shots
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
cup
Token cup
Feature activation+0.000
on
Token on
Feature activation+0.000
much
Token much
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
has
Token has
Feature activation+0.000
impacted
Token impacted
Feature activation+0.000
my
Token my
Feature activation+0.000
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Much
TokenMuch
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
committee
Token committee
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
conversations
Token conversations
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
President
Token President
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
allegedly
Token allegedly
Feature activation+0.000
was
Token was
Feature activation+0.000
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
praise
Token praise
Feature activation+0.000
and
Token and
Feature activation+0.000
criticism
Token criticism
Feature activation+0.000
.
Token.
Feature activation+0.000
Fans
Token Fans
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
her
Token her
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
regrets
Token regrets
Feature activation+0.000
and
Token and
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
struggle
Token struggle
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
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 H11.4: (feature 8377)

TOP ACTIVATIONS
MAX = 6.166

unpredictable
Token unpredictable
Feature activation+0.000
web
Token web
Feature activation+0.000
content
Token content
Feature activation+0.000
:
Token:
Feature activation+2.699
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
content
Token content
Feature activation+0.000
:
Token:
Feature activation+2.699
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
update
Token update
Feature activation+0.000
this
Token this
Feature activation+0.000
thread
Token thread
Feature activation+0.000
as
Token as
Feature activation+5.774
myself
Token myself
Feature activation+0.000
am
Token am
Feature activation+0.000
updated
Token updated
Feature activation+0.000
.
Token.
Feature activation+0.711
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+2.699
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000
speech
Token speech
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000
speech
Token speech
Feature activation+0.000
recognition
Token recognition
Feature activation+0.000
from
Token from
Feature activation+1.763
and
Token and
Feature activation+0.000
good
Token good
Feature activation+0.000
faith
Token faith
Feature activation+0.000
.
Token.
Feature activation+3.955
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+4.872
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.642
[
Token[
Feature activation+0.000
image
Tokenimage
Feature activation+0.000
via
Token via
Feature activation+0.867
policies
Token policies
Feature activation+0.000
of
Token of
Feature activation+0.000
ii
Token ii
Feature activation+0.000
Net
TokenNet
Feature activation+0.000
,
Token,
Feature activation+2.142
or
Token or
Feature activation+4.780
of
Token of
Feature activation+4.396
games
Token games
Feature activation+0.000
.
Token.
Feature activation+1.175
on
Tokenon
Feature activation+0.000
.
Token.
Feature activation+0.063
a
Token a
Feature activation+0.000
secure
Token secure
Feature activation+0.000
application
Token application
Feature activation+0.000
container
Token container
Feature activation+0.000
.
Token.
Feature activation+3.591
The
Token The
Feature activation+4.699
Q
Token Q
Feature activation+0.000
N
TokenN
Feature activation+0.000
X
TokenX
Feature activation+1.845
CAR
Token CAR
Feature activation+0.000
Platform
Token Platform
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.492
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.227
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+4.681
,
Token,
Feature activation+4.449
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.227
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+4.681
,
Token,
Feature activation+4.449
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
of
Token of
Feature activation+0.000
ii
Token ii
Feature activation+0.000
Net
TokenNet
Feature activation+0.000
,
Token,
Feature activation+2.142
or
Token or
Feature activation+4.780
of
Token of
Feature activation+4.396
games
Token games
Feature activation+0.000
.
Token.
Feature activation+1.175
on
Tokenon
Feature activation+0.000
.
Token.
Feature activation+0.063
net
Tokennet
Feature activation+0.000
some
Token some
Feature activation+0.761
of
Token of
Feature activation+0.265
the
Token the
Feature activation+2.416
parts
Token parts
Feature activation+0.000
from
Token from
Feature activation+0.557
the
Token the
Feature activation+4.346
article
Token article
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Many
TokenMany
Feature activation+0.000
i
Token i
Feature activation+0.000
Ac
TokenAc
Feature activation+0.000
quire
Tokenquire
Feature activation+4.319
developers
Token developers
Feature activation+0.000
are
Token are
Feature activation+0.925
currently
Token currently
Feature activation+0.720
using
Token using
Feature activation+3.283
Ubuntu
Token Ubuntu
Feature activation+0.000
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000
speech
Token speech
Feature activation+0.000
recognition
Token recognition
Feature activation+0.000
from
Token from
Feature activation+1.763
Nu
Token Nu
Feature activation+0.000
semble
Tokensemble
Feature activation+1.222
using
Token using
Feature activation+0.595
the
Token the
Feature activation+1.631
Kit
Token Kit
Feature activation+0.000
.
Token.
Feature activation+0.116
The
Token The
Feature activation+4.146
kit
Token kit
Feature activation+0.000
is
Token is
Feature activation+0.000
listed
Token listed
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.266
accuracy
Token accuracy
Feature activation+0.000
and
Token and
Feature activation+0.000
good
Token good
Feature activation+0.000
faith
Token faith
Feature activation+0.000
.
Token.
Feature activation+3.955
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+4.872
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.642
[
Token[
Feature activation+0.000
Including
Token Including
Feature activation+2.145
my
Token my
Feature activation+0.000
sister
Token sister
Feature activation+0.353
.
Token.
Feature activation+2.903
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.945
Ċ
TokenĊ
Feature activation+2.086
Ċ
TokenĊ
Feature activation+1.524
CL
TokenCL
Feature activation+0.000
ICK
TokenICK
Feature activation+1.004
CONTIN
Token CONTIN
Feature activation+0.000
i
Token i
Feature activation+0.000
Cle
TokenCle
Feature activation+0.000
ver
Tokenver
Feature activation+1.459
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.940
Wireless
Token Wireless
Feature activation+0.000
Charg
Token Charg
Feature activation+0.000
er
Tokener
Feature activation+0.068
are
Token are
Feature activation+0.853
all
Token all
Feature activation+0.310
BMW
Token BMW
Feature activation+0.000
i
Token i
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.050
The
Token The
Feature activation+2.129
first
Token first
Feature activation+3.714
ever
Token ever
Feature activation+2.279
BMW
Token BMW
Feature activation+0.578
i
Token i
Feature activation+0.247
3
Token3
Feature activation+0.900
s
Tokens
Feature activation+0.777
CONTIN
Token CONTIN
Feature activation+0.000
UE
TokenUE
Feature activation+0.154
READ
Token READ
Feature activation+0.000
ING
TokenING
Feature activation+0.000
FOR
Token FOR
Feature activation+1.148
MORE
Token MORE
Feature activation+3.644
!
Token!
Feature activation+3.463
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.611
Kyle
TokenKyle
Feature activation+0.000
went
Token went
Feature activation+0.000

Top DFA by src position
MAX = 7.212

Android
Token Android
Feature activation-0.073
Top resid features:
Jelly
Token Jelly
Feature activation+0.007
Top resid features:
bean
Tokenbean
Feature activation-0.002
Top resid features:
version
Token version
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.028
Top resid features:
i
Token i
Feature activation+7.212
Top resid features:
Heart
TokenHeart
Feature activation+0.014
Top resid features:
Radio
TokenRadio
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
Clear
Token Clear
Feature activation+0.022
Top resid features:
Channel
Token Channel
Feature activation+0.002
Top resid features:
Android
Token Android
Feature activation-0.041
Top resid features:
Jelly
Token Jelly
Feature activation+0.009
Top resid features:
bean
Tokenbean
Feature activation-0.003
Top resid features:
version
Token version
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.030
Top resid features:
i
Token i
Feature activation+6.700
Top resid features:
Heart
TokenHeart
Feature activation+0.022
Top resid features:
Radio
TokenRadio
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
Clear
Token Clear
Feature activation+0.007
Top resid features:
Channel
Token Channel
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
be
Token be
Feature activation+0.015
Top resid features:
true
Token true
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
but
Token but
Feature activation+0.016
Top resid features:
i
Token i
Feature activation+6.739
Top resid features:
assure
Token assure
Feature activation+0.007
Top resid features:
you
Token you
Feature activation+0.024
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
all
Token all
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.044
Top resid features:
Android
Token Android
Feature activation-0.060
Top resid features:
Jelly
Token Jelly
Feature activation+0.027
Top resid features:
bean
Tokenbean
Feature activation-0.006
Top resid features:
version
Token version
Feature activation+0.031
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
i
Token i
Feature activation+6.138
Top resid features:
Heart
TokenHeart
Feature activation+0.013
Top resid features:
Radio
TokenRadio
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
Clear
Token Clear
Feature activation+0.013
Top resid features:
Channel
Token Channel
Feature activation-0.000
Top resid features:
Android
Token Android
Feature activation-0.037
Top resid features:
Jelly
Token Jelly
Feature activation+0.020
Top resid features:
bean
Tokenbean
Feature activation-0.007
Top resid features:
version
Token version
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
i
Token i
Feature activation+5.648
Top resid features:
Heart
TokenHeart
Feature activation+0.038
Top resid features:
Radio
TokenRadio
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Clear
Token Clear
Feature activation+0.025
Top resid features:
Channel
Token Channel
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Similarly
TokenSimilarly
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
i
Token i
Feature activation+5.177
Top resid features:
Media
TokenMedia
Feature activation+0.027
Top resid features:
Eth
TokenEth
Feature activation-0.011
Top resid features:
ics
Tokenics
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
ĺ
Tokenĺ
Feature activation-0.003
Top resid features:
keeping
Token keeping
Feature activation+0.044
Top resid features:
with
Token with
Feature activation+0.018
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
policies
Token policies
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.078
Top resid features:
ii
Token ii
Feature activation+6.244
Top resid features:
Net
TokenNet
Feature activation+0.171
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
or
Token or
Feature activation+0.056
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
Android
Token Android
Feature activation-0.073
Top resid features:
Jelly
Token Jelly
Feature activation-0.031
Top resid features:
bean
Tokenbean
Feature activation-0.015
Top resid features:
version
Token version
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
i
Token i
Feature activation+5.865
Top resid features:
Heart
TokenHeart
Feature activation+0.035
Top resid features:
Radio
TokenRadio
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
Clear
Token Clear
Feature activation+0.012
Top resid features:
Channel
Token Channel
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
website
Token website
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
"
Token "
Feature activation-0.007
Top resid features:
i
Tokeni
Feature activation+5.852
Top resid features:
am
Token am
Feature activation-0.005
Top resid features:
done
Token done
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
i
Tokeni
Feature activation+0.416
Top resid features:
take
Token take
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
website
Token website
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
"
Token "
Feature activation+0.003
Top resid features:
i
Tokeni
Feature activation+5.942
Top resid features:
am
Token am
Feature activation-0.005
Top resid features:
done
Token done
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
i
Tokeni
Feature activation+0.399
Top resid features:
take
Token take
Feature activation-0.001
Top resid features:
keeping
Token keeping
Feature activation+0.016
Top resid features:
with
Token with
Feature activation-0.049
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
policies
Token policies
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
ii
Token ii
Feature activation+6.155
Top resid features:
Net
TokenNet
Feature activation+0.133
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
or
Token or
Feature activation+0.005
Top resid features:
of
Token of
Feature activation-0.028
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
rest
Token rest
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
i
Token i
Feature activation+5.661
Top resid features:
Ac
TokenAc
Feature activation+0.023
Top resid features:
quire
Tokenquire
Feature activation-0.015
Top resid features:
team
Token team
Feature activation+0.015
Top resid features:
as
Token as
Feature activation+0.005
Top resid features:
soon
Token soon
Feature activation+0.001
Top resid features:
ang
Tokenang
Feature activation-0.009
Top resid features:
olin
Tokenolin
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
Many
TokenMany
Feature activation-0.040
Top resid features:
i
Token i
Feature activation+5.786
Top resid features:
Ac
TokenAc
Feature activation+0.036
Top resid features:
quire
Tokenquire
Feature activation-0.015
Top resid features:
developers
Token developers
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
currently
Token currently
Feature activation+0.000
Top resid features:
Android
Token Android
Feature activation-0.040
Top resid features:
Jelly
Token Jelly
Feature activation+0.013
Top resid features:
bean
Tokenbean
Feature activation-0.006
Top resid features:
version
Token version
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
i
Token i
Feature activation+5.166
Top resid features:
Heart
TokenHeart
Feature activation+0.021
Top resid features:
Radio
TokenRadio
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
Clear
Token Clear
Feature activation+0.022
Top resid features:
Channel
Token Channel
Feature activation+0.001
Top resid features:
necessary
Token necessary
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
turn
Token turn
Feature activation-0.022
Top resid features:
your
Token your
Feature activation-0.006
Top resid features:
own
Token own
Feature activation-0.005
Top resid features:
i
Token i
Feature activation+4.085
Top resid features:
Mac
TokenMac
Feature activation+0.041
Top resid features:
into
Token into
Feature activation+0.018
Top resid features:
an
Token an
Feature activation+0.018
Top resid features:
aquarium
Token aquarium
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ŀ
TokenĿ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Similarly
TokenSimilarly
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
i
Token i
Feature activation+3.826
Top resid features:
Media
TokenMedia
Feature activation+0.029
Top resid features:
Eth
TokenEth
Feature activation-0.014
Top resid features:
ics
Tokenics
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
ĺ
Tokenĺ
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.015
Top resid features:
i
Tokeni
Feature activation+4.582
Top resid features:
is
Token is
Feature activation-0.005
Top resid features:
not
Token not
Feature activation-0.004
Top resid features:
my
Token my
Feature activation+0.009
Top resid features:
friend
Token friend
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
-
Token-
Feature activation+0.035
Top resid features:
PC
TokenPC
Feature activation+0.054
Top resid features:
06
Token06
Feature activation-0.025
Top resid features:
3
Token3
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
i
Token i
Feature activation+5.230
Top resid features:
Cle
TokenCle
Feature activation+0.046
Top resid features:
ver
Tokenver
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.036
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.039
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.056
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
New
TokenNew
Feature activation+0.011
Top resid features:
BMW
Token BMW
Feature activation+0.621
Top resid features:
i
Token i
Feature activation+2.776
Top resid features:
3
Token3
Feature activation+0.075
Top resid features:
s
Tokens
Feature activation+0.095
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.054
Top resid features:
The
TokenThe
Feature activation+0.071
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.024
Top resid features:
i
Tokeni
Feature activation+4.764
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
my
Token my
Feature activation-0.004
Top resid features:
friend
Token friend
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.05

Head 3: 0.05

Head 4: 0.38

Head 5: 0.05

Head 6: 0.05

Head 7: 0.08

Head 8: 0.10

Head 9: 0.05

Head 10: 0.04

Head 11: 0.04

Positive logits

i9.41

i6.23

ii5.56

iT5.24

iii4.07

ii3.66

e3.53

iii3.02

im2.97

iP2.97

xi2.89

iv2.83

nt2.82

iq2.77

ie2.76

didnt2.72

u2.66

dont2.64

happ2.47

iological2.44

Negative logits

#$-2.30

Lod-2.24

pes-2.16

oshenko-2.09

-2.08

mort-2.08

agall-2.07

disappro-2.04

henko-2.01

etting-2.00

ospel-1.99

Breed-1.98

rity-1.98

ener-1.97

oras-1.97

Mas-1.96

Obst-1.94

boss-1.91

-1.89

shelters-1.87

INTERVAL 5.549 - 6.166
CONTAINS 0.000%

I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
update
Token update
Feature activation+0.000
this
Token this
Feature activation+0.000
thread
Token thread
Feature activation+0.000
as
Token as
Feature activation+5.774
myself
Token myself
Feature activation+0.000
am
Token am
Feature activation+0.000
updated
Token updated
Feature activation+0.000
.
Token.
Feature activation+0.711
Ċ
TokenĊ
Feature activation+0.000
unpredictable
Token unpredictable
Feature activation+0.000
web
Token web
Feature activation+0.000
content
Token content
Feature activation+0.000
:
Token:
Feature activation+2.699
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
content
Token content
Feature activation+0.000
:
Token:
Feature activation+2.699
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000

INTERVAL 4.933 - 5.549
CONTAINS 0.000%

:
Token:
Feature activation+2.699
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000
speech
Token speech
Feature activation+0.000

INTERVAL 4.316 - 4.933
CONTAINS 0.001%

policies
Token policies
Feature activation+0.000
of
Token of
Feature activation+0.000
ii
Token ii
Feature activation+0.000
Net
TokenNet
Feature activation+0.000
,
Token,
Feature activation+2.142
or
Token or
Feature activation+4.780
of
Token of
Feature activation+4.396
games
Token games
Feature activation+0.000
.
Token.
Feature activation+1.175
on
Tokenon
Feature activation+0.000
.
Token.
Feature activation+0.063
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Many
TokenMany
Feature activation+0.000
i
Token i
Feature activation+0.000
Ac
TokenAc
Feature activation+0.000
quire
Tokenquire
Feature activation+4.319
developers
Token developers
Feature activation+0.000
are
Token are
Feature activation+0.925
currently
Token currently
Feature activation+0.720
using
Token using
Feature activation+3.283
Ubuntu
Token Ubuntu
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.492
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.227
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+4.681
,
Token,
Feature activation+4.449
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.227
For
TokenFor
Feature activation+0.000
the
Token the
Feature activation+0.000
record
Token record
Feature activation+4.681
,
Token,
Feature activation+4.449
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.166
Additionally
TokenAdditionally
Feature activation+2.272
,
Token,
Feature activation+5.836
the
Token the
Feature activation+5.236
company
Token company
Feature activation+0.000
says
Token says
Feature activation+4.917
that
Token that
Feature activation+4.310
natural
Token natural
Feature activation+0.000
speech
Token speech
Feature activation+0.000
recognition
Token recognition
Feature activation+0.000
from
Token from
Feature activation+1.763

INTERVAL 3.700 - 4.316
CONTAINS 0.001%

semble
Tokensemble
Feature activation+1.222
using
Token using
Feature activation+0.595
the
Token the
Feature activation+1.631
Kit
Token Kit
Feature activation+0.000
.
Token.
Feature activation+0.116
The
Token The
Feature activation+4.146
kit
Token kit
Feature activation+0.000
is
Token is
Feature activation+0.000
listed
Token listed
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
i
Token i
Feature activation+0.000
Cle
TokenCle
Feature activation+0.000
ver
Tokenver
Feature activation+1.459
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.940
Wireless
Token Wireless
Feature activation+0.000
Charg
Token Charg
Feature activation+0.000
er
Tokener
Feature activation+0.068
are
Token are
Feature activation+0.853
all
Token all
Feature activation+0.310
Including
Token Including
Feature activation+2.145
my
Token my
Feature activation+0.000
sister
Token sister
Feature activation+0.353
.
Token.
Feature activation+2.903
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.945
Ċ
TokenĊ
Feature activation+2.086
Ċ
TokenĊ
Feature activation+1.524
CL
TokenCL
Feature activation+0.000
ICK
TokenICK
Feature activation+1.004
CONTIN
Token CONTIN
Feature activation+0.000
of
Token of
Feature activation+0.266
accuracy
Token accuracy
Feature activation+0.000
and
Token and
Feature activation+0.000
good
Token good
Feature activation+0.000
faith
Token faith
Feature activation+0.000
.
Token.
Feature activation+3.955
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+4.872
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.642
[
Token[
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
i
Token i
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.050
The
Token The
Feature activation+2.129
first
Token first
Feature activation+3.714
ever
Token ever
Feature activation+2.279
BMW
Token BMW
Feature activation+0.578
i
Token i
Feature activation+0.247
3
Token3
Feature activation+0.900
s
Tokens
Feature activation+0.777

INTERVAL 3.083 - 3.700
CONTAINS 0.002%

UE
TokenUE
Feature activation+0.154
READ
Token READ
Feature activation+0.000
ING
TokenING
Feature activation+0.000
FOR
Token FOR
Feature activation+1.148
MORE
Token MORE
Feature activation+3.644
!
Token!
Feature activation+3.463
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.611
Kyle
TokenKyle
Feature activation+0.000
went
Token went
Feature activation+0.000
on
Token on
Feature activation+0.000
rest
Token rest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
i
Token i
Feature activation+0.000
Ac
TokenAc
Feature activation+0.000
quire
Tokenquire
Feature activation+3.583
team
Token team
Feature activation+0.000
as
Token as
Feature activation+0.222
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
.
Token.
Feature activation+0.977
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.699
Several
TokenSeveral
Feature activation+2.188
of
Token of
Feature activation+3.128
the
Token the
Feature activation+1.928
i
Token i
Feature activation+0.000
Ac
TokenAc
Feature activation+0.000
quire
Tokenquire
Feature activation+2.153
developers
Token developers
Feature activation+0.000
Q
Token Q
Feature activation+0.000
N
TokenN
Feature activation+0.000
X
TokenX
Feature activation+1.845
CAR
Token CAR
Feature activation+0.000
Platform
Token Platform
Feature activation+0.000
takes
Token takes
Feature activation+3.561
this
Token this
Feature activation+0.033
same
Token same
Feature activation+0.393
sandbox
Token sandbox
Feature activation+0.000
ed
Tokened
Feature activation+0.000
approach
Token approach
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.799
.
Token.
Feature activation+0.000
Upon
Token Upon
Feature activation+0.000
success
Token success
Feature activation+0.341
of
Token of
Feature activation+3.207
this
Token this
Feature activation+2.956
project
Token project
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
plans
Token plans
Feature activation+0.000

INTERVAL 2.466 - 3.083
CONTAINS 0.003%

a
Token a
Feature activation+0.293
sport
Token sport
Feature activation+0.000
ier
Tokenier
Feature activation+2.559
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
powerful
Token powerful
Feature activation+2.563
variant
Token variant
Feature activation+0.000
of
Token of
Feature activation+1.092
the
Token the
Feature activation+1.392
BMW
Token BMW
Feature activation+0.000
i
Token i
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
.
Token.
Feature activation+1.954
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.574
What
TokenWhat
Feature activation+0.798
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
torque
Token torque
Feature activation+0.000
of
Token of
Feature activation+0.000
269
Token 269
Feature activation+0.000
NM
Token NM
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+2.634
BMW
Token BMW
Feature activation+0.194
i
Token i
Feature activation+0.000
3
Token3
Feature activation+1.006
s
Tokens
Feature activation+0.356
acceler
Token acceler
Feature activation+0.000
later
Token later
Feature activation+0.649
Taliban
Token Taliban
Feature activation+0.000
(
Token (
Feature activation+0.216
light
Tokenlight
Feature activation+0.000
green
Token green
Feature activation+0.000
).
Token).
Feature activation+2.709
Ċ
TokenĊ
Feature activation+1.106
Ċ
TokenĊ
Feature activation+1.256
After
TokenAfter
Feature activation+1.252
the
Token the
Feature activation+0.000
fall
Token fall
Feature activation+0.086
i
Token i
Feature activation+0.000
3
Token3
Feature activation+0.814
s
Tokens
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.680
The
TokenThe
Feature activation+2.792
new
Token new
Feature activation+2.390
BMW
Token BMW
Feature activation+0.526
i
Token i
Feature activation+0.000
3
Token3
Feature activation+1.258
s
Tokens
Feature activation+0.302

INTERVAL 1.850 - 2.466
CONTAINS 0.006%

the
Token the
Feature activation+1.392
BMW
Token BMW
Feature activation+0.000
i
Token i
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.050
The
Token The
Feature activation+2.129
first
Token first
Feature activation+3.714
ever
Token ever
Feature activation+2.279
BMW
Token BMW
Feature activation+0.578
i
Token i
Feature activation+0.247
3
Token3
Feature activation+0.900
games
Token games
Feature activation+0.000
.
Token.
Feature activation+1.175
on
Tokenon
Feature activation+0.000
.
Token.
Feature activation+0.063
net
Tokennet
Feature activation+0.000
,
Token,
Feature activation+1.948
and
Token and
Feature activation+2.644
indeed
Token indeed
Feature activation+1.611
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.378
sleep
Token sleep
Feature activation+0.000
centers
Token centers
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
.
Token.
Feature activation+1.954
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.574
What
TokenWhat
Feature activation+0.798
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
-
Token-
Feature activation+0.000
P
TokenP
Feature activation+0.000
atel
Tokenatel
Feature activation+0.000
,
Token,
Feature activation+1.199
founder
Token founder
Feature activation+1.221
of
Token of
Feature activation+2.325
Global
Token Global
Feature activation+0.809
Life
Token Life
Feature activation+0.057
Enterprises
Token Enterprises
Feature activation+3.266
,
Token,
Feature activation+0.455
who
Token who
Feature activation+0.000
same
Token same
Feature activation+0.393
sandbox
Token sandbox
Feature activation+0.000
ed
Tokened
Feature activation+0.000
approach
Token approach
Feature activation+0.000
to
Token to
Feature activation+1.699
running
Token running
Feature activation+2.105
HTML
Token HTML
Feature activation+0.000
5
Token5
Feature activation+0.000
apps
Token apps
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000

INTERVAL 1.233 - 1.850
CONTAINS 0.012%

and
Token and
Feature activation+1.009
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
."
Token."
Feature activation+1.176
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.622
Attempts
TokenAttempts
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.988
Anthony
Token Anthony
Feature activation+0.000
through
Token through
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
powerful
Token powerful
Feature activation+2.563
variant
Token variant
Feature activation+0.000
of
Token of
Feature activation+1.092
the
Token the
Feature activation+1.392
BMW
Token BMW
Feature activation+0.000
i
Token i
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.050
The
Token The
Feature activation+2.129
ae
Tokenae
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.545
Now
Token Now
Feature activation+1.252
,
Token,
Feature activation+1.323
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
read
Token read
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
i
Token i
Feature activation+0.000
Heart
TokenHeart
Feature activation+0.000
Radio
TokenRadio
Feature activation+0.000
,
Token,
Feature activation+1.426
Clear
Token Clear
Feature activation+0.000
Channel
Token Channel
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.548
.
Token.
Feature activation+0.791
They
Token They
Feature activation+0.000
finally
Token finally
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+1.405
embarrassed
Token embarrassed
Feature activation+1.819
,
Token,
Feature activation+0.225
with
Token with
Feature activation+0.000
bruised
Token bruised
Feature activation+0.000
and
Token and
Feature activation+0.000
bright
Token bright
Feature activation+0.000

INTERVAL 0.617 - 1.233
CONTAINS 0.022%

ve
Tokenve
Feature activation+0.000
ils
Tokenils
Feature activation+2.189
New
Token New
Feature activation+1.709
i
Token i
Feature activation+0.000
3
Token3
Feature activation+0.533
S
TokenS
Feature activation+0.959
Electric
Token Electric
Feature activation+0.191
Sports
Token Sports
Feature activation+0.000
Edition
Token Edition
Feature activation+0.094
Ahead
Token Ahead
Feature activation+0.000
Of
Token Of
Feature activation+0.718
s
Tokens
Feature activation+0.000
then
Token then
Feature activation+0.000
turning
Token turning
Feature activation+0.000
on
Token on
Feature activation+0.000
me
Token me
Feature activation+0.000
made
Token made
Feature activation+0.651
things
Token things
Feature activation+0.000
abundantly
Token abundantly
Feature activation+0.000
clear
Token clear
Feature activation+0.651
to
Token to
Feature activation+0.526
me
Token me
Feature activation+0.610
is
Token is
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
memory
Token memory
Feature activation+0.000
of
Token of
Feature activation+0.993
colleague
Token colleague
Feature activation+0.032
and
Token and
Feature activation+0.000
friend
Token friend
Feature activation+0.777
Professor
Token Professor
Feature activation+0.000
W
Token W
Feature activation+0.000
true
Token true
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
i
Token i
Feature activation+0.000
assure
Token assure
Feature activation+0.000
you
Token you
Feature activation+0.653
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.454
There
Token There
Feature activation+0.000
i
Token i
Feature activation+0.000
think
Token think
Feature activation+0.627
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
recognize
Token recognize
Feature activation+0.000
that
Token that
Feature activation+0.632
after
Token after
Feature activation+0.559
a
Token a
Feature activation+0.000
while
Token while
Feature activation+0.671
the
Token the
Feature activation+0.000
word
Token word
Feature activation+0.000

INTERVAL 0.000 - 0.617
CONTAINS 99.955%

ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
know
Token know
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
allegation
Token allegation
Feature activation+0.000
by
Token by
Feature activation+0.000
saying
Token saying
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
Im
TokenIm
Feature activation+0.000
ran
Tokenran
Feature activation+0.000
Khan
Token Khan
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
get
Token get
Feature activation+0.000
good
Token good
Feature activation+0.000
its
Token its
Feature activation+0.000
bailout
Token bailout
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Following
TokenFollowing
Feature activation+0.000
the
Token the
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
pri
Tokenpri
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
off
Token off
Feature activation+0.000
shoot
Tokenshoot
Feature activation+0.000
of
Token of
Feature activation+0.000
Occupy
Token Occupy
Feature activation+0.000
Wall
Token Wall
Feature activation+0.000
Street
Token Street
Feature activation+0.000
called
Token called
Feature activation+0.000
Occupy
Token Occupy
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 H11.4: (feature 10669)

TOP ACTIVATIONS
MAX = 7.554

literature
Token literature
Feature activation+0.000
,
Token,
Feature activation+1.862
our
Token our
Feature activation+0.000
previous
Token previous
Feature activation+0.000
work
Token work
Feature activation+0.000
(
Token (
Feature activation+7.554
Mont
TokenMont
Feature activation+0.000
al
Tokenal
Feature activation+0.000
vo
Tokenvo
Feature activation+0.000
-
Token-
Feature activation+1.334
Or
TokenOr
Feature activation+0.000
Airport
Token Airport
Feature activation+0.000
82
Token 82
Feature activation+0.000
U
Token U
Feature activation+0.033
pt
Tokenpt
Feature activation+0.000
own
Tokenown
Feature activation+2.535
81
Token 81
Feature activation+6.370
76
Token 76
Feature activation+4.096
Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+3.190
80
Token 80
Feature activation+5.863
Park
Token Park
Feature activation+0.000
during
Token during
Feature activation+0.000
one
Token one
Feature activation+0.000
confrontation
Token confrontation
Feature activation+0.000
.
Token.
Feature activation+3.963
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.056
During
TokenDuring
Feature activation+3.037
a
Token a
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+1.880
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
happened
Token happened
Feature activation+0.000
if
Token if
Feature activation+6.033
the
Token the
Feature activation+0.000
board
Token board
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
own
Tokenown
Feature activation+2.535
81
Token 81
Feature activation+6.370
76
Token 76
Feature activation+4.096
Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+3.190
80
Token 80
Feature activation+5.863
Park
Token Park
Feature activation+0.000
81
Token 81
Feature activation+4.781
82
Token 82
Feature activation+2.739
80
Token 80
Feature activation+3.188
80
Token 80
Feature activation+3.269
m
Tokenm
Feature activation+0.000
arsh
Tokenarsh
Feature activation+0.000
Prison
Token Prison
Feature activation+0.000
.
Token.
Feature activation+2.680
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.767
Hor
TokenHor
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+1.546
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.666
Now
TokenNow
Feature activation+5.615
due
Token due
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
th
Tokenth
Feature activation+0.000
game
Token game
Feature activation+1.128
for
Token for
Feature activation+3.809
the
Token the
Feature activation+2.128
longest
Token longest
Feature activation+0.000
time
Token time
Feature activation+0.173
and
Token and
Feature activation+5.406
featured
Token featured
Feature activation+2.494
a
Token a
Feature activation+0.349
final
Token final
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+2.696
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.143
an
Token an
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
picture
Token picture
Feature activation+0.000
of
Token of
Feature activation+5.266
don
Token don
Feature activation+0.000
uts
Tokenuts
Feature activation+0.000
.
Token.
Feature activation+1.380
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.506
urine
Token urine
Feature activation+0.031
specimens
Token specimens
Feature activation+0.000
(
Token (
Feature activation+0.770
233
Token233
Feature activation+0.120
patients
Token patients
Feature activation+0.000
with
Token with
Feature activation+5.265
u
Token u
Feature activation+0.000
rol
Tokenrol
Feature activation+0.000
ogical
Tokenogical
Feature activation+3.722
chronic
Token chronic
Feature activation+2.898
pelvic
Token pelvic
Feature activation+0.000
fight
Token fight
Feature activation+4.006
huge
Token huge
Feature activation+2.081
waves
Token waves
Feature activation+0.000
of
Token of
Feature activation+1.407
monsters
Token monsters
Feature activation+0.000
until
Token until
Feature activation+5.177
the
Token the
Feature activation+1.736
boss
Token boss
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
,
Token,
Feature activation+0.000
take
Token take
Feature activation+0.392
managers
Token managers
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+3.271
them
Token them
Feature activation+0.000
know
Token know
Feature activation+4.981
they
Token they
Feature activation+0.000
had
Token had
Feature activation+1.691
to
Token to
Feature activation+0.000
give
Token give
Feature activation+4.681
the
Token the
Feature activation+0.412
10
Token10
Feature activation+0.000
,
Token,
Feature activation+0.000
610
Token610
Feature activation+0.000
per
Token per
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+4.961
non
Token non
Feature activation+0.000
-
Token-
Feature activation+1.248
resident
Tokenresident
Feature activation+1.588
,
Token,
Feature activation+1.277
$
Token $
Feature activation+0.000
U
Token U
Feature activation+0.000
WP
TokenWP
Feature activation+0.907
apps
Token apps
Feature activation+0.518
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+4.893
the
Token the
Feature activation+3.372
same
Token same
Feature activation+3.686
app
Token app
Feature activation+0.000
on
Token on
Feature activation+1.754
the
Token the
Feature activation+1.650
82
Token 82
Feature activation+2.739
80
Token 80
Feature activation+3.188
80
Token 80
Feature activation+3.269
80
Token 80
Feature activation+4.178
80
Token 80
Feature activation+4.726
80
Token 80
Feature activation+4.817
Lincoln
Token Lincoln
Feature activation+0.000
Park
Token Park
Feature activation+2.113
In
Token In
Feature activation+0.000
racially
Token racially
Feature activation+0.000
diverse
Token diverse
Feature activation+0.000
76
Token 76
Feature activation+4.096
Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+3.190
80
Token 80
Feature activation+5.863
Park
Token Park
Feature activation+0.000
81
Token 81
Feature activation+4.781
82
Token 82
Feature activation+2.739
80
Token 80
Feature activation+3.188
80
Token 80
Feature activation+3.269
80
Token 80
Feature activation+4.178
80
Token 80
Feature activation+4.726
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
happened
Token happened
Feature activation+0.000
if
Token if
Feature activation+4.761
we
Token we
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.250
backend
Token backend
Feature activation+0.000
system
Token system
Feature activation+0.288
,
Token,
Feature activation+1.047
with
Token with
Feature activation+4.754
differing
Token differing
Feature activation+0.270
user
Token user
Feature activation+0.000
interfaces
Token interfaces
Feature activation+0.000
and
Token and
Feature activation+0.521
capabilities
Token capabilities
Feature activation+0.000
and
Token and
Feature activation+1.149
Don
Token Don
Feature activation+0.000
Cannon
Token Cannon
Feature activation+0.000
,
Token,
Feature activation+0.405
two
Token two
Feature activation+0.000
of
Token of
Feature activation+4.742
U
Token U
Feature activation+0.000
zi
Tokenzi
Feature activation+0.000
's
Token's
Feature activation+0.000
managers
Token managers
Feature activation+0.000
,
Token,
Feature activation+0.000
champion
Token champion
Feature activation+0.727
spawns
Token spawns
Feature activation+0.694
were
Token were
Feature activation+0.204
the
Token the
Feature activation+0.513
meat
Token meat
Feature activation+0.000
of
Token of
Feature activation+4.741
the
Token the
Feature activation+3.362
game
Token game
Feature activation+1.128
for
Token for
Feature activation+3.809
the
Token the
Feature activation+2.128
longest
Token longest
Feature activation+0.000

Top DFA by src position
MAX = 7.518

and
Token and
Feature activation+0.004
Top resid features:
older
Token older
Feature activation+0.004
Top resid features:
patient
Token patient
Feature activation+0.006
Top resid features:
populations
Token populations
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.073
Top resid features:
U
TokenU
Feature activation+4.310
Top resid features:
ch
Tokench
Feature activation+0.023
Top resid features:
ida
Tokenida
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
M
Token M
Feature activation-0.001
Top resid features:
amo
Tokenamo
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
H
TokenH
Feature activation-0.005
Top resid features:
are
Tokenare
Feature activation+0.034
Top resid features:
Airport
Token Airport
Feature activation+0.064
Top resid features:
82
Token 82
Feature activation+0.038
Top resid features:
U
Token U
Feature activation+6.658
Top resid features:
pt
Tokenpt
Feature activation+0.049
Top resid features:
own
Tokenown
Feature activation+0.058
Top resid features:
81
Token 81
Feature activation+0.038
Top resid features:
76
Token 76
Feature activation+0.000
Top resid features:
Port
Token Port
Feature activation+0.000
Top resid features:
uses
Token uses
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
name
Token name
Feature activation+0.010
Top resid features:
Jama
Token Jama
Feature activation-0.102
Top resid features:
al
Tokenal
Feature activation+0.008
Top resid features:
U
Token U
Feature activation+7.491
Top resid features:
dd
Tokendd
Feature activation+0.006
Top resid features:
in
Tokenin
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
admitted
Token admitted
Feature activation-0.010
Top resid features:
assaulting
Token assaulting
Feature activation+0.009
Top resid features:
spring
Token spring
Feature activation+0.011
Top resid features:
under
Token under
Feature activation+0.033
Top resid features:
president
Token president
Feature activation+0.017
Top resid features:
Mas
Token Mas
Feature activation-0.101
Top resid features:
ai
Tokenai
Feature activation+0.008
Top resid features:
U
Token U
Feature activation+7.518
Top resid features:
j
Tokenj
Feature activation+0.060
Top resid features:
iri
Tokeniri
Feature activation+0.029
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.009
Top resid features:
yet
Token yet
Feature activation-0.003
Top resid features:
another
Token another
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.031
Top resid features:
H
TokenH
Feature activation-0.005
Top resid features:
are
Tokenare
Feature activation+0.031
Top resid features:
Airport
Token Airport
Feature activation+0.051
Top resid features:
82
Token 82
Feature activation+0.044
Top resid features:
U
Token U
Feature activation+6.344
Top resid features:
pt
Tokenpt
Feature activation+0.040
Top resid features:
own
Tokenown
Feature activation+0.041
Top resid features:
81
Token 81
Feature activation+0.029
Top resid features:
76
Token 76
Feature activation+0.015
Top resid features:
Port
Token Port
Feature activation-0.077
Top resid features:
uses
Token uses
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
name
Token name
Feature activation+0.007
Top resid features:
Jama
Token Jama
Feature activation-0.065
Top resid features:
al
Tokenal
Feature activation+0.005
Top resid features:
U
Token U
Feature activation+7.026
Top resid features:
dd
Tokendd
Feature activation+0.006
Top resid features:
in
Tokenin
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
admitted
Token admitted
Feature activation-0.005
Top resid features:
assaulting
Token assaulting
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
who
Token who
Feature activation+0.007
Top resid features:
would
Token would
Feature activation+0.014
Top resid features:
have
Token have
Feature activation+0.004
Top resid features:
thought
Token thought
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+6.880
Top resid features:
bi
Tokenbi
Feature activation+0.017
Top resid features:
could
Token could
Feature activation+0.005
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
ones
Token ones
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.069
Top resid features:
of
Token of
Feature activation+0.028
Top resid features:
everything
Token everything
Feature activation+0.019
Top resid features:
that
Token that
Feature activation+0.044
Top resid features:
U
Token U
Feature activation+5.969
Top resid features:
O
TokenO
Feature activation+0.237
Top resid features:
offered
Token offered
Feature activation+0.040
Top resid features:
?
Token?
Feature activation+0.089
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
Ċ
TokenĊ
Feature activation+0.106
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
did
Token did
Feature activation+0.001
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
see
Token see
Feature activation+0.007
Top resid features:
U
Token U
Feature activation+6.000
Top resid features:
nexpected
Tokennexpected
Feature activation+0.010
Top resid features:
T
Token T
Feature activation+0.009
Top resid features:
ender
Tokenender
Feature activation+0.016
Top resid features:
ness
Tokenness
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
culture
Token culture
Feature activation+0.007
Top resid features:
negative
Token negative
Feature activation+0.040
Top resid features:
female
Token female
Feature activation+0.052
Top resid features:
patients
Token patients
Feature activation+0.008
Top resid features:
with
Token with
Feature activation+0.032
Top resid features:
u
Token u
Feature activation+5.187
Top resid features:
rol
Tokenrol
Feature activation+0.016
Top resid features:
ogical
Tokenogical
Feature activation+0.010
Top resid features:
chronic
Token chronic
Feature activation+0.024
Top resid features:
pelvic
Token pelvic
Feature activation+0.010
Top resid features:
pain
Token pain
Feature activation+0.036
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.057
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
everything
Token everything
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
U
Token U
Feature activation+6.190
Top resid features:
O
TokenO
Feature activation+0.145
Top resid features:
offered
Token offered
Feature activation+0.007
Top resid features:
?
Token?
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
Don
Token Don
Feature activation+0.046
Top resid features:
Cannon
Token Cannon
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
U
Token U
Feature activation+4.164
Top resid features:
zi
Tokenzi
Feature activation+0.003
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
managers
Token managers
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
2014
Token 2014
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.086
Top resid features:
Resident
Token Resident
Feature activation+0.175
Top resid features:
tuition
Token tuition
Feature activation+0.041
Top resid features:
at
Token at
Feature activation+0.023
Top resid features:
U
Token U
Feature activation+1.774
Top resid features:
H
TokenH
Feature activation+0.034
Top resid features:
Man
Token Man
Feature activation+0.000
Top resid features:
oa
Tokenoa
Feature activation+0.018
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
at
Token at
Feature activation+0.011
Top resid features:
The
TokenThe
Feature activation+0.041
Top resid features:
also
Token also
Feature activation+0.011
Top resid features:
describe
Token describe
Feature activation+0.030
Top resid features:
how
Token how
Feature activation+0.025
Top resid features:
using
Token using
Feature activation+0.039
Top resid features:
U
Token U
Feature activation+5.866
Top resid features:
WP
TokenWP
Feature activation+0.148
Top resid features:
apps
Token apps
Feature activation+0.009
Top resid features:
they
Token they
Feature activation+0.034
Top resid features:
can
Token can
Feature activation+0.017
Top resid features:
use
Token use
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
H
TokenH
Feature activation-0.004
Top resid features:
are
Tokenare
Feature activation+0.013
Top resid features:
Airport
Token Airport
Feature activation+0.028
Top resid features:
82
Token 82
Feature activation+0.011
Top resid features:
U
Token U
Feature activation+5.629
Top resid features:
pt
Tokenpt
Feature activation+0.054
Top resid features:
own
Tokenown
Feature activation+0.027
Top resid features:
81
Token 81
Feature activation+0.006
Top resid features:
76
Token 76
Feature activation-0.001
Top resid features:
Port
Token Port
Feature activation-0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.022
Top resid features:
H
TokenH
Feature activation-0.001
Top resid features:
are
Tokenare
Feature activation+0.018
Top resid features:
Airport
Token Airport
Feature activation+0.065
Top resid features:
82
Token 82
Feature activation+0.010
Top resid features:
U
Token U
Feature activation+5.722
Top resid features:
pt
Tokenpt
Feature activation+0.072
Top resid features:
own
Tokenown
Feature activation+0.051
Top resid features:
81
Token 81
Feature activation+0.016
Top resid features:
76
Token 76
Feature activation+0.019
Top resid features:
Port
Token Port
Feature activation-0.082
Top resid features:
spring
Token spring
Feature activation+0.005
Top resid features:
under
Token under
Feature activation+0.023
Top resid features:
president
Token president
Feature activation+0.017
Top resid features:
Mas
Token Mas
Feature activation-0.095
Top resid features:
ai
Tokenai
Feature activation+0.005
Top resid features:
U
Token U
Feature activation+6.251
Top resid features:
j
Tokenj
Feature activation+0.058
Top resid features:
iri
Tokeniri
Feature activation+0.018
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.007
Top resid features:
yet
Token yet
Feature activation-0.003
Top resid features:
another
Token another
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation+0.029
Top resid features:
also
Token also
Feature activation+0.011
Top resid features:
describe
Token describe
Feature activation+0.021
Top resid features:
how
Token how
Feature activation+0.016
Top resid features:
using
Token using
Feature activation+0.034
Top resid features:
U
Token U
Feature activation+5.818
Top resid features:
WP
TokenWP
Feature activation+0.107
Top resid features:
apps
Token apps
Feature activation+0.007
Top resid features:
they
Token they
Feature activation+0.033
Top resid features:
can
Token can
Feature activation+0.015
Top resid features:
use
Token use
Feature activation+0.034
Top resid features:
finished
Token finished
Feature activation+0.006
Top resid features:
track
Token track
Feature activation+0.016
Top resid features:
three
Token three
Feature activation-0.000
Top resid features:
weeks
Token weeks
Feature activation+0.001
Top resid features:
before
Token before
Feature activation+0.012
Top resid features:
U
Token U
Feature activation+5.918
Top resid features:
zi
Tokenzi
Feature activation+0.010
Top resid features:
released
Token released
Feature activation+0.020
Top resid features:
it
Token it
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.066
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
everything
Token everything
Feature activation+0.041
Top resid features:
that
Token that
Feature activation+0.068
Top resid features:
U
Token U
Feature activation+4.973
Top resid features:
O
TokenO
Feature activation+0.559
Top resid features:
offered
Token offered
Feature activation+0.036
Top resid features:
?
Token?
Feature activation+0.100
Top resid features:
Ċ
TokenĊ
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.141
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.05

Head 3: 0.05

Head 4: 0.38

Head 5: 0.04

Head 6: 0.07

Head 7: 0.07

Head 8: 0.07

Head 9: 0.05

Head 10: 0.07

Head 11: 0.04

Positive logits

U8.08

U6.50

u5.29

UU3.46

Ug3.21

United3.18

u2.74

UA2.64

UD2.61

UF2.58

UM2.56

Us2.50

United2.45

UNITED2.44

UW2.41

UCH2.39

UR2.32

uin2.27

UC2.25

UMP2.23

Negative logits

schild-2.14

reau-2.09

*/(-2.06

ティ-2.05

esp-2.03

gently-2.00

"]=>-1.95

secut-1.92

rats-1.92

usting-1.89

paio-1.88

覚醒-1.88

ウス-1.88

emale-1.87

-1.86

riots-1.85

olean-1.84

mire-1.84

armoured-1.80

kees-1.79

INTERVAL 6.799 - 7.554
CONTAINS 0.000%

literature
Token literature
Feature activation+0.000
,
Token,
Feature activation+1.862
our
Token our
Feature activation+0.000
previous
Token previous
Feature activation+0.000
work
Token work
Feature activation+0.000
(
Token (
Feature activation+7.554
Mont
TokenMont
Feature activation+0.000
al
Tokenal
Feature activation+0.000
vo
Tokenvo
Feature activation+0.000
-
Token-
Feature activation+1.334
Or
TokenOr
Feature activation+0.000

INTERVAL 6.043 - 6.799
CONTAINS 0.000%

Airport
Token Airport
Feature activation+0.000
82
Token 82
Feature activation+0.000
U
Token U
Feature activation+0.033
pt
Tokenpt
Feature activation+0.000
own
Tokenown
Feature activation+2.535
81
Token 81
Feature activation+6.370
76
Token 76
Feature activation+4.096
Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+3.190
80
Token 80
Feature activation+5.863
Park
Token Park
Feature activation+0.000
during
Token during
Feature activation+0.000
one
Token one
Feature activation+0.000
confrontation
Token confrontation
Feature activation+0.000
.
Token.
Feature activation+3.963
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.056
During
TokenDuring
Feature activation+3.037
a
Token a
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 5.288 - 6.043
CONTAINS 0.001%

of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+1.546
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.666
Now
TokenNow
Feature activation+5.615
due
Token due
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
th
Tokenth
Feature activation+0.000
own
Tokenown
Feature activation+2.535
81
Token 81
Feature activation+6.370
76
Token 76
Feature activation+4.096
Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+3.190
80
Token 80
Feature activation+5.863
Park
Token Park
Feature activation+0.000
81
Token 81
Feature activation+4.781
82
Token 82
Feature activation+2.739
80
Token 80
Feature activation+3.188
80
Token 80
Feature activation+3.269
of
Token of
Feature activation+1.880
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
happened
Token happened
Feature activation+0.000
if
Token if
Feature activation+6.033
the
Token the
Feature activation+0.000
board
Token board
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
game
Token game
Feature activation+1.128
for
Token for
Feature activation+3.809
the
Token the
Feature activation+2.128
longest
Token longest
Feature activation+0.000
time
Token time
Feature activation+0.173
and
Token and
Feature activation+5.406
featured
Token featured
Feature activation+2.494
a
Token a
Feature activation+0.349
final
Token final
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+2.696
m
Tokenm
Feature activation+0.000
arsh
Tokenarsh
Feature activation+0.000
Prison
Token Prison
Feature activation+0.000
.
Token.
Feature activation+2.680
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.767
Hor
TokenHor
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000

INTERVAL 4.532 - 5.288
CONTAINS 0.002%

secretly
Token secretly
Feature activation+0.000
in
Token in
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
caves
Token caves
Feature activation+0.000
.
Token.
Feature activation+1.711
So
Token So
Feature activation+4.658
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.855
bliss
Token bliss
Feature activation+0.000
of
Token of
Feature activation+0.630
the
Token the
Feature activation+0.000
champion
Token champion
Feature activation+0.727
spawns
Token spawns
Feature activation+0.694
were
Token were
Feature activation+0.204
the
Token the
Feature activation+0.513
meat
Token meat
Feature activation+0.000
of
Token of
Feature activation+4.741
the
Token the
Feature activation+3.362
game
Token game
Feature activation+1.128
for
Token for
Feature activation+3.809
the
Token the
Feature activation+2.128
longest
Token longest
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.000
delay
Token delay
Feature activation+1.012
the
Token the
Feature activation+0.406
PC
Token PC
Feature activation+0.550
version
Token version
Feature activation+0.000
of
Token of
Feature activation+4.603
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
ele
Token ele
Feature activation+0.000
t
Tokent
Feature activation+0.303
prepared
Token prepared
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+4.694
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
million
Token million
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.977
a
Token a
Feature activation+1.014
similar
Token similar
Feature activation+2.492
Reaper
Token Reaper
Feature activation+4.588
U
Token U
Feature activation+0.000
AV
TokenAV
Feature activation+0.572
made
Token made
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.777 - 4.532
CONTAINS 0.004%

of
Token of
Feature activation+0.000
U
Token U
Feature activation+0.000
mber
Tokenmber
Feature activation+0.000
to
Tokento
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
where
Token where
Feature activation+4.464
Gand
Token Gand
Feature activation+0.000
olf
Tokenolf
Feature activation+0.000
ini
Tokenini
Feature activation+0.000
was
Token was
Feature activation+0.000
pronounced
Token pronounced
Feature activation+0.000
Cart
Token Cart
Feature activation+0.000
el
Tokenel
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
.
Token.
Feature activation+1.237
And
Token And
Feature activation+4.187
others
Token others
Feature activation+0.000
of
Token of
Feature activation+0.916
their
Token their
Feature activation+0.000
games
Token games
Feature activation+0.000
in
Token in
Feature activation+0.000
-
Token-
Feature activation+0.684
239
Token239
Feature activation+1.230
cycle
Token cycle
Feature activation+0.146
,
Token,
Feature activation+0.884
Th
Token Th
Feature activation+0.000
-
Token-
Feature activation+4.374
232
Token232
Feature activation+2.386
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
in
Token in
Feature activation+0.512
Park
Token Park
Feature activation+0.000
81
Token 81
Feature activation+4.781
82
Token 82
Feature activation+2.739
80
Token 80
Feature activation+3.188
80
Token 80
Feature activation+3.269
80
Token 80
Feature activation+4.178
80
Token 80
Feature activation+4.726
80
Token 80
Feature activation+4.817
Lincoln
Token Lincoln
Feature activation+0.000
Park
Token Park
Feature activation+2.113
In
Token In
Feature activation+0.000
of
Token of
Feature activation+0.000
Regional
Token Regional
Feature activation+0.000
Technology
Token Technology
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Centers
Token Centers
Feature activation+0.000
.
Token.
Feature activation+4.114
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.574
Ban
TokenBan
Feature activation+0.000
er
Tokener
Feature activation+0.000
jee
Tokenjee
Feature activation+0.000

INTERVAL 3.022 - 3.777
CONTAINS 0.008%

between
Token between
Feature activation+2.144
flare
Token flare
Feature activation+0.755
and
Token and
Feature activation+4.046
non
Token non
Feature activation+3.970
fl
Tokenfl
Feature activation+0.000
are
Tokenare
Feature activation+3.593
groups
Token groups
Feature activation+0.000
for
Token for
Feature activation+2.677
presence
Token presence
Feature activation+0.000
or
Token or
Feature activation+0.000
number
Token number
Feature activation+0.000
after
Token after
Feature activation+3.868
it
Token it
Feature activation+0.000
dropped
Token dropped
Feature activation+1.354
,
Token,
Feature activation+2.703
TM
Token TM
Feature activation+0.000
knew
Token knew
Feature activation+3.257
the
Token the
Feature activation+0.000
song
Token song
Feature activation+0.165
was
Token was
Feature activation+0.000
special
Token special
Feature activation+0.000
.
Token.
Feature activation+1.993
of
Token of
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
end
Tokenend
Feature activation+0.740
items
Token items
Feature activation+0.000
.
Token.
Feature activation+3.397
The
Token The
Feature activation+1.800
main
Token main
Feature activation+0.033
sought
Token sought
Feature activation+0.000
items
Token items
Feature activation+0.474
were
Token were
Feature activation+0.000
faith
Token faith
Feature activation+0.000
,
Token,
Feature activation+2.958
Tan
Token Tan
Feature activation+0.000
en
Tokenen
Feature activation+0.000
baum
Tokenbaum
Feature activation+0.000
and
Token and
Feature activation+3.148
ML
Token ML
Feature activation+0.000
SE
TokenSE
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.286
somehow
Token somehow
Feature activation+1.118
,
Token,
Feature activation+1.231
even
Token even
Feature activation+0.224
worse
Token worse
Feature activation+0.000
than
Token than
Feature activation+3.430
Labour
Token Labour
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
media
Token media
Feature activation+0.000

INTERVAL 2.266 - 3.022
CONTAINS 0.013%

Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+3.190
80
Token 80
Feature activation+5.863
Park
Token Park
Feature activation+0.000
81
Token 81
Feature activation+4.781
82
Token 82
Feature activation+2.739
80
Token 80
Feature activation+3.188
80
Token 80
Feature activation+3.269
80
Token 80
Feature activation+4.178
80
Token 80
Feature activation+4.726
80
Token 80
Feature activation+4.817
Technology
Token Technology
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Centers
Token Centers
Feature activation+0.000
.
Token.
Feature activation+4.114
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.574
Ban
TokenBan
Feature activation+0.000
er
Tokener
Feature activation+0.000
jee
Tokenjee
Feature activation+0.000
,
Token,
Feature activation+0.884
a
Token a
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
shipped
Token shipped
Feature activation+0.000
with
Token with
Feature activation+1.013
every
Token every
Feature activation+1.951
single
Token single
Feature activation+2.337
pledge
Token pledge
Feature activation+0.000
order
Token order
Feature activation+0.000
$
Token $
Feature activation+0.000
35
Token35
Feature activation+0.000
and
Token and
Feature activation+0.000
reports
Token reports
Feature activation+0.000
.
Token.
Feature activation+2.783
On
Token On
Feature activation+0.940
a
Token a
Feature activation+2.496
bigger
Token bigger
Feature activation+0.000
screen
Token screen
Feature activation+2.860
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
be
Token be
Feature activation+0.000
April
Token April
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.050
-
Token-
Feature activation+2.294
Ward
TokenWard
Feature activation+0.000
4
Token 4
Feature activation+0.009
council
Token council
Feature activation+0.000
member
Token member
Feature activation+0.000
Bowser
Token Bowser
Feature activation+0.000

INTERVAL 1.511 - 2.266
CONTAINS 0.033%

Thanks
Token Thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
those
Token those
Feature activation+0.229
who
Token who
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+1.554
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
.
Token.
Feature activation+0.000
K
Token K
Feature activation+0.000
Generations
Token Generations
Feature activation+0.000
Gal
Token Gal
Feature activation+0.000
a
Tokena
Feature activation+0.000
.
Token.
Feature activation+1.663
Ċ
TokenĊ
Feature activation+0.732
Ċ
TokenĊ
Feature activation+1.824
Day
TokenDay
Feature activation+0.000
Seven
Token Seven
Feature activation+0.319
(
Token (
Feature activation+0.285
Sunday
TokenSunday
Feature activation+0.000
6
Token 6
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.340
Soy
Token Soy
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
and
Token and
Feature activation+1.705
Mol
Token Mol
Feature activation+0.000
ni
Tokenni
Feature activation+0.000
ya
Tokenya
Feature activation+0.000
variants
Token variants
Feature activation+0.000
then
Token then
Feature activation+0.000
being
Token being
Feature activation+0.000
declared
Token declared
Feature activation+0.047
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
compliance
Token compliance
Feature activation+0.000
with
Token with
Feature activation+1.746
federal
Token federal
Feature activation+0.000
Clean
Token Clean
Feature activation+0.000
Air
Token Air
Feature activation+0.000
Act
Token Act
Feature activation+0.000
limits
Token limits
Feature activation+0.000
organ
Tokenorgan
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
species
Token species
Feature activation+0.000
.
Token.
Feature activation+3.268
Differences
Token Differences
Feature activation+0.000
between
Token between
Feature activation+2.144
flare
Token flare
Feature activation+0.755
and
Token and
Feature activation+4.046
non
Token non
Feature activation+3.970
fl
Tokenfl
Feature activation+0.000
are
Tokenare
Feature activation+3.593

INTERVAL 0.755 - 1.511
CONTAINS 0.063%

a
Token a
Feature activation+0.000
map
Token map
Feature activation+0.000
of
Token of
Feature activation+2.318
the
Token the
Feature activation+1.212
world
Token world
Feature activation+0.286
inside
Token inside
Feature activation+1.508
the
Token the
Feature activation+4.090
Quantum
Token Quantum
Feature activation+0.293
RPG
Token RPG
Feature activation+0.323
hard
Token hard
Feature activation+0.000
cover
Tokencover
Feature activation+0.579
.
Token.
Feature activation+1.939
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
write
Token write
Feature activation+1.831
!
Token !
Feature activation+0.371
!
Token !
Feature activation+0.885
testing
Token testing
Feature activation+0.000
the
Token the
Feature activation+0.440
UK
Token UK
Feature activation+0.000
pipeline
Token pipeline
Feature activation+0.000
:
Token :
Feature activation+1.670
when
Token when
Feature activation+0.212
both
Token both
Feature activation+0.000
a
Token a
Feature activation+0.000
corner
Token corner
Feature activation+0.000
of
Token of
Feature activation+1.684
the
Token the
Feature activation+0.929
old
Token old
Feature activation+2.054
City
Token City
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
and
Token and
Feature activation+1.233
excessive
Token excessive
Feature activation+0.000
and
Token and
Feature activation+0.000
disproportionate
Token disproportionate
Feature activation+0.000
force
Token force
Feature activation+0.000
against
Token against
Feature activation+2.073
the
Token the
Feature activation+0.865
fl
Token fl
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
illa
Tokenilla
Feature activation+0.000
passengers
Token passengers
Feature activation+0.000
.
Token.
Feature activation+1.172
the
Token the
Feature activation+0.929
old
Token old
Feature activation+2.054
City
Token City
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
and
Token and
Feature activation+1.233
part
Token part
Feature activation+0.000
of
Token of
Feature activation+1.982
the
Token the
Feature activation+1.850
cemetery
Token cemetery
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 0.000 - 0.755
CONTAINS 99.877%

ed
Tokened
Feature activation+0.000
HERO
Token HERO
Feature activation+0.000
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
âĢĶ-
TokenâĢĶ-
Feature activation+0.000
4
Token4
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+0.000
B
Token B
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
are
Token are
Feature activation+0.000
extremely
Token extremely
Feature activation+0.000
sick
Token sick
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
dist
Token dist
Feature activation+0.000
em
Tokenem
Feature activation+0.000
per
Tokenper
Feature activation+0.000
know
Token know
Feature activation+0.000
what
Token what
Feature activation+0.000
desperation
Token desperation
Feature activation+0.000
is
Token is
Feature activation+0.000
until
Token until
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
move
Token move
Feature activation+0.000
to
Token to
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
Nor
Token Nor
Feature activation+0.000
walk
Tokenwalk
Feature activation+0.000
,
Token,
Feature activation+0.000
Conn
Token Conn
Feature activation+0.000
.,
Token.,
Feature activation+0.000
or
Token or
Feature activation+0.000
other
Token other
Feature activation+0.000
GE
Token GE
Feature activation+0.000
asked
Token asked
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
You
TokenYou
Feature activation+0.000
still
Token still
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
Simon
Token Simon
Feature activation+0.000
thing
Token thing
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H11.4: (feature 1299)

TOP ACTIVATIONS
MAX = 5.020

of
Token of
Feature activation+2.404
months
Token months
Feature activation+0.000
of
Token of
Feature activation+1.095
fighting
Token fighting
Feature activation+0.025
there
Token there
Feature activation+0.000
between
Token between
Feature activation+4.864
P
Token P
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
with
Token with
Feature activation+2.649
the
Token the
Feature activation+0.476
band
Token band
Feature activation+0.647
.
Token.
Feature activation+2.840
Soon
Token Soon
Feature activation+1.940
after
Token after
Feature activation+4.845
the
Token the
Feature activation+1.359
festival
Token festival
Feature activation+4.331
they
Token they
Feature activation+0.000
left
Token left
Feature activation+3.022
K
Token K
Feature activation+0.000
band
Token band
Feature activation+0.647
.
Token.
Feature activation+2.840
Soon
Token Soon
Feature activation+1.940
after
Token after
Feature activation+4.845
the
Token the
Feature activation+1.359
festival
Token festival
Feature activation+4.331
they
Token they
Feature activation+0.000
left
Token left
Feature activation+3.022
K
Token K
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
compared
Token compared
Feature activation+0.000
and
Token and
Feature activation+1.643
contrasted
Token contrasted
Feature activation+0.000
with
Token with
Feature activation+2.865
two
Token two
Feature activation+0.000
of
Token of
Feature activation+4.227
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
stars
Token stars
Feature activation+1.067
at
Token at
Feature activation+1.209
his
Token his
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.998
vowed
Token vowed
Feature activation+0.156
to
Token to
Feature activation+0.000
fight
Token fight
Feature activation+4.154
on
Token on
Feature activation+1.206
.
Token.
Feature activation+2.718
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.642
In
TokenIn
Feature activation+0.404
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
gu
Token gu
Feature activation+0.000
err
Tokenerr
Feature activation+0.000
illas
Tokenillas
Feature activation+0.000
and
Token and
Feature activation+4.115
government
Token government
Feature activation+0.000
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+2.977
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+3.886
what
Token what
Feature activation+3.564
Jennings
Token Jennings
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+4.069
P
Token P
Feature activation+0.000
onder
Tokenonder
Feature activation+0.000
after
Token after
Feature activation+2.676
his
Token his
Feature activation+0.000
years
Token years
Feature activation+0.000
ping
Tokenping
Feature activation+0.000
on
Token on
Feature activation+0.682
a
Token a
Feature activation+0.348
budget
Token budget
Feature activation+0.481
less
Token less
Feature activation+0.000
than
Token than
Feature activation+4.030
P
Token P
Feature activation+0.984
100
Token100
Feature activation+0.000
million
Token million
Feature activation+0.869
in
Token in
Feature activation+0.790
2014
Token 2014
Feature activation+1.149
.
Token.
Feature activation+1.596
It
Token It
Feature activation+0.000
was
Token was
Feature activation+1.022
the
Token the
Feature activation+0.505
first
Token first
Feature activation+1.362
time
Token time
Feature activation+4.030
the
Token the
Feature activation+1.249
group
Token group
Feature activation+0.000
had
Token had
Feature activation+0.000
experienced
Token experienced
Feature activation+0.016
such
Token such
Feature activation+0.000
in
Token in
Feature activation+1.037
Italian
Token Italian
Feature activation+0.000
football
Token football
Feature activation+0.000
and
Token and
Feature activation+2.079
one
Token one
Feature activation+0.204
of
Token of
Feature activation+3.949
the
Token the
Feature activation+0.000
longest
Token longest
Feature activation+0.000
in
Token in
Feature activation+0.636
Europe
Token Europe
Feature activation+0.000
.
Token.
Feature activation+2.519
"
Token"
Feature activation+2.097
Working
TokenWorking
Feature activation+0.000
together
Token together
Feature activation+1.539
is
Token is
Feature activation+0.881
good
Token good
Feature activation+0.000
for
Token for
Feature activation+3.893
both
Token both
Feature activation+1.798
parties
Token parties
Feature activation+0.000
.
Token.
Feature activation+2.455
Especially
Token Especially
Feature activation+2.208
now
Token now
Feature activation+2.724
comparison
Token comparison
Feature activation+0.000
.
Token.
Feature activation+2.388
Many
Token Many
Feature activation+0.210
want
Token want
Feature activation+2.617
to
Token to
Feature activation+0.000
know
Token know
Feature activation+3.886
what
Token what
Feature activation+3.564
Jennings
Token Jennings
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+4.069
P
Token P
Feature activation+0.000
Much
Token Much
Feature activation+0.000
like
Token like
Feature activation+2.018
other
Token other
Feature activation+2.983
gaming
Token gaming
Feature activation+0.325
options
Token options
Feature activation+0.026
,
Token,
Feature activation+3.886
p
Token p
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
isl
Tokenisl
Feature activation+0.000
ot
Tokenot
Feature activation+1.156
systems
Token systems
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
.
Token.
Feature activation+1.592
I
Token I
Feature activation+0.000
told
Token told
Feature activation+3.828
her
Token her
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
want
Token want
Feature activation+1.492
,
Token,
Feature activation+2.950
from
Token from
Feature activation+2.116
teammates
Token teammates
Feature activation+0.301
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+3.788
about
Token about
Feature activation+2.582
Fav
Token Fav
Feature activation+0.000
re
Tokenre
Feature activation+0.000
or
Token or
Feature activation+2.227
Rodgers
Token Rodgers
Feature activation+0.000
P
TokenP
Feature activation+0.826
(
Token(
Feature activation+0.392
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
),
Token),
Feature activation+1.765
so
Token so
Feature activation+3.780
we
Token we
Feature activation+0.341
can
Token can
Feature activation+0.000
conclude
Token conclude
Feature activation+3.092
that
Token that
Feature activation+2.676
P
Token P
Feature activation+0.242
P
Token P
Feature activation+0.000
uss
Tokenuss
Feature activation+0.078
just
Token just
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
enjoy
Token enjoy
Feature activation+3.780
hanging
Token hanging
Feature activation+0.000
around
Token around
Feature activation+2.981
with
Token with
Feature activation+2.277
The
Token The
Feature activation+0.000
Kid
Token Kid
Feature activation+0.000
posed
Token posed
Feature activation+0.000
was
Token was
Feature activation+0.000
little
Token little
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.910
offering
Token offering
Feature activation+3.763
Americans
Token Americans
Feature activation+0.000
places
Token places
Feature activation+0.000
to
Token to
Feature activation+0.000
casually
Token casually
Feature activation+0.000
lounge
Token lounge
Feature activation+0.000
of
Token of
Feature activation+0.000
insecurity
Token insecurity
Feature activation+0.590
or
Token or
Feature activation+0.000
wear
Token wear
Feature activation+0.000
iness
Tokeniness
Feature activation+0.000
about
Token about
Feature activation+3.745
having
Token having
Feature activation+3.016
his
Token his
Feature activation+0.000
name
Token name
Feature activation+0.000
and
Token and
Feature activation+0.000
game
Token game
Feature activation+0.000
the
Token the
Feature activation+3.673
most
Token most
Feature activation+1.110
awesome
Token awesome
Feature activation+3.434
changes
Token changes
Feature activation+2.318
coming
Token coming
Feature activation+0.977
with
Token with
Feature activation+3.741
Patch
Token Patch
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.090
!
Token!
Feature activation+0.577

Top DFA by src position
MAX = 6.066

âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
Party
Token Party
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
or
Token or
Feature activation+0.008
Top resid features:
P
Token P
Feature activation+6.066
Top resid features:
.
Token.
Feature activation+0.146
Top resid features:
K
TokenK
Feature activation+0.117
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
K
TokenK
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
last
Token last
Feature activation-0.002
Top resid features:
gig
Token gig
Feature activation-0.012
Top resid features:
for
Token for
Feature activation+0.021
Top resid features:
P
Token P
Feature activation+5.474
Top resid features:
ov
Tokenov
Feature activation+0.029
Top resid features:
il
Tokenil
Feature activation+0.019
Top resid features:
as
Tokenas
Feature activation+0.016
Top resid features:
Me
Token Me
Feature activation-0.120
Top resid features:
Å¡
Tokenš
Feature activation+0.007
Top resid features:
was
Token was
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
last
Token last
Feature activation+0.005
Top resid features:
gig
Token gig
Feature activation-0.008
Top resid features:
for
Token for
Feature activation+0.030
Top resid features:
P
Token P
Feature activation+4.959
Top resid features:
ov
Tokenov
Feature activation+0.028
Top resid features:
il
Tokenil
Feature activation+0.022
Top resid features:
as
Tokenas
Feature activation+0.017
Top resid features:
Me
Token Me
Feature activation-0.099
Top resid features:
Å¡
Tokenš
Feature activation+0.006
Top resid features:
know
Token know
Feature activation+0.008
Top resid features:
what
Token what
Feature activation+0.011
Top resid features:
Jennings
Token Jennings
Feature activation+0.024
Top resid features:
see
Token see
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.026
Top resid features:
P
Token P
Feature activation+2.489
Top resid features:
onder
Tokenonder
Feature activation+0.014
Top resid features:
after
Token after
Feature activation+0.019
Top resid features:
his
Token his
Feature activation+0.003
Top resid features:
years
Token years
Feature activation+0.002
Top resid features:
catching
Token catching
Feature activation+0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.015
Top resid features:
forces
Token forces
Feature activation+0.013
Top resid features:
refused
Token refused
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
recognize
Token recognize
Feature activation+0.006
Top resid features:
P
Token P
Feature activation+4.265
Top resid features:
é
Tokené
Feature activation+0.003
Top resid features:
tain
Tokentain
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
Party
Token Party
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
or
Token or
Feature activation+0.004
Top resid features:
P
Token P
Feature activation+2.949
Top resid features:
.
Token.
Feature activation+0.124
Top resid features:
K
TokenK
Feature activation+0.104
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
K
TokenK
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
NFC
Token NFC
Feature activation-0.022
Top resid features:
Championship
Token Championship
Feature activation+0.011
Top resid features:
game
Token game
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.084
Top resid features:
Even
Token Even
Feature activation+0.016
Top resid features:
P
Token P
Feature activation+4.960
Top resid features:
onder
Tokenonder
Feature activation+0.034
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.033
Top resid features:
newest
Token newest
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
For
TokenFor
Feature activation+0.000
Top resid features:
example
Token example
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
P
Token P
Feature activation+3.363
Top resid features:
118
Token118
Feature activation+0.006
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
million
Tokenmillion
Feature activation+0.007
Top resid features:
contract
Token contract
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
election
Token election
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
DIY
Token DIY
Feature activation+0.019
Top resid features:
punk
Token punk
Feature activation+0.025
Top resid features:
duo
Token duo
Feature activation+0.020
Top resid features:
P
Token P
Feature activation+4.465
Top resid features:
WR
TokenWR
Feature activation+0.068
Top resid features:
B
Token B
Feature activation+0.023
Top resid features:
TT
TokenTT
Feature activation+0.023
Top resid features:
M
TokenM
Feature activation+0.026
Top resid features:
travelled
Token travelled
Feature activation-0.001
Top resid features:
's
Token's
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
long
Token long
Feature activation-0.000
Top resid features:
relationship
Token relationship
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.043
Top resid features:
P
Token P
Feature activation+3.119
Top resid features:
ire
Tokenire
Feature activation+0.017
Top resid features:
lli
Tokenlli
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
The
Token The
Feature activation+0.014
Top resid features:
agreement
Token agreement
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.014
Top resid features:
agreement
Token agreement
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.011
Top resid features:
P
Token P
Feature activation+2.488
Top resid features:
ire
Tokenire
Feature activation+0.037
Top resid features:
lli
Tokenlli
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Can
Token Can
Feature activation-0.025
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
NFC
Token NFC
Feature activation-0.018
Top resid features:
Championship
Token Championship
Feature activation+0.004
Top resid features:
game
Token game
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.141
Top resid features:
Even
Token Even
Feature activation+0.030
Top resid features:
P
Token P
Feature activation+4.427
Top resid features:
onder
Tokenonder
Feature activation+0.071
Top resid features:
âĢ
TokenâĢ
Feature activation+0.093
Top resid features:
Ļ
TokenĻ
Feature activation+0.038
Top resid features:
s
Tokens
Feature activation+0.019
Top resid features:
newest
Token newest
Feature activation+0.002
Top resid features:
ot
Tokenot
Feature activation+0.017
Top resid features:
machine
Token machine
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
named
Token named
Feature activation+0.035
Top resid features:
"
Token "
Feature activation+0.042
Top resid features:
P
TokenP
Feature activation+3.318
Top resid features:
ach
Tokenach
Feature activation+0.053
Top resid features:
isl
Tokenisl
Feature activation+0.010
Top resid features:
ot
Tokenot
Feature activation+0.010
Top resid features:
Hok
Token Hok
Feature activation-0.069
Top resid features:
uto
Tokenuto
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.023
Top resid features:
Jennifer
Token Jennifer
Feature activation+0.215
Top resid features:
P
Token P
Feature activation+4.312
Top resid features:
ritz
Tokenritz
Feature activation+0.042
Top resid features:
ker
Tokenker
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
whom
Token whom
Feature activation+0.026
Top resid features:
I
Token I
Feature activation+0.061
Top resid features:
NFC
Token NFC
Feature activation-0.009
Top resid features:
Championship
Token Championship
Feature activation+0.002
Top resid features:
game
Token game
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
Even
Token Even
Feature activation+0.010
Top resid features:
P
Token P
Feature activation+2.066
Top resid features:
onder
Tokenonder
Feature activation+0.025
Top resid features:
âĢ
TokenâĢ
Feature activation+0.026
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
newest
Token newest
Feature activation-0.000
Top resid features:
some
Token some
Feature activation+0.014
Top resid features:
event
Token event
Feature activation+0.019
Top resid features:
E
Token E
Feature activation+0.088
Top resid features:
such
Token such
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
P
Token P
Feature activation+1.864
Top resid features:
(
Token(
Feature activation+0.030
Top resid features:
E
TokenE
Feature activation-0.003
Top resid features:
|
Token|
Feature activation+0.008
Top resid features:
H
TokenH
Feature activation-0.004
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
verbally
Token verbally
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
physically
Token physically
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.161
Top resid features:
And
Token And
Feature activation+0.061
Top resid features:
P
Token P
Feature activation+2.868
Top resid features:
uss
Tokenuss
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
well
Token well
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.118
Top resid features:
P
Token P
Feature activation+1.581
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
United
Token United
Feature activation-0.001
Top resid features:
States
Token States
Feature activation-0.008
Top resid features:
more
Token more
Feature activation+0.016
Top resid features:
than
Token than
Feature activation+0.028
Top resid features:
P
Token P
Feature activation+5.024
Top resid features:
ab
Tokenab
Feature activation+0.058
Top resid features:
st
Tokenst
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
Schl
Token Schl
Feature activation+0.068
Top resid features:
itz
Tokenitz
Feature activation+0.006
Top resid features:
know
Token know
Feature activation+0.018
Top resid features:
what
Token what
Feature activation+0.029
Top resid features:
Jennings
Token Jennings
Feature activation+0.027
Top resid features:
see
Token see
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.038
Top resid features:
P
Token P
Feature activation+2.868
Top resid features:
onder
Tokenonder
Feature activation+0.028
Top resid features:
after
Token after
Feature activation+0.032
Top resid features:
his
Token his
Feature activation+0.014
Top resid features:
years
Token years
Feature activation-0.005
Top resid features:
catching
Token catching
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
tweet
Token tweet
Feature activation+0.003
Top resid features:
confirming
Token confirming
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
P
Token P
Feature activation+2.901
Top resid features:
TR
TokenTR
Feature activation+0.013
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
going
Token going
Feature activation+0.001
Top resid features:
live
Token live
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.07

Head 2: 0.04

Head 3: 0.06

Head 4: 0.38

Head 5: 0.05

Head 6: 0.08

Head 7: 0.05

Head 8: 0.08

Head 9: 0.05

Head 10: 0.06

Head 11: 0.05

Positive logits

P8.29

P6.47

p5.17

p4.38

Pony2.92

pus2.91

Pom2.83

POR2.74

VIDEOS2.66

Ps2.62

PV2.55

PP2.45

PJ2.44

PG2.41

Pants2.41

PW2.40

PG2.35

PN2.34

PP2.34

Pu2.33

Negative logits

rawdownloadcloneembedreportprint-2.54

ubi-2.50

thur-2.25

Sov-2.15

iru-2.11

obb-2.10

osate-2.09

jri-2.09

roma-2.08

icides-2.07

zbollah-2.06

ItemTracker-2.03

ゼウス-2.01

stration-2.01

arrang-2.00

obe-1.98

ornia-1.96

iral-1.91

"},-1.91

ources-1.89

INTERVAL 4.518 - 5.020
CONTAINS 0.000%

with
Token with
Feature activation+2.649
the
Token the
Feature activation+0.476
band
Token band
Feature activation+0.647
.
Token.
Feature activation+2.840
Soon
Token Soon
Feature activation+1.940
after
Token after
Feature activation+4.845
the
Token the
Feature activation+1.359
festival
Token festival
Feature activation+4.331
they
Token they
Feature activation+0.000
left
Token left
Feature activation+3.022
K
Token K
Feature activation+0.000
of
Token of
Feature activation+2.404
months
Token months
Feature activation+0.000
of
Token of
Feature activation+1.095
fighting
Token fighting
Feature activation+0.025
there
Token there
Feature activation+0.000
between
Token between
Feature activation+4.864
P
Token P
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000

INTERVAL 4.016 - 4.518
CONTAINS 0.001%

to
Token to
Feature activation+0.000
know
Token know
Feature activation+3.886
what
Token what
Feature activation+3.564
Jennings
Token Jennings
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+4.069
P
Token P
Feature activation+0.000
onder
Tokenonder
Feature activation+0.000
after
Token after
Feature activation+2.676
his
Token his
Feature activation+0.000
years
Token years
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
gu
Token gu
Feature activation+0.000
err
Tokenerr
Feature activation+0.000
illas
Tokenillas
Feature activation+0.000
and
Token and
Feature activation+4.115
government
Token government
Feature activation+0.000
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+2.977
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
band
Token band
Feature activation+0.647
.
Token.
Feature activation+2.840
Soon
Token Soon
Feature activation+1.940
after
Token after
Feature activation+4.845
the
Token the
Feature activation+1.359
festival
Token festival
Feature activation+4.331
they
Token they
Feature activation+0.000
left
Token left
Feature activation+3.022
K
Token K
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
compared
Token compared
Feature activation+0.000
and
Token and
Feature activation+1.643
contrasted
Token contrasted
Feature activation+0.000
with
Token with
Feature activation+2.865
two
Token two
Feature activation+0.000
of
Token of
Feature activation+4.227
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
stars
Token stars
Feature activation+1.067
at
Token at
Feature activation+1.209
his
Token his
Feature activation+0.000
ping
Tokenping
Feature activation+0.000
on
Token on
Feature activation+0.682
a
Token a
Feature activation+0.348
budget
Token budget
Feature activation+0.481
less
Token less
Feature activation+0.000
than
Token than
Feature activation+4.030
P
Token P
Feature activation+0.984
100
Token100
Feature activation+0.000
million
Token million
Feature activation+0.869
in
Token in
Feature activation+0.790
2014
Token 2014
Feature activation+1.149

INTERVAL 3.514 - 4.016
CONTAINS 0.002%

season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.490
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+3.621
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+2.631
comparison
Token comparison
Feature activation+0.000
.
Token.
Feature activation+2.388
Many
Token Many
Feature activation+0.210
want
Token want
Feature activation+2.617
to
Token to
Feature activation+0.000
know
Token know
Feature activation+3.886
what
Token what
Feature activation+3.564
Jennings
Token Jennings
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+4.069
P
Token P
Feature activation+0.000
agreement
Token agreement
Feature activation+1.343
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
positive
Token positive
Feature activation+0.000
thing
Token thing
Feature activation+0.000
for
Token for
Feature activation+3.596
our
Token our
Feature activation+0.000
relations
Token relations
Feature activation+0.000
,
Token,
Feature activation+1.532
we
Token we
Feature activation+0.000
've
Token've
Feature activation+0.000
Quick
TokenQuick
Feature activation+0.000
round
Token round
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.055
of
Token of
Feature activation+3.537
the
Token the
Feature activation+3.673
most
Token most
Feature activation+1.110
awesome
Token awesome
Feature activation+3.434
changes
Token changes
Feature activation+2.318
coming
Token coming
Feature activation+0.977
with
Token with
Feature activation+3.741
P
TokenP
Feature activation+0.826
(
Token(
Feature activation+0.392
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
),
Token),
Feature activation+1.765
so
Token so
Feature activation+3.780
we
Token we
Feature activation+0.341
can
Token can
Feature activation+0.000
conclude
Token conclude
Feature activation+3.092
that
Token that
Feature activation+2.676
P
Token P
Feature activation+0.242

INTERVAL 3.012 - 3.514
CONTAINS 0.003%

was
Token was
Feature activation+1.375
.
Token.
Feature activation+3.463
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.154
I
TokenI
Feature activation+0.000
wrote
Token wrote
Feature activation+3.315
this
Token this
Feature activation+0.404
during
Token during
Feature activation+0.593
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.009
not
Tokennot
Feature activation+2.464
observing
Token observing
Feature activation+1.617
E
Token E
Feature activation+0.000
lowers
Token lowers
Feature activation+3.498
the
Token the
Feature activation+0.443
probability
Token probability
Feature activation+1.283
of
Token of
Feature activation+1.469
H
Token H
Feature activation+0.000
.
Token.
Feature activation+1.176
what
Token what
Feature activation+3.129
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.564
s
Tokens
Feature activation+1.103
on
Token on
Feature activation+2.703
the
Token the
Feature activation+3.149
P
Token P
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+3.125
-
Token-
Feature activation+1.179
Z
TokenZ
Feature activation+0.000
either
Token either
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.849
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+3.062
he
Token he
Feature activation+0.000
once
Token once
Feature activation+0.000
as
Token as
Feature activation+0.000
pired
Tokenpired
Feature activation+0.000
to
Token to
Feature activation+0.000
ind
Tokenind
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
and
Token and
Feature activation+0.000
Sam
Token Sam
Feature activation+0.780
Phillips
Token Phillips
Feature activation+0.000
claim
Token claim
Feature activation+3.033
they
Token they
Feature activation+0.000
lost
Token lost
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000

INTERVAL 2.510 - 3.012
CONTAINS 0.008%

failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
garner
Token garner
Feature activation+0.000
enough
Token enough
Feature activation+0.000
support
Token support
Feature activation+0.000
.
Token.
Feature activation+2.541
But
Token But
Feature activation+2.303
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
deter
Token deter
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
gig
Token gig
Feature activation+0.000
.
Token.
Feature activation+1.510
As
Token As
Feature activation+2.882
they
Token they
Feature activation+0.000
arrived
Token arrived
Feature activation+1.510
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
venue
Token venue
Feature activation+1.744
is
Token is
Feature activation+0.372
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
brand
Token brand
Feature activation+0.000
and
Token and
Feature activation+1.300
so
Token so
Feature activation+2.555
is
Token is
Feature activation+1.909
Inter
Token Inter
Feature activation+0.000
.
Token.
Feature activation+2.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
can
Token can
Feature activation+0.260
do
Token do
Feature activation+1.186
Saturday
Token Saturday
Feature activation+0.211
Night
Token Night
Feature activation+0.000
.
Token.
Feature activation+2.036
if
Tokenif
Feature activation+2.622
a
Token a
Feature activation+1.223
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+1.348
you
Token you
Feature activation+0.249
think
Token think
Feature activation+1.914
new
Token new
Feature activation+0.000
and
Token and
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
to
Token to
Feature activation+0.000
us
Token us
Feature activation+0.000
,"
Token,"
Feature activation+2.734
de
Token de
Feature activation+0.000
Vill
Token Vill
Feature activation+0.000
iers
Tokeniers
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.008 - 2.510
CONTAINS 0.015%

smiles
Token smiles
Feature activation+0.000
a
Token a
Feature activation+0.000
minute
Token minute
Feature activation+0.000
.
Token.
Feature activation+0.924
When
Token When
Feature activation+0.363
the
Token the
Feature activation+2.238
mood
Token mood
Feature activation+0.000
dev
Token dev
Feature activation+0.000
iates
Tokeniates
Feature activation+0.000
from
Token from
Feature activation+0.000
that
Token that
Feature activation+0.000
P
Token P
Feature activation+0.000
aley
Tokenaley
Feature activation+0.000
Fest
TokenFest
Feature activation+0.105
that
Token that
Feature activation+0.678
most
Token most
Feature activation+0.567
of
Token of
Feature activation+2.233
the
Token the
Feature activation+0.951
season
Token season
Feature activation+0.000
three
Token three
Feature activation+0.000
cast
Token cast
Feature activation+0.000
would
Token would
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.661
Here
TokenHere
Feature activation+0.048
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.014
what
Token what
Feature activation+3.129
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.564
s
Tokens
Feature activation+1.103
on
Token on
Feature activation+2.703
professors
Token professors
Feature activation+0.000
and
Token and
Feature activation+0.000
college
Token college
Feature activation+0.000
counselors
Token counselors
Feature activation+0.000
routinely
Token routinely
Feature activation+0.000
tell
Token tell
Feature activation+2.120
their
Token their
Feature activation+0.000
students
Token students
Feature activation+1.001
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
rely
Token rely
Feature activation+0.000
3
Token3
Feature activation+0.090
!
Token!
Feature activation+0.577
Keep
Token Keep
Feature activation+0.000
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+1.847
some
Token some
Feature activation+2.191
of
Token of
Feature activation+1.779
these
Token these
Feature activation+1.101
are
Token are
Feature activation+0.585
subject
Token subject
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.506 - 2.008
CONTAINS 0.032%

Posted
Token Posted
Feature activation+0.000
by
Token by
Feature activation+0.859
Blizzard
Token Blizzard
Feature activation+0.000
(
Token (
Feature activation+0.000
Twitter
TokenTwitter
Feature activation+0.000
)
Token)
Feature activation+1.785
That
Token That
Feature activation+0.919
seems
Token seems
Feature activation+0.000
fair
Token fair
Feature activation+0.000
.
Token.
Feature activation+2.954
The
Token The
Feature activation+2.478
to
Token to
Feature activation+0.000
compromise
Token compromise
Feature activation+1.334
the
Token the
Feature activation+0.000
router
Token router
Feature activation+0.000
.
Token.
Feature activation+1.830
And
Token And
Feature activation+1.806
unlike
Token unlike
Feature activation+0.257
other
Token other
Feature activation+0.626
projects
Token projects
Feature activation+2.162
,
Token,
Feature activation+1.980
he
Token he
Feature activation+0.000
species
Token species
Feature activation+0.000
of
Token of
Feature activation+1.573
plants
Token plants
Feature activation+0.000
and
Token and
Feature activation+0.000
animals
Token animals
Feature activation+0.000
benefit
Token benefit
Feature activation+1.524
from
Token from
Feature activation+1.432
that
Token that
Feature activation+0.378
mutual
Token mutual
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
between
Token between
Feature activation+0.000
in
Token in
Feature activation+0.175
the
Token the
Feature activation+0.847
US
Token US
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+1.556
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.062
I
TokenI
Feature activation+0.000
tried
Token tried
Feature activation+0.575
my
Token my
Feature activation+0.787
goers
Tokengoers
Feature activation+0.000
and
Token and
Feature activation+0.000
himself
Token himself
Feature activation+0.000
.
Token.
Feature activation+0.033
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.612
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
like
Token like
Feature activation+0.000

INTERVAL 1.004 - 1.506
CONTAINS 0.047%

Still
TokenStill
Feature activation+0.000
,
Token,
Feature activation+2.188
the
Token the
Feature activation+1.331
victory
Token victory
Feature activation+0.000
ensures
Token ensures
Feature activation+0.929
that
Token that
Feature activation+1.300
just
Token just
Feature activation+0.000
one
Token one
Feature activation+0.612
chunk
Token chunk
Feature activation+0.000
of
Token of
Feature activation+1.728
the
Token the
Feature activation+1.965
,
Token,
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+1.090
much
Token much
Feature activation+0.000
of
Token of
Feature activation+1.970
their
Token their
Feature activation+1.046
spending
Token spending
Feature activation+0.000
promises
Token promises
Feature activation+0.000
being
Token being
Feature activation+0.000
ramp
Token ramp
Feature activation+0.000
ed
Tokened
Feature activation+0.000
get
Token get
Feature activation+0.318
involved
Token involved
Feature activation+0.000
.
Token.
Feature activation+1.426
So
Token So
Feature activation+1.025
too
Token too
Feature activation+0.505
might
Token might
Feature activation+1.375
the
Token the
Feature activation+1.527
other
Token other
Feature activation+1.004
suppliers
Token suppliers
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
both
Token both
Feature activation+1.798
parties
Token parties
Feature activation+0.000
.
Token.
Feature activation+2.455
Especially
Token Especially
Feature activation+2.208
now
Token now
Feature activation+2.724
both
Token both
Feature activation+1.465
companies
Token companies
Feature activation+0.000
are
Token are
Feature activation+0.000
looking
Token looking
Feature activation+0.000
at
Token at
Feature activation+1.413
Asia
Token Asia
Feature activation+0.000
age
Tokenage
Feature activation+0.360
looked
Token looked
Feature activation+0.000
over
Token over
Feature activation+0.551
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.939
saw
Token saw
Feature activation+1.340
that
Token that
Feature activation+1.141
Vic
Token Vic
Feature activation+0.000
's
Token's
Feature activation+0.000
body
Token body
Feature activation+0.000
had
Token had
Feature activation+0.000

INTERVAL 0.502 - 1.004
CONTAINS 0.080%

frown
Token frown
Feature activation+0.959
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
200
Token200
Feature activation+0.916
smiles
Token smiles
Feature activation+0.000
a
Token a
Feature activation+0.000
minute
Token minute
Feature activation+0.000
.
Token.
Feature activation+0.924
When
Token When
Feature activation+0.363
's
Token's
Feature activation+0.000
4
Token 4
Feature activation+0.000
Christmas
Token Christmas
Feature activation+0.000
Give
Token Give
Feature activation+0.000
aways
Tokenaways
Feature activation+0.000
Ph
Token Ph
Feature activation+0.929
p
Tokenp
Feature activation+0.000
260
Token 260
Feature activation+0.000
,
Token,
Feature activation+0.000
593
Token593
Feature activation+0.000
,
Token,
Feature activation+0.000
called
Token called
Feature activation+0.000
"
Token "
Feature activation+0.000
opt
Tokenopt
Feature activation+0.000
ogen
Tokenogen
Feature activation+0.000
etics
Tokenetics
Feature activation+0.000
"
Token"
Feature activation+0.863
that
Token that
Feature activation+0.000
triggers
Token triggers
Feature activation+0.174
neural
Token neural
Feature activation+0.000
activity
Token activity
Feature activation+0.000
with
Token with
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.318
involved
Token involved
Feature activation+0.000
.
Token.
Feature activation+1.426
So
Token So
Feature activation+1.025
too
Token too
Feature activation+0.505
might
Token might
Feature activation+1.375
the
Token the
Feature activation+1.527
other
Token other
Feature activation+1.004
suppliers
Token suppliers
Feature activation+0.000
,
Token,
Feature activation+0.000
P
Token P
Feature activation+0.000
CT
TokenCT
Feature activation+0.000
A
TokenA
Feature activation+0.000
will
Token will
Feature activation+0.000
happen
Token happen
Feature activation+0.000
.
Token.
Feature activation+0.826
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.000 - 0.502
CONTAINS 99.812%

but
Token but
Feature activation+0.000
that
Token that
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
is
Token is
Feature activation+0.000
how
Token how
Feature activation+0.000
he
Token he
Feature activation+0.000
interpre
Token interpre
Feature activation+0.000
ts
Tokents
Feature activation+0.000
criticism
Token criticism
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
are
Token are
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
James
TokenJames
Feature activation+0.000
Bond
Token Bond
Feature activation+0.000
,
Token,
Feature activation+0.000
Agent
Token Agent
Feature activation+0.000
energy
Token energy
Feature activation+0.000
must
Token must
Feature activation+0.000
listen
Token listen
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
stated
Token stated
Feature activation+0.000
a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.000
sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
We
TokenWe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
all
Token all
Feature activation+0.000
heard
Token heard
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
gap
Token gap
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
this
Token this
Feature activation+0.000
build
Token build
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
as
Token as
Feature activation+0.000
effective
Token effective
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H11.4: (feature 4326)

TOP ACTIVATIONS
MAX = 6.188

Ċ
TokenĊ
Feature activation+1.493
What
TokenWhat
Feature activation+1.979
can
Token can
Feature activation+5.065
startups
Token startups
Feature activation+0.000
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+6.188
the
Token the
Feature activation+2.788
series
Token series
Feature activation+0.600
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+4.448
Start
TokenStart
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.104
,
Token,
Feature activation+0.000
strength
Token strength
Feature activation+0.000
and
Token and
Feature activation+0.000
instincts
Token instincts
Feature activation+5.158
that
Token that
Feature activation+1.642
made
Token made
Feature activation+2.905
him
Token him
Feature activation+0.000
the
Token the
Feature activation+0.000
No
Token No
Feature activation+0.000
comes
Token comes
Feature activation+0.000
.
Token.
Feature activation+3.203
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.493
What
TokenWhat
Feature activation+1.979
can
Token can
Feature activation+5.065
startups
Token startups
Feature activation+0.000
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+6.188
the
Token the
Feature activation+2.788
series
Token series
Feature activation+0.600
's
Token's
Feature activation+0.000
Court
Token Court
Feature activation+0.000
heard
Token heard
Feature activation+3.691
yesterday
Token yesterday
Feature activation+4.629
how
Token how
Feature activation+2.350
Louie
Token Louie
Feature activation+4.916
was
Token was
Feature activation+0.000
bullied
Token bullied
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
decision
Token decision
Feature activation+0.000
by
Token by
Feature activation+0.000
half
Token half
Feature activation+0.000
.
Token.
Feature activation+3.262
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.533
Considering
TokenConsidering
Feature activation+4.913
ad
Token ad
Feature activation+0.000
blockers
Token blockers
Feature activation+0.191
have
Token have
Feature activation+0.000
ruined
Token ruined
Feature activation+3.824
the
Token the
Feature activation+0.741
behind
Token behind
Feature activation+0.000
setting
Token setting
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
embassy
Token embassy
Feature activation+0.000
.
Token.
Feature activation+4.630
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.550
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.889
,
Token,
Feature activation+0.000
Cor
Token Cor
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
's
Token's
Feature activation+0.000
Court
Token Court
Feature activation+0.000
heard
Token heard
Feature activation+3.691
yesterday
Token yesterday
Feature activation+4.629
how
Token how
Feature activation+2.350
Louie
Token Louie
Feature activation+4.916
was
Token was
Feature activation+0.000
bullied
Token bullied
Feature activation+0.000
for
Token for
Feature activation+0.000
in
Token in
Feature activation+0.567
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+1.380
this
Token this
Feature activation+0.000
is
Token is
Feature activation+4.516
not
Token not
Feature activation+3.848
one
Token one
Feature activation+0.000
of
Token of
Feature activation+1.765
them
Token them
Feature activation+0.000
.
Token.
Feature activation+1.467
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+6.188
the
Token the
Feature activation+2.788
series
Token series
Feature activation+0.600
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+4.448
Start
TokenStart
Feature activation+0.000
Up
TokenUp
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.999
?
Token?
Feature activation+1.843
team
Token team
Feature activation+0.000
place
Token place
Feature activation+3.276
the
Token the
Feature activation+0.035
flow
Token flow
Feature activation+0.000
meters
Token meters
Feature activation+0.000
on
Token on
Feature activation+4.370
the
Token the
Feature activation+0.886
animals
Token animals
Feature activation+0.000
'
Token'
Feature activation+0.000
heads
Token heads
Feature activation+0.000
because
Token because
Feature activation+2.972
decade
Token decade
Feature activation+0.000
than
Token than
Feature activation+2.106
the
Token the
Feature activation+1.917
f
Token f
Feature activation+0.000
***
Token***
Feature activation+0.000
ing
Tokening
Feature activation+4.362
N
Token N
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
ies
Tokenies
Feature activation+0.039
and
Token and
Feature activation+0.384
never
Token never
Feature activation+0.000
because
Token because
Feature activation+2.972
of
Token of
Feature activation+3.346
the
Token the
Feature activation+0.000
level
Token level
Feature activation+0.000
of
Token of
Feature activation+0.000
trust
Token trust
Feature activation+4.362
between
Token between
Feature activation+2.110
the
Token the
Feature activation+0.818
trainers
Token trainers
Feature activation+0.000
and
Token and
Feature activation+1.048
the
Token the
Feature activation+0.797
,
Token,
Feature activation+4.248
one
Token one
Feature activation+0.384
must
Token must
Feature activation+0.000
also
Token also
Feature activation+0.000
wonder
Token wonder
Feature activation+0.012
when
Token when
Feature activation+4.293
there
Token there
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.586
ad
Token ad
Feature activation+0.000
blockers
Token blockers
Feature activation+0.000
ruined
Token ruined
Feature activation+3.824
the
Token the
Feature activation+0.741
banner
Token banner
Feature activation+0.000
ad
Token ad
Feature activation+0.000
industry
Token industry
Feature activation+1.077
,
Token,
Feature activation+4.248
one
Token one
Feature activation+0.384
must
Token must
Feature activation+0.000
also
Token also
Feature activation+0.000
wonder
Token wonder
Feature activation+0.012
when
Token when
Feature activation+4.293
a
Token a
Feature activation+0.784
device
Token device
Feature activation+0.000
or
Token or
Feature activation+0.000
sensor
Token sensor
Feature activation+0.000
near
Token near
Feature activation+1.689
an
Token an
Feature activation+4.235
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.000
compound
Token compound
Feature activation+0.000
were
Token were
Feature activation+0.000
which
Token which
Feature activation+1.250
was
Token was
Feature activation+0.000
established
Token established
Feature activation+0.030
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+4.163
The
Token The
Feature activation+3.221
two
Token two
Feature activation+2.040
companies
Token companies
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+2.912
F
Token F
Feature activation+0.000
SF
TokenSF
Feature activation+0.292
's
Token's
Feature activation+0.838
founder
Token founder
Feature activation+0.000
,
Token,
Feature activation+1.106
with
Token with
Feature activation+4.052
the
Token the
Feature activation+2.004
title
Token title
Feature activation+1.370
"
Token "
Feature activation+1.873
Why
TokenWhy
Feature activation+3.257
Open
Token Open
Feature activation+0.000
and
Token and
Feature activation+0.000
corruption
Token corruption
Feature activation+0.000
charges
Token charges
Feature activation+0.000
.
Token.
Feature activation+2.778
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.000
South
TokenSouth
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.854
Carter
Token Carter
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.337
At
TokenAt
Feature activation+2.423
the
Token the
Feature activation+0.147
Reform
Token Reform
Feature activation+0.000
Club
Token Club
Feature activation+3.993
,
Token,
Feature activation+2.606
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
gets
Token gets
Feature activation+0.000
involved
Token involved
Feature activation+0.000
-
Token-
Feature activation+0.000
host
Tokenhost
Feature activation+1.121
Lisa
Token Lisa
Feature activation+0.000
Chow
Token Chow
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
with
Token with
Feature activation+3.951
Geek
Token Geek
Feature activation+0.000
time
Tokentime
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.062
For
TokenFor
Feature activation+2.135

Top DFA by src position
MAX = 7.017

<|endoftext|>
Token<|endoftext|>
Feature activation+0.007
Top resid features:
like
Token like
Feature activation+0.053
Top resid features:
F
Token F
Feature activation+7.017
Top resid features:
idelity
Tokenidelity
Feature activation+0.089
Top resid features:
have
Token have
Feature activation+0.013
Top resid features:
severely
Token severely
Feature activation+0.017
Top resid features:
deval
Token deval
Feature activation+0.015
Top resid features:
ued
Tokenued
Feature activation+0.023
Top resid features:
case
Token case
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
Week
Token Week
Feature activation+0.006
Top resid features:
1
Token 1
Feature activation+0.015
Top resid features:
,
Token,
Feature activation-0.115
Top resid features:
F
Token F
Feature activation+6.664
Top resid features:
ourn
Tokenourn
Feature activation+0.142
Top resid features:
ette
Tokenette
Feature activation+0.196
Top resid features:
early
Token early
Feature activation+0.000
Top resid features:
Sunday
Token Sunday
Feature activation+0.002
Top resid features:
showed
Token showed
Feature activation+0.090
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.005
Top resid features:
like
Token like
Feature activation+0.043
Top resid features:
F
Token F
Feature activation+6.094
Top resid features:
idelity
Tokenidelity
Feature activation+0.099
Top resid features:
have
Token have
Feature activation+0.009
Top resid features:
severely
Token severely
Feature activation+0.004
Top resid features:
deval
Token deval
Feature activation+0.004
Top resid features:
ued
Tokenued
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Lou
TokenLou
Feature activation+0.012
Top resid features:
ie
Tokenie
Feature activation+0.011
Top resid features:
Tom
Token Tom
Feature activation-0.070
Top resid features:
F
Token F
Feature activation+6.750
Top resid features:
enton
Tokenenton
Feature activation+0.204
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
pronounced
Token pronounced
Feature activation+0.001
Top resid features:
dead
Token dead
Feature activation-0.023
Top resid features:
after
Token after
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.021
Top resid features:
like
Token like
Feature activation+0.102
Top resid features:
F
Token F
Feature activation+5.570
Top resid features:
idelity
Tokenidelity
Feature activation+0.157
Top resid features:
have
Token have
Feature activation+0.041
Top resid features:
severely
Token severely
Feature activation+0.019
Top resid features:
deval
Token deval
Feature activation+0.014
Top resid features:
ued
Tokenued
Feature activation+0.052
Top resid features:
ob
Tokenob
Feature activation+0.007
Top resid features:
uy
Tokenuy
Feature activation+0.001
Top resid features:
er
Tokener
Feature activation-0.000
Top resid features:
),
Token),
Feature activation+0.047
Top resid features:
Jorge
Token Jorge
Feature activation+0.146
Top resid features:
F
Token F
Feature activation+5.832
Top resid features:
ari
Tokenari
Feature activation+0.028
Top resid features:
as
Tokenas
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
get
Token get
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Lou
TokenLou
Feature activation+0.090
Top resid features:
ie
Tokenie
Feature activation+0.119
Top resid features:
Tom
Token Tom
Feature activation-0.086
Top resid features:
F
Token F
Feature activation+6.239
Top resid features:
enton
Tokenenton
Feature activation+0.076
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
pronounced
Token pronounced
Feature activation-0.000
Top resid features:
dead
Token dead
Feature activation-0.003
Top resid features:
after
Token after
Feature activation+0.008
Top resid features:
ones
Token ones
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
world
Token world
Feature activation+0.008
Top resid features:
Michael
Token Michael
Feature activation-0.012
Top resid features:
F
Token F
Feature activation+5.346
Top resid features:
ass
Tokenass
Feature activation+0.095
Top resid features:
bender
Tokenbender
Feature activation+0.117
Top resid features:
can
Token can
Feature activation+0.008
Top resid features:
call
Token call
Feature activation+0.005
Top resid features:
his
Token his
Feature activation+0.010
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.015
Top resid features:
like
Token like
Feature activation+0.100
Top resid features:
F
Token F
Feature activation+5.481
Top resid features:
idelity
Tokenidelity
Feature activation+0.069
Top resid features:
have
Token have
Feature activation+0.012
Top resid features:
severely
Token severely
Feature activation+0.009
Top resid features:
deval
Token deval
Feature activation+0.010
Top resid features:
ued
Tokenued
Feature activation+0.019
Top resid features:
Quest
Token Quest
Feature activation+0.003
Top resid features:
were
Token were
Feature activation+0.006
Top resid features:
able
Token able
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
help
Token help
Feature activation+0.019
Top resid features:
F
Token F
Feature activation+5.900
Top resid features:
ahl
Tokenahl
Feature activation+0.031
Top resid features:
man
Tokenman
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
his
Token his
Feature activation+0.007
Top resid features:
team
Token team
Feature activation+0.003
Top resid features:
***
Token***
Feature activation+0.048
Top resid features:
ing
Tokening
Feature activation+0.047
Top resid features:
decade
Token decade
Feature activation-0.036
Top resid features:
than
Token than
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
f
Token f
Feature activation+2.661
Top resid features:
***
Token***
Feature activation+0.065
Top resid features:
ing
Tokening
Feature activation+0.064
Top resid features:
N
Token N
Feature activation+0.000
Top resid features:
ought
Tokenought
Feature activation+0.000
Top resid features:
ies
Tokenies
Feature activation+0.000
Top resid features:
Quest
Token Quest
Feature activation+0.014
Top resid features:
were
Token were
Feature activation+0.004
Top resid features:
able
Token able
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
help
Token help
Feature activation+0.025
Top resid features:
F
Token F
Feature activation+5.999
Top resid features:
ahl
Tokenahl
Feature activation+0.044
Top resid features:
man
Tokenman
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.060
Top resid features:
his
Token his
Feature activation+0.009
Top resid features:
team
Token team
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.021
Top resid features:
like
Token like
Feature activation+0.079
Top resid features:
F
Token F
Feature activation+4.951
Top resid features:
idelity
Tokenidelity
Feature activation+0.132
Top resid features:
have
Token have
Feature activation+0.028
Top resid features:
severely
Token severely
Feature activation+0.035
Top resid features:
deval
Token deval
Feature activation+0.017
Top resid features:
ued
Tokenued
Feature activation+0.055
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.024
Top resid features:
like
Token like
Feature activation+0.100
Top resid features:
F
Token F
Feature activation+4.971
Top resid features:
idelity
Tokenidelity
Feature activation+0.127
Top resid features:
have
Token have
Feature activation+0.032
Top resid features:
severely
Token severely
Feature activation+0.022
Top resid features:
deval
Token deval
Feature activation+0.016
Top resid features:
ued
Tokenued
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
kitchen
Token kitchen
Feature activation+0.005
Top resid features:
sink
Token sink
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
F
Token F
Feature activation+5.659
Top resid features:
ATA
TokenATA
Feature activation+0.062
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+0.006
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
day
Tokenday
Feature activation-0.000
Top resid features:
conference
Token conference
Feature activation+0.016
Top resid features:
organised
Token organised
Feature activation+0.010
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
F
Token F
Feature activation+3.287
Top resid features:
int
Tokenint
Feature activation+0.005
Top resid features:
ech
Tokenech
Feature activation+0.008
Top resid features:
Valley
Token Valley
Feature activation+0.019
Top resid features:
Viz
Token Viz
Feature activation+0.015
Top resid features:
ag
Tokenag
Feature activation+0.001
Top resid features:
software
Token software
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
Indeed
Token Indeed
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
on
Token on
Feature activation+0.018
Top resid features:
F
Token F
Feature activation+1.696
Top resid features:
SF
TokenSF
Feature activation+0.007
Top resid features:
's
Token's
Feature activation+0.012
Top resid features:
front
Token front
Feature activation+0.001
Top resid features:
page
Token page
Feature activation+0.001
Top resid features:
there
Token there
Feature activation+0.002
Top resid features:
2011
Token 2011
Feature activation-0.003
Top resid features:
under
Token under
Feature activation+0.010
Top resid features:
County
Token County
Feature activation+0.002
Top resid features:
Executive
Token Executive
Feature activation+0.010
Top resid features:
Bob
Token Bob
Feature activation+0.007
Top resid features:
F
Token F
Feature activation+4.636
Top resid features:
ic
Tokenic
Feature activation+0.122
Top resid features:
ano
Tokenano
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.117
Top resid features:
Work
Token Work
Feature activation-0.011
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
30
Token30
Feature activation+0.001
Top resid features:
°
Token °
Feature activation+0.001
Top resid features:
C
TokenC
Feature activation+0.003
Top resid features:
),
Token),
Feature activation+0.070
Top resid features:
F
Token F
Feature activation+2.136
Top resid features:
ogg
Tokenogg
Feature activation+0.003
Top resid features:
hires
Token hires
Feature activation+0.011
Top resid features:
Frenchman
Token Frenchman
Feature activation+0.016
Top resid features:
Jean
Token Jean
Feature activation+0.008
Top resid features:
Pas
Token Pas
Feature activation+0.118
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.021
Top resid features:
like
Token like
Feature activation+0.034
Top resid features:
F
Token F
Feature activation+4.723
Top resid features:
idelity
Tokenidelity
Feature activation+0.059
Top resid features:
have
Token have
Feature activation+0.009
Top resid features:
severely
Token severely
Feature activation+0.002
Top resid features:
deval
Token deval
Feature activation+0.002
Top resid features:
ued
Tokenued
Feature activation+0.011
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.05

Head 3: 0.06

Head 4: 0.38

Head 5: 0.04

Head 6: 0.06

Head 7: 0.04

Head 8: 0.08

Head 9: 0.05

Head 10: 0.05

Head 11: 0.06

Positive logits

F8.31

F6.42

f5.51

f4.45

Fs3.73

FSA3.25

Fn3.24

FAC3.22

Fiji3.08

FTA2.91

FH2.83

Fang2.78

FP2.74

FK2.72

Fame2.68

FN2.66

fen2.63

Fern2.58

FF2.56

fy2.56

Negative logits

��-2.50

achus-2.25

ocon-2.24

ploy-2.17

ourke-2.15

isSpecialOrderable-2.11

rush-2.11

drops-2.08

ependence-2.04

srf-2.01

doi-1.99

keley-1.98

yon-1.98

elaide-1.97

aunted-1.95

ptions-1.93

apolis-1.91

obic-1.89

aven-1.88

holiday-1.88

INTERVAL 5.569 - 6.188
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+1.493
What
TokenWhat
Feature activation+1.979
can
Token can
Feature activation+5.065
startups
Token startups
Feature activation+0.000
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+6.188
the
Token the
Feature activation+2.788
series
Token series
Feature activation+0.600
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+4.448
Start
TokenStart
Feature activation+0.000

INTERVAL 4.950 - 5.569
CONTAINS 0.000%

comes
Token comes
Feature activation+0.000
.
Token.
Feature activation+3.203
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.493
What
TokenWhat
Feature activation+1.979
can
Token can
Feature activation+5.065
startups
Token startups
Feature activation+0.000
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+6.188
the
Token the
Feature activation+2.788
series
Token series
Feature activation+0.600
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.104
,
Token,
Feature activation+0.000
strength
Token strength
Feature activation+0.000
and
Token and
Feature activation+0.000
instincts
Token instincts
Feature activation+5.158
that
Token that
Feature activation+1.642
made
Token made
Feature activation+2.905
him
Token him
Feature activation+0.000
the
Token the
Feature activation+0.000
No
Token No
Feature activation+0.000

INTERVAL 4.332 - 4.950
CONTAINS 0.001%

because
Token because
Feature activation+2.972
of
Token of
Feature activation+3.346
the
Token the
Feature activation+0.000
level
Token level
Feature activation+0.000
of
Token of
Feature activation+0.000
trust
Token trust
Feature activation+4.362
between
Token between
Feature activation+2.110
the
Token the
Feature activation+0.818
trainers
Token trainers
Feature activation+0.000
and
Token and
Feature activation+1.048
the
Token the
Feature activation+0.797
's
Token's
Feature activation+0.000
Court
Token Court
Feature activation+0.000
heard
Token heard
Feature activation+3.691
yesterday
Token yesterday
Feature activation+4.629
how
Token how
Feature activation+2.350
Louie
Token Louie
Feature activation+4.916
was
Token was
Feature activation+0.000
bullied
Token bullied
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
decision
Token decision
Feature activation+0.000
Cor
Token Cor
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
's
Token's
Feature activation+0.000
Court
Token Court
Feature activation+0.000
heard
Token heard
Feature activation+3.691
yesterday
Token yesterday
Feature activation+4.629
how
Token how
Feature activation+2.350
Louie
Token Louie
Feature activation+4.916
was
Token was
Feature activation+0.000
bullied
Token bullied
Feature activation+0.000
for
Token for
Feature activation+0.000
team
Token team
Feature activation+0.000
place
Token place
Feature activation+3.276
the
Token the
Feature activation+0.035
flow
Token flow
Feature activation+0.000
meters
Token meters
Feature activation+0.000
on
Token on
Feature activation+4.370
the
Token the
Feature activation+0.886
animals
Token animals
Feature activation+0.000
'
Token'
Feature activation+0.000
heads
Token heads
Feature activation+0.000
because
Token because
Feature activation+2.972
in
Token in
Feature activation+0.567
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+1.380
this
Token this
Feature activation+0.000
is
Token is
Feature activation+4.516
not
Token not
Feature activation+3.848
one
Token one
Feature activation+0.000
of
Token of
Feature activation+1.765
them
Token them
Feature activation+0.000
.
Token.
Feature activation+1.467

INTERVAL 3.713 - 4.332
CONTAINS 0.002%

whom
Token whom
Feature activation+0.000
probably
Token probably
Feature activation+0.000
waste
Token waste
Feature activation+0.000
time
Token time
Feature activation+0.000
per
Token per
Feature activation+0.000
using
Tokenusing
Feature activation+3.780
list
Token list
Feature activation+0.000
icles
Tokenicles
Feature activation+0.000
like
Token like
Feature activation+2.059
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.440
Ċ
TokenĊ
Feature activation+2.533
Considering
TokenConsidering
Feature activation+4.913
ad
Token ad
Feature activation+0.000
blockers
Token blockers
Feature activation+0.191
have
Token have
Feature activation+0.000
ruined
Token ruined
Feature activation+3.824
the
Token the
Feature activation+0.741
banner
Token banner
Feature activation+0.000
ad
Token ad
Feature activation+0.000
industry
Token industry
Feature activation+1.077
,
Token,
Feature activation+4.248
(
Token (
Feature activation+0.033
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+1.855
and
Token and
Feature activation+3.429
Mah
Token Mah
Feature activation+0.000
ali
Tokenali
Feature activation+3.778
became
Token became
Feature activation+0.000
agitated
Token agitated
Feature activation+0.000
after
Token after
Feature activation+2.945
a
Token a
Feature activation+0.579
visitor
Token visitor
Feature activation+0.000
and
Token and
Feature activation+0.000
corruption
Token corruption
Feature activation+0.000
charges
Token charges
Feature activation+0.000
.
Token.
Feature activation+2.778
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.000
South
TokenSouth
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.854
Carter
Token Carter
Feature activation+0.000
F
Token F
Feature activation+0.000
SF
TokenSF
Feature activation+0.292
's
Token's
Feature activation+0.838
founder
Token founder
Feature activation+0.000
,
Token,
Feature activation+1.106
with
Token with
Feature activation+4.052
the
Token the
Feature activation+2.004
title
Token title
Feature activation+1.370
"
Token "
Feature activation+1.873
Why
TokenWhy
Feature activation+3.257
Open
Token Open
Feature activation+0.000

INTERVAL 3.094 - 3.713
CONTAINS 0.006%

Over
TokenOver
Feature activation+0.894
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
28
Token 28
Feature activation+0.000
years
Token years
Feature activation+2.211
,
Token,
Feature activation+3.241
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
go
Token go
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
never
Token never
Feature activation+0.000
has
Token has
Feature activation+1.193
there
Token there
Feature activation+0.000
been
Token been
Feature activation+0.445
a
Token a
Feature activation+2.398
more
Token more
Feature activation+3.650
nond
Token nond
Feature activation+0.000
esc
Tokenesc
Feature activation+0.000
ript
Tokenript
Feature activation+2.231
f
Token f
Feature activation+0.000
***
Token***
Feature activation+0.000
and
Token and
Feature activation+1.666
worthy
Token worthy
Feature activation+0.000
of
Token of
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
.
Token.
Feature activation+2.915
Rather
Token Rather
Feature activation+3.485
,
Token,
Feature activation+3.676
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
charging
Token charging
Feature activation+3.459
F
Token F
Feature activation+2.026
AV
TokenAV
Feature activation+0.000
ES
TokenES
Feature activation+0.000
Gor
Token Gor
Feature activation+0.000
illas
Tokenillas
Feature activation+0.000
Fat
Token Fat
Feature activation+0.000
aki
Tokenaki
Feature activation+3.671
(
Token (
Feature activation+0.033
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+1.855
and
Token and
Feature activation+3.429
Mah
Token Mah
Feature activation+0.000
iol
Tokeniol
Feature activation+0.000
x
Tokenx
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ilde
Tokenilde
Feature activation+0.000
reveals
Token reveals
Feature activation+1.644
to
Token to
Feature activation+3.427
Dur
Token Dur
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
us
Tokenus
Feature activation+0.000
how
Token how
Feature activation+1.067

INTERVAL 2.475 - 3.094
CONTAINS 0.010%

ators
Tokenators
Feature activation+0.073
by
Token by
Feature activation+1.844
IC
Token IC
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
I
TokenI
Feature activation+0.000
and
Token and
Feature activation+2.850
Mah
Token Mah
Feature activation+0.000
ind
Tokenind
Feature activation+0.000
ra
Tokenra
Feature activation+0.148
Finance
Token Finance
Feature activation+0.000
in
Token in
Feature activation+1.522
adding
Token adding
Feature activation+0.000
proof
Token proof
Feature activation+0.000
to
Token to
Feature activation+0.171
the
Token the
Feature activation+0.000
argument
Token argument
Feature activation+0.000
that
Token that
Feature activation+2.846
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.228
fans
Token fans
Feature activation+0.000
can
Token can
Feature activation+0.000
design
Token design
Feature activation+0.722
titled
Token titled
Feature activation+0.000
Foreign
Token Foreign
Feature activation+0.000
Pod
Token Pod
Feature activation+0.000
icy
Tokenicy
Feature activation+0.000
.
Token.
Feature activation+2.042
The
Token The
Feature activation+2.642
show
Token show
Feature activation+0.000
,
Token,
Feature activation+1.779
hosted
Token hosted
Feature activation+0.000
by
Token by
Feature activation+2.793
F
Token F
Feature activation+0.000
Speaking
TokenSpeaking
Feature activation+0.000
of
Token of
Feature activation+2.307
Lockheed
Token Lockheed
Feature activation+0.000
,
Token,
Feature activation+0.546
Trump
Token Trump
Feature activation+0.000
said
Token said
Feature activation+2.948
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
nowhere
Token nowhere
Feature activation+0.755
to
Token to
Feature activation+0.000
expand
Token expand
Feature activation+1.242
âĢĵ
Token âĢĵ
Feature activation+2.050
in
Token in
Feature activation+1.800
fact
Token fact
Feature activation+2.798
,
Token,
Feature activation+3.693
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.022
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.527

INTERVAL 1.856 - 2.475
CONTAINS 0.022%

she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
willing
Token willing
Feature activation+0.000
to
Token to
Feature activation+0.000
debate
Token debate
Feature activation+1.919
me
Token me
Feature activation+0.000
on
Token on
Feature activation+0.000
TV
Token TV
Feature activation+0.000
.
Token.
Feature activation+2.527
She
Token She
Feature activation+0.000
cross
Token cross
Feature activation+0.000
-
Token-
Feature activation+0.000
party
Tokenparty
Feature activation+0.310
nature
Token nature
Feature activation+0.000
of
Token of
Feature activation+0.451
the
Token the
Feature activation+2.384
measures
Token measures
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.049
If
TokenIf
Feature activation+0.582
you
Token you
Feature activation+0.000
"
Token"
Feature activation+0.000
and
Token and
Feature activation+1.415
his
Token his
Feature activation+1.552
review
Token review
Feature activation+0.000
of
Token of
Feature activation+0.285
the
Token the
Feature activation+2.125
Al
Token Al
Feature activation+0.000
fa
Tokenfa
Feature activation+0.000
Romeo
Token Romeo
Feature activation+0.374
4
Token 4
Feature activation+0.000
C
TokenC
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+1.219
one
Token one
Feature activation+0.965
acc
Token acc
Feature activation+0.000
reditation
Tokenreditation
Feature activation+0.000
,
Token,
Feature activation+1.922
it
Token it
Feature activation+0.000
's
Token's
Feature activation+1.144
lever
Token lever
Feature activation+0.000
aged
Tokenaged
Feature activation+1.554
across
Token across
Feature activation+1.165
and
Token and
Feature activation+0.384
never
Token never
Feature activation+0.000
has
Token has
Feature activation+1.193
there
Token there
Feature activation+0.000
been
Token been
Feature activation+0.445
a
Token a
Feature activation+2.398
more
Token more
Feature activation+3.650
nond
Token nond
Feature activation+0.000
esc
Tokenesc
Feature activation+0.000
ript
Tokenript
Feature activation+2.231
f
Token f
Feature activation+0.000

INTERVAL 1.238 - 1.856
CONTAINS 0.042%

at
Token at
Feature activation+0.186
the
Token the
Feature activation+0.000
very
Token very
Feature activation+0.000
time
Token time
Feature activation+1.378
they
Token they
Feature activation+0.000
made
Token made
Feature activation+1.402
that
Token that
Feature activation+0.000
invention
Token invention
Feature activation+0.000
.
Token.
Feature activation+1.340
He
Token He
Feature activation+0.000
worked
Token worked
Feature activation+0.000
rash
Token rash
Feature activation+0.000
of
Token of
Feature activation+0.172
bipartisan
Token bipartisan
Feature activation+0.268
efforts
Token efforts
Feature activation+0.000
in
Token in
Feature activation+0.461
the
Token the
Feature activation+1.801
House
Token House
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
Old
Token Old
Feature activation+0.036
CS
Token CS
Feature activation+0.000
flies
Token flies
Feature activation+0.000
have
Token have
Feature activation+0.461
significantly
Token significantly
Feature activation+0.000
lower
Token lower
Feature activation+1.612
fat
Token fat
Feature activation+0.000
levels
Token levels
Feature activation+0.000
prior
Token prior
Feature activation+0.000
to
Token to
Feature activation+1.757
starvation
Token starvation
Feature activation+0.000
with
Token with
Feature activation+1.335
Mark
Token Mark
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
.
Token.
Feature activation+2.208
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.786
Over
TokenOver
Feature activation+0.894
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
28
Token 28
Feature activation+0.000
years
Token years
Feature activation+2.211
,
Token,
Feature activation+1.380
this
Token this
Feature activation+0.000
is
Token is
Feature activation+4.516
not
Token not
Feature activation+3.848
one
Token one
Feature activation+0.000
of
Token of
Feature activation+1.765
them
Token them
Feature activation+0.000
.
Token.
Feature activation+1.467
He
Token He
Feature activation+0.000
moved
Token moved
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.619 - 1.238
CONTAINS 0.074%

4
Token 4
Feature activation+0.491
5
Token 5
Feature activation+0.000
6
Token 6
Feature activation+0.000
7
Token 7
Feature activation+0.000
8
Token 8
Feature activation+0.044
9
Token 9
Feature activation+0.785
10
Token 10
Feature activation+0.000
11
Token 11
Feature activation+0.000
12
Token 12
Feature activation+0.000
13
Token 13
Feature activation+0.000
14
Token 14
Feature activation+0.000
users
Token users
Feature activation+0.000
.
Token.
Feature activation+0.276
We
Token We
Feature activation+0.000
advise
Token advise
Feature activation+0.782
you
Token you
Feature activation+0.000
change
Token change
Feature activation+1.182
your
Token your
Feature activation+0.630
F
Token F
Feature activation+0.000
OV
TokenOV
Feature activation+0.000
setting
Token setting
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Tokenres
Feature activation+0.000
no
Tokenno
Feature activation+0.000
Police
Token Police
Feature activation+0.000
Department
Token Department
Feature activation+0.000
)
Token)
Feature activation+0.000
[
Token [
Feature activation+1.007
+
Token +
Feature activation+0.000
-
Token -
Feature activation+0.000
]
Token ]
Feature activation+0.000
Video
Token Video
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
Token The
Feature activation+0.000
starting
Token starting
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.053
was
Token was
Feature activation+3.190
positioned
Token positioned
Feature activation+0.000
as
Token as
Feature activation+1.006
a
Token a
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
,
Token,
Feature activation+1.601
and
Token and
Feature activation+2.956
a
Token a
Feature activation+0.000
elligence
Tokenelligence
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
said
Token said
Feature activation+0.623
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000

INTERVAL 0.000 - 0.619
CONTAINS 99.842%

box
Token box
Feature activation+0.000
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
the
Token the
Feature activation+0.000
Sprint
Token Sprint
Feature activation+0.000
2
Token 2
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
a
Token a
Feature activation+0.000
quick
Token quick
Feature activation+0.000
and
Token and
Feature activation+0.000
easy
Token easy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
moment
Token moment
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Ragnarok
Token Ragnarok
Feature activation+0.000
trailers
Token trailers
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
Beck
Token Beck
Feature activation+0.000
ett
Tokenett
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
stiffness
Token stiffness
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
right
Token right
Feature activation+0.000
lat
Token lat
Feature activation+0.000
muscle
Token muscle
Feature activation+0.000
elements
Token elements
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
suicide
Token suicide
Feature activation+0.000
hij
Token hij
Feature activation+0.000
acking
Tokenacking
Feature activation+0.000
plan
Token plan
Feature activation+0.000
were
Token were
Feature activation+0.000
known
Token known
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
1
Token 1
Feature activation+0.000
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
got
Token got
Feature activation+0.000
in
Token in
Feature activation+0.000
country
Token country
Feature activation+0.000
to
Token to
Feature activation+0.000
teach
Token teach
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H11.4: (feature 5854)

TOP ACTIVATIONS
MAX = 5.806

vs
Token vs
Feature activation+0.000
.
Token.
Feature activation+0.000
Qatar
Token Qatar
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.003
the
Token the
Feature activation+0.000
country
Token country
Feature activation+5.806
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.000
match
Token match
Feature activation+0.594
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.000
match
Token match
Feature activation+0.594
since
Token since
Feature activation+5.120
their
Token their
Feature activation+0.000
run
Token run
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Africa
Token Africa
Feature activation+0.000
the
Token the
Feature activation+0.428
goals
Token goals
Feature activation+0.276
the
Token the
Feature activation+0.692
team
Token team
Feature activation+0.000
has
Token has
Feature activation+0.000
given
Token given
Feature activation+4.702
up
Token up
Feature activation+0.000
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
and
Token and
Feature activation+0.000
lo
Token lo
Feature activation+0.000
fts
Tokenfts
Feature activation+0.846
one
Token one
Feature activation+0.000
to
Token to
Feature activation+4.599
Gray
Token Gray
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
with
Token with
Feature activation+1.020
Ottawa
Token Ottawa
Feature activation+0.000
to
Token to
Feature activation+0.021
set
Token set
Feature activation+2.967
up
Token up
Feature activation+4.118
a
Token a
Feature activation+2.785
$
Token $
Feature activation+0.000
400
Token400
Feature activation+0.000
million
Token million
Feature activation+2.097
Fisheries
Token Fisheries
Feature activation+0.000
9
Token9
Feature activation+0.000
dt
Tokendt
Feature activation+0.000
I
TokenI
Feature activation+0.000
Y
TokenY
Feature activation+0.000
9
Token9
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+3.873
GL
Token GL
Feature activation+0.000
A
TokenA
Feature activation+0.000
AD
TokenAD
Feature activation+0.000
(@
Token (@
Feature activation+0.000
gl
Tokengl
Feature activation+0.000
on
Token on
Feature activation+0.631
M
Token M
Feature activation+0.000
escal
Tokenescal
Feature activation+0.000
ito
Tokenito
Feature activation+0.000
and
Token and
Feature activation+2.073
finishing
Token finishing
Feature activation+3.849
on
Token on
Feature activation+2.468
the
Token the
Feature activation+0.000
Dawn
Token Dawn
Feature activation+0.000
Wall
Token Wall
Feature activation+0.000
.
Token.
Feature activation+0.723
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Well
TokenWell
Feature activation+0.886
,
Token,
Feature activation+3.269
now
Token now
Feature activation+2.753
that
Token that
Feature activation+3.848
repeal
Token repeal
Feature activation+0.000
has
Token has
Feature activation+0.000
gone
Token gone
Feature activation+0.000
through
Token through
Feature activation+0.000
,
Token,
Feature activation+1.841
portal
Token portal
Feature activation+0.000
.
Token.
Feature activation+1.858
Today
Token Today
Feature activation+2.449
was
Token was
Feature activation+1.449
the
Token the
Feature activation+0.000
day
Token day
Feature activation+3.838
of
Token of
Feature activation+2.540
its
Token its
Feature activation+0.000
initial
Token initial
Feature activation+0.000
test
Token test
Feature activation+0.000
run
Token run
Feature activation+0.000
destroy
Token destroy
Feature activation+1.297
the
Token the
Feature activation+0.327
world
Token world
Feature activation+0.000
-
Token -
Feature activation+0.612
not
Token not
Feature activation+0.000
that
Token that
Feature activation+3.835
M
Token M
Feature activation+0.000
ondo
Tokenondo
Feature activation+0.000
can
Token can
Feature activation+0.000
hear
Token hear
Feature activation+1.955
anything
Token anything
Feature activation+0.932
Is
Token Is
Feature activation+1.557
there
Token there
Feature activation+0.172
a
Token a
Feature activation+2.271
long
Token long
Feature activation+0.406
-
Token-
Feature activation+0.000
running
Tokenrunning
Feature activation+3.760
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+2.307
top
Token top
Feature activation+0.943
-
Token-
Feature activation+0.000
level
Tokenlevel
Feature activation+3.207
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
catching
Token catching
Feature activation+0.907
behind
Token behind
Feature activation+3.718
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.347
so
Token so
Feature activation+2.126
yeah
Token yeah
Feature activation+0.000
I
Token I
Feature activation+0.000
it
Token it
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.445
"
Token"
Feature activation+3.653
As
TokenAs
Feature activation+1.524
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.802
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
the
Token the
Feature activation+0.000
Winchester
Token Winchester
Feature activation+0.000
plant
Token plant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.645
The
TokenThe
Feature activation+3.648
US
Token US
Feature activation+0.568
entered
Token entered
Feature activation+0.000
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
I
Token I
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
guests
Token guests
Feature activation+0.000
but
Token but
Feature activation+2.371
the
Token the
Feature activation+0.000
instant
Token instant
Feature activation+3.590
he
Token he
Feature activation+0.000
saw
Token saw
Feature activation+3.075
the
Token the
Feature activation+0.000
tribal
Token tribal
Feature activation+0.000
woman
Token woman
Feature activation+1.485
can
Token can
Feature activation+0.000
be
Token be
Feature activation+2.485
mod
Token mod
Feature activation+0.000
elled
Tokenelled
Feature activation+0.040
as
Token as
Feature activation+1.270
a
Token a
Feature activation+3.576
finite
Token finite
Feature activation+1.810
sequences
Token sequences
Feature activation+1.892
of
Token of
Feature activation+1.777
states
Token states
Feature activation+0.000
,
Token,
Feature activation+0.445
Apocalypse
Token Apocalypse
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+2.554
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.557
When
TokenWhen
Feature activation+3.569
you
Token you
Feature activation+0.000
take
Token take
Feature activation+2.082
an
Token an
Feature activation+1.149
action
Token action
Feature activation+0.000
that
Token that
Feature activation+0.000
close
Token close
Feature activation+0.000
quarters
Token quarters
Feature activation+0.000
combat
Token combat
Feature activation+0.000
.
Token.
Feature activation+2.114
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.525
If
TokenIf
Feature activation+1.211
the
Token the
Feature activation+0.872
Army
Token Army
Feature activation+0.000
does
Token does
Feature activation+0.000
go
Token go
Feature activation+0.000
meaning
Token meaning
Feature activation+0.710
M
Token M
Feature activation+0.000
16
Token16
Feature activation+0.000
users
Token users
Feature activation+0.000
could
Token could
Feature activation+0.000
carry
Token carry
Feature activation+3.521
twice
Token twice
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+1.685
ammo
Token ammo
Feature activation+0.000
into
Token into
Feature activation+0.000
I
Token I
Feature activation+0.000
helicopter
Token helicopter
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
hangar
Token hangar
Feature activation+0.000
and
Token and
Feature activation+3.512
landing
Token landing
Feature activation+0.000
deck
Token deck
Feature activation+0.000
were
Token were
Feature activation+0.000
accordingly
Token accordingly
Feature activation+0.000
enlarged
Token enlarged
Feature activation+0.000

Top DFA by src position
MAX = 6.108

coach
Token coach
Feature activation-0.001
Top resid features:
Jim
Token Jim
Feature activation+0.003
Top resid features:
Curt
Token Curt
Feature activation+0.070
Top resid features:
in
Tokenin
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.099
Top resid features:
M
Token M
Feature activation+4.591
Top resid features:
bol
Tokenbol
Feature activation+0.007
Top resid features:
hi
Tokenhi
Feature activation+0.021
Top resid features:
turned
Token turned
Feature activation+0.004
Top resid features:
down
Token down
Feature activation+0.015
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
coach
Token coach
Feature activation-0.001
Top resid features:
Jim
Token Jim
Feature activation+0.001
Top resid features:
Curt
Token Curt
Feature activation+0.212
Top resid features:
in
Tokenin
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
M
Token M
Feature activation+4.047
Top resid features:
bol
Tokenbol
Feature activation+0.007
Top resid features:
hi
Tokenhi
Feature activation+0.022
Top resid features:
turned
Token turned
Feature activation+0.003
Top resid features:
down
Token down
Feature activation+0.031
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
draws
Token draws
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
loss
Token loss
Feature activation+0.001
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.034
Top resid features:
M
Token M
Feature activation+6.108
Top resid features:
bol
Tokenbol
Feature activation+0.013
Top resid features:
hi
Tokenhi
Feature activation+0.020
Top resid features:
has
Token has
Feature activation+0.026
Top resid features:
yet
Token yet
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
nickel
Token nickel
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.073
Top resid features:
M
Token M
Feature activation+5.496
Top resid features:
ink
Tokenink
Feature activation+0.008
Top resid features:
ah
Tokenah
Feature activation+0.005
Top resid features:
Fitzpatrick
Token Fitzpatrick
Feature activation+0.006
Top resid features:
comes
Token comes
Feature activation-0.000
Top resid features:
down
Token down
Feature activation+0.004
Top resid features:
ending
Token ending
Feature activation+0.011
Top resid features:
minimum
Token minimum
Feature activation+0.068
Top resid features:
processing
Token processing
Feature activation+0.014
Top resid features:
requirements
Token requirements
Feature activation+0.001
Top resid features:
(
Token (
Feature activation+0.025
Top resid features:
M
TokenM
Feature activation+5.430
Top resid features:
PR
TokenPR
Feature activation-0.033
Top resid features:
).
Token).
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
As
TokenAs
Feature activation+0.008
Top resid features:
told
Token told
Feature activation+0.009
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
about
Token about
Feature activation+0.023
Top resid features:
FCC
Token FCC
Feature activation-0.026
Top resid features:
commissioner
Token commissioner
Feature activation+0.040
Top resid features:
M
Token M
Feature activation+5.865
Top resid features:
ign
Tokenign
Feature activation+0.043
Top resid features:
on
Tokenon
Feature activation+0.015
Top resid features:
Cly
Token Cly
Feature activation-0.061
Top resid features:
burn
Tokenburn
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
I
TokenI
Feature activation+0.042
Top resid features:
had
Token had
Feature activation+0.040
Top resid features:
my
Token my
Feature activation+0.006
Top resid features:
eye
Token eye
Feature activation-0.000
Top resid features:
on
Token on
Feature activation+0.030
Top resid features:
M
Token M
Feature activation+2.687
Top resid features:
esc
Tokenesc
Feature activation+0.014
Top resid features:
a
Tokena
Feature activation+0.061
Top resid features:
-
Token-
Feature activation+0.046
Top resid features:
D
TokenD
Feature activation+0.021
Top resid features:
awn
Tokenawn
Feature activation+0.154
Top resid features:
told
Token told
Feature activation+0.005
Top resid features:
you
Token you
Feature activation+0.013
Top resid features:
about
Token about
Feature activation+0.019
Top resid features:
FCC
Token FCC
Feature activation-0.008
Top resid features:
commissioner
Token commissioner
Feature activation+0.030
Top resid features:
M
Token M
Feature activation+5.311
Top resid features:
ign
Tokenign
Feature activation+0.024
Top resid features:
on
Tokenon
Feature activation+0.014
Top resid features:
Cly
Token Cly
Feature activation-0.135
Top resid features:
burn
Tokenburn
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
bor
Tokenbor
Feature activation+0.001
Top resid features:
row
Tokenrow
Feature activation+0.001
Top resid features:
ed
Tokened
Feature activation+0.002
Top resid features:
"
Token"
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.003
Top resid features:
M
Token M
Feature activation+4.899
Top resid features:
AGES
TokenAGES
Feature activation+0.092
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
(
Token (
Feature activation+0.038
Top resid features:
she
Tokenshe
Feature activation+0.021
Top resid features:
would
Token would
Feature activation+0.014
Top resid features:
follows
Token follows
Feature activation+0.007
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
boss
Token boss
Feature activation+0.087
Top resid features:
battle
Token battle
Feature activation+0.007
Top resid features:
between
Token between
Feature activation+0.011
Top resid features:
M
Token M
Feature activation+4.480
Top resid features:
ondo
Tokenondo
Feature activation+0.128
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
g
Token g
Feature activation+0.012
Top resid features:
hou
Tokenhou
Feature activation-0.024
Top resid features:
Has
Token Has
Feature activation+0.021
Top resid features:
there
Token there
Feature activation+0.008
Top resid features:
been
Token been
Feature activation+0.008
Top resid features:
a
Token a
Feature activation-0.018
Top resid features:
wholesale
Token wholesale
Feature activation+0.028
Top resid features:
M
Token M
Feature activation+5.055
Top resid features:
(
Token(
Feature activation+0.296
Top resid features:
S
TokenS
Feature activation+0.020
Top resid features:
)
Token)
Feature activation+0.032
Top resid features:
P
TokenP
Feature activation+0.038
Top resid features:
expenses
Token expenses
Feature activation+0.010
Top resid features:
game
Token game
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
here
Token here
Feature activation-0.000
Top resid features:
's
Token's
Feature activation+0.047
Top resid features:
Willie
Token Willie
Feature activation+0.121
Top resid features:
M
Token M
Feature activation+4.644
Top resid features:
ays
Tokenays
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.035
Top resid features:
here
Token here
Feature activation-0.004
Top resid features:
's
Token's
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Updated
TokenUpdated
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
M
TokenM
Feature activation+2.226
Top resid features:
ood
Tokenood
Feature activation+0.044
Top resid features:
y
Tokeny
Feature activation+0.019
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
credit
Token credit
Feature activation+0.007
Top resid features:
rating
Token rating
Feature activation+0.001
Top resid features:
W
TokenW
Feature activation+0.015
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
variant
Token variant
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
M
Token M
Feature activation+2.545
Top resid features:
14
Token14
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
without
Token without
Feature activation-0.003
Top resid features:
L
Token L
Feature activation+0.098
Top resid features:
ili
Tokenili
Feature activation+0.030
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
father
Token father
Feature activation+0.028
Top resid features:
because
Token because
Feature activation+0.041
Top resid features:
M
Token M
Feature activation+4.018
Top resid features:
ua
Tokenua
Feature activation+0.023
Top resid features:
had
Token had
Feature activation+0.015
Top resid features:
stepped
Token stepped
Feature activation+0.001
Top resid features:
forward
Token forward
Feature activation+0.004
Top resid features:
into
Token into
Feature activation+0.008
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
mod
Token mod
Feature activation-0.002
Top resid features:
elled
Tokenelled
Feature activation+0.005
Top resid features:
as
Token as
Feature activation+0.052
Top resid features:
an
Token an
Feature activation+0.030
Top resid features:
M
Token M
Feature activation+2.765
Top resid features:
DP
TokenDP
Feature activation+0.077
Top resid features:
as
Token as
Feature activation+0.020
Top resid features:
well
Token well
Feature activation+0.003
Top resid features:
because
Token because
Feature activation+0.024
Top resid features:
one
Token one
Feature activation+0.025
Top resid features:
last
Token last
Feature activation+0.001
Top resid features:
ten
Token ten
Feature activation-0.002
Top resid features:
years
Token years
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
M
Token M
Feature activation+4.665
Top resid features:
asks
Tokenasks
Feature activation+0.045
Top resid features:
has
Token has
Feature activation+0.005
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
built
Token built
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.023
Top resid features:
replaced
Token replaced
Feature activation+0.023
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
meaning
Token meaning
Feature activation+0.025
Top resid features:
M
Token M
Feature activation+3.015
Top resid features:
16
Token16
Feature activation+0.006
Top resid features:
users
Token users
Feature activation+0.052
Top resid features:
could
Token could
Feature activation+0.025
Top resid features:
carry
Token carry
Feature activation+0.004
Top resid features:
twice
Token twice
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.036
Top resid features:
replaced
Token replaced
Feature activation+0.054
Top resid features:
it
Token it
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.116
Top resid features:
meaning
Token meaning
Feature activation+0.082
Top resid features:
M
Token M
Feature activation+2.675
Top resid features:
16
Token16
Feature activation+0.023
Top resid features:
users
Token users
Feature activation+0.064
Top resid features:
could
Token could
Feature activation+0.342
Top resid features:
carry
Token carry
Feature activation+0.059
Top resid features:
twice
Token twice
Feature activation+0.000
Top resid features:
ids
Tokenids
Feature activation+0.003
Top resid features:
hips
Tokenhips
Feature activation+0.027
Top resid features:
aft
Token aft
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
m
Token m
Feature activation+4.951
Top resid features:
ack
Tokenack
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Beginning
Token Beginning
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.07

Head 2: 0.06

Head 3: 0.05

Head 4: 0.37

Head 5: 0.04

Head 6: 0.07

Head 7: 0.06

Head 8: 0.09

Head 9: 0.06

Head 10: 0.05

Head 11: 0.04

Positive logits

M8.74

M6.29

m5.16

MQ4.24

m3.25

mosqu2.89

Moose2.62

MFT2.55

MV2.51

mummy2.43

MH2.38

MU2.36

Mb2.34

MEP2.26

mound2.25

MG2.25

Rena2.24

Ment2.22

moth2.21

MN2.21

Negative logits

istor-2.90

acious-2.35

ieties-2.34

ewski-2.29

atron-2.27

ihad-2.27

ppo-2.25

oppable-2.21

ilus-2.19

nas-2.16

illum-2.15

uador-2.15

brates-2.15

pp-2.14

ndra-2.14

rets-2.13

icer-2.12

icum-2.12

agne-2.10

gat-2.09

INTERVAL 5.225 - 5.806
CONTAINS 0.000%

vs
Token vs
Feature activation+0.000
.
Token.
Feature activation+0.000
Qatar
Token Qatar
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.003
the
Token the
Feature activation+0.000
country
Token country
Feature activation+5.806
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.000
match
Token match
Feature activation+0.594

INTERVAL 4.645 - 5.225
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.000
match
Token match
Feature activation+0.594
since
Token since
Feature activation+5.120
their
Token their
Feature activation+0.000
run
Token run
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Africa
Token Africa
Feature activation+0.000
the
Token the
Feature activation+0.428
goals
Token goals
Feature activation+0.276
the
Token the
Feature activation+0.692
team
Token team
Feature activation+0.000
has
Token has
Feature activation+0.000
given
Token given
Feature activation+4.702
up
Token up
Feature activation+0.000
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000

INTERVAL 4.064 - 4.645
CONTAINS 0.000%

off
Tokenoff
Feature activation+0.000
and
Token and
Feature activation+0.000
lo
Token lo
Feature activation+0.000
fts
Tokenfts
Feature activation+0.846
one
Token one
Feature activation+0.000
to
Token to
Feature activation+4.599
Gray
Token Gray
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
with
Token with
Feature activation+1.020
Ottawa
Token Ottawa
Feature activation+0.000
to
Token to
Feature activation+0.021
set
Token set
Feature activation+2.967
up
Token up
Feature activation+4.118
a
Token a
Feature activation+2.785
$
Token $
Feature activation+0.000
400
Token400
Feature activation+0.000
million
Token million
Feature activation+2.097
Fisheries
Token Fisheries
Feature activation+0.000

INTERVAL 3.484 - 4.064
CONTAINS 0.002%

Apocalypse
Token Apocalypse
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+2.554
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.557
When
TokenWhen
Feature activation+3.569
you
Token you
Feature activation+0.000
take
Token take
Feature activation+2.082
an
Token an
Feature activation+1.149
action
Token action
Feature activation+0.000
that
Token that
Feature activation+0.000
really
Token really
Feature activation+0.165
,
Token,
Feature activation+1.832
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
deserve
Token deserve
Feature activation+2.159
a
Token a
Feature activation+3.504
warm
Token warm
Feature activation+1.349
meal
Token meal
Feature activation+0.000
).
Token).
Feature activation+0.635
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.278
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
catching
Token catching
Feature activation+0.907
behind
Token behind
Feature activation+3.718
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.347
so
Token so
Feature activation+2.126
yeah
Token yeah
Feature activation+0.000
I
Token I
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
guests
Token guests
Feature activation+0.000
but
Token but
Feature activation+2.371
the
Token the
Feature activation+0.000
instant
Token instant
Feature activation+3.590
he
Token he
Feature activation+0.000
saw
Token saw
Feature activation+3.075
the
Token the
Feature activation+0.000
tribal
Token tribal
Feature activation+0.000
woman
Token woman
Feature activation+1.485
destroy
Token destroy
Feature activation+1.297
the
Token the
Feature activation+0.327
world
Token world
Feature activation+0.000
-
Token -
Feature activation+0.612
not
Token not
Feature activation+0.000
that
Token that
Feature activation+3.835
M
Token M
Feature activation+0.000
ondo
Tokenondo
Feature activation+0.000
can
Token can
Feature activation+0.000
hear
Token hear
Feature activation+1.955
anything
Token anything
Feature activation+0.932

INTERVAL 2.903 - 3.484
CONTAINS 0.004%

take
Token take
Feature activation+2.082
an
Token an
Feature activation+1.149
action
Token action
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
trigger
Token trigger
Feature activation+3.232
a
Token a
Feature activation+0.266
move
Token move
Feature activation+0.000
,
Token,
Feature activation+3.019
you
Token you
Feature activation+0.000
roll
Token roll
Feature activation+0.000
running
Tokenrunning
Feature activation+3.760
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+2.307
top
Token top
Feature activation+0.943
-
Token-
Feature activation+0.000
level
Tokenlevel
Feature activation+3.207
conspiracy
Token conspiracy
Feature activation+0.000
on
Token on
Feature activation+0.579
child
Token child
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
or
Token or
Feature activation+0.465
somewhat
Token somewhat
Feature activation+0.000
compelling
Token compelling
Feature activation+0.092
in
Token in
Feature activation+0.997
itself
Token itself
Feature activation+0.000
.
Token.
Feature activation+2.591
But
Token But
Feature activation+2.938
more
Token more
Feature activation+0.000
significantly
Token significantly
Feature activation+2.075
,
Token,
Feature activation+2.265
according
Token according
Feature activation+0.067
to
Token to
Feature activation+2.236
to
Token to
Feature activation+0.000
hurt
Token hurt
Feature activation+0.564
anybody
Token anybody
Feature activation+0.000
's
Token's
Feature activation+0.000
feelings
Token feelings
Feature activation+0.000
,"
Token,"
Feature activation+2.950
Hon
Token Hon
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
choking
Token choking
Feature activation+0.000
for
Token for
Feature activation+1.208
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.498
I
Token I
Feature activation+0.000
once
Token once
Feature activation+0.000
asked
Token asked
Feature activation+3.038
the
Token the
Feature activation+0.000
late
Token late
Feature activation+1.065
Miguel
Token Miguel
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
ran
Tokenran
Feature activation+0.000

INTERVAL 2.322 - 2.903
CONTAINS 0.008%

he
Token he
Feature activation+0.000
previews
Token previews
Feature activation+1.056
the
Token the
Feature activation+0.414
second
Token second
Feature activation+0.000
race
Token race
Feature activation+0.000
of
Token of
Feature activation+2.742
the
Token the
Feature activation+1.076
2009
Token 2009
Feature activation+1.137
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
Dawn
Token Dawn
Feature activation+0.000
Wall
Token Wall
Feature activation+0.000
.
Token.
Feature activation+0.723
It
Token It
Feature activation+0.000
seemed
Token seemed
Feature activation+2.326
to
Token to
Feature activation+0.000
me
Token me
Feature activation+1.094
then
Token then
Feature activation+0.732
to
Token to
Feature activation+0.000
be
Token be
Feature activation+2.111
conversation
Token conversation
Feature activation+1.520
with
Token with
Feature activation+3.512
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
guests
Token guests
Feature activation+0.000
but
Token but
Feature activation+2.371
the
Token the
Feature activation+0.000
instant
Token instant
Feature activation+3.590
he
Token he
Feature activation+0.000
saw
Token saw
Feature activation+3.075
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
ES
TokenES
Feature activation+0.000
I
TokenI
Feature activation+0.000
).
Token).
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+2.411
E
Token E
Feature activation+0.000
SI
TokenSI
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
usually
Token usually
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
L
TokenL
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ik
Tokenik
Feature activation+2.689
Can
Token Can
Feature activation+0.000
a
Tokena
Feature activation+0.000
's
Token's
Feature activation+0.000
last
Token last
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.742 - 2.322
CONTAINS 0.018%

have
Token have
Feature activation+0.000
his
Token his
Feature activation+0.000
hands
Token hands
Feature activation+0.000
full
Token full
Feature activation+0.000
dealing
Token dealing
Feature activation+0.000
with
Token with
Feature activation+1.782
Atlanta
Token Atlanta
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
talented
Token talented
Feature activation+0.000
application
Token application
Feature activation+0.000
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
from
Token from
Feature activation+0.094
the
Token the
Feature activation+1.958
Windows
Token Windows
Feature activation+0.000
Phone
Token Phone
Feature activation+0.000
Marketplace
Token Marketplace
Feature activation+0.000
.
Token.
Feature activation+0.132
Ċ
TokenĊ
Feature activation+0.000
VC
TokenVC
Feature activation+0.000
)
Token)
Feature activation+1.029
pattern
Token pattern
Feature activation+0.000
,
Token,
Feature activation+0.902
since
Token since
Feature activation+1.302
most
Token most
Feature activation+1.754
developers
Token developers
Feature activation+0.000
are
Token are
Feature activation+0.568
familiar
Token familiar
Feature activation+0.000
with
Token with
Feature activation+1.446
it
Token it
Feature activation+0.000
because
Tokenbecause
Feature activation+1.370
really
Token really
Feature activation+0.165
,
Token,
Feature activation+1.832
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
deserve
Token deserve
Feature activation+2.159
a
Token a
Feature activation+3.504
warm
Token warm
Feature activation+1.349
meal
Token meal
Feature activation+0.000
).
Token).
Feature activation+0.635
Ċ
TokenĊ
Feature activation+0.000
how
Token how
Feature activation+0.867
they
Token they
Feature activation+0.000
mist
Token mist
Feature activation+0.000
reat
Tokenreat
Feature activation+0.214
Latinos
Token Latinos
Feature activation+0.000
in
Token in
Feature activation+2.189
their
Token their
Feature activation+0.780
custody
Token custody
Feature activation+0.000
and
Token and
Feature activation+0.000
Latinos
Token Latinos
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 1.161 - 1.742
CONTAINS 0.037%

ok
Tokenok
Feature activation+0.000
atana
Tokenatana
Feature activation+1.700
Star
Token Star
Feature activation+0.000
comes
Token comes
Feature activation+0.000
with
Token with
Feature activation+2.224
all
Token all
Feature activation+1.177
the
Token the
Feature activation+1.214
brow
Token brow
Feature activation+0.000
colour
Token colour
Feature activation+0.000
options
Token options
Feature activation+0.486
you
Token you
Feature activation+0.000
ful
Tokenful
Feature activation+1.175
ball
Token ball
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
(
Token (
Feature activation+0.000
more
Tokenmore
Feature activation+0.000
on
Token on
Feature activation+1.420
that
Token that
Feature activation+0.000
later
Token later
Feature activation+0.000
)
Token)
Feature activation+1.196
this
Token this
Feature activation+0.000
song
Token song
Feature activation+0.000
said
Token said
Feature activation+0.000
M
Token M
Feature activation+0.000
x
Tokenx
Feature activation+0.000
.
Token.
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+1.422
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
new
Tokennew
Feature activation+0.000
-
Token-
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+1.420
classic
Token classic
Feature activation+1.908
model
Token model
Feature activation+0.153
-
Token-
Feature activation+0.000
view
Tokenview
Feature activation+0.073
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.366
Now
TokenNow
Feature activation+0.498
we
Token we
Feature activation+0.000
know
Token know
Feature activation+0.514
our
Token our
Feature activation+1.323
IP
Token IP
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
add
Token add
Feature activation+0.545

INTERVAL 0.581 - 1.161
CONTAINS 0.070%

.
Token.
Feature activation+0.723
It
Token It
Feature activation+0.000
seemed
Token seemed
Feature activation+2.326
to
Token to
Feature activation+0.000
me
Token me
Feature activation+1.094
then
Token then
Feature activation+0.732
to
Token to
Feature activation+0.000
be
Token be
Feature activation+2.111
the
Token the
Feature activation+0.000
true
Token true
Feature activation+0.474
line
Token line
Feature activation+0.058
run
Token run
Feature activation+0.000
small
Token small
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.971
them
Token them
Feature activation+0.000
supply
Token supply
Feature activation+0.000
goods
Token goods
Feature activation+0.000
and
Token and
Feature activation+0.000
services
Token services
Feature activation+0.000
M
Token M
Feature activation+0.000
ua
Tokenua
Feature activation+0.000
's
Token's
Feature activation+0.000
passing
Token passing
Feature activation+0.000
echoes
Token echoes
Feature activation+0.000
though
Token though
Feature activation+0.889
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
's
Token's
Feature activation+0.000
population
Token population
Feature activation+0.000
but
Token but
Feature activation+0.755
were
Token were
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
information
Token information
Feature activation+0.000
,
Token,
Feature activation+0.865
they
Token they
Feature activation+0.000
found
Token found
Feature activation+0.000
big
Token big
Feature activation+0.000
premium
Token premium
Feature activation+0.000
increases
Token increases
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.861
To
TokenTo
Feature activation+0.118
be
Token be
Feature activation+0.000
clear
Token clear
Feature activation+1.424
,
Token,
Feature activation+0.848
even
Token even
Feature activation+0.804
if
Token if
Feature activation+0.933
there
Token there
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 0.000 - 0.581
CONTAINS 99.861%

angu
Tokenangu
Feature activation+0.000
inis
Tokeninis
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
frequency
Token frequency
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
tongue
Token tongue
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Tokenan
Feature activation+0.000
mi
Tokenmi
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
reached
Token reached
Feature activation+0.000
for
Token for
Feature activation+0.000
comment
Token comment
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
plus
Token plus
Feature activation+0.000
for
Token for
Feature activation+0.000
big
Token big
Feature activation+0.000
s
Tokens
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
makes
Token makes
Feature activation+0.000
inaccurate
Token inaccurate
Feature activation+0.000
statements
Token statements
Feature activation+0.000
about
Token about
Feature activation+0.000
government
Token government
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
and
Token and
Feature activation+0.000
fails
Token fails
Feature activation+0.000
to
Token to
Feature activation+0.000
correct
Token correct
Feature activation+0.000
the
Token the
Feature activation+0.000
15
Token15
Feature activation+0.000
.
Token.
Feature activation+0.000
Jason
Token Jason
Feature activation+0.000
Ford
Token Ford
Feature activation+0.000
e
Tokene
Feature activation+0.000
(
Token (
Feature activation+0.000
Silver
TokenSilver
Feature activation+0.000
min
Tokenmin
Feature activation+0.000
es
Tokenes
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H11.4: (feature 15867)

TOP ACTIVATIONS
MAX = 5.533

2001
Token 2001
Feature activation+0.000
.
Token.
Feature activation+1.718
In
Token In
Feature activation+0.638
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.317
year
Token year
Feature activation+5.533
of
Token of
Feature activation+0.885
its
Token its
Feature activation+0.000
existence
Token existence
Feature activation+1.356
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.844
,
Token,
Feature activation+2.892
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+1.289
Alice
Token Alice
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000
,
Token,
Feature activation+5.397
Kerr
Token Kerr
Feature activation+0.000
is
Token is
Feature activation+0.000
conducting
Token conducting
Feature activation+0.331
super
Token super
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+2.476
platform
Token platform
Feature activation+0.000
world
Token world
Feature activation+0.000
between
Token between
Feature activation+3.495
the
Token the
Feature activation+2.034
whole
Token whole
Feature activation+5.136
ex
Token ex
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
/
Token /
Feature activation+0.000
genome
Token genome
Feature activation+0.000
camp
Token camp
Feature activation+0.000
for
Token for
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
.
Token.
Feature activation+3.793
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.764
The
TokenThe
Feature activation+1.449
landslide
Token landslide
Feature activation+1.148
that
Token that
Feature activation+2.400
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
woman
Token woman
Feature activation+0.000
's
Token's
Feature activation+0.000
mother
Token mother
Feature activation+0.000
have
Token have
Feature activation+0.000
criticised
Token criticised
Feature activation+2.672
Mr
Token Mr
Feature activation+4.645
Johns
Token Johns
Feature activation+0.000
for
Token for
Feature activation+0.000
not
Token not
Feature activation+0.000
going
Token going
Feature activation+0.000
far
Token far
Feature activation+0.000
the
Token the
Feature activation+2.889
world
Token world
Feature activation+0.000
regarding
Token regarding
Feature activation+2.708
inequality
Token inequality
Feature activation+0.000
and
Token and
Feature activation+1.337
so
Token so
Feature activation+4.266
N
Token N
Feature activation+0.000
EM
TokenEM
Feature activation+0.000
equality
Token equality
Feature activation+0.000
experiment
Token experiment
Feature activation+0.219
comes
Token comes
Feature activation+0.000
remember
Token remember
Feature activation+1.660
2000
Token 2000
Feature activation+0.000
are
Token are
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
associate
Token associate
Feature activation+4.080
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.628
v
Tokenv
Feature activation+0.000
oting
Tokenoting
Feature activation+0.141
your
Token your
Feature activation+0.000
arc
Tokenarc
Feature activation+0.000
eny
Tokeneny
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+1.600
police
Token police
Feature activation+0.000
said
Token said
Feature activation+4.076
that
Token that
Feature activation+2.481
more
Token more
Feature activation+0.000
charges
Token charges
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
mode
Token mode
Feature activation+0.000
.
Token.
Feature activation+2.189
Through
Token Through
Feature activation+2.368
the
Token the
Feature activation+2.134
browser
Token browser
Feature activation+0.191
interface
Token interface
Feature activation+3.899
,
Token,
Feature activation+3.505
the
Token the
Feature activation+2.132
N
Token N
Feature activation+0.693
900
Token900
Feature activation+0.787
can
Token can
Feature activation+0.000
for
Token for
Feature activation+2.662
a
Token a
Feature activation+0.000
California
Token California
Feature activation+0.000
biotech
Token biotech
Feature activation+0.000
lab
Token lab
Feature activation+0.000
.
Token.
Feature activation+3.837
In
Token In
Feature activation+1.369
collaboration
Token collaboration
Feature activation+1.551
with
Token with
Feature activation+1.870
N
Token N
Feature activation+0.000
aylor
Tokenaylor
Feature activation+1.575
from
Token from
Feature activation+0.000
academics
Token academics
Feature activation+0.000
for
Token for
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
.
Token.
Feature activation+3.793
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.764
The
TokenThe
Feature activation+1.449
landslide
Token landslide
Feature activation+1.148
that
Token that
Feature activation+2.400
on
Token on
Feature activation+0.000
administrative
Token administrative
Feature activation+0.000
leave
Token leave
Feature activation+0.000
until
Token until
Feature activation+2.404
it
Token it
Feature activation+0.000
determines
Token determines
Feature activation+3.771
the
Token the
Feature activation+0.000
Delta
Token Delta
Feature activation+0.000
Nu
Token Nu
Feature activation+0.000
chapter
Token chapter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
flashes
Token flashes
Feature activation+0.000
of
Token of
Feature activation+0.000
brilliance
Token brilliance
Feature activation+0.000
.
Token.
Feature activation+3.629
N
Token N
Feature activation+0.000
j
Tokenj
Feature activation+0.000
oku
Tokenoku
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
already
Token already
Feature activation+0.000
,
Token,
Feature activation+2.518
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
covert
Token covert
Feature activation+0.000
study
Token study
Feature activation+3.623
in
Token in
Feature activation+0.000
which
Token which
Feature activation+2.475
prisoners
Token prisoners
Feature activation+0.000
were
Token were
Feature activation+0.000
subjected
Token subjected
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.416
because
Token because
Feature activation+1.564
in
Token in
Feature activation+0.649
October
Token October
Feature activation+3.621
the
Token the
Feature activation+0.668
following
Token following
Feature activation+1.393
year
Token year
Feature activation+0.972
1901
Token 1901
Feature activation+1.520
,
Token,
Feature activation+0.925
ini
Tokenini
Feature activation+0.000
-
Token-
Feature activation+0.000
Z
TokenZ
Feature activation+0.000
uma
Tokenuma
Feature activation+0.000
would
Token would
Feature activation+0.000
find
Token find
Feature activation+3.541
themselves
Token themselves
Feature activation+0.000
in
Token in
Feature activation+0.552
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
void
Token void
Feature activation+0.000
ing
Tokening
Feature activation+0.301
her
Token her
Feature activation+0.000
passport
Token passport
Feature activation+0.000
and
Token and
Feature activation+0.000
turning
Token turning
Feature activation+3.530
her
Token her
Feature activation+0.005
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.357
Kenya
Token Kenya
Feature activation+0.000
for
Token for
Feature activation+0.000
.
Token.
Feature activation+2.189
Through
Token Through
Feature activation+2.368
the
Token the
Feature activation+2.134
browser
Token browser
Feature activation+0.191
interface
Token interface
Feature activation+3.899
,
Token,
Feature activation+3.505
the
Token the
Feature activation+2.132
N
Token N
Feature activation+0.693
900
Token900
Feature activation+0.787
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
divide
Token divide
Feature activation+0.000
in
Token in
Feature activation+2.280
the
Token the
Feature activation+2.476
platform
Token platform
Feature activation+0.000
world
Token world
Feature activation+0.000
between
Token between
Feature activation+3.495
the
Token the
Feature activation+2.034
whole
Token whole
Feature activation+5.136
ex
Token ex
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
/
Token /
Feature activation+0.000
is
Tokenis
Feature activation+0.000
wrote
Token wrote
Feature activation+0.476
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.419
So
TokenSo
Feature activation+3.415
far
Token far
Feature activation+1.095
,
Token,
Feature activation+1.880
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
only
Token only
Feature activation+0.000

Top DFA by src position
MAX = 6.397

server
Token server
Feature activation+0.005
Top resid features:
as
Token as
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
successor
Token successor
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
N
Token N
Feature activation+6.397
Top resid features:
up
Tokenup
Feature activation+0.034
Top resid features:
edia
Tokenedia
Feature activation+0.042
Top resid features:
.
Token.
Feature activation+0.322
Top resid features:
Its
Token Its
Feature activation+0.053
Top resid features:
first
Token first
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
FBI
Token FBI
Feature activation+0.018
Top resid features:
director
Token director
Feature activation-0.000
Top resid features:
Mad
Token Mad
Feature activation+0.026
Top resid features:
eline
Tokeneline
Feature activation-0.002
Top resid features:
N
Token N
Feature activation+4.176
Top resid features:
aylor
Tokenaylor
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
who
Token who
Feature activation+0.016
Top resid features:
believes
Token believes
Feature activation+0.025
Top resid features:
criminals
Token criminals
Feature activation+0.013
Top resid features:
conference
Token conference
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
push
Token push
Feature activation+0.005
Top resid features:
towards
Token towards
Feature activation+0.023
Top resid features:
N
Token N
Feature activation+6.229
Top resid features:
GS
TokenGS
Feature activation+0.029
Top resid features:
continues
Token continues
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
c
Tokenc
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
support
Token support
Feature activation+0.008
Top resid features:
from
Token from
Feature activation+0.020
Top resid features:
academics
Token academics
Feature activation+0.013
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
N
Token N
Feature activation+5.521
Top resid features:
ader
Tokenader
Feature activation+0.086
Top resid features:
.
Token.
Feature activation+0.709
Top resid features:
âĢ
Token âĢ
Feature activation+0.029
Top resid features:
ľ
Tokenľ
Feature activation+0.080
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
K
TokenK
Feature activation+0.006
Top resid features:
atherine
Tokenatherine
Feature activation+0.053
Top resid features:
N
Token N
Feature activation+6.135
Top resid features:
att
Tokenatt
Feature activation+0.102
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
24
Token 24
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
died
Token died
Feature activation+0.001
Top resid features:
I
Token I
Feature activation-0.023
Top resid features:
found
Token found
Feature activation+0.025
Top resid features:
myself
Token myself
Feature activation+0.015
Top resid features:
reflecting
Token reflecting
Feature activation+0.018
Top resid features:
on
Token on
Feature activation+0.081
Top resid features:
N
Token N
Feature activation+4.677
Top resid features:
EM
TokenEM
Feature activation+0.053
Top resid features:
,
Token,
Feature activation+0.071
Top resid features:
what
Token what
Feature activation+0.052
Top resid features:
it
Token it
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.007
Top resid features:
combined
Token combined
Feature activation+0.005
Top resid features:
vote
Token vote
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
N
Token N
Feature activation+5.359
Top resid features:
ader
Tokenader
Feature activation+0.058
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
Green
Token Green
Feature activation+0.012
Top resid features:
candidates
Token candidates
Feature activation+0.004
Top resid features:
since
Token since
Feature activation+0.008
Top resid features:
On
TokenOn
Feature activation+0.021
Top resid features:
his
Token his
Feature activation+0.017
Top resid features:
Twitter
Token Twitter
Feature activation+0.013
Top resid features:
account
Token account
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.076
Top resid features:
N
Token N
Feature activation+4.740
Top resid features:
ott
Tokenott
Feature activation+0.212
Top resid features:
is
Tokenis
Feature activation+0.087
Top resid features:
wrote
Token wrote
Feature activation+0.019
Top resid features:
:
Token:
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
WiFi
Token WiFi
Feature activation+0.015
Top resid features:
radios
Token radios
Feature activation+0.011
Top resid features:
inside
Token inside
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
N
Token N
Feature activation+5.075
Top resid features:
900
Token900
Feature activation+0.040
Top resid features:
can
Token can
Feature activation+0.005
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
turned
Token turned
Feature activation-0.006
Top resid features:
off
Token off
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
FBI
Token FBI
Feature activation+0.010
Top resid features:
director
Token director
Feature activation-0.007
Top resid features:
Mad
Token Mad
Feature activation+0.034
Top resid features:
eline
Tokeneline
Feature activation-0.003
Top resid features:
N
Token N
Feature activation+4.937
Top resid features:
aylor
Tokenaylor
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.151
Top resid features:
who
Token who
Feature activation+0.040
Top resid features:
believes
Token believes
Feature activation+0.021
Top resid features:
criminals
Token criminals
Feature activation+0.009
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
support
Token support
Feature activation+0.015
Top resid features:
from
Token from
Feature activation+0.022
Top resid features:
academics
Token academics
Feature activation+0.020
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
N
Token N
Feature activation+4.591
Top resid features:
ader
Tokenader
Feature activation+0.056
Top resid features:
.
Token.
Feature activation+0.561
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
University
Token University
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
Southern
Token Southern
Feature activation-0.009
Top resid features:
Mississippi
Token Mississippi
Feature activation+0.023
Top resid features:
barred
Token barred
Feature activation+0.024
Top resid features:
N
Token N
Feature activation+2.618
Top resid features:
ott
Tokenott
Feature activation+0.017
Top resid features:
is
Tokenis
Feature activation+0.024
Top resid features:
from
Token from
Feature activation+0.020
Top resid features:
campus
Token campus
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.072
Top resid features:
My
TokenMy
Feature activation-0.022
Top resid features:
les
Tokenles
Feature activation+0.012
Top resid features:
Garrett
Token Garrett
Feature activation+0.126
Top resid features:
and
Token and
Feature activation+0.090
Top resid features:
David
Token David
Feature activation+0.187
Top resid features:
N
Token N
Feature activation+4.346
Top resid features:
j
Tokenj
Feature activation+0.128
Top resid features:
oku
Tokenoku
Feature activation+0.062
Top resid features:
for
Token for
Feature activation+0.015
Top resid features:
example
Token example
Feature activation+0.027
Top resid features:
have
Token have
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
FBI
Token FBI
Feature activation+0.004
Top resid features:
director
Token director
Feature activation-0.001
Top resid features:
Mad
Token Mad
Feature activation+0.004
Top resid features:
eline
Tokeneline
Feature activation-0.002
Top resid features:
N
Token N
Feature activation+2.482
Top resid features:
aylor
Tokenaylor
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
who
Token who
Feature activation+0.017
Top resid features:
believes
Token believes
Feature activation+0.011
Top resid features:
criminals
Token criminals
Feature activation+0.005
Top resid features:
Julian
Token Julian
Feature activation+0.023
Top resid features:
Pal
Token Pal
Feature activation+0.017
Top resid features:
ac
Tokenac
Feature activation+0.003
Top resid features:
ios
Tokenios
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
N
Token N
Feature activation+3.430
Top resid features:
ue
Tokenue
Feature activation+0.003
Top resid features:
va
Tokenva
Feature activation+0.003
Top resid features:
Soc
Token Soc
Feature activation-0.000
Top resid features:
ied
Tokenied
Feature activation+0.002
Top resid features:
ad
Tokenad
Feature activation+0.003
Top resid features:
That
TokenThat
Feature activation+0.016
Top resid features:
said
Token said
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.136
Top resid features:
backers
Token backers
Feature activation+0.022
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
N
Token N
Feature activation+4.701
Top resid features:
kos
Tokenkos
Feature activation+0.010
Top resid features:
az
Tokenaz
Feature activation+0.000
Top resid features:
ana
Tokenana
Feature activation+0.001
Top resid features:
D
Token D
Feature activation+0.071
Top resid features:
lam
Tokenlam
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
Canada
Token Canada
Feature activation+0.024
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
embassy
Token embassy
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
N
Token N
Feature activation+2.723
Top resid features:
airo
Tokenairo
Feature activation+0.007
Top resid features:
bi
Tokenbi
Feature activation+0.013
Top resid features:
issued
Token issued
Feature activation+0.006
Top resid features:
her
Token her
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
WiFi
Token WiFi
Feature activation+0.014
Top resid features:
radios
Token radios
Feature activation+0.006
Top resid features:
inside
Token inside
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
N
Token N
Feature activation+4.491
Top resid features:
900
Token900
Feature activation+0.041
Top resid features:
can
Token can
Feature activation+0.005
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
turned
Token turned
Feature activation-0.004
Top resid features:
off
Token off
Feature activation-0.003
Top resid features:
conference
Token conference
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
push
Token push
Feature activation+0.009
Top resid features:
towards
Token towards
Feature activation+0.025
Top resid features:
N
Token N
Feature activation+4.426
Top resid features:
GS
TokenGS
Feature activation+0.018
Top resid features:
continues
Token continues
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.018
Top resid features:
on
Token on
Feature activation+0.013
Top resid features:
c
Tokenc
Feature activation-0.002
Top resid features:
On
TokenOn
Feature activation+0.038
Top resid features:
his
Token his
Feature activation+0.052
Top resid features:
Twitter
Token Twitter
Feature activation+0.025
Top resid features:
account
Token account
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.099
Top resid features:
N
Token N
Feature activation+4.419
Top resid features:
ott
Tokenott
Feature activation+0.138
Top resid features:
is
Tokenis
Feature activation+0.044
Top resid features:
wrote
Token wrote
Feature activation+0.025
Top resid features:
:
Token:
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.06

Head 2: 0.05

Head 3: 0.06

Head 4: 0.37

Head 5: 0.04

Head 6: 0.07

Head 7: 0.06

Head 8: 0.09

Head 9: 0.04

Head 10: 0.05

Head 11: 0.05

Positive logits

N9.37

N7.29

n5.69

Ns4.86

n4.39

NCT3.64

NF3.26

NIC2.98

Verb2.97

NK2.96

NTS2.94

NP2.74

NW2.70

NW2.70

NC2.68

NB2.66

Nab2.65

NT2.64

NC2.62

NA2.61

Negative logits

obal-2.57

inventoryQuantity-2.38

adeon-2.33

maxwell-2.29

ffen-2.20

ocene-2.18

ozo-2.13

yx-2.12

isner-2.12

alez-2.09

rawl-2.07

uten-2.06

etooth-2.06

gow-2.01

=-=--2.01

effic-2.00

espie-1.97

exerc-1.95

itable-1.95

aston-1.92

INTERVAL 4.980 - 5.533
CONTAINS 0.000%

the
Token the
Feature activation+2.476
platform
Token platform
Feature activation+0.000
world
Token world
Feature activation+0.000
between
Token between
Feature activation+3.495
the
Token the
Feature activation+2.034
whole
Token whole
Feature activation+5.136
ex
Token ex
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
/
Token /
Feature activation+0.000
genome
Token genome
Feature activation+0.000
camp
Token camp
Feature activation+0.000
,
Token,
Feature activation+2.892
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+1.289
Alice
Token Alice
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000
,
Token,
Feature activation+5.397
Kerr
Token Kerr
Feature activation+0.000
is
Token is
Feature activation+0.000
conducting
Token conducting
Feature activation+0.331
super
Token super
Feature activation+0.000
-
Token-
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
.
Token.
Feature activation+1.718
In
Token In
Feature activation+0.638
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.317
year
Token year
Feature activation+5.533
of
Token of
Feature activation+0.885
its
Token its
Feature activation+0.000
existence
Token existence
Feature activation+1.356
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.844

INTERVAL 4.427 - 4.980
CONTAINS 0.000%

woman
Token woman
Feature activation+0.000
's
Token's
Feature activation+0.000
mother
Token mother
Feature activation+0.000
have
Token have
Feature activation+0.000
criticised
Token criticised
Feature activation+2.672
Mr
Token Mr
Feature activation+4.645
Johns
Token Johns
Feature activation+0.000
for
Token for
Feature activation+0.000
not
Token not
Feature activation+0.000
going
Token going
Feature activation+0.000
far
Token far
Feature activation+0.000
for
Token for
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
.
Token.
Feature activation+3.793
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.764
The
TokenThe
Feature activation+1.449
landslide
Token landslide
Feature activation+1.148
that
Token that
Feature activation+2.400
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 3.873 - 4.427
CONTAINS 0.000%

arc
Tokenarc
Feature activation+0.000
eny
Tokeneny
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+1.600
police
Token police
Feature activation+0.000
said
Token said
Feature activation+4.076
that
Token that
Feature activation+2.481
more
Token more
Feature activation+0.000
charges
Token charges
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
mode
Token mode
Feature activation+0.000
.
Token.
Feature activation+2.189
Through
Token Through
Feature activation+2.368
the
Token the
Feature activation+2.134
browser
Token browser
Feature activation+0.191
interface
Token interface
Feature activation+3.899
,
Token,
Feature activation+3.505
the
Token the
Feature activation+2.132
N
Token N
Feature activation+0.693
900
Token900
Feature activation+0.787
can
Token can
Feature activation+0.000
remember
Token remember
Feature activation+1.660
2000
Token 2000
Feature activation+0.000
are
Token are
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
associate
Token associate
Feature activation+4.080
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.628
v
Tokenv
Feature activation+0.000
oting
Tokenoting
Feature activation+0.141
your
Token your
Feature activation+0.000
the
Token the
Feature activation+2.889
world
Token world
Feature activation+0.000
regarding
Token regarding
Feature activation+2.708
inequality
Token inequality
Feature activation+0.000
and
Token and
Feature activation+1.337
so
Token so
Feature activation+4.266
N
Token N
Feature activation+0.000
EM
TokenEM
Feature activation+0.000
equality
Token equality
Feature activation+0.000
experiment
Token experiment
Feature activation+0.219
comes
Token comes
Feature activation+0.000

INTERVAL 3.320 - 3.873
CONTAINS 0.002%

from
Token from
Feature activation+0.000
academics
Token academics
Feature activation+0.000
for
Token for
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
.
Token.
Feature activation+3.793
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.764
The
TokenThe
Feature activation+1.449
landslide
Token landslide
Feature activation+1.148
that
Token that
Feature activation+2.400
,
Token,
Feature activation+1.699
what
Token what
Feature activation+2.492
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
and
Token and
Feature activation+0.888
what
Token what
Feature activation+3.350
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
want
Token want
Feature activation+1.194
to
Token to
Feature activation+0.000
make
Token make
Feature activation+2.972
is
Tokenis
Feature activation+0.000
wrote
Token wrote
Feature activation+0.476
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.419
So
TokenSo
Feature activation+3.415
far
Token far
Feature activation+1.095
,
Token,
Feature activation+1.880
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
only
Token only
Feature activation+0.000
void
Token void
Feature activation+0.000
ing
Tokening
Feature activation+0.301
her
Token her
Feature activation+0.000
passport
Token passport
Feature activation+0.000
and
Token and
Feature activation+0.000
turning
Token turning
Feature activation+3.530
her
Token her
Feature activation+0.005
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.357
Kenya
Token Kenya
Feature activation+0.000
for
Token for
Feature activation+0.000
on
Token on
Feature activation+0.000
administrative
Token administrative
Feature activation+0.000
leave
Token leave
Feature activation+0.000
until
Token until
Feature activation+2.404
it
Token it
Feature activation+0.000
determines
Token determines
Feature activation+3.771
the
Token the
Feature activation+0.000
Delta
Token Delta
Feature activation+0.000
Nu
Token Nu
Feature activation+0.000
chapter
Token chapter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 2.767 - 3.320
CONTAINS 0.004%

Mark
Token Mark
Feature activation+0.000
Johns
Token Johns
Feature activation+0.000
said
Token said
Feature activation+1.711
a
Token a
Feature activation+0.000
suicide
Token suicide
Feature activation+0.000
note
Token note
Feature activation+3.007
left
Token left
Feature activation+0.689
by
Token by
Feature activation+1.654
the
Token the
Feature activation+0.216
Adelaide
Token Adelaide
Feature activation+0.000
woman
Token woman
Feature activation+0.000
(
Token (
Feature activation+0.446
In
TokenIn
Feature activation+0.352
an
Token an
Feature activation+0.000
ironic
Token ironic
Feature activation+0.000
reversal
Token reversal
Feature activation+0.000
,
Token,
Feature activation+3.018
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
third
Token third
Feature activation+0.000
-
Token-
Feature activation+0.000
party
Tokenparty
Feature activation+0.000
form
Token form
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.947
Mad
TokenMad
Feature activation+0.000
rid
Tokenrid
Feature activation+0.000
currently
Token currently
Feature activation+0.000
lead
Token lead
Feature activation+0.000
rivals
Token rivals
Feature activation+0.000
more
Token more
Feature activation+0.000
discreet
Token discreet
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
with
Token with
Feature activation+0.559
his
Token his
Feature activation+3.100
basic
Token basic
Feature activation+1.547
,
Token,
Feature activation+0.855
white
Token white
Feature activation+1.469
sneakers
Token sneakers
Feature activation+0.000
.
Token.
Feature activation+0.283
upon
Token upon
Feature activation+0.000
Himself
Token Himself
Feature activation+0.000
.
Token.
Feature activation+0.366
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.719
in
Token in
Feature activation+3.052
part
Token part
Feature activation+0.000
three
Token three
Feature activation+0.000
of
Token of
Feature activation+0.696
Chronicles
Token Chronicles
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.213 - 2.767
CONTAINS 0.009%

material
Token material
Feature activation+0.000
in
Token in
Feature activation+0.017
late
Token late
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+1.178
when
Token when
Feature activation+2.281
the
Token the
Feature activation+2.224
press
Token press
Feature activation+0.000
was
Token was
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.331
Before
TokenBefore
Feature activation+1.571
her
Token her
Feature activation+0.000
death
Token death
Feature activation+2.256
,
Token,
Feature activation+0.869
Ms
Token Ms
Feature activation+0.438
N
Token N
Feature activation+0.152
att
Tokenatt
Feature activation+0.000
worked
Token worked
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
funding
Tokenfunding
Feature activation+0.000
round
Token round
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+2.218
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.044
There
TokenThere
Feature activation+0.000
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
threshold
Token threshold
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
whether
Token whether
Feature activation+0.000
each
Token each
Feature activation+2.340
band
Token band
Feature activation+0.000
it
Tokenit
Feature activation+0.000
steals
Token steals
Feature activation+0.000
100
Token 100
Feature activation+1.194
beans
Token beans
Feature activation+0.000
for
Token for
Feature activation+2.579
a
Token a
Feature activation+0.647
program
Token program
Feature activation+0.000
to
Token to
Feature activation+0.000
communicate
Token communicate
Feature activation+0.000
with
Token with
Feature activation+2.441
the
Token the
Feature activation+1.741
Bor
Token Bor
Feature activation+0.000
land
Tokenland
Feature activation+0.219
debugger
Token debugger
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 1.660 - 2.213
CONTAINS 0.018%

ľ
Tokenľ
Feature activation+0.249
st
Tokenst
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
born
Tokenborn
Feature activation+0.000
integrity
Token integrity
Feature activation+0.000
kept
Token kept
Feature activation+1.685
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
safe
Token safe
Feature activation+0.000
and
Token and
Feature activation+0.000
turned
Token turned
Feature activation+2.099
the
Token the
Feature activation+0.735
gods
Token gods
Feature activation+0.000
,
Token,
Feature activation+0.135
Vall
Token Vall
Feature activation+0.000
halla
Tokenhalla
Feature activation+0.000
being
Token being
Feature activation+1.856
the
Token the
Feature activation+0.000
heaven
Token heaven
Feature activation+0.000
version
Token version
Feature activation+0.000
.
Token.
Feature activation+1.501
You
Token You
Feature activation+0.000
n
Token n
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
days
Token days
Feature activation+0.930
pass
Token pass
Feature activation+2.743
,
Token,
Feature activation+2.075
none
Token none
Feature activation+0.532
of
Token of
Feature activation+0.718
the
Token the
Feature activation+1.624
blue
Token blue
Feature activation+0.000
-
Token-
Feature activation+0.000
founded
Token founded
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+1.914
three
Token three
Feature activation+2.145
teams
Token teams
Feature activation+0.000
formerly
Token formerly
Feature activation+0.000
of
Token of
Feature activation+0.088
the
Token the
Feature activation+0.859
Premier
Token Premier
Feature activation+0.000
.
Token.
Feature activation+2.871
When
Token When
Feature activation+2.656
Kerr
Token Kerr
Feature activation+0.000
is
Token is
Feature activation+0.000
told
Token told
Feature activation+2.874
that
Token that
Feature activation+1.962
her
Token her
Feature activation+0.000
theories
Token theories
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
implemented
Token implemented
Feature activation+0.000

INTERVAL 1.107 - 1.660
CONTAINS 0.034%

of
Token of
Feature activation+0.000
N
Token N
Feature activation+0.000
arn
Tokenarn
Feature activation+0.000
ia
Tokenia
Feature activation+0.404
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.162
The
TokenThe
Feature activation+0.496
White
Token White
Feature activation+0.000
Witch
Token Witch
Feature activation+0.000
runs
Token runs
Feature activation+0.000
a
Token a
Feature activation+0.000
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.148
to
Token to
Feature activation+0.000
genocide
Token genocide
Feature activation+0.000
.
Token.
Feature activation+0.313
And
Token And
Feature activation+1.117
so
Token so
Feature activation+1.260
in
Token in
Feature activation+0.017
this
Token this
Feature activation+0.000
way
Token way
Feature activation+1.474
,
Token,
Feature activation+0.724
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.682
This
TokenThis
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
tapped
Token tapped
Feature activation+0.131
into
Token into
Feature activation+1.572
readers
Token readers
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
rage
Token rage
Feature activation+0.000
when
Token when
Feature activation+0.810
of
Token of
Feature activation+0.718
the
Token the
Feature activation+1.624
blue
Token blue
Feature activation+0.000
-
Token-
Feature activation+0.000
eyed
Tokeneyed
Feature activation+0.986
people
Token people
Feature activation+1.421
do
Token do
Feature activation+0.428
so
Token so
Feature activation+0.419
(
Token (
Feature activation+0.984
because
Tokenbecause
Feature activation+1.546
at
Token at
Feature activation+0.629
ur
Tokenur
Feature activation+0.000
am
Tokenam
Feature activation+0.000
in
Token in
Feature activation+2.192
Tamil
Token Tamil
Feature activation+0.000
Nadu
Token Nadu
Feature activation+0.000
from
Token from
Feature activation+1.294
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
police
Token police
Feature activation+0.000
nab
Token nab
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000

INTERVAL 0.553 - 1.107
CONTAINS 0.061%

Ċ
TokenĊ
Feature activation+1.224
Up
TokenUp
Feature activation+0.000
dating
Tokendating
Feature activation+1.557
with
Token with
Feature activation+1.574
additional
Token additional
Feature activation+1.010
information
Token information
Feature activation+0.806
and
Token and
Feature activation+0.000
clarification
Token clarification
Feature activation+0.120
:
Token:
Feature activation+1.747
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.901
and
Token and
Feature activation+0.000
N
Token N
Feature activation+0.000
iff
Tokeniff
Feature activation+0.000
el
Tokenel
Feature activation+0.000
heim
Tokenheim
Feature activation+0.000
and
Token and
Feature activation+0.800
the
Token the
Feature activation+1.110
granted
Token granted
Feature activation+1.937
the
Token the
Feature activation+0.088
title
Token title
Feature activation+1.995
of
Token of
Feature activation+0.897
Ċ
TokenĊ
Feature activation+0.000
President
TokenPresident
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
two
Token two
Feature activation+0.592
Republicans
Token Republicans
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+1.903
five
Token five
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.093
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.025
Additionally
TokenAdditionally
Feature activation+0.000
,
Token,
Feature activation+0.851
on
Token on
Feature activation+0.000
[
Token [
Feature activation+0.265
her
Tokenher
Feature activation+0.000
]
Token]
Feature activation+0.000
website
Token website
Feature activation+0.073
obtain
Token obtain
Feature activation+0.000
water
Token water
Feature activation+0.000
,
Token,
Feature activation+0.311
according
Token according
Feature activation+0.306
to
Token to
Feature activation+0.374
data
Token data
Feature activation+1.020
from
Token from
Feature activation+0.000
Global
Token Global
Feature activation+0.000
Water
Token Water
Feature activation+0.000
Intelligence
Token Intelligence
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.553
CONTAINS 99.872%

their
Token their
Feature activation+0.000
character
Token character
Feature activation+0.000
rank
Token rank
Feature activation+0.000
and
Token and
Feature activation+0.000
character
Token character
Feature activation+0.000
rib
Token rib
Feature activation+0.000
bons
Tokenbons
Feature activation+0.000
and
Token and
Feature activation+0.000
badges
Token badges
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.000
job
Token job
Feature activation+0.000
of
Token of
Feature activation+0.000
decoding
Token decoding
Feature activation+0.000
home
Token home
Feature activation+0.000
improvement
Token improvement
Feature activation+0.000
,
Token,
Feature activation+0.000
remod
Token remod
Feature activation+0.000
eling
Tokeneling
Feature activation+0.000
and
Token and
Feature activation+0.000
repairs
Token repairs
Feature activation+0.000
,
Token,
Feature activation+0.000
gardening
Token gardening
Feature activation+0.000
and
Token and
Feature activation+0.000
landsc
Token landsc
Feature activation+0.000
voters
Token voters
Feature activation+0.000
still
Token still
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
vote
Token vote
Feature activation+0.000
more
Token more
Feature activation+0.000
based
Token based
Feature activation+0.000
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
's
Token's
Feature activation+0.000
iss
Tokeniss
Feature activation+0.000
made
Token made
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
embodies
Token embodies
Feature activation+0.000
a
Token a
Feature activation+0.000
concept
Token concept
Feature activation+0.000
of
Token of
Feature activation+0.000
quality
Token quality
Feature activation+0.000
that
Token that
Feature activation+0.000
includes
Token includes
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 H11.4: (feature 14082)

TOP ACTIVATIONS
MAX = 5.100

letter
Token letter
Feature activation+0.000
this
Token this
Feature activation+0.000
past
Token past
Feature activation+0.000
fall
Token fall
Feature activation+0.000
informing
Token informing
Feature activation+1.898
them
Token them
Feature activation+5.034
that
Token that
Feature activation+1.987
allowing
Token allowing
Feature activation+1.573
such
Token such
Feature activation+0.000
prose
Token prose
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
in
Tokenin
Feature activation+0.506
a
Token a
Feature activation+0.000
tone
Token tone
Feature activation+3.803
of
Token of
Feature activation+0.000
voice
Token voice
Feature activation+0.689
that
Token that
Feature activation+4.929
suggested
Token suggested
Feature activation+3.877
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
angry
Token angry
Feature activation+0.000
an
Token an
Feature activation+0.000
integral
Token integral
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+2.116
life
Token life
Feature activation+0.000
and
Token and
Feature activation+4.882
culture
Token culture
Feature activation+0.000
in
Token in
Feature activation+0.562
this
Token this
Feature activation+0.000
vast
Token vast
Feature activation+0.000
city
Token city
Feature activation+0.000
them
Token them
Feature activation+0.000
from
Token from
Feature activation+0.000
cheating
Token cheating
Feature activation+0.863
to
Token to
Feature activation+0.000
gain
Token gain
Feature activation+0.000
advantage
Token advantage
Feature activation+4.805
.
Token.
Feature activation+0.895
CH
Token CH
Feature activation+0.000
E
TokenE
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
to
Token to
Feature activation+0.000
He
Token He
Feature activation+0.000
trips
Token trips
Feature activation+3.514
and
Token and
Feature activation+2.150
falls
Token falls
Feature activation+0.000
,
Token,
Feature activation+2.593
then
Token then
Feature activation+4.592
suddenly
Token suddenly
Feature activation+3.767
finds
Token finds
Feature activation+3.139
himself
Token himself
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+4.573
then
Token then
Feature activation+4.592
suddenly
Token suddenly
Feature activation+3.767
finds
Token finds
Feature activation+3.139
himself
Token himself
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+4.573
a
Token a
Feature activation+0.000
country
Token country
Feature activation+0.000
road
Token road
Feature activation+0.000
,
Token,
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
.
Token.
Feature activation+2.961
So
Token So
Feature activation+1.664
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
surprising
Token surprising
Feature activation+4.509
that
Token that
Feature activation+3.392
the
Token the
Feature activation+0.412
bill
Token bill
Feature activation+0.000
then
Token then
Feature activation+0.000
moved
Token moved
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
Arm
Token Arm
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
ister
Tokenister
Feature activation+0.000
.
Token.
Feature activation+2.345
And
Token And
Feature activation+4.340
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.358
when
Token when
Feature activation+2.484
we
Token we
Feature activation+0.000
really
Token really
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
Blue
Token Blue
Feature activation+0.549
Mustang
Token Mustang
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.686
first
Token first
Feature activation+4.263
production
Token production
Feature activation+2.890
hard
Token hard
Feature activation+0.000
top
Tokentop
Feature activation+1.015
assigned
Token assigned
Feature activation+0.000
a
Token a
Feature activation+0.041
taxpayer
Token taxpayer
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
flowing
Token flowing
Feature activation+0.000
its
Token its
Feature activation+0.000
way
Token way
Feature activation+0.000
despite
Token despite
Feature activation+4.206
its
Token its
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.984
child
Token child
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
supply
Token supply
Feature activation+0.000
problem
Token problem
Feature activation+0.000
,"
Token,"
Feature activation+2.347
Saunders
Token Saunders
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+4.011
"
Token "
Feature activation+0.895
We
TokenWe
Feature activation+0.000
just
Token just
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
quite
Token quite
Feature activation+0.000
big
Token big
Feature activation+0.000
.
Token.
Feature activation+3.922
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sony
TokenSony
Feature activation+0.000
Pictures
Token Pictures
Feature activation+0.000
boss
Token boss
Feature activation+0.000
ple
Token ple
Feature activation+0.000
a
Token a
Feature activation+0.000
tone
Token tone
Feature activation+3.803
of
Token of
Feature activation+0.000
voice
Token voice
Feature activation+0.689
that
Token that
Feature activation+4.929
suggested
Token suggested
Feature activation+3.877
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
angry
Token angry
Feature activation+0.000
and
Token and
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
in
Tokenin
Feature activation+0.506
a
Token a
Feature activation+0.000
tone
Token tone
Feature activation+3.803
of
Token of
Feature activation+0.000
voice
Token voice
Feature activation+0.689
that
Token that
Feature activation+4.929
suggested
Token suggested
Feature activation+3.877
he
Token he
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
was
Token was
Feature activation+0.000
Pete
Token Pete
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
.
Token.
Feature activation+1.520
And
Token And
Feature activation+3.803
we
Token we
Feature activation+0.000
had
Token had
Feature activation+1.780
a
Token a
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
trips
Token trips
Feature activation+3.514
and
Token and
Feature activation+2.150
falls
Token falls
Feature activation+0.000
,
Token,
Feature activation+2.593
then
Token then
Feature activation+4.592
suddenly
Token suddenly
Feature activation+3.767
finds
Token finds
Feature activation+3.139
himself
Token himself
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+4.573
a
Token a
Feature activation+0.000
assumes
Token assumes
Feature activation+1.288
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.205
talking
Token talking
Feature activation+3.760
about
Token about
Feature activation+1.515
a
Token a
Feature activation+0.825
quality
Token quality
Feature activation+0.906
watch
Token watch
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+2.249
Braz
Token Braz
Feature activation+0.000
au
Tokenau
Feature activation+0.000
had
Token had
Feature activation+0.000
argued
Token argued
Feature activation+1.984
that
Token that
Feature activation+3.760
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
intend
Token intend
Feature activation+0.327
to
Token to
Feature activation+0.000
MM
Token MM
Feature activation+0.000
Y
TokenY
Feature activation+0.000
,
Token,
Feature activation+2.007
European
Token European
Feature activation+0.000
players
Token players
Feature activation+0.000
like
Token like
Feature activation+3.717
F
Token F
Feature activation+0.000
ATA
TokenATA
Feature activation+0.000
and
Token and
Feature activation+0.414
X
Token X
Feature activation+0.000
bo
Tokenbo
Feature activation+0.000
19
Token 19
Feature activation+0.000
assists
Token assists
Feature activation+0.000
in
Token in
Feature activation+0.000
82
Token 82
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+3.677
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.941
D
TokenD
Feature activation+0.000
erek
Tokenerek
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000

Top DFA by src position
MAX = 6.359

Freedom
Token Freedom
Feature activation-0.026
Top resid features:
From
Token From
Feature activation-0.001
Top resid features:
Religion
Token Religion
Feature activation+0.013
Top resid features:
Foundation
Token Foundation
Feature activation-0.001
Top resid features:
sent
Token sent
Feature activation+0.044
Top resid features:
C
Token C
Feature activation+3.876
Top resid features:
apps
Tokenapps
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.050
Top resid features:
Ļ
TokenĻ
Feature activation+0.023
Top resid features:
district
Token district
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
Braz
Token Braz
Feature activation+0.064
Top resid features:
au
Tokenau
Feature activation+0.006
Top resid features:
had
Token had
Feature activation+0.019
Top resid features:
argued
Token argued
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
C
Token C
Feature activation+6.033
Top resid features:
lements
Tokenlements
Feature activation+0.054
Top resid features:
said
Token said
Feature activation+0.008
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
College
Token College
Feature activation+0.024
Top resid features:
daily
Token daily
Feature activation-0.003
Top resid features:
commute
Token commute
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
For
TokenFor
Feature activation+0.010
Top resid features:
C
Token C
Feature activation+4.181
Top resid features:
resp
Tokenresp
Feature activation+0.014
Top resid features:
o
Tokeno
Feature activation+0.007
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
other
Token other
Feature activation+0.025
Top resid features:
player
Token player
Feature activation+0.046
Top resid features:
Worldwide
Token Worldwide
Feature activation-0.082
Top resid features:
!!
Token!!
Feature activation+0.060
Top resid features:
C
Token C
Feature activation+6.359
Top resid features:
ATCH
TokenATCH
Feature activation+0.010
Top resid features:
CPU
Token CPU
Feature activation-0.035
Top resid features:
players
Token players
Feature activation+0.112
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
prevent
Token prevent
Feature activation+0.025
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
hall
Token hall
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
with
Token with
Feature activation+0.084
Top resid features:
C
Token C
Feature activation+4.558
Top resid features:
ane
Tokenane
Feature activation+0.041
Top resid features:
's
Token's
Feature activation+0.019
Top resid features:
monsters
Token monsters
Feature activation+0.015
Top resid features:
close
Token close
Feature activation+0.007
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
down
Token down
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
hall
Token hall
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
with
Token with
Feature activation+0.078
Top resid features:
C
Token C
Feature activation+4.275
Top resid features:
ane
Tokenane
Feature activation+0.030
Top resid features:
's
Token's
Feature activation+0.012
Top resid features:
monsters
Token monsters
Feature activation+0.009
Top resid features:
close
Token close
Feature activation+0.011
Top resid features:
on
Token on
Feature activation+0.005
Top resid features:
general
Token general
Feature activation+0.006
Top resid features:
settled
Token settled
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
case
Token case
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.013
Top resid features:
C
Token C
Feature activation+3.734
Top resid features:
MD
TokenMD
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
2014
Token 2014
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
paying
Token paying
Feature activation+0.003
Top resid features:
made
Token made
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.042
Top resid features:
Joe
Token Joe
Feature activation+0.026
Top resid features:
Morgan
Token Morgan
Feature activation+0.068
Top resid features:
for
Token for
Feature activation+0.045
Top resid features:
C
Token C
Feature activation+5.674
Top resid features:
esar
Tokenesar
Feature activation+0.012
Top resid features:
Ger
Token Ger
Feature activation+0.017
Top resid features:
on
Tokenon
Feature activation+0.000
Top resid features:
imo
Tokenimo
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.046
Top resid features:
Complex
Token Complex
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.040
Top resid features:
This
TokenThis
Feature activation+0.059
Top resid features:
C
Token C
Feature activation+5.845
Top resid features:
asp
Tokenasp
Feature activation+0.003
Top resid features:
ian
Tokenian
Feature activation+0.020
Top resid features:
Blue
Token Blue
Feature activation-0.078
Top resid features:
Mustang
Token Mustang
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
Soldiers
Token Soldiers
Feature activation+0.001
Top resid features:
Prevention
Token Prevention
Feature activation+0.002
Top resid features:
Act
Token Act
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
or
Token or
Feature activation+0.002
Top resid features:
C
Token C
Feature activation+5.645
Top resid features:
SPA
TokenSPA
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
after
Token after
Feature activation+0.039
Top resid features:
South
Token South
Feature activation-0.021
Top resid features:
spokesperson
Token spokesperson
Feature activation+0.004
Top resid features:
Wendy
Token Wendy
Feature activation-0.003
Top resid features:
Saunders
Token Saunders
Feature activation+0.023
Top resid features:
said
Token said
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.144
Top resid features:
C
Token C
Feature activation+2.810
Top resid features:
ADA
TokenADA
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
public
Token public
Feature activation+0.010
Top resid features:
agency
Token agency
Feature activation+0.003
Top resid features:
club
Token club
Feature activation+0.004
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
sporting
Token sporting
Feature activation+0.004
Top resid features:
director
Token director
Feature activation+0.022
Top resid features:
Antonio
Token Antonio
Feature activation-0.012
Top resid features:
C
Token C
Feature activation+4.943
Top resid features:
ordon
Tokenordon
Feature activation+0.056
Top resid features:
revealed
Token revealed
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.052
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
striker
Token striker
Feature activation-0.002
Top resid features:
Braz
Token Braz
Feature activation+0.053
Top resid features:
au
Tokenau
Feature activation+0.013
Top resid features:
had
Token had
Feature activation+0.007
Top resid features:
argued
Token argued
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
C
Token C
Feature activation+4.939
Top resid features:
lements
Tokenlements
Feature activation+0.060
Top resid features:
said
Token said
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
College
Token College
Feature activation+0.011
Top resid features:
Braz
Token Braz
Feature activation+0.061
Top resid features:
au
Tokenau
Feature activation+0.006
Top resid features:
had
Token had
Feature activation+0.009
Top resid features:
argued
Token argued
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
C
Token C
Feature activation+4.778
Top resid features:
lements
Tokenlements
Feature activation+0.044
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
College
Token College
Feature activation+0.015
Top resid features:
made
Token made
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.015
Top resid features:
Joe
Token Joe
Feature activation+0.018
Top resid features:
Morgan
Token Morgan
Feature activation+0.031
Top resid features:
for
Token for
Feature activation+0.014
Top resid features:
C
Token C
Feature activation+5.050
Top resid features:
esar
Tokenesar
Feature activation+0.013
Top resid features:
Ger
Token Ger
Feature activation+0.011
Top resid features:
on
Tokenon
Feature activation+0.000
Top resid features:
imo
Tokenimo
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
down
Token down
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
hall
Token hall
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.051
Top resid features:
with
Token with
Feature activation+0.062
Top resid features:
C
Token C
Feature activation+3.890
Top resid features:
ane
Tokenane
Feature activation+0.036
Top resid features:
's
Token's
Feature activation+0.016
Top resid features:
monsters
Token monsters
Feature activation+0.020
Top resid features:
close
Token close
Feature activation+0.009
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.029
Top resid features:
just
Token just
Feature activation+0.010
Top resid features:
about
Token about
Feature activation+0.016
Top resid features:
any
Token any
Feature activation+0.016
Top resid features:
fresh
Token fresh
Feature activation+0.063
Top resid features:
C
Token C
Feature activation+4.630
Top resid features:
NC
TokenNC
Feature activation+0.113
Top resid features:
part
Token part
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
they
Token they
Feature activation+0.009
Top resid features:
must
Token must
Feature activation+0.009
Top resid features:
Braz
Token Braz
Feature activation+0.045
Top resid features:
au
Tokenau
Feature activation+0.007
Top resid features:
had
Token had
Feature activation+0.004
Top resid features:
argued
Token argued
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
C
Token C
Feature activation+4.246
Top resid features:
lements
Tokenlements
Feature activation+0.039
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
College
Token College
Feature activation+0.033
Top resid features:
transfer
Token transfer
Feature activation+0.006
Top resid features:
window
Token window
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.063
Top resid features:
Aside
Token Aside
Feature activation+0.002
Top resid features:
from
Token from
Feature activation+0.026
Top resid features:
C
Token C
Feature activation+4.446
Top resid features:
ty
Tokenty
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.156
Top resid features:
H
Token H
Feature activation-0.166
Top resid features:
ao
Tokenao
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.241
Top resid features:
2016
Token 2016
Feature activation-0.003
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
2017
Token2017
Feature activation+0.001
Top resid features:
season
Token season
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.126
Top resid features:
C
Token C
Feature activation+2.045
Top resid features:
ogl
Tokenogl
Feature activation+0.015
Top resid features:
iano
Tokeniano
Feature activation+0.008
Top resid features:
scored
Token scored
Feature activation+0.012
Top resid features:
16
Token 16
Feature activation-0.006
Top resid features:
goals
Token goals
Feature activation-0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.05

Head 3: 0.06

Head 4: 0.37

Head 5: 0.05

Head 6: 0.06

Head 7: 0.05

Head 8: 0.09

Head 9: 0.06

Head 10: 0.05

Head 11: 0.05

Positive logits

C8.34

C6.14

c5.23

c4.16

Cs3.78

Ce3.02

cider2.88

CMS2.62

cpp2.61

Ced2.50

Ces2.46

cuff2.41

cus2.40

CU2.40

CPR2.37

CIS2.33

Celsius2.30

CCC2.24

caul2.21

CK2.21

Negative logits

utra-2.43

hran-2.27

jri-2.23

soever-2.16

nob-2.03

gew-2.03

DragonMagazine-1.97

era-1.96

ettel-1.96

enegger-1.94

seeker-1.85

dstg-1.85

raq-1.84

ophon-1.84

earth-1.82

lag-1.82

atari-1.78

wash-1.77

agara-1.76

phony-1.75

INTERVAL 4.590 - 5.100
CONTAINS 0.001%

an
Token an
Feature activation+0.000
integral
Token integral
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+2.116
life
Token life
Feature activation+0.000
and
Token and
Feature activation+4.882
culture
Token culture
Feature activation+0.000
in
Token in
Feature activation+0.562
this
Token this
Feature activation+0.000
vast
Token vast
Feature activation+0.000
city
Token city
Feature activation+0.000
in
Tokenin
Feature activation+0.506
a
Token a
Feature activation+0.000
tone
Token tone
Feature activation+3.803
of
Token of
Feature activation+0.000
voice
Token voice
Feature activation+0.689
that
Token that
Feature activation+4.929
suggested
Token suggested
Feature activation+3.877
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
angry
Token angry
Feature activation+0.000
He
Token He
Feature activation+0.000
trips
Token trips
Feature activation+3.514
and
Token and
Feature activation+2.150
falls
Token falls
Feature activation+0.000
,
Token,
Feature activation+2.593
then
Token then
Feature activation+4.592
suddenly
Token suddenly
Feature activation+3.767
finds
Token finds
Feature activation+3.139
himself
Token himself
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+4.573
them
Token them
Feature activation+0.000
from
Token from
Feature activation+0.000
cheating
Token cheating
Feature activation+0.863
to
Token to
Feature activation+0.000
gain
Token gain
Feature activation+0.000
advantage
Token advantage
Feature activation+4.805
.
Token.
Feature activation+0.895
CH
Token CH
Feature activation+0.000
E
TokenE
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
to
Token to
Feature activation+0.000
letter
Token letter
Feature activation+0.000
this
Token this
Feature activation+0.000
past
Token past
Feature activation+0.000
fall
Token fall
Feature activation+0.000
informing
Token informing
Feature activation+1.898
them
Token them
Feature activation+5.034
that
Token that
Feature activation+1.987
allowing
Token allowing
Feature activation+1.573
such
Token such
Feature activation+0.000
prose
Token prose
Feature activation+0.000
ly
Tokenly
Feature activation+0.000

INTERVAL 4.080 - 4.590
CONTAINS 0.001%

.
Token.
Feature activation+2.961
So
Token So
Feature activation+1.664
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
surprising
Token surprising
Feature activation+4.509
that
Token that
Feature activation+3.392
the
Token the
Feature activation+0.412
bill
Token bill
Feature activation+0.000
then
Token then
Feature activation+0.000
moved
Token moved
Feature activation+0.000
then
Token then
Feature activation+4.592
suddenly
Token suddenly
Feature activation+3.767
finds
Token finds
Feature activation+3.139
himself
Token himself
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+4.573
a
Token a
Feature activation+0.000
country
Token country
Feature activation+0.000
road
Token road
Feature activation+0.000
,
Token,
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
Blue
Token Blue
Feature activation+0.549
Mustang
Token Mustang
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.686
first
Token first
Feature activation+4.263
production
Token production
Feature activation+2.890
hard
Token hard
Feature activation+0.000
top
Tokentop
Feature activation+1.015
assigned
Token assigned
Feature activation+0.000
a
Token a
Feature activation+0.041
taxpayer
Token taxpayer
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
flowing
Token flowing
Feature activation+0.000
its
Token its
Feature activation+0.000
way
Token way
Feature activation+0.000
despite
Token despite
Feature activation+4.206
its
Token its
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.984
child
Token child
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
Arm
Token Arm
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
ister
Tokenister
Feature activation+0.000
.
Token.
Feature activation+2.345
And
Token And
Feature activation+4.340
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.358
when
Token when
Feature activation+2.484
we
Token we
Feature activation+0.000
really
Token really
Feature activation+0.000

INTERVAL 3.570 - 4.080
CONTAINS 0.002%

the
Token the
Feature activation+0.000
door
Token door
Feature activation+0.000
,"
Token,"
Feature activation+2.450
Saunders
Token Saunders
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+3.634
Property
Token Property
Feature activation+0.000
managers
Token managers
Feature activation+0.000
said
Token said
Feature activation+2.893
the
Token the
Feature activation+0.449
wait
Token wait
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
-
Token-
Feature activation+0.000
scenes
Tokenscenes
Feature activation+0.315
negotiations
Token negotiations
Feature activation+0.000
with
Token with
Feature activation+3.642
Cricket
Token Cricket
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
and
Token and
Feature activation+2.218
will
Token will
Feature activation+0.000
see
Token see
Feature activation+2.896
ju
Tokenju
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
or
Token or
Feature activation+0.000
Dar
Token Dar
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
.
Token.
Feature activation+3.640
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.096
Until
TokenUntil
Feature activation+1.241
this
Token this
Feature activation+0.000
weekend
Token weekend
Feature activation+2.177
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+2.031
low
Token low
Feature activation+0.000
inventory
Token inventory
Feature activation+0.000
.
Token.
Feature activation+3.599
"
Token "
Feature activation+0.904
In
TokenIn
Feature activation+0.212
my
Token my
Feature activation+0.000
view
Token view
Feature activation+0.549
,
Token,
Feature activation+1.626
trips
Token trips
Feature activation+3.514
and
Token and
Feature activation+2.150
falls
Token falls
Feature activation+0.000
,
Token,
Feature activation+2.593
then
Token then
Feature activation+4.592
suddenly
Token suddenly
Feature activation+3.767
finds
Token finds
Feature activation+3.139
himself
Token himself
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+4.573
a
Token a
Feature activation+0.000

INTERVAL 3.060 - 3.570
CONTAINS 0.003%

,
Token,
Feature activation+0.105
25
Token 25
Feature activation+0.000
percent
Token percent
Feature activation+0.000
being
Token being
Feature activation+0.490
affordable
Token affordable
Feature activation+0.000
.
Token.
Feature activation+3.268
"
Token "
Feature activation+1.567
We
TokenWe
Feature activation+0.000
open
Token open
Feature activation+0.000
up
Token up
Feature activation+0.537
our
Token our
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+2.868
the
Token the
Feature activation+1.289
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
issued
Token issued
Feature activation+3.243
annual
Token annual
Feature activation+0.158
waivers
Token waivers
Feature activation+0.000
that
Token that
Feature activation+0.000
kept
Token kept
Feature activation+1.102
taxpayer
Token taxpayer
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
response
Token response
Feature activation+0.000
and
Token and
Feature activation+1.731
Ms
Token Ms
Feature activation+3.260
Le
Token Le
Feature activation+0.000
Con
Token Con
Feature activation+0.000
te
Tokente
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
games
Token games
Feature activation+0.000
played
Token played
Feature activation+0.000
with
Token with
Feature activation+0.000
9
Token 9
Feature activation+0.000
64
Token64
Feature activation+0.000
.
Token.
Feature activation+3.075
In
TokenIn
Feature activation+1.082
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
-
Token-
Feature activation+0.000
2017
Token2017
Feature activation+0.000
.
Token.
Feature activation+1.141
However
Token However
Feature activation+1.186
,
Token,
Feature activation+0.877
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.899
the
Token the
Feature activation+3.157
box
Token box
Feature activation+0.453
,
Token,
Feature activation+0.597
the
Token the
Feature activation+0.873
C
Token C
Feature activation+0.000
++
Token++
Feature activation+2.144

INTERVAL 2.550 - 3.060
CONTAINS 0.008%

and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
officials
Token officials
Feature activation+0.000
.
Token.
Feature activation+1.654
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.649
Il
TokenIl
Feature activation+0.000
legal
Tokenlegal
Feature activation+0.000
structures
Token structures
Feature activation+0.000
in
Token in
Feature activation+1.434
the
Token the
Feature activation+0.877
Sudan
Token Sudan
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.445
independence
Token independence
Feature activation+0.000
,
Token,
Feature activation+2.765
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+2.868
the
Token the
Feature activation+1.289
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
C
Token C
Feature activation+0.000
aj
Tokenaj
Feature activation+0.000
un
Tokenun
Feature activation+1.355
French
Token French
Feature activation+0.164
poetry
Token poetry
Feature activation+0.000
and
Token and
Feature activation+2.797
lyrics
Token lyrics
Feature activation+0.000
to
Token to
Feature activation+1.384
C
Token C
Feature activation+0.000
aj
Tokenaj
Feature activation+0.000
un
Tokenun
Feature activation+1.000
said
Token said
Feature activation+2.457
it
Token it
Feature activation+0.000
received
Token received
Feature activation+0.117
a
Token a
Feature activation+0.000
complaint
Token complaint
Feature activation+0.000
from
Token from
Feature activation+2.636
a
Token a
Feature activation+1.562
parent
Token parent
Feature activation+0.000
of
Token of
Feature activation+2.114
a
Token a
Feature activation+1.514
Mo
Token Mo
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
capital
Token capital
Feature activation+0.000
.
Token.
Feature activation+0.992
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.559
The
TokenThe
Feature activation+1.012
plan
Token plan
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
executed
Token executed
Feature activation+0.000

INTERVAL 2.040 - 2.550
CONTAINS 0.014%

"
Token "
Feature activation+0.000
Saturday
TokenSaturday
Feature activation+0.000
TV
Token TV
Feature activation+0.000
Fun
Token Fun
Feature activation+0.000
house
Tokenhouse
Feature activation+0.000
."
Token."
Feature activation+2.210
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.553
The
TokenThe
Feature activation+1.904
comedian
Token comedian
Feature activation+0.000
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
by
Token by
Feature activation+3.406
a
Token a
Feature activation+2.093
pas
Token pas
Feature activation+0.000
sel
Tokensel
Feature activation+0.000
of
Token of
Feature activation+1.391
ALEC
Token ALEC
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
club
Token club
Feature activation+0.000
meets
Token meets
Feature activation+1.985
his
Token his
Feature activation+0.000
exit
Token exit
Feature activation+0.000
clause
Token clause
Feature activation+0.000
which
Token which
Feature activation+2.130
is
Token is
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
quite
Token quite
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Place
Token Place
Feature activation+0.000
,
Token,
Feature activation+0.000
Player
Token Player
Feature activation+0.000
B
Token B
Feature activation+0.000
:
Token:
Feature activation+2.050
True
Token True
Feature activation+0.000
Draco
Token Draco
Feature activation+0.000
Dinosaur
Token Dinosaur
Feature activation+0.000
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.000
UK
Token UK
Feature activation+0.000
physi
Token physi
Feature activation+0.000
other
Tokenother
Feature activation+0.000
ap
Tokenap
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
prefer
Token prefer
Feature activation+2.178
to
Token to
Feature activation+0.000
use
Token use
Feature activation+1.507
MC
Token MC
Feature activation+0.000
SP
TokenSP
Feature activation+0.000
or
Token or
Feature activation+1.018

INTERVAL 1.530 - 2.040
CONTAINS 0.028%

als
Tokenals
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+2.095
talent
Token talent
Feature activation+0.000
-
Token-
Feature activation+0.000
heavy
Tokenheavy
Feature activation+1.826
Giants
Token Giants
Feature activation+0.000
midfield
Token midfield
Feature activation+0.000
.
Token.
Feature activation+0.000
Won
Token Won
Feature activation+0.000
eight
Token eight
Feature activation+0.000
maximize
Token maximize
Feature activation+0.000
after
Token after
Feature activation+0.000
-
Token-
Feature activation+0.000
tax
Tokentax
Feature activation+0.000
income
Token income
Feature activation+0.000
.
Token.
Feature activation+1.620
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.446
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.854
Tax
TokenTax
Feature activation+0.000
the
Token the
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
.
Token.
Feature activation+0.875
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.840
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.248
Pe
Token Pe
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
pistol
Token pistol
Feature activation+0.000
.
Token.
Feature activation+1.850
Under
Token Under
Feature activation+1.628
current
Token current
Feature activation+1.929
federal
Token federal
Feature activation+0.000
law
Token law
Feature activation+1.499
and
Token and
Feature activation+1.020
ATF
Token ATF
Feature activation+0.000
policy
Token policy
Feature activation+2.965
,
Token,
Feature activation+0.000
launched
Token launched
Feature activation+0.073
a
Token a
Feature activation+0.000
corruption
Token corruption
Feature activation+0.000
probe
Token probe
Feature activation+0.000
into
Token into
Feature activation+1.734
Gray
Token Gray
Feature activation+0.000
's
Token's
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
mayoral
Token mayoral
Feature activation+0.000
election
Token election
Feature activation+0.000

INTERVAL 1.020 - 1.530
CONTAINS 0.049%

ĺ
Tokenĺ
Feature activation+0.000
ret
Tokenret
Feature activation+0.000
ired
Tokenired
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
and
Token and
Feature activation+1.216
came
Token came
Feature activation+0.000
back
Token back
Feature activation+0.000
twice
Token twice
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
member
Token member
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
C
Token C
Feature activation+0.000
erv
Tokenerv
Feature activation+0.000
antes
Tokenantes
Feature activation+0.000
joined
Token joined
Feature activation+1.397
the
Token the
Feature activation+0.000
Santa
Token Santa
Feature activation+0.000
Barbara
Token Barbara
Feature activation+0.000
rally
Token rally
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.254
more
Token more
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
media
Token media
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
and
Token and
Feature activation+1.052
eventually
Token eventually
Feature activation+0.869
the
Token the
Feature activation+0.000
attention
Token attention
Feature activation+1.015
of
Token of
Feature activation+0.039
the
Token the
Feature activation+0.000
depth
Token depth
Feature activation+0.000
=
Token=
Feature activation+0.000
2
Token2
Feature activation+0.000
C
Token C
Feature activation+0.000
=
Token =
Feature activation+0.000
US
Token US
Feature activation+1.071
,
Token,
Feature activation+0.138
O
Token O
Feature activation+0.010
=
Token =
Feature activation+0.561
Geo
Token Geo
Feature activation+0.000
Trust
TokenTrust
Feature activation+0.000
moments
Token moments
Feature activation+0.000
.
Token.
Feature activation+0.758
Most
Token Most
Feature activation+1.155
observ
Token observ
Feature activation+0.000
atories
Tokenatories
Feature activation+0.000
(
Token (
Feature activation+1.096
such
Tokensuch
Feature activation+0.000
as
Token as
Feature activation+0.458
Plan
Token Plan
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.510 - 1.020
CONTAINS 0.080%

Bike
Token Bike
Feature activation+0.000
to
Token to
Feature activation+0.000
hurry
Token hurry
Feature activation+0.283
up
Token up
Feature activation+0.000
and
Token and
Feature activation+0.000
expand
Token expand
Feature activation+0.901
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
neighborhoods
Token neighborhoods
Feature activation+0.000
,
Token,
Feature activation+0.043
even
Token even
Feature activation+0.000
and
Token and
Feature activation+0.928
a
Token a
Feature activation+0.000
congressional
Token congressional
Feature activation+0.000
commission
Token commission
Feature activation+0.000
even
Token even
Feature activation+0.000
acknowledged
Token acknowledged
Feature activation+0.896
that
Token that
Feature activation+1.149
the
Token the
Feature activation+0.000
kidnapping
Token kidnapping
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
some
Token some
Feature activation+1.086
of
Token of
Feature activation+0.322
the
Token the
Feature activation+1.511
problem
Token problem
Feature activation+0.000
.
Token.
Feature activation+0.527
But
Token But
Feature activation+0.677
to
Token to
Feature activation+0.000
solve
Token solve
Feature activation+0.311
the
Token the
Feature activation+0.579
rest
Token rest
Feature activation+0.138
we
Token we
Feature activation+0.000
C
Token C
Feature activation+0.000
=
Token =
Feature activation+0.000
US
Token US
Feature activation+1.071
,
Token,
Feature activation+0.138
O
Token O
Feature activation+0.010
=
Token =
Feature activation+0.561
Geo
Token Geo
Feature activation+0.000
Trust
TokenTrust
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
.,
Token.,
Feature activation+0.000
CN
Token CN
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.386
To
TokenTo
Feature activation+0.000
recap
Token recap
Feature activation+0.607
,
Token,
Feature activation+1.561
all
Token all
Feature activation+0.722
four
Token four
Feature activation+1.749
crowds
Token crowds
Feature activation+0.000
ales
Tokenales
Feature activation+0.008
will
Token will
Feature activation+0.000
have
Token have
Feature activation+2.499

INTERVAL 0.000 - 0.510
CONTAINS 99.815%

and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
City
Token City
Feature activation+0.000
of
Token of
Feature activation+0.000
Petersburg
Token Petersburg
Feature activation+0.000
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
everybody
Token everybody
Feature activation+0.000
know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
The
Token The
Feature activation+0.000
Finnish
Token Finnish
Feature activation+0.000
Miracle
Token Miracle
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
name
Token name
Feature activation+0.000
of
Token of
Feature activation+0.000
And
Token And
Feature activation+0.000
ré
Tokenré
Feature activation+0.000
are
Token are
Feature activation+0.000
paying
Token paying
Feature activation+0.000
for
Token for
Feature activation+0.000
Jindal
Token Jindal
Feature activation+0.000
's
Token's
Feature activation+0.000
mass
Token mass
Feature activation+0.000
prayer
Token prayer
Feature activation+0.000
event
Token event
Feature activation+0.000
at
Token at
Feature activation+0.000
LSU
Token LSU
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
diabetes
Token diabetes
Feature activation+0.000
,
Token,
Feature activation+0.000
depression
Token depression
Feature activation+0.000
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.,
Token.,
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
paint
Token paint
Feature activation+0.000
colour
Token colour
Feature activation+0.000
,
Token,
Feature activation+0.000
matched
Token matched
Feature activation+0.000
with
Token with
Feature activation+0.000
maintenance
Token maintenance
Feature activation+0.000
records
Token records
Feature activation+0.000
for
Token for
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H11.4: (feature 5662)

TOP ACTIVATIONS
MAX = 5.140

most
Token most
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
.
Token.
Feature activation+0.748
From
Token From
Feature activation+1.973
its
Token its
Feature activation+0.000
conception
Token conception
Feature activation+5.140
,
Token,
Feature activation+2.364
Planned
Token Planned
Feature activation+0.000
Parenthood
Token Parenthood
Feature activation+0.000
was
Token was
Feature activation+0.000
built
Token built
Feature activation+0.000
marvel
Token marvel
Feature activation+0.686
at
Token at
Feature activation+3.721
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000
consequences
Token consequences
Feature activation+4.823
of
Token of
Feature activation+4.951
one
Token one
Feature activation+0.000
of
Token of
Feature activation+4.710
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
complex
Token complex
Feature activation+0.000
and
Token and
Feature activation+0.000
marvel
Token marvel
Feature activation+0.686
at
Token at
Feature activation+3.721
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000
consequences
Token consequences
Feature activation+4.823
of
Token of
Feature activation+4.951
one
Token one
Feature activation+0.000
of
Token of
Feature activation+4.710
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000
consequences
Token consequences
Feature activation+4.823
of
Token of
Feature activation+4.951
one
Token one
Feature activation+0.000
of
Token of
Feature activation+4.710
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
complex
Token complex
Feature activation+0.000
botched
Token botched
Feature activation+0.000
big
Token big
Feature activation+0.000
plan
Token plan
Feature activation+0.000
to
Token to
Feature activation+0.000
marry
Token marry
Feature activation+1.555
this
Token this
Feature activation+0.000
fall
Token fall
Feature activation+0.000
and
Token and
Feature activation+4.658
are
Token are
Feature activation+0.000
releasing
Token releasing
Feature activation+0.896
a
Token a
Feature activation+0.000
book
Token book
Feature activation+0.396
next
Token next
Feature activation+0.000
the
Token the
Feature activation+0.776
Cit
Token Cit
Feature activation+0.000
igroup
Tokenigroup
Feature activation+0.000
settlement
Token settlement
Feature activation+0.000
.
Token.
Feature activation+3.726
Judge
Token Judge
Feature activation+4.597
Rak
Token Rak
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
has
Token has
Feature activation+0.000
asked
Token asked
Feature activation+3.121
the
Token the
Feature activation+2.372
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.641
As
TokenAs
Feature activation+3.890
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.410
,
Token,
Feature activation+3.470
Tim
Token Tim
Feature activation+1.100
and
Token and
Feature activation+1.699
I
Token I
Feature activation+0.000
are
Token are
Feature activation+0.000
i
Tokeni
Feature activation+0.006
is
Token is
Feature activation+0.198
destined
Token destined
Feature activation+0.000
for
Token for
Feature activation+1.363
the
Token the
Feature activation+0.000
pinnacle
Token pinnacle
Feature activation+4.393
of
Token of
Feature activation+0.068
world
Token world
Feature activation+0.000
football
Token football
Feature activation+4.087
,
Token,
Feature activation+2.102
according
Token according
Feature activation+0.851
aa
Tokenaa
Feature activation+0.000
S
TokenS
Feature activation+0.000
application
Token application
Feature activation+0.000
in
Token in
Feature activation+1.591
a
Token a
Feature activation+0.044
full
Token full
Feature activation+4.236
-
Token-
Feature activation+0.000
stack
Tokenstack
Feature activation+2.013
,
Token,
Feature activation+2.427
easy
Token easy
Feature activation+0.492
-
Token-
Feature activation+0.000
sub
Token sub
Feature activation+0.000
-
Token-
Feature activation+0.000
groups
Tokengroups
Feature activation+0.164
form
Token form
Feature activation+1.123
the
Token the
Feature activation+2.492
group
Token group
Feature activation+4.183
of
Token of
Feature activation+2.728
Fr
Token Fr
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
languages
Token languages
Feature activation+0.000
for
Token for
Feature activation+1.363
the
Token the
Feature activation+0.000
pinnacle
Token pinnacle
Feature activation+4.393
of
Token of
Feature activation+0.068
world
Token world
Feature activation+0.000
football
Token football
Feature activation+4.087
,
Token,
Feature activation+2.102
according
Token according
Feature activation+0.851
to
Token to
Feature activation+1.895
S
Token S
Feature activation+0.000
oun
Tokenoun
Feature activation+0.000
black
Token black
Feature activation+0.000
.
Token.
Feature activation+2.134
It
Token It
Feature activation+0.000
is
Token is
Feature activation+1.744
that
Token that
Feature activation+2.351
of
Token of
Feature activation+3.940
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
who
Token who
Feature activation+0.000
knows
Token knows
Feature activation+0.000
a
Token a
Feature activation+0.000
's
Token's
Feature activation+0.000
stated
Token stated
Feature activation+0.000
reluctance
Token reluctance
Feature activation+0.000
to
Token to
Feature activation+0.000
interfere
Token interfere
Feature activation+0.386
with
Token with
Feature activation+3.896
the
Token the
Feature activation+1.064
judicial
Token judicial
Feature activation+0.000
process
Token process
Feature activation+2.751
,
Token,
Feature activation+3.387
statements
Token statements
Feature activation+1.795
about
Token about
Feature activation+0.000
here
Token here
Feature activation+0.000
).
Token).
Feature activation+3.446
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.641
As
TokenAs
Feature activation+3.890
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.410
,
Token,
Feature activation+3.470
Tim
Token Tim
Feature activation+1.100
owners
Token owners
Feature activation+0.000
.
Token.
Feature activation+0.209
S
Token S
Feature activation+0.000
IP
TokenIP
Feature activation+0.000
O
TokenO
Feature activation+0.000
granted
Token granted
Feature activation+3.882
209
Token 209
Feature activation+1.571
,
Token,
Feature activation+0.000
000
Token000
Feature activation+1.009
patents
Token patents
Feature activation+0.000
during
Token during
Feature activation+1.415
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
contracts
Token contracts
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.869
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
led
Token led
Feature activation+0.030
to
Token to
Feature activation+1.640
support
Token support
Feature activation+0.000
that
Token that
Feature activation+2.721
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+3.844
the
Token the
Feature activation+0.075
appeals
Token appeals
Feature activation+0.000
process
Token process
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+1.259
soft
Token soft
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
of
Token of
Feature activation+0.083
that
Token that
Feature activation+0.000
stance
Token stance
Feature activation+0.000
.
Token.
Feature activation+3.755
In
Token In
Feature activation+0.527
July
Token July
Feature activation+0.827
local
Token local
Feature activation+0.000
media
Token media
Feature activation+0.000
reported
Token reported
Feature activation+4.400
System
Token System
Feature activation+0.000
board
Token board
Feature activation+0.000
.
Token.
Feature activation+1.755
These
Token These
Feature activation+0.000
positions
Token positions
Feature activation+0.000
give
Token give
Feature activation+3.739
him
Token him
Feature activation+0.000
unique
Token unique
Feature activation+0.000
platforms
Token platforms
Feature activation+0.000
and
Token and
Feature activation+0.000
standing
Token standing
Feature activation+0.000
happen
Token happen
Feature activation+0.000
next
Token next
Feature activation+0.000
.
Token.
Feature activation+0.645
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.557
Despite
TokenDespite
Feature activation+3.727
S
Token S
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
's
Token's
Feature activation+0.000
stated
Token stated
Feature activation+0.000
reluctance
Token reluctance
Feature activation+0.000

Top DFA by src position
MAX = 5.863

e
Token e
Feature activation-0.005
Top resid features:
ug
Tokenug
Feature activation+0.001
Top resid features:
enic
Tokenenic
Feature activation+0.003
Top resid features:
ist
Tokenist
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.063
Top resid features:
S
Token S
Feature activation+3.601
Top resid features:
anger
Tokenanger
Feature activation+0.034
Top resid features:
encouraged
Token encouraged
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
steril
Token steril
Feature activation+0.001
Top resid features:
ization
Tokenization
Feature activation+0.002
Top resid features:
Sunday
Token Sunday
Feature activation+0.004
Top resid features:
afternoon
Token afternoon
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
a
Token a
Feature activation+0.025
Top resid features:
journey
Token journey
Feature activation+0.003
Top resid features:
S
Token S
Feature activation+3.079
Top resid features:
án
Tokenán
Feature activation+0.029
Top resid features:
che
Tokenche
Feature activation+0.015
Top resid features:
z
Tokenz
Feature activation+0.011
Top resid features:
seemed
Token seemed
Feature activation+0.010
Top resid features:
so
Token so
Feature activation+0.008
Top resid features:
Sunday
Token Sunday
Feature activation-0.001
Top resid features:
afternoon
Token afternoon
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
journey
Token journey
Feature activation+0.002
Top resid features:
S
Token S
Feature activation+3.202
Top resid features:
án
Tokenán
Feature activation+0.027
Top resid features:
che
Tokenche
Feature activation+0.013
Top resid features:
z
Tokenz
Feature activation+0.010
Top resid features:
seemed
Token seemed
Feature activation+0.009
Top resid features:
so
Token so
Feature activation+0.011
Top resid features:
Indeed
Token Indeed
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
as
Token as
Feature activation+0.032
Top resid features:
Arsenal
Token Arsenal
Feature activation-0.020
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
S
Token S
Feature activation+2.520
Top resid features:
án
Tokenán
Feature activation+0.020
Top resid features:
che
Tokenche
Feature activation+0.008
Top resid features:
z
Tokenz
Feature activation+0.013
Top resid features:
travel
Token travel
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
my
Token my
Feature activation+0.001
Top resid features:
worst
Token worst
Feature activation+0.001
Top resid features:
day
Token day
Feature activation+0.001
Top resid features:
,"
Token,"
Feature activation+0.036
Top resid features:
S
Token S
Feature activation+4.381
Top resid features:
do
Tokendo
Feature activation+0.016
Top resid features:
ia
Tokenia
Feature activation+0.017
Top resid features:
told
Token told
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
New
Token New
Feature activation+0.004
Top resid features:
On
TokenOn
Feature activation+0.022
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
Judge
Token Judge
Feature activation+0.023
Top resid features:
Jed
Token Jed
Feature activation+0.021
Top resid features:
S
Token S
Feature activation+5.509
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Rak
Token Rak
Feature activation+0.196
Top resid features:
off
Tokenoff
Feature activation+0.093
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
likely
Token likely
Feature activation+0.003
Top resid features:
familiar
Token familiar
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.009
Top resid features:
Tim
Token Tim
Feature activation-0.052
Top resid features:
S
Token S
Feature activation+5.509
Top resid features:
led
Tokenled
Feature activation+0.059
Top resid features:
d
Tokend
Feature activation+0.012
Top resid features:
as
Token as
Feature activation+0.027
Top resid features:
he
Token he
Feature activation+0.033
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.019
Top resid features:
S
Token S
Feature activation+3.063
Top resid features:
oun
Tokenoun
Feature activation+0.046
Top resid features:
ess
Tokeness
Feature activation+0.028
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
left
Token left
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
how
Token how
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
make
Token make
Feature activation+0.010
Top resid features:
your
Token your
Feature activation+0.018
Top resid features:
own
Token own
Feature activation+0.005
Top resid features:
S
Token S
Feature activation+5.756
Top resid features:
aa
Tokenaa
Feature activation+0.108
Top resid features:
S
TokenS
Feature activation+0.119
Top resid features:
application
Token application
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.051
Top resid features:
a
Token a
Feature activation+0.029
Top resid features:
is
Tokenis
Feature activation+0.018
Top resid features:
ian
Tokenian
Feature activation+0.004
Top resid features:
languages
Token languages
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
S
Token S
Feature activation+5.863
Top resid features:
ater
Tokenater
Feature activation+0.046
Top resid features:
land
Tokenland
Feature activation+0.015
Top resid features:
Fr
Token Fr
Feature activation-0.053
Top resid features:
is
Tokenis
Feature activation+0.011
Top resid features:
ian
Tokenian
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.012
Top resid features:
S
Token S
Feature activation+3.459
Top resid features:
oun
Tokenoun
Feature activation+0.059
Top resid features:
ess
Tokeness
Feature activation+0.039
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
left
Token left
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
be
Token be
Feature activation+0.006
Top resid features:
m
Token m
Feature activation+0.012
Top resid features:
add
Tokenadd
Feature activation+0.002
Top resid features:
ening
Tokenening
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
S
Token S
Feature activation+4.853
Top resid features:
owell
Tokenowell
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
even
Token even
Feature activation+0.002
Top resid features:
more
Token more
Feature activation-0.000
Top resid features:
so
Token so
Feature activation+0.001
Top resid features:
next
Token next
Feature activation-0.007
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.060
Top resid features:
Despite
TokenDespite
Feature activation+0.016
Top resid features:
S
Token S
Feature activation+4.466
Top resid features:
isi
Tokenisi
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
stated
Token stated
Feature activation+0.003
Top resid features:
reluctance
Token reluctance
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
likely
Token likely
Feature activation+0.005
Top resid features:
familiar
Token familiar
Feature activation+0.005
Top resid features:
with
Token with
Feature activation+0.013
Top resid features:
Tim
Token Tim
Feature activation-0.063
Top resid features:
S
Token S
Feature activation+4.965
Top resid features:
led
Tokenled
Feature activation+0.059
Top resid features:
d
Tokend
Feature activation+0.008
Top resid features:
as
Token as
Feature activation+0.032
Top resid features:
he
Token he
Feature activation+0.033
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
favor
Token favor
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
patent
Token patent
Feature activation-0.030
Top resid features:
owners
Token owners
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.070
Top resid features:
S
Token S
Feature activation+4.568
Top resid features:
IP
TokenIP
Feature activation+0.008
Top resid features:
O
TokenO
Feature activation+0.073
Top resid features:
granted
Token granted
Feature activation+0.096
Top resid features:
209
Token 209
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
summer
Token summer
Feature activation+0.003
Top resid features:
by
Token by
Feature activation+0.031
Top resid features:
signing
Token signing
Feature activation+0.032
Top resid features:
defenseman
Token defenseman
Feature activation+0.022
Top resid features:
Ryan
Token Ryan
Feature activation+0.007
Top resid features:
S
Token S
Feature activation+4.976
Top resid features:
uter
Tokenuter
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.072
Top resid features:
forward
Token forward
Feature activation+0.011
Top resid features:
Zach
Token Zach
Feature activation-0.001
Top resid features:
Par
Token Par
Feature activation+0.010
Top resid features:
F
Token F
Feature activation+0.096
Top resid features:
att
Tokenatt
Feature activation+0.018
Top resid features:
ah
Tokenah
Feature activation+0.047
Top resid features:
el
Token el
Feature activation+0.096
Top resid features:
-
Token-
Feature activation+0.096
Top resid features:
S
TokenS
Feature activation+5.387
Top resid features:
isi
Tokenisi
Feature activation-0.007
Top resid features:
may
Token may
Feature activation+0.006
Top resid features:
issue
Token issue
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
presidential
Token presidential
Feature activation-0.003
Top resid features:
next
Token next
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.097
Top resid features:
Despite
TokenDespite
Feature activation+0.008
Top resid features:
S
Token S
Feature activation+4.267
Top resid features:
isi
Tokenisi
Feature activation-0.010
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
stated
Token stated
Feature activation+0.003
Top resid features:
reluctance
Token reluctance
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
2016
Token 2016
Feature activation+0.006
Top resid features:
board
Token board
Feature activation-0.009
Top resid features:
chair
Token chair
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
S
Token S
Feature activation+4.360
Top resid features:
AND
TokenAND
Feature activation+0.241
Top resid features:
AG
TokenAG
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.223
Top resid features:
He
Token He
Feature activation+0.010
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
F
Token F
Feature activation+0.100
Top resid features:
att
Tokenatt
Feature activation+0.007
Top resid features:
ah
Tokenah
Feature activation+0.015
Top resid features:
el
Token el
Feature activation+0.119
Top resid features:
-
Token-
Feature activation+0.099
Top resid features:
S
TokenS
Feature activation+4.851
Top resid features:
isi
Tokenisi
Feature activation-0.009
Top resid features:
may
Token may
Feature activation+0.006
Top resid features:
issue
Token issue
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
presidential
Token presidential
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.06

Head 3: 0.06

Head 4: 0.37

Head 5: 0.04

Head 6: 0.07

Head 7: 0.05

Head 8: 0.09

Head 9: 0.05

Head 10: 0.06

Head 11: 0.06

Positive logits

S8.58

S5.67

s5.64

SAR3.20

Crossref2.91

Sabb2.64

SV2.56

ante2.56

Annotations2.51

SAP2.38

sulf2.38

SQ2.36

SEM2.33

Si2.31

ensed2.22

sclerosis2.15

condol2.03

bye2.03

ss2.02

Spiral2.00

Negative logits

GW-2.30

perty-2.15

dan-2.14

grave-2.09

iere-2.07

Verse-2.04

nie-2.02

OGR-2.00

oons-1.99

lust-1.98

mask-1.97

minster-1.97

lehem-1.96

ajo-1.96

-1.95

-1.94

eday-1.93

assic-1.92

-1.92

ERAL-1.90

INTERVAL 4.626 - 5.140
CONTAINS 0.001%

most
Token most
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
.
Token.
Feature activation+0.748
From
Token From
Feature activation+1.973
its
Token its
Feature activation+0.000
conception
Token conception
Feature activation+5.140
,
Token,
Feature activation+2.364
Planned
Token Planned
Feature activation+0.000
Parenthood
Token Parenthood
Feature activation+0.000
was
Token was
Feature activation+0.000
built
Token built
Feature activation+0.000
and
Token and
Feature activation+0.000
marvel
Token marvel
Feature activation+0.686
at
Token at
Feature activation+3.721
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000
consequences
Token consequences
Feature activation+4.823
of
Token of
Feature activation+4.951
one
Token one
Feature activation+0.000
of
Token of
Feature activation+4.710
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
marvel
Token marvel
Feature activation+0.686
at
Token at
Feature activation+3.721
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000
consequences
Token consequences
Feature activation+4.823
of
Token of
Feature activation+4.951
one
Token one
Feature activation+0.000
of
Token of
Feature activation+4.710
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
complex
Token complex
Feature activation+0.000
the
Token the
Feature activation+0.000
unforeseen
Token unforeseen
Feature activation+0.000
consequences
Token consequences
Feature activation+4.823
of
Token of
Feature activation+4.951
one
Token one
Feature activation+0.000
of
Token of
Feature activation+4.710
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
complex
Token complex
Feature activation+0.000
botched
Token botched
Feature activation+0.000
big
Token big
Feature activation+0.000
plan
Token plan
Feature activation+0.000
to
Token to
Feature activation+0.000
marry
Token marry
Feature activation+1.555
this
Token this
Feature activation+0.000
fall
Token fall
Feature activation+0.000
and
Token and
Feature activation+4.658
are
Token are
Feature activation+0.000
releasing
Token releasing
Feature activation+0.896
a
Token a
Feature activation+0.000
book
Token book
Feature activation+0.396
next
Token next
Feature activation+0.000

INTERVAL 4.112 - 4.626
CONTAINS 0.001%

aa
Tokenaa
Feature activation+0.000
S
TokenS
Feature activation+0.000
application
Token application
Feature activation+0.000
in
Token in
Feature activation+1.591
a
Token a
Feature activation+0.044
full
Token full
Feature activation+4.236
-
Token-
Feature activation+0.000
stack
Tokenstack
Feature activation+2.013
,
Token,
Feature activation+2.427
easy
Token easy
Feature activation+0.492
-
Token-
Feature activation+0.000
sub
Token sub
Feature activation+0.000
-
Token-
Feature activation+0.000
groups
Tokengroups
Feature activation+0.164
form
Token form
Feature activation+1.123
the
Token the
Feature activation+2.492
group
Token group
Feature activation+4.183
of
Token of
Feature activation+2.728
Fr
Token Fr
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
languages
Token languages
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.641
As
TokenAs
Feature activation+3.890
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+4.410
,
Token,
Feature activation+3.470
Tim
Token Tim
Feature activation+1.100
and
Token and
Feature activation+1.699
I
Token I
Feature activation+0.000
are
Token are
Feature activation+0.000
i
Tokeni
Feature activation+0.006
is
Token is
Feature activation+0.198
destined
Token destined
Feature activation+0.000
for
Token for
Feature activation+1.363
the
Token the
Feature activation+0.000
pinnacle
Token pinnacle
Feature activation+4.393
of
Token of
Feature activation+0.068
world
Token world
Feature activation+0.000
football
Token football
Feature activation+4.087
,
Token,
Feature activation+2.102
according
Token according
Feature activation+0.851
the
Token the
Feature activation+0.776
Cit
Token Cit
Feature activation+0.000
igroup
Tokenigroup
Feature activation+0.000
settlement
Token settlement
Feature activation+0.000
.
Token.
Feature activation+3.726
Judge
Token Judge
Feature activation+4.597
Rak
Token Rak
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
has
Token has
Feature activation+0.000
asked
Token asked
Feature activation+3.121
the
Token the
Feature activation+2.372

INTERVAL 3.598 - 4.112
CONTAINS 0.001%

review
Token review
Feature activation+2.061
the
Token the
Feature activation+0.776
Cit
Token Cit
Feature activation+0.000
igroup
Tokenigroup
Feature activation+0.000
settlement
Token settlement
Feature activation+0.000
.
Token.
Feature activation+3.726
Judge
Token Judge
Feature activation+4.597
Rak
Token Rak
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
has
Token has
Feature activation+0.000
asked
Token asked
Feature activation+3.121
soft
Token soft
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
of
Token of
Feature activation+0.083
that
Token that
Feature activation+0.000
stance
Token stance
Feature activation+0.000
.
Token.
Feature activation+3.755
In
Token In
Feature activation+0.527
July
Token July
Feature activation+0.827
local
Token local
Feature activation+0.000
media
Token media
Feature activation+0.000
reported
Token reported
Feature activation+4.400
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
contracts
Token contracts
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+3.869
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
led
Token led
Feature activation+0.030
to
Token to
Feature activation+1.640
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
Gi
Token Gi
Feature activation+0.000
Review
TokenReview
Feature activation+0.000
s
Tokens
Feature activation+0.000
Podcast
Token Podcast
Feature activation+0.000
.
Token.
Feature activation+3.625
Ċ
TokenĊ
Feature activation+0.178
Ċ
TokenĊ
Feature activation+1.828
Tim
TokenTim
Feature activation+1.605
owns
Token owns
Feature activation+0.000
and
Token and
Feature activation+0.000
happen
Token happen
Feature activation+0.000
next
Token next
Feature activation+0.000
.
Token.
Feature activation+0.645
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.557
Despite
TokenDespite
Feature activation+3.727
S
Token S
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
's
Token's
Feature activation+0.000
stated
Token stated
Feature activation+0.000
reluctance
Token reluctance
Feature activation+0.000

INTERVAL 3.084 - 3.598
CONTAINS 0.003%

talents
Token talents
Feature activation+0.703
of
Token of
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
season
Tokenseason
Feature activation+0.000
,
Token,
Feature activation+3.590
fans
Token fans
Feature activation+0.000
must
Token must
Feature activation+0.000
keep
Token keep
Feature activation+0.489
a
Token a
Feature activation+0.000
lid
Token lid
Feature activation+0.000
interfere
Token interfere
Feature activation+0.386
with
Token with
Feature activation+3.896
the
Token the
Feature activation+1.064
judicial
Token judicial
Feature activation+0.000
process
Token process
Feature activation+2.751
,
Token,
Feature activation+3.387
statements
Token statements
Feature activation+1.795
he
Token he
Feature activation+0.000
made
Token made
Feature activation+0.000
in
Token in
Feature activation+0.061
recent
Token recent
Feature activation+0.000
.
Token.
Feature activation+0.523
Indeed
Token Indeed
Feature activation+1.038
,
Token,
Feature activation+2.191
as
Token as
Feature activation+1.716
Arsenal
Token Arsenal
Feature activation+0.000
and
Token and
Feature activation+3.447
S
Token S
Feature activation+0.000
án
Tokenán
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
travel
Token travel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.590
Egyptian
Token Egyptian
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
defended
Token defended
Feature activation+3.401
the
Token the
Feature activation+0.000
incarceration
Token incarceration
Feature activation+0.000
of
Token of
Feature activation+1.643
the
Token the
Feature activation+0.000
journalists
Token journalists
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
leaders
Token leaders
Feature activation+0.544
on
Token on
Feature activation+0.048
Sunday
Token Sunday
Feature activation+2.607
afternoon
Token afternoon
Feature activation+3.396
,
Token,
Feature activation+3.333
a
Token a
Feature activation+0.509
journey
Token journey
Feature activation+1.957
S
Token S
Feature activation+0.000
án
Tokenán
Feature activation+0.000

INTERVAL 2.570 - 3.084
CONTAINS 0.004%

Ċ
TokenĊ
Feature activation+0.379
Ċ
TokenĊ
Feature activation+1.314
WARNING
TokenWARNING
Feature activation+0.000
:
Token:
Feature activation+1.000
Here
Token Here
Feature activation+0.322
are
Token are
Feature activation+2.679
some
Token some
Feature activation+0.000
concepts
Token concepts
Feature activation+1.264
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
-
Token-
Feature activation+0.000
groups
Tokengroups
Feature activation+0.164
form
Token form
Feature activation+1.123
the
Token the
Feature activation+2.492
group
Token group
Feature activation+4.183
of
Token of
Feature activation+2.728
Fr
Token Fr
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
languages
Token languages
Feature activation+0.000
.
Token.
Feature activation+0.852
more
Token more
Feature activation+0.000
so
Token so
Feature activation+0.000
than
Token than
Feature activation+1.748
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+2.891
other
Token other
Feature activation+0.000
notable
Token notable
Feature activation+0.000
black
Token black
Feature activation+0.000
conservatives
Token conservatives
Feature activation+0.568
.
Token.
Feature activation+1.821
palace
Token palace
Feature activation+0.000
.
Token.
Feature activation+0.513
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.347
He
TokenHe
Feature activation+0.000
called
Token called
Feature activation+2.897
for
Token for
Feature activation+1.137
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
penalty
Token penalty
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+1.978
After
Token After
Feature activation+1.874
Burn
Token Burn
Feature activation+0.000
er
Tokener
Feature activation+0.541
Clim
Token Clim
Feature activation+0.000
ax
Tokenax
Feature activation+2.703
released
Token released
Feature activation+1.331
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
arc
Token arc
Feature activation+0.000
ades
Tokenades
Feature activation+1.097

INTERVAL 2.056 - 2.570
CONTAINS 0.009%

after
Token after
Feature activation+1.917
the
Token the
Feature activation+0.284
bombing
Token bombing
Feature activation+0.000
.
Token.
Feature activation+2.071
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.501
"
Token"
Feature activation+3.116
He
TokenHe
Feature activation+0.000
's
Token's
Feature activation+0.000
seen
Token seen
Feature activation+1.844
me
Token me
Feature activation+0.000
of
Token of
Feature activation+0.171
Kh
Token Kh
Feature activation+0.000
ass
Tokenass
Feature activation+0.000
arat
Tokenarat
Feature activation+0.000
district
Token district
Feature activation+0.000
from
Token from
Feature activation+2.062
ISIS
Token ISIS
Feature activation+0.000
in
Token in
Feature activation+0.720
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.239
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+1.841
,
Token,
Feature activation+2.102
Prince
Token Prince
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
visited
Token visited
Feature activation+0.564
Ted
Token Ted
Feature activation+0.000
worth
Tokenworth
Feature activation+0.000
critic
Token critic
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
scheduled
Token scheduled
Feature activation+0.000
to
Token to
Feature activation+0.000
review
Token review
Feature activation+2.061
the
Token the
Feature activation+0.776
Cit
Token Cit
Feature activation+0.000
igroup
Tokenigroup
Feature activation+0.000
settlement
Token settlement
Feature activation+0.000
.
Token.
Feature activation+3.726
me
Token me
Feature activation+0.000
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.000
worst
Token worst
Feature activation+0.000
day
Token day
Feature activation+0.000
,"
Token,"
Feature activation+2.171
S
Token S
Feature activation+0.207
do
Tokendo
Feature activation+0.000
ia
Tokenia
Feature activation+0.202
told
Token told
Feature activation+0.699
the
Token the
Feature activation+0.000

INTERVAL 1.542 - 2.056
CONTAINS 0.019%

way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Stanley
Token Stanley
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
.
Token.
Feature activation+1.582
That
Token That
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.431
quite
Token quite
Feature activation+0.000
the
Token the
Feature activation+0.000
After
Token After
Feature activation+0.000
Burn
Token Burn
Feature activation+0.000
er
Tokener
Feature activation+0.000
franchise
Token franchise
Feature activation+0.000
.
Token.
Feature activation+1.978
After
Token After
Feature activation+1.874
Burn
Token Burn
Feature activation+0.000
er
Tokener
Feature activation+0.541
Clim
Token Clim
Feature activation+0.000
ax
Tokenax
Feature activation+2.703
released
Token released
Feature activation+1.331
to
Token to
Feature activation+0.803
Fr
Token Fr
Feature activation+0.000
is
Tokenis
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
.
Token.
Feature activation+0.154
The
Token The
Feature activation+1.595
two
Token two
Feature activation+0.112
languages
Token languages
Feature activation+0.000
are
Token are
Feature activation+0.000
classified
Token classified
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+2.011
precisely
Token precisely
Feature activation+2.742
the
Token the
Feature activation+0.000
reason
Token reason
Feature activation+3.026
why
Token why
Feature activation+2.000
we
Token we
Feature activation+0.000
chose
Token chose
Feature activation+1.960
Russia
Token Russia
Feature activation+0.000
.
Token.
Feature activation+2.134
Ċ
TokenĊ
Feature activation+0.000
studying
Token studying
Feature activation+0.000
journalism
Token journalism
Feature activation+0.000
in
Token in
Feature activation+0.733
Islamic
Token Islamic
Feature activation+0.000
University
Token University
Feature activation+0.000
of
Token of
Feature activation+1.575
Science
Token Science
Feature activation+0.000
and
Token and
Feature activation+0.000
Technology
Token Technology
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.028 - 1.542
CONTAINS 0.038%

atheist
Token atheist
Feature activation+0.000
.
Token.
Feature activation+0.757
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+1.688
as
Token as
Feature activation+1.153
far
Token far
Feature activation+1.118
as
Token as
Feature activation+1.205
he
Token he
Feature activation+0.000
knew
Token knew
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
un
Token un
Feature activation+0.000
ed
Tokened
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
sight
Token sight
Feature activation+0.000
of
Token of
Feature activation+1.438
a
Token a
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.000
minister
Token minister
Feature activation+0.000
of
Token of
Feature activation+0.335
,"
Token,"
Feature activation+1.784
he
Token he
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.231
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.037
S
TokenS
Feature activation+0.000
otto
Tokenotto
Feature activation+0.000
apologized
Token apologized
Feature activation+0.000
to
Token to
Feature activation+1.131
everyone
Token everyone
Feature activation+0.000
prone
Token prone
Feature activation+0.000
to
Token to
Feature activation+0.000
some
Token some
Feature activation+0.000
foolish
Token foolish
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
but
Token but
Feature activation+1.278
Tim
Token Tim
Feature activation+0.770
takes
Token takes
Feature activation+0.000
his
Token his
Feature activation+0.000
Jiu
Token Jiu
Feature activation+0.000
J
Token J
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.)
Token.)
Feature activation+0.000
for
Token for
Feature activation+0.637
GHC
Token GHC
Feature activation+0.000
JS
TokenJS
Feature activation+0.000
.
Token.
Feature activation+1.075
It
Token It
Feature activation+0.000
turns
Token turns
Feature activation+0.000
out
Token out
Feature activation+3.486
that
Token that
Feature activation+2.347
cost
Token cost
Feature activation+0.000

INTERVAL 0.514 - 1.028
CONTAINS 0.067%

rates
Token rates
Feature activation+0.000
decreased
Token decreased
Feature activation+0.000
with
Token with
Feature activation+0.000
accumulating
Token accumulating
Feature activation+0.239
volume
Token volume
Feature activation+0.000
of
Token of
Feature activation+0.644
intake
Token intake
Feature activation+0.000
water
Token water
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
filter
Token filter
Feature activation+0.000
issues
Token issues
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
legal
Token legal
Feature activation+0.000
.
Token.
Feature activation+1.423
Recently
TokenRecently
Feature activation+0.989
,
Token,
Feature activation+1.119
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Tokenand
Feature activation+0.296
for
Tokenfor
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Aside
TokenAside
Feature activation+0.000
from
Token from
Feature activation+0.000
that
Token that
Feature activation+0.154
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.818
bank
Token bank
Feature activation+0.000
acts
Token acts
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
bankers
Token bankers
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
Elvis
Token Elvis
Feature activation+0.000
imperson
Token imperson
Feature activation+0.000
ator
Tokenator
Feature activation+0.000
.
Token.
Feature activation+0.923
But
Token But
Feature activation+1.978
here
Token here
Feature activation+2.374
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.582
s
Tokens
Feature activation+2.583
those
Token those
Feature activation+0.000
wanting
Token wanting
Feature activation+1.377
to
Token to
Feature activation+0.000
hear
Token hear
Feature activation+2.743
Boone
Token Boone
Feature activation+0.000
sing
Token sing
Feature activation+0.706
again
Token again
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.555
and
Tokenand
Feature activation+0.856
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.000 - 0.514
CONTAINS 99.857%

.
Token.
Feature activation+0.000
#
Token #
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
ef
Tokenef
Feature activation+0.000
ban
Tokenban
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
In
Token In
Feature activation+0.000
West
Token West
Feature activation+0.000
Bengal
Token Bengal
Feature activation+0.000
Poland
Token Poland
Feature activation+0.000
and
Token and
Feature activation+0.000
Hungary
Token Hungary
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
major
Tokenmajor
Feature activation+0.000
no
Token no
Feature activation+0.000
greater
Token greater
Feature activation+0.000
usage
Token usage
Feature activation+0.000
.
Token.
Feature activation+0.000
Energy
Token Energy
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.000
source
Token source
Feature activation+0.000
separated
Token separated
Feature activation+0.000
food
Token food
Feature activation+0.000
and
Token and
Feature activation+0.000
zone
Token zone
Feature activation+0.000
allows
Token allows
Feature activation+0.000
the
Token the
Feature activation+0.000
opposite
Token opposite
Feature activation+0.000
faction
Token faction
Feature activation+0.000
to
Token to
Feature activation+0.000
attack
Token attack
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
Do
Token Do
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
[
Token [
Feature activation+0.000
email
Tokenemail
Feature activation+0.000
protected
Token protected
Feature activation+0.000
]
Token]
Feature activation+0.000
badass
Token badass
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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